Replaced vendored xlrd/xlwt by dependencies (#277)

Refs #273.
This commit is contained in:
Claude Paroz
2017-02-20 21:29:22 +01:00
committed by Iuri de Silvio
parent e66eb4a189
commit 0ca5520bbc
95 changed files with 7 additions and 42919 deletions
+1 -163
View File
@@ -1,5 +1,5 @@
Tablib includes some vendorized python libraries: ordereddict, odfpy, pyyaml,
simplejson, unicodecsv, xlrd, xlrd3, xlwt, and xlwt3.
simplejson, unicodecsv.
Markup License
==============
@@ -295,165 +295,3 @@ ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
The views and conclusions contained in the software and documentation are those of the
authors and should not be interpreted as representing official policies, either expressed
or implied, of Jeremy Dunck.
XLWT (and XLWT3) License
========================
Portions copyright © 2007, Stephen John Machin, Lingfo Pty Ltd
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. None of the names of Stephen John Machin, Lingfo Pty Ltd and any
contributors may be used to endorse or promote products derived from this
software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS
BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
THE POSSIBILITY OF SUCH DAMAGE.
"""
"""
Copyright (C) 2005 Roman V. Kiseliov
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in
the documentation and/or other materials provided with the
distribution.
3. All advertising materials mentioning features or use of this
software must display the following acknowledgment:
"This product includes software developed by
Roman V. Kiseliov <roman@kiseliov.ru>."
4. Redistributions of any form whatsoever must retain the following
acknowledgment:
"This product includes software developed by
Roman V. Kiseliov <roman@kiseliov.ru>."
THIS SOFTWARE IS PROVIDED BY Roman V. Kiseliov ``AS IS'' AND ANY
EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL Roman V. Kiseliov OR
ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
OF THE POSSIBILITY OF SUCH DAMAGE.
Roman V. Kiseliov
Russia
Kursk
Libknecht St., 4
+7(0712)56-09-83
<roman@kiseliov.ru>
Subject: pyExcelerator
XLRD (and XLRD3) License
========================
Portions copyright © 2005-2009, Stephen John Machin, Lingfo Pty Ltd
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. None of the names of Stephen John Machin, Lingfo Pty Ltd and any
contributors may be used to endorse or promote products derived from this
software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS
BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
THE POSSIBILITY OF SUCH DAMAGE.
Copyright (c) 2001 David Giffin.
All rights reserved.
Based on the the Java version: Andrew Khan Copyright (c) 2000.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions
are met:
1. Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in
the documentation and/or other materials provided with the
distribution.
3. All advertising materials mentioning features or use of this
software must display the following acknowledgment:
"This product includes software developed by
David Giffin <david@giffin.org>."
4. Redistributions of any form whatsoever must retain the following
acknowledgment:
"This product includes software developed by
David Giffin <david@giffin.org>."
THIS SOFTWARE IS PROVIDED BY DAVID GIFFIN ``AS IS'' AND ANY
EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DAVID GIFFIN OR
ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
OF THE POSSIBILITY OF SUCH DAMAGE.
+2 -4
View File
@@ -38,13 +38,9 @@ packages = [
'tablib', 'tablib.formats',
'tablib.packages',
'tablib.packages.omnijson',
'tablib.packages.xlwt',
'tablib.packages.xlrd',
'tablib.packages.odf',
'tablib.packages.yaml',
'tablib.packages.dbfpy',
'tablib.packages.xlwt3',
'tablib.packages.xlrd3',
'tablib.packages.odf3',
'tablib.packages.yaml3',
'tablib.packages.dbfpy3'
@@ -53,6 +49,8 @@ packages = [
install = [
'openpyxl',
'unicodecsv',
'xlrd',
'xlwt',
]
with open('tablib/core.py', 'r') as fd:
-6
View File
@@ -22,9 +22,6 @@ except ImportError:
if is_py3:
from io import BytesIO
import tablib.packages.xlwt3 as xlwt
import tablib.packages.xlrd3 as xlrd
from tablib.packages.xlrd3.biffh import XLRDError
from tablib.packages import markup3 as markup
from tablib.packages.odf3 import opendocument, style, text, table
import tablib.packages.dbfpy3 as dbfpy
@@ -42,9 +39,6 @@ if is_py3:
else:
from cStringIO import StringIO as BytesIO
from cStringIO import StringIO
import tablib.packages.xlwt as xlwt
import tablib.packages.xlrd as xlrd
from tablib.packages.xlrd.biffh import XLRDError
from tablib.packages import markup
from itertools import ifilter
from tablib.packages.odf import opendocument, style, text, table
+4 -1
View File
@@ -5,8 +5,11 @@
import sys
from tablib.compat import BytesIO, xlwt, xlrd, XLRDError, xrange
from tablib.compat import BytesIO, xrange
import tablib
import xlrd
import xlwt
from xlrd.biffh import XLRDError
title = 'xls'
extensions = ('xls',)
File diff suppressed because it is too large Load Diff
-639
View File
@@ -1,639 +0,0 @@
# -*- coding: cp1252 -*-
##
# Support module for the xlrd package.
#
# <p>Portions copyright © 2005-2008 Stephen John Machin, Lingfo Pty Ltd</p>
# <p>This module is part of the xlrd package, which is released under a BSD-style licence.</p>
##
# 2008-02-10 SJM BIFF2 BLANK record
# 2008-02-08 SJM Preparation for Excel 2.0 support
# 2008-02-02 SJM Added suffixes (_B2, _B2_ONLY, etc) on record names for biff_dump & biff_count
# 2007-12-04 SJM Added support for Excel 2.x (BIFF2) files.
# 2007-09-08 SJM Avoid crash when zero-length Unicode string missing options byte.
# 2007-04-22 SJM Remove experimental "trimming" facility.
DEBUG = 0
from struct import unpack
import sys
from timemachine import *
class XLRDError(Exception):
pass
##
# Parent of almost all other classes in the package. Defines a common "dump" method
# for debugging.
class BaseObject(object):
_repr_these = []
##
# @param f open file object, to which the dump is written
# @param header text to write before the dump
# @param footer text to write after the dump
# @param indent number of leading spaces (for recursive calls)
def dump(self, f=None, header=None, footer=None, indent=0):
if f is None:
f = sys.stderr
alist = self.__dict__.items()
alist.sort()
pad = " " * indent
if header is not None: print >> f, header
list_type = type([])
dict_type = type({})
for attr, value in alist:
if getattr(value, 'dump', None) and attr != 'book':
value.dump(f,
header="%s%s (%s object):" % (pad, attr, value.__class__.__name__),
indent=indent+4)
elif attr not in self._repr_these and (
isinstance(value, list_type) or isinstance(value, dict_type)
):
print >> f, "%s%s: %s, len = %d" % (pad, attr, type(value), len(value))
else:
print >> f, "%s%s: %r" % (pad, attr, value)
if footer is not None: print >> f, footer
FUN, FDT, FNU, FGE, FTX = range(5) # unknown, date, number, general, text
DATEFORMAT = FDT
NUMBERFORMAT = FNU
(
XL_CELL_EMPTY,
XL_CELL_TEXT,
XL_CELL_NUMBER,
XL_CELL_DATE,
XL_CELL_BOOLEAN,
XL_CELL_ERROR,
XL_CELL_BLANK, # for use in debugging, gathering stats, etc
) = range(7)
biff_text_from_num = {
0: "(not BIFF)",
20: "2.0",
21: "2.1",
30: "3",
40: "4S",
45: "4W",
50: "5",
70: "7",
80: "8",
85: "8X",
}
##
# <p>This dictionary can be used to produce a text version of the internal codes
# that Excel uses for error cells. Here are its contents:
# <pre>
# 0x00: '#NULL!', # Intersection of two cell ranges is empty
# 0x07: '#DIV/0!', # Division by zero
# 0x0F: '#VALUE!', # Wrong type of operand
# 0x17: '#REF!', # Illegal or deleted cell reference
# 0x1D: '#NAME?', # Wrong function or range name
# 0x24: '#NUM!', # Value range overflow
# 0x2A: '#N/A!', # Argument or function not available
# </pre></p>
error_text_from_code = {
0x00: '#NULL!', # Intersection of two cell ranges is empty
0x07: '#DIV/0!', # Division by zero
0x0F: '#VALUE!', # Wrong type of operand
0x17: '#REF!', # Illegal or deleted cell reference
0x1D: '#NAME?', # Wrong function or range name
0x24: '#NUM!', # Value range overflow
0x2A: '#N/A!', # Argument or function not available
}
BIFF_FIRST_UNICODE = 80
XL_WORKBOOK_GLOBALS = WBKBLOBAL = 0x5
XL_WORKBOOK_GLOBALS_4W = 0x100
XL_WORKSHEET = WRKSHEET = 0x10
XL_BOUNDSHEET_WORKSHEET = 0x00
XL_BOUNDSHEET_CHART = 0x02
XL_BOUNDSHEET_VB_MODULE = 0x06
# XL_RK2 = 0x7e
XL_ARRAY = 0x0221
XL_ARRAY2 = 0x0021
XL_BLANK = 0x0201
XL_BLANK_B2 = 0x01
XL_BOF = 0x809
XL_BOOLERR = 0x205
XL_BOOLERR_B2 = 0x5
XL_BOUNDSHEET = 0x85
XL_BUILTINFMTCOUNT = 0x56
XL_CF = 0x01B1
XL_CODEPAGE = 0x42
XL_COLINFO = 0x7D
XL_COLUMNDEFAULT = 0x20 # BIFF2 only
XL_COLWIDTH = 0x24 # BIFF2 only
XL_CONDFMT = 0x01B0
XL_CONTINUE = 0x3c
XL_COUNTRY = 0x8C
XL_DATEMODE = 0x22
XL_DEFAULTROWHEIGHT = 0x0225
XL_DEFCOLWIDTH = 0x55
XL_DIMENSION = 0x200
XL_DIMENSION2 = 0x0
XL_EFONT = 0x45
XL_EOF = 0x0a
XL_EXTERNNAME = 0x23
XL_EXTERNSHEET = 0x17
XL_EXTSST = 0xff
XL_FEAT11 = 0x872
XL_FILEPASS = 0x2f
XL_FONT = 0x31
XL_FONT_B3B4 = 0x231
XL_FORMAT = 0x41e
XL_FORMAT2 = 0x1E # BIFF2, BIFF3
XL_FORMULA = 0x6
XL_FORMULA3 = 0x206
XL_FORMULA4 = 0x406
XL_GCW = 0xab
XL_INDEX = 0x20b
XL_INTEGER = 0x2 # BIFF2 only
XL_IXFE = 0x44 # BIFF2 only
XL_LABEL = 0x204
XL_LABEL_B2 = 0x04
XL_LABELRANGES = 0x15f
XL_LABELSST = 0xfd
XL_MERGEDCELLS = 0xE5
XL_MSO_DRAWING = 0x00EC
XL_MSO_DRAWING_GROUP = 0x00EB
XL_MSO_DRAWING_SELECTION = 0x00ED
XL_MULRK = 0xbd
XL_MULBLANK = 0xbe
XL_NAME = 0x18
XL_NOTE = 0x1c
XL_NUMBER = 0x203
XL_NUMBER_B2 = 0x3
XL_OBJ = 0x5D
XL_PALETTE = 0x92
XL_RK = 0x27e
XL_ROW = 0x208
XL_ROW_B2 = 0x08
XL_RSTRING = 0xd6
XL_SHEETHDR = 0x8F # BIFF4W only
XL_SHEETSOFFSET = 0x8E # BIFF4W only
XL_SHRFMLA = 0x04bc
XL_SST = 0xfc
XL_STANDARDWIDTH = 0x99
XL_STRING = 0x207
XL_STRING_B2 = 0x7
XL_STYLE = 0x293
XL_SUPBOOK = 0x1AE
XL_TABLEOP = 0x236
XL_TABLEOP2 = 0x37
XL_TABLEOP_B2 = 0x36
XL_TXO = 0x1b6
XL_UNCALCED = 0x5e
XL_UNKNOWN = 0xffff
XL_WINDOW2 = 0x023E
XL_WRITEACCESS = 0x5C
XL_XF = 0xe0
XL_XF2 = 0x0043 # BIFF2 version of XF record
XL_XF3 = 0x0243 # BIFF3 version of XF record
XL_XF4 = 0x0443 # BIFF4 version of XF record
boflen = {0x0809: 8, 0x0409: 6, 0x0209: 6, 0x0009: 4}
bofcodes = (0x0809, 0x0409, 0x0209, 0x0009)
XL_FORMULA_OPCODES = (0x0006, 0x0406, 0x0206)
_cell_opcode_list = [
XL_BOOLERR,
XL_FORMULA,
XL_FORMULA3,
XL_FORMULA4,
XL_LABEL,
XL_LABELSST,
XL_MULRK,
XL_NUMBER,
XL_RK,
XL_RSTRING,
]
_cell_opcode_dict = {}
for _cell_opcode in _cell_opcode_list:
_cell_opcode_dict[_cell_opcode] = 1
is_cell_opcode = _cell_opcode_dict.has_key
# def fprintf(f, fmt, *vargs): f.write(fmt % vargs)
def fprintf(f, fmt, *vargs):
if fmt.endswith('\n'):
print >> f, fmt[:-1] % vargs
else:
print >> f, fmt % vargs,
def upkbits(tgt_obj, src, manifest, local_setattr=setattr):
for n, mask, attr in manifest:
local_setattr(tgt_obj, attr, (src & mask) >> n)
def upkbitsL(tgt_obj, src, manifest, local_setattr=setattr, local_int=int):
for n, mask, attr in manifest:
local_setattr(tgt_obj, attr, local_int((src & mask) >> n))
def unpack_string(data, pos, encoding, lenlen=1):
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
pos += lenlen
return unicode(data[pos:pos+nchars], encoding)
def unpack_string_update_pos(data, pos, encoding, lenlen=1, known_len=None):
if known_len is not None:
# On a NAME record, the length byte is detached from the front of the string.
nchars = known_len
else:
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
pos += lenlen
newpos = pos + nchars
return (unicode(data[pos:newpos], encoding), newpos)
def unpack_unicode(data, pos, lenlen=2):
"Return unicode_strg"
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
if not nchars:
# Ambiguous whether 0-length string should have an "options" byte.
# Avoid crash if missing.
return u""
pos += lenlen
options = ord(data[pos])
pos += 1
# phonetic = options & 0x04
# richtext = options & 0x08
if options & 0x08:
# rt = unpack('<H', data[pos:pos+2])[0] # unused
pos += 2
if options & 0x04:
# sz = unpack('<i', data[pos:pos+4])[0] # unused
pos += 4
if options & 0x01:
# Uncompressed UTF-16-LE
rawstrg = data[pos:pos+2*nchars]
# if DEBUG: print "nchars=%d pos=%d rawstrg=%r" % (nchars, pos, rawstrg)
strg = unicode(rawstrg, 'utf_16_le')
# pos += 2*nchars
else:
# Note: this is COMPRESSED (not ASCII!) encoding!!!
# Merely returning the raw bytes would work OK 99.99% of the time
# if the local codepage was cp1252 -- however this would rapidly go pear-shaped
# for other codepages so we grit our Anglocentric teeth and return Unicode :-)
strg = unicode(data[pos:pos+nchars], "latin_1")
# pos += nchars
# if richtext:
# pos += 4 * rt
# if phonetic:
# pos += sz
# return (strg, pos)
return strg
def unpack_unicode_update_pos(data, pos, lenlen=2, known_len=None):
"Return (unicode_strg, updated value of pos)"
if known_len is not None:
# On a NAME record, the length byte is detached from the front of the string.
nchars = known_len
else:
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
pos += lenlen
if not nchars and not data[pos:]:
# Zero-length string with no options byte
return (u"", pos)
options = ord(data[pos])
pos += 1
phonetic = options & 0x04
richtext = options & 0x08
if richtext:
rt = unpack('<H', data[pos:pos+2])[0]
pos += 2
if phonetic:
sz = unpack('<i', data[pos:pos+4])[0]
pos += 4
if options & 0x01:
# Uncompressed UTF-16-LE
strg = unicode(data[pos:pos+2*nchars], 'utf_16_le')
pos += 2*nchars
else:
# Note: this is COMPRESSED (not ASCII!) encoding!!!
strg = unicode(data[pos:pos+nchars], "latin_1")
pos += nchars
if richtext:
pos += 4 * rt
if phonetic:
pos += sz
return (strg, pos)
def unpack_cell_range_address_list_update_pos(
output_list, data, pos, biff_version, addr_size=6):
# output_list is updated in situ
if biff_version < 80:
assert addr_size == 6
else:
assert addr_size in (6, 8)
n, = unpack("<H", data[pos:pos+2])
pos += 2
if n:
if addr_size == 6:
fmt = "<HHBB"
else:
fmt = "<HHHH"
for _unused in xrange(n):
ra, rb, ca, cb = unpack(fmt, data[pos:pos+addr_size])
output_list.append((ra, rb+1, ca, cb+1))
pos += addr_size
return pos
_brecstrg = """\
0000 DIMENSIONS_B2
0001 BLANK_B2
0002 INTEGER_B2_ONLY
0003 NUMBER_B2
0004 LABEL_B2
0005 BOOLERR_B2
0006 FORMULA
0007 STRING_B2
0008 ROW_B2
0009 BOF_B2
000A EOF
000B INDEX_B2_ONLY
000C CALCCOUNT
000D CALCMODE
000E PRECISION
000F REFMODE
0010 DELTA
0011 ITERATION
0012 PROTECT
0013 PASSWORD
0014 HEADER
0015 FOOTER
0016 EXTERNCOUNT
0017 EXTERNSHEET
0018 NAME_B2,5+
0019 WINDOWPROTECT
001A VERTICALPAGEBREAKS
001B HORIZONTALPAGEBREAKS
001C NOTE
001D SELECTION
001E FORMAT_B2-3
001F BUILTINFMTCOUNT_B2
0020 COLUMNDEFAULT_B2_ONLY
0021 ARRAY_B2_ONLY
0022 DATEMODE
0023 EXTERNNAME
0024 COLWIDTH_B2_ONLY
0025 DEFAULTROWHEIGHT_B2_ONLY
0026 LEFTMARGIN
0027 RIGHTMARGIN
0028 TOPMARGIN
0029 BOTTOMMARGIN
002A PRINTHEADERS
002B PRINTGRIDLINES
002F FILEPASS
0031 FONT
0032 FONT2_B2_ONLY
0036 TABLEOP_B2
0037 TABLEOP2_B2
003C CONTINUE
003D WINDOW1
003E WINDOW2_B2
0040 BACKUP
0041 PANE
0042 CODEPAGE
0043 XF_B2
0044 IXFE_B2_ONLY
0045 EFONT_B2_ONLY
004D PLS
0051 DCONREF
0055 DEFCOLWIDTH
0056 BUILTINFMTCOUNT_B3-4
0059 XCT
005A CRN
005B FILESHARING
005C WRITEACCESS
005D OBJECT
005E UNCALCED
005F SAVERECALC
0063 OBJECTPROTECT
007D COLINFO
007E RK2_mythical_?
0080 GUTS
0081 WSBOOL
0082 GRIDSET
0083 HCENTER
0084 VCENTER
0085 BOUNDSHEET
0086 WRITEPROT
008C COUNTRY
008D HIDEOBJ
008E SHEETSOFFSET
008F SHEETHDR
0090 SORT
0092 PALETTE
0099 STANDARDWIDTH
009B FILTERMODE
009C FNGROUPCOUNT
009D AUTOFILTERINFO
009E AUTOFILTER
00A0 SCL
00A1 SETUP
00AB GCW
00BD MULRK
00BE MULBLANK
00C1 MMS
00D6 RSTRING
00D7 DBCELL
00DA BOOKBOOL
00DD SCENPROTECT
00E0 XF
00E1 INTERFACEHDR
00E2 INTERFACEEND
00E5 MERGEDCELLS
00E9 BITMAP
00EB MSO_DRAWING_GROUP
00EC MSO_DRAWING
00ED MSO_DRAWING_SELECTION
00EF PHONETIC
00FC SST
00FD LABELSST
00FF EXTSST
013D TABID
015F LABELRANGES
0160 USESELFS
0161 DSF
01AE SUPBOOK
01AF PROTECTIONREV4
01B0 CONDFMT
01B1 CF
01B2 DVAL
01B6 TXO
01B7 REFRESHALL
01B8 HLINK
01BC PASSWORDREV4
01BE DV
01C0 XL9FILE
01C1 RECALCID
0200 DIMENSIONS
0201 BLANK
0203 NUMBER
0204 LABEL
0205 BOOLERR
0206 FORMULA_B3
0207 STRING
0208 ROW
0209 BOF
020B INDEX_B3+
0218 NAME
0221 ARRAY
0223 EXTERNNAME_B3-4
0225 DEFAULTROWHEIGHT
0231 FONT_B3B4
0236 TABLEOP
023E WINDOW2
0243 XF_B3
027E RK
0293 STYLE
0406 FORMULA_B4
0409 BOF
041E FORMAT
0443 XF_B4
04BC SHRFMLA
0800 QUICKTIP
0809 BOF
0862 SHEETLAYOUT
0867 SHEETPROTECTION
0868 RANGEPROTECTION
"""
biff_rec_name_dict = {}
for _buff in _brecstrg.splitlines():
_numh, _name = _buff.split()
biff_rec_name_dict[int(_numh, 16)] = _name
del _buff, _name, _brecstrg
def hex_char_dump(strg, ofs, dlen, base=0, fout=sys.stdout, unnumbered=False):
endpos = min(ofs + dlen, len(strg))
pos = ofs
numbered = not unnumbered
num_prefix = ''
while pos < endpos:
endsub = min(pos + 16, endpos)
substrg = strg[pos:endsub]
lensub = endsub - pos
if lensub <= 0 or lensub != len(substrg):
fprintf(
sys.stdout,
'??? hex_char_dump: ofs=%d dlen=%d base=%d -> endpos=%d pos=%d endsub=%d substrg=%r\n',
ofs, dlen, base, endpos, pos, endsub, substrg)
break
hexd = ''.join(["%02x " % ord(c) for c in substrg])
chard = ''
for c in substrg:
if c == '\0':
c = '~'
elif not (' ' <= c <= '~'):
c = '?'
chard += c
if numbered:
num_prefix = "%5d: " % (base+pos-ofs)
fprintf(fout, "%s %-48s %s\n", num_prefix, hexd, chard)
pos = endsub
def biff_dump(mem, stream_offset, stream_len, base=0, fout=sys.stdout, unnumbered=False):
pos = stream_offset
stream_end = stream_offset + stream_len
adj = base - stream_offset
dummies = 0
numbered = not unnumbered
num_prefix = ''
while stream_end - pos >= 4:
rc, length = unpack('<HH', mem[pos:pos+4])
if rc == 0 and length == 0:
if mem[pos:] == '\0' * (stream_end - pos):
dummies = stream_end - pos
savpos = pos
pos = stream_end
break
if dummies:
dummies += 4
else:
savpos = pos
dummies = 4
pos += 4
else:
if dummies:
if numbered:
num_prefix = "%5d: " % (adj + savpos)
fprintf(fout, "%s---- %d zero bytes skipped ----\n", num_prefix, dummies)
dummies = 0
recname = biff_rec_name_dict.get(rc, '<UNKNOWN>')
if numbered:
num_prefix = "%5d: " % (adj + pos)
fprintf(fout, "%s%04x %s len = %04x (%d)\n", num_prefix, rc, recname, length, length)
pos += 4
hex_char_dump(mem, pos, length, adj+pos, fout, unnumbered)
pos += length
if dummies:
if numbered:
num_prefix = "%5d: " % (adj + savpos)
fprintf(fout, "%s---- %d zero bytes skipped ----\n", num_prefix, dummies)
if pos < stream_end:
if numbered:
num_prefix = "%5d: " % (adj + pos)
fprintf(fout, "%s---- Misc bytes at end ----\n", num_prefix)
hex_char_dump(mem, pos, stream_end-pos, adj + pos, fout, unnumbered)
elif pos > stream_end:
fprintf(fout, "Last dumped record has length (%d) that is too large\n", length)
def biff_count_records(mem, stream_offset, stream_len, fout=sys.stdout):
pos = stream_offset
stream_end = stream_offset + stream_len
tally = {}
while stream_end - pos >= 4:
rc, length = unpack('<HH', mem[pos:pos+4])
if rc == 0 and length == 0:
if mem[pos:] == '\0' * (stream_end - pos):
break
recname = "<Dummy (zero)>"
else:
recname = biff_rec_name_dict.get(rc, None)
if recname is None:
recname = "Unknown_0x%04X" % rc
if tally.has_key(recname):
tally[recname] += 1
else:
tally[recname] = 1
pos += length + 4
slist = tally.items()
slist.sort()
for recname, count in slist:
print >> fout, "%8d %s" % (count, recname)
encoding_from_codepage = {
1200 : 'utf_16_le',
10000: 'mac_roman',
10006: 'mac_greek', # guess
10007: 'mac_cyrillic', # guess
10029: 'mac_latin2', # guess
10079: 'mac_iceland', # guess
10081: 'mac_turkish', # guess
32768: 'mac_roman',
32769: 'cp1252',
}
# some more guessing, for Indic scripts
# codepage 57000 range:
# 2 Devanagari [0]
# 3 Bengali [1]
# 4 Tamil [5]
# 5 Telegu [6]
# 6 Assamese [1] c.f. Bengali
# 7 Oriya [4]
# 8 Kannada [7]
# 9 Malayalam [8]
# 10 Gujarati [3]
# 11 Gurmukhi [2]
-358
View File
@@ -1,358 +0,0 @@
# -*- coding: cp1252 -*-
##
# Implements the minimal functionality required
# to extract a "Workbook" or "Book" stream (as one big string)
# from an OLE2 Compound Document file.
# <p>Copyright © 2005-2008 Stephen John Machin, Lingfo Pty Ltd</p>
# <p>This module is part of the xlrd package, which is released under a BSD-style licence.</p>
##
# No part of the content of this file was derived from the works of David Giffin.
# 2008-11-04 SJM Avoid assertion error when -1 used instead of -2 for first_SID of empty SCSS [Frank Hoffsuemmer]
# 2007-09-08 SJM Warning message if sector sizes are extremely large.
# 2007-05-07 SJM Meaningful exception instead of IndexError if a SAT (sector allocation table) is corrupted.
# 2007-04-22 SJM Missing "<" in a struct.unpack call => can't open files on bigendian platforms.
import sys
from struct import unpack
from timemachine import *
##
# Magic cookie that should appear in the first 8 bytes of the file.
SIGNATURE = "\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1"
EOCSID = -2
FREESID = -1
SATSID = -3
MSATSID = -4
class CompDocError(Exception):
pass
class DirNode(object):
def __init__(self, DID, dent, DEBUG=0):
# dent is the 128-byte directory entry
self.DID = DID
# (cbufsize, self.etype, self.colour, self.left_DID, self.right_DID,
# self.root_DID,
# self.first_SID,
# self.tot_size) = \
# unpack('<HBBiii16x4x8x8xii4x', dent[64:128])
(cbufsize, self.etype, self.colour, self.left_DID, self.right_DID,
self.root_DID) = \
unpack('<HBBiii', dent[64:80])
(self.first_SID, self.tot_size) = \
unpack('<ii', dent[116:124])
if cbufsize == 0:
self.name = u''
else:
self.name = unicode(dent[0:cbufsize-2], 'utf_16_le') # omit the trailing U+0000
self.children = [] # filled in later
self.parent = -1 # indicates orphan; fixed up later
self.tsinfo = unpack('<IIII', dent[100:116])
if DEBUG:
self.dump(DEBUG)
def dump(self, DEBUG=1):
print "DID=%d name=%r etype=%d DIDs(left=%d right=%d root=%d parent=%d kids=%r) first_SID=%d tot_size=%d" \
% (self.DID, self.name, self.etype, self.left_DID,
self.right_DID, self.root_DID, self.parent, self.children, self.first_SID, self.tot_size)
if DEBUG == 2:
# cre_lo, cre_hi, mod_lo, mod_hi = tsinfo
print "timestamp info", self.tsinfo
def _build_family_tree(dirlist, parent_DID, child_DID):
if child_DID < 0: return
_build_family_tree(dirlist, parent_DID, dirlist[child_DID].left_DID)
dirlist[parent_DID].children.append(child_DID)
dirlist[child_DID].parent = parent_DID
_build_family_tree(dirlist, parent_DID, dirlist[child_DID].right_DID)
if dirlist[child_DID].etype == 1: # storage
_build_family_tree(dirlist, child_DID, dirlist[child_DID].root_DID)
##
# Compound document handler.
# @param mem The raw contents of the file, as a string, or as an mmap.mmap() object. The
# only operation it needs to support is slicing.
class CompDoc(object):
def __init__(self, mem, logfile=sys.stdout, DEBUG=0):
self.logfile = logfile
if mem[0:8] != SIGNATURE:
raise CompDocError('Not an OLE2 compound document')
if mem[28:30] != '\xFE\xFF':
raise CompDocError('Expected "little-endian" marker, found %r' % mem[28:30])
revision, version = unpack('<HH', mem[24:28])
if DEBUG:
print >> logfile, "\nCompDoc format: version=0x%04x revision=0x%04x" % (version, revision)
self.mem = mem
ssz, sssz = unpack('<HH', mem[30:34])
if ssz > 20: # allows for 2**20 bytes i.e. 1MB
print >> logfile, \
"WARNING: sector size (2**%d) is preposterous; assuming 512 and continuing ..." \
% ssz
ssz = 9
if sssz > ssz:
print >> logfile, \
"WARNING: short stream sector size (2**%d) is preposterous; assuming 64 and continuing ..." \
% sssz
sssz = 6
self.sec_size = sec_size = 1 << ssz
self.short_sec_size = 1 << sssz
(
SAT_tot_secs, self.dir_first_sec_sid, _unused, self.min_size_std_stream,
SSAT_first_sec_sid, SSAT_tot_secs,
MSAT_first_sec_sid, MSAT_tot_secs,
# ) = unpack('<ii4xiiiii', mem[44:76])
) = unpack('<iiiiiiii', mem[44:76])
mem_data_len = len(mem) - 512
mem_data_secs, left_over = divmod(mem_data_len, sec_size)
if left_over:
#### raise CompDocError("Not a whole number of sectors")
print >> logfile, \
"WARNING *** file size (%d) not 512 + multiple of sector size (%d)" \
% (len(mem), sec_size)
if DEBUG:
print >> logfile, 'sec sizes', ssz, sssz, sec_size, self.short_sec_size
print >> logfile, "mem data: %d bytes == %d sectors" % (mem_data_len, mem_data_secs)
print >> logfile, "SAT_tot_secs=%d, dir_first_sec_sid=%d, min_size_std_stream=%d" \
% (SAT_tot_secs, self.dir_first_sec_sid, self.min_size_std_stream,)
print >> logfile, "SSAT_first_sec_sid=%d, SSAT_tot_secs=%d" % (SSAT_first_sec_sid, SSAT_tot_secs,)
print >> logfile, "MSAT_first_sec_sid=%d, MSAT_tot_secs=%d" % (MSAT_first_sec_sid, MSAT_tot_secs,)
nent = int_floor_div(sec_size, 4) # number of SID entries in a sector
fmt = "<%di" % nent
trunc_warned = 0
#
# === build the MSAT ===
#
MSAT = list(unpack('<109i', mem[76:512]))
sid = MSAT_first_sec_sid
while sid >= 0:
if sid >= mem_data_secs:
raise CompDocError(
"MSAT extension: accessing sector %d but only %d in file" % (sid, mem_data_secs)
)
offset = 512 + sec_size * sid
news = list(unpack(fmt, mem[offset:offset+sec_size]))
sid = news.pop()
MSAT.extend(news)
if DEBUG:
print >> logfile, "MSAT: len =", len(MSAT)
print >> logfile, MSAT
#
# === build the SAT ===
#
self.SAT = []
for msid in MSAT:
if msid == FREESID: continue
if msid >= mem_data_secs:
if not trunc_warned:
print >> logfile, "WARNING *** File is truncated, or OLE2 MSAT is corrupt!!"
print >> logfile, \
"INFO: Trying to access sector %d but only %d available" \
% (msid, mem_data_secs)
trunc_warned = 1
continue
offset = 512 + sec_size * msid
news = list(unpack(fmt, mem[offset:offset+sec_size]))
self.SAT.extend(news)
if DEBUG:
print >> logfile, "SAT: len =", len(self.SAT)
print >> logfile, self.SAT
# print >> logfile, "SAT ",
# for i, s in enumerate(self.SAT):
# print >> logfile, "entry: %4d offset: %6d, next entry: %4d" % (i, 512 + sec_size * i, s)
# print >> logfile, "%d:%d " % (i, s),
print
# === build the directory ===
#
dbytes = self._get_stream(
self.mem, 512, self.SAT, self.sec_size, self.dir_first_sec_sid,
name="directory")
dirlist = []
did = -1
for pos in xrange(0, len(dbytes), 128):
did += 1
dirlist.append(DirNode(did, dbytes[pos:pos+128], 0))
self.dirlist = dirlist
_build_family_tree(dirlist, 0, dirlist[0].root_DID) # and stand well back ...
if DEBUG:
for d in dirlist:
d.dump(DEBUG)
#
# === get the SSCS ===
#
sscs_dir = self.dirlist[0]
assert sscs_dir.etype == 5 # root entry
if sscs_dir.first_SID < 0 and sscs_dir.tot_size == 0:
# Problem reported by Frank Hoffsuemmer: some software was
# writing -1 instead of -2 (EOCSID) for the first_SID
# when the SCCS was empty. Not having EOCSID caused assertion
# failure in _get_stream.
# Solution: avoid calling _get_stream in any case when the
# SCSS appears to be empty.
self.SSCS = ""
else:
self.SSCS = self._get_stream(
self.mem, 512, self.SAT, sec_size, sscs_dir.first_SID,
sscs_dir.tot_size, name="SSCS")
# if DEBUG: print >> logfile, "SSCS", repr(self.SSCS)
#
# === build the SSAT ===
#
self.SSAT = []
if SSAT_tot_secs > 0 and sscs_dir.tot_size == 0:
print >> logfile, \
"WARNING *** OLE2 inconsistency: SSCS size is 0 but SSAT size is non-zero"
if sscs_dir.tot_size > 0:
sid = SSAT_first_sec_sid
nsecs = SSAT_tot_secs
while sid >= 0 and nsecs > 0:
nsecs -= 1
start_pos = 512 + sid * sec_size
news = list(unpack(fmt, mem[start_pos:start_pos+sec_size]))
self.SSAT.extend(news)
sid = self.SAT[sid]
# assert SSAT_tot_secs == 0 or sid == EOCSID
if DEBUG: print >> logfile, "SSAT last sid %d; remaining sectors %d" % (sid, nsecs)
assert nsecs == 0 and sid == EOCSID
if DEBUG: print >> logfile, "SSAT", self.SSAT
def _get_stream(self, mem, base, sat, sec_size, start_sid, size=None, name=''):
# print >> self.logfile, "_get_stream", base, sec_size, start_sid, size
sectors = []
s = start_sid
if size is None:
# nothing to check against
while s >= 0:
start_pos = base + s * sec_size
sectors.append(mem[start_pos:start_pos+sec_size])
try:
s = sat[s]
except IndexError:
raise CompDocError(
"OLE2 stream %r: sector allocation table invalid entry (%d)" %
(name, s)
)
assert s == EOCSID
else:
todo = size
while s >= 0:
start_pos = base + s * sec_size
grab = sec_size
if grab > todo:
grab = todo
todo -= grab
sectors.append(mem[start_pos:start_pos+grab])
try:
s = sat[s]
except IndexError:
raise CompDocError(
"OLE2 stream %r: sector allocation table invalid entry (%d)" %
(name, s)
)
assert s == EOCSID
if todo != 0:
print >> self.logfile, \
"WARNING *** OLE2 stream %r: expected size %d, actual size %d" \
% (name, size, size - todo)
return ''.join(sectors)
def _dir_search(self, path, storage_DID=0):
# Return matching DirNode instance, or None
head = path[0]
tail = path[1:]
dl = self.dirlist
for child in dl[storage_DID].children:
if dl[child].name.lower() == head.lower():
et = dl[child].etype
if et == 2:
return dl[child]
if et == 1:
if not tail:
raise CompDocError("Requested component is a 'storage'")
return self._dir_search(tail, child)
dl[child].dump(1)
raise CompDocError("Requested stream is not a 'user stream'")
return None
##
# Interrogate the compound document's directory; return the stream as a string if found, otherwise
# return None.
# @param qname Name of the desired stream e.g. u'Workbook'. Should be in Unicode or convertible thereto.
def get_named_stream(self, qname):
d = self._dir_search(qname.split("/"))
if d is None:
return None
if d.tot_size >= self.min_size_std_stream:
return self._get_stream(
self.mem, 512, self.SAT, self.sec_size, d.first_SID,
d.tot_size, name=qname)
else:
return self._get_stream(
self.SSCS, 0, self.SSAT, self.short_sec_size, d.first_SID,
d.tot_size, name=qname + " (from SSCS)")
##
# Interrogate the compound document's directory.
# If the named stream is not found, (None, 0, 0) will be returned.
# If the named stream is found and is contiguous within the original byte sequence ("mem")
# used when the document was opened,
# then (mem, offset_to_start_of_stream, length_of_stream) is returned.
# Otherwise a new string is built from the fragments and (new_string, 0, length_of_stream) is returned.
# @param qname Name of the desired stream e.g. u'Workbook'. Should be in Unicode or convertible thereto.
def locate_named_stream(self, qname):
d = self._dir_search(qname.split("/"))
if d is None:
return (None, 0, 0)
if d.tot_size >= self.min_size_std_stream:
return self._locate_stream(self.mem, 512, self.SAT, self.sec_size, d.first_SID, d.tot_size)
else:
return (
self._get_stream(
self.SSCS, 0, self.SSAT, self.short_sec_size, d.first_SID,
d.tot_size, qname + " (from SSCS)"),
0,
d.tot_size
)
return (None, 0, 0) # not found
def _locate_stream(self, mem, base, sat, sec_size, start_sid, size):
# print >> self.logfile, "_locate_stream", base, sec_size, start_sid, size
s = start_sid
if s < 0:
raise CompDocError("_locate_stream: start_sid (%d) is -ve" % start_sid)
p = -99 # dummy previous SID
start_pos = -9999
end_pos = -8888
slices = []
while s >= 0:
if s == p+1:
# contiguous sectors
end_pos += sec_size
else:
# start new slice
if p >= 0:
# not first time
slices.append((start_pos, end_pos))
start_pos = base + s * sec_size
end_pos = start_pos + sec_size
p = s
s = sat[s]
assert s == EOCSID
# print >> self.logfile, len(slices) + 1, "slices"
if not slices:
# The stream is contiguous ... just what we like!
return (mem, start_pos, size)
slices.append((start_pos, end_pos))
return (''.join([mem[start_pos:end_pos] for start_pos, end_pos in slices]), 0, size)
# ==========================================================================================
-69
View File
@@ -1,69 +0,0 @@
<!DOCTYPE html PUBLIC '-//W3C//DTD XHTML 1.0 Strict//EN' 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd'>
<html>
<head>
<meta http-equiv='Content-Type' content='text/html; charset=us-ascii' />
<title>The compdoc Module</title>
</head>
<body>
<h1>The compdoc Module</h1>
<p>Implements the minimal functionality required
to extract a "Workbook" or "Book" stream (as one big string)
from an OLE2 Compound Document file.
</p><p>Copyright &#169; 2005-2008 Stephen John Machin, Lingfo Pty Ltd</p>
<p>This module is part of the xlrd package, which is released under a BSD-style licence.</p>
<h2>Module Contents</h2>
<dl>
<dt><b>CompDoc(mem, logfile=sys.stdout, DEBUG=0)</b> (class) [<a href='#compdoc.CompDoc-class'>#</a>]</dt>
<dd>
<p>Compound document handler.</p>
<dl>
<dt><i>mem</i></dt>
<dd>
The raw contents of the file, as a string, or as an mmap.mmap() object. The
only operation it needs to support is slicing.</dd>
</dl><br />
<p>For more information about this class, see <a href='#compdoc.CompDoc-class'><i>The CompDoc Class</i></a>.</p>
</dd>
<dt><a id='compdoc.SIGNATURE-variable' name='compdoc.SIGNATURE-variable'><b>SIGNATURE</b></a> (variable) [<a href='#compdoc.SIGNATURE-variable'>#</a>]</dt>
<dd>
<p>Magic cookie that should appear in the first 8 bytes of the file.</p>
</dd>
</dl>
<h2><a id='compdoc.CompDoc-class' name='compdoc.CompDoc-class'>The CompDoc Class</a></h2>
<dl>
<dt><b>CompDoc(mem, logfile=sys.stdout, DEBUG=0)</b> (class) [<a href='#compdoc.CompDoc-class'>#</a>]</dt>
<dd>
<p>Compound document handler.</p>
<dl>
<dt><i>mem</i></dt>
<dd>
The raw contents of the file, as a string, or as an mmap.mmap() object. The
only operation it needs to support is slicing.</dd>
</dl><br />
</dd>
<dt><a id='compdoc.CompDoc.get_named_stream-method' name='compdoc.CompDoc.get_named_stream-method'><b>get_named_stream(qname)</b></a> [<a href='#compdoc.CompDoc.get_named_stream-method'>#</a>]</dt>
<dd>
<p>Interrogate the compound document's directory; return the stream as a string if found, otherwise
return None.</p>
<dl>
<dt><i>qname</i></dt>
<dd>
Name of the desired stream e.g. u'Workbook'. Should be in Unicode or convertible thereto.</dd>
</dl><br />
</dd>
<dt><a id='compdoc.CompDoc.locate_named_stream-method' name='compdoc.CompDoc.locate_named_stream-method'><b>locate_named_stream(qname)</b></a> [<a href='#compdoc.CompDoc.locate_named_stream-method'>#</a>]</dt>
<dd>
<p>Interrogate the compound document's directory.
If the named stream is not found, (None, 0, 0) will be returned.
If the named stream is found and is contiguous within the original byte sequence (&quot;mem&quot;)
used when the document was opened,
then (mem, offset_to_start_of_stream, length_of_stream) is returned.
Otherwise a new string is built from the fragments and (new_string, 0, length_of_stream) is returned.</p>
<dl>
<dt><i>qname</i></dt>
<dd>
Name of the desired stream e.g. u'Workbook'. Should be in Unicode or convertible thereto.</dd>
</dl><br />
</dd>
</dl>
</body></html>
File diff suppressed because it is too large Load Diff
Binary file not shown.
@@ -1,178 +0,0 @@
# -*- coding: cp1252 -*-
##
# Module/script example of the xlrd API for extracting information
# about named references, named constants, etc.
#
# <p>Copyright © 2006 Stephen John Machin, Lingfo Pty Ltd</p>
# <p>This module is part of the xlrd package, which is released under a BSD-style licence.</p>
##
import xlrd
import sys
import glob
def scope_as_string(book, scope):
if 0 <= scope < book.nsheets:
return "sheet #%d (%r)" % (scope, book.sheet_names()[scope])
if scope == -1:
return "Global"
if scope == -2:
return "Macro/VBA"
return "Unknown scope value (%r)" % scope
def do_scope_query(book, scope_strg, show_contents=0, f=sys.stdout):
try:
qscope = int(scope_strg)
except ValueError:
if scope_strg == "*":
qscope = None # means "all'
else:
# so assume it's a sheet name ...
qscope = book.sheet_names().index(scope_strg)
print >> f, "%r => %d" % (scope_strg, qscope)
for nobj in book.name_obj_list:
if qscope is None or nobj.scope == qscope:
show_name_object(book, nobj, show_contents, f)
def show_name_details(book, name, show_contents=0, f=sys.stdout):
"""
book -- Book object obtained from xlrd.open_workbook().
name -- The name that's being investigated.
show_contents -- 0: Don't; 1: Non-empty cells only; 2: All cells
f -- Open output file handle.
"""
name_lcase = name.lower() # Excel names are case-insensitive.
nobj_list = book.name_map.get(name_lcase)
if not nobj_list:
print >> f, "%r: unknown name" % name
return
for nobj in nobj_list:
show_name_object(book, nobj, show_contents, f)
def show_name_details_in_scope(
book, name, scope_strg, show_contents=0, f=sys.stdout,
):
try:
scope = int(scope_strg)
except ValueError:
# so assume it's a sheet name ...
scope = book.sheet_names().index(scope_strg)
print >> f, "%r => %d" % (scope_strg, scope)
name_lcase = name.lower() # Excel names are case-insensitive.
while 1:
nobj = book.name_and_scope_map.get((name_lcase, scope))
if nobj:
break
print >> f, "Name %r not found in scope %d" % (name, scope)
if scope == -1:
return
scope = -1 # Try again with global scope
print >> f, "Name %r found in scope %d" % (name, scope)
show_name_object(book, nobj, show_contents, f)
def showable_cell_value(celltype, cellvalue, datemode):
if celltype == xlrd.XL_CELL_DATE:
try:
showval = xlrd.xldate_as_tuple(cellvalue, datemode)
except xlrd.XLDateError:
e1, e2 = sys.exc_info()[:2]
showval = "%s:%s" % (e1.__name__, e2)
elif celltype == xlrd.XL_CELL_ERROR:
showval = xlrd.error_text_from_code.get(
cellvalue, '<Unknown error code 0x%02x>' % cellvalue)
else:
showval = cellvalue
return showval
def show_name_object(book, nobj, show_contents=0, f=sys.stdout):
print >> f, "\nName: %r, scope: %r (%s)" \
% (nobj.name, nobj.scope, scope_as_string(book, nobj.scope))
res = nobj.result
print >> f, "Formula eval result: %r" % res
if res is None:
return
# result should be an instance of the Operand class
kind = res.kind
value = res.value
if kind >= 0:
# A scalar, or unknown ... you've seen all there is to see.
pass
elif kind == xlrd.oREL:
# A list of Ref3D objects representing *relative* ranges
for i in xrange(len(value)):
ref3d = value[i]
print >> f, "Range %d: %r ==> %s"% (i, ref3d.coords, xlrd.rangename3drel(book, ref3d))
elif kind == xlrd.oREF:
# A list of Ref3D objects
for i in xrange(len(value)):
ref3d = value[i]
print >> f, "Range %d: %r ==> %s"% (i, ref3d.coords, xlrd.rangename3d(book, ref3d))
if not show_contents:
continue
datemode = book.datemode
for shx in xrange(ref3d.shtxlo, ref3d.shtxhi):
sh = book.sheet_by_index(shx)
print >> f, " Sheet #%d (%s)" % (shx, sh.name)
rowlim = min(ref3d.rowxhi, sh.nrows)
collim = min(ref3d.colxhi, sh.ncols)
for rowx in xrange(ref3d.rowxlo, rowlim):
for colx in xrange(ref3d.colxlo, collim):
cty = sh.cell_type(rowx, colx)
if cty == xlrd.XL_CELL_EMPTY and show_contents == 1:
continue
cval = sh.cell_value(rowx, colx)
sval = showable_cell_value(cty, cval, datemode)
print >> f, " (%3d,%3d) %-5s: %r" \
% (rowx, colx, xlrd.cellname(rowx, colx), sval)
if __name__ == "__main__":
def usage():
text = """
usage: xlrdnameAIPdemo.py glob_pattern name scope show_contents
where:
"glob_pattern" designates a set of files
"name" is a name or '*' (all names)
"scope" is -1 (global) or a sheet number
or a sheet name or * (all scopes)
"show_contents" is one of 0 (no show),
1 (only non-empty cells), or 2 (all cells)
Examples (script name and glob_pattern arg omitted for brevity)
[Searching through book.name_obj_list]
* * 0 lists all names
* * 1 lists all names, showing referenced non-empty cells
* 1 0 lists all names local to the 2nd sheet
* Northern 0 lists all names local to the 'Northern' sheet
* -1 0 lists all names with global scope
[Initial direct access through book.name_map]
Sales * 0 lists all occurrences of "Sales" in any scope
[Direct access through book.name_and_scope_map]
Revenue -1 0 checks if "Revenue" exists in global scope
"""
sys.stdout.write(text)
if len(sys.argv) != 5:
usage()
sys.exit(0)
arg_pattern = sys.argv[1] # glob pattern e.g. "foo*.xls"
arg_name = sys.argv[2] # see below
arg_scope = sys.argv[3] # see below
arg_show_contents = int(sys.argv[4]) # 0: no show, 1: only non-empty cells,
# 2: all cells
for fname in glob.glob(arg_pattern):
book = xlrd.open_workbook(fname)
if arg_name == "*":
# Examine book.name_obj_list to find all names
# in a given scope ("*" => all scopes)
do_scope_query(book, arg_scope, arg_show_contents)
elif arg_scope == "*":
# Using book.name_map to find all usage of a name.
show_name_details(book, arg_name, arg_show_contents)
else:
# Using book.name_and_scope_map to find which if any instances
# of a name are visible in the given scope, which can be supplied
# as -1 (global) or a sheet number or a sheet name.
show_name_details_in_scope(book, arg_name, arg_scope, arg_show_contents)
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
-77
View File
@@ -1,77 +0,0 @@
# -*- coding: cp1252 -*-
"""
Portions copyright © 2005-2009, Stephen John Machin, Lingfo Pty Ltd
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. None of the names of Stephen John Machin, Lingfo Pty Ltd and any
contributors may be used to endorse or promote products derived from this
software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS
BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
THE POSSIBILITY OF SUCH DAMAGE.
"""
"""
/*-
* Copyright (c) 2001 David Giffin.
* All rights reserved.
*
* Based on the the Java version: Andrew Khan Copyright (c) 2000.
*
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. All advertising materials mentioning features or use of this
* software must display the following acknowledgment:
* "This product includes software developed by
* David Giffin <david@giffin.org>."
*
* 4. Redistributions of any form whatsoever must retain the following
* acknowledgment:
* "This product includes software developed by
* David Giffin <david@giffin.org>."
*
* THIS SOFTWARE IS PROVIDED BY DAVID GIFFIN ``AS IS'' AND ANY
* EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL DAVID GIFFIN OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
* NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
* OF THE POSSIBILITY OF SUCH DAMAGE.
*/
"""
File diff suppressed because it is too large Load Diff
-44
View File
@@ -1,44 +0,0 @@
# -*- coding: cp1252 -*-
##
# <p>Copyright © 2006-2008 Stephen John Machin, Lingfo Pty Ltd</p>
# <p>This module is part of the xlrd package, which is released under a BSD-style licence.</p>
##
# timemachine.py -- adaptation for earlier Pythons e.g. 2.1
# usage: from timemachine import *
# 2008-02-08 SJM Generalised method of detecting IronPython
import sys
python_version = sys.version_info[:2] # e.g. version 2.4 -> (2, 4)
CAN_PICKLE_ARRAY = python_version >= (2, 5)
CAN_SUBCLASS_BUILTIN = python_version >= (2, 2)
if sys.version.find("IronPython") >= 0:
array_array = None
else:
from array import array as array_array
if python_version < (2, 2):
class object:
pass
False = 0
True = 1
def int_floor_div(x, y):
return divmod(x, y)[0]
def intbool(x):
if x:
return 1
return 0
if python_version < (2, 3):
def sum(sequence, start=0):
tot = start
for item in aseq:
tot += item
return tot
-171
View File
@@ -1,171 +0,0 @@
# -*- coding: cp1252 -*-
# No part of the content of this file was derived from the works of David Giffin.
##
# <p>Copyright © 2005-2008 Stephen John Machin, Lingfo Pty Ltd</p>
# <p>This module is part of the xlrd package, which is released under a BSD-style licence.</p>
#
# <p>Provides function(s) for dealing with Microsoft Excel ™ dates.</p>
##
# 2008-10-18 SJM Fix bug in xldate_from_date_tuple (affected some years after 2099)
# The conversion from days to (year, month, day) starts with
# an integral "julian day number" aka JDN.
# FWIW, JDN 0 corresponds to noon on Monday November 24 in Gregorian year -4713.
# More importantly:
# Noon on Gregorian 1900-03-01 (day 61 in the 1900-based system) is JDN 2415080.0
# Noon on Gregorian 1904-01-02 (day 1 in the 1904-based system) is JDN 2416482.0
from timemachine import int_floor_div as ifd
_JDN_delta = (2415080 - 61, 2416482 - 1)
assert _JDN_delta[1] - _JDN_delta[0] == 1462
class XLDateError(ValueError): pass
class XLDateNegative(XLDateError): pass
class XLDateAmbiguous(XLDateError): pass
class XLDateTooLarge(XLDateError): pass
class XLDateBadDatemode(XLDateError): pass
class XLDateBadTuple(XLDateError): pass
_XLDAYS_TOO_LARGE = (2958466, 2958466 - 1462) # This is equivalent to 10000-01-01
##
# Convert an Excel number (presumed to represent a date, a datetime or a time) into
# a tuple suitable for feeding to datetime or mx.DateTime constructors.
# @param xldate The Excel number
# @param datemode 0: 1900-based, 1: 1904-based.
# <br>WARNING: when using this function to
# interpret the contents of a workbook, you should pass in the Book.datemode
# attribute of that workbook. Whether
# the workbook has ever been anywhere near a Macintosh is irrelevant.
# @return Gregorian (year, month, day, hour, minute, nearest_second).
# <br>Special case: if 0.0 <= xldate < 1.0, it is assumed to represent a time;
# (0, 0, 0, hour, minute, second) will be returned.
# <br>Note: 1904-01-01 is not regarded as a valid date in the datemode 1 system; its "serial number"
# is zero.
# @throws XLDateNegative xldate < 0.00
# @throws XLDateAmbiguous The 1900 leap-year problem (datemode == 0 and 1.0 <= xldate < 61.0)
# @throws XLDateTooLarge Gregorian year 10000 or later
# @throws XLDateBadDatemode datemode arg is neither 0 nor 1
# @throws XLDateError Covers the 4 specific errors
def xldate_as_tuple(xldate, datemode):
if datemode not in (0, 1):
raise XLDateBadDatemode(datemode)
if xldate == 0.00:
return (0, 0, 0, 0, 0, 0)
if xldate < 0.00:
raise XLDateNegative(xldate)
xldays = int(xldate)
frac = xldate - xldays
seconds = int(round(frac * 86400.0))
assert 0 <= seconds <= 86400
if seconds == 86400:
hour = minute = second = 0
xldays += 1
else:
# second = seconds % 60; minutes = seconds // 60
minutes, second = divmod(seconds, 60)
# minute = minutes % 60; hour = minutes // 60
hour, minute = divmod(minutes, 60)
if xldays >= _XLDAYS_TOO_LARGE[datemode]:
raise XLDateTooLarge(xldate)
if xldays == 0:
return (0, 0, 0, hour, minute, second)
if xldays < 61 and datemode == 0:
raise XLDateAmbiguous(xldate)
jdn = xldays + _JDN_delta[datemode]
yreg = (ifd(ifd(jdn * 4 + 274277, 146097) * 3, 4) + jdn + 1363) * 4 + 3
mp = ifd(yreg % 1461, 4) * 535 + 333
d = ifd(mp % 16384, 535) + 1
# mp /= 16384
mp >>= 14
if mp >= 10:
return (ifd(yreg, 1461) - 4715, mp - 9, d, hour, minute, second)
else:
return (ifd(yreg, 1461) - 4716, mp + 3, d, hour, minute, second)
# === conversions from date/time to xl numbers
def _leap(y):
if y % 4: return 0
if y % 100: return 1
if y % 400: return 0
return 1
_days_in_month = (None, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31)
##
# Convert a date tuple (year, month, day) to an Excel date.
# @param year Gregorian year.
# @param month 1 <= month <= 12
# @param day 1 <= day <= last day of that (year, month)
# @param datemode 0: 1900-based, 1: 1904-based.
# @throws XLDateAmbiguous The 1900 leap-year problem (datemode == 0 and 1.0 <= xldate < 61.0)
# @throws XLDateBadDatemode datemode arg is neither 0 nor 1
# @throws XLDateBadTuple (year, month, day) is too early/late or has invalid component(s)
# @throws XLDateError Covers the specific errors
def xldate_from_date_tuple((year, month, day), datemode):
if datemode not in (0, 1):
raise XLDateBadDatemode(datemode)
if year == 0 and month == 0 and day == 0:
return 0.00
if not (1900 <= year <= 9999):
raise XLDateBadTuple("Invalid year: %r" % ((year, month, day),))
if not (1 <= month <= 12):
raise XLDateBadTuple("Invalid month: %r" % ((year, month, day),))
if day < 1 \
or (day > _days_in_month[month] and not(day == 29 and month == 2 and _leap(year))):
raise XLDateBadTuple("Invalid day: %r" % ((year, month, day),))
Yp = year + 4716
M = month
if M <= 2:
Yp = Yp - 1
Mp = M + 9
else:
Mp = M - 3
jdn = ifd(1461 * Yp, 4) + ifd(979 * Mp + 16, 32) + \
day - 1364 - ifd(ifd(Yp + 184, 100) * 3, 4)
xldays = jdn - _JDN_delta[datemode]
if xldays <= 0:
raise XLDateBadTuple("Invalid (year, month, day): %r" % ((year, month, day),))
if xldays < 61 and datemode == 0:
raise XLDateAmbiguous("Before 1900-03-01: %r" % ((year, month, day),))
return float(xldays)
##
# Convert a time tuple (hour, minute, second) to an Excel "date" value (fraction of a day).
# @param hour 0 <= hour < 24
# @param minute 0 <= minute < 60
# @param second 0 <= second < 60
# @throws XLDateBadTuple Out-of-range hour, minute, or second
def xldate_from_time_tuple((hour, minute, second)):
if 0 <= hour < 24 and 0 <= minute < 60 and 0 <= second < 60:
return ((second / 60.0 + minute) / 60.0 + hour) / 24.0
raise XLDateBadTuple("Invalid (hour, minute, second): %r" % ((hour, minute, second),))
##
# Convert a datetime tuple (year, month, day, hour, minute, second) to an Excel date value.
# For more details, refer to other xldate_from_*_tuple functions.
# @param datetime_tuple (year, month, day, hour, minute, second)
# @param datemode 0: 1900-based, 1: 1904-based.
def xldate_from_datetime_tuple(datetime_tuple, datemode):
return (
xldate_from_date_tuple(datetime_tuple[:3], datemode)
+
xldate_from_time_tuple(datetime_tuple[3:])
)
File diff suppressed because it is too large Load Diff
-620
View File
@@ -1,620 +0,0 @@
# Support module for the xlrd3 package.
#
# Portions copyright (c) 2005-2008 Stephen John Machin, Lingfo Pty Ltd
# This module is part of the xlrd package, which is released under a
# BSD-style licence.
#
# 2010-12-08 mozman refactoring for python 3
# 2008-02-10 SJM BIFF2 BLANK record
# 2008-02-08 SJM Preparation for Excel 2.0 support
# 2008-02-02 SJM Added suffixes (_B2, _B2_ONLY, etc) on record names for
# biff_dump & biff_count
# 2007-12-04 SJM Added support for Excel 2.x (BIFF2) files.
# 2007-09-08 SJM Avoid crash when zero-length Unicode string missing options byte.
# 2007-04-22 SJM Remove experimental "trimming" facility.
import sys
from struct import unpack
encoding_from_codepage = {
1200 : 'utf_16_le',
10000: 'mac_roman',
10006: 'mac_greek', # guess
10007: 'mac_cyrillic', # guess
10029: 'mac_latin2', # guess
10079: 'mac_iceland', # guess
10081: 'mac_turkish', # guess
32768: 'mac_roman',
32769: 'cp1252',
}
# some more guessing, for Indic scripts
# codepage 57000 range:
# 2 Devanagari [0]
# 3 Bengali [1]
# 4 Tamil [5]
# 5 Telegu [6]
# 6 Assamese [1] c.f. Bengali
# 7 Oriya [4]
# 8 Kannada [7]
# 9 Malayalam [8]
# 10 Gujarati [3]
# 11 Gurmukhi [2]
FUN = 0 # unknown
FDT = 1 # date
FNU = 2 # number
FGE = 3 # general
FTX = 4 # text
DATEFORMAT = FDT
NUMBERFORMAT = FNU
XL_CELL_EMPTY = 0
XL_CELL_TEXT = 1
XL_CELL_NUMBER = 2
XL_CELL_DATE = 3
XL_CELL_BOOLEAN = 4
XL_CELL_ERROR = 5
XL_CELL_BLANK = 6 # for use in debugging, gathering stats, etc
biff_text_from_num = {
0: "(not BIFF)",
20: "2.0",
21: "2.1",
30: "3",
40: "4S",
45: "4W",
50: "5",
70: "7",
80: "8",
85: "8X",
}
# This dictionary can be used to produce a text version of the internal codes
# that Excel uses for error cells. Here are its contents:
error_text_from_code = {
0x00: '#NULL!', # Intersection of two cell ranges is empty
0x07: '#DIV/0!', # Division by zero
0x0F: '#VALUE!', # Wrong type of operand
0x17: '#REF!', # Illegal or deleted cell reference
0x1D: '#NAME?', # Wrong function or range name
0x24: '#NUM!', # Value range overflow
0x2A: '#N/A!', # Argument or function not available
}
BIFF_FIRST_UNICODE = 80
XL_WORKBOOK_GLOBALS = WBKBLOBAL = 0x5
XL_WORKBOOK_GLOBALS_4W = 0x100
XL_WORKSHEET = WRKSHEET = 0x10
XL_BOUNDSHEET_WORKSHEET = 0x00
XL_BOUNDSHEET_CHART = 0x02
XL_BOUNDSHEET_VB_MODULE = 0x06
# XL_RK2 = 0x7e
XL_ARRAY = 0x0221
XL_ARRAY2 = 0x0021
XL_BLANK = 0x0201
XL_BLANK_B2 = 0x01
XL_BOF = 0x809
XL_BOOLERR = 0x205
XL_BOOLERR_B2 = 0x5
XL_BOUNDSHEET = 0x85
XL_BUILTINFMTCOUNT = 0x56
XL_CF = 0x01B1
XL_CODEPAGE = 0x42
XL_COLINFO = 0x7D
XL_COLUMNDEFAULT = 0x20 # BIFF2 only
XL_COLWIDTH = 0x24 # BIFF2 only
XL_CONDFMT = 0x01B0
XL_CONTINUE = 0x3c
XL_COUNTRY = 0x8C
XL_DATEMODE = 0x22
XL_DEFAULTROWHEIGHT = 0x0225
XL_DEFCOLWIDTH = 0x55
XL_DIMENSION = 0x200
XL_DIMENSION2 = 0x0
XL_EFONT = 0x45
XL_EOF = 0x0a
XL_EXTERNNAME = 0x23
XL_EXTERNSHEET = 0x17
XL_EXTSST = 0xff
XL_FEAT11 = 0x872
XL_FILEPASS = 0x2f
XL_FONT = 0x31
XL_FONT_B3B4 = 0x231
XL_FORMAT = 0x41e
XL_FORMAT2 = 0x1E # BIFF2, BIFF3
XL_FORMULA = 0x6
XL_FORMULA3 = 0x206
XL_FORMULA4 = 0x406
XL_GCW = 0xab
XL_INDEX = 0x20b
XL_INTEGER = 0x2 # BIFF2 only
XL_IXFE = 0x44 # BIFF2 only
XL_LABEL = 0x204
XL_LABEL_B2 = 0x04
XL_LABELRANGES = 0x15f
XL_LABELSST = 0xfd
XL_MERGEDCELLS = 0xE5
XL_MSO_DRAWING = 0x00EC
XL_MSO_DRAWING_GROUP = 0x00EB
XL_MSO_DRAWING_SELECTION = 0x00ED
XL_MULRK = 0xbd
XL_MULBLANK = 0xbe
XL_NAME = 0x18
XL_NOTE = 0x1c
XL_NUMBER = 0x203
XL_NUMBER_B2 = 0x3
XL_OBJ = 0x5D
XL_PALETTE = 0x92
XL_RK = 0x27e
XL_ROW = 0x208
XL_ROW_B2 = 0x08
XL_RSTRING = 0xd6
XL_SHEETHDR = 0x8F # BIFF4W only
XL_SHEETSOFFSET = 0x8E # BIFF4W only
XL_SHRFMLA = 0x04bc
XL_SST = 0xfc
XL_STANDARDWIDTH = 0x99
XL_STRING = 0x207
XL_STRING_B2 = 0x7
XL_STYLE = 0x293
XL_SUPBOOK = 0x1AE
XL_TABLEOP = 0x236
XL_TABLEOP2 = 0x37
XL_TABLEOP_B2 = 0x36
XL_TXO = 0x1b6
XL_UNCALCED = 0x5e
XL_UNKNOWN = 0xffff
XL_WINDOW2 = 0x023E
XL_WRITEACCESS = 0x5C
XL_XF = 0xe0
XL_XF2 = 0x0043 # BIFF2 version of XF record
XL_XF3 = 0x0243 # BIFF3 version of XF record
XL_XF4 = 0x0443 # BIFF4 version of XF record
boflen = {
0x0809: 8,
0x0409: 6,
0x0209: 6,
0x0009: 4,
}
bofcodes = (0x0809, 0x0409, 0x0209, 0x0009)
XL_FORMULA_OPCODES = (0x0006, 0x0406, 0x0206)
_cell_opcode_list = (
XL_BOOLERR,
XL_FORMULA,
XL_FORMULA3,
XL_FORMULA4,
XL_LABEL,
XL_LABELSST,
XL_MULRK,
XL_NUMBER,
XL_RK,
XL_RSTRING,
)
biff_rec_name_dict = {
0x0000: 'DIMENSIONS_B2',
0x0001: 'BLANK_B2',
0x0002: 'INTEGER_B2_ONLY',
0x0003: 'NUMBER_B2',
0x0004: 'LABEL_B2',
0x0005: 'BOOLERR_B2',
0x0006: 'FORMULA',
0x0007: 'STRING_B2',
0x0008: 'ROW_B2',
0x0009: 'BOF_B2',
0x000A: 'EOF',
0x000B: 'INDEX_B2_ONLY',
0x000C: 'CALCCOUNT',
0x000D: 'CALCMODE',
0x000E: 'PRECISION',
0x000F: 'REFMODE',
0x0010: 'DELTA',
0x0011: 'ITERATION',
0x0012: 'PROTECT',
0x0013: 'PASSWORD',
0x0014: 'HEADER',
0x0015: 'FOOTER',
0x0016: 'EXTERNCOUNT',
0x0017: 'EXTERNSHEET',
0x0018: 'NAME_B2,5+',
0x0019: 'WINDOWPROTECT',
0x001A: 'VERTICALPAGEBREAKS',
0x001B: 'HORIZONTALPAGEBREAKS',
0x001C: 'NOTE',
0x001D: 'SELECTION',
0x001E: 'FORMAT_B2-3',
0x001F: 'BUILTINFMTCOUNT_B2',
0x0020: 'COLUMNDEFAULT_B2_ONLY',
0x0021: 'ARRAY_B2_ONLY',
0x0022: 'DATEMODE',
0x0023: 'EXTERNNAME',
0x0024: 'COLWIDTH_B2_ONLY',
0x0025: 'DEFAULTROWHEIGHT_B2_ONLY',
0x0026: 'LEFTMARGIN',
0x0027: 'RIGHTMARGIN',
0x0028: 'TOPMARGIN',
0x0029: 'BOTTOMMARGIN',
0x002A: 'PRINTHEADERS',
0x002B: 'PRINTGRIDLINES',
0x002F: 'FILEPASS',
0x0031: 'FONT',
0x0032: 'FONT2_B2_ONLY',
0x0036: 'TABLEOP_B2',
0x0037: 'TABLEOP2_B2',
0x003C: 'CONTINUE',
0x003D: 'WINDOW1',
0x003E: 'WINDOW2_B2',
0x0040: 'BACKUP',
0x0041: 'PANE',
0x0042: 'CODEPAGE',
0x0043: 'XF_B2',
0x0044: 'IXFE_B2_ONLY',
0x0045: 'EFONT_B2_ONLY',
0x004D: 'PLS',
0x0051: 'DCONREF',
0x0055: 'DEFCOLWIDTH',
0x0056: 'BUILTINFMTCOUNT_B3-4',
0x0059: 'XCT',
0x005A: 'CRN',
0x005B: 'FILESHARING',
0x005C: 'WRITEACCESS',
0x005D: 'OBJECT',
0x005E: 'UNCALCED',
0x005F: 'SAVERECALC',
0x0063: 'OBJECTPROTECT',
0x007D: 'COLINFO',
0x007E: 'RK2_mythical_?',
0x0080: 'GUTS',
0x0081: 'WSBOOL',
0x0082: 'GRIDSET',
0x0083: 'HCENTER',
0x0084: 'VCENTER',
0x0085: 'BOUNDSHEET',
0x0086: 'WRITEPROT',
0x008C: 'COUNTRY',
0x008D: 'HIDEOBJ',
0x008E: 'SHEETSOFFSET',
0x008F: 'SHEETHDR',
0x0090: 'SORT',
0x0092: 'PALETTE',
0x0099: 'STANDARDWIDTH',
0x009B: 'FILTERMODE',
0x009C: 'FNGROUPCOUNT',
0x009D: 'AUTOFILTERINFO',
0x009E: 'AUTOFILTER',
0x00A0: 'SCL',
0x00A1: 'SETUP',
0x00AB: 'GCW',
0x00BD: 'MULRK',
0x00BE: 'MULBLANK',
0x00C1: 'MMS',
0x00D6: 'RSTRING',
0x00D7: 'DBCELL',
0x00DA: 'BOOKBOOL',
0x00DD: 'SCENPROTECT',
0x00E0: 'XF',
0x00E1: 'INTERFACEHDR',
0x00E2: 'INTERFACEEND',
0x00E5: 'MERGEDCELLS',
0x00E9: 'BITMAP',
0x00EB: 'MSO_DRAWING_GROUP',
0x00EC: 'MSO_DRAWING',
0x00ED: 'MSO_DRAWING_SELECTION',
0x00EF: 'PHONETIC',
0x00FC: 'SST',
0x00FD: 'LABELSST',
0x00FF: 'EXTSST',
0x013D: 'TABID',
0x015F: 'LABELRANGES',
0x0160: 'USESELFS',
0x0161: 'DSF',
0x01AE: 'SUPBOOK',
0x01AF: 'PROTECTIONREV4',
0x01B0: 'CONDFMT',
0x01B1: 'CF',
0x01B2: 'DVAL',
0x01B6: 'TXO',
0x01B7: 'REFRESHALL',
0x01B8: 'HLINK',
0x01BC: 'PASSWORDREV4',
0x01BE: 'DV',
0x01C0: 'XL9FILE',
0x01C1: 'RECALCID',
0x0200: 'DIMENSIONS',
0x0201: 'BLANK',
0x0203: 'NUMBER',
0x0204: 'LABEL',
0x0205: 'BOOLERR',
0x0206: 'FORMULA_B3',
0x0207: 'STRING',
0x0208: 'ROW',
0x0209: 'BOF',
0x020B: 'INDEX_B3+',
0x0218: 'NAME',
0x0221: 'ARRAY',
0x0223: 'EXTERNNAME_B3-4',
0x0225: 'DEFAULTROWHEIGHT',
0x0231: 'FONT_B3B4',
0x0236: 'TABLEOP',
0x023E: 'WINDOW2',
0x0243: 'XF_B3',
0x027E: 'RK',
0x0293: 'STYLE',
0x0406: 'FORMULA_B4',
0x0409: 'BOF',
0x041E: 'FORMAT',
0x0443: 'XF_B4',
0x04BC: 'SHRFMLA',
0x0800: 'QUICKTIP',
0x0809: 'BOF',
0x0862: 'SHEETLAYOUT',
0x0867: 'SHEETPROTECTION',
0x0868: 'RANGEPROTECTION',
}
class XLRDError(Exception):
pass
class BaseObject:
"""
Parent of almost all other classes in the package. Defines a common
'dump' method for debugging.
"""
_repr_these = []
def dump(self, f=None, header=None, footer=None, indent=0):
"""
:param f: open file object, to which the dump is written
:param header: text to write before the dump
:param footer: text to write after the dump
:param indent: number of leading spaces (for recursive calls)
"""
if f is None:
f = sys.stderr
pad = " " * indent
if header is not None:
print(header, file=f)
for attr, value in sorted(self.__dict__.items()):
if getattr(value, 'dump', None) and attr != 'book':
value.dump(f,
header="%s%s (%s object):" % (pad, attr, value.__class__.__name__),
indent=indent+4)
elif attr not in self._repr_these and \
(isinstance(value, list) or
isinstance(value, dict)):
print("%s%s: %s, len = %d" % (pad, attr, type(value), len(value)), file=f)
else:
print("%s%s: %r" % (pad, attr, value), file=f)
if footer is not None:
print(footer, file=f)
def fprintf(f, fmt, *vargs):
print(fmt.rstrip('\n') % vargs, file=f)
def upkbits(tgt_obj, src, manifest, local_setattr=setattr):
for n, mask, attr in manifest:
local_setattr(tgt_obj, attr, (src & mask) >> n)
def upkbitsL(tgt_obj, src, manifest, local_setattr=setattr, local_int=int):
for n, mask, attr in manifest:
local_setattr(tgt_obj, attr, local_int((src & mask) >> n))
def unpack_string(data, pos, encoding, lenlen=1):
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
pos += lenlen
return str(data[pos:pos+nchars], encoding)
def unpack_string_update_pos(data, pos, encoding, lenlen=1, known_len=None):
if known_len is not None:
# On a NAME record, the length byte is detached from the front of the string.
nchars = known_len
else:
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
pos += lenlen
newpos = pos + nchars
return (str(data[pos:newpos], encoding), newpos)
def unpack_unicode(data, pos, lenlen=2):
""" Return unicode_strg """
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
if not nchars:
# Ambiguous whether 0-length string should have an "options" byte.
# Avoid crash if missing.
return ""
pos += lenlen
options = data[pos]
pos += 1
if options & 0x08: # richtext
pos += 2
if options & 0x04: # phonetic
pos += 4
if options & 0x01:
# Uncompressed UTF-16-LE
rawstrg = data[pos:pos+2*nchars]
strg = str(rawstrg, 'utf_16_le')
else:
# Note: this is COMPRESSED (not ASCII!) encoding!!!
# Merely returning the raw bytes would work OK 99.99% of the time
# if the local codepage was cp1252 -- however this would rapidly go pear-shaped
# for other codepages so we grit our Anglocentric teeth and return Unicode :-)
strg = str(data[pos:pos+nchars], "latin_1")
return strg
def unpack_unicode_update_pos(data, pos, lenlen=2, known_len=None):
""" Return (unicode_strg, updated value of pos) """
if known_len is not None:
# On a NAME record, the length byte is detached from the front of the string.
nchars = known_len
else:
nchars = unpack('<' + 'BH'[lenlen-1], data[pos:pos+lenlen])[0]
pos += lenlen
if not nchars and not data[pos:]:
# Zero-length string with no options byte
return ("", pos)
options = data[pos]
pos += 1
phonetic = options & 0x04
richtext = options & 0x08
if richtext:
rt = unpack('<H', data[pos:pos+2])[0]
pos += 2
if phonetic:
sz = unpack('<i', data[pos:pos+4])[0]
pos += 4
if options & 0x01:
# Uncompressed UTF-16-LE
strg = str(data[pos:pos+2*nchars], 'utf_16_le')
pos += 2*nchars
else:
# Note: this is COMPRESSED (not ASCII!) encoding!!!
strg = str(data[pos:pos+nchars], "latin_1")
pos += nchars
if richtext:
pos += 4 * rt
if phonetic:
pos += sz
return (strg, pos)
def unpack_cell_range_address_list_update_pos(
output_list, data, pos, biff_version, addr_size=6):
# output_list is updated in situ
if biff_version < 80:
assert addr_size == 6
else:
assert addr_size in (6, 8)
n, = unpack("<H", data[pos:pos+2])
pos += 2
if n:
fmt = "<HHBB" if addr_size == 6 else "<HHHH"
for _unused in range(n):
ra, rb, ca, cb = unpack(fmt, data[pos:pos+addr_size])
output_list.append((ra, rb+1, ca, cb+1))
pos += addr_size
return pos
def hex_char_dump(strg, ofs, dlen, base=0, fout=sys.stdout, unnumbered=False):
endpos = min(ofs + dlen, len(strg))
pos = ofs
numbered = not unnumbered
num_prefix = ''
while pos < endpos:
endsub = min(pos + 16, endpos)
substrg = strg[pos:endsub]
lensub = endsub - pos
if lensub <= 0 or lensub != len(substrg):
fprintf(
sys.stdout,
'??? hex_char_dump: ofs=%d dlen=%d base=%d -> endpos=%d pos=%d endsub=%d substrg=%r\n',
ofs, dlen, base, endpos, pos, endsub, substrg)
break
hexd = ''.join(["%02x " % c for c in substrg])
chard = ''
for c in substrg:
if c == ord('\0'):
c = '~'
elif not (' ' <= chr(c) <= '~'):
c = '?'
if isinstance(c, int):
c = chr(c)
chard += c
if numbered:
num_prefix = "%5d: " % (base+pos-ofs)
fprintf(fout, "%s %-48s %s\n", num_prefix, hexd, chard)
pos = endsub
def biff_dump(mem, stream_offset, stream_len, base=0, fout=sys.stdout,
unnumbered=False):
pos = stream_offset
stream_end = stream_offset + stream_len
adj = base - stream_offset
dummies = 0
numbered = not unnumbered
num_prefix = ''
while stream_end - pos >= 4:
rc, length = unpack('<HH', mem[pos:pos+4])
if rc == 0 and length == 0:
if mem[pos:] == '\0' * (stream_end - pos):
dummies = stream_end - pos
savpos = pos
pos = stream_end
break
if dummies:
dummies += 4
else:
savpos = pos
dummies = 4
pos += 4
else:
if dummies:
if numbered:
num_prefix = "%5d: " % (adj + savpos)
fprintf(fout, "%s---- %d zero bytes skipped ----\n",
num_prefix, dummies)
dummies = 0
recname = biff_rec_name_dict.get(rc, '<UNKNOWN>')
if numbered:
num_prefix = "%5d: " % (adj + pos)
fprintf(fout, "%s%04x %s len = %04x (%d)\n",
num_prefix, rc, recname, length, length)
pos += 4
hex_char_dump(mem, pos, length, adj+pos, fout, unnumbered)
pos += length
if dummies:
if numbered:
num_prefix = "%5d: " % (adj + savpos)
fprintf(fout, "%s---- %d zero bytes skipped ----\n", num_prefix, dummies)
if pos < stream_end:
if numbered:
num_prefix = "%5d: " % (adj + pos)
fprintf(fout, "%s---- Misc bytes at end ----\n", num_prefix)
hex_char_dump(mem, pos, stream_end-pos, adj + pos, fout, unnumbered)
elif pos > stream_end:
fprintf(fout, "Last dumped record has length (%d) that is too large\n", length)
def biff_count_records(mem, stream_offset, stream_len, fout=sys.stdout):
pos = stream_offset
stream_end = stream_offset + stream_len
tally = {}
while stream_end - pos >= 4:
rc, length = unpack('<HH', mem[pos:pos+4])
if rc == 0 and length == 0:
if mem[pos:] == '\0' * (stream_end - pos):
break
recname = "<Dummy (zero)>"
else:
recname = biff_rec_name_dict.get(rc, None)
if recname is None:
recname = "Unknown_0x%04X" % rc
if recname in tally:
tally[recname] += 1
else:
tally[recname] = 1
pos += length + 4
for recname, count in sorted(tally.items()):
fprintf(fout, "%8d %s", count, recname)
-346
View File
@@ -1,346 +0,0 @@
# Implements the minimal functionality required
# to extract a "Workbook" or "Book" stream (as one big string)
# from an OLE2 Compound Document file.
#
# Copyright © 2005-2008 Stephen John Machin, Lingfo Pty Ltd
# This module is part of the xlrd3 package, which is released under a BSD-style licence.
# No part of the content of this file was derived from the works of David Giffin.
# 2008-11-04 SJM Avoid assertion error when -1 used instead of -2 for first_SID of empty SCSS [Frank Hoffsuemmer]
# 2007-09-08 SJM Warning message if sector sizes are extremely large.
# 2007-05-07 SJM Meaningful exception instead of IndexError if a SAT (sector allocation table) is corrupted.
# 2007-04-22 SJM Missing "<" in a struct.unpack call => can't open files on bigendian platforms.
import sys
from struct import unpack
# Magic cookie that should appear in the first 8 bytes of the file.
SIGNATURE = b"\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1"
EOCSID = -2
FREESID = -1
SATSID = -3
MSATSID = -4
def int_floor_div(x, y):
return divmod(x, y)[0]
class CompDocError(Exception):
pass
class DirNode(object):
def __init__(self, DID, dent, DEBUG=0):
# dent is the 128-byte directory entry
self.DID = DID
# (cbufsize, self.etype, self.colour, self.left_DID, self.right_DID,
# self.root_DID,
# self.first_SID,
# self.tot_size) = \
# unpack('<HBBiii16x4x8x8xii4x', dent[64:128])
(cbufsize, self.etype, self.colour, self.left_DID, self.right_DID,
self.root_DID) = \
unpack('<HBBiii', dent[64:80])
(self.first_SID, self.tot_size) = \
unpack('<ii', dent[116:124])
if cbufsize == 0:
self.name = ''
else:
self.name = str(dent[0:cbufsize-2], 'utf_16_le') # omit the trailing U+0000
self.children = [] # filled in later
self.parent = -1 # indicates orphan; fixed up later
self.tsinfo = unpack('<IIII', dent[100:116])
if DEBUG:
self.dump(DEBUG)
def dump(self, DEBUG=1):
print("DID=%d name=%r etype=%d DIDs(left=%d right=%d root=%d parent=%d kids=%r) first_SID=%d tot_size=%d" \
% (self.DID, self.name, self.etype, self.left_DID,
self.right_DID, self.root_DID, self.parent, self.children, self.first_SID, self.tot_size))
if DEBUG == 2:
# cre_lo, cre_hi, mod_lo, mod_hi = tsinfo
print("timestamp info", self.tsinfo)
def _build_family_tree(dirlist, parent_DID, child_DID):
if child_DID < 0: return
_build_family_tree(dirlist, parent_DID, dirlist[child_DID].left_DID)
dirlist[parent_DID].children.append(child_DID)
dirlist[child_DID].parent = parent_DID
_build_family_tree(dirlist, parent_DID, dirlist[child_DID].right_DID)
if dirlist[child_DID].etype == 1: # storage
_build_family_tree(dirlist, child_DID, dirlist[child_DID].root_DID)
# Compound document handler.
# @param mem The raw contents of the file, as a string, or as an mmap.mmap() object. The
# only operation it needs to support is slicing.
class CompDoc(object):
def __init__(self, mem, logfile=sys.stdout, DEBUG=0):
self.logfile = logfile
if mem[0:8] != SIGNATURE:
raise CompDocError('Not an OLE2 compound document')
if mem[28:30] != b'\xFE\xFF':
raise CompDocError('Expected "little-endian" marker, found %r' % mem[28:30])
revision, version = unpack('<HH', mem[24:28])
if DEBUG:
print("\nCompDoc format: version=0x%04x revision=0x%04x" % (version, revision), file=logfile)
self.mem = mem
ssz, sssz = unpack('<HH', mem[30:34])
if ssz > 20: # allows for 2**20 bytes i.e. 1MB
print("WARNING: sector size (2**%d) is preposterous; assuming 512 and continuing ..." \
% ssz, file=logfile)
ssz = 9
if sssz > ssz:
print("WARNING: short stream sector size (2**%d) is preposterous; assuming 64 and continuing ..." \
% sssz, file=logfile)
sssz = 6
self.sec_size = sec_size = 1 << ssz
self.short_sec_size = 1 << sssz
(
SAT_tot_secs, self.dir_first_sec_sid, _unused, self.min_size_std_stream,
SSAT_first_sec_sid, SSAT_tot_secs,
MSAT_first_sec_sid, MSAT_tot_secs,
# ) = unpack('<ii4xiiiii', mem[44:76])
) = unpack('<iiiiiiii', mem[44:76])
mem_data_len = len(mem) - 512
mem_data_secs, left_over = divmod(mem_data_len, sec_size)
if left_over:
#### raise CompDocError("Not a whole number of sectors")
print("WARNING *** file size (%d) not 512 + multiple of sector size (%d)" \
% (len(mem), sec_size), file=logfile)
if DEBUG:
print('sec sizes', ssz, sssz, sec_size, self.short_sec_size, file=logfile)
print("mem data: %d bytes == %d sectors" % (mem_data_len, mem_data_secs), file=logfile)
print("SAT_tot_secs=%d, dir_first_sec_sid=%d, min_size_std_stream=%d" \
% (SAT_tot_secs, self.dir_first_sec_sid, self.min_size_std_stream,), file=logfile)
print("SSAT_first_sec_sid=%d, SSAT_tot_secs=%d" % (SSAT_first_sec_sid, SSAT_tot_secs,), file=logfile)
print("MSAT_first_sec_sid=%d, MSAT_tot_secs=%d" % (MSAT_first_sec_sid, MSAT_tot_secs,), file=logfile)
nent = int_floor_div(sec_size, 4) # number of SID entries in a sector
fmt = "<%di" % nent
trunc_warned = 0
#
# === build the MSAT ===
#
MSAT = list(unpack('<109i', mem[76:512]))
sid = MSAT_first_sec_sid
while sid >= 0:
if sid >= mem_data_secs:
raise CompDocError(
"MSAT extension: accessing sector %d but only %d in file" % (sid, mem_data_secs)
)
offset = 512 + sec_size * sid
news = list(unpack(fmt, mem[offset:offset+sec_size]))
sid = news.pop()
MSAT.extend(news)
if DEBUG:
print("MSAT: len =", len(MSAT), file=logfile)
print(MSAT, file=logfile)
#
# === build the SAT ===
#
self.SAT = []
for msid in MSAT:
if msid == FREESID: continue
if msid >= mem_data_secs:
if not trunc_warned:
print("WARNING *** File is truncated, or OLE2 MSAT is corrupt!!", file=logfile)
print("INFO: Trying to access sector %d but only %d available" \
% (msid, mem_data_secs), file=logfile)
trunc_warned = 1
continue
offset = 512 + sec_size * msid
news = list(unpack(fmt, mem[offset:offset+sec_size]))
self.SAT.extend(news)
if DEBUG:
print("SAT: len =", len(self.SAT), file=logfile)
print(self.SAT, file=logfile)
# print >> logfile, "SAT ",
# for i, s in enumerate(self.SAT):
# print >> logfile, "entry: %4d offset: %6d, next entry: %4d" % (i, 512 + sec_size * i, s)
# print >> logfile, "%d:%d " % (i, s),
print()
# === build the directory ===
#
dbytes = self._get_stream(
self.mem, 512, self.SAT, self.sec_size, self.dir_first_sec_sid,
name="directory")
dirlist = []
did = -1
for pos in range(0, len(dbytes), 128):
did += 1
dirlist.append(DirNode(did, dbytes[pos:pos+128], 0))
self.dirlist = dirlist
_build_family_tree(dirlist, 0, dirlist[0].root_DID) # and stand well back ...
if DEBUG:
for d in dirlist:
d.dump(DEBUG)
#
# === get the SSCS ===
#
sscs_dir = self.dirlist[0]
assert sscs_dir.etype == 5 # root entry
if sscs_dir.first_SID < 0 and sscs_dir.tot_size == 0:
# Problem reported by Frank Hoffsuemmer: some software was
# writing -1 instead of -2 (EOCSID) for the first_SID
# when the SCCS was empty. Not having EOCSID caused assertion
# failure in _get_stream.
# Solution: avoid calling _get_stream in any case when the
# SCSS appears to be empty.
self.SSCS = ""
else:
self.SSCS = self._get_stream(
self.mem, 512, self.SAT, sec_size, sscs_dir.first_SID,
sscs_dir.tot_size, name="SSCS")
# if DEBUG: print >> logfile, "SSCS", repr(self.SSCS)
#
# === build the SSAT ===
#
self.SSAT = []
if SSAT_tot_secs > 0 and sscs_dir.tot_size == 0:
print("WARNING *** OLE2 inconsistency: SSCS size is 0 but SSAT size is non-zero", file=logfile)
if sscs_dir.tot_size > 0:
sid = SSAT_first_sec_sid
nsecs = SSAT_tot_secs
while sid >= 0 and nsecs > 0:
nsecs -= 1
start_pos = 512 + sid * sec_size
news = list(unpack(fmt, mem[start_pos:start_pos+sec_size]))
self.SSAT.extend(news)
sid = self.SAT[sid]
# assert SSAT_tot_secs == 0 or sid == EOCSID
if DEBUG: print("SSAT last sid %d; remaining sectors %d" % (sid, nsecs), file=logfile)
assert nsecs == 0 and sid == EOCSID
if DEBUG: print("SSAT", self.SSAT, file=logfile)
def _get_stream(self, mem, base, sat, sec_size, start_sid, size=None, name=''):
# print >> self.logfile, "_get_stream", base, sec_size, start_sid, size
sectors = []
s = start_sid
if size is None:
# nothing to check against
while s >= 0:
start_pos = base + s * sec_size
sectors.append(mem[start_pos:start_pos+sec_size])
try:
s = sat[s]
except IndexError:
raise CompDocError(
"OLE2 stream %r: sector allocation table invalid entry (%d)" %
(name, s)
)
assert s == EOCSID
else:
todo = size
while s >= 0:
start_pos = base + s * sec_size
grab = sec_size
if grab > todo:
grab = todo
todo -= grab
sectors.append(mem[start_pos:start_pos+grab])
try:
s = sat[s]
except IndexError:
raise CompDocError(
"OLE2 stream %r: sector allocation table invalid entry (%d)" %
(name, s)
)
assert s == EOCSID
if todo != 0:
print("WARNING *** OLE2 stream %r: expected size %d, actual size %d" \
% (name, size, size - todo), file=self.logfile)
return b''.join(sectors)
def _dir_search(self, path, storage_DID=0):
# Return matching DirNode instance, or None
head = path[0]
tail = path[1:]
dl = self.dirlist
for child in dl[storage_DID].children:
if dl[child].name.lower() == head.lower():
et = dl[child].etype
if et == 2:
return dl[child]
if et == 1:
if not tail:
raise CompDocError("Requested component is a 'storage'")
return self._dir_search(tail, child)
dl[child].dump(1)
raise CompDocError("Requested stream is not a 'user stream'")
return None
##
# Interrogate the compound document's directory; return the stream as a string if found, otherwise
# return None.
# @param qname Name of the desired stream e.g. u'Workbook'. Should be in Unicode or convertible thereto.
def get_named_stream(self, qname):
d = self._dir_search(qname.split("/"))
if d is None:
return None
if d.tot_size >= self.min_size_std_stream:
return self._get_stream(
self.mem, 512, self.SAT, self.sec_size, d.first_SID,
d.tot_size, name=qname)
else:
return self._get_stream(
self.SSCS, 0, self.SSAT, self.short_sec_size, d.first_SID,
d.tot_size, name=qname + " (from SSCS)")
# Interrogate the compound document's directory.
# If the named stream is not found, (None, 0, 0) will be returned.
# If the named stream is found and is contiguous within the original byte sequence ("mem")
# used when the document was opened,
# then (mem, offset_to_start_of_stream, length_of_stream) is returned.
# Otherwise a new string is built from the fragments and (new_string, 0, length_of_stream) is returned.
# @param qname Name of the desired stream e.g. u'Workbook'. Should be in Unicode or convertible thereto.
def locate_named_stream(self, qname):
d = self._dir_search(qname.split("/"))
if d is None:
return (None, 0, 0)
if d.tot_size >= self.min_size_std_stream:
return self._locate_stream(self.mem, 512, self.SAT, self.sec_size, d.first_SID, d.tot_size)
else:
return (
self._get_stream(
self.SSCS, 0, self.SSAT, self.short_sec_size, d.first_SID,
d.tot_size, qname + " (from SSCS)"),
0,
d.tot_size
)
return (None, 0, 0) # not found
def _locate_stream(self, mem, base, sat, sec_size, start_sid, size):
# print >> self.logfile, "_locate_stream", base, sec_size, start_sid, size
s = start_sid
if s < 0:
raise CompDocError("_locate_stream: start_sid (%d) is -ve" % start_sid)
p = -99 # dummy previous SID
start_pos = -9999
end_pos = -8888
slices = []
while s >= 0:
if s == p+1:
# contiguous sectors
end_pos += sec_size
else:
# start new slice
if p >= 0:
# not first time
slices.append((start_pos, end_pos))
start_pos = base + s * sec_size
end_pos = start_pos + sec_size
p = s
s = sat[s]
assert s == EOCSID
# print >> self.logfile, len(slices) + 1, "slices"
if not slices:
# The stream is contiguous ... just what we like!
return (mem, start_pos, size)
slices.append((start_pos, end_pos))
return (b''.join([mem[start_pos:end_pos] for start_pos, end_pos in slices]), 0, size)
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
-276
View File
@@ -1,276 +0,0 @@
# Author: mozman <mozman@gmx.at>
# Purpose: xfcell -- cell with convenient xf function
# Created: 04.12.2010
# Copyright (C) 2010, Manfred Moitzi
# License: BSD-style licence
"""
The XFCell() object contains the data for one cell.
WARNING: You don't call this class yourself. You access Cell objects
via methods of the Sheet object(s) that you found in the Book object that
was returned when you called xlrd.open_workbook("myfile.xls").
Cell objects have four attributes: `ctype` is an int, `value` (which depends
on `ctype`), `xf_index` and `sheet`, a reference to the containing sheet. If
**formatting_info** is not enabled when the workbook is opened, xf_index will
be **None**.
The following table describes the types of cells and how their values
are represented in Python.
=============== ===== ============ ==========================================
Type symbol Const Python value Note
=============== ===== ============ ==========================================
XL_CELL_EMPTY 0 ""
XL_CELL_TEXT 1 str
XL_CELL_NUMBER 2 float
XL_CELL_DATE 3 float
XL_CELL_BOOLEAN 4 int 1 means TRUE, 0 means FALSE
XL_CELL_ERROR 5 int representing internal Excel codes; for a
text representation, refer to the supplied
dictionary error_text_from_code
XL_CELL_BLANK 6 "" this type will appear only when
open_workbook(..., formatting_info=True)
is used.
=============== ===== ============ ==========================================
"""
import datetime
from .xldate import xldate_as_tuple
from .biffh import XL_CELL_DATE, BaseObject
class XFCell(BaseObject):
""" Extended Cell() class with convenient methods for easy access of cell
properties.
"""
__slots__ = ['sheet', 'ctype', 'value', 'xf']
def __init__(self, ctype, value, xf_index=None, sheet=None):
self.sheet = sheet
self.ctype = ctype
self.value = value
if xf_index is not None:
self.xf = self.book.xf_list[xf_index]
else:
self.xf = None
@property
def book(self):
return self.sheet.book
@property
def has_xf(self):
return (self.xf is not None)
@property
def xf_index(self):
if self.has_xf:
return self.xf.xf_index
else:
return None
@property
def parent_style(self):
return self.book.xf_list[self.xf.parent_style_index]
@property
def is_datetime(self):
return self.ctype == XL_CELL_DATE
@property
def has_date(self):
if self.is_datetime:
return self.value > 1.
return False
def get_color(self, index):
return self.book.colour_map[index]
def datetime(self):
""" Returns a datetime.datetime object if cell type is XL_CELL_DATE
else raises a TypeError, and raises ValueError if the the cell has
not date value (only time value is present).
"""
if self.is_datetime:
if self.has_date:
date = xldate_as_tuple(self.value, self.book.datemode)
return datetime.datetime(*date)
else:
raise ValueError("Cell has no date value.")
else:
raise TypeError("Cell is not a XL_CELL_DATE.")
def date(self):
""" Returns a datetime.date object if cell type is XL_CELL_DATE
else raises a **TypeError**. Raises **ValueError** if the cell
doesn't have a date value (only time value is present).
"""
dt = self.datetime()
return dt.date()
def time(self):
""" Returns a datetime.time object if cell type is XL_CELL_DATE else
raises a TypeError.
"""
if self.is_datetime:
date = xldate_as_tuple(self.value, self.book.datemode)
return datetime.time(date[3], date[4], date[5])
else:
raise TypeError("Cell is not a XL_CELL_DATE.")
#
# access the XFBackground() class
#
@property
def background(self):
if self.xf.is_style and \
self.xf._background_flag == 0:
return self.xf.background
elif self.xf._background_flag:
return self.xf.background
else:
return self.parent_style.background
def background_color(self):
""" Get cell background-color as 3-tuple. """
color_index = self.xf.background.background_colour_index
return self.get_color(color_index)
def fill_pattern(self):
return self.xf.background.fill_pattern
def pattern_color(self):
color_index = self.xf.background.pattern_colour_index
return self.get_color(color_index)
#
# access the Font() class
#
@property
def font_index(self):
if self.xf.is_style and \
self.xf._font_flag == 0:
return self.xf.font_index
elif self.xf._font_flag:
return self.xf.font_index
else:
return self.parent_style.font_index
@property
def font(self):
""" Get the Font() class. """
return self.book.font_list[self.xf.font_index]
def font_color(self):
""" Get cell foreground-color as 3-tuple. """
return self.get_color(self.font.colour_index)
#
# access the Format() class
#
@property
def format_key(self):
if self.xf.is_style and \
self.xf._format_flag == 0:
return self.xf.format_key
elif self.xf._format_flag:
return self.xf.format_key
else:
return self.parent_style.format_key
@property
def format(self):
""" Get the Format() class. """
return self.book.format_map[self.format_key]
def format_str(self):
""" Get the associated 'format_str'. """
return self.format.format_str
#
# access the XFAligment() class
#
@property
def alignment(self):
if self.xf.is_style and \
self.xf._alignment_flag == 0:
return self.xf.alignment
elif self.xf._alignment_flag:
return self.xf.alignment
else:
return self.parent_style.alignment
#
# access the XFBorder() class
#
@property
def border(self):
if self.xf.is_style and \
self.xf._border_flag == 0:
return self.xf.border
elif self.xf._border_flag:
return self.xf.border
else:
return self.parent_style.border
def bordercolors(self):
""" Get border color as dict of rgb-color-tuples. """
border = self.border
return {
'top': self.get_color(border.top_colour_index),
'bottom': self.get_color(border.bottom_colour_index),
'left': self.get_color(border.left_colour_index),
'right': self.get_color(border.right_colour_index),
'diag': self.get_color(border.diag_colour_index),
}
def borderstyles(self):
""" Get border styles as dict of ints. """
border = self.border
return {
'top': border.top_line_style,
'bottom': border.bottom_line_style,
'left': border.left_line_style,
'right': border.right_line_style,
'diag': border.diag_line_style,
}
@property
def has_up_diag(self):
""" Draw a line across the cell from bottom left to top right. """
return bool(self.border.diag_up)
@property
def has_down_diag(self):
""" Draw a line across the cell from top left to bottom right. """
return bool(self.border.diag_down)
#
# access the XFProtection() class
#
@property
def protection(self):
if self.xf.is_style and \
self.xf._protection_flag == 0:
return self.xf.protection
elif self.xf._protection_flag:
return self.xf.protection
else:
return self.parent_style.protection
@property
def is_cell_locked(self):
return bool(self.protection.cell_locked)
@property
def is_formula_hidden(self):
return bool(self.protection.cell_locked)
-84
View File
@@ -1,84 +0,0 @@
# Author: mozman <mozman@gmx.at>
# Purpose: xfconst -- xf constants
# Created: 05.12.2010
# Copyright (C) 2010, Manfred Moitzi
# License: BSD-style licence
# excelfileformat section 5.115.1 pg. 219
HOR_ALIGN_GENERAL = 0
HOR_ALIGN_LEFT = 1
HOR_ALIGN_CENTRED = 2
HOR_ALIGN_RIGHT = 3
HOR_ALIGN_FILLED = 4
HOR_ALIGN_JUSTIFIED = 5
HOR_ALIGN_CENTRED_ACROSS_SELECTION = 6
HOR_ALIGN_DISTRIBUTED = 7
# excelfileformat section 5.115.1 pg. 220
VERT_ALIGN_TOP = 0
VERT_ALIGN_CENTRED = 1
VERT_ALIGN_BOTTOM = 2
VERT_ALIGN_JUSTIFIED = 3
VERT_ALIGN_DISTRIBUTED = 4
# excelfileformat section 5.115.1 pg. 220
ORIENTATION_NONE = 0
ORIENTATION_STACKED = 1
ORIENTATION_90_COUNTERCLOCKWISE = 2
ORIENTATION_90_CLOCKWISE = 3
# excelfileformat section 5.115.1 pg. 220
ROTATION_NONE = 0
ROTATION_STACKED = 255
# other values:
# Value Description
# ======= =================================
# 1-90 1 to 90 degrees counterclockwise
# 91-180 1 to 90 degrees clockwise
# excelfileformat section 2.5.11 Line Styles for Cell Borders pg. 24
LS_NOLINE = 0
# solid line
LS_THIN = 1
# solid line
LS_MEDIUM = 2
# - - - - - - - - -
LS_DASHED = 3
# .................
LS_DOTTED = 4
# solid line
LS_THICK = 5
# =================
LS_DOUBLE = 6
# very thin dotted
LS_HAIR = 7
# - - - - - - - - -
LS_MEDIUM_DASHED = 8
# - . - . - . - . -
LS_THIN_DASH_DOTTED = 9
# - . - . - . - . -
LS_MEDIUM_DASH_DOTTED = 10
# - .. - .. - .. - .. -
LS_THIN_DASH_DOT_DOTTED = 11
# - .. - .. - .. - .. -
LS_MEDIUM_DASH_DOT_DOTTED = 12
# \\\ . \\\ . \\\ . \\\ . \\\
LS_SLANTED_MEDIUM_DASH_DOTTED = 13
-167
View File
@@ -1,167 +0,0 @@
# No part of the content of this file was derived from the works of David Giffin.
#
# Copyright © 2005-2008 Stephen John Machin, Lingfo Pty Ltd
# This module is part of the xlrd3 package, which is released under a
# BSD-style licence.
#
# Provides function(s) for dealing with Microsoft Excel ™ dates.
#
# 2008-10-18 SJM Fix bug in xldate_from_date_tuple (affected some years after 2099)
#
# The conversion from days to (year, month, day) starts with
# an integral "julian day number" aka JDN.
# FWIW, JDN 0 corresponds to noon on Monday November 24 in Gregorian year -4713.
# More importantly:
# Noon on Gregorian 1900-03-01 (day 61 in the 1900-based system) is JDN 2415080.0
# Noon on Gregorian 1904-01-02 (day 1 in the 1904-based system) is JDN 2416482.0
def ifd(x, y):
return divmod(x, y)[0]
_JDN_delta = (2415080 - 61, 2416482 - 1)
assert _JDN_delta[1] - _JDN_delta[0] == 1462
class XLDateError(ValueError): pass
class XLDateNegative(XLDateError): pass
class XLDateAmbiguous(XLDateError): pass
class XLDateTooLarge(XLDateError): pass
class XLDateBadDatemode(XLDateError): pass
class XLDateBadTuple(XLDateError): pass
_XLDAYS_TOO_LARGE = (2958466, 2958466 - 1462) # This is equivalent to 10000-01-01
# Convert an Excel number (presumed to represent a date, a datetime or a time) into
# a tuple suitable for feeding to datetime or mx.DateTime constructors.
# @param xldate The Excel number
# @param datemode 0: 1900-based, 1: 1904-based.
# <br>WARNING: when using this function to
# interpret the contents of a workbook, you should pass in the Book.datemode
# attribute of that workbook. Whether
# the workbook has ever been anywhere near a Macintosh is irrelevant.
# @return Gregorian (year, month, day, hour, minute, nearest_second).
# <br>Special case: if 0.0 <= xldate < 1.0, it is assumed to represent a time;
# (0, 0, 0, hour, minute, second) will be returned.
# <br>Note: 1904-01-01 is not regarded as a valid date in the datemode 1 system; its "serial number"
# is zero.
# @throws XLDateNegative xldate < 0.00
# @throws XLDateAmbiguous The 1900 leap-year problem (datemode == 0 and 1.0 <= xldate < 61.0)
# @throws XLDateTooLarge Gregorian year 10000 or later
# @throws XLDateBadDatemode datemode arg is neither 0 nor 1
# @throws XLDateError Covers the 4 specific errors
def xldate_as_tuple(xldate, datemode):
if datemode not in (0, 1):
raise XLDateBadDatemode(datemode)
if xldate == 0.00:
return (0, 0, 0, 0, 0, 0)
if xldate < 0.00:
raise XLDateNegative(xldate)
xldays = int(xldate)
frac = xldate - xldays
seconds = int(round(frac * 86400.0))
assert 0 <= seconds <= 86400
if seconds == 86400:
hour = minute = second = 0
xldays += 1
else:
# second = seconds % 60; minutes = seconds // 60
minutes, second = divmod(seconds, 60)
# minute = minutes % 60; hour = minutes // 60
hour, minute = divmod(minutes, 60)
if xldays >= _XLDAYS_TOO_LARGE[datemode]:
raise XLDateTooLarge(xldate)
if xldays == 0:
return (0, 0, 0, hour, minute, second)
if xldays < 61 and datemode == 0:
raise XLDateAmbiguous(xldate)
jdn = xldays + _JDN_delta[datemode]
yreg = (ifd(ifd(jdn * 4 + 274277, 146097) * 3, 4) + jdn + 1363) * 4 + 3
mp = ifd(yreg % 1461, 4) * 535 + 333
d = ifd(mp % 16384, 535) + 1
# mp /= 16384
mp >>= 14
if mp >= 10:
return (ifd(yreg, 1461) - 4715, mp - 9, d, hour, minute, second)
else:
return (ifd(yreg, 1461) - 4716, mp + 3, d, hour, minute, second)
# === conversions from date/time to xl numbers
def _leap(y):
if y % 4: return 0
if y % 100: return 1
if y % 400: return 0
return 1
_days_in_month = (None, 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31)
# Convert a date tuple (year, month, day) to an Excel date.
# @param year Gregorian year.
# @param month 1 <= month <= 12
# @param day 1 <= day <= last day of that (year, month)
# @param datemode 0: 1900-based, 1: 1904-based.
# @throws XLDateAmbiguous The 1900 leap-year problem (datemode == 0 and 1.0 <= xldate < 61.0)
# @throws XLDateBadDatemode datemode arg is neither 0 nor 1
# @throws XLDateBadTuple (year, month, day) is too early/late or has invalid component(s)
# @throws XLDateError Covers the specific errors
def xldate_from_date_tuple(datetuple, datemode):
(year, month, day) = datetuple
if datemode not in (0, 1):
raise XLDateBadDatemode(datemode)
if year == 0 and month == 0 and day == 0:
return 0.00
if not (1900 <= year <= 9999):
raise XLDateBadTuple("Invalid year: %r" % ((year, month, day),))
if not (1 <= month <= 12):
raise XLDateBadTuple("Invalid month: %r" % ((year, month, day),))
if day < 1 \
or (day > _days_in_month[month] and not(day == 29 and month == 2 and _leap(year))):
raise XLDateBadTuple("Invalid day: %r" % ((year, month, day),))
Yp = year + 4716
M = month
if M <= 2:
Yp = Yp - 1
Mp = M + 9
else:
Mp = M - 3
jdn = ifd(1461 * Yp, 4) + ifd(979 * Mp + 16, 32) + \
day - 1364 - ifd(ifd(Yp + 184, 100) * 3, 4)
xldays = jdn - _JDN_delta[datemode]
if xldays <= 0:
raise XLDateBadTuple("Invalid (year, month, day): %r" % ((year, month, day),))
if xldays < 61 and datemode == 0:
raise XLDateAmbiguous("Before 1900-03-01: %r" % ((year, month, day),))
return float(xldays)
# Convert a time tuple (hour, minute, second) to an Excel "date" value (fraction of a day).
# @param hour 0 <= hour < 24
# @param minute 0 <= minute < 60
# @param second 0 <= second < 60
# @throws XLDateBadTuple Out-of-range hour, minute, or second
def xldate_from_time_tuple(timetuple):
(hour, minute, second) = timetuple
if 0 <= hour < 24 and 0 <= minute < 60 and 0 <= second < 60:
return ((second / 60.0 + minute) / 60.0 + hour) / 24.0
raise XLDateBadTuple("Invalid (hour, minute, second): %r" % ((hour, minute, second),))
# Convert a datetime tuple (year, month, day, hour, minute, second) to an Excel date value.
# For more details, refer to other xldate_from_*_tuple functions.
# @param datetime_tuple (year, month, day, hour, minute, second)
# @param datemode 0: 1900-based, 1: 1904-based.
def xldate_from_datetime_tuple(datetime_tuple, datemode):
return (
xldate_from_date_tuple(datetime_tuple[:3], datemode)
+
xldate_from_time_tuple(datetime_tuple[3:])
)
File diff suppressed because it is too large Load Diff
-262
View File
@@ -1,262 +0,0 @@
# -*- coding: windows-1251 -*-
# Portions are Copyright (C) 2005 Roman V. Kiseliov
# Portions are Copyright (c) 2004 Evgeny Filatov <fufff@users.sourceforge.net>
# Portions are Copyright (c) 2002-2004 John McNamara (Perl Spreadsheet::WriteExcel)
from BIFFRecords import BiffRecord
from struct import *
def _size_col(sheet, col):
return sheet.col_width(col)
def _size_row(sheet, row):
return sheet.row_height(row)
def _position_image(sheet, row_start, col_start, x1, y1, width, height):
"""Calculate the vertices that define the position of the image as required by
the OBJ record.
+------------+------------+
| A | B |
+-----+------------+------------+
| |(x1,y1) | |
| 1 |(A1)._______|______ |
| | | | |
| | | | |
+-----+----| BITMAP |-----+
| | | | |
| 2 | |______________. |
| | | (B2)|
| | | (x2,y2)|
+---- +------------+------------+
Example of a bitmap that covers some of the area from cell A1 to cell B2.
Based on the width and height of the bitmap we need to calculate 8 vars:
col_start, row_start, col_end, row_end, x1, y1, x2, y2.
The width and height of the cells are also variable and have to be taken into
account.
The values of col_start and row_start are passed in from the calling
function. The values of col_end and row_end are calculated by subtracting
the width and height of the bitmap from the width and height of the
underlying cells.
The vertices are expressed as a percentage of the underlying cell width as
follows (rhs values are in pixels):
x1 = X / W *1024
y1 = Y / H *256
x2 = (X-1) / W *1024
y2 = (Y-1) / H *256
Where: X is distance from the left side of the underlying cell
Y is distance from the top of the underlying cell
W is the width of the cell
H is the height of the cell
Note: the SDK incorrectly states that the height should be expressed as a
percentage of 1024.
col_start - Col containing upper left corner of object
row_start - Row containing top left corner of object
x1 - Distance to left side of object
y1 - Distance to top of object
width - Width of image frame
height - Height of image frame
"""
# Adjust start column for offsets that are greater than the col width
while x1 >= _size_col(sheet, col_start):
x1 -= _size_col(sheet, col_start)
col_start += 1
# Adjust start row for offsets that are greater than the row height
while y1 >= _size_row(sheet, row_start):
y1 -= _size_row(sheet, row_start)
row_start += 1
# Initialise end cell to the same as the start cell
row_end = row_start # Row containing bottom right corner of object
col_end = col_start # Col containing lower right corner of object
width = width + x1 - 1
height = height + y1 - 1
# Subtract the underlying cell widths to find the end cell of the image
while (width >= _size_col(sheet, col_end)):
width -= _size_col(sheet, col_end)
col_end += 1
# Subtract the underlying cell heights to find the end cell of the image
while (height >= _size_row(sheet, row_end)):
height -= _size_row(sheet, row_end)
row_end += 1
# Bitmap isn't allowed to start or finish in a hidden cell, i.e. a cell
# with zero height or width.
if ((_size_col(sheet, col_start) == 0) or (_size_col(sheet, col_end) == 0)
or (_size_row(sheet, row_start) == 0) or (_size_row(sheet, row_end) == 0)):
return
# Convert the pixel values to the percentage value expected by Excel
x1 = int(float(x1) / _size_col(sheet, col_start) * 1024)
y1 = int(float(y1) / _size_row(sheet, row_start) * 256)
# Distance to right side of object
x2 = int(float(width) / _size_col(sheet, col_end) * 1024)
# Distance to bottom of object
y2 = int(float(height) / _size_row(sheet, row_end) * 256)
return (col_start, x1, row_start, y1, col_end, x2, row_end, y2)
class ObjBmpRecord(BiffRecord):
_REC_ID = 0x005D # Record identifier
def __init__(self, row, col, sheet, im_data_bmp, x, y, scale_x, scale_y):
# Scale the frame of the image.
width = im_data_bmp.width * scale_x
height = im_data_bmp.height * scale_y
# Calculate the vertices of the image and write the OBJ record
coordinates = _position_image(sheet, row, col, x, y, width, height)
# print coordinates
col_start, x1, row_start, y1, col_end, x2, row_end, y2 = coordinates
"""Store the OBJ record that precedes an IMDATA record. This could be generalise
to support other Excel objects.
"""
cObj = 0x0001 # Count of objects in file (set to 1)
OT = 0x0008 # Object type. 8 = Picture
id = 0x0001 # Object ID
grbit = 0x0614 # Option flags
colL = col_start # Col containing upper left corner of object
dxL = x1 # Distance from left side of cell
rwT = row_start # Row containing top left corner of object
dyT = y1 # Distance from top of cell
colR = col_end # Col containing lower right corner of object
dxR = x2 # Distance from right of cell
rwB = row_end # Row containing bottom right corner of object
dyB = y2 # Distance from bottom of cell
cbMacro = 0x0000 # Length of FMLA structure
Reserved1 = 0x0000 # Reserved
Reserved2 = 0x0000 # Reserved
icvBack = 0x09 # Background colour
icvFore = 0x09 # Foreground colour
fls = 0x00 # Fill pattern
fAuto = 0x00 # Automatic fill
icv = 0x08 # Line colour
lns = 0xff # Line style
lnw = 0x01 # Line weight
fAutoB = 0x00 # Automatic border
frs = 0x0000 # Frame style
cf = 0x0009 # Image format, 9 = bitmap
Reserved3 = 0x0000 # Reserved
cbPictFmla = 0x0000 # Length of FMLA structure
Reserved4 = 0x0000 # Reserved
grbit2 = 0x0001 # Option flags
Reserved5 = 0x0000 # Reserved
data = pack("<L", cObj)
data += pack("<H", OT)
data += pack("<H", id)
data += pack("<H", grbit)
data += pack("<H", colL)
data += pack("<H", dxL)
data += pack("<H", rwT)
data += pack("<H", dyT)
data += pack("<H", colR)
data += pack("<H", dxR)
data += pack("<H", rwB)
data += pack("<H", dyB)
data += pack("<H", cbMacro)
data += pack("<L", Reserved1)
data += pack("<H", Reserved2)
data += pack("<B", icvBack)
data += pack("<B", icvFore)
data += pack("<B", fls)
data += pack("<B", fAuto)
data += pack("<B", icv)
data += pack("<B", lns)
data += pack("<B", lnw)
data += pack("<B", fAutoB)
data += pack("<H", frs)
data += pack("<L", cf)
data += pack("<H", Reserved3)
data += pack("<H", cbPictFmla)
data += pack("<H", Reserved4)
data += pack("<H", grbit2)
data += pack("<L", Reserved5)
self._rec_data = data
def _process_bitmap(bitmap):
"""Convert a 24 bit bitmap into the modified internal format used by Windows.
This is described in BITMAPCOREHEADER and BITMAPCOREINFO structures in the
MSDN library.
"""
# Open file and binmode the data in case the platform needs it.
fh = file(bitmap, "rb")
try:
# Slurp the file into a string.
data = fh.read()
finally:
fh.close()
# Check that the file is big enough to be a bitmap.
if len(data) <= 0x36:
raise Exception("bitmap doesn't contain enough data.")
# The first 2 bytes are used to identify the bitmap.
if (data[:2] != "BM"):
raise Exception("bitmap doesn't appear to to be a valid bitmap image.")
# Remove bitmap data: ID.
data = data[2:]
# Read and remove the bitmap size. This is more reliable than reading
# the data size at offset 0x22.
#
size = unpack("<L", data[:4])[0]
size -= 0x36 # Subtract size of bitmap header.
size += 0x0C # Add size of BIFF header.
data = data[4:]
# Remove bitmap data: reserved, offset, header length.
data = data[12:]
# Read and remove the bitmap width and height. Verify the sizes.
width, height = unpack("<LL", data[:8])
data = data[8:]
if (width > 0xFFFF):
raise Exception("bitmap: largest image width supported is 65k.")
if (height > 0xFFFF):
raise Exception("bitmap: largest image height supported is 65k.")
# Read and remove the bitmap planes and bpp data. Verify them.
planes, bitcount = unpack("<HH", data[:4])
data = data[4:]
if (bitcount != 24):
raise Exception("bitmap isn't a 24bit true color bitmap.")
if (planes != 1):
raise Exception("bitmap: only 1 plane supported in bitmap image.")
# Read and remove the bitmap compression. Verify compression.
compression = unpack("<L", data[:4])[0]
data = data[4:]
if (compression != 0):
raise Exception("bitmap: compression not supported in bitmap image.")
# Remove bitmap data: data size, hres, vres, colours, imp. colours.
data = data[20:]
# Add the BITMAPCOREHEADER data
header = pack("<LHHHH", 0x000c, width, height, 0x01, 0x18)
data = header + data
return (width, height, size, data)
class ImDataBmpRecord(BiffRecord):
_REC_ID = 0x007F
def __init__(self, filename):
"""Insert a 24bit bitmap image in a worksheet. The main record required is
IMDATA but it must be proceeded by a OBJ record to define its position.
"""
BiffRecord.__init__(self)
self.width, self.height, self.size, data = _process_bitmap(filename)
# Write the IMDATA record to store the bitmap data
cf = 0x09
env = 0x01
lcb = self.size
self._rec_data = pack("<HHL", cf, env, lcb) + data
-243
View File
@@ -1,243 +0,0 @@
# -*- coding: windows-1252 -*-
from struct import unpack, pack
import BIFFRecords
class StrCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "sst_idx"]
def __init__(self, rowx, colx, xf_idx, sst_idx):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.sst_idx = sst_idx
def get_biff_data(self):
# return BIFFRecords.LabelSSTRecord(self.rowx, self.colx, self.xf_idx, self.sst_idx).get()
return pack('<5HL', 0x00FD, 10, self.rowx, self.colx, self.xf_idx, self.sst_idx)
class BlankCell(object):
__slots__ = ["rowx", "colx", "xf_idx"]
def __init__(self, rowx, colx, xf_idx):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
def get_biff_data(self):
# return BIFFRecords.BlankRecord(self.rowx, self.colx, self.xf_idx).get()
return pack('<5H', 0x0201, 6, self.rowx, self.colx, self.xf_idx)
class MulBlankCell(object):
__slots__ = ["rowx", "colx1", "colx2", "xf_idx"]
def __init__(self, rowx, colx1, colx2, xf_idx):
self.rowx = rowx
self.colx1 = colx1
self.colx2 = colx2
self.xf_idx = xf_idx
def get_biff_data(self):
return BIFFRecords.MulBlankRecord(self.rowx,
self.colx1, self.colx2, self.xf_idx).get()
class NumberCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "number"]
def __init__(self, rowx, colx, xf_idx, number):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.number = float(number)
def get_encoded_data(self):
rk_encoded = 0
num = self.number
# The four possible kinds of RK encoding are *not* mutually exclusive.
# The 30-bit integer variety picks up the most.
# In the code below, the four varieties are checked in descending order
# of bangs per buck, or not at all.
# SJM 2007-10-01
if -0x20000000 <= num < 0x20000000: # fits in 30-bit *signed* int
inum = int(num)
if inum == num: # survives round-trip
# print "30-bit integer RK", inum, hex(inum)
rk_encoded = 2 | (inum << 2)
return 1, rk_encoded
temp = num * 100
if -0x20000000 <= temp < 0x20000000:
# That was step 1: the coded value will fit in
# a 30-bit signed integer.
itemp = int(round(temp, 0))
# That was step 2: "itemp" is the best candidate coded value.
# Now for step 3: simulate the decoding,
# to check for round-trip correctness.
if itemp / 100.0 == num:
# print "30-bit integer RK*100", itemp, hex(itemp)
rk_encoded = 3 | (itemp << 2)
return 1, rk_encoded
if 0: # Cost of extra pack+unpack not justified by tiny yield.
packed = pack('<d', num)
w01, w23 = unpack('<2i', packed)
if not w01 and not(w23 & 3):
# 34 lsb are 0
# print "float RK", w23, hex(w23)
return 1, w23
packed100 = pack('<d', temp)
w01, w23 = unpack('<2i', packed100)
if not w01 and not(w23 & 3):
# 34 lsb are 0
# print "float RK*100", w23, hex(w23)
return 1, w23 | 1
#print "Number"
#print
return 0, pack('<5Hd', 0x0203, 14, self.rowx, self.colx, self.xf_idx, num)
def get_biff_data(self):
isRK, value = self.get_encoded_data()
if isRK:
return pack('<5Hi', 0x27E, 10, self.rowx, self.colx, self.xf_idx, value)
return value # NUMBER record already packed
class BooleanCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "number"]
def __init__(self, rowx, colx, xf_idx, number):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.number = number
def get_biff_data(self):
return BIFFRecords.BoolErrRecord(self.rowx,
self.colx, self.xf_idx, self.number, 0).get()
error_code_map = {
0x00: 0, # Intersection of two cell ranges is empty
0x07: 7, # Division by zero
0x0F: 15, # Wrong type of operand
0x17: 23, # Illegal or deleted cell reference
0x1D: 29, # Wrong function or range name
0x24: 36, # Value range overflow
0x2A: 42, # Argument or function not available
'#NULL!' : 0, # Intersection of two cell ranges is empty
'#DIV/0!': 7, # Division by zero
'#VALUE!': 36, # Wrong type of operand
'#REF!' : 23, # Illegal or deleted cell reference
'#NAME?' : 29, # Wrong function or range name
'#NUM!' : 36, # Value range overflow
'#N/A!' : 42, # Argument or function not available
}
class ErrorCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "number"]
def __init__(self, rowx, colx, xf_idx, error_string_or_code):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
try:
self.number = error_code_map[error_string_or_code]
except KeyError:
raise Exception('Illegal error value (%r)' % error_string_or_code)
def get_biff_data(self):
return BIFFRecords.BoolErrRecord(self.rowx,
self.colx, self.xf_idx, self.number, 1).get()
class FormulaCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "frmla", "calc_flags"]
def __init__(self, rowx, colx, xf_idx, frmla, calc_flags=0):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.frmla = frmla
self.calc_flags = calc_flags
def get_biff_data(self):
return BIFFRecords.FormulaRecord(self.rowx,
self.colx, self.xf_idx, self.frmla.rpn(), self.calc_flags).get()
# module-level function for *internal* use by the Row module
def _get_cells_biff_data_mul(rowx, cell_items):
# Return the BIFF data for all cell records in the row.
# Adjacent BLANK|RK records are combined into MUL(BLANK|RK) records.
pieces = []
nitems = len(cell_items)
i = 0
while i < nitems:
icolx, icell = cell_items[i]
if isinstance(icell, NumberCell):
isRK, value = icell.get_encoded_data()
if not isRK:
pieces.append(value) # pre-packed NUMBER record
i += 1
continue
muldata = [(value, icell.xf_idx)]
target = NumberCell
elif isinstance(icell, BlankCell):
muldata = [icell.xf_idx]
target = BlankCell
else:
pieces.append(icell.get_biff_data())
i += 1
continue
lastcolx = icolx
j = i
packed_record = ''
for j in xrange(i+1, nitems):
jcolx, jcell = cell_items[j]
if jcolx != lastcolx + 1:
nexti = j
break
if not isinstance(jcell, target):
nexti = j
break
if target == NumberCell:
isRK, value = jcell.get_encoded_data()
if not isRK:
packed_record = value
nexti = j + 1
break
muldata.append((value, jcell.xf_idx))
else:
muldata.append(jcell.xf_idx)
lastcolx = jcolx
else:
nexti = j + 1
if target == NumberCell:
if lastcolx == icolx:
# RK record
value, xf_idx = muldata[0]
pieces.append(pack('<5Hi', 0x027E, 10, rowx, icolx, xf_idx, value))
else:
# MULRK record
nc = lastcolx - icolx + 1
pieces.append(pack('<4H', 0x00BD, 6 * nc + 6, rowx, icolx))
pieces.append(''.join([pack('<Hi', xf_idx, value) for value, xf_idx in muldata]))
pieces.append(pack('<H', lastcolx))
else:
if lastcolx == icolx:
# BLANK record
xf_idx = muldata[0]
pieces.append(pack('<5H', 0x0201, 6, rowx, icolx, xf_idx))
else:
# MULBLANK record
nc = lastcolx - icolx + 1
pieces.append(pack('<4H', 0x00BE, 2 * nc + 6, rowx, icolx))
pieces.append(''.join([pack('<H', xf_idx) for xf_idx in muldata]))
pieces.append(pack('<H', lastcolx))
if packed_record:
pieces.append(packed_record)
i = nexti
return ''.join(pieces)
-34
View File
@@ -1,34 +0,0 @@
# -*- coding: windows-1252 -*-
from BIFFRecords import ColInfoRecord
class Column(object):
def __init__(self, colx, parent_sheet):
if not(isinstance(colx, int) and 0 <= colx <= 255):
raise ValueError("column index (%r) not an int in range(256)" % colx)
self._index = colx
self._parent = parent_sheet
self._parent_wb = parent_sheet.get_parent()
self._xf_index = 0x0F
self.width = 0x0B92
self.hidden = 0
self.level = 0
self.collapse = 0
def set_style(self, style):
self._xf_index = self._parent_wb.add_style(style)
def width_in_pixels(self):
# *** Approximation ****
return int(round(self.width * 0.0272 + 0.446, 0))
def get_biff_record(self):
options = (self.hidden & 0x01) << 0
options |= (self.level & 0x07) << 8
options |= (self.collapse & 0x01) << 12
return ColInfoRecord(self._index, self._index, self.width, self._xf_index, options).get()
-516
View File
@@ -1,516 +0,0 @@
# -*- coding: windows-1252 -*-
import sys
import struct
class Reader:
def __init__(self, filename, dump = False):
self.dump = dump
self.STREAMS = {}
doc = file(filename, 'rb').read()
self.header, self.data = doc[0:512], doc[512:]
del doc
self.__build_header()
self.__build_MSAT()
self.__build_SAT()
self.__build_directory()
self.__build_short_sectors_data()
if len(self.short_sectors_data) > 0:
self.__build_SSAT()
else:
if self.dump and (self.total_ssat_sectors != 0 or self.ssat_start_sid != -2):
print 'NOTE: header says that must be', self.total_ssat_sectors, 'short sectors'
print 'NOTE: starting at', self.ssat_start_sid, 'sector'
print 'NOTE: but file does not contains data in short sectors'
self.ssat_start_sid = -2
self.total_ssat_sectors = 0
self.SSAT = [-2]
for dentry in self.dir_entry_list[1:]:
(did,
sz, name,
t, c,
did_left, did_right, did_root,
dentry_start_sid,
stream_size
) = dentry
stream_data = ''
if stream_size > 0:
if stream_size >= self.min_stream_size:
args = (self.data, self.SAT, dentry_start_sid, self.sect_size)
else:
args = (self.short_sectors_data, self.SSAT, dentry_start_sid, self.short_sect_size)
stream_data = self.get_stream_data(*args)
if name != '':
# BAD IDEA: names may be equal. NEED use full paths...
self.STREAMS[name] = stream_data
def __build_header(self):
self.doc_magic = self.header[0:8]
if self.doc_magic != '\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1':
raise Exception, 'Not an OLE file.'
self.file_uid = self.header[8:24]
self.rev_num = self.header[24:26]
self.ver_num = self.header[26:28]
self.byte_order = self.header[28:30]
self.log2_sect_size, = struct.unpack('<H', self.header[30:32])
self.log2_short_sect_size, = struct.unpack('<H', self.header[32:34])
self.total_sat_sectors, = struct.unpack('<L', self.header[44:48])
self.dir_start_sid, = struct.unpack('<l', self.header[48:52])
self.min_stream_size, = struct.unpack('<L', self.header[56:60])
self.ssat_start_sid, = struct.unpack('<l', self.header[60:64])
self.total_ssat_sectors, = struct.unpack('<L', self.header[64:68])
self.msat_start_sid, = struct.unpack('<l', self.header[68:72])
self.total_msat_sectors, = struct.unpack('<L', self.header[72:76])
self.sect_size = 1 << self.log2_sect_size
self.short_sect_size = 1 << self.log2_short_sect_size
if self.dump:
print 'file magic: '
print_bin_data(self.doc_magic)
print 'file uid: '
print_bin_data(self.file_uid)
print 'revision number: '
print_bin_data(self.rev_num)
print 'version number: '
print_bin_data(self.ver_num)
print 'byte order: '
print_bin_data(self.byte_order)
print 'sector size :', hex(self.sect_size), self.sect_size
#print 'total sectors in file :', hex(self.total_sectors), self.total_sectors
print 'short sector size :', hex(self.short_sect_size), self.short_sect_size
print 'Total number of sectors used for the SAT :', hex(self.total_sat_sectors), self.total_sat_sectors
print 'SID of first sector of the directory stream:', hex(self.dir_start_sid), self.dir_start_sid
print 'Minimum size of a standard stream :', hex(self.min_stream_size), self.min_stream_size
print 'SID of first sector of the SSAT :', hex(self.ssat_start_sid), self.ssat_start_sid
print 'Total number of sectors used for the SSAT :', hex(self.total_ssat_sectors), self.total_ssat_sectors
print 'SID of first additional sector of the MSAT :', hex(self.msat_start_sid), self.msat_start_sid
print 'Total number of sectors used for the MSAT :', hex(self.total_msat_sectors), self.total_msat_sectors
def __build_MSAT(self):
self.MSAT = list(struct.unpack('<109l', self.header[76:]))
next = self.msat_start_sid
while next > 0:
msat_sector = struct.unpack('<128l', self.data[next*self.sect_size:(next+1)*self.sect_size])
self.MSAT.extend(msat_sector[:127])
next = msat_sector[-1]
if self.dump:
print 'MSAT (header part): \n', self.MSAT[:109]
print 'additional MSAT sectors: \n', self.MSAT[109:]
def __build_SAT(self):
sat_stream = ''.join([self.data[i*self.sect_size:(i+1)*self.sect_size] for i in self.MSAT if i >= 0])
sat_sids_count = len(sat_stream) >> 2
self.SAT = struct.unpack('<%dl' % sat_sids_count, sat_stream) # SIDs tuple
if self.dump:
print 'SAT sid count:\n', sat_sids_count
print 'SAT content:\n', self.SAT
def __build_SSAT(self):
ssat_stream = self.get_stream_data(self.data, self.SAT, self.ssat_start_sid, self.sect_size)
ssids_count = len(ssat_stream) >> 2
self.SSAT = struct.unpack('<%dl' % ssids_count, ssat_stream)
if self.dump:
print 'SSID count:', ssids_count
print 'SSAT content:\n', self.SSAT
def __build_directory(self):
dir_stream = self.get_stream_data(self.data, self.SAT, self.dir_start_sid, self.sect_size)
self.dir_entry_list = []
i = 0
while i < len(dir_stream):
dentry = dir_stream[i:i+128] # 128 -- dir entry size
i += 128
did = len(self.dir_entry_list)
sz, = struct.unpack('<H', dentry[64:66])
if sz > 0 :
name = dentry[0:sz-2].decode('utf_16_le', 'replace')
else:
name = u''
t, = struct.unpack('B', dentry[66])
c, = struct.unpack('B', dentry[67])
did_left , = struct.unpack('<l', dentry[68:72])
did_right , = struct.unpack('<l', dentry[72:76])
did_root , = struct.unpack('<l', dentry[76:80])
dentry_start_sid , = struct.unpack('<l', dentry[116:120])
stream_size , = struct.unpack('<L', dentry[120:124])
self.dir_entry_list.extend([(did, sz, name, t, c,
did_left, did_right, did_root,
dentry_start_sid, stream_size)])
if self.dump:
dentry_types = {
0x00: 'Empty',
0x01: 'User storage',
0x02: 'User stream',
0x03: 'LockBytes',
0x04: 'Property',
0x05: 'Root storage'
}
node_colours = {
0x00: 'Red',
0x01: 'Black'
}
print 'total directory entries:', len(self.dir_entry_list)
for dentry in self.dir_entry_list:
(did, sz, name, t, c,
did_left, did_right, did_root,
dentry_start_sid, stream_size) = dentry
print 'DID', did
print 'Size of the used area of the character buffer of the name:', sz
print 'dir entry name:', repr(name)
print 'type of entry:', t, dentry_types[t]
print 'entry colour:', c, node_colours[c]
print 'left child DID :', did_left
print 'right child DID:', did_right
print 'root DID :', did_root
print 'start SID :', dentry_start_sid
print 'stream size :', stream_size
if stream_size == 0:
print 'stream is empty'
elif stream_size >= self.min_stream_size:
print 'stream stored as normal stream'
else:
print 'stream stored as short-stream'
def __build_short_sectors_data(self):
(did, sz, name, t, c,
did_left, did_right, did_root,
dentry_start_sid, stream_size) = self.dir_entry_list[0]
assert t == 0x05 # Short-Stream Container Stream (SSCS) resides in Root Storage
if stream_size == 0:
self.short_sectors_data = ''
else:
self.short_sectors_data = self.get_stream_data(self.data, self.SAT, dentry_start_sid, self.sect_size)
def get_stream_data(self, data, SAT, start_sid, sect_size):
sid = start_sid
chunks = [(sid, sid)]
stream_data = ''
while SAT[sid] >= 0:
next_in_chain = SAT[sid]
last_chunk_start, last_chunk_finish = chunks[-1]
if next_in_chain == last_chunk_finish + 1:
chunks[-1] = last_chunk_start, next_in_chain
else:
chunks.extend([(next_in_chain, next_in_chain)])
sid = next_in_chain
for s, f in chunks:
stream_data += data[s*sect_size:(f+1)*sect_size]
#print chunks
return stream_data
def print_bin_data(data):
i = 0
while i < len(data):
j = 0
while (i < len(data)) and (j < 16):
c = '0x%02X' % ord(data[i])
sys.stdout.write(c)
sys.stdout.write(' ')
i += 1
j += 1
print
if i == 0:
print '<NO DATA>'
# This implementation writes only 'Root Entry', 'Workbook' streams
# and 2 empty streams for aligning directory stream on sector boundary
#
# LAYOUT:
# 0 header
# 76 MSAT (1st part: 109 SID)
# 512 workbook stream
# ... additional MSAT sectors if streams' size > about 7 Mb == (109*512 * 128)
# ... SAT
# ... directory stream
#
# NOTE: this layout is "ad hoc". It can be more general. RTFM
class XlsDoc:
SECTOR_SIZE = 0x0200
MIN_LIMIT = 0x1000
SID_FREE_SECTOR = -1
SID_END_OF_CHAIN = -2
SID_USED_BY_SAT = -3
SID_USED_BY_MSAT = -4
def __init__(self):
#self.book_stream = '' # padded
self.book_stream_sect = []
self.dir_stream = ''
self.dir_stream_sect = []
self.packed_SAT = ''
self.SAT_sect = []
self.packed_MSAT_1st = ''
self.packed_MSAT_2nd = ''
self.MSAT_sect_2nd = []
self.header = ''
def __build_directory(self): # align on sector boundary
self.dir_stream = ''
dentry_name = '\x00'.join('Root Entry\x00') + '\x00'
dentry_name_sz = len(dentry_name)
dentry_name_pad = '\x00'*(64 - dentry_name_sz)
dentry_type = 0x05 # root storage
dentry_colour = 0x01 # black
dentry_did_left = -1
dentry_did_right = -1
dentry_did_root = 1
dentry_start_sid = -2
dentry_stream_sz = 0
self.dir_stream += struct.pack('<64s H 2B 3l 9L l L L',
dentry_name + dentry_name_pad,
dentry_name_sz,
dentry_type,
dentry_colour,
dentry_did_left,
dentry_did_right,
dentry_did_root,
0, 0, 0, 0, 0, 0, 0, 0, 0,
dentry_start_sid,
dentry_stream_sz,
0
)
dentry_name = '\x00'.join('Workbook\x00') + '\x00'
dentry_name_sz = len(dentry_name)
dentry_name_pad = '\x00'*(64 - dentry_name_sz)
dentry_type = 0x02 # user stream
dentry_colour = 0x01 # black
dentry_did_left = -1
dentry_did_right = -1
dentry_did_root = -1
dentry_start_sid = 0
dentry_stream_sz = self.book_stream_len
self.dir_stream += struct.pack('<64s H 2B 3l 9L l L L',
dentry_name + dentry_name_pad,
dentry_name_sz,
dentry_type,
dentry_colour,
dentry_did_left,
dentry_did_right,
dentry_did_root,
0, 0, 0, 0, 0, 0, 0, 0, 0,
dentry_start_sid,
dentry_stream_sz,
0
)
# padding
dentry_name = ''
dentry_name_sz = len(dentry_name)
dentry_name_pad = '\x00'*(64 - dentry_name_sz)
dentry_type = 0x00 # empty
dentry_colour = 0x01 # black
dentry_did_left = -1
dentry_did_right = -1
dentry_did_root = -1
dentry_start_sid = -2
dentry_stream_sz = 0
self.dir_stream += struct.pack('<64s H 2B 3l 9L l L L',
dentry_name + dentry_name_pad,
dentry_name_sz,
dentry_type,
dentry_colour,
dentry_did_left,
dentry_did_right,
dentry_did_root,
0, 0, 0, 0, 0, 0, 0, 0, 0,
dentry_start_sid,
dentry_stream_sz,
0
) * 2
def __build_sat(self):
# Build SAT
book_sect_count = self.book_stream_len >> 9
dir_sect_count = len(self.dir_stream) >> 9
total_sect_count = book_sect_count + dir_sect_count
SAT_sect_count = 0
MSAT_sect_count = 0
SAT_sect_count_limit = 109
while total_sect_count > 128*SAT_sect_count or SAT_sect_count > SAT_sect_count_limit:
SAT_sect_count += 1
total_sect_count += 1
if SAT_sect_count > SAT_sect_count_limit:
MSAT_sect_count += 1
total_sect_count += 1
SAT_sect_count_limit += 127
SAT = [self.SID_FREE_SECTOR]*128*SAT_sect_count
sect = 0
while sect < book_sect_count - 1:
self.book_stream_sect.append(sect)
SAT[sect] = sect + 1
sect += 1
self.book_stream_sect.append(sect)
SAT[sect] = self.SID_END_OF_CHAIN
sect += 1
while sect < book_sect_count + MSAT_sect_count:
self.MSAT_sect_2nd.append(sect)
SAT[sect] = self.SID_USED_BY_MSAT
sect += 1
while sect < book_sect_count + MSAT_sect_count + SAT_sect_count:
self.SAT_sect.append(sect)
SAT[sect] = self.SID_USED_BY_SAT
sect += 1
while sect < book_sect_count + MSAT_sect_count + SAT_sect_count + dir_sect_count - 1:
self.dir_stream_sect.append(sect)
SAT[sect] = sect + 1
sect += 1
self.dir_stream_sect.append(sect)
SAT[sect] = self.SID_END_OF_CHAIN
sect += 1
self.packed_SAT = struct.pack('<%dl' % (SAT_sect_count*128), *SAT)
MSAT_1st = [self.SID_FREE_SECTOR]*109
for i, SAT_sect_num in zip(range(0, 109), self.SAT_sect):
MSAT_1st[i] = SAT_sect_num
self.packed_MSAT_1st = struct.pack('<109l', *MSAT_1st)
MSAT_2nd = [self.SID_FREE_SECTOR]*128*MSAT_sect_count
if MSAT_sect_count > 0:
MSAT_2nd[- 1] = self.SID_END_OF_CHAIN
i = 109
msat_sect = 0
sid_num = 0
while i < SAT_sect_count:
if (sid_num + 1) % 128 == 0:
#print 'link: ',
msat_sect += 1
if msat_sect < len(self.MSAT_sect_2nd):
MSAT_2nd[sid_num] = self.MSAT_sect_2nd[msat_sect]
else:
#print 'sid: ',
MSAT_2nd[sid_num] = self.SAT_sect[i]
i += 1
#print sid_num, MSAT_2nd[sid_num]
sid_num += 1
self.packed_MSAT_2nd = struct.pack('<%dl' % (MSAT_sect_count*128), *MSAT_2nd)
#print vars()
#print zip(range(0, sect), SAT)
#print self.book_stream_sect
#print self.MSAT_sect_2nd
#print MSAT_2nd
#print self.SAT_sect
#print self.dir_stream_sect
def __build_header(self):
doc_magic = '\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1'
file_uid = '\x00'*16
rev_num = '\x3E\x00'
ver_num = '\x03\x00'
byte_order = '\xFE\xFF'
log_sect_size = struct.pack('<H', 9)
log_short_sect_size = struct.pack('<H', 6)
not_used0 = '\x00'*10
total_sat_sectors = struct.pack('<L', len(self.SAT_sect))
dir_start_sid = struct.pack('<l', self.dir_stream_sect[0])
not_used1 = '\x00'*4
min_stream_size = struct.pack('<L', 0x1000)
ssat_start_sid = struct.pack('<l', -2)
total_ssat_sectors = struct.pack('<L', 0)
if len(self.MSAT_sect_2nd) == 0:
msat_start_sid = struct.pack('<l', -2)
else:
msat_start_sid = struct.pack('<l', self.MSAT_sect_2nd[0])
total_msat_sectors = struct.pack('<L', len(self.MSAT_sect_2nd))
self.header = ''.join([ doc_magic,
file_uid,
rev_num,
ver_num,
byte_order,
log_sect_size,
log_short_sect_size,
not_used0,
total_sat_sectors,
dir_start_sid,
not_used1,
min_stream_size,
ssat_start_sid,
total_ssat_sectors,
msat_start_sid,
total_msat_sectors
])
def save(self, file_name_or_filelike_obj, stream):
# 1. Align stream on 0x1000 boundary (and therefore on sector boundary)
padding = '\x00' * (0x1000 - (len(stream) % 0x1000))
self.book_stream_len = len(stream) + len(padding)
self.__build_directory()
self.__build_sat()
self.__build_header()
f = file_name_or_filelike_obj
we_own_it = not hasattr(f, 'write')
if we_own_it:
f = open(file_name_or_filelike_obj, 'wb')
f.write(self.header)
f.write(self.packed_MSAT_1st)
f.write(stream)
f.write(padding)
f.write(self.packed_MSAT_2nd)
f.write(self.packed_SAT)
f.write(self.dir_stream)
if we_own_it:
f.close()
-43
View File
@@ -1,43 +0,0 @@
# -*- coding: windows-1252 -*-
import ExcelFormulaParser, ExcelFormulaLexer
import struct
from antlr import ANTLRException
class Formula(object):
__slots__ = ["__init__", "__s", "__parser", "__sheet_refs", "__xcall_refs"]
def __init__(self, s):
try:
self.__s = s
lexer = ExcelFormulaLexer.Lexer(s)
self.__parser = ExcelFormulaParser.Parser(lexer)
self.__parser.formula()
self.__sheet_refs = self.__parser.sheet_references
self.__xcall_refs = self.__parser.xcall_references
except ANTLRException, e:
# print e
raise ExcelFormulaParser.FormulaParseException, "can't parse formula " + s
def get_references(self):
return self.__sheet_refs, self.__xcall_refs
def patch_references(self, patches):
for offset, idx in patches:
self.__parser.rpn = self.__parser.rpn[:offset] + struct.pack('<H', idx) + self.__parser.rpn[offset+2:]
def text(self):
return self.__s
def rpn(self):
'''
Offset Size Contents
0 2 Size of the following formula data (sz)
2 sz Formula data (RPN token array)
[2+sz] var. (optional) Additional data for specific tokens
'''
return struct.pack("<H", len(self.__parser.rpn)) + self.__parser.rpn
-128
View File
@@ -1,128 +0,0 @@
# -*- coding: windows-1252 -*-
import sys
from antlr import EOF, CommonToken as Tok, TokenStream, TokenStreamException
import struct
import ExcelFormulaParser
from re import compile as recompile, match, UNICODE, IGNORECASE, VERBOSE
int_const_pattern = r"\d+\b"
flt_const_pattern = r"""
(?:
(?: \d* \. \d+ ) # .1 .12 .123 etc 9.1 etc 98.1 etc
|
(?: \d+ \. ) # 1. 12. 123. etc
)
# followed by optional exponent part
(?: [Ee] [+-]? \d+ ) ?
"""
str_const_pattern = r'"(?:[^"]|"")*"'
#range2d_pattern = recompile(r"\$?[A-I]?[A-Z]\$?\d+:\$?[A-I]?[A-Z]\$?\d+"
ref2d_r1c1_pattern = r"[Rr]0*[1-9][0-9]*[Cc]0*[1-9][0-9]*"
ref2d_pattern = r"\$?[A-I]?[A-Z]\$?0*[1-9][0-9]*"
true_pattern = r"TRUE\b"
false_pattern = r"FALSE\b"
if_pattern = r"IF\b"
choose_pattern = r"CHOOSE\b"
name_pattern = r"\w[\.\w]*"
quotename_pattern = r"'(?:[^']|'')*'" #### It's essential that this bracket be non-grouping.
ne_pattern = r"<>"
ge_pattern = r">="
le_pattern = r"<="
pattern_type_tuples = (
(flt_const_pattern, ExcelFormulaParser.NUM_CONST),
(int_const_pattern, ExcelFormulaParser.INT_CONST),
(str_const_pattern, ExcelFormulaParser.STR_CONST),
# (range2d_pattern , ExcelFormulaParser.RANGE2D),
(ref2d_r1c1_pattern, ExcelFormulaParser.REF2D_R1C1),
(ref2d_pattern , ExcelFormulaParser.REF2D),
(true_pattern , ExcelFormulaParser.TRUE_CONST),
(false_pattern , ExcelFormulaParser.FALSE_CONST),
(if_pattern , ExcelFormulaParser.FUNC_IF),
(choose_pattern , ExcelFormulaParser.FUNC_CHOOSE),
(name_pattern , ExcelFormulaParser.NAME),
(quotename_pattern, ExcelFormulaParser.QUOTENAME),
(ne_pattern, ExcelFormulaParser.NE),
(ge_pattern, ExcelFormulaParser.GE),
(le_pattern, ExcelFormulaParser.LE),
)
_re = recompile(
'(' + ')|('.join([i[0] for i in pattern_type_tuples]) + ')',
VERBOSE+IGNORECASE)
_toktype = [None] + [i[1] for i in pattern_type_tuples]
# need dummy at start because re.MatchObject.lastindex counts from 1
single_char_lookup = {
'=': ExcelFormulaParser.EQ,
'<': ExcelFormulaParser.LT,
'>': ExcelFormulaParser.GT,
'+': ExcelFormulaParser.ADD,
'-': ExcelFormulaParser.SUB,
'*': ExcelFormulaParser.MUL,
'/': ExcelFormulaParser.DIV,
':': ExcelFormulaParser.COLON,
';': ExcelFormulaParser.SEMICOLON,
',': ExcelFormulaParser.COMMA,
'(': ExcelFormulaParser.LP,
')': ExcelFormulaParser.RP,
'&': ExcelFormulaParser.CONCAT,
'%': ExcelFormulaParser.PERCENT,
'^': ExcelFormulaParser.POWER,
'!': ExcelFormulaParser.BANG,
}
class Lexer(TokenStream):
def __init__(self, text):
self._text = text[:]
self._pos = 0
self._line = 0
def isEOF(self):
return len(self._text) <= self._pos
def curr_ch(self):
return self._text[self._pos]
def next_ch(self, n = 1):
self._pos += n
def is_whitespace(self):
return self.curr_ch() in " \t\n\r\f\v"
def match_pattern(self):
m = _re.match(self._text, self._pos)
if not m:
return None
self._pos = m.end(0)
return Tok(type = _toktype[m.lastindex], text = m.group(0), col = m.start(0) + 1)
def nextToken(self):
# skip whitespace
while not self.isEOF() and self.is_whitespace():
self.next_ch()
if self.isEOF():
return Tok(type = EOF)
# first, try to match token with 2 or more chars
t = self.match_pattern()
if t:
return t
# second, we want 1-char tokens
te = self.curr_ch()
try:
ty = single_char_lookup[te]
except KeyError:
raise TokenStreamException(
"Unexpected char %r in column %u." % (self.curr_ch(), self._pos))
self.next_ch()
return Tok(type=ty, text=te, col=self._pos)
if __name__ == '__main__':
try:
for t in Lexer(""" 1.23 456 "abcd" R2C2 a1 iv65536 true false if choose a_name 'qname' <> >= <= """):
print t
except TokenStreamException, e:
print "error:", e
-677
View File
@@ -1,677 +0,0 @@
### $ANTLR 2.7.7 (20060930): "xlwt/excel-formula.g" -> "ExcelFormulaParser.py"$
### import antlr and other modules ..
import sys
import antlr
version = sys.version.split()[0]
if version < '2.2.1':
False = 0
if version < '2.3':
True = not False
### header action >>>
import struct
import Utils
from UnicodeUtils import upack1
from ExcelMagic import *
_RVAdelta = {"R": 0, "V": 0x20, "A": 0x40}
_RVAdeltaRef = {"R": 0, "V": 0x20, "A": 0x40, "D": 0x20}
_RVAdeltaArea = {"R": 0, "V": 0x20, "A": 0x40, "D": 0}
class FormulaParseException(Exception):
"""
An exception indicating that a Formula could not be successfully parsed.
"""
### header action <<<
### preamble action>>>
### preamble action <<<
### import antlr.Token
from antlr import Token
### >>>The Known Token Types <<<
SKIP = antlr.SKIP
INVALID_TYPE = antlr.INVALID_TYPE
EOF_TYPE = antlr.EOF_TYPE
EOF = antlr.EOF
NULL_TREE_LOOKAHEAD = antlr.NULL_TREE_LOOKAHEAD
MIN_USER_TYPE = antlr.MIN_USER_TYPE
TRUE_CONST = 4
FALSE_CONST = 5
STR_CONST = 6
NUM_CONST = 7
INT_CONST = 8
FUNC_IF = 9
FUNC_CHOOSE = 10
NAME = 11
QUOTENAME = 12
EQ = 13
NE = 14
GT = 15
LT = 16
GE = 17
LE = 18
ADD = 19
SUB = 20
MUL = 21
DIV = 22
POWER = 23
PERCENT = 24
LP = 25
RP = 26
LB = 27
RB = 28
COLON = 29
COMMA = 30
SEMICOLON = 31
REF2D = 32
REF2D_R1C1 = 33
BANG = 34
CONCAT = 35
class Parser(antlr.LLkParser):
### user action >>>
### user action <<<
def __init__(self, *args, **kwargs):
antlr.LLkParser.__init__(self, *args, **kwargs)
self.tokenNames = _tokenNames
### __init__ header action >>>
self.rpn = ""
self.sheet_references = []
self.xcall_references = []
### __init__ header action <<<
def formula(self):
pass
self.expr("V")
def expr(self,
arg_type
):
pass
self.prec0_expr(arg_type)
while True:
if ((self.LA(1) >= EQ and self.LA(1) <= LE)):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [EQ]:
pass
self.match(EQ)
op = struct.pack('B', ptgEQ)
elif la1 and la1 in [NE]:
pass
self.match(NE)
op = struct.pack('B', ptgNE)
elif la1 and la1 in [GT]:
pass
self.match(GT)
op = struct.pack('B', ptgGT)
elif la1 and la1 in [LT]:
pass
self.match(LT)
op = struct.pack('B', ptgLT)
elif la1 and la1 in [GE]:
pass
self.match(GE)
op = struct.pack('B', ptgGE)
elif la1 and la1 in [LE]:
pass
self.match(LE)
op = struct.pack('B', ptgLE)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.prec0_expr(arg_type)
self.rpn += op
else:
break
def prec0_expr(self,
arg_type
):
pass
self.prec1_expr(arg_type)
while True:
if (self.LA(1)==CONCAT):
pass
pass
self.match(CONCAT)
op = struct.pack('B', ptgConcat)
self.prec1_expr(arg_type)
self.rpn += op
else:
break
def prec1_expr(self,
arg_type
):
pass
self.prec2_expr(arg_type)
while True:
if (self.LA(1)==ADD or self.LA(1)==SUB):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [ADD]:
pass
self.match(ADD)
op = struct.pack('B', ptgAdd)
elif la1 and la1 in [SUB]:
pass
self.match(SUB)
op = struct.pack('B', ptgSub)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.prec2_expr(arg_type)
self.rpn += op;
# print "**prec1_expr4 %s" % arg_type
else:
break
def prec2_expr(self,
arg_type
):
pass
self.prec3_expr(arg_type)
while True:
if (self.LA(1)==MUL or self.LA(1)==DIV):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [MUL]:
pass
self.match(MUL)
op = struct.pack('B', ptgMul)
elif la1 and la1 in [DIV]:
pass
self.match(DIV)
op = struct.pack('B', ptgDiv)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.prec3_expr(arg_type)
self.rpn += op
else:
break
def prec3_expr(self,
arg_type
):
pass
self.prec4_expr(arg_type)
while True:
if (self.LA(1)==POWER):
pass
pass
self.match(POWER)
op = struct.pack('B', ptgPower)
self.prec4_expr(arg_type)
self.rpn += op
else:
break
def prec4_expr(self,
arg_type
):
pass
self.prec5_expr(arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [PERCENT]:
pass
self.match(PERCENT)
self.rpn += struct.pack('B', ptgPercent)
elif la1 and la1 in [EOF,EQ,NE,GT,LT,GE,LE,ADD,SUB,MUL,DIV,POWER,RP,COMMA,SEMICOLON,CONCAT]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
def prec5_expr(self,
arg_type
):
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,LP,REF2D]:
pass
self.primary(arg_type)
elif la1 and la1 in [SUB]:
pass
self.match(SUB)
self.primary(arg_type)
self.rpn += struct.pack('B', ptgUminus)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
def primary(self,
arg_type
):
str_tok = None
int_tok = None
num_tok = None
ref2d_tok = None
ref2d1_tok = None
ref2d2_tok = None
ref3d_ref2d = None
ref3d_ref2d2 = None
name_tok = None
func_tok = None
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST]:
pass
self.match(TRUE_CONST)
self.rpn += struct.pack("2B", ptgBool, 1)
elif la1 and la1 in [FALSE_CONST]:
pass
self.match(FALSE_CONST)
self.rpn += struct.pack("2B", ptgBool, 0)
elif la1 and la1 in [STR_CONST]:
pass
str_tok = self.LT(1)
self.match(STR_CONST)
self.rpn += struct.pack("B", ptgStr) + upack1(str_tok.text[1:-1].replace("\"\"", "\""))
elif la1 and la1 in [NUM_CONST]:
pass
num_tok = self.LT(1)
self.match(NUM_CONST)
self.rpn += struct.pack("<Bd", ptgNum, float(num_tok.text))
elif la1 and la1 in [FUNC_IF]:
pass
self.match(FUNC_IF)
self.match(LP)
self.expr("V")
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.rpn += struct.pack("<BBH", ptgAttr, 0x02, 0) # tAttrIf
pos0 = len(self.rpn) - 2
self.expr(arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.rpn += struct.pack("<BBH", ptgAttr, 0x08, 0) # tAttrSkip
pos1 = len(self.rpn) - 2
self.rpn = self.rpn[:pos0] + struct.pack("<H", pos1-pos0) + self.rpn[pos0+2:]
self.expr(arg_type)
self.match(RP)
self.rpn += struct.pack("<BBH", ptgAttr, 0x08, 3) # tAttrSkip
self.rpn += struct.pack("<BBH", ptgFuncVarR, 3, 1) # 3 = nargs, 1 = IF func
pos2 = len(self.rpn)
self.rpn = self.rpn[:pos1] + struct.pack("<H", pos2-(pos1+2)-1) + self.rpn[pos1+2:]
elif la1 and la1 in [FUNC_CHOOSE]:
pass
self.match(FUNC_CHOOSE)
arg_type = "R"
rpn_chunks = []
self.match(LP)
self.expr("V")
rpn_start = len(self.rpn)
ref_markers = [len(self.sheet_references)]
while True:
if (self.LA(1)==COMMA or self.LA(1)==SEMICOLON):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
mark = len(self.rpn)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,SUB,LP,REF2D]:
pass
self.expr(arg_type)
elif la1 and la1 in [RP,COMMA,SEMICOLON]:
pass
self.rpn += struct.pack("B", ptgMissArg)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
rpn_chunks.append(self.rpn[mark:])
ref_markers.append(len(self.sheet_references))
else:
break
self.match(RP)
self.rpn = self.rpn[:rpn_start]
nc = len(rpn_chunks)
chunklens = [len(chunk) for chunk in rpn_chunks]
skiplens = [0] * nc
skiplens[-1] = 3
for ic in xrange(nc-1, 0, -1):
skiplens[ic-1] = skiplens[ic] + chunklens[ic] + 4
jump_pos = [2 * nc + 2]
for ic in xrange(nc):
jump_pos.append(jump_pos[-1] + chunklens[ic] + 4)
chunk_shift = 2 * nc + 6 # size of tAttrChoose
for ic in xrange(nc):
for refx in xrange(ref_markers[ic], ref_markers[ic+1]):
ref = self.sheet_references[refx]
self.sheet_references[refx] = (ref[0], ref[1], ref[2] + chunk_shift)
chunk_shift += 4 # size of tAttrSkip
choose_rpn = []
choose_rpn.append(struct.pack("<BBH", ptgAttr, 0x04, nc)) # 0x04 is tAttrChoose
choose_rpn.append(struct.pack("<%dH" % (nc+1), *jump_pos))
for ic in xrange(nc):
choose_rpn.append(rpn_chunks[ic])
choose_rpn.append(struct.pack("<BBH", ptgAttr, 0x08, skiplens[ic])) # 0x08 is tAttrSkip
choose_rpn.append(struct.pack("<BBH", ptgFuncVarV, nc+1, 100)) # 100 is CHOOSE fn
self.rpn += "".join(choose_rpn)
elif la1 and la1 in [LP]:
pass
self.match(LP)
self.expr(arg_type)
self.match(RP)
self.rpn += struct.pack("B", ptgParen)
else:
if (self.LA(1)==INT_CONST) and (_tokenSet_0.member(self.LA(2))):
pass
int_tok = self.LT(1)
self.match(INT_CONST)
# print "**int_const", int_tok.text
int_value = int(int_tok.text)
if int_value <= 65535:
self.rpn += struct.pack("<BH", ptgInt, int_value)
else:
self.rpn += struct.pack("<Bd", ptgNum, float(int_value))
elif (self.LA(1)==REF2D) and (_tokenSet_0.member(self.LA(2))):
pass
ref2d_tok = self.LT(1)
self.match(REF2D)
# print "**ref2d %s %s" % (ref2d_tok.text, arg_type)
r, c = Utils.cell_to_packed_rowcol(ref2d_tok.text)
ptg = ptgRefR + _RVAdeltaRef[arg_type]
self.rpn += struct.pack("<B2H", ptg, r, c)
elif (self.LA(1)==REF2D) and (self.LA(2)==COLON):
pass
ref2d1_tok = self.LT(1)
self.match(REF2D)
self.match(COLON)
ref2d2_tok = self.LT(1)
self.match(REF2D)
r1, c1 = Utils.cell_to_packed_rowcol(ref2d1_tok.text)
r2, c2 = Utils.cell_to_packed_rowcol(ref2d2_tok.text)
ptg = ptgAreaR + _RVAdeltaArea[arg_type]
self.rpn += struct.pack("<B4H", ptg, r1, r2, c1, c2)
elif (self.LA(1)==INT_CONST or self.LA(1)==NAME or self.LA(1)==QUOTENAME) and (self.LA(2)==COLON or self.LA(2)==BANG):
pass
sheet1=self.sheet()
sheet2 = sheet1
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [COLON]:
pass
self.match(COLON)
sheet2=self.sheet()
elif la1 and la1 in [BANG]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.match(BANG)
ref3d_ref2d = self.LT(1)
self.match(REF2D)
ptg = ptgRef3dR + _RVAdeltaRef[arg_type]
rpn_ref2d = ""
r1, c1 = Utils.cell_to_packed_rowcol(ref3d_ref2d.text)
rpn_ref2d = struct.pack("<3H", 0x0000, r1, c1)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [COLON]:
pass
self.match(COLON)
ref3d_ref2d2 = self.LT(1)
self.match(REF2D)
ptg = ptgArea3dR + _RVAdeltaArea[arg_type]
r2, c2 = Utils.cell_to_packed_rowcol(ref3d_ref2d2.text)
rpn_ref2d = struct.pack("<5H", 0x0000, r1, r2, c1, c2)
elif la1 and la1 in [EOF,EQ,NE,GT,LT,GE,LE,ADD,SUB,MUL,DIV,POWER,PERCENT,RP,COMMA,SEMICOLON,CONCAT]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.rpn += struct.pack("<B", ptg)
self.sheet_references.append((sheet1, sheet2, len(self.rpn)))
self.rpn += rpn_ref2d
elif (self.LA(1)==NAME) and (_tokenSet_0.member(self.LA(2))):
pass
name_tok = self.LT(1)
self.match(NAME)
raise Exception("[formula] found unexpected NAME token (%r)" % name_tok.txt)
# #### TODO: handle references to defined names here
elif (self.LA(1)==NAME) and (self.LA(2)==LP):
pass
func_tok = self.LT(1)
self.match(NAME)
func_toku = func_tok.text.upper()
if func_toku in all_funcs_by_name:
(opcode,
min_argc,
max_argc,
func_type,
arg_type_str) = all_funcs_by_name[func_toku]
arg_type_list = list(arg_type_str)
else:
raise Exception("[formula] unknown function (%s)" % func_tok.text)
# print "**func_tok1 %s %s" % (func_toku, func_type)
xcall = opcode < 0
if xcall:
# The name of the add-in function is passed as the 1st arg
# of the hidden XCALL function
self.xcall_references.append((func_toku, len(self.rpn) + 1))
self.rpn += struct.pack("<BHHH",
ptgNameXR,
0xadde, # ##PATCHME## index to REF entry in EXTERNSHEET record
0xefbe, # ##PATCHME## one-based index to EXTERNNAME record
0x0000) # unused
self.match(LP)
arg_count=self.expr_list(arg_type_list, min_argc, max_argc)
self.match(RP)
if arg_count > max_argc or arg_count < min_argc:
raise Exception, "%d parameters for function: %s" % (arg_count, func_tok.text)
if xcall:
func_ptg = ptgFuncVarR + _RVAdelta[func_type]
self.rpn += struct.pack("<2BH", func_ptg, arg_count + 1, 255) # 255 is magic XCALL function
elif min_argc == max_argc:
func_ptg = ptgFuncR + _RVAdelta[func_type]
self.rpn += struct.pack("<BH", func_ptg, opcode)
elif arg_count == 1 and func_tok.text.upper() == "SUM":
self.rpn += struct.pack("<BBH", ptgAttr, 0x10, 0) # tAttrSum
else:
func_ptg = ptgFuncVarR + _RVAdelta[func_type]
self.rpn += struct.pack("<2BH", func_ptg, arg_count, opcode)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
def sheet(self):
ref = None
sheet_ref_name = None
sheet_ref_int = None
sheet_ref_quote = None
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [NAME]:
pass
sheet_ref_name = self.LT(1)
self.match(NAME)
ref = sheet_ref_name.text
elif la1 and la1 in [INT_CONST]:
pass
sheet_ref_int = self.LT(1)
self.match(INT_CONST)
ref = sheet_ref_int.text
elif la1 and la1 in [QUOTENAME]:
pass
sheet_ref_quote = self.LT(1)
self.match(QUOTENAME)
ref = sheet_ref_quote.text[1:-1].replace("''", "'")
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
return ref
def expr_list(self,
arg_type_list, min_argc, max_argc
):
arg_cnt = None
arg_cnt = 0
arg_type = arg_type_list[arg_cnt]
# print "**expr_list1[%d] req=%s" % (arg_cnt, arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,SUB,LP,REF2D]:
pass
self.expr(arg_type)
arg_cnt += 1
while True:
if (self.LA(1)==COMMA or self.LA(1)==SEMICOLON):
pass
if arg_cnt < len(arg_type_list):
arg_type = arg_type_list[arg_cnt]
else:
arg_type = arg_type_list[-1]
if arg_type == "+":
arg_type = arg_type_list[-2]
# print "**expr_list2[%d] req=%s" % (arg_cnt, arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,SUB,LP,REF2D]:
pass
self.expr(arg_type)
elif la1 and la1 in [RP,COMMA,SEMICOLON]:
pass
self.rpn += struct.pack("B", ptgMissArg)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
arg_cnt += 1
else:
break
elif la1 and la1 in [RP]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
return arg_cnt
_tokenNames = [
"<0>",
"EOF",
"<2>",
"NULL_TREE_LOOKAHEAD",
"TRUE_CONST",
"FALSE_CONST",
"STR_CONST",
"NUM_CONST",
"INT_CONST",
"FUNC_IF",
"FUNC_CHOOSE",
"NAME",
"QUOTENAME",
"EQ",
"NE",
"GT",
"LT",
"GE",
"LE",
"ADD",
"SUB",
"MUL",
"DIV",
"POWER",
"PERCENT",
"LP",
"RP",
"LB",
"RB",
"COLON",
"COMMA",
"SEMICOLON",
"REF2D",
"REF2D_R1C1",
"BANG",
"CONCAT"
]
### generate bit set
def mk_tokenSet_0():
### var1
data = [ 37681618946L, 0L]
return data
_tokenSet_0 = antlr.BitSet(mk_tokenSet_0())
-862
View File
@@ -1,862 +0,0 @@
# -*- coding: ascii -*-
"""
lots of Excel Magic Numbers
"""
# Boundaries BIFF8+
MAX_ROW = 65536
MAX_COL = 256
biff_records = {
0x0000: "DIMENSIONS",
0x0001: "BLANK",
0x0002: "INTEGER",
0x0003: "NUMBER",
0x0004: "LABEL",
0x0005: "BOOLERR",
0x0006: "FORMULA",
0x0007: "STRING",
0x0008: "ROW",
0x0009: "BOF",
0x000A: "EOF",
0x000B: "INDEX",
0x000C: "CALCCOUNT",
0x000D: "CALCMODE",
0x000E: "PRECISION",
0x000F: "REFMODE",
0x0010: "DELTA",
0x0011: "ITERATION",
0x0012: "PROTECT",
0x0013: "PASSWORD",
0x0014: "HEADER",
0x0015: "FOOTER",
0x0016: "EXTERNCOUNT",
0x0017: "EXTERNSHEET",
0x0018: "NAME",
0x0019: "WINDOWPROTECT",
0x001A: "VERTICALPAGEBREAKS",
0x001B: "HORIZONTALPAGEBREAKS",
0x001C: "NOTE",
0x001D: "SELECTION",
0x001E: "FORMAT",
0x001F: "FORMATCOUNT",
0x0020: "COLUMNDEFAULT",
0x0021: "ARRAY",
0x0022: "1904",
0x0023: "EXTERNNAME",
0x0024: "COLWIDTH",
0x0025: "DEFAULTROWHEIGHT",
0x0026: "LEFTMARGIN",
0x0027: "RIGHTMARGIN",
0x0028: "TOPMARGIN",
0x0029: "BOTTOMMARGIN",
0x002A: "PRINTHEADERS",
0x002B: "PRINTGRIDLINES",
0x002F: "FILEPASS",
0x0031: "FONT",
0x0036: "TABLE",
0x003C: "CONTINUE",
0x003D: "WINDOW1",
0x003E: "WINDOW2",
0x0040: "BACKUP",
0x0041: "PANE",
0x0042: "CODEPAGE",
0x0043: "XF",
0x0044: "IXFE",
0x0045: "EFONT",
0x004D: "PLS",
0x0050: "DCON",
0x0051: "DCONREF",
0x0053: "DCONNAME",
0x0055: "DEFCOLWIDTH",
0x0056: "BUILTINFMTCNT",
0x0059: "XCT",
0x005A: "CRN",
0x005B: "FILESHARING",
0x005C: "WRITEACCESS",
0x005D: "OBJ",
0x005E: "UNCALCED",
0x005F: "SAFERECALC",
0x0060: "TEMPLATE",
0x0063: "OBJPROTECT",
0x007D: "COLINFO",
0x007E: "RK",
0x007F: "IMDATA",
0x0080: "GUTS",
0x0081: "WSBOOL",
0x0082: "GRIDSET",
0x0083: "HCENTER",
0x0084: "VCENTER",
0x0085: "BOUNDSHEET",
0x0086: "WRITEPROT",
0x0087: "ADDIN",
0x0088: "EDG",
0x0089: "PUB",
0x008C: "COUNTRY",
0x008D: "HIDEOBJ",
0x008E: "BUNDLESOFFSET",
0x008F: "BUNDLEHEADER",
0x0090: "SORT",
0x0091: "SUB",
0x0092: "PALETTE",
0x0093: "STYLE",
0x0094: "LHRECORD",
0x0095: "LHNGRAPH",
0x0096: "SOUND",
0x0098: "LPR",
0x0099: "STANDARDWIDTH",
0x009A: "FNGROUPNAME",
0x009B: "FILTERMODE",
0x009C: "FNGROUPCOUNT",
0x009D: "AUTOFILTERINFO",
0x009E: "AUTOFILTER",
0x00A0: "SCL",
0x00A1: "SETUP",
0x00A9: "COORDLIST",
0x00AB: "GCW",
0x00AE: "SCENMAN",
0x00AF: "SCENARIO",
0x00B0: "SXVIEW",
0x00B1: "SXVD",
0x00B2: "SXVI",
0x00B4: "SXIVD",
0x00B5: "SXLI",
0x00B6: "SXPI",
0x00B8: "DOCROUTE",
0x00B9: "RECIPNAME",
0x00BC: "SHRFMLA",
0x00BD: "MULRK",
0x00BE: "MULBLANK",
0x00C1: "MMS",
0x00C2: "ADDMENU",
0x00C3: "DELMENU",
0x00C5: "SXDI",
0x00C6: "SXDB",
0x00C7: "SXFIELD",
0x00C8: "SXINDEXLIST",
0x00C9: "SXDOUBLE",
0x00CD: "SXSTRING",
0x00CE: "SXDATETIME",
0x00D0: "SXTBL",
0x00D1: "SXTBRGITEM",
0x00D2: "SXTBPG",
0x00D3: "OBPROJ",
0x00D5: "SXIDSTM",
0x00D6: "RSTRING",
0x00D7: "DBCELL",
0x00DA: "BOOKBOOL",
0x00DC: "SXEXT|PARAMQRY",
0x00DD: "SCENPROTECT",
0x00DE: "OLESIZE",
0x00DF: "UDDESC",
0x00E0: "XF",
0x00E1: "INTERFACEHDR",
0x00E2: "INTERFACEEND",
0x00E3: "SXVS",
0x00E5: "MERGEDCELLS",
0x00E9: "BITMAP",
0x00EB: "MSODRAWINGGROUP",
0x00EC: "MSODRAWING",
0x00ED: "MSODRAWINGSELECTION",
0x00F0: "SXRULE",
0x00F1: "SXEX",
0x00F2: "SXFILT",
0x00F6: "SXNAME",
0x00F7: "SXSELECT",
0x00F8: "SXPAIR",
0x00F9: "SXFMLA",
0x00FB: "SXFORMAT",
0x00FC: "SST",
0x00FD: "LABELSST",
0x00FF: "EXTSST",
0x0100: "SXVDEX",
0x0103: "SXFORMULA",
0x0122: "SXDBEX",
0x0137: "CHTRINSERT",
0x0138: "CHTRINFO",
0x013B: "CHTRCELLCONTENT",
0x013D: "TABID",
0x0140: "CHTRMOVERANGE",
0x014D: "CHTRINSERTTAB",
0x015F: "LABELRANGES",
0x0160: "USESELFS",
0x0161: "DSF",
0x0162: "XL5MODIFY",
0x0196: "CHTRHEADER",
0x01A9: "USERBVIEW",
0x01AA: "USERSVIEWBEGIN",
0x01AB: "USERSVIEWEND",
0x01AD: "QSI",
0x01AE: "SUPBOOK",
0x01AF: "PROT4REV",
0x01B0: "CONDFMT",
0x01B1: "CF",
0x01B2: "DVAL",
0x01B5: "DCONBIN",
0x01B6: "TXO",
0x01B7: "REFRESHALL",
0x01B8: "HLINK",
0x01BA: "CODENAME",
0x01BB: "SXFDBTYPE",
0x01BC: "PROT4REVPASS",
0x01BE: "DV",
0x01C0: "XL9FILE",
0x01C1: "RECALCID",
0x0200: "DIMENSIONS",
0x0201: "BLANK",
0x0203: "NUMBER",
0x0204: "LABEL",
0x0205: "BOOLERR",
0x0206: "FORMULA",
0x0207: "STRING",
0x0208: "ROW",
0x0209: "BOF",
0x020B: "INDEX",
0x0218: "NAME",
0x0221: "ARRAY",
0x0223: "EXTERNNAME",
0x0225: "DEFAULTROWHEIGHT",
0x0231: "FONT",
0x0236: "TABLE",
0x023E: "WINDOW2",
0x0243: "XF",
0x027E: "RK",
0x0293: "STYLE",
0x0406: "FORMULA",
0x0409: "BOF",
0x041E: "FORMAT",
0x0443: "XF",
0x04BC: "SHRFMLA",
0x0800: "SCREENTIP",
0x0803: "WEBQRYSETTINGS",
0x0804: "WEBQRYTABLES",
0x0809: "BOF",
0x0862: "SHEETLAYOUT",
0x0867: "SHEETPROTECTION",
0x1001: "UNITS",
0x1002: "ChartChart",
0x1003: "ChartSeries",
0x1006: "ChartDataformat",
0x1007: "ChartLineformat",
0x1009: "ChartMarkerformat",
0x100A: "ChartAreaformat",
0x100B: "ChartPieformat",
0x100C: "ChartAttachedlabel",
0x100D: "ChartSeriestext",
0x1014: "ChartChartformat",
0x1015: "ChartLegend",
0x1016: "ChartSerieslist",
0x1017: "ChartBar",
0x1018: "ChartLine",
0x1019: "ChartPie",
0x101A: "ChartArea",
0x101B: "ChartScatter",
0x101C: "ChartChartline",
0x101D: "ChartAxis",
0x101E: "ChartTick",
0x101F: "ChartValuerange",
0x1020: "ChartCatserrange",
0x1021: "ChartAxislineformat",
0x1022: "ChartFormatlink",
0x1024: "ChartDefaulttext",
0x1025: "ChartText",
0x1026: "ChartFontx",
0x1027: "ChartObjectLink",
0x1032: "ChartFrame",
0x1033: "BEGIN",
0x1034: "END",
0x1035: "ChartPlotarea",
0x103A: "Chart3D",
0x103C: "ChartPicf",
0x103D: "ChartDropbar",
0x103E: "ChartRadar",
0x103F: "ChartSurface",
0x1040: "ChartRadararea",
0x1041: "ChartAxisparent",
0x1043: "ChartLegendxn",
0x1044: "ChartShtprops",
0x1045: "ChartSertocrt",
0x1046: "ChartAxesused",
0x1048: "ChartSbaseref",
0x104A: "ChartSerparent",
0x104B: "ChartSerauxtrend",
0x104E: "ChartIfmt",
0x104F: "ChartPos",
0x1050: "ChartAlruns",
0x1051: "ChartAI",
0x105B: "ChartSerauxerrbar",
0x105D: "ChartSerfmt",
0x105F: "Chart3DDataFormat",
0x1060: "ChartFbi",
0x1061: "ChartBoppop",
0x1062: "ChartAxcext",
0x1063: "ChartDat",
0x1064: "ChartPlotgrowth",
0x1065: "ChartSiindex",
0x1066: "ChartGelframe",
0x1067: "ChartBoppcustom",
0xFFFF: ""
}
all_funcs_by_name = {
# Includes Analysis ToolPak aka ATP aka add-in aka xcall functions,
# distinguished by -ve opcode.
# name: (opcode, min # args, max # args, func return type, func arg types)
# + in func arg types means more of the same.
'ABS' : ( 24, 1, 1, 'V', 'V'),
'ACCRINT' : ( -1, 6, 7, 'V', 'VVVVVVV'),
'ACCRINTM' : ( -1, 3, 5, 'V', 'VVVVV'),
'ACOS' : ( 99, 1, 1, 'V', 'V'),
'ACOSH' : (233, 1, 1, 'V', 'V'),
'ADDRESS' : (219, 2, 5, 'V', 'VVVVV'),
'AMORDEGRC' : ( -1, 7, 7, 'V', 'VVVVVVV'),
'AMORLINC' : ( -1, 7, 7, 'V', 'VVVVVVV'),
'AND' : ( 36, 1, 30, 'V', 'D+'),
'AREAS' : ( 75, 1, 1, 'V', 'R'),
'ASC' : (214, 1, 1, 'V', 'V'),
'ASIN' : ( 98, 1, 1, 'V', 'V'),
'ASINH' : (232, 1, 1, 'V', 'V'),
'ATAN' : ( 18, 1, 1, 'V', 'V'),
'ATAN2' : ( 97, 2, 2, 'V', 'VV'),
'ATANH' : (234, 1, 1, 'V', 'V'),
'AVEDEV' : (269, 1, 30, 'V', 'D+'),
'AVERAGE' : ( 5, 1, 30, 'V', 'D+'),
'AVERAGEA' : (361, 1, 30, 'V', 'D+'),
'BAHTTEXT' : (368, 1, 1, 'V', 'V'),
'BESSELI' : ( -1, 2, 2, 'V', 'VV'),
'BESSELJ' : ( -1, 2, 2, 'V', 'VV'),
'BESSELK' : ( -1, 2, 2, 'V', 'VV'),
'BESSELY' : ( -1, 2, 2, 'V', 'VV'),
'BETADIST' : (270, 3, 5, 'V', 'VVVVV'),
'BETAINV' : (272, 3, 5, 'V', 'VVVVV'),
'BIN2DEC' : ( -1, 1, 1, 'V', 'V'),
'BIN2HEX' : ( -1, 1, 2, 'V', 'VV'),
'BIN2OCT' : ( -1, 1, 2, 'V', 'VV'),
'BINOMDIST' : (273, 4, 4, 'V', 'VVVV'),
'CEILING' : (288, 2, 2, 'V', 'VV'),
'CELL' : (125, 1, 2, 'V', 'VR'),
'CHAR' : (111, 1, 1, 'V', 'V'),
'CHIDIST' : (274, 2, 2, 'V', 'VV'),
'CHIINV' : (275, 2, 2, 'V', 'VV'),
'CHITEST' : (306, 2, 2, 'V', 'AA'),
'CHOOSE' : (100, 2, 30, 'R', 'VR+'),
'CLEAN' : (162, 1, 1, 'V', 'V'),
'CODE' : (121, 1, 1, 'V', 'V'),
'COLUMN' : ( 9, 0, 1, 'V', 'R'),
'COLUMNS' : ( 77, 1, 1, 'V', 'R'),
'COMBIN' : (276, 2, 2, 'V', 'VV'),
'COMPLEX' : ( -1, 2, 3, 'V', 'VVV'),
'CONCATENATE' : (336, 1, 30, 'V', 'V+'),
'CONFIDENCE' : (277, 3, 3, 'V', 'VVV'),
'CONVERT' : ( -1, 3, 3, 'V', 'VVV'),
'CORREL' : (307, 2, 2, 'V', 'AA'),
'COS' : ( 16, 1, 1, 'V', 'V'),
'COSH' : (230, 1, 1, 'V', 'V'),
'COUNT' : ( 0, 1, 30, 'V', 'D+'),
'COUNTA' : (169, 1, 30, 'V', 'D+'),
'COUNTBLANK' : (347, 1, 1, 'V', 'R'),
'COUNTIF' : (346, 2, 2, 'V', 'RV'),
'COUPDAYBS' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPDAYS' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPDAYSNC' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPNCD' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPNUM' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPPCD' : ( -1, 3, 5, 'V', 'VVVVV'),
'COVAR' : (308, 2, 2, 'V', 'AA'),
'CRITBINOM' : (278, 3, 3, 'V', 'VVV'),
'CUMIPMT' : ( -1, 6, 6, 'V', 'VVVVVV'),
'CUMPRINC' : ( -1, 6, 6, 'V', 'VVVVVV'),
'DATE' : ( 65, 3, 3, 'V', 'VVV'),
'DATEDIF' : (351, 3, 3, 'V', 'VVV'),
'DATEVALUE' : (140, 1, 1, 'V', 'V'),
'DAVERAGE' : ( 42, 3, 3, 'V', 'RRR'),
'DAY' : ( 67, 1, 1, 'V', 'V'),
'DAYS360' : (220, 2, 3, 'V', 'VVV'),
'DB' : (247, 4, 5, 'V', 'VVVVV'),
'DBCS' : (215, 1, 1, 'V', 'V'),
'DCOUNT' : ( 40, 3, 3, 'V', 'RRR'),
'DCOUNTA' : (199, 3, 3, 'V', 'RRR'),
'DDB' : (144, 4, 5, 'V', 'VVVVV'),
'DEC2BIN' : ( -1, 1, 2, 'V', 'VV'),
'DEC2HEX' : ( -1, 1, 2, 'V', 'VV'),
'DEC2OCT' : ( -1, 1, 2, 'V', 'VV'),
'DEGREES' : (343, 1, 1, 'V', 'V'),
'DELTA' : ( -1, 1, 2, 'V', 'VV'),
'DEVSQ' : (318, 1, 30, 'V', 'D+'),
'DGET' : (235, 3, 3, 'V', 'RRR'),
'DISC' : ( -1, 4, 5, 'V', 'VVVVV'),
'DMAX' : ( 44, 3, 3, 'V', 'RRR'),
'DMIN' : ( 43, 3, 3, 'V', 'RRR'),
'DOLLAR' : ( 13, 1, 2, 'V', 'VV'),
'DOLLARDE' : ( -1, 2, 2, 'V', 'VV'),
'DOLLARFR' : ( -1, 2, 2, 'V', 'VV'),
'DPRODUCT' : (189, 3, 3, 'V', 'RRR'),
'DSTDEV' : ( 45, 3, 3, 'V', 'RRR'),
'DSTDEVP' : (195, 3, 3, 'V', 'RRR'),
'DSUM' : ( 41, 3, 3, 'V', 'RRR'),
'DURATION' : ( -1, 5, 6, 'V', 'VVVVVV'),
'DVAR' : ( 47, 3, 3, 'V', 'RRR'),
'DVARP' : (196, 3, 3, 'V', 'RRR'),
'EDATE' : ( -1, 2, 2, 'V', 'VV'),
'EFFECT' : ( -1, 2, 2, 'V', 'VV'),
'EOMONTH' : ( -1, 1, 2, 'V', 'VV'),
'ERF' : ( -1, 1, 2, 'V', 'VV'),
'ERFC' : ( -1, 1, 1, 'V', 'V'),
'ERROR.TYPE' : (261, 1, 1, 'V', 'V'),
'EVEN' : (279, 1, 1, 'V', 'V'),
'EXACT' : (117, 2, 2, 'V', 'VV'),
'EXP' : ( 21, 1, 1, 'V', 'V'),
'EXPONDIST' : (280, 3, 3, 'V', 'VVV'),
'FACT' : (184, 1, 1, 'V', 'V'),
'FACTDOUBLE' : ( -1, 1, 1, 'V', 'V'),
'FALSE' : ( 35, 0, 0, 'V', '-'),
'FDIST' : (281, 3, 3, 'V', 'VVV'),
'FIND' : (124, 2, 3, 'V', 'VVV'),
'FINDB' : (205, 2, 3, 'V', 'VVV'),
'FINV' : (282, 3, 3, 'V', 'VVV'),
'FISHER' : (283, 1, 1, 'V', 'V'),
'FISHERINV' : (284, 1, 1, 'V', 'V'),
'FIXED' : ( 14, 2, 3, 'V', 'VVV'),
'FLOOR' : (285, 2, 2, 'V', 'VV'),
'FORECAST' : (309, 3, 3, 'V', 'VAA'),
'FREQUENCY' : (252, 2, 2, 'A', 'RR'),
'FTEST' : (310, 2, 2, 'V', 'AA'),
'FV' : ( 57, 3, 5, 'V', 'VVVVV'),
'FVSCHEDULE' : ( -1, 2, 2, 'V', 'VA'),
'GAMMADIST' : (286, 4, 4, 'V', 'VVVV'),
'GAMMAINV' : (287, 3, 3, 'V', 'VVV'),
'GAMMALN' : (271, 1, 1, 'V', 'V'),
'GCD' : ( -1, 1, 29, 'V', 'V+'),
'GEOMEAN' : (319, 1, 30, 'V', 'D+'),
'GESTEP' : ( -1, 1, 2, 'V', 'VV'),
'GETPIVOTDATA': (358, 2, 30, 'A', 'VAV+'),
'GROWTH' : ( 52, 1, 4, 'A', 'RRRV'),
'HARMEAN' : (320, 1, 30, 'V', 'D+'),
'HEX2BIN' : ( -1, 1, 2, 'V', 'VV'),
'HEX2DEC' : ( -1, 1, 1, 'V', 'V'),
'HEX2OCT' : ( -1, 1, 2, 'V', 'VV'),
'HLOOKUP' : (101, 3, 4, 'V', 'VRRV'),
'HOUR' : ( 71, 1, 1, 'V', 'V'),
'HYPERLINK' : (359, 1, 2, 'V', 'VV'),
'HYPGEOMDIST' : (289, 4, 4, 'V', 'VVVV'),
'IF' : ( 1, 2, 3, 'R', 'VRR'),
'IMABS' : ( -1, 1, 1, 'V', 'V'),
'IMAGINARY' : ( -1, 1, 1, 'V', 'V'),
'IMARGUMENT' : ( -1, 1, 1, 'V', 'V'),
'IMCONJUGATE' : ( -1, 1, 1, 'V', 'V'),
'IMCOS' : ( -1, 1, 1, 'V', 'V'),
'IMDIV' : ( -1, 2, 2, 'V', 'VV'),
'IMEXP' : ( -1, 1, 1, 'V', 'V'),
'IMLN' : ( -1, 1, 1, 'V', 'V'),
'IMLOG10' : ( -1, 1, 1, 'V', 'V'),
'IMLOG2' : ( -1, 1, 1, 'V', 'V'),
'IMPOWER' : ( -1, 2, 2, 'V', 'VV'),
'IMPRODUCT' : ( -1, 2, 2, 'V', 'VV'),
'IMREAL' : ( -1, 1, 1, 'V', 'V'),
'IMSIN' : ( -1, 1, 1, 'V', 'V'),
'IMSQRT' : ( -1, 1, 1, 'V', 'V'),
'IMSUB' : ( -1, 2, 2, 'V', 'VV'),
'IMSUM' : ( -1, 1, 29, 'V', 'V+'),
'INDEX' : ( 29, 2, 4, 'R', 'RVVV'),
'INDIRECT' : (148, 1, 2, 'R', 'VV'),
'INFO' : (244, 1, 1, 'V', 'V'),
'INT' : ( 25, 1, 1, 'V', 'V'),
'INTERCEPT' : (311, 2, 2, 'V', 'AA'),
'INTRATE' : ( -1, 4, 5, 'V', 'VVVVV'),
'IPMT' : (167, 4, 6, 'V', 'VVVVVV'),
'IRR' : ( 62, 1, 2, 'V', 'RV'),
'ISBLANK' : (129, 1, 1, 'V', 'V'),
'ISERR' : (126, 1, 1, 'V', 'V'),
'ISERROR' : ( 3, 1, 1, 'V', 'V'),
'ISEVEN' : ( -1, 1, 1, 'V', 'V'),
'ISLOGICAL' : (198, 1, 1, 'V', 'V'),
'ISNA' : ( 2, 1, 1, 'V', 'V'),
'ISNONTEXT' : (190, 1, 1, 'V', 'V'),
'ISNUMBER' : (128, 1, 1, 'V', 'V'),
'ISODD' : ( -1, 1, 1, 'V', 'V'),
'ISPMT' : (350, 4, 4, 'V', 'VVVV'),
'ISREF' : (105, 1, 1, 'V', 'R'),
'ISTEXT' : (127, 1, 1, 'V', 'V'),
'KURT' : (322, 1, 30, 'V', 'D+'),
'LARGE' : (325, 2, 2, 'V', 'RV'),
'LCM' : ( -1, 1, 29, 'V', 'V+'),
'LEFT' : (115, 1, 2, 'V', 'VV'),
'LEFTB' : (208, 1, 2, 'V', 'VV'),
'LEN' : ( 32, 1, 1, 'V', 'V'),
'LENB' : (211, 1, 1, 'V', 'V'),
'LINEST' : ( 49, 1, 4, 'A', 'RRVV'),
'LN' : ( 22, 1, 1, 'V', 'V'),
'LOG' : (109, 1, 2, 'V', 'VV'),
'LOG10' : ( 23, 1, 1, 'V', 'V'),
'LOGEST' : ( 51, 1, 4, 'A', 'RRVV'),
'LOGINV' : (291, 3, 3, 'V', 'VVV'),
'LOGNORMDIST' : (290, 3, 3, 'V', 'VVV'),
'LOOKUP' : ( 28, 2, 3, 'V', 'VRR'),
'LOWER' : (112, 1, 1, 'V', 'V'),
'MATCH' : ( 64, 2, 3, 'V', 'VRR'),
'MAX' : ( 7, 1, 30, 'V', 'D+'),
'MAXA' : (362, 1, 30, 'V', 'D+'),
'MDETERM' : (163, 1, 1, 'V', 'A'),
'MDURATION' : ( -1, 5, 6, 'V', 'VVVVVV'),
'MEDIAN' : (227, 1, 30, 'V', 'D+'),
'MID' : ( 31, 3, 3, 'V', 'VVV'),
'MIDB' : (210, 3, 3, 'V', 'VVV'),
'MIN' : ( 6, 1, 30, 'V', 'D+'),
'MINA' : (363, 1, 30, 'V', 'D+'),
'MINUTE' : ( 72, 1, 1, 'V', 'V'),
'MINVERSE' : (164, 1, 1, 'A', 'A'),
'MIRR' : ( 61, 3, 3, 'V', 'RVV'),
'MMULT' : (165, 2, 2, 'A', 'AA'),
'MOD' : ( 39, 2, 2, 'V', 'VV'),
'MODE' : (330, 1, 30, 'V', 'A+'), ################ weird #################
'MONTH' : ( 68, 1, 1, 'V', 'V'),
'MROUND' : ( -1, 2, 2, 'V', 'VV'),
'MULTINOMIAL' : ( -1, 1, 29, 'V', 'V+'),
'N' : (131, 1, 1, 'V', 'R'),
'NA' : ( 10, 0, 0, 'V', '-'),
'NEGBINOMDIST': (292, 3, 3, 'V', 'VVV'),
'NETWORKDAYS' : ( -1, 2, 3, 'V', 'VVR'),
'NOMINAL' : ( -1, 2, 2, 'V', 'VV'),
'NORMDIST' : (293, 4, 4, 'V', 'VVVV'),
'NORMINV' : (295, 3, 3, 'V', 'VVV'),
'NORMSDIST' : (294, 1, 1, 'V', 'V'),
'NORMSINV' : (296, 1, 1, 'V', 'V'),
'NOT' : ( 38, 1, 1, 'V', 'V'),
'NOW' : ( 74, 0, 0, 'V', '-'),
'NPER' : ( 58, 3, 5, 'V', 'VVVVV'),
'NPV' : ( 11, 2, 30, 'V', 'VD+'),
'OCT2BIN' : ( -1, 1, 2, 'V', 'VV'),
'OCT2DEC' : ( -1, 1, 1, 'V', 'V'),
'OCT2HEX' : ( -1, 1, 2, 'V', 'VV'),
'ODD' : (298, 1, 1, 'V', 'V'),
'ODDFPRICE' : ( -1, 9, 9, 'V', 'VVVVVVVVV'),
'ODDFYIELD' : ( -1, 9, 9, 'V', 'VVVVVVVVV'),
'ODDLPRICE' : ( -1, 8, 8, 'V', 'VVVVVVVV'),
'ODDLYIELD' : ( -1, 8, 8, 'V', 'VVVVVVVV'),
'OFFSET' : ( 78, 3, 5, 'R', 'RVVVV'),
'OR' : ( 37, 1, 30, 'V', 'D+'),
'PEARSON' : (312, 2, 2, 'V', 'AA'),
'PERCENTILE' : (328, 2, 2, 'V', 'RV'),
'PERCENTRANK' : (329, 2, 3, 'V', 'RVV'),
'PERMUT' : (299, 2, 2, 'V', 'VV'),
'PHONETIC' : (360, 1, 1, 'V', 'R'),
'PI' : ( 19, 0, 0, 'V', '-'),
'PMT' : ( 59, 3, 5, 'V', 'VVVVV'),
'POISSON' : (300, 3, 3, 'V', 'VVV'),
'POWER' : (337, 2, 2, 'V', 'VV'),
'PPMT' : (168, 4, 6, 'V', 'VVVVVV'),
'PRICE' : ( -1, 6, 7, 'V', 'VVVVVVV'),
'PRICEDISC' : ( -1, 4, 5, 'V', 'VVVVV'),
'PRICEMAT' : ( -1, 5, 6, 'V', 'VVVVVV'),
'PROB' : (317, 3, 4, 'V', 'AAVV'),
'PRODUCT' : (183, 1, 30, 'V', 'D+'),
'PROPER' : (114, 1, 1, 'V', 'V'),
'PV' : ( 56, 3, 5, 'V', 'VVVVV'),
'QUARTILE' : (327, 2, 2, 'V', 'RV'),
'QUOTIENT' : ( -1, 2, 2, 'V', 'VV'),
'RADIANS' : (342, 1, 1, 'V', 'V'),
'RAND' : ( 63, 0, 0, 'V', '-'),
'RANDBETWEEN' : ( -1, 2, 2, 'V', 'VV'),
'RANK' : (216, 2, 3, 'V', 'VRV'),
'RATE' : ( 60, 3, 6, 'V', 'VVVVVV'),
'RECEIVED' : ( -1, 4, 5, 'V', 'VVVVV'),
'REPLACE' : (119, 4, 4, 'V', 'VVVV'),
'REPLACEB' : (207, 4, 4, 'V', 'VVVV'),
'REPT' : ( 30, 2, 2, 'V', 'VV'),
'RIGHT' : (116, 1, 2, 'V', 'VV'),
'RIGHTB' : (209, 1, 2, 'V', 'VV'),
'ROMAN' : (354, 1, 2, 'V', 'VV'),
'ROUND' : ( 27, 2, 2, 'V', 'VV'),
'ROUNDDOWN' : (213, 2, 2, 'V', 'VV'),
'ROUNDUP' : (212, 2, 2, 'V', 'VV'),
'ROW' : ( 8, 0, 1, 'V', 'R'),
'ROWS' : ( 76, 1, 1, 'V', 'R'),
'RSQ' : (313, 2, 2, 'V', 'AA'),
'RTD' : (379, 3, 30, 'A', 'VVV+'),
'SEARCH' : ( 82, 2, 3, 'V', 'VVV'),
'SEARCHB' : (206, 2, 3, 'V', 'VVV'),
'SECOND' : ( 73, 1, 1, 'V', 'V'),
'SERIESSUM' : ( -1, 4, 4, 'V', 'VVVA'),
'SIGN' : ( 26, 1, 1, 'V', 'V'),
'SIN' : ( 15, 1, 1, 'V', 'V'),
'SINH' : (229, 1, 1, 'V', 'V'),
'SKEW' : (323, 1, 30, 'V', 'D+'),
'SLN' : (142, 3, 3, 'V', 'VVV'),
'SLOPE' : (315, 2, 2, 'V', 'AA'),
'SMALL' : (326, 2, 2, 'V', 'RV'),
'SQRT' : ( 20, 1, 1, 'V', 'V'),
'SQRTPI' : ( -1, 1, 1, 'V', 'V'),
'STANDARDIZE' : (297, 3, 3, 'V', 'VVV'),
'STDEV' : ( 12, 1, 30, 'V', 'D+'),
'STDEVA' : (366, 1, 30, 'V', 'D+'),
'STDEVP' : (193, 1, 30, 'V', 'D+'),
'STDEVPA' : (364, 1, 30, 'V', 'D+'),
'STEYX' : (314, 2, 2, 'V', 'AA'),
'SUBSTITUTE' : (120, 3, 4, 'V', 'VVVV'),
'SUBTOTAL' : (344, 2, 30, 'V', 'VR+'),
'SUM' : ( 4, 1, 30, 'V', 'D+'),
'SUMIF' : (345, 2, 3, 'V', 'RVR'),
'SUMPRODUCT' : (228, 1, 30, 'V', 'A+'),
'SUMSQ' : (321, 1, 30, 'V', 'D+'),
'SUMX2MY2' : (304, 2, 2, 'V', 'AA'),
'SUMX2PY2' : (305, 2, 2, 'V', 'AA'),
'SUMXMY2' : (303, 2, 2, 'V', 'AA'),
'SYD' : (143, 4, 4, 'V', 'VVVV'),
'T' : (130, 1, 1, 'V', 'R'),
'TAN' : ( 17, 1, 1, 'V', 'V'),
'TANH' : (231, 1, 1, 'V', 'V'),
'TBILLEQ' : ( -1, 3, 3, 'V', 'VVV'),
'TBILLPRICE' : ( -1, 3, 3, 'V', 'VVV'),
'TBILLYIELD' : ( -1, 3, 3, 'V', 'VVV'),
'TDIST' : (301, 3, 3, 'V', 'VVV'),
'TEXT' : ( 48, 2, 2, 'V', 'VV'),
'TIME' : ( 66, 3, 3, 'V', 'VVV'),
'TIMEVALUE' : (141, 1, 1, 'V', 'V'),
'TINV' : (332, 2, 2, 'V', 'VV'),
'TODAY' : (221, 0, 0, 'V', '-'),
'TRANSPOSE' : ( 83, 1, 1, 'A', 'A'),
'TREND' : ( 50, 1, 4, 'A', 'RRRV'),
'TRIM' : (118, 1, 1, 'V', 'V'),
'TRIMMEAN' : (331, 2, 2, 'V', 'RV'),
'TRUE' : ( 34, 0, 0, 'V', '-'),
'TRUNC' : (197, 1, 2, 'V', 'VV'),
'TTEST' : (316, 4, 4, 'V', 'AAVV'),
'TYPE' : ( 86, 1, 1, 'V', 'V'),
'UPPER' : (113, 1, 1, 'V', 'V'),
'USDOLLAR' : (204, 1, 2, 'V', 'VV'),
'VALUE' : ( 33, 1, 1, 'V', 'V'),
'VAR' : ( 46, 1, 30, 'V', 'D+'),
'VARA' : (367, 1, 30, 'V', 'D+'),
'VARP' : (194, 1, 30, 'V', 'D+'),
'VARPA' : (365, 1, 30, 'V', 'D+'),
'VDB' : (222, 5, 7, 'V', 'VVVVVVV'),
'VLOOKUP' : (102, 3, 4, 'V', 'VRRV'),
'WEEKDAY' : ( 70, 1, 2, 'V', 'VV'),
'WEEKNUM' : ( -1, 1, 2, 'V', 'VV'),
'WEIBULL' : (302, 4, 4, 'V', 'VVVV'),
'WORKDAY' : ( -1, 2, 3, 'V', 'VVR'),
'XIRR' : ( -1, 2, 3, 'V', 'AAV'),
'XNPV' : ( -1, 3, 3, 'V', 'VAA'),
'YEAR' : ( 69, 1, 1, 'V', 'V'),
'YEARFRAC' : ( -1, 2, 3, 'V', 'VVV'),
'YIELD' : ( -1, 6, 7, 'V', 'VVVVVVV'),
'YIELDDISC' : ( -1, 4, 5, 'V', 'VVVVV'),
'YIELDMAT' : ( -1, 5, 6, 'V', 'VVVVVV'),
'ZTEST' : (324, 2, 3, 'V', 'RVV'),
}
# Formulas Parse things
ptgExp = 0x01
ptgTbl = 0x02
ptgAdd = 0x03
ptgSub = 0x04
ptgMul = 0x05
ptgDiv = 0x06
ptgPower = 0x07
ptgConcat = 0x08
ptgLT = 0x09
ptgLE = 0x0a
ptgEQ = 0x0b
ptgGE = 0x0c
ptgGT = 0x0d
ptgNE = 0x0e
ptgIsect = 0x0f
ptgUnion = 0x10
ptgRange = 0x11
ptgUplus = 0x12
ptgUminus = 0x13
ptgPercent = 0x14
ptgParen = 0x15
ptgMissArg = 0x16
ptgStr = 0x17
ptgExtend = 0x18
ptgAttr = 0x19
ptgSheet = 0x1a
ptgEndSheet = 0x1b
ptgErr = 0x1c
ptgBool = 0x1d
ptgInt = 0x1e
ptgNum = 0x1f
ptgArrayR = 0x20
ptgFuncR = 0x21
ptgFuncVarR = 0x22
ptgNameR = 0x23
ptgRefR = 0x24
ptgAreaR = 0x25
ptgMemAreaR = 0x26
ptgMemErrR = 0x27
ptgMemNoMemR = 0x28
ptgMemFuncR = 0x29
ptgRefErrR = 0x2a
ptgAreaErrR = 0x2b
ptgRefNR = 0x2c
ptgAreaNR = 0x2d
ptgMemAreaNR = 0x2e
ptgMemNoMemNR = 0x2f
ptgNameXR = 0x39
ptgRef3dR = 0x3a
ptgArea3dR = 0x3b
ptgRefErr3dR = 0x3c
ptgAreaErr3dR = 0x3d
ptgArrayV = 0x40
ptgFuncV = 0x41
ptgFuncVarV = 0x42
ptgNameV = 0x43
ptgRefV = 0x44
ptgAreaV = 0x45
ptgMemAreaV = 0x46
ptgMemErrV = 0x47
ptgMemNoMemV = 0x48
ptgMemFuncV = 0x49
ptgRefErrV = 0x4a
ptgAreaErrV = 0x4b
ptgRefNV = 0x4c
ptgAreaNV = 0x4d
ptgMemAreaNV = 0x4e
ptgMemNoMemNV = 0x4f
ptgFuncCEV = 0x58
ptgNameXV = 0x59
ptgRef3dV = 0x5a
ptgArea3dV = 0x5b
ptgRefErr3dV = 0x5c
ptgAreaErr3dV = 0x5d
ptgArrayA = 0x60
ptgFuncA = 0x61
ptgFuncVarA = 0x62
ptgNameA = 0x63
ptgRefA = 0x64
ptgAreaA = 0x65
ptgMemAreaA = 0x66
ptgMemErrA = 0x67
ptgMemNoMemA = 0x68
ptgMemFuncA = 0x69
ptgRefErrA = 0x6a
ptgAreaErrA = 0x6b
ptgRefNA = 0x6c
ptgAreaNA = 0x6d
ptgMemAreaNA = 0x6e
ptgMemNoMemNA = 0x6f
ptgFuncCEA = 0x78
ptgNameXA = 0x79
ptgRef3dA = 0x7a
ptgArea3dA = 0x7b
ptgRefErr3dA = 0x7c
ptgAreaErr3dA = 0x7d
PtgNames = {
ptgExp : "ptgExp",
ptgTbl : "ptgTbl",
ptgAdd : "ptgAdd",
ptgSub : "ptgSub",
ptgMul : "ptgMul",
ptgDiv : "ptgDiv",
ptgPower : "ptgPower",
ptgConcat : "ptgConcat",
ptgLT : "ptgLT",
ptgLE : "ptgLE",
ptgEQ : "ptgEQ",
ptgGE : "ptgGE",
ptgGT : "ptgGT",
ptgNE : "ptgNE",
ptgIsect : "ptgIsect",
ptgUnion : "ptgUnion",
ptgRange : "ptgRange",
ptgUplus : "ptgUplus",
ptgUminus : "ptgUminus",
ptgPercent : "ptgPercent",
ptgParen : "ptgParen",
ptgMissArg : "ptgMissArg",
ptgStr : "ptgStr",
ptgExtend : "ptgExtend",
ptgAttr : "ptgAttr",
ptgSheet : "ptgSheet",
ptgEndSheet : "ptgEndSheet",
ptgErr : "ptgErr",
ptgBool : "ptgBool",
ptgInt : "ptgInt",
ptgNum : "ptgNum",
ptgArrayR : "ptgArrayR",
ptgFuncR : "ptgFuncR",
ptgFuncVarR : "ptgFuncVarR",
ptgNameR : "ptgNameR",
ptgRefR : "ptgRefR",
ptgAreaR : "ptgAreaR",
ptgMemAreaR : "ptgMemAreaR",
ptgMemErrR : "ptgMemErrR",
ptgMemNoMemR : "ptgMemNoMemR",
ptgMemFuncR : "ptgMemFuncR",
ptgRefErrR : "ptgRefErrR",
ptgAreaErrR : "ptgAreaErrR",
ptgRefNR : "ptgRefNR",
ptgAreaNR : "ptgAreaNR",
ptgMemAreaNR : "ptgMemAreaNR",
ptgMemNoMemNR : "ptgMemNoMemNR",
ptgNameXR : "ptgNameXR",
ptgRef3dR : "ptgRef3dR",
ptgArea3dR : "ptgArea3dR",
ptgRefErr3dR : "ptgRefErr3dR",
ptgAreaErr3dR : "ptgAreaErr3dR",
ptgArrayV : "ptgArrayV",
ptgFuncV : "ptgFuncV",
ptgFuncVarV : "ptgFuncVarV",
ptgNameV : "ptgNameV",
ptgRefV : "ptgRefV",
ptgAreaV : "ptgAreaV",
ptgMemAreaV : "ptgMemAreaV",
ptgMemErrV : "ptgMemErrV",
ptgMemNoMemV : "ptgMemNoMemV",
ptgMemFuncV : "ptgMemFuncV",
ptgRefErrV : "ptgRefErrV",
ptgAreaErrV : "ptgAreaErrV",
ptgRefNV : "ptgRefNV",
ptgAreaNV : "ptgAreaNV",
ptgMemAreaNV : "ptgMemAreaNV",
ptgMemNoMemNV : "ptgMemNoMemNV",
ptgFuncCEV : "ptgFuncCEV",
ptgNameXV : "ptgNameXV",
ptgRef3dV : "ptgRef3dV",
ptgArea3dV : "ptgArea3dV",
ptgRefErr3dV : "ptgRefErr3dV",
ptgAreaErr3dV : "ptgAreaErr3dV",
ptgArrayA : "ptgArrayA",
ptgFuncA : "ptgFuncA",
ptgFuncVarA : "ptgFuncVarA",
ptgNameA : "ptgNameA",
ptgRefA : "ptgRefA",
ptgAreaA : "ptgAreaA",
ptgMemAreaA : "ptgMemAreaA",
ptgMemErrA : "ptgMemErrA",
ptgMemNoMemA : "ptgMemNoMemA",
ptgMemFuncA : "ptgMemFuncA",
ptgRefErrA : "ptgRefErrA",
ptgAreaErrA : "ptgAreaErrA",
ptgRefNA : "ptgRefNA",
ptgAreaNA : "ptgAreaNA",
ptgMemAreaNA : "ptgMemAreaNA",
ptgMemNoMemNA : "ptgMemNoMemNA",
ptgFuncCEA : "ptgFuncCEA",
ptgNameXA : "ptgNameXA",
ptgRef3dA : "ptgRef3dA",
ptgArea3dA : "ptgArea3dA",
ptgRefErr3dA : "ptgRefErr3dA",
ptgAreaErr3dA : "ptgAreaErr3dA"
}
error_msg_by_code = {
0x00: u"#NULL!", # intersection of two cell ranges is empty
0x07: u"#DIV/0!", # division by zero
0x0F: u"#VALUE!", # wrong type of operand
0x17: u"#REF!", # illegal or deleted cell reference
0x1D: u"#NAME?", # wrong function or range name
0x24: u"#NUM!", # value range overflow
0x2A: u"#N/A!" # argument or function not available
}
-261
View File
@@ -1,261 +0,0 @@
#!/usr/bin/env python
'''
The XF record is able to store explicit cell formatting attributes or the
attributes of a cell style. Explicit formatting includes the reference to
a cell style XF record. This allows to extend a defined cell style with
some explicit attributes. The formatting attributes are divided into
6 groups:
Group Attributes
-------------------------------------
Number format Number format index (index to FORMAT record)
Font Font index (index to FONT record)
Alignment Horizontal and vertical alignment, text wrap, indentation,
orientation/rotation, text direction
Border Border line styles and colours
Background Background area style and colours
Protection Cell locked, formula hidden
For each group a flag in the cell XF record specifies whether to use the
attributes contained in that XF record or in the referenced style
XF record. In style XF records, these flags specify whether the attributes
will overwrite explicit cell formatting when the style is applied to
a cell. Changing a cell style (without applying this style to a cell) will
change all cells which already use that style and do not contain explicit
cell attributes for the changed style attributes. If a cell XF record does
not contain explicit attributes in a group (if the attribute group flag
is not set), it repeats the attributes of its style XF record.
'''
import BIFFRecords
class Font(object):
ESCAPEMENT_NONE = 0x00
ESCAPEMENT_SUPERSCRIPT = 0x01
ESCAPEMENT_SUBSCRIPT = 0x02
UNDERLINE_NONE = 0x00
UNDERLINE_SINGLE = 0x01
UNDERLINE_SINGLE_ACC = 0x21
UNDERLINE_DOUBLE = 0x02
UNDERLINE_DOUBLE_ACC = 0x22
FAMILY_NONE = 0x00
FAMILY_ROMAN = 0x01
FAMILY_SWISS = 0x02
FAMILY_MODERN = 0x03
FAMILY_SCRIPT = 0x04
FAMILY_DECORATIVE = 0x05
CHARSET_ANSI_LATIN = 0x00
CHARSET_SYS_DEFAULT = 0x01
CHARSET_SYMBOL = 0x02
CHARSET_APPLE_ROMAN = 0x4D
CHARSET_ANSI_JAP_SHIFT_JIS = 0x80
CHARSET_ANSI_KOR_HANGUL = 0x81
CHARSET_ANSI_KOR_JOHAB = 0x82
CHARSET_ANSI_CHINESE_GBK = 0x86
CHARSET_ANSI_CHINESE_BIG5 = 0x88
CHARSET_ANSI_GREEK = 0xA1
CHARSET_ANSI_TURKISH = 0xA2
CHARSET_ANSI_VIETNAMESE = 0xA3
CHARSET_ANSI_HEBREW = 0xB1
CHARSET_ANSI_ARABIC = 0xB2
CHARSET_ANSI_BALTIC = 0xBA
CHARSET_ANSI_CYRILLIC = 0xCC
CHARSET_ANSI_THAI = 0xDE
CHARSET_ANSI_LATIN_II = 0xEE
CHARSET_OEM_LATIN_I = 0xFF
def __init__(self):
# twip = 1/20 of a point = 1/1440 of a inch
# usually resolution == 96 pixels per 1 inch
# (rarely 120 pixels per 1 inch or another one)
self.height = 0x00C8 # 200: this is font with height 10 points
self.italic = False
self.struck_out = False
self.outline = False
self.shadow = False
self.colour_index = 0x7FFF
self.bold = False
self._weight = 0x0190 # 0x02BC gives bold font
self.escapement = self.ESCAPEMENT_NONE
self.underline = self.UNDERLINE_NONE
self.family = self.FAMILY_NONE
self.charset = self.CHARSET_SYS_DEFAULT
self.name = 'Arial'
def get_biff_record(self):
height = self.height
options = 0x00
if self.bold:
options |= 0x01
self._weight = 0x02BC
if self.italic:
options |= 0x02
if self.underline != self.UNDERLINE_NONE:
options |= 0x04
if self.struck_out:
options |= 0x08
if self.outline:
options |= 0x010
if self.shadow:
options |= 0x020
colour_index = self.colour_index
weight = self._weight
escapement = self.escapement
underline = self.underline
family = self.family
charset = self.charset
name = self.name
return BIFFRecords.FontRecord(height, options, colour_index, weight, escapement,
underline, family, charset,
name)
def _search_key(self):
return (
self.height,
self.italic,
self.struck_out,
self.outline,
self.shadow,
self.colour_index,
self.bold,
self._weight,
self.escapement,
self.underline,
self.family,
self.charset,
self.name,
)
class Alignment(object):
HORZ_GENERAL = 0x00
HORZ_LEFT = 0x01
HORZ_CENTER = 0x02
HORZ_RIGHT = 0x03
HORZ_FILLED = 0x04
HORZ_JUSTIFIED = 0x05 # BIFF4-BIFF8X
HORZ_CENTER_ACROSS_SEL = 0x06 # Centred across selection (BIFF4-BIFF8X)
HORZ_DISTRIBUTED = 0x07 # Distributed (BIFF8X)
VERT_TOP = 0x00
VERT_CENTER = 0x01
VERT_BOTTOM = 0x02
VERT_JUSTIFIED = 0x03 # Justified (BIFF5-BIFF8X)
VERT_DISTRIBUTED = 0x04 # Distributed (BIFF8X)
DIRECTION_GENERAL = 0x00 # BIFF8X
DIRECTION_LR = 0x01
DIRECTION_RL = 0x02
ORIENTATION_NOT_ROTATED = 0x00
ORIENTATION_STACKED = 0x01
ORIENTATION_90_CC = 0x02
ORIENTATION_90_CW = 0x03
ROTATION_0_ANGLE = 0x00
ROTATION_STACKED = 0xFF
WRAP_AT_RIGHT = 0x01
NOT_WRAP_AT_RIGHT = 0x00
SHRINK_TO_FIT = 0x01
NOT_SHRINK_TO_FIT = 0x00
def __init__(self):
self.horz = self.HORZ_GENERAL
self.vert = self.VERT_BOTTOM
self.dire = self.DIRECTION_GENERAL
self.orie = self.ORIENTATION_NOT_ROTATED
self.rota = self.ROTATION_0_ANGLE
self.wrap = self.NOT_WRAP_AT_RIGHT
self.shri = self.NOT_SHRINK_TO_FIT
self.inde = 0
self.merg = 0
def _search_key(self):
return (
self.horz, self.vert, self.dire, self.orie, self.rota,
self.wrap, self.shri, self.inde, self.merg,
)
class Borders(object):
NO_LINE = 0x00
THIN = 0x01
MEDIUM = 0x02
DASHED = 0x03
DOTTED = 0x04
THICK = 0x05
DOUBLE = 0x06
HAIR = 0x07
#The following for BIFF8
MEDIUM_DASHED = 0x08
THIN_DASH_DOTTED = 0x09
MEDIUM_DASH_DOTTED = 0x0A
THIN_DASH_DOT_DOTTED = 0x0B
MEDIUM_DASH_DOT_DOTTED = 0x0C
SLANTED_MEDIUM_DASH_DOTTED = 0x0D
NEED_DIAG1 = 0x01
NEED_DIAG2 = 0x01
NO_NEED_DIAG1 = 0x00
NO_NEED_DIAG2 = 0x00
def __init__(self):
self.left = self.NO_LINE
self.right = self.NO_LINE
self.top = self.NO_LINE
self.bottom = self.NO_LINE
self.diag = self.NO_LINE
self.left_colour = 0x40
self.right_colour = 0x40
self.top_colour = 0x40
self.bottom_colour = 0x40
self.diag_colour = 0x40
self.need_diag1 = self.NO_NEED_DIAG1
self.need_diag2 = self.NO_NEED_DIAG2
def _search_key(self):
return (
self.left, self.right, self.top, self.bottom, self.diag,
self.left_colour, self.right_colour, self.top_colour,
self.bottom_colour, self.diag_colour,
self.need_diag1, self.need_diag2,
)
class Pattern(object):
# patterns 0x00 - 0x12
NO_PATTERN = 0x00
SOLID_PATTERN = 0x01
def __init__(self):
self.pattern = self.NO_PATTERN
self.pattern_fore_colour = 0x40
self.pattern_back_colour = 0x41
def _search_key(self):
return (
self.pattern,
self.pattern_fore_colour,
self.pattern_back_colour,
)
class Protection(object):
def __init__(self):
self.cell_locked = 1
self.formula_hidden = 0
def _search_key(self):
return (
self.cell_locked,
self.formula_hidden,
)
-253
View File
@@ -1,253 +0,0 @@
# -*- coding: windows-1252 -*-
import BIFFRecords
import Style
from Cell import StrCell, BlankCell, NumberCell, FormulaCell, MulBlankCell, BooleanCell, ErrorCell, \
_get_cells_biff_data_mul
import ExcelFormula
import datetime as dt
try:
from decimal import Decimal
except ImportError:
# Python 2.3: decimal not supported; create dummy Decimal class
class Decimal(object):
pass
class Row(object):
__slots__ = [# private variables
"__idx",
"__parent",
"__parent_wb",
"__cells",
"__min_col_idx",
"__max_col_idx",
"__xf_index",
"__has_default_xf_index",
"__height_in_pixels",
# public variables
"height",
"has_default_height",
"height_mismatch",
"level",
"collapse",
"hidden",
"space_above",
"space_below"]
def __init__(self, rowx, parent_sheet):
if not (isinstance(rowx, int) and 0 <= rowx <= 65535):
raise ValueError("row index (%r) not an int in range(65536)" % rowx)
self.__idx = rowx
self.__parent = parent_sheet
self.__parent_wb = parent_sheet.get_parent()
self.__cells = {}
self.__min_col_idx = 0
self.__max_col_idx = 0
self.__xf_index = 0x0F
self.__has_default_xf_index = 0
self.__height_in_pixels = 0x11
self.height = 0x00FF
self.has_default_height = 0x00
self.height_mismatch = 0
self.level = 0
self.collapse = 0
self.hidden = 0
self.space_above = 0
self.space_below = 0
def __adjust_height(self, style):
twips = style.font.height
points = float(twips)/20.0
# Cell height in pixels can be calcuted by following approx. formula:
# cell height in pixels = font height in points * 83/50 + 2/5
# It works when screen resolution is 96 dpi
pix = int(round(points*83.0/50.0 + 2.0/5.0))
if pix > self.__height_in_pixels:
self.__height_in_pixels = pix
def __adjust_bound_col_idx(self, *args):
for arg in args:
iarg = int(arg)
if not ((0 <= iarg <= 255) and arg == iarg):
raise ValueError("column index (%r) not an int in range(256)" % arg)
sheet = self.__parent
if iarg < self.__min_col_idx:
self.__min_col_idx = iarg
if iarg > self.__max_col_idx:
self.__max_col_idx = iarg
if iarg < sheet.first_used_col:
sheet.first_used_col = iarg
if iarg > sheet.last_used_col:
sheet.last_used_col = iarg
def __excel_date_dt(self, date):
if isinstance(date, dt.date) and (not isinstance(date, dt.datetime)):
epoch = dt.date(1899, 12, 31)
elif isinstance(date, dt.time):
date = dt.datetime.combine(dt.datetime(1900, 1, 1), date)
epoch = dt.datetime(1900, 1, 1, 0, 0, 0)
else:
epoch = dt.datetime(1899, 12, 31, 0, 0, 0)
delta = date - epoch
xldate = delta.days + float(delta.seconds) / (24*60*60)
# Add a day for Excel's missing leap day in 1900
if xldate > 59:
xldate += 1
return xldate
def get_height_in_pixels(self):
return self.__height_in_pixels
def set_style(self, style):
self.__adjust_height(style)
self.__xf_index = self.__parent_wb.add_style(style)
self.__has_default_xf_index = 1
def get_xf_index(self):
return self.__xf_index
def get_cells_count(self):
return len(self.__cells)
def get_min_col(self):
return self.__min_col_idx
def get_max_col(self):
return self.__max_col_idx
def get_row_biff_data(self):
height_options = (self.height & 0x07FFF)
height_options |= (self.has_default_height & 0x01) << 15
options = (self.level & 0x07) << 0
options |= (self.collapse & 0x01) << 4
options |= (self.hidden & 0x01) << 5
options |= (self.height_mismatch & 0x01) << 6
options |= (self.__has_default_xf_index & 0x01) << 7
options |= (0x01 & 0x01) << 8
options |= (self.__xf_index & 0x0FFF) << 16
options |= (self.space_above & 1) << 28
options |= (self.space_below & 1) << 29
return BIFFRecords.RowRecord(self.__idx, self.__min_col_idx,
self.__max_col_idx, height_options, options).get()
def insert_cell(self, col_index, cell_obj):
if col_index in self.__cells:
if not self.__parent._cell_overwrite_ok:
msg = "Attempt to overwrite cell: sheetname=%r rowx=%d colx=%d" \
% (self.__parent.name, self.__idx, col_index)
raise Exception(msg)
prev_cell_obj = self.__cells[col_index]
sst_idx = getattr(prev_cell_obj, 'sst_idx', None)
if sst_idx is not None:
self.__parent_wb.del_str(sst_idx)
self.__cells[col_index] = cell_obj
def insert_mulcells(self, colx1, colx2, cell_obj):
self.insert_cell(colx1, cell_obj)
for col_index in xrange(colx1+1, colx2+1):
self.insert_cell(col_index, None)
def get_cells_biff_data(self):
cell_items = [item for item in self.__cells.iteritems() if item[1] is not None]
cell_items.sort() # in column order
return _get_cells_biff_data_mul(self.__idx, cell_items)
# previously:
# return ''.join([cell.get_biff_data() for colx, cell in cell_items])
def get_index(self):
return self.__idx
def set_cell_text(self, colx, value, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, StrCell(self.__idx, colx, xf_index, self.__parent_wb.add_str(value)))
def set_cell_blank(self, colx, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, BlankCell(self.__idx, colx, xf_index))
def set_cell_mulblanks(self, first_colx, last_colx, style=Style.default_style):
assert 0 <= first_colx <= last_colx <= 255
self.__adjust_height(style)
self.__adjust_bound_col_idx(first_colx, last_colx)
xf_index = self.__parent_wb.add_style(style)
# ncols = last_colx - first_colx + 1
self.insert_mulcells(first_colx, last_colx, MulBlankCell(self.__idx, first_colx, last_colx, xf_index))
def set_cell_number(self, colx, number, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, NumberCell(self.__idx, colx, xf_index, number))
def set_cell_date(self, colx, datetime_obj, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx,
NumberCell(self.__idx, colx, xf_index, self.__excel_date_dt(datetime_obj)))
def set_cell_formula(self, colx, formula, style=Style.default_style, calc_flags=0):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.__parent_wb.add_sheet_reference(formula)
self.insert_cell(colx, FormulaCell(self.__idx, colx, xf_index, formula, calc_flags=0))
def set_cell_boolean(self, colx, value, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, BooleanCell(self.__idx, colx, xf_index, bool(value)))
def set_cell_error(self, colx, error_string_or_code, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, ErrorCell(self.__idx, colx, xf_index, error_string_or_code))
def write(self, col, label, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(col)
style_index = self.__parent_wb.add_style(style)
if isinstance(label, basestring):
if len(label) > 0:
self.insert_cell(col,
StrCell(self.__idx, col, style_index, self.__parent_wb.add_str(label))
)
else:
self.insert_cell(col, BlankCell(self.__idx, col, style_index))
elif isinstance(label, bool): # bool is subclass of int; test bool first
self.insert_cell(col, BooleanCell(self.__idx, col, style_index, label))
elif isinstance(label, (float, int, long, Decimal)):
self.insert_cell(col, NumberCell(self.__idx, col, style_index, label))
elif isinstance(label, (dt.datetime, dt.date, dt.time)):
date_number = self.__excel_date_dt(label)
self.insert_cell(col, NumberCell(self.__idx, col, style_index, date_number))
elif label is None:
self.insert_cell(col, BlankCell(self.__idx, col, style_index))
elif isinstance(label, ExcelFormula.Formula):
self.__parent_wb.add_sheet_reference(label)
self.insert_cell(col, FormulaCell(self.__idx, col, style_index, label))
else:
raise Exception("Unexpected data type %r" % type(label))
write_blanks = set_cell_mulblanks
-592
View File
@@ -1,592 +0,0 @@
# -*- coding: windows-1252 -*-
import Formatting
from BIFFRecords import *
FIRST_USER_DEFINED_NUM_FORMAT_IDX = 164
class XFStyle(object):
def __init__(self):
self.num_format_str = 'General'
self.font = Formatting.Font()
self.alignment = Formatting.Alignment()
self.borders = Formatting.Borders()
self.pattern = Formatting.Pattern()
self.protection = Formatting.Protection()
default_style = XFStyle()
class StyleCollection(object):
_std_num_fmt_list = [
'general',
'0',
'0.00',
'#,##0',
'#,##0.00',
'"$"#,##0_);("$"#,##',
'"$"#,##0_);[Red]("$"#,##',
'"$"#,##0.00_);("$"#,##',
'"$"#,##0.00_);[Red]("$"#,##',
'0%',
'0.00%',
'0.00E+00',
'# ?/?',
'# ??/??',
'M/D/YY',
'D-MMM-YY',
'D-MMM',
'MMM-YY',
'h:mm AM/PM',
'h:mm:ss AM/PM',
'h:mm',
'h:mm:ss',
'M/D/YY h:mm',
'_(#,##0_);(#,##0)',
'_(#,##0_);[Red](#,##0)',
'_(#,##0.00_);(#,##0.00)',
'_(#,##0.00_);[Red](#,##0.00)',
'_("$"* #,##0_);_("$"* (#,##0);_("$"* "-"_);_(@_)',
'_(* #,##0_);_(* (#,##0);_(* "-"_);_(@_)',
'_("$"* #,##0.00_);_("$"* (#,##0.00);_("$"* "-"??_);_(@_)',
'_(* #,##0.00_);_(* (#,##0.00);_(* "-"??_);_(@_)',
'mm:ss',
'[h]:mm:ss',
'mm:ss.0',
'##0.0E+0',
'@'
]
def __init__(self, style_compression=0):
self.style_compression = style_compression
self.stats = [0, 0, 0, 0, 0, 0]
self._font_id2x = {}
self._font_x2id = {}
self._font_val2x = {}
for x in (0, 1, 2, 3, 5): # The font with index 4 is omitted in all BIFF versions
font = Formatting.Font()
search_key = font._search_key()
self._font_id2x[font] = x
self._font_x2id[x] = font
self._font_val2x[search_key] = x
self._xf_id2x = {}
self._xf_x2id = {}
self._xf_val2x = {}
self._num_formats = {}
for fmtidx, fmtstr in zip(range(0, 23), StyleCollection._std_num_fmt_list[0:23]):
self._num_formats[fmtstr] = fmtidx
for fmtidx, fmtstr in zip(range(37, 50), StyleCollection._std_num_fmt_list[23:]):
self._num_formats[fmtstr] = fmtidx
self.default_style = XFStyle()
self._default_xf = self._add_style(self.default_style)[0]
def add(self, style):
if style == None:
return 0x10
return self._add_style(style)[1]
def _add_style(self, style):
num_format_str = style.num_format_str
if num_format_str in self._num_formats:
num_format_idx = self._num_formats[num_format_str]
else:
num_format_idx = (
FIRST_USER_DEFINED_NUM_FORMAT_IDX
+ len(self._num_formats)
- len(StyleCollection._std_num_fmt_list)
)
self._num_formats[num_format_str] = num_format_idx
font = style.font
if font in self._font_id2x:
font_idx = self._font_id2x[font]
self.stats[0] += 1
elif self.style_compression:
search_key = font._search_key()
font_idx = self._font_val2x.get(search_key)
if font_idx is not None:
self._font_id2x[font] = font_idx
self.stats[1] += 1
else:
font_idx = len(self._font_x2id) + 1 # Why plus 1? Font 4 is missing
self._font_id2x[font] = font_idx
self._font_val2x[search_key] = font_idx
self._font_x2id[font_idx] = font
self.stats[2] += 1
else:
font_idx = len(self._font_id2x) + 1
self._font_id2x[font] = font_idx
self.stats[2] += 1
gof = (style.alignment, style.borders, style.pattern, style.protection)
xf = (font_idx, num_format_idx) + gof
if xf in self._xf_id2x:
xf_index = self._xf_id2x[xf]
self.stats[3] += 1
elif self.style_compression == 2:
xf_key = (font_idx, num_format_idx) + tuple([obj._search_key() for obj in gof])
xf_index = self._xf_val2x.get(xf_key)
if xf_index is not None:
self._xf_id2x[xf] = xf_index
self.stats[4] += 1
else:
xf_index = 0x10 + len(self._xf_x2id)
self._xf_id2x[xf] = xf_index
self._xf_val2x[xf_key] = xf_index
self._xf_x2id[xf_index] = xf
self.stats[5] += 1
else:
xf_index = 0x10 + len(self._xf_id2x)
self._xf_id2x[xf] = xf_index
self.stats[5] += 1
if xf_index >= 0xFFF:
# 12 bits allowed, 0xFFF is a sentinel value
raise ValueError("More than 4094 XFs (styles)")
return xf, xf_index
def get_biff_data(self):
result = ''
result += self._all_fonts()
result += self._all_num_formats()
result += self._all_cell_styles()
result += self._all_styles()
return result
def _all_fonts(self):
result = ''
if self.style_compression:
alist = self._font_x2id.items()
else:
alist = [(x, o) for o, x in self._font_id2x.items()]
alist.sort()
for font_idx, font in alist:
result += font.get_biff_record().get()
return result
def _all_num_formats(self):
result = ''
alist = [
(v, k)
for k, v in self._num_formats.items()
if v >= FIRST_USER_DEFINED_NUM_FORMAT_IDX
]
alist.sort()
for fmtidx, fmtstr in alist:
result += NumberFormatRecord(fmtidx, fmtstr).get()
return result
def _all_cell_styles(self):
result = ''
for i in range(0, 16):
result += XFRecord(self._default_xf, 'style').get()
if self.style_compression == 2:
alist = self._xf_x2id.items()
else:
alist = [(x, o) for o, x in self._xf_id2x.items()]
alist.sort()
for xf_idx, xf in alist:
result += XFRecord(xf).get()
return result
def _all_styles(self):
return StyleRecord().get()
# easyxf and its supporting objects ###################################
class EasyXFException(Exception):
pass
class EasyXFCallerError(EasyXFException):
pass
class EasyXFAuthorError(EasyXFException):
pass
class IntULim(object):
# If astring represents a valid unsigned integer ('123', '0xabcd', etc)
# and it is <= limit, return the int value; otherwise return None.
def __init__(self, limit):
self.limit = limit
def __call__(self, astring):
try:
value = int(astring, 0)
except ValueError:
return None
if not 0 <= value <= self.limit:
return None
return value
bool_map = {
# Text values for all Boolean attributes
'1': 1, 'yes': 1, 'true': 1, 'on': 1,
'0': 0, 'no': 0, 'false': 0, 'off': 0,
}
border_line_map = {
# Text values for these borders attributes:
# left, right, top, bottom and diag
'no_line': 0x00,
'thin': 0x01,
'medium': 0x02,
'dashed': 0x03,
'dotted': 0x04,
'thick': 0x05,
'double': 0x06,
'hair': 0x07,
'medium_dashed': 0x08,
'thin_dash_dotted': 0x09,
'medium_dash_dotted': 0x0a,
'thin_dash_dot_dotted': 0x0b,
'medium_dash_dot_dotted': 0x0c,
'slanted_medium_dash_dotted': 0x0d,
}
charset_map = {
# Text values for font.charset
'ansi_latin': 0x00,
'sys_default': 0x01,
'symbol': 0x02,
'apple_roman': 0x4d,
'ansi_jap_shift_jis': 0x80,
'ansi_kor_hangul': 0x81,
'ansi_kor_johab': 0x82,
'ansi_chinese_gbk': 0x86,
'ansi_chinese_big5': 0x88,
'ansi_greek': 0xa1,
'ansi_turkish': 0xa2,
'ansi_vietnamese': 0xa3,
'ansi_hebrew': 0xb1,
'ansi_arabic': 0xb2,
'ansi_baltic': 0xba,
'ansi_cyrillic': 0xcc,
'ansi_thai': 0xde,
'ansi_latin_ii': 0xee,
'oem_latin_i': 0xff,
}
# Text values for colour indices. "grey" is a synonym of "gray".
# The names are those given by Microsoft Excel 2003 to the colours
# in the default palette. There is no great correspondence with
# any W3C name-to-RGB mapping.
_colour_map_text = """\
aqua 0x31
black 0x08
blue 0x0C
blue_gray 0x36
bright_green 0x0B
brown 0x3C
coral 0x1D
cyan_ega 0x0F
dark_blue 0x12
dark_blue_ega 0x12
dark_green 0x3A
dark_green_ega 0x11
dark_purple 0x1C
dark_red 0x10
dark_red_ega 0x10
dark_teal 0x38
dark_yellow 0x13
gold 0x33
gray_ega 0x17
gray25 0x16
gray40 0x37
gray50 0x17
gray80 0x3F
green 0x11
ice_blue 0x1F
indigo 0x3E
ivory 0x1A
lavender 0x2E
light_blue 0x30
light_green 0x2A
light_orange 0x34
light_turquoise 0x29
light_yellow 0x2B
lime 0x32
magenta_ega 0x0E
ocean_blue 0x1E
olive_ega 0x13
olive_green 0x3B
orange 0x35
pale_blue 0x2C
periwinkle 0x18
pink 0x0E
plum 0x3D
purple_ega 0x14
red 0x0A
rose 0x2D
sea_green 0x39
silver_ega 0x16
sky_blue 0x28
tan 0x2F
teal 0x15
teal_ega 0x15
turquoise 0x0F
violet 0x14
white 0x09
yellow 0x0D"""
colour_map = {}
for _line in _colour_map_text.splitlines():
_name, _num = _line.split()
_num = int(_num, 0)
colour_map[_name] = _num
if 'gray' in _name:
colour_map[_name.replace('gray', 'grey')] = _num
del _colour_map_text, _line, _name, _num
pattern_map = {
# Text values for pattern.pattern
# xlwt/doc/pattern_examples.xls showcases all of these patterns.
'no_fill': 0,
'none': 0,
'solid': 1,
'solid_fill': 1,
'solid_pattern': 1,
'fine_dots': 2,
'alt_bars': 3,
'sparse_dots': 4,
'thick_horz_bands': 5,
'thick_vert_bands': 6,
'thick_backward_diag': 7,
'thick_forward_diag': 8,
'big_spots': 9,
'bricks': 10,
'thin_horz_bands': 11,
'thin_vert_bands': 12,
'thin_backward_diag': 13,
'thin_forward_diag': 14,
'squares': 15,
'diamonds': 16,
}
def any_str_func(s):
return s.strip()
def colour_index_func(s, maxval=0x7F):
try:
value = int(s, 0)
except ValueError:
return None
if not (0 <= value <= maxval):
return None
return value
colour_index_func_7 = colour_index_func
def colour_index_func_15(s):
return colour_index_func(s, maxval=0x7FFF)
def rotation_func(s):
try:
value = int(s, 0)
except ValueError:
return None
if not (-90 <= value <= 90):
raise EasyXFCallerError("rotation %d: should be -90 to +90 degrees" % value)
if value < 0:
value = 90 - value # encode as 91 to 180 (clockwise)
return value
xf_dict = {
'align': 'alignment', # synonym
'alignment': {
'dire': {
'general': 0,
'lr': 1,
'rl': 2,
},
'direction': 'dire',
'horiz': 'horz',
'horizontal': 'horz',
'horz': {
'general': 0,
'left': 1,
'center': 2,
'centre': 2, # "align: horiz centre" means xf.alignment.horz is set to 2
'right': 3,
'filled': 4,
'justified': 5,
'center_across_selection': 6,
'centre_across_selection': 6,
'distributed': 7,
},
'inde': IntULim(15), # restriction: 0 <= value <= 15
'indent': 'inde',
'rota': [{'stacked': 255, 'none': 0, }, rotation_func],
'rotation': 'rota',
'shri': bool_map,
'shrink': 'shri',
'shrink_to_fit': 'shri',
'vert': {
'top': 0,
'center': 1,
'centre': 1,
'bottom': 2,
'justified': 3,
'distributed': 4,
},
'vertical': 'vert',
'wrap': bool_map,
},
'border': 'borders',
'borders': {
'left': [border_line_map, IntULim(0x0d)],
'right': [border_line_map, IntULim(0x0d)],
'top': [border_line_map, IntULim(0x0d)],
'bottom': [border_line_map, IntULim(0x0d)],
'diag': [border_line_map, IntULim(0x0d)],
'top_colour': [colour_map, colour_index_func_7],
'bottom_colour': [colour_map, colour_index_func_7],
'left_colour': [colour_map, colour_index_func_7],
'right_colour': [colour_map, colour_index_func_7],
'diag_colour': [colour_map, colour_index_func_7],
'top_color': 'top_colour',
'bottom_color': 'bottom_colour',
'left_color': 'left_colour',
'right_color': 'right_colour',
'diag_color': 'diag-colour',
'need_diag_1': bool_map,
'need_diag_2': bool_map,
},
'font': {
'bold': bool_map,
'charset': charset_map,
'color': 'colour_index',
'color_index': 'colour_index',
'colour': 'colour_index',
'colour_index': [colour_map, colour_index_func_15],
'escapement': {'none': 0, 'superscript': 1, 'subscript': 2},
'family': {'none': 0, 'roman': 1, 'swiss': 2, 'modern': 3, 'script': 4, 'decorative': 5, },
'height': IntULim(0xFFFF), # practical limits are much narrower e.g. 160 to 1440 (8pt to 72pt)
'italic': bool_map,
'name': any_str_func,
'outline': bool_map,
'shadow': bool_map,
'struck_out': bool_map,
'underline': [bool_map, {'none': 0, 'single': 1, 'single_acc': 0x21, 'double': 2, 'double_acc': 0x22, }],
},
'pattern': {
'back_color': 'pattern_back_colour',
'back_colour': 'pattern_back_colour',
'fore_color': 'pattern_fore_colour',
'fore_colour': 'pattern_fore_colour',
'pattern': [pattern_map, IntULim(16)],
'pattern_back_color': 'pattern_back_colour',
'pattern_back_colour': [colour_map, colour_index_func_7],
'pattern_fore_color': 'pattern_fore_colour',
'pattern_fore_colour': [colour_map, colour_index_func_7],
},
'protection': {
'cell_locked' : bool_map,
'formula_hidden': bool_map,
},
}
def _esplit(s, split_char, esc_char="\\"):
escaped = False
olist = ['']
for c in s:
if escaped:
olist[-1] += c
escaped = False
elif c == esc_char:
escaped = True
elif c == split_char:
olist.append('')
else:
olist[-1] += c
return olist
def _parse_strg_to_obj(strg, obj, parse_dict,
field_sep=",", line_sep=";", intro_sep=":", esc_char="\\", debug=False):
for line in _esplit(strg, line_sep, esc_char):
line = line.strip()
if not line:
break
split_line = _esplit(line, intro_sep, esc_char)
if len(split_line) != 2:
raise EasyXFCallerError('line %r should have exactly 1 "%c"' % (line, intro_sep))
section, item_str = split_line
section = section.strip().lower()
for counter in range(2):
result = parse_dict.get(section)
if result is None:
raise EasyXFCallerError('section %r is unknown' % section)
if isinstance(result, dict):
break
if not isinstance(result, str):
raise EasyXFAuthorError(
'section %r should map to dict or str object; found %r' % (section, type(result)))
# synonym
old_section = section
section = result
else:
raise EasyXFAuthorError('Attempt to define synonym of synonym (%r: %r)' % (old_section, result))
section_dict = result
section_obj = getattr(obj, section, None)
if section_obj is None:
raise EasyXFAuthorError('instance of %s class has no attribute named %s' % (obj.__class__.__name__, section))
for kv_str in _esplit(item_str, field_sep, esc_char):
guff = kv_str.split()
if not guff:
continue
k = guff[0].lower().replace('-', '_')
v = ' '.join(guff[1:])
if not v:
raise EasyXFCallerError("no value supplied for %s.%s" % (section, k))
for counter in xrange(2):
result = section_dict.get(k)
if result is None:
raise EasyXFCallerError('%s.%s is not a known attribute' % (section, k))
if not isinstance(result, basestring):
break
# synonym
old_k = k
k = result
else:
raise EasyXFAuthorError('Attempt to define synonym of synonym (%r: %r)' % (old_k, result))
value_info = result
if not isinstance(value_info, list):
value_info = [value_info]
for value_rule in value_info:
if isinstance(value_rule, dict):
# dict maps strings to integer field values
vl = v.lower().replace('-', '_')
if vl in value_rule:
value = value_rule[vl]
break
elif callable(value_rule):
value = value_rule(v)
if value is not None:
break
else:
raise EasyXFAuthorError("unknown value rule for attribute %r: %r" % (k, value_rule))
else:
raise EasyXFCallerError("unexpected value %r for %s.%s" % (v, section, k))
try:
orig = getattr(section_obj, k)
except AttributeError:
raise EasyXFAuthorError('%s.%s in dictionary but not in supplied object' % (section, k))
if debug: print "+++ %s.%s = %r # %s; was %r" % (section, k, value, v, orig)
setattr(section_obj, k, value)
def easyxf(strg_to_parse="", num_format_str=None,
field_sep=",", line_sep=";", intro_sep=":", esc_char="\\", debug=False):
xfobj = XFStyle()
if num_format_str is not None:
xfobj.num_format_str = num_format_str
if strg_to_parse:
_parse_strg_to_obj(strg_to_parse, xfobj, xf_dict,
field_sep=field_sep, line_sep=line_sep, intro_sep=intro_sep, esc_char=esc_char, debug=debug)
return xfobj
-81
View File
@@ -1,81 +0,0 @@
# -*- coding: windows-1252 -*-
'''
From BIFF8 on, strings are always stored using UTF-16LE text encoding. The
character array is a sequence of 16-bit values4. Additionally it is
possible to use a compressed format, which omits the high bytes of all
characters, if they are all zero.
The following tables describe the standard format of the entire string, but
in many records the strings differ from this format. This will be mentioned
separately. It is possible (but not required) to store Rich-Text formatting
information and Asian phonetic information inside a Unicode string. This
results in four different ways to store a string. The character array
is not zero-terminated.
The string consists of the character count (as usual an 8-bit value or
a 16-bit value), option flags, the character array and optional formatting
information. If the string is empty, sometimes the option flags field will
not occur. This is mentioned at the respective place.
Offset Size Contents
0 1 or 2 Length of the string (character count, ln)
1 or 2 1 Option flags:
Bit Mask Contents
0 01H Character compression (ccompr):
0 = Compressed (8-bit characters)
1 = Uncompressed (16-bit characters)
2 04H Asian phonetic settings (phonetic):
0 = Does not contain Asian phonetic settings
1 = Contains Asian phonetic settings
3 08H Rich-Text settings (richtext):
0 = Does not contain Rich-Text settings
1 = Contains Rich-Text settings
[2 or 3] 2 (optional, only if richtext=1) Number of Rich-Text formatting runs (rt)
[var.] 4 (optional, only if phonetic=1) Size of Asian phonetic settings block (in bytes, sz)
var. ln or
2·ln Character array (8-bit characters or 16-bit characters, dependent on ccompr)
[var.] 4·rt (optional, only if richtext=1) List of rt formatting runs
[var.] sz (optional, only if phonetic=1) Asian Phonetic Settings Block
'''
from struct import pack
def upack2(s, encoding='ascii'):
# If not unicode, make it so.
if isinstance(s, unicode):
us = s
else:
us = unicode(s, encoding)
# Limit is based on number of content characters
# (not on number of bytes in packed result)
len_us = len(us)
if len_us > 65535:
raise Exception('String longer than 65535 characters')
try:
encs = us.encode('latin1')
# Success here means all chars are in U+0000 to U+00FF
# inclusive, meaning that we can use "compressed format".
flag = 0
except UnicodeEncodeError:
encs = us.encode('utf_16_le')
flag = 1
return pack('<HB', len_us, flag) + encs
def upack1(s, encoding='ascii'):
# Same as upack2(), but with a one-byte length field.
if isinstance(s, unicode):
us = s
else:
us = unicode(s, encoding)
len_us = len(us)
if len_us > 255:
raise Exception('String longer than 255 characters')
try:
encs = us.encode('latin1')
flag = 0
except UnicodeEncodeError:
encs = us.encode('utf_16_le')
flag = 1
return pack('<BB', len_us, flag) + encs
-196
View File
@@ -1,196 +0,0 @@
# pyXLWriter: A library for generating Excel Spreadsheets
# Copyright (c) 2004 Evgeny Filatov <fufff@users.sourceforge.net>
# Copyright (c) 2002-2004 John McNamara (Perl Spreadsheet::WriteExcel)
#
# This library is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation; either version 2.1 of the License, or
# (at your option) any later version.
#
# This library is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser
# General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with this library; if not, write to the Free Software Foundation,
# Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#----------------------------------------------------------------------------
# This module was written/ported from PERL Spreadsheet::WriteExcel module
# The author of the PERL Spreadsheet::WriteExcel module is John McNamara
# <jmcnamara@cpan.org>
#----------------------------------------------------------------------------
# See the README.txt distributed with pyXLWriter for more details.
# Portions are (C) Roman V. Kiseliov, 2005
# Utilities for work with reference to cells and with sheetnames
__rev_id__ = """$Id: Utils.py 3844 2009-05-20 01:02:54Z sjmachin $"""
import re
from struct import pack
from ExcelMagic import MAX_ROW, MAX_COL
_re_cell_ex = re.compile(r"(\$?)([A-I]?[A-Z])(\$?)(\d+)", re.IGNORECASE)
_re_row_range = re.compile(r"\$?(\d+):\$?(\d+)")
_re_col_range = re.compile(r"\$?([A-I]?[A-Z]):\$?([A-I]?[A-Z])", re.IGNORECASE)
_re_cell_range = re.compile(r"\$?([A-I]?[A-Z]\$?\d+):\$?([A-I]?[A-Z]\$?\d+)", re.IGNORECASE)
_re_cell_ref = re.compile(r"\$?([A-I]?[A-Z]\$?\d+)", re.IGNORECASE)
def col_by_name(colname):
"""
"""
col = 0
pow = 1
for i in xrange(len(colname)-1, -1, -1):
ch = colname[i]
col += (ord(ch) - ord('A') + 1) * pow
pow *= 26
return col - 1
def cell_to_rowcol(cell):
"""Convert an Excel cell reference string in A1 notation
to numeric row/col notation.
Returns: row, col, row_abs, col_abs
"""
m = _re_cell_ex.match(cell)
if not m:
raise Exception("Ill-formed single_cell reference: %s" % cell)
col_abs, col, row_abs, row = m.groups()
row_abs = bool(row_abs)
col_abs = bool(col_abs)
row = int(row) - 1
col = col_by_name(col.upper())
return row, col, row_abs, col_abs
def cell_to_rowcol2(cell):
"""Convert an Excel cell reference string in A1 notation
to numeric row/col notation.
Returns: row, col
"""
m = _re_cell_ex.match(cell)
if not m:
raise Exception("Error in cell format")
col_abs, col, row_abs, row = m.groups()
# Convert base26 column string to number
# All your Base are belong to us.
row = int(row) - 1
col = col_by_name(col.upper())
return row, col
def rowcol_to_cell(row, col, row_abs=False, col_abs=False):
"""Convert numeric row/col notation to an Excel cell reference string in
A1 notation.
"""
assert 0 <= row < MAX_ROW # MAX_ROW counts from 1
assert 0 <= col < MAX_COL # MAX_COL counts from 1
d = col // 26
m = col % 26
chr1 = "" # Most significant character in AA1
if row_abs:
row_abs = '$'
else:
row_abs = ''
if col_abs:
col_abs = '$'
else:
col_abs = ''
if d > 0:
chr1 = chr(ord('A') + d - 1)
chr2 = chr(ord('A') + m)
# Zero index to 1-index
return col_abs + chr1 + chr2 + row_abs + str(row + 1)
def rowcol_pair_to_cellrange(row1, col1, row2, col2,
row1_abs=False, col1_abs=False, row2_abs=False, col2_abs=False):
"""Convert two (row,column) pairs
into a cell range string in A1:B2 notation.
Returns: cell range string
"""
assert row1 <= row2
assert col1 <= col2
return (
rowcol_to_cell(row1, col1, row1_abs, col1_abs)
+ ":"
+ rowcol_to_cell(row2, col2, row2_abs, col2_abs)
)
def cellrange_to_rowcol_pair(cellrange):
"""Convert cell range string in A1 notation to numeric row/col
pair.
Returns: row1, col1, row2, col2
"""
cellrange = cellrange.upper()
# Convert a row range: '1:3'
res = _re_row_range.match(cellrange)
if res:
row1 = int(res.group(1)) - 1
col1 = 0
row2 = int(res.group(2)) - 1
col2 = -1
return row1, col1, row2, col2
# Convert a column range: 'A:A' or 'B:G'.
# A range such as A:A is equivalent to A1:A16384, so add rows as required
res = _re_col_range.match(cellrange)
if res:
col1 = col_by_name(res.group(1).upper())
row1 = 0
col2 = col_by_name(res.group(2).upper())
row2 = -1
return row1, col1, row2, col2
# Convert a cell range: 'A1:B7'
res = _re_cell_range.match(cellrange)
if res:
row1, col1 = cell_to_rowcol2(res.group(1))
row2, col2 = cell_to_rowcol2(res.group(2))
return row1, col1, row2, col2
# Convert a cell reference: 'A1' or 'AD2000'
res = _re_cell_ref.match(cellrange)
if res:
row1, col1 = cell_to_rowcol2(res.group(1))
return row1, col1, row1, col1
raise Exception("Unknown cell reference %s" % (cell))
def cell_to_packed_rowcol(cell):
""" pack row and column into the required 4 byte format """
row, col, row_abs, col_abs = cell_to_rowcol(cell)
if col >= MAX_COL:
raise Exception("Column %s greater than IV in formula" % cell)
if row >= MAX_ROW: # this for BIFF8. for BIFF7 available 2^14
raise Exception("Row %s greater than %d in formula" % (cell, MAX_ROW))
col |= int(not row_abs) << 15
col |= int(not col_abs) << 14
return row, col
# === sheetname functions ===
def valid_sheet_name(sheet_name):
if sheet_name == u"" or sheet_name[0] == u"'" or len(sheet_name) > 31:
return False
for c in sheet_name:
if c in u"[]:\\?/*\x00":
return False
return True
def quote_sheet_name(unquoted_sheet_name):
if not valid_sheet_name(unquoted_sheet_name):
raise Exception(
'attempt to quote an invalid worksheet name %r' % unquoted_sheet_name)
return u"'" + unquoted_sheet_name.replace(u"'", u"''") + u"'"
-636
View File
@@ -1,636 +0,0 @@
# -*- coding: windows-1252 -*-
'''
Record Order in BIFF8
Workbook Globals Substream
BOF Type = workbook globals
Interface Header
MMS
Interface End
WRITEACCESS
CODEPAGE
DSF
TABID
FNGROUPCOUNT
Workbook Protection Block
WINDOWPROTECT
PROTECT
PASSWORD
PROT4REV
PROT4REVPASS
BACKUP
HIDEOBJ
WINDOW1
DATEMODE
PRECISION
REFRESHALL
BOOKBOOL
FONT +
FORMAT *
XF +
STYLE +
? PALETTE
USESELFS
BOUNDSHEET +
COUNTRY
? Link Table
SST
ExtSST
EOF
'''
import BIFFRecords
import Style
class Workbook(object):
#################################################################
## Constructor
#################################################################
def __init__(self, encoding='ascii', style_compression=0):
self.encoding = encoding
self.__owner = 'None'
self.__country_code = None # 0x07 is Russia :-)
self.__wnd_protect = 0
self.__obj_protect = 0
self.__protect = 0
self.__backup_on_save = 0
# for WINDOW1 record
self.__hpos_twips = 0x01E0
self.__vpos_twips = 0x005A
self.__width_twips = 0x3FCF
self.__height_twips = 0x2A4E
self.__active_sheet = 0
self.__first_tab_index = 0
self.__selected_tabs = 0x01
self.__tab_width_twips = 0x0258
self.__wnd_hidden = 0
self.__wnd_mini = 0
self.__hscroll_visible = 1
self.__vscroll_visible = 1
self.__tabs_visible = 1
self.__styles = Style.StyleCollection(style_compression)
self.__dates_1904 = 0
self.__use_cell_values = 1
self.__sst = BIFFRecords.SharedStringTable(self.encoding)
self.__worksheets = []
self.__worksheet_idx_from_name = {}
self.__sheet_refs = {}
self._supbook_xref = {}
self._xcall_xref = {}
self._ownbook_supbookx = None
self._ownbook_supbook_ref = None
self._xcall_supbookx = None
self._xcall_supbook_ref = None
#################################################################
## Properties, "getters", "setters"
#################################################################
def get_style_stats(self):
return self.__styles.stats[:]
def set_owner(self, value):
self.__owner = value
def get_owner(self):
return self.__owner
owner = property(get_owner, set_owner)
#################################################################
def set_country_code(self, value):
self.__country_code = value
def get_country_code(self):
return self.__country_code
country_code = property(get_country_code, set_country_code)
#################################################################
def set_wnd_protect(self, value):
self.__wnd_protect = int(value)
def get_wnd_protect(self):
return bool(self.__wnd_protect)
wnd_protect = property(get_wnd_protect, set_wnd_protect)
#################################################################
def set_obj_protect(self, value):
self.__obj_protect = int(value)
def get_obj_protect(self):
return bool(self.__obj_protect)
obj_protect = property(get_obj_protect, set_obj_protect)
#################################################################
def set_protect(self, value):
self.__protect = int(value)
def get_protect(self):
return bool(self.__protect)
protect = property(get_protect, set_protect)
#################################################################
def set_backup_on_save(self, value):
self.__backup_on_save = int(value)
def get_backup_on_save(self):
return bool(self.__backup_on_save)
backup_on_save = property(get_backup_on_save, set_backup_on_save)
#################################################################
def set_hpos(self, value):
self.__hpos_twips = value & 0xFFFF
def get_hpos(self):
return self.__hpos_twips
hpos = property(get_hpos, set_hpos)
#################################################################
def set_vpos(self, value):
self.__vpos_twips = value & 0xFFFF
def get_vpos(self):
return self.__vpos_twips
vpos = property(get_vpos, set_vpos)
#################################################################
def set_width(self, value):
self.__width_twips = value & 0xFFFF
def get_width(self):
return self.__width_twips
width = property(get_width, set_width)
#################################################################
def set_height(self, value):
self.__height_twips = value & 0xFFFF
def get_height(self):
return self.__height_twips
height = property(get_height, set_height)
#################################################################
def set_active_sheet(self, value):
self.__active_sheet = value & 0xFFFF
self.__first_tab_index = self.__active_sheet
def get_active_sheet(self):
return self.__active_sheet
active_sheet = property(get_active_sheet, set_active_sheet)
#################################################################
def set_tab_width(self, value):
self.__tab_width_twips = value & 0xFFFF
def get_tab_width(self):
return self.__tab_width_twips
tab_width = property(get_tab_width, set_tab_width)
#################################################################
def set_wnd_visible(self, value):
self.__wnd_hidden = int(not value)
def get_wnd_visible(self):
return not bool(self.__wnd_hidden)
wnd_visible = property(get_wnd_visible, set_wnd_visible)
#################################################################
def set_wnd_mini(self, value):
self.__wnd_mini = int(value)
def get_wnd_mini(self):
return bool(self.__wnd_mini)
wnd_mini = property(get_wnd_mini, set_wnd_mini)
#################################################################
def set_hscroll_visible(self, value):
self.__hscroll_visible = int(value)
def get_hscroll_visible(self):
return bool(self.__hscroll_visible)
hscroll_visible = property(get_hscroll_visible, set_hscroll_visible)
#################################################################
def set_vscroll_visible(self, value):
self.__vscroll_visible = int(value)
def get_vscroll_visible(self):
return bool(self.__vscroll_visible)
vscroll_visible = property(get_vscroll_visible, set_vscroll_visible)
#################################################################
def set_tabs_visible(self, value):
self.__tabs_visible = int(value)
def get_tabs_visible(self):
return bool(self.__tabs_visible)
tabs_visible = property(get_tabs_visible, set_tabs_visible)
#################################################################
def set_dates_1904(self, value):
self.__dates_1904 = int(value)
def get_dates_1904(self):
return bool(self.__dates_1904)
dates_1904 = property(get_dates_1904, set_dates_1904)
#################################################################
def set_use_cell_values(self, value):
self.__use_cell_values = int(value)
def get_use_cell_values(self):
return bool(self.__use_cell_values)
use_cell_values = property(get_use_cell_values, set_use_cell_values)
#################################################################
def get_default_style(self):
return self.__styles.default_style
default_style = property(get_default_style)
##################################################################
## Methods
##################################################################
def add_style(self, style):
return self.__styles.add(style)
def add_str(self, s):
return self.__sst.add_str(s)
def del_str(self, sst_idx):
self.__sst.del_str(sst_idx)
def str_index(self, s):
return self.__sst.str_index(s)
def add_sheet(self, sheetname, cell_overwrite_ok=False):
import Worksheet, Utils
if not isinstance(sheetname, unicode):
sheetname = sheetname.decode(self.encoding)
if not Utils.valid_sheet_name(sheetname):
raise Exception("invalid worksheet name %r" % sheetname)
lower_name = sheetname.lower()
if lower_name in self.__worksheet_idx_from_name:
raise Exception("duplicate worksheet name %r" % sheetname)
self.__worksheet_idx_from_name[lower_name] = len(self.__worksheets)
self.__worksheets.append(Worksheet.Worksheet(sheetname, self, cell_overwrite_ok))
return self.__worksheets[-1]
def get_sheet(self, sheetnum):
return self.__worksheets[sheetnum]
def raise_bad_sheetname(self, sheetname):
raise Exception("Formula: unknown sheet name %s" % sheetname)
def convert_sheetindex(self, strg_ref, n_sheets):
idx = int(strg_ref)
if 0 <= idx < n_sheets:
return idx
msg = "Formula: sheet index (%s) >= number of sheets (%d)" % (strg_ref, n_sheets)
raise Exception(msg)
def _get_supbook_index(self, tag):
if tag in self._supbook_xref:
return self._supbook_xref[tag]
self._supbook_xref[tag] = idx = len(self._supbook_xref)
return idx
def setup_ownbook(self):
self._ownbook_supbookx = self._get_supbook_index(('ownbook', 0))
self._ownbook_supbook_ref = None
reference = (self._ownbook_supbookx, 0xFFFE, 0xFFFE)
if reference in self.__sheet_refs:
raise Exception("can't happen")
self.__sheet_refs[reference] = self._ownbook_supbook_ref = len(self.__sheet_refs)
def setup_xcall(self):
self._xcall_supbookx = self._get_supbook_index(('xcall', 0))
self._xcall_supbook_ref = None
reference = (self._xcall_supbookx, 0xFFFE, 0xFFFE)
if reference in self.__sheet_refs:
raise Exception("can't happen")
self.__sheet_refs[reference] = self._xcall_supbook_ref = len(self.__sheet_refs)
def add_sheet_reference(self, formula):
patches = []
n_sheets = len(self.__worksheets)
sheet_refs, xcall_refs = formula.get_references()
for ref0, ref1, offset in sheet_refs:
if not ref0.isdigit():
try:
ref0n = self.__worksheet_idx_from_name[ref0.lower()]
except KeyError:
self.raise_bad_sheetname(ref0)
else:
ref0n = self.convert_sheetindex(ref0, n_sheets)
if ref1 == ref0:
ref1n = ref0n
elif not ref1.isdigit():
try:
ref1n = self.__worksheet_idx_from_name[ref1.lower()]
except KeyError:
self.raise_bad_sheetname(ref1)
else:
ref1n = self.convert_sheetindex(ref1, n_sheets)
if ref1n < ref0n:
msg = "Formula: sheets out of order; %r:%r -> (%d, %d)" \
% (ref0, ref1, ref0n, ref1n)
raise Exception(msg)
if self._ownbook_supbookx is None:
self.setup_ownbook()
reference = (self._ownbook_supbookx, ref0n, ref1n)
if reference in self.__sheet_refs:
patches.append((offset, self.__sheet_refs[reference]))
else:
nrefs = len(self.__sheet_refs)
if nrefs > 65535:
raise Exception('More than 65536 inter-sheet references')
self.__sheet_refs[reference] = nrefs
patches.append((offset, nrefs))
for funcname, offset in xcall_refs:
if self._ownbook_supbookx is None:
self.setup_ownbook()
if self._xcall_supbookx is None:
self.setup_xcall()
# print funcname, self._supbook_xref
patches.append((offset, self._xcall_supbook_ref))
if not isinstance(funcname, unicode):
funcname = funcname.decode(self.encoding)
if funcname in self._xcall_xref:
idx = self._xcall_xref[funcname]
else:
self._xcall_xref[funcname] = idx = len(self._xcall_xref)
patches.append((offset + 2, idx + 1))
formula.patch_references(patches)
##################################################################
## BIFF records generation
##################################################################
def __bof_rec(self):
return BIFFRecords.Biff8BOFRecord(BIFFRecords.Biff8BOFRecord.BOOK_GLOBAL).get()
def __eof_rec(self):
return BIFFRecords.EOFRecord().get()
def __intf_hdr_rec(self):
return BIFFRecords.InteraceHdrRecord().get()
def __intf_end_rec(self):
return BIFFRecords.InteraceEndRecord().get()
def __intf_mms_rec(self):
return BIFFRecords.MMSRecord().get()
def __write_access_rec(self):
return BIFFRecords.WriteAccessRecord(self.__owner).get()
def __wnd_protect_rec(self):
return BIFFRecords.WindowProtectRecord(self.__wnd_protect).get()
def __obj_protect_rec(self):
return BIFFRecords.ObjectProtectRecord(self.__obj_protect).get()
def __protect_rec(self):
return BIFFRecords.ProtectRecord(self.__protect).get()
def __password_rec(self):
return BIFFRecords.PasswordRecord().get()
def __prot4rev_rec(self):
return BIFFRecords.Prot4RevRecord().get()
def __prot4rev_pass_rec(self):
return BIFFRecords.Prot4RevPassRecord().get()
def __backup_rec(self):
return BIFFRecords.BackupRecord(self.__backup_on_save).get()
def __hide_obj_rec(self):
return BIFFRecords.HideObjRecord().get()
def __window1_rec(self):
flags = 0
flags |= (self.__wnd_hidden) << 0
flags |= (self.__wnd_mini) << 1
flags |= (self.__hscroll_visible) << 3
flags |= (self.__vscroll_visible) << 4
flags |= (self.__tabs_visible) << 5
return BIFFRecords.Window1Record(self.__hpos_twips, self.__vpos_twips,
self.__width_twips, self.__height_twips,
flags,
self.__active_sheet, self.__first_tab_index,
self.__selected_tabs, self.__tab_width_twips).get()
def __codepage_rec(self):
return BIFFRecords.CodepageBiff8Record().get()
def __country_rec(self):
if not self.__country_code:
return ''
return BIFFRecords.CountryRecord(self.__country_code, self.__country_code).get()
def __dsf_rec(self):
return BIFFRecords.DSFRecord().get()
def __tabid_rec(self):
return BIFFRecords.TabIDRecord(len(self.__worksheets)).get()
def __fngroupcount_rec(self):
return BIFFRecords.FnGroupCountRecord().get()
def __datemode_rec(self):
return BIFFRecords.DateModeRecord(self.__dates_1904).get()
def __precision_rec(self):
return BIFFRecords.PrecisionRecord(self.__use_cell_values).get()
def __refresh_all_rec(self):
return BIFFRecords.RefreshAllRecord().get()
def __bookbool_rec(self):
return BIFFRecords.BookBoolRecord().get()
def __all_fonts_num_formats_xf_styles_rec(self):
return self.__styles.get_biff_data()
def __palette_rec(self):
result = ''
return result
def __useselfs_rec(self):
return BIFFRecords.UseSelfsRecord().get()
def __boundsheets_rec(self, data_len_before, data_len_after, sheet_biff_lens):
# .................................
# BOUNDSEHEET0
# BOUNDSEHEET1
# BOUNDSEHEET2
# ..................................
# WORKSHEET0
# WORKSHEET1
# WORKSHEET2
boundsheets_len = 0
for sheet in self.__worksheets:
boundsheets_len += len(BIFFRecords.BoundSheetRecord(
0x00L, sheet.visibility, sheet.name, self.encoding
).get())
start = data_len_before + boundsheets_len + data_len_after
result = ''
for sheet_biff_len, sheet in zip(sheet_biff_lens, self.__worksheets):
result += BIFFRecords.BoundSheetRecord(
start, sheet.visibility, sheet.name, self.encoding
).get()
start += sheet_biff_len
return result
def __all_links_rec(self):
pieces = []
temp = [(idx, tag) for tag, idx in self._supbook_xref.items()]
temp.sort()
for idx, tag in temp:
stype, snum = tag
if stype == 'ownbook':
rec = BIFFRecords.InternalReferenceSupBookRecord(len(self.__worksheets)).get()
pieces.append(rec)
elif stype == 'xcall':
rec = BIFFRecords.XcallSupBookRecord().get()
pieces.append(rec)
temp = [(idx, name) for name, idx in self._xcall_xref.items()]
temp.sort()
for idx, name in temp:
rec = BIFFRecords.ExternnameRecord(
options=0, index=0, name=name, fmla='\x02\x00\x1c\x17').get()
pieces.append(rec)
else:
raise Exception('unknown supbook stype %r' % stype)
if len(self.__sheet_refs) > 0:
# get references in index order
temp = [(idx, ref) for ref, idx in self.__sheet_refs.items()]
temp.sort()
temp = [ref for idx, ref in temp]
externsheet_record = BIFFRecords.ExternSheetRecord(temp).get()
pieces.append(externsheet_record)
return ''.join(pieces)
def __sst_rec(self):
return self.__sst.get_biff_record()
def __ext_sst_rec(self, abs_stream_pos):
return ''
#return BIFFRecords.ExtSSTRecord(abs_stream_pos, self.sst_record.str_placement,
#self.sst_record.portions_len).get()
def get_biff_data(self):
before = ''
before += self.__bof_rec()
before += self.__intf_hdr_rec()
before += self.__intf_mms_rec()
before += self.__intf_end_rec()
before += self.__write_access_rec()
before += self.__codepage_rec()
before += self.__dsf_rec()
before += self.__tabid_rec()
before += self.__fngroupcount_rec()
before += self.__wnd_protect_rec()
before += self.__protect_rec()
before += self.__obj_protect_rec()
before += self.__password_rec()
before += self.__prot4rev_rec()
before += self.__prot4rev_pass_rec()
before += self.__backup_rec()
before += self.__hide_obj_rec()
before += self.__window1_rec()
before += self.__datemode_rec()
before += self.__precision_rec()
before += self.__refresh_all_rec()
before += self.__bookbool_rec()
before += self.__all_fonts_num_formats_xf_styles_rec()
before += self.__palette_rec()
before += self.__useselfs_rec()
country = self.__country_rec()
all_links = self.__all_links_rec()
shared_str_table = self.__sst_rec()
after = country + all_links + shared_str_table
ext_sst = self.__ext_sst_rec(0) # need fake cause we need calc stream pos
eof = self.__eof_rec()
self.__worksheets[self.__active_sheet].selected = True
sheets = ''
sheet_biff_lens = []
for sheet in self.__worksheets:
data = sheet.get_biff_data()
sheets += data
sheet_biff_lens.append(len(data))
bundlesheets = self.__boundsheets_rec(len(before), len(after)+len(ext_sst)+len(eof), sheet_biff_lens)
sst_stream_pos = len(before) + len(bundlesheets) + len(country) + len(all_links)
ext_sst = self.__ext_sst_rec(sst_stream_pos)
return before + bundlesheets + after + ext_sst + eof + sheets
def save(self, filename):
import CompoundDoc
doc = CompoundDoc.XlsDoc()
doc.save(filename, self.get_biff_data())
File diff suppressed because it is too large Load Diff
-13
View File
@@ -1,13 +0,0 @@
# -*- coding: windows-1252 -*-
__VERSION__ = '0.7.2'
import sys
from Workbook import Workbook
from Worksheet import Worksheet
from Row import Row
from Column import Column
from Formatting import Font, Alignment, Borders, Pattern, Protection
from Style import XFStyle, easyxf
from ExcelFormula import *
File diff suppressed because it is too large Load Diff
-199
View File
@@ -1,199 +0,0 @@
<!DOCTYPE html PUBLIC '-//W3C//DTD XHTML 1.0 Strict//EN' 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd'>
<html>
<head>
<meta http-equiv='Content-Type' content='text/html; charset=us-ascii' />
<title>The xlwt Module</title>
</head>
<body>
<h1>The xlwt Module</h1>
<p /><p><b>A Python package for generating Microsoft Excel &#8482; spreadsheet files.
</b></p>
<h2>General information</h2>
<h3>State of Documentation</h3>
<p>
This documentation is currently incomplete. There may be methods and
classes not included and any item marked with a <em
style="color:red;">[NC]</em> is not complete and may have further
parameters, methods, attributes and functionality that are not
documented. In these cases, you'll have to refer to the source if the
documentation provided is insufficient.
</p>
</p>
<h2>Module Contents <em style="color:red;">[NC]</em></h2>
<dl>
<dt><b>easyxf</b> (function)</dt>
<dd>
<p>
This function is used to create and configure XFStyle objects
for use with (for example) the Worksheet.write method.
</p>
<dl>
<dt><i>strg_to_parse</i></dt>
<dd>
<p>
A string to be parsed to obtain attribute values for Alignment, Borders, Font,
Pattern and Protection objects. Refer to the examples
in the file .../examples/xlwt_easyxf_simple_demo.py and to the xf_dict
dictionary in Style.py. Various synonyms including color/colour, center/centre and gray/grey
are allowed. Case is irrelevant (except maybe in font names). '-' may be used instead
of '_'.<br />
Example: "font: bold on; align: wrap on, vert centre, horiz center"
</p>
</dd>
<dt><i>num_format_str</i></dt>
<dd>
<p>
To get the "number format string" of an existing cell whose format you want to reproduce,
select the cell and click on Format/Cells/Number/Custom. Otherwise, refer to Excel help.<br />
Examples: "#,##0.00", "dd/mm/yyyy"
</p>
</dd>
<dt>Returns:</dt>
<dd>
An object of the XFstyle class
</dd>
</dl>
<br />
</dd>
<dt><b>Workbook</b> (class) [<a href='#xlwt.Workbook-class'>#</a>]</dt>
<dd>
<p>The class to instantiate to create a workbook</p>
<p>For more information about this class, see <a href='#xlwt.Workbook-class'><i>The Workbook Class</i></a>.</p>
</dd>
<dt><b>Worksheet</b> (class) [<a href='#xlwt.Worksheet-class'>#</a>]</dt>
<dd>
<p>A class to represent the contents of a sheet in a workbook.</p>
<p>For more information about this class, see <a href='#xlwt.Worksheet-class'><i>The Worksheet Class</i></a>.</p>
</dd>
</dl>
<h2><a id='xlwt.Workbook-class' name='xlwt.Workbook-class'>The Workbook Class</a><em style="color:red;">[NC]</em></h2>
<dl>
<dt><b>Workbook(encoding='ascii',style_compression=0)</b> (class) [<a href='#xlwt.Workbook-class'>#</a>]</dt>
<dd>
<p>
This is a class representing a workbook and all its contents.
When creating Excel files with xlwt, you will normally start by
instantiating an object of this class.
</p>
<dl>
<dt><i>encoding</i></dt>
<dd>
<em style="color:red;">[NC]</em>
</dd>
<dt><i>style_compression</i></dt>
<dd>
<em style="color:red;">[NC]</em>
</dd>
<dt>Returns:</dt>
<dd>
An object of the <a href="#xlwt.Workbook-class">Workbook</a> class
</dd>
</dl>
<br />
</dd>
<dt><a id='xlwt.Workbook.add_sheet-method' name='xlwt.Workbook.add_sheet-method'><b>add_sheet(sheetname)</b></a> [<a href='#xlwt.Workbook.add_sheet-method'>#</a>]</dt>
<dd>
<p>
This method is used to create Worksheets in a Workbook.
</p>
<dl>
<dt><i>sheetname</i></dt>
<dd>
The name to use for this sheet, as it will appear in the tabs at
the bottom of the Excel application.
</dd>
<dt>Returns:</dt>
<dd>
An object of the <a href="#xlwt.Worksheet-class">Worksheet</a> class
</dd>
</dl>
<br />
</dd>
<dt><a id='xlwt.Workbook.save-method' name='xlwt.Workbook.save-method'><b>save(filename_or_stream)</b></a> [<a href='#xlwt.Workbook.save-method'>#</a>]</dt>
<dd>
<p>
This method is used to save Workbook to a file in native Excel format.
</p>
<dl>
<dt><i>filename_or_stream</i></dt>
<dd>
<p>
This can be a string containing a filename of the file, in which case
the excel file is saved to disk using the name provided.
</p>
<p>
It can also be a stream object with a write method, such as a
StringIO, in which case the data for the excel file is written
to the stream.
</p>
</dd>
</dl>
<br />
</dd>
</dl>
<h2><a id='xlwt.Worksheet-class' name='xlwt.Worksheet-class'>The Worksheet Class</a><em style="color:red;">[NC]</em></h2>
<dl>
<dt><b>Worksheet(sheetname, parent_book)</b> (class) [<a href='#xlwt.Worksheet-class'>#</a>]</dt>
<dd>
<p>
This is a class representing the contents of a sheet in a workbook.
</p>
<p>
WARNING: You don't normally create instances of this class
yourself. They are returned from calls to <a href="#xlwt.Workbook.add_sheet-method">Workbook.add_sheet</a>
</p>
</dd>
<dt><a id='xlwt.Worksheet.write-method'
name='xlwt.Worksheet.write-method'><b>write(r, c, label="", style=Style.default_style)</b></a> [<a href='#xlwt.Worksheet.write-method'>#</a>]</dt>
<dd>
<p>
This method is used to write a cell to a Worksheet..
</p>
<dl>
<dt><i>r</i></dt>
<dd>
The zero-relative number of the row in the worksheet to which the cell should be written.
</dd>
<dt><i>c</i></dt>
<dd>
The zero-relative number of the column in the worksheet to which the cell should be written.
</dd>
<dt><i>label</i></dt>
<dd>
The data value to be written.
An int, long, or decimal.Decimal instance is converted to float.
A unicode instance is written as is.
A str instance is converted to unicode using the encoding (default: 'ascii') specified
when the Workbook instance was created.
A datetime.datetime, datetime.date, or datetime.time instance is converted into Excel date format
(a float representing the number of days since (typically) 1899-12-31T00:00:00,
under the pretence that 1900 was a leap year).
A bool instance will show up as TRUE or FALSE in Excel.
None causes the cell to be blank -- no data, only formatting.
An xlwt.Formula instance causes an Excel formula to be written.
<em style="color:red;">[NC]</em>
</dd>
<dt><i>style</i></dt>
<dd>
A style -- also known as an XF (extended format) -- is an XFStyle object, which encapsulates
the formatting applied to the cell and its contents. XFStyle objects are best set up using the
<i>easyxf</i> function. They may also be set up by setting attributes in
Alignment, Borders, Pattern, Font and Protection objects
then setting those objects and a format string as attributes of an XFStyle object.
<em style="color:red;">[NC]</em>
</dd>
</dl>
<br />
</dd>
</dl>
</body></html>
-35
View File
@@ -1,35 +0,0 @@
#!/usr/bin/env python
# tries stress SST, SAT and MSAT
from time import *
from xlwt.Workbook import *
from xlwt.Style import *
style = XFStyle()
wb = Workbook()
ws0 = wb.add_sheet('0')
colcount = 200 + 1
rowcount = 6000 + 1
t0 = time()
print "\nstart: %s" % ctime(t0)
print "Filling..."
for col in xrange(colcount):
print "[%d]" % col,
for row in xrange(rowcount):
#ws0.write(row, col, "BIG(%d, %d)" % (row, col))
ws0.write(row, col, "BIG")
t1 = time() - t0
print "\nsince starting elapsed %.2f s" % (t1)
print "Storing..."
wb.save('big-16Mb.xls')
t2 = time() - t0
print "since starting elapsed %.2f s" % (t2)
-34
View File
@@ -1,34 +0,0 @@
#!/usr/bin/env python
# tries stress SST, SAT and MSAT
from time import *
from xlwt import *
style = XFStyle()
wb = Workbook()
ws0 = wb.add_sheet('0')
colcount = 200 + 1
rowcount = 6000 + 1
t0 = time()
print "\nstart: %s" % ctime(t0)
print "Filling..."
for col in xrange(colcount):
print "[%d]" % col,
for row in xrange(rowcount):
ws0.write(row, col, "BIG(%d, %d)" % (row, col))
#ws0.write(row, col, "BIG")
t1 = time() - t0
print "\nsince starting elapsed %.2f s" % (t1)
print "Storing..."
wb.save('big-35Mb.xls')
t2 = time() - t0
print "since starting elapsed %.2f s" % (t2)
-36
View File
@@ -1,36 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
font0 = Font()
font0.name = 'Times New Roman'
font0.struck_out = True
font0.bold = True
style0 = XFStyle()
style0.font = font0
wb = Workbook()
ws0 = wb.add_sheet('0')
ws0.write(1, 1, 'Test', style0)
for i in range(0, 0x53):
borders = Borders()
borders.left = i
borders.right = i
borders.top = i
borders.bottom = i
style = XFStyle()
style.borders = borders
ws0.write(i, 2, '', style)
ws0.write(i, 3, hex(i), style0)
ws0.write_merge(5, 8, 6, 10, "")
wb.save('blanks.xls')
@@ -1,19 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
__rev_id__ = """$Id: col_width.py 3315 2008-03-14 14:44:52Z chris $"""
from xlwt import *
w = Workbook()
ws = w.add_sheet('Hey, Dude')
for i in range(6, 80):
fnt = Font()
fnt.height = i*20
style = XFStyle()
style.font = fnt
ws.write(1, i, 'Test')
ws.col(i).width = 0x0d00 + i
w.save('col_width.xls')
-10
View File
@@ -1,10 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1252 -*-
# Copyright (C) 2007 John Machin
from xlwt import *
w = Workbook()
w.country_code = 61
ws = w.add_sheet('AU')
w.save('country.xls')
-37
View File
@@ -1,37 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
from datetime import datetime
w = Workbook()
ws = w.add_sheet('Hey, Dude')
fmts = [
'M/D/YY',
'D-MMM-YY',
'D-MMM',
'MMM-YY',
'h:mm AM/PM',
'h:mm:ss AM/PM',
'h:mm',
'h:mm:ss',
'M/D/YY h:mm',
'mm:ss',
'[h]:mm:ss',
'mm:ss.0',
]
i = 0
for fmt in fmts:
ws.write(i, 0, fmt)
style = XFStyle()
style.num_format_str = fmt
ws.write(i, 4, datetime.now(), style)
i += 1
w.save('dates.xls')
-38
View File
@@ -1,38 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
font0 = Font()
font0.name = 'Times New Roman'
font0.struck_out = True
font0.bold = True
style0 = XFStyle()
style0.font = font0
wb = Workbook()
ws0 = wb.add_sheet('0')
ws0.write(1, 1, 'Test', style0)
for i in range(0, 0x53):
fnt = Font()
fnt.name = 'Arial'
fnt.colour_index = i
fnt.outline = True
borders = Borders()
borders.left = i
style = XFStyle()
style.font = fnt
style.borders = borders
ws0.write(i, 2, 'colour', style)
ws0.write(i, 3, hex(i), style0)
wb.save('format.xls')
@@ -1,34 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
from xlwt.ExcelFormulaParser import FormulaParseException
w = Workbook()
ws = w.add_sheet('F')
## This example is a little silly since the formula building is
## so simplistic that it often fails because the generated text
## has the wrong number of parameters for the function being
## tested.
i = 0
succeed_count = 0
fail_count = 0
for n in sorted(ExcelMagic.std_func_by_name):
ws.write(i, 0, n)
text = n + "($A$1)"
try:
formula = Formula(text)
except FormulaParseException,e:
print "Could not parse %r: %s" % (text,e.args[0])
fail_count += 1
else:
ws.write(i, 3, formula)
succeed_count += 1
i += 1
w.save('formula_names.xls')
print "succeeded with %i functions, failed with %i" % (succeed_count,fail_count)
-47
View File
@@ -1,47 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws = w.add_sheet('F')
ws.write(0, 0, Formula("-(1+1)"))
ws.write(1, 0, Formula("-(1+1)/(-2-2)"))
ws.write(2, 0, Formula("-(134.8780789+1)"))
ws.write(3, 0, Formula("-(134.8780789e-10+1)"))
ws.write(4, 0, Formula("-1/(1+1)+9344"))
ws.write(0, 1, Formula("-(1+1)"))
ws.write(1, 1, Formula("-(1+1)/(-2-2)"))
ws.write(2, 1, Formula("-(134.8780789+1)"))
ws.write(3, 1, Formula("-(134.8780789e-10+1)"))
ws.write(4, 1, Formula("-1/(1+1)+9344"))
ws.write(0, 2, Formula("A1*B1"))
ws.write(1, 2, Formula("A2*B2"))
ws.write(2, 2, Formula("A3*B3"))
ws.write(3, 2, Formula("A4*B4*sin(pi()/4)"))
ws.write(4, 2, Formula("A5%*B5*pi()/1000"))
##############
## NOTE: parameters are separated by semicolon!!!
##############
ws.write(5, 2, Formula("C1+C2+C3+C4+C5/(C1+C2+C3+C4/(C1+C2+C3+C4/(C1+C2+C3+C4)+C5)+C5)-20.3e-2"))
ws.write(5, 3, Formula("C1^2"))
ws.write(6, 2, Formula("SUM(C1;C2;;;;;C3;;;C4)"))
ws.write(6, 3, Formula("SUM($A$1:$C$5)"))
ws.write(7, 0, Formula('"lkjljllkllkl"'))
ws.write(7, 1, Formula('"yuyiyiyiyi"'))
ws.write(7, 2, Formula('A8 & B8 & A8'))
ws.write(8, 2, Formula('now()'))
ws.write(10, 2, Formula('TRUE'))
ws.write(11, 2, Formula('FALSE'))
ws.write(12, 3, Formula('IF(A1>A2;3;"hkjhjkhk")'))
w.save('formulas.xls')
@@ -1,28 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
f = Font()
f.height = 20*72
f.name = 'Verdana'
f.bold = True
f.underline = Font.UNDERLINE_DOUBLE
f.colour_index = 4
h_style = XFStyle()
h_style.font = f
w = Workbook()
ws = w.add_sheet('F')
##############
## NOTE: parameters are separated by semicolon!!!
##############
n = "HYPERLINK"
ws.write_merge(1, 1, 1, 10, Formula(n + '("http://www.irs.gov/pub/irs-pdf/f1000.pdf";"f1000.pdf")'), h_style)
ws.write_merge(2, 2, 2, 25, Formula(n + '("mailto:roman.kiseliov@gmail.com?subject=pyExcelerator-feedback&Body=Hello,%20Roman!";"pyExcelerator-feedback")'), h_style)
w.save("hyperlinks.xls")
-12
View File
@@ -1,12 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws = w.add_sheet('Image')
ws.insert_bitmap('python.bmp', 2, 2)
ws.insert_bitmap('python.bmp', 10, 2)
w.save('image.xls')
-39
View File
@@ -1,39 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
fnt = Font()
fnt.name = 'Arial'
fnt.colour_index = 4
fnt.bold = True
borders = Borders()
borders.left = 6
borders.right = 6
borders.top = 6
borders.bottom = 6
al = Alignment()
al.horz = Alignment.HORZ_CENTER
al.vert = Alignment.VERT_CENTER
style = XFStyle()
style.font = fnt
style.borders = borders
style.alignment = al
wb = Workbook()
ws0 = wb.add_sheet('sheet0')
ws1 = wb.add_sheet('sheet1')
ws2 = wb.add_sheet('sheet2')
for i in range(0, 0x200, 2):
ws0.write_merge(i, i+1, 1, 5, 'test %d' % i, style)
ws1.write_merge(i, i, 1, 7, 'test %d' % i, style)
ws2.write_merge(i, i+1, 1, 7 + (i%10), 'test %d' % i, style)
wb.save('merged.xls')
-30
View File
@@ -1,30 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
wb = Workbook()
ws0 = wb.add_sheet('sheet0')
fnt = Font()
fnt.name = 'Arial'
fnt.colour_index = 4
fnt.bold = True
borders = Borders()
borders.left = 6
borders.right = 6
borders.top = 6
borders.bottom = 6
style = XFStyle()
style.font = fnt
style.borders = borders
ws0.write_merge(3, 3, 1, 5, 'test1', style)
ws0.write_merge(4, 10, 1, 5, 'test2', style)
ws0.col(1).width = 0x0d00
wb.save('merged0.xls')
-102
View File
@@ -1,102 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
wb = Workbook()
ws0 = wb.add_sheet('sheet0')
fnt1 = Font()
fnt1.name = 'Verdana'
fnt1.bold = True
fnt1.height = 18*0x14
pat1 = Pattern()
pat1.pattern = Pattern.SOLID_PATTERN
pat1.pattern_fore_colour = 0x16
brd1 = Borders()
brd1.left = 0x06
brd1.right = 0x06
brd1.top = 0x06
brd1.bottom = 0x06
fnt2 = Font()
fnt2.name = 'Verdana'
fnt2.bold = True
fnt2.height = 14*0x14
brd2 = Borders()
brd2.left = 0x01
brd2.right = 0x01
brd2.top = 0x01
brd2.bottom = 0x01
pat2 = Pattern()
pat2.pattern = Pattern.SOLID_PATTERN
pat2.pattern_fore_colour = 0x01F
fnt3 = Font()
fnt3.name = 'Verdana'
fnt3.bold = True
fnt3.italic = True
fnt3.height = 12*0x14
brd3 = Borders()
brd3.left = 0x07
brd3.right = 0x07
brd3.top = 0x07
brd3.bottom = 0x07
fnt4 = Font()
al1 = Alignment()
al1.horz = Alignment.HORZ_CENTER
al1.vert = Alignment.VERT_CENTER
al2 = Alignment()
al2.horz = Alignment.HORZ_RIGHT
al2.vert = Alignment.VERT_CENTER
al3 = Alignment()
al3.horz = Alignment.HORZ_LEFT
al3.vert = Alignment.VERT_CENTER
style1 = XFStyle()
style1.font = fnt1
style1.alignment = al1
style1.pattern = pat1
style1.borders = brd1
style2 = XFStyle()
style2.font = fnt2
style2.alignment = al1
style2.pattern = pat2
style2.borders = brd2
style3 = XFStyle()
style3.font = fnt3
style3.alignment = al1
style3.pattern = pat2
style3.borders = brd3
price_style = XFStyle()
price_style.font = fnt4
price_style.alignment = al2
price_style.borders = brd3
price_style.num_format_str = '_(#,##0.00_) "money"'
ware_style = XFStyle()
ware_style.font = fnt4
ware_style.alignment = al3
ware_style.borders = brd3
ws0.merge(3, 3, 1, 5, style1)
ws0.merge(4, 10, 1, 6, style2)
ws0.merge(14, 16, 1, 7, style3)
ws0.col(1).width = 0x0d00
wb.save('merged1.xls')
-9
View File
@@ -1,9 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws = w.add_sheet('xlwt was here')
w.save('mini.xls')
@@ -1,60 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws = w.add_sheet('Hey, Dude')
fmts = [
'general',
'0',
'0.00',
'#,##0',
'#,##0.00',
'"$"#,##0_);("$"#,##',
'"$"#,##0_);[Red]("$"#,##',
'"$"#,##0.00_);("$"#,##',
'"$"#,##0.00_);[Red]("$"#,##',
'0%',
'0.00%',
'0.00E+00',
'# ?/?',
'# ??/??',
'M/D/YY',
'D-MMM-YY',
'D-MMM',
'MMM-YY',
'h:mm AM/PM',
'h:mm:ss AM/PM',
'h:mm',
'h:mm:ss',
'M/D/YY h:mm',
'_(#,##0_);(#,##0)',
'_(#,##0_);[Red](#,##0)',
'_(#,##0.00_);(#,##0.00)',
'_(#,##0.00_);[Red](#,##0.00)',
'_("$"* #,##0_);_("$"* (#,##0);_("$"* "-"_);_(@_)',
'_(* #,##0_);_(* (#,##0);_(* "-"_);_(@_)',
'_("$"* #,##0.00_);_("$"* (#,##0.00);_("$"* "-"??_);_(@_)',
'_(* #,##0.00_);_(* (#,##0.00);_(* "-"??_);_(@_)',
'mm:ss',
'[h]:mm:ss',
'mm:ss.0',
'##0.0E+0',
'@'
]
i = 0
for fmt in fmts:
ws.write(i, 0, fmt)
style = XFStyle()
style.num_format_str = fmt
ws.write(i, 4, -1278.9078, style)
i += 1
w.save('num_formats.xls')
-25
View File
@@ -1,25 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws = w.add_sheet('Hey, Dude')
ws.write(0, 0, 1)
ws.write(1, 0, 1.23)
ws.write(2, 0, 12345678)
ws.write(3, 0, 123456.78)
ws.write(0, 1, -1)
ws.write(1, 1, -1.23)
ws.write(2, 1, -12345678)
ws.write(3, 1, -123456.78)
ws.write(0, 2, -17867868678687.0)
ws.write(1, 2, -1.23e-5)
ws.write(2, 2, -12345678.90780980)
ws.write(3, 2, -123456.78)
w.save('numbers.xls')
-113
View File
@@ -1,113 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
fnt = Font()
fnt.name = 'Arial'
fnt.colour_index = 4
fnt.bold = True
borders = Borders()
borders.left = 6
borders.right = 6
borders.top = 6
borders.bottom = 6
style = XFStyle()
style.font = fnt
style.borders = borders
wb = Workbook()
ws0 = wb.add_sheet('Rows Outline')
ws0.write_merge(1, 1, 1, 5, 'test 1', style)
ws0.write_merge(2, 2, 1, 4, 'test 1', style)
ws0.write_merge(3, 3, 1, 3, 'test 2', style)
ws0.write_merge(4, 4, 1, 4, 'test 1', style)
ws0.write_merge(5, 5, 1, 4, 'test 3', style)
ws0.write_merge(6, 6, 1, 5, 'test 1', style)
ws0.write_merge(7, 7, 1, 5, 'test 4', style)
ws0.write_merge(8, 8, 1, 4, 'test 1', style)
ws0.write_merge(9, 9, 1, 3, 'test 5', style)
ws0.row(1).level = 1
ws0.row(2).level = 1
ws0.row(3).level = 2
ws0.row(4).level = 2
ws0.row(5).level = 2
ws0.row(6).level = 2
ws0.row(7).level = 2
ws0.row(8).level = 1
ws0.row(9).level = 1
ws1 = wb.add_sheet('Columns Outline')
ws1.write_merge(1, 1, 1, 5, 'test 1', style)
ws1.write_merge(2, 2, 1, 4, 'test 1', style)
ws1.write_merge(3, 3, 1, 3, 'test 2', style)
ws1.write_merge(4, 4, 1, 4, 'test 1', style)
ws1.write_merge(5, 5, 1, 4, 'test 3', style)
ws1.write_merge(6, 6, 1, 5, 'test 1', style)
ws1.write_merge(7, 7, 1, 5, 'test 4', style)
ws1.write_merge(8, 8, 1, 4, 'test 1', style)
ws1.write_merge(9, 9, 1, 3, 'test 5', style)
ws1.col(1).level = 1
ws1.col(2).level = 1
ws1.col(3).level = 2
ws1.col(4).level = 2
ws1.col(5).level = 2
ws1.col(6).level = 2
ws1.col(7).level = 2
ws1.col(8).level = 1
ws1.col(9).level = 1
ws2 = wb.add_sheet('Rows and Columns Outline')
ws2.write_merge(1, 1, 1, 5, 'test 1', style)
ws2.write_merge(2, 2, 1, 4, 'test 1', style)
ws2.write_merge(3, 3, 1, 3, 'test 2', style)
ws2.write_merge(4, 4, 1, 4, 'test 1', style)
ws2.write_merge(5, 5, 1, 4, 'test 3', style)
ws2.write_merge(6, 6, 1, 5, 'test 1', style)
ws2.write_merge(7, 7, 1, 5, 'test 4', style)
ws2.write_merge(8, 8, 1, 4, 'test 1', style)
ws2.write_merge(9, 9, 1, 3, 'test 5', style)
ws2.row(1).level = 1
ws2.row(2).level = 1
ws2.row(3).level = 2
ws2.row(4).level = 2
ws2.row(5).level = 2
ws2.row(6).level = 2
ws2.row(7).level = 2
ws2.row(8).level = 1
ws2.row(9).level = 1
ws2.write_merge(1, 1, 1, 5, 'test 1', style)
ws2.write_merge(2, 2, 1, 4, 'test 1', style)
ws2.write_merge(3, 3, 1, 3, 'test 2', style)
ws2.write_merge(4, 4, 1, 4, 'test 1', style)
ws2.write_merge(5, 5, 1, 4, 'test 3', style)
ws2.write_merge(6, 6, 1, 5, 'test 1', style)
ws2.write_merge(7, 7, 1, 5, 'test 4', style)
ws2.write_merge(8, 8, 1, 4, 'test 1', style)
ws2.write_merge(9, 9, 1, 3, 'test 5', style)
ws2.col(1).level = 1
ws2.col(2).level = 1
ws2.col(3).level = 2
ws2.col(4).level = 2
ws2.col(5).level = 2
ws2.col(6).level = 2
ws2.col(7).level = 2
ws2.col(8).level = 1
ws2.col(9).level = 1
wb.save('outline.xls')
-58
View File
@@ -1,58 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws1 = w.add_sheet('sheet 1')
ws2 = w.add_sheet('sheet 2')
ws3 = w.add_sheet('sheet 3')
ws4 = w.add_sheet('sheet 4')
ws5 = w.add_sheet('sheet 5')
ws6 = w.add_sheet('sheet 6')
for i in range(0x100):
ws1.write(i/0x10, i%0x10, i)
for i in range(0x100):
ws2.write(i/0x10, i%0x10, i)
for i in range(0x100):
ws3.write(i/0x10, i%0x10, i)
for i in range(0x100):
ws4.write(i/0x10, i%0x10, i)
for i in range(0x100):
ws5.write(i/0x10, i%0x10, i)
for i in range(0x100):
ws6.write(i/0x10, i%0x10, i)
ws1.panes_frozen = True
ws1.horz_split_pos = 2
ws2.panes_frozen = True
ws2.vert_split_pos = 2
ws3.panes_frozen = True
ws3.horz_split_pos = 1
ws3.vert_split_pos = 1
ws4.panes_frozen = False
ws4.horz_split_pos = 12
ws4.horz_split_first_visible = 2
ws5.panes_frozen = False
ws5.vert_split_pos = 40
ws4.vert_split_first_visible = 2
ws6.panes_frozen = False
ws6.horz_split_pos = 12
ws4.horz_split_first_visible = 2
ws6.vert_split_pos = 40
ws4.vert_split_first_visible = 2
w.save('panes.xls')
@@ -1,12 +0,0 @@
from xlwt import ExcelFormulaParser, ExcelFormula
import sys
f = ExcelFormula.Formula(
""" -((1.80 + 2.898 * 1)/(1.80 + 2.898))*
AVERAGE((1.80 + 2.898 * 1)/(1.80 + 2.898);
(1.80 + 2.898 * 1)/(1.80 + 2.898);
(1.80 + 2.898 * 1)/(1.80 + 2.898)) +
SIN(PI()/4)""")
#for t in f.rpn():
# print "%15s %15s" % (ExcelFormulaParser.PtgNames[t[0]], t[1])
-122
View File
@@ -1,122 +0,0 @@
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
fnt = Font()
fnt.name = 'Arial'
fnt.colour_index = 4
fnt.bold = True
borders = Borders()
borders.left = 6
borders.right = 6
borders.top = 6
borders.bottom = 6
style = XFStyle()
style.font = fnt
style.borders = borders
wb = Workbook()
ws0 = wb.add_sheet('Rows Outline')
ws0.write_merge(1, 1, 1, 5, 'test 1', style)
ws0.write_merge(2, 2, 1, 4, 'test 1', style)
ws0.write_merge(3, 3, 1, 3, 'test 2', style)
ws0.write_merge(4, 4, 1, 4, 'test 1', style)
ws0.write_merge(5, 5, 1, 4, 'test 3', style)
ws0.write_merge(6, 6, 1, 5, 'test 1', style)
ws0.write_merge(7, 7, 1, 5, 'test 4', style)
ws0.write_merge(8, 8, 1, 4, 'test 1', style)
ws0.write_merge(9, 9, 1, 3, 'test 5', style)
ws0.row(1).level = 1
ws0.row(2).level = 1
ws0.row(3).level = 2
ws0.row(4).level = 2
ws0.row(5).level = 2
ws0.row(6).level = 2
ws0.row(7).level = 2
ws0.row(8).level = 1
ws0.row(9).level = 1
ws1 = wb.add_sheet('Columns Outline')
ws1.write_merge(1, 1, 1, 5, 'test 1', style)
ws1.write_merge(2, 2, 1, 4, 'test 1', style)
ws1.write_merge(3, 3, 1, 3, 'test 2', style)
ws1.write_merge(4, 4, 1, 4, 'test 1', style)
ws1.write_merge(5, 5, 1, 4, 'test 3', style)
ws1.write_merge(6, 6, 1, 5, 'test 1', style)
ws1.write_merge(7, 7, 1, 5, 'test 4', style)
ws1.write_merge(8, 8, 1, 4, 'test 1', style)
ws1.write_merge(9, 9, 1, 3, 'test 5', style)
ws1.col(1).level = 1
ws1.col(2).level = 1
ws1.col(3).level = 2
ws1.col(4).level = 2
ws1.col(5).level = 2
ws1.col(6).level = 2
ws1.col(7).level = 2
ws1.col(8).level = 1
ws1.col(9).level = 1
ws2 = wb.add_sheet('Rows and Columns Outline')
ws2.write_merge(1, 1, 1, 5, 'test 1', style)
ws2.write_merge(2, 2, 1, 4, 'test 1', style)
ws2.write_merge(3, 3, 1, 3, 'test 2', style)
ws2.write_merge(4, 4, 1, 4, 'test 1', style)
ws2.write_merge(5, 5, 1, 4, 'test 3', style)
ws2.write_merge(6, 6, 1, 5, 'test 1', style)
ws2.write_merge(7, 7, 1, 5, 'test 4', style)
ws2.write_merge(8, 8, 1, 4, 'test 1', style)
ws2.write_merge(9, 9, 1, 3, 'test 5', style)
ws2.row(1).level = 1
ws2.row(2).level = 1
ws2.row(3).level = 2
ws2.row(4).level = 2
ws2.row(5).level = 2
ws2.row(6).level = 2
ws2.row(7).level = 2
ws2.row(8).level = 1
ws2.row(9).level = 1
ws2.col(1).level = 1
ws2.col(2).level = 1
ws2.col(3).level = 2
ws2.col(4).level = 2
ws2.col(5).level = 2
ws2.col(6).level = 2
ws2.col(7).level = 2
ws2.col(8).level = 1
ws2.col(9).level = 1
ws0.protect = True
ws0.wnd_protect = True
ws0.obj_protect = True
ws0.scen_protect = True
ws0.password = "123456"
ws1.protect = True
ws1.wnd_protect = True
ws1.obj_protect = True
ws1.scen_protect = True
ws1.password = "abcdefghij"
ws2.protect = True
ws2.wnd_protect = True
ws2.obj_protect = True
ws2.scen_protect = True
ws2.password = "ok"
wb.protect = True
wb.wnd_protect = True
wb.obj_protect = True
wb.save('protection.xls')
Binary file not shown.

Before

Width:  |  Height:  |  Size: 37 KiB

@@ -1,17 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws = w.add_sheet('Hey, Dude')
for i in range(6, 80):
fnt = Font()
fnt.height = i*20
style = XFStyle()
style.font = fnt
ws.write(i, 1, 'Test')
ws.row(i).set_style(style)
w.save('row_styles.xls')
@@ -1,18 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
__rev_id__ = """$Id: row_styles_empty.py 3309 2008-03-14 11:04:30Z chris $"""
from pyExcelerator import *
w = Workbook()
ws = w.add_sheet('Hey, Dude')
for i in range(6, 80):
fnt = Font()
fnt.height = i*20
style = XFStyle()
style.font = fnt
ws.row(i).set_style(style)
w.save('row_styles_empty.xls')
-24
View File
@@ -1,24 +0,0 @@
import xlwt
from datetime import datetime
font0 = xlwt.Font()
font0.name = 'Times New Roman'
font0.colour_index = 2
font0.bold = True
style0 = xlwt.XFStyle()
style0.font = font0
style1 = xlwt.XFStyle()
style1.num_format_str = 'D-MMM-YY'
wb = xlwt.Workbook()
ws = wb.add_sheet('A Test Sheet')
ws.write(0, 0, 'Test', style0)
ws.write(1, 0, datetime.now(), style1)
ws.write(2, 0, 1)
ws.write(2, 1, 1)
ws.write(2, 2, xlwt.Formula("A3+B3"))
wb.save('example.xls')
-52
View File
@@ -1,52 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
font0 = Formatting.Font()
font0.name = 'Arial'
font1 = Formatting.Font()
font1.name = 'Arial Cyr'
font2 = Formatting.Font()
font2.name = 'Times New Roman'
font3 = Formatting.Font()
font3.name = 'Courier New Cyr'
num_format0 = '0.00000'
num_format1 = '0.000000'
num_format2 = '0.0000000'
num_format3 = '0.00000000'
st0 = XFStyle()
st1 = XFStyle()
st2 = XFStyle()
st3 = XFStyle()
st4 = XFStyle()
st0.font = font0
st0.num_format = num_format0
st1.font = font1
st1.num_format = num_format1
st2.font = font2
st2.num_format = num_format2
st3.font = font3
st3.num_format = num_format3
wb = Workbook()
wb.add_style(st0)
wb.add_style(st1)
wb.add_style(st2)
wb.add_style(st3)
ws0 = wb.add_sheet('0')
ws0.write(0, 0, 'Olya'*0x4000, st0)
#for i in range(0, 0x10):
# ws0.write(i, 2, ('%d'%i)*0x4000, st1)
wb.save('sst.xls')
-12
View File
@@ -1,12 +0,0 @@
#!/usr/bin/env python
import xlwt
# Strings passed to (for example) Worksheet.write can be unicode objects,
# or str (8-bit) objects, which are then decoded into unicode.
# The encoding to be used defaults to 'ascii'. This can be overridden
# when the Workbook instance is created:
book = xlwt.Workbook(encoding='cp1251')
sheet = book.add_sheet('cp1251-demo')
sheet.write(0, 0, '\xce\xeb\xff')
book.save('unicode0.xls')
-28
View File
@@ -1,28 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws1 = w.add_sheet(u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK SMALL LETTER BETA}\N{GREEK SMALL LETTER GAMMA}')
ws1.write(0, 0, u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK SMALL LETTER BETA}\N{GREEK SMALL LETTER GAMMA}')
ws1.write(1, 1, u'\N{GREEK SMALL LETTER DELTA}x = 1 + \N{GREEK SMALL LETTER DELTA}')
ws1.write(2,0, u'A\u2262\u0391.') # RFC2152 example
ws1.write(3,0, u'Hi Mom -\u263a-!') # RFC2152 example
ws1.write(4,0, u'\u65E5\u672C\u8A9E') # RFC2152 example
ws1.write(5,0, u'Item 3 is \u00a31.') # RFC2152 example
ws1.write(8,0, u'\N{INTEGRAL}') # RFC2152 example
w.add_sheet(u'A\u2262\u0391.') # RFC2152 example
w.add_sheet(u'Hi Mom -\u263a-!') # RFC2152 example
one_more_ws = w.add_sheet(u'\u65E5\u672C\u8A9E') # RFC2152 example
w.add_sheet(u'Item 3 is \u00a31.') # RFC2152 example
one_more_ws.write(0, 0, u'\u2665\u2665')
w.add_sheet(u'\N{GREEK SMALL LETTER ETA WITH TONOS}')
w.save('unicode1.xls')
-19
View File
@@ -1,19 +0,0 @@
#!/usr/bin/env python
# -*- coding: windows-1251 -*-
# Copyright (C) 2005 Kiseliov Roman
from xlwt import *
w = Workbook()
ws1 = w.add_sheet(u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK SMALL LETTER BETA}\N{GREEK SMALL LETTER GAMMA}\u2665\u041e\u041b\u042f\u2665')
fnt = Font()
fnt.height = 26*20
style = XFStyle()
style.font = fnt
for i in range(0x10000):
ws1.write(i/0x10, i%0x10, unichr(i), style)
w.save('unicode2.xls')
-155
View File
@@ -1,155 +0,0 @@
props = \
[
'name',
'parent',
'rows',
'cols',
'merged_ranges',
'bmp_rec',
'show_formulas',
'show_grid',
'show_headers',
'panes_frozen',
'show_empty_as_zero',
'auto_colour_grid',
'cols_right_to_left',
'show_outline',
'remove_splits',
'selected',
'hidden',
'page_preview',
'first_visible_row',
'first_visible_col',
'grid_colour',
'preview_magn',
'normal_magn',
'row_gut_width',
'col_gut_height',
'show_auto_page_breaks',
'dialogue_sheet',
'auto_style_outline',
'outline_below',
'outline_right',
'fit_num_pages',
'show_row_outline',
'show_col_outline',
'alt_expr_eval',
'alt_formula_entries',
'row_default_height',
'col_default_width',
'calc_mode',
'calc_count',
'RC_ref_mode',
'iterations_on',
'delta',
'save_recalc',
'print_headers',
'print_grid',
'grid_set',
'vert_page_breaks',
'horz_page_breaks',
'header_str',
'footer_str',
'print_centered_vert',
'print_centered_horz',
'left_margin',
'right_margin',
'top_margin',
'bottom_margin',
'paper_size_code',
'print_scaling',
'start_page_number',
'fit_width_to_pages',
'fit_height_to_pages',
'print_in_rows',
'portrait',
'print_not_colour',
'print_draft',
'print_notes',
'print_notes_at_end',
'print_omit_errors',
'print_hres',
'print_vres',
'header_margin',
'footer_margin',
'copies_num',
]
from xlwt import *
wb = Workbook()
ws = wb.add_sheet('sheet')
print ws.name
print ws.parent
print ws.rows
print ws.cols
print ws.merged_ranges
print ws.bmp_rec
print ws.show_formulas
print ws.show_grid
print ws.show_headers
print ws.panes_frozen
print ws.show_empty_as_zero
print ws.auto_colour_grid
print ws.cols_right_to_left
print ws.show_outline
print ws.remove_splits
print ws.selected
# print ws.hidden
print ws.page_preview
print ws.first_visible_row
print ws.first_visible_col
print ws.grid_colour
print ws.preview_magn
print ws.normal_magn
#print ws.row_gut_width
#print ws.col_gut_height
print ws.show_auto_page_breaks
print ws.dialogue_sheet
print ws.auto_style_outline
print ws.outline_below
print ws.outline_right
print ws.fit_num_pages
print ws.show_row_outline
print ws.show_col_outline
print ws.alt_expr_eval
print ws.alt_formula_entries
print ws.row_default_height
print ws.col_default_width
print ws.calc_mode
print ws.calc_count
print ws.RC_ref_mode
print ws.iterations_on
print ws.delta
print ws.save_recalc
print ws.print_headers
print ws.print_grid
#print ws.grid_set
print ws.vert_page_breaks
print ws.horz_page_breaks
print ws.header_str
print ws.footer_str
print ws.print_centered_vert
print ws.print_centered_horz
print ws.left_margin
print ws.right_margin
print ws.top_margin
print ws.bottom_margin
print ws.paper_size_code
print ws.print_scaling
print ws.start_page_number
print ws.fit_width_to_pages
print ws.fit_height_to_pages
print ws.print_in_rows
print ws.portrait
print ws.print_colour
print ws.print_draft
print ws.print_notes
print ws.print_notes_at_end
print ws.print_omit_errors
print ws.print_hres
print ws.print_vres
print ws.header_margin
print ws.footer_margin
print ws.copies_num
@@ -1,46 +0,0 @@
# Write an XLS file with a single worksheet, containing
# a heading row and some rows of data.
import xlwt
import datetime
ezxf = xlwt.easyxf
def write_xls(file_name, sheet_name, headings, data, heading_xf, data_xfs):
book = xlwt.Workbook()
sheet = book.add_sheet(sheet_name)
rowx = 0
for colx, value in enumerate(headings):
sheet.write(rowx, colx, value, heading_xf)
sheet.set_panes_frozen(True) # frozen headings instead of split panes
sheet.set_horz_split_pos(rowx+1) # in general, freeze after last heading row
sheet.set_remove_splits(True) # if user does unfreeze, don't leave a split there
for row in data:
rowx += 1
for colx, value in enumerate(row):
sheet.write(rowx, colx, value, data_xfs[colx])
book.save(file_name)
if __name__ == '__main__':
import sys
mkd = datetime.date
hdngs = ['Date', 'Stock Code', 'Quantity', 'Unit Price', 'Value', 'Message']
kinds = 'date text int price money text'.split()
data = [
[mkd(2007, 7, 1), 'ABC', 1000, 1.234567, 1234.57, ''],
[mkd(2007, 12, 31), 'XYZ', -100, 4.654321, -465.43, 'Goods returned'],
] + [
[mkd(2008, 6, 30), 'PQRCD', 100, 2.345678, 234.57, ''],
] * 100
heading_xf = ezxf('font: bold on; align: wrap on, vert centre, horiz center')
kind_to_xf_map = {
'date': ezxf(num_format_str='yyyy-mm-dd'),
'int': ezxf(num_format_str='#,##0'),
'money': ezxf('font: italic on; pattern: pattern solid, fore-colour grey25',
num_format_str='$#,##0.00'),
'price': ezxf(num_format_str='#0.000000'),
'text': ezxf(),
}
data_xfs = [kind_to_xf_map[k] for k in kinds]
write_xls('xlwt_easyxf_simple_demo.xls', 'Demo', hdngs, data, heading_xf, data_xfs)
-374
View File
@@ -1,374 +0,0 @@
header {
import struct
import Utils
from UnicodeUtils import upack1
from ExcelMagic import *
_RVAdelta = {"R": 0, "V": 0x20, "A": 0x40}
_RVAdeltaRef = {"R": 0, "V": 0x20, "A": 0x40, "D": 0x20}
_RVAdeltaArea = {"R": 0, "V": 0x20, "A": 0x40, "D": 0}
class FormulaParseException(Exception):
"""
An exception indicating that a Formula could not be successfully parsed.
"""
}
header "ExcelFormulaParser.__init__" {
self.rpn = ""
self.sheet_references = []
self.xcall_references = []
}
options {
language = "Python";
}
class ExcelFormulaParser extends Parser;
options {
k = 2;
defaultErrorHandler = false;
buildAST = false;
}
tokens {
TRUE_CONST;
FALSE_CONST;
STR_CONST;
NUM_CONST;
INT_CONST;
FUNC_IF;
FUNC_CHOOSE;
NAME;
QUOTENAME;
EQ;
NE;
GT;
LT;
GE;
LE;
ADD;
SUB;
MUL;
DIV;
POWER;
PERCENT;
LP;
RP;
LB;
RB;
COLON;
COMMA;
SEMICOLON;
REF2D;
REF2D_R1C1;
BANG;
}
formula
: expr["V"]
;
expr[arg_type]
: // {print "\n**expr %s" % arg_type}
prec0_expr[arg_type]
(
(
EQ { op = struct.pack('B', ptgEQ) }
| NE { op = struct.pack('B', ptgNE) }
| GT { op = struct.pack('B', ptgGT) }
| LT { op = struct.pack('B', ptgLT) }
| GE { op = struct.pack('B', ptgGE) }
| LE { op = struct.pack('B', ptgLE) }
)
prec0_expr[arg_type] { self.rpn += op }
)*
;
prec0_expr[arg_type]
: prec1_expr[arg_type]
(
(
CONCAT { op = struct.pack('B', ptgConcat) }
)
prec1_expr[arg_type] { self.rpn += op }
)*
;
prec1_expr[arg_type]
: // {print "**prec1_expr1 %s" % arg_type}
prec2_expr[arg_type]
// {print "**prec1_expr2 %s" % arg_type}
(
(
ADD { op = struct.pack('B', ptgAdd) }
| SUB { op = struct.pack('B', ptgSub) }
)
// {print "**prec1_expr3 %s" % arg_type}
prec2_expr[arg_type]
{ self.rpn += op;
// print "**prec1_expr4 %s" % arg_type
}
)*
;
prec2_expr[arg_type]
: prec3_expr[arg_type]
(
(
MUL { op = struct.pack('B', ptgMul) }
| DIV { op = struct.pack('B', ptgDiv) }
)
prec3_expr[arg_type] { self.rpn += op }
)*
;
prec3_expr[arg_type]
: prec4_expr[arg_type]
(
(
POWER { op = struct.pack('B', ptgPower) }
)
prec4_expr[arg_type] { self.rpn += op }
)*
;
prec4_expr[arg_type]
: prec5_expr[arg_type]
(
PERCENT { self.rpn += struct.pack('B', ptgPercent) }
)?
;
prec5_expr[arg_type]
: primary[arg_type]
| SUB primary[arg_type] { self.rpn += struct.pack('B', ptgUminus) }
;
primary[arg_type]
: TRUE_CONST
{
self.rpn += struct.pack("2B", ptgBool, 1)
}
| FALSE_CONST
{
self.rpn += struct.pack("2B", ptgBool, 0)
}
| str_tok:STR_CONST
{
self.rpn += struct.pack("B", ptgStr) + upack1(str_tok.text[1:-1].replace("\"\"", "\""))
}
| int_tok:INT_CONST
{
// print "**int_const", int_tok.text
int_value = int(int_tok.text)
if int_value <= 65535:
self.rpn += struct.pack("<BH", ptgInt, int_value)
else:
self.rpn += struct.pack("<Bd", ptgNum, float(int_value))
}
| num_tok:NUM_CONST
{
self.rpn += struct.pack("<Bd", ptgNum, float(num_tok.text))
}
| ref2d_tok:REF2D
{
// print "**ref2d %s %s" % (ref2d_tok.text, arg_type)
r, c = Utils.cell_to_packed_rowcol(ref2d_tok.text)
ptg = ptgRefR + _RVAdeltaRef[arg_type]
self.rpn += struct.pack("<B2H", ptg, r, c)
}
| ref2d1_tok:REF2D COLON ref2d2_tok:REF2D
{
r1, c1 = Utils.cell_to_packed_rowcol(ref2d1_tok.text)
r2, c2 = Utils.cell_to_packed_rowcol(ref2d2_tok.text)
ptg = ptgAreaR + _RVAdeltaArea[arg_type]
self.rpn += struct.pack("<B4H", ptg, r1, r2, c1, c2)
}
| sheet1 = sheet
{
sheet2 = sheet1
}
( COLON sheet2 = sheet )? BANG ref3d_ref2d: REF2D
{
ptg = ptgRef3dR + _RVAdeltaRef[arg_type]
rpn_ref2d = ""
r1, c1 = Utils.cell_to_packed_rowcol(ref3d_ref2d.text)
rpn_ref2d = struct.pack("<3H", 0x0000, r1, c1)
}
( COLON ref3d_ref2d2: REF2D
{
ptg = ptgArea3dR + _RVAdeltaArea[arg_type]
r2, c2 = Utils.cell_to_packed_rowcol(ref3d_ref2d2.text)
rpn_ref2d = struct.pack("<5H", 0x0000, r1, r2, c1, c2)
}
)?
{
self.rpn += struct.pack("<B", ptg)
self.sheet_references.append((sheet1, sheet2, len(self.rpn)))
self.rpn += rpn_ref2d
}
| FUNC_IF
LP expr["V"] (SEMICOLON | COMMA)
{
self.rpn += struct.pack("<BBH", ptgAttr, 0x02, 0) // tAttrIf
pos0 = len(self.rpn) - 2
}
expr[arg_type] (SEMICOLON | COMMA)
{
self.rpn += struct.pack("<BBH", ptgAttr, 0x08, 0) // tAttrSkip
pos1 = len(self.rpn) - 2
self.rpn = self.rpn[:pos0] + struct.pack("<H", pos1-pos0) + self.rpn[pos0+2:]
}
expr[arg_type] RP
{
self.rpn += struct.pack("<BBH", ptgAttr, 0x08, 3) // tAttrSkip
self.rpn += struct.pack("<BBH", ptgFuncVarR, 3, 1) // 3 = nargs, 1 = IF func
pos2 = len(self.rpn)
self.rpn = self.rpn[:pos1] + struct.pack("<H", pos2-(pos1+2)-1) + self.rpn[pos1+2:]
}
| FUNC_CHOOSE
{
arg_type = "R"
rpn_chunks = []
}
LP expr["V"] // first argument (the selector)
{
rpn_start = len(self.rpn)
ref_markers = [len(self.sheet_references)]
}
(
(SEMICOLON | COMMA)
{ mark = len(self.rpn) }
(
expr[arg_type]
| { self.rpn += struct.pack("B", ptgMissArg) }
)
{
rpn_chunks.append(self.rpn[mark:])
ref_markers.append(len(self.sheet_references))
}
)*
RP
{
self.rpn = self.rpn[:rpn_start]
nc = len(rpn_chunks)
chunklens = [len(chunk) for chunk in rpn_chunks]
skiplens = [0] * nc
skiplens[-1] = 3
for ic in xrange(nc-1, 0, -1):
skiplens[ic-1] = skiplens[ic] + chunklens[ic] + 4
jump_pos = [2 * nc + 2]
for ic in xrange(nc):
jump_pos.append(jump_pos[-1] + chunklens[ic] + 4)
chunk_shift = 2 * nc + 6 // size of tAttrChoose
for ic in xrange(nc):
for refx in xrange(ref_markers[ic], ref_markers[ic+1]):
ref = self.sheet_references[refx]
self.sheet_references[refx] = (ref[0], ref[1], ref[2] + chunk_shift)
chunk_shift += 4 // size of tAttrSkip
choose_rpn = []
choose_rpn.append(struct.pack("<BBH", ptgAttr, 0x04, nc)) // 0x04 is tAttrChoose
choose_rpn.append(struct.pack("<%dH" % (nc+1), *jump_pos))
for ic in xrange(nc):
choose_rpn.append(rpn_chunks[ic])
choose_rpn.append(struct.pack("<BBH", ptgAttr, 0x08, skiplens[ic])) // 0x08 is tAttrSkip
choose_rpn.append(struct.pack("<BBH", ptgFuncVarV, nc+1, 100)) // 100 is CHOOSE fn
self.rpn += "".join(choose_rpn)
}
| name_tok:NAME
{
raise Exception("[formula] found unexpected NAME token (%r)" % name_tok.txt)
// #### TODO: handle references to defined names here
}
| func_tok:NAME
{
func_toku = func_tok.text.upper()
if func_toku in all_funcs_by_name:
(opcode,
min_argc,
max_argc,
func_type,
arg_type_str) = all_funcs_by_name[func_toku]
arg_type_list = list(arg_type_str)
else:
raise Exception("[formula] unknown function (%s)" % func_tok.text)
// print "**func_tok1 %s %s" % (func_toku, func_type)
xcall = opcode < 0
if xcall:
// The name of the add-in function is passed as the 1st arg
// of the hidden XCALL function
self.xcall_references.append((func_toku, len(self.rpn) + 1))
self.rpn += struct.pack("<BHHH",
ptgNameXR,
0xadde, // ##PATCHME## index to REF entry in EXTERNSHEET record
0xefbe, // ##PATCHME## one-based index to EXTERNNAME record
0x0000) // unused
}
LP arg_count = expr_list[arg_type_list, min_argc, max_argc] RP
{
if arg_count > max_argc or arg_count < min_argc:
raise Exception, "%d parameters for function: %s" % (arg_count, func_tok.text)
if xcall:
func_ptg = ptgFuncVarR + _RVAdelta[func_type]
self.rpn += struct.pack("<2BH", func_ptg, arg_count + 1, 255) // 255 is magic XCALL function
elif min_argc == max_argc:
func_ptg = ptgFuncR + _RVAdelta[func_type]
self.rpn += struct.pack("<BH", func_ptg, opcode)
elif arg_count == 1 and func_tok.text.upper() == "SUM":
self.rpn += struct.pack("<BBH", ptgAttr, 0x10, 0) // tAttrSum
else:
func_ptg = ptgFuncVarR + _RVAdelta[func_type]
self.rpn += struct.pack("<2BH", func_ptg, arg_count, opcode)
}
| LP expr[arg_type] RP
{
self.rpn += struct.pack("B", ptgParen)
}
;
expr_list[arg_type_list, min_argc, max_argc] returns [arg_cnt]
{
arg_cnt = 0
arg_type = arg_type_list[arg_cnt]
// print "**expr_list1[%d] req=%s" % (arg_cnt, arg_type)
}
: expr[arg_type] { arg_cnt += 1 }
(
{
if arg_cnt < len(arg_type_list):
arg_type = arg_type_list[arg_cnt]
else:
arg_type = arg_type_list[-1]
if arg_type == "+":
arg_type = arg_type_list[-2]
// print "**expr_list2[%d] req=%s" % (arg_cnt, arg_type)
}
(SEMICOLON | COMMA)
(
expr[arg_type]
| { self.rpn += struct.pack("B", ptgMissArg) }
)
{ arg_cnt += 1 }
)*
|
;
sheet returns[ref]
: sheet_ref_name: NAME
{ ref = sheet_ref_name.text }
| sheet_ref_int: INT_CONST
{ ref = sheet_ref_int.text }
| sheet_ref_quote: QUOTENAME
{ ref = sheet_ref_quote.text[1:-1].replace("''", "'") }
;
File diff suppressed because it is too large Load Diff
-258
View File
@@ -1,258 +0,0 @@
# Portions are Copyright (C) 2005 Roman V. Kiseliov
# Portions are Copyright (c) 2004 Evgeny Filatov <fufff@users.sourceforge.net>
# Portions are Copyright (c) 2002-2004 John McNamara (Perl Spreadsheet::WriteExcel)
from .BIFFRecords import BiffRecord
from struct import *
def _size_col(sheet, col):
return sheet.col_width(col)
def _size_row(sheet, row):
return sheet.row_height(row)
def _position_image(sheet, row_start, col_start, x1, y1, width, height):
"""Calculate the vertices that define the position of the image as required by
the OBJ record.
+------------+------------+
| A | B |
+-----+------------+------------+
| |(x1,y1) | |
| 1 |(A1)._______|______ |
| | | | |
| | | | |
+-----+----| BITMAP |-----+
| | | | |
| 2 | |______________. |
| | | (B2)|
| | | (x2,y2)|
+---- +------------+------------+
Example of a bitmap that covers some of the area from cell A1 to cell B2.
Based on the width and height of the bitmap we need to calculate 8 vars:
col_start, row_start, col_end, row_end, x1, y1, x2, y2.
The width and height of the cells are also variable and have to be taken into
account.
The values of col_start and row_start are passed in from the calling
function. The values of col_end and row_end are calculated by subtracting
the width and height of the bitmap from the width and height of the
underlying cells.
The vertices are expressed as a percentage of the underlying cell width as
follows (rhs values are in pixels):
x1 = X / W *1024
y1 = Y / H *256
x2 = (X-1) / W *1024
y2 = (Y-1) / H *256
Where: X is distance from the left side of the underlying cell
Y is distance from the top of the underlying cell
W is the width of the cell
H is the height of the cell
Note: the SDK incorrectly states that the height should be expressed as a
percentage of 1024.
col_start - Col containing upper left corner of object
row_start - Row containing top left corner of object
x1 - Distance to left side of object
y1 - Distance to top of object
width - Width of image frame
height - Height of image frame
"""
# Adjust start column for offsets that are greater than the col width
while x1 >= _size_col(sheet, col_start):
x1 -= _size_col(sheet, col_start)
col_start += 1
# Adjust start row for offsets that are greater than the row height
while y1 >= _size_row(sheet, row_start):
y1 -= _size_row(sheet, row_start)
row_start += 1
# Initialise end cell to the same as the start cell
row_end = row_start # Row containing bottom right corner of object
col_end = col_start # Col containing lower right corner of object
width = width + x1 - 1
height = height + y1 - 1
# Subtract the underlying cell widths to find the end cell of the image
while (width >= _size_col(sheet, col_end)):
width -= _size_col(sheet, col_end)
col_end += 1
# Subtract the underlying cell heights to find the end cell of the image
while (height >= _size_row(sheet, row_end)):
height -= _size_row(sheet, row_end)
row_end += 1
# Bitmap isn't allowed to start or finish in a hidden cell, i.e. a cell
# with zero height or width.
if ((_size_col(sheet, col_start) == 0) or (_size_col(sheet, col_end) == 0)
or (_size_row(sheet, row_start) == 0) or (_size_row(sheet, row_end) == 0)):
return
# Convert the pixel values to the percentage value expected by Excel
x1 = int(float(x1) / _size_col(sheet, col_start) * 1024)
y1 = int(float(y1) / _size_row(sheet, row_start) * 256)
# Distance to right side of object
x2 = int(float(width) / _size_col(sheet, col_end) * 1024)
# Distance to bottom of object
y2 = int(float(height) / _size_row(sheet, row_end) * 256)
return (col_start, x1, row_start, y1, col_end, x2, row_end, y2)
class ObjBmpRecord(BiffRecord):
_REC_ID = 0x005D # Record identifier
def __init__(self, row, col, sheet, im_data_bmp, x, y, scale_x, scale_y):
# Scale the frame of the image.
width = im_data_bmp.width * scale_x
height = im_data_bmp.height * scale_y
# Calculate the vertices of the image and write the OBJ record
coordinates = _position_image(sheet, row, col, x, y, width, height)
# print coordinates
col_start, x1, row_start, y1, col_end, x2, row_end, y2 = coordinates
"""Store the OBJ record that precedes an IMDATA record. This could be generalise
to support other Excel objects.
"""
cObj = 0x0001 # Count of objects in file (set to 1)
OT = 0x0008 # Object type. 8 = Picture
id = 0x0001 # Object ID
grbit = 0x0614 # Option flags
colL = col_start # Col containing upper left corner of object
dxL = x1 # Distance from left side of cell
rwT = row_start # Row containing top left corner of object
dyT = y1 # Distance from top of cell
colR = col_end # Col containing lower right corner of object
dxR = x2 # Distance from right of cell
rwB = row_end # Row containing bottom right corner of object
dyB = y2 # Distance from bottom of cell
cbMacro = 0x0000 # Length of FMLA structure
Reserved1 = 0x0000 # Reserved
Reserved2 = 0x0000 # Reserved
icvBack = 0x09 # Background colour
icvFore = 0x09 # Foreground colour
fls = 0x00 # Fill pattern
fAuto = 0x00 # Automatic fill
icv = 0x08 # Line colour
lns = 0xff # Line style
lnw = 0x01 # Line weight
fAutoB = 0x00 # Automatic border
frs = 0x0000 # Frame style
cf = 0x0009 # Image format, 9 = bitmap
Reserved3 = 0x0000 # Reserved
cbPictFmla = 0x0000 # Length of FMLA structure
Reserved4 = 0x0000 # Reserved
grbit2 = 0x0001 # Option flags
Reserved5 = 0x0000 # Reserved
data = pack("<L", cObj)
data += pack("<H", OT)
data += pack("<H", id)
data += pack("<H", grbit)
data += pack("<H", colL)
data += pack("<H", dxL)
data += pack("<H", rwT)
data += pack("<H", dyT)
data += pack("<H", colR)
data += pack("<H", dxR)
data += pack("<H", rwB)
data += pack("<H", dyB)
data += pack("<H", cbMacro)
data += pack("<L", Reserved1)
data += pack("<H", Reserved2)
data += pack("<B", icvBack)
data += pack("<B", icvFore)
data += pack("<B", fls)
data += pack("<B", fAuto)
data += pack("<B", icv)
data += pack("<B", lns)
data += pack("<B", lnw)
data += pack("<B", fAutoB)
data += pack("<H", frs)
data += pack("<L", cf)
data += pack("<H", Reserved3)
data += pack("<H", cbPictFmla)
data += pack("<H", Reserved4)
data += pack("<H", grbit2)
data += pack("<L", Reserved5)
self._rec_data = data
def _process_bitmap(bitmap):
"""Convert a 24 bit bitmap into the modified internal format used by Windows.
This is described in BITMAPCOREHEADER and BITMAPCOREINFO structures in the
MSDN library.
"""
# Open file and binmode the data in case the platform needs it.
fh = open(bitmap, 'rb')
try:
# Slurp the file into a string.
data = fh.read()
finally:
fh.close()
# Check that the file is big enough to be a bitmap.
if len(data) <= 0x36:
raise Exception("bitmap doesn't contain enough data.")
# The first 2 bytes are used to identify the bitmap.
if (data[:2] != b"BM"):
raise Exception("bitmap doesn't appear to to be a valid bitmap image.")
# Remove bitmap data: ID.
data = data[2:]
# Read and remove the bitmap size. This is more reliable than reading
# the data size at offset 0x22.
#
size = unpack("<L", data[:4])[0]
size -= 0x36 # Subtract size of bitmap header.
size += 0x0C # Add size of BIFF header.
data = data[4:]
# Remove bitmap data: reserved, offset, header length.
data = data[12:]
# Read and remove the bitmap width and height. Verify the sizes.
width, height = unpack("<LL", data[:8])
data = data[8:]
if (width > 0xFFFF):
raise Exception("bitmap: largest image width supported is 65k.")
if (height > 0xFFFF):
raise Exception("bitmap: largest image height supported is 65k.")
# Read and remove the bitmap planes and bpp data. Verify them.
planes, bitcount = unpack("<HH", data[:4])
data = data[4:]
if (bitcount != 24):
raise Exception("bitmap isn't a 24bit true color bitmap.")
if (planes != 1):
raise Exception("bitmap: only 1 plane supported in bitmap image.")
# Read and remove the bitmap compression. Verify compression.
compression = unpack("<L", data[:4])[0]
data = data[4:]
if (compression != 0):
raise Exception("bitmap: compression not supported in bitmap image.")
# Remove bitmap data: data size, hres, vres, colours, imp. colours.
data = data[20:]
# Add the BITMAPCOREHEADER data
header = pack("<LHHHH", 0x000c, width, height, 0x01, 0x18)
data = header + data
return (width, height, size, data)
class ImDataBmpRecord(BiffRecord):
_REC_ID = 0x007F
def __init__(self, filename):
"""Insert a 24bit bitmap image in a worksheet. The main record required is
IMDATA but it must be proceeded by a OBJ record to define its position.
"""
BiffRecord.__init__(self)
self.width, self.height, self.size, data = _process_bitmap(filename)
# Write the IMDATA record to store the bitmap data
cf = 0x09
env = 0x01
lcb = self.size
self._rec_data = pack("<HHL", cf, env, lcb) + data
-233
View File
@@ -1,233 +0,0 @@
from struct import unpack, pack
from . import BIFFRecords
class StrCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "sst_idx"]
def __init__(self, rowx, colx, xf_idx, sst_idx):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.sst_idx = sst_idx
def get_biff_data(self):
return pack('<5HL', 0x00FD, 10, self.rowx, self.colx, self.xf_idx, self.sst_idx)
class BlankCell(object):
__slots__ = ["rowx", "colx", "xf_idx"]
def __init__(self, rowx, colx, xf_idx):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
def get_biff_data(self):
return pack('<5H', 0x0201, 6, self.rowx, self.colx, self.xf_idx)
class MulBlankCell(object):
__slots__ = ["rowx", "colx1", "colx2", "xf_idx"]
def __init__(self, rowx, colx1, colx2, xf_idx):
self.rowx = rowx
self.colx1 = colx1
self.colx2 = colx2
self.xf_idx = xf_idx
def get_biff_data(self):
return BIFFRecords.MulBlankRecord(self.rowx,
self.colx1, self.colx2, self.xf_idx).get()
class NumberCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "number"]
def __init__(self, rowx, colx, xf_idx, number):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.number = float(number)
def get_encoded_data(self):
rk_encoded = 0
num = self.number
# The four possible kinds of RK encoding are *not* mutually exclusive.
# The 30-bit integer variety picks up the most.
# In the code below, the four varieties are checked in descending order
# of bangs per buck, or not at all.
# SJM 2007-10-01
if -0x20000000 <= num < 0x20000000: # fits in 30-bit *signed* int
inum = int(num)
if inum == num: # survives round-trip
rk_encoded = 2 | (inum << 2)
return 1, rk_encoded
temp = num * 100
if -0x20000000 <= temp < 0x20000000:
# That was step 1: the coded value will fit in
# a 30-bit signed integer.
itemp = int(round(temp, 0))
# That was step 2: "itemp" is the best candidate coded value.
# Now for step 3: simulate the decoding,
# to check for round-trip correctness.
if itemp / 100.0 == num:
rk_encoded = 3 | (itemp << 2)
return 1, rk_encoded
if 0: # Cost of extra pack+unpack not justified by tiny yield.
packed = pack('<d', num)
w01, w23 = unpack('<2i', packed)
if not w01 and not(w23 & 3):
return 1, w23
packed100 = pack('<d', temp)
w01, w23 = unpack('<2i', packed100)
if not w01 and not(w23 & 3):
return 1, w23 | 1
return 0, pack('<5Hd', 0x0203, 14, self.rowx, self.colx, self.xf_idx, num)
def get_biff_data(self):
isRK, value = self.get_encoded_data()
if isRK:
return pack('<5Hi', 0x27E, 10, self.rowx, self.colx, self.xf_idx, value)
return value # NUMBER record already packed
class BooleanCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "number"]
def __init__(self, rowx, colx, xf_idx, number):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.number = number
def get_biff_data(self):
return BIFFRecords.BoolErrRecord(self.rowx,
self.colx, self.xf_idx, self.number, 0).get()
error_code_map = {
0x00: 0, # Intersection of two cell ranges is empty
0x07: 7, # Division by zero
0x0F: 15, # Wrong type of operand
0x17: 23, # Illegal or deleted cell reference
0x1D: 29, # Wrong function or range name
0x24: 36, # Value range overflow
0x2A: 42, # Argument or function not available
'#NULL!' : 0, # Intersection of two cell ranges is empty
'#DIV/0!': 7, # Division by zero
'#VALUE!': 36, # Wrong type of operand
'#REF!' : 23, # Illegal or deleted cell reference
'#NAME?' : 29, # Wrong function or range name
'#NUM!' : 36, # Value range overflow
'#N/A!' : 42, # Argument or function not available
}
class ErrorCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "number"]
def __init__(self, rowx, colx, xf_idx, error_string_or_code):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
try:
self.number = error_code_map[error_string_or_code]
except KeyError:
raise Exception('Illegal error value (%r)' % error_string_or_code)
def get_biff_data(self):
return BIFFRecords.BoolErrRecord(self.rowx,
self.colx, self.xf_idx, self.number, 1).get()
class FormulaCell(object):
__slots__ = ["rowx", "colx", "xf_idx", "frmla", "calc_flags"]
def __init__(self, rowx, colx, xf_idx, frmla, calc_flags=0):
self.rowx = rowx
self.colx = colx
self.xf_idx = xf_idx
self.frmla = frmla
self.calc_flags = calc_flags
def get_biff_data(self):
return BIFFRecords.FormulaRecord(self.rowx,
self.colx, self.xf_idx, self.frmla.rpn(), self.calc_flags).get()
# module-level function for *internal* use by the Row module
def _get_cells_biff_data_mul(rowx, cell_items):
# Return the BIFF data for all cell records in the row.
# Adjacent BLANK|RK records are combined into MUL(BLANK|RK) records.
pieces = []
nitems = len(cell_items)
i = 0
while i < nitems:
icolx, icell = cell_items[i]
if isinstance(icell, NumberCell):
isRK, value = icell.get_encoded_data()
if not isRK:
pieces.append(value) # pre-packed NUMBER record
i += 1
continue
muldata = [(value, icell.xf_idx)]
target = NumberCell
elif isinstance(icell, BlankCell):
muldata = [icell.xf_idx]
target = BlankCell
else:
pieces.append(icell.get_biff_data())
i += 1
continue
lastcolx = icolx
j = i
packed_record = b'' # (to_py3): 'b' binary data
for j in range(i+1, nitems):
jcolx, jcell = cell_items[j]
if jcolx != lastcolx + 1:
nexti = j
break
if not isinstance(jcell, target):
nexti = j
break
if target == NumberCell:
isRK, value = jcell.get_encoded_data()
if not isRK:
packed_record = value
nexti = j + 1
break
muldata.append((value, jcell.xf_idx))
else:
muldata.append(jcell.xf_idx)
lastcolx = jcolx
else:
nexti = j + 1
if target == NumberCell:
if lastcolx == icolx:
# RK record
value, xf_idx = muldata[0]
pieces.append(pack('<5Hi', 0x027E, 10, rowx, icolx, xf_idx, value))
else:
# MULRK record
nc = lastcolx - icolx + 1
pieces.append(pack('<4H', 0x00BD, 6 * nc + 6, rowx, icolx))
# (to_py3): 'b' binary data
pieces.append(b''.join([pack('<Hi', xf_idx, value) for value, xf_idx in muldata]))
pieces.append(pack('<H', lastcolx))
else:
if lastcolx == icolx:
# BLANK record
xf_idx = muldata[0]
pieces.append(pack('<5H', 0x0201, 6, rowx, icolx, xf_idx))
else:
# MULBLANK record
nc = lastcolx - icolx + 1
pieces.append(pack('<4H', 0x00BE, 2 * nc + 6, rowx, icolx))
# (to_py3): 'b' binary data
pieces.append(b''.join([pack('<H', xf_idx) for xf_idx in muldata]))
pieces.append(pack('<H', lastcolx))
if packed_record:
pieces.append(packed_record)
i = nexti
return b''.join(pieces) # (to_py3): 'b' binary data
-34
View File
@@ -1,34 +0,0 @@
# -*- coding: windows-1252 -*-
from .BIFFRecords import ColInfoRecord
class Column(object):
def __init__(self, colx, parent_sheet):
if not(isinstance(colx, int) and 0 <= colx <= 255):
raise ValueError("column index (%r) not an int in range(256)" % colx)
self._index = colx
self._parent = parent_sheet
self._parent_wb = parent_sheet.get_parent()
self._xf_index = 0x0F
self.width = 0x0B92
self.hidden = 0
self.level = 0
self.collapse = 0
def set_style(self, style):
self._xf_index = self._parent_wb.add_style(style)
def width_in_pixels(self):
# *** Approximation ****
return int(round(self.width * 0.0272 + 0.446, 0))
def get_biff_record(self):
options = (self.hidden & 0x01) << 0
options |= (self.level & 0x07) << 8
options |= (self.collapse & 0x01) << 12
return ColInfoRecord(self._index, self._index, self.width, self._xf_index, options).get()
-516
View File
@@ -1,516 +0,0 @@
import sys
import struct
ENCODING = 'utf-16-le'
class Reader:
def __init__(self, filename, dump = False):
self.dump = dump
self.STREAMS = {}
doc = file(filename, 'rb').read()
self.header, self.data = doc[0:512], doc[512:]
del doc
self.__build_header()
self.__build_MSAT()
self.__build_SAT()
self.__build_directory()
self.__build_short_sectors_data()
if len(self.short_sectors_data) > 0:
self.__build_SSAT()
else:
if self.dump and (self.total_ssat_sectors != 0 or self.ssat_start_sid != -2):
print('NOTE: header says that must be', self.total_ssat_sectors, 'short sectors')
print('NOTE: starting at', self.ssat_start_sid, 'sector')
print('NOTE: but file does not contains data in short sectors')
self.ssat_start_sid = -2
self.total_ssat_sectors = 0
self.SSAT = [-2]
for dentry in self.dir_entry_list[1:]:
(did,
sz, name,
t, c,
did_left, did_right, did_root,
dentry_start_sid,
stream_size
) = dentry
stream_data = b''
if stream_size > 0:
if stream_size >= self.min_stream_size:
args = (self.data, self.SAT, dentry_start_sid, self.sect_size)
else:
args = (self.short_sectors_data, self.SSAT, dentry_start_sid, self.short_sect_size)
stream_data = self.get_stream_data(*args)
if name != b'':
# BAD IDEA: names may be equal. NEED use full paths...
self.STREAMS[name] = stream_data
def __build_header(self):
self.doc_magic = self.header[0:8]
if self.doc_magic != b'\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1':
raise Exception('Not an OLE file.')
self.file_uid = self.header[8:24]
self.rev_num = self.header[24:26]
self.ver_num = self.header[26:28]
self.byte_order = self.header[28:30]
self.log2_sect_size, = struct.unpack('<H', self.header[30:32])
self.log2_short_sect_size, = struct.unpack('<H', self.header[32:34])
self.total_sat_sectors, = struct.unpack('<L', self.header[44:48])
self.dir_start_sid, = struct.unpack('<l', self.header[48:52])
self.min_stream_size, = struct.unpack('<L', self.header[56:60])
self.ssat_start_sid, = struct.unpack('<l', self.header[60:64])
self.total_ssat_sectors, = struct.unpack('<L', self.header[64:68])
self.msat_start_sid, = struct.unpack('<l', self.header[68:72])
self.total_msat_sectors, = struct.unpack('<L', self.header[72:76])
self.sect_size = 1 << self.log2_sect_size
self.short_sect_size = 1 << self.log2_short_sect_size
if self.dump:
print('file magic: ')
print_bin_data(self.doc_magic)
print('file uid: ')
print_bin_data(self.file_uid)
print('revision number: ')
print_bin_data(self.rev_num)
print('version number: ')
print_bin_data(self.ver_num)
print('byte order: ')
print_bin_data(self.byte_order)
print('sector size :', hex(self.sect_size), self.sect_size)
#print 'total sectors in file :', hex(self.total_sectors), self.total_sectors
print('short sector size :', hex(self.short_sect_size), self.short_sect_size)
print('Total number of sectors used for the SAT :', hex(self.total_sat_sectors), self.total_sat_sectors)
print('SID of first sector of the directory stream:', hex(self.dir_start_sid), self.dir_start_sid)
print('Minimum size of a standard stream :', hex(self.min_stream_size), self.min_stream_size)
print('SID of first sector of the SSAT :', hex(self.ssat_start_sid), self.ssat_start_sid)
print('Total number of sectors used for the SSAT :', hex(self.total_ssat_sectors), self.total_ssat_sectors)
print('SID of first additional sector of the MSAT :', hex(self.msat_start_sid), self.msat_start_sid)
print('Total number of sectors used for the MSAT :', hex(self.total_msat_sectors), self.total_msat_sectors)
def __build_MSAT(self):
self.MSAT = list(struct.unpack('<109l', self.header[76:]))
next = self.msat_start_sid
while next > 0:
msat_sector = struct.unpack('<128l', self.data[next*self.sect_size:(next+1)*self.sect_size])
self.MSAT.extend(msat_sector[:127])
next = msat_sector[-1]
if self.dump:
print('MSAT (header part): \n', self.MSAT[:109])
print('additional MSAT sectors: \n', self.MSAT[109:])
def __build_SAT(self):
sat_stream = b''.join([self.data[i*self.sect_size:(i+1)*self.sect_size] for i in self.MSAT if i >= 0])
sat_sids_count = len(sat_stream) >> 2
self.SAT = struct.unpack('<%dl' % sat_sids_count, sat_stream) # SIDs tuple
if self.dump:
print('SAT sid count:\n', sat_sids_count)
print('SAT content:\n', self.SAT)
def __build_SSAT(self):
ssat_stream = self.get_stream_data(self.data, self.SAT, self.ssat_start_sid, self.sect_size)
ssids_count = len(ssat_stream) >> 2
self.SSAT = struct.unpack('<%dl' % ssids_count, ssat_stream)
if self.dump:
print('SSID count:', ssids_count)
print('SSAT content:\n', self.SSAT)
def __build_directory(self):
dir_stream = self.get_stream_data(self.data, self.SAT, self.dir_start_sid, self.sect_size)
self.dir_entry_list = []
i = 0
while i < len(dir_stream):
dentry = dir_stream[i:i+128] # 128 -- dir entry size
i += 128
did = len(self.dir_entry_list)
sz, = struct.unpack('<H', dentry[64:66])
if sz > 0 :
name = dentry[0:sz-2].decode('utf_16_le', 'replace')
else:
name = b''
t, = struct.unpack('B', dentry[66])
c, = struct.unpack('B', dentry[67])
did_left , = struct.unpack('<l', dentry[68:72])
did_right , = struct.unpack('<l', dentry[72:76])
did_root , = struct.unpack('<l', dentry[76:80])
dentry_start_sid , = struct.unpack('<l', dentry[116:120])
stream_size , = struct.unpack('<L', dentry[120:124])
self.dir_entry_list.extend([(did, sz, name, t, c,
did_left, did_right, did_root,
dentry_start_sid, stream_size)])
if self.dump:
dentry_types = {
0x00: 'Empty',
0x01: 'User storage',
0x02: 'User stream',
0x03: 'LockBytes',
0x04: 'Property',
0x05: 'Root storage'
}
node_colours = {
0x00: 'Red',
0x01: 'Black'
}
print('total directory entries:', len(self.dir_entry_list))
for dentry in self.dir_entry_list:
(did, sz, name, t, c,
did_left, did_right, did_root,
dentry_start_sid, stream_size) = dentry
print('DID', did)
print('Size of the used area of the character buffer of the name:', sz)
print('dir entry name:', repr(name))
print('type of entry:', t, dentry_types[t])
print('entry colour:', c, node_colours[c])
print('left child DID :', did_left)
print('right child DID:', did_right)
print('root DID :', did_root)
print('start SID :', dentry_start_sid)
print('stream size :', stream_size)
if stream_size == 0:
print('stream is empty')
elif stream_size >= self.min_stream_size:
print('stream stored as normal stream')
else:
print('stream stored as short-stream')
def __build_short_sectors_data(self):
(did, sz, name, t, c,
did_left, did_right, did_root,
dentry_start_sid, stream_size) = self.dir_entry_list[0]
assert t == 0x05 # Short-Stream Container Stream (SSCS) resides in Root Storage
if stream_size == 0:
self.short_sectors_data = b''
else:
self.short_sectors_data = self.get_stream_data(self.data, self.SAT, dentry_start_sid, self.sect_size)
def get_stream_data(self, data, SAT, start_sid, sect_size):
sid = start_sid
chunks = [(sid, sid)]
stream_data = b''
while SAT[sid] >= 0:
next_in_chain = SAT[sid]
last_chunk_start, last_chunk_finish = chunks[-1]
if next_in_chain == last_chunk_finish + 1:
chunks[-1] = last_chunk_start, next_in_chain
else:
chunks.extend([(next_in_chain, next_in_chain)])
sid = next_in_chain
for s, f in chunks:
stream_data += data[s*sect_size:(f+1)*sect_size]
#print chunks
return stream_data
def print_bin_data(data):
i = 0
while i < len(data):
j = 0
while (i < len(data)) and (j < 16):
c = b'0x%02X' % ord(data[i])
sys.stdout.write(c)
sys.stdout.write(' ')
i += 1
j += 1
print()
if i == 0:
print('<NO DATA>')
# This implementation writes only 'Root Entry', 'Workbook' streams
# and 2 empty streams for aligning directory stream on sector boundary
#
# LAYOUT:
# 0 header
# 76 MSAT (1st part: 109 SID)
# 512 workbook stream
# ... additional MSAT sectors if streams' size > about 7 Mb == (109*512 * 128)
# ... SAT
# ... directory stream
#
# NOTE: this layout is "ad hoc". It can be more general. RTFM
class XlsDoc:
SECTOR_SIZE = 0x0200
MIN_LIMIT = 0x1000
SID_FREE_SECTOR = -1
SID_END_OF_CHAIN = -2
SID_USED_BY_SAT = -3
SID_USED_BY_MSAT = -4
def __init__(self):
self.book_stream_sect = []
self.dir_stream = b''
self.dir_stream_sect = []
self.packed_SAT = b''
self.SAT_sect = []
self.packed_MSAT_1st = b''
self.packed_MSAT_2nd = b''
self.MSAT_sect_2nd = []
self.header = b''
def __build_directory(self): # align on sector boundary
self.dir_stream = b''
#(to_py3): replaced = b'\x00'.join(b'Root Entry\x00') + b'\x00'
dentry_name = 'Root Entry\x00'.encode(ENCODING)
dentry_name_sz = len(dentry_name)
dentry_name_pad = b'\x00'*(64 - dentry_name_sz)
dentry_type = 0x05 # root storage
dentry_colour = 0x01 # black
dentry_did_left = -1
dentry_did_right = -1
dentry_did_root = 1
dentry_start_sid = -2
dentry_stream_sz = 0
self.dir_stream += struct.pack('<64s H 2B 3l 9L l L L',
dentry_name + dentry_name_pad,
dentry_name_sz,
dentry_type,
dentry_colour,
dentry_did_left,
dentry_did_right,
dentry_did_root,
0, 0, 0, 0, 0, 0, 0, 0, 0,
dentry_start_sid,
dentry_stream_sz,
0
)
# (to_py3): replaced = b'\x00'.join(b'Workbook\x00') + b'\x00'
dentry_name = 'Workbook\x00'.encode(ENCODING)
dentry_name_sz = len(dentry_name)
dentry_name_pad = b'\x00'*(64 - dentry_name_sz)
dentry_type = 0x02 # user stream
dentry_colour = 0x01 # black
dentry_did_left = -1
dentry_did_right = -1
dentry_did_root = -1
dentry_start_sid = 0
dentry_stream_sz = self.book_stream_len
self.dir_stream += struct.pack('<64s H 2B 3l 9L l L L',
dentry_name + dentry_name_pad,
dentry_name_sz,
dentry_type,
dentry_colour,
dentry_did_left,
dentry_did_right,
dentry_did_root,
0, 0, 0, 0, 0, 0, 0, 0, 0,
dentry_start_sid,
dentry_stream_sz,
0
)
# padding
dentry_name = b''
dentry_name_sz = len(dentry_name)
dentry_name_pad = b'\x00'*(64 - dentry_name_sz)
dentry_type = 0x00 # empty
dentry_colour = 0x01 # black
dentry_did_left = -1
dentry_did_right = -1
dentry_did_root = -1
dentry_start_sid = -2
dentry_stream_sz = 0
self.dir_stream += struct.pack('<64s H 2B 3l 9L l L L',
dentry_name + dentry_name_pad,
dentry_name_sz,
dentry_type,
dentry_colour,
dentry_did_left,
dentry_did_right,
dentry_did_root,
0, 0, 0, 0, 0, 0, 0, 0, 0,
dentry_start_sid,
dentry_stream_sz,
0
) * 2
def __build_sat(self):
# Build SAT
book_sect_count = self.book_stream_len >> 9
dir_sect_count = len(self.dir_stream) >> 9
total_sect_count = book_sect_count + dir_sect_count
SAT_sect_count = 0
MSAT_sect_count = 0
SAT_sect_count_limit = 109
while total_sect_count > 128*SAT_sect_count or SAT_sect_count > SAT_sect_count_limit:
SAT_sect_count += 1
total_sect_count += 1
if SAT_sect_count > SAT_sect_count_limit:
MSAT_sect_count += 1
total_sect_count += 1
SAT_sect_count_limit += 127
SAT = [self.SID_FREE_SECTOR]*128*SAT_sect_count
sect = 0
while sect < book_sect_count - 1:
self.book_stream_sect.append(sect)
SAT[sect] = sect + 1
sect += 1
self.book_stream_sect.append(sect)
SAT[sect] = self.SID_END_OF_CHAIN
sect += 1
while sect < book_sect_count + MSAT_sect_count:
self.MSAT_sect_2nd.append(sect)
SAT[sect] = self.SID_USED_BY_MSAT
sect += 1
while sect < book_sect_count + MSAT_sect_count + SAT_sect_count:
self.SAT_sect.append(sect)
SAT[sect] = self.SID_USED_BY_SAT
sect += 1
while sect < book_sect_count + MSAT_sect_count + SAT_sect_count + dir_sect_count - 1:
self.dir_stream_sect.append(sect)
SAT[sect] = sect + 1
sect += 1
self.dir_stream_sect.append(sect)
SAT[sect] = self.SID_END_OF_CHAIN
sect += 1
self.packed_SAT = struct.pack('<%dl' % (SAT_sect_count*128), *SAT)
MSAT_1st = [self.SID_FREE_SECTOR]*109
for i, SAT_sect_num in zip(list(range(0, 109)), self.SAT_sect):
MSAT_1st[i] = SAT_sect_num
self.packed_MSAT_1st = struct.pack('<109l', *MSAT_1st)
MSAT_2nd = [self.SID_FREE_SECTOR]*128*MSAT_sect_count
if MSAT_sect_count > 0:
MSAT_2nd[- 1] = self.SID_END_OF_CHAIN
i = 109
msat_sect = 0
sid_num = 0
while i < SAT_sect_count:
if (sid_num + 1) % 128 == 0:
#print 'link: ',
msat_sect += 1
if msat_sect < len(self.MSAT_sect_2nd):
MSAT_2nd[sid_num] = self.MSAT_sect_2nd[msat_sect]
else:
#print 'sid: ',
MSAT_2nd[sid_num] = self.SAT_sect[i]
i += 1
#print sid_num, MSAT_2nd[sid_num]
sid_num += 1
self.packed_MSAT_2nd = struct.pack('<%dl' % (MSAT_sect_count*128), *MSAT_2nd)
#print vars()
#print zip(range(0, sect), SAT)
#print self.book_stream_sect
#print self.MSAT_sect_2nd
#print MSAT_2nd
#print self.SAT_sect
#print self.dir_stream_sect
def __build_header(self):
doc_magic = b'\xD0\xCF\x11\xE0\xA1\xB1\x1A\xE1'
file_uid = b'\x00'*16
rev_num = b'\x3E\x00'
ver_num = b'\x03\x00'
byte_order = b'\xFE\xFF'
log_sect_size = struct.pack('<H', 9)
log_short_sect_size = struct.pack('<H', 6)
not_used0 = b'\x00'*10
total_sat_sectors = struct.pack('<L', len(self.SAT_sect))
dir_start_sid = struct.pack('<l', self.dir_stream_sect[0])
not_used1 = b'\x00'*4
min_stream_size = struct.pack('<L', 0x1000)
ssat_start_sid = struct.pack('<l', -2)
total_ssat_sectors = struct.pack('<L', 0)
if len(self.MSAT_sect_2nd) == 0:
msat_start_sid = struct.pack('<l', -2)
else:
msat_start_sid = struct.pack('<l', self.MSAT_sect_2nd[0])
total_msat_sectors = struct.pack('<L', len(self.MSAT_sect_2nd))
self.header = b''.join([ doc_magic,
file_uid,
rev_num,
ver_num,
byte_order,
log_sect_size,
log_short_sect_size,
not_used0,
total_sat_sectors,
dir_start_sid,
not_used1,
min_stream_size,
ssat_start_sid,
total_ssat_sectors,
msat_start_sid,
total_msat_sectors
])
def save(self, file_name_or_filelike_obj, stream):
# 1. Align stream on 0x1000 boundary (and therefore on sector boundary)
padding = b'\x00' * (0x1000 - (len(stream) % 0x1000))
self.book_stream_len = len(stream) + len(padding)
self.__build_directory()
self.__build_sat()
self.__build_header()
f = file_name_or_filelike_obj
we_own_it = not hasattr(f, 'write')
if we_own_it:
f = open(file_name_or_filelike_obj, 'wb')
f.write(self.header)
f.write(self.packed_MSAT_1st)
f.write(stream)
f.write(padding)
f.write(self.packed_MSAT_2nd)
f.write(self.packed_SAT)
f.write(self.dir_stream)
if we_own_it:
f.close()
-41
View File
@@ -1,41 +0,0 @@
from . import ExcelFormulaParser, ExcelFormulaLexer
import struct
from .antlr import ANTLRException
class Formula(object):
__slots__ = ["__s", "__parser", "__sheet_refs", "__xcall_refs"]
def __init__(self, s):
try:
self.__s = s
lexer = ExcelFormulaLexer.Lexer(s)
self.__parser = ExcelFormulaParser.Parser(lexer)
self.__parser.formula()
self.__sheet_refs = self.__parser.sheet_references
self.__xcall_refs = self.__parser.xcall_references
except ANTLRException as e:
# print e
raise ExcelFormulaParser.FormulaParseException("can't parse formula " + s)
def get_references(self):
return self.__sheet_refs, self.__xcall_refs
def patch_references(self, patches):
for offset, idx in patches:
self.__parser.rpn = self.__parser.rpn[:offset] + struct.pack('<H', idx) + self.__parser.rpn[offset+2:]
def text(self):
return self.__s
def rpn(self):
'''
Offset Size Contents
0 2 Size of the following formula data (sz)
2 sz Formula data (RPN token array)
[2+sz] var. (optional) Additional data for specific tokens
'''
return struct.pack("<H", len(self.__parser.rpn)) + self.__parser.rpn
-126
View File
@@ -1,126 +0,0 @@
import sys
from .antlr import EOF, CommonToken as Tok, TokenStream, TokenStreamException
import struct
from . import ExcelFormulaParser
from re import compile as recompile, match, UNICODE, IGNORECASE, VERBOSE
int_const_pattern = r"\d+\b"
flt_const_pattern = r"""
(?:
(?: \d* \. \d+ ) # .1 .12 .123 etc 9.1 etc 98.1 etc
|
(?: \d+ \. ) # 1. 12. 123. etc
)
# followed by optional exponent part
(?: [Ee] [+-]? \d+ ) ?
"""
str_const_pattern = r'"(?:[^"]|"")*"'
#range2d_pattern = recompile(r"\$?[A-I]?[A-Z]\$?\d+:\$?[A-I]?[A-Z]\$?\d+"
ref2d_r1c1_pattern = r"[Rr]0*[1-9][0-9]*[Cc]0*[1-9][0-9]*"
ref2d_pattern = r"\$?[A-I]?[A-Z]\$?0*[1-9][0-9]*"
true_pattern = r"TRUE\b"
false_pattern = r"FALSE\b"
if_pattern = r"IF\b"
choose_pattern = r"CHOOSE\b"
name_pattern = r"\w[\.\w]*"
quotename_pattern = r"'(?:[^']|'')*'" #### It's essential that this bracket be non-grouping.
ne_pattern = r"<>"
ge_pattern = r">="
le_pattern = r"<="
pattern_type_tuples = (
(flt_const_pattern, ExcelFormulaParser.NUM_CONST),
(int_const_pattern, ExcelFormulaParser.INT_CONST),
(str_const_pattern, ExcelFormulaParser.STR_CONST),
# (range2d_pattern , ExcelFormulaParser.RANGE2D),
(ref2d_r1c1_pattern, ExcelFormulaParser.REF2D_R1C1),
(ref2d_pattern , ExcelFormulaParser.REF2D),
(true_pattern , ExcelFormulaParser.TRUE_CONST),
(false_pattern , ExcelFormulaParser.FALSE_CONST),
(if_pattern , ExcelFormulaParser.FUNC_IF),
(choose_pattern , ExcelFormulaParser.FUNC_CHOOSE),
(name_pattern , ExcelFormulaParser.NAME),
(quotename_pattern, ExcelFormulaParser.QUOTENAME),
(ne_pattern, ExcelFormulaParser.NE),
(ge_pattern, ExcelFormulaParser.GE),
(le_pattern, ExcelFormulaParser.LE),
)
_re = recompile(
'(' + ')|('.join([i[0] for i in pattern_type_tuples]) + ')',
VERBOSE+IGNORECASE)
_toktype = [None] + [i[1] for i in pattern_type_tuples]
# need dummy at start because re.MatchObject.lastindex counts from 1
single_char_lookup = {
'=': ExcelFormulaParser.EQ,
'<': ExcelFormulaParser.LT,
'>': ExcelFormulaParser.GT,
'+': ExcelFormulaParser.ADD,
'-': ExcelFormulaParser.SUB,
'*': ExcelFormulaParser.MUL,
'/': ExcelFormulaParser.DIV,
':': ExcelFormulaParser.COLON,
';': ExcelFormulaParser.SEMICOLON,
',': ExcelFormulaParser.COMMA,
'(': ExcelFormulaParser.LP,
')': ExcelFormulaParser.RP,
'&': ExcelFormulaParser.CONCAT,
'%': ExcelFormulaParser.PERCENT,
'^': ExcelFormulaParser.POWER,
'!': ExcelFormulaParser.BANG,
}
class Lexer(TokenStream):
def __init__(self, text):
self._text = text[:]
self._pos = 0
self._line = 0
def isEOF(self):
return len(self._text) <= self._pos
def curr_ch(self):
return self._text[self._pos]
def next_ch(self, n = 1):
self._pos += n
def is_whitespace(self):
return self.curr_ch() in " \t\n\r\f\v"
def match_pattern(self):
m = _re.match(self._text, self._pos)
if not m:
return None
self._pos = m.end(0)
return Tok(type = _toktype[m.lastindex], text = m.group(0), col = m.start(0) + 1)
def nextToken(self):
# skip whitespace
while not self.isEOF() and self.is_whitespace():
self.next_ch()
if self.isEOF():
return Tok(type = EOF)
# first, try to match token with 2 or more chars
t = self.match_pattern()
if t:
return t
# second, we want 1-char tokens
te = self.curr_ch()
try:
ty = single_char_lookup[te]
except KeyError:
raise TokenStreamException(
"Unexpected char %r in column %u." % (self.curr_ch(), self._pos))
self.next_ch()
return Tok(type=ty, text=te, col=self._pos)
if __name__ == '__main__':
try:
for t in Lexer(""" 1.23 456 "abcd" R2C2 a1 iv65536 true false if choose a_name 'qname' <> >= <= """):
print(t)
except TokenStreamException as e:
print("error:", e)
-659
View File
@@ -1,659 +0,0 @@
### $ANTLR 2.7.7 (20060930): "xlwt/excel-formula.g" -> "ExcelFormulaParser.py"$
### import antlr and other modules ..
import sys
from . import antlr
### header action >>>
import struct
from . import Utils
from .UnicodeUtils import upack1
from .ExcelMagic import *
_RVAdelta = {"R": 0, "V": 0x20, "A": 0x40}
_RVAdeltaRef = {"R": 0, "V": 0x20, "A": 0x40, "D": 0x20}
_RVAdeltaArea = {"R": 0, "V": 0x20, "A": 0x40, "D": 0}
class FormulaParseException(Exception):
"""
An exception indicating that a Formula could not be successfully parsed.
"""
### header action <<<
### preamble action>>>
### preamble action <<<
### import antlr.Token
from .antlr import Token
### >>>The Known Token Types <<<
SKIP = antlr.SKIP
INVALID_TYPE = antlr.INVALID_TYPE
EOF_TYPE = antlr.EOF_TYPE
EOF = antlr.EOF
NULL_TREE_LOOKAHEAD = antlr.NULL_TREE_LOOKAHEAD
MIN_USER_TYPE = antlr.MIN_USER_TYPE
TRUE_CONST = 4
FALSE_CONST = 5
STR_CONST = 6
NUM_CONST = 7
INT_CONST = 8
FUNC_IF = 9
FUNC_CHOOSE = 10
NAME = 11
QUOTENAME = 12
EQ = 13
NE = 14
GT = 15
LT = 16
GE = 17
LE = 18
ADD = 19
SUB = 20
MUL = 21
DIV = 22
POWER = 23
PERCENT = 24
LP = 25
RP = 26
LB = 27
RB = 28
COLON = 29
COMMA = 30
SEMICOLON = 31
REF2D = 32
REF2D_R1C1 = 33
BANG = 34
CONCAT = 35
class Parser(antlr.LLkParser):
### user action >>>
### user action <<<
def __init__(self, *args, **kwargs):
antlr.LLkParser.__init__(self, *args, **kwargs)
self.tokenNames = _tokenNames
### __init__ header action >>>
self.rpn = b""
self.sheet_references = []
self.xcall_references = []
### __init__ header action <<<
def formula(self):
self.expr("V")
def expr(self, arg_type):
self.prec0_expr(arg_type)
while True:
if ((self.LA(1) >= EQ and self.LA(1) <= LE)):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [EQ]:
pass
self.match(EQ)
op = struct.pack('B', ptgEQ)
elif la1 and la1 in [NE]:
pass
self.match(NE)
op = struct.pack('B', ptgNE)
elif la1 and la1 in [GT]:
pass
self.match(GT)
op = struct.pack('B', ptgGT)
elif la1 and la1 in [LT]:
pass
self.match(LT)
op = struct.pack('B', ptgLT)
elif la1 and la1 in [GE]:
pass
self.match(GE)
op = struct.pack('B', ptgGE)
elif la1 and la1 in [LE]:
pass
self.match(LE)
op = struct.pack('B', ptgLE)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.prec0_expr(arg_type)
self.rpn += op
else:
break
def prec0_expr(self,
arg_type
):
pass
self.prec1_expr(arg_type)
while True:
if (self.LA(1)==CONCAT):
pass
pass
self.match(CONCAT)
op = struct.pack('B', ptgConcat)
self.prec1_expr(arg_type)
self.rpn += op
else:
break
def prec1_expr(self,
arg_type
):
pass
self.prec2_expr(arg_type)
while True:
if (self.LA(1)==ADD or self.LA(1)==SUB):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [ADD]:
pass
self.match(ADD)
op = struct.pack('B', ptgAdd)
elif la1 and la1 in [SUB]:
pass
self.match(SUB)
op = struct.pack('B', ptgSub)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.prec2_expr(arg_type)
self.rpn += op;
# print "**prec1_expr4 %s" % arg_type
else:
break
def prec2_expr(self,
arg_type
):
pass
self.prec3_expr(arg_type)
while True:
if (self.LA(1)==MUL or self.LA(1)==DIV):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [MUL]:
pass
self.match(MUL)
op = struct.pack('B', ptgMul)
elif la1 and la1 in [DIV]:
pass
self.match(DIV)
op = struct.pack('B', ptgDiv)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.prec3_expr(arg_type)
self.rpn += op
else:
break
def prec3_expr(self,
arg_type
):
pass
self.prec4_expr(arg_type)
while True:
if (self.LA(1)==POWER):
pass
pass
self.match(POWER)
op = struct.pack('B', ptgPower)
self.prec4_expr(arg_type)
self.rpn += op
else:
break
def prec4_expr(self,
arg_type
):
pass
self.prec5_expr(arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [PERCENT]:
pass
self.match(PERCENT)
self.rpn += struct.pack('B', ptgPercent)
elif la1 and la1 in [EOF,EQ,NE,GT,LT,GE,LE,ADD,SUB,MUL,DIV,POWER,RP,COMMA,SEMICOLON,CONCAT]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
def prec5_expr(self,
arg_type
):
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,LP,REF2D]:
pass
self.primary(arg_type)
elif la1 and la1 in [SUB]:
pass
self.match(SUB)
self.primary(arg_type)
self.rpn += struct.pack('B', ptgUminus)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
def primary(self,
arg_type
):
str_tok = None
int_tok = None
num_tok = None
ref2d_tok = None
ref2d1_tok = None
ref2d2_tok = None
ref3d_ref2d = None
ref3d_ref2d2 = None
name_tok = None
func_tok = None
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST]:
pass
self.match(TRUE_CONST)
self.rpn += struct.pack("2B", ptgBool, 1)
elif la1 and la1 in [FALSE_CONST]:
pass
self.match(FALSE_CONST)
self.rpn += struct.pack("2B", ptgBool, 0)
elif la1 and la1 in [STR_CONST]:
pass
str_tok = self.LT(1)
self.match(STR_CONST)
self.rpn += struct.pack("B", ptgStr) + upack1(str_tok.text[1:-1].replace("\"\"", "\""))
elif la1 and la1 in [NUM_CONST]:
pass
num_tok = self.LT(1)
self.match(NUM_CONST)
self.rpn += struct.pack("<Bd", ptgNum, float(num_tok.text))
elif la1 and la1 in [FUNC_IF]:
pass
self.match(FUNC_IF)
self.match(LP)
self.expr("V")
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.rpn += struct.pack("<BBH", ptgAttr, 0x02, 0) # tAttrIf
pos0 = len(self.rpn) - 2
self.expr(arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.rpn += struct.pack("<BBH", ptgAttr, 0x08, 0) # tAttrSkip
pos1 = len(self.rpn) - 2
self.rpn = self.rpn[:pos0] + struct.pack("<H", pos1-pos0) + self.rpn[pos0+2:]
self.expr(arg_type)
self.match(RP)
self.rpn += struct.pack("<BBH", ptgAttr, 0x08, 3) # tAttrSkip
self.rpn += struct.pack("<BBH", ptgFuncVarR, 3, 1) # 3 = nargs, 1 = IF func
pos2 = len(self.rpn)
self.rpn = self.rpn[:pos1] + struct.pack("<H", pos2-(pos1+2)-1) + self.rpn[pos1+2:]
elif la1 and la1 in [FUNC_CHOOSE]:
pass
self.match(FUNC_CHOOSE)
arg_type = b"R"
rpn_chunks = []
self.match(LP)
self.expr("V")
rpn_start = len(self.rpn)
ref_markers = [len(self.sheet_references)]
while True:
if (self.LA(1)==COMMA or self.LA(1)==SEMICOLON):
pass
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
mark = len(self.rpn)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,SUB,LP,REF2D]:
pass
self.expr(arg_type)
elif la1 and la1 in [RP,COMMA,SEMICOLON]:
pass
self.rpn += struct.pack("B", ptgMissArg)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
rpn_chunks.append(self.rpn[mark:])
ref_markers.append(len(self.sheet_references))
else:
break
self.match(RP)
self.rpn = self.rpn[:rpn_start]
nc = len(rpn_chunks)
chunklens = [len(chunk) for chunk in rpn_chunks]
skiplens = [0] * nc
skiplens[-1] = 3
for ic in range(nc-1, 0, -1):
skiplens[ic-1] = skiplens[ic] + chunklens[ic] + 4
jump_pos = [2 * nc + 2]
for ic in range(nc):
jump_pos.append(jump_pos[-1] + chunklens[ic] + 4)
chunk_shift = 2 * nc + 6 # size of tAttrChoose
for ic in range(nc):
for refx in range(ref_markers[ic], ref_markers[ic+1]):
ref = self.sheet_references[refx]
self.sheet_references[refx] = (ref[0], ref[1], ref[2] + chunk_shift)
chunk_shift += 4 # size of tAttrSkip
choose_rpn = []
choose_rpn.append(struct.pack("<BBH", ptgAttr, 0x04, nc)) # 0x04 is tAttrChoose
choose_rpn.append(struct.pack("<%dH" % (nc+1), *jump_pos))
for ic in range(nc):
choose_rpn.append(rpn_chunks[ic])
choose_rpn.append(struct.pack("<BBH", ptgAttr, 0x08, skiplens[ic])) # 0x08 is tAttrSkip
choose_rpn.append(struct.pack("<BBH", ptgFuncVarV, nc+1, 100)) # 100 is CHOOSE fn
self.rpn += b"".join(choose_rpn)
elif la1 and la1 in [LP]:
pass
self.match(LP)
self.expr(arg_type)
self.match(RP)
self.rpn += struct.pack("B", ptgParen)
else:
if (self.LA(1)==INT_CONST) and (_tokenSet_0.member(self.LA(2))):
pass
int_tok = self.LT(1)
self.match(INT_CONST)
# print "**int_const", int_tok.text
int_value = int(int_tok.text)
if int_value <= 65535:
self.rpn += struct.pack("<BH", ptgInt, int_value)
else:
self.rpn += struct.pack("<Bd", ptgNum, float(int_value))
elif (self.LA(1)==REF2D) and (_tokenSet_0.member(self.LA(2))):
pass
ref2d_tok = self.LT(1)
self.match(REF2D)
# print "**ref2d %s %s" % (ref2d_tok.text, arg_type)
r, c = Utils.cell_to_packed_rowcol(ref2d_tok.text)
ptg = ptgRefR + _RVAdeltaRef[arg_type]
self.rpn += struct.pack("<B2H", ptg, r, c)
elif (self.LA(1)==REF2D) and (self.LA(2)==COLON):
pass
ref2d1_tok = self.LT(1)
self.match(REF2D)
self.match(COLON)
ref2d2_tok = self.LT(1)
self.match(REF2D)
r1, c1 = Utils.cell_to_packed_rowcol(ref2d1_tok.text)
r2, c2 = Utils.cell_to_packed_rowcol(ref2d2_tok.text)
ptg = ptgAreaR + _RVAdeltaArea[arg_type]
self.rpn += struct.pack("<B4H", ptg, r1, r2, c1, c2)
elif (self.LA(1)==INT_CONST or self.LA(1)==NAME or self.LA(1)==QUOTENAME) and (self.LA(2)==COLON or self.LA(2)==BANG):
pass
sheet1=self.sheet()
sheet2 = sheet1
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [COLON]:
pass
self.match(COLON)
sheet2=self.sheet()
elif la1 and la1 in [BANG]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.match(BANG)
ref3d_ref2d = self.LT(1)
self.match(REF2D)
ptg = ptgRef3dR + _RVAdeltaRef[arg_type]
rpn_ref2d = b""
r1, c1 = Utils.cell_to_packed_rowcol(ref3d_ref2d.text)
rpn_ref2d = struct.pack("<3H", 0x0000, r1, c1)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [COLON]:
pass
self.match(COLON)
ref3d_ref2d2 = self.LT(1)
self.match(REF2D)
ptg = ptgArea3dR + _RVAdeltaArea[arg_type]
r2, c2 = Utils.cell_to_packed_rowcol(ref3d_ref2d2.text)
rpn_ref2d = struct.pack("<5H", 0x0000, r1, r2, c1, c2)
elif la1 and la1 in [EOF,EQ,NE,GT,LT,GE,LE,ADD,SUB,MUL,DIV,POWER,PERCENT,RP,COMMA,SEMICOLON,CONCAT]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
self.rpn += struct.pack("<B", ptg)
self.sheet_references.append((sheet1, sheet2, len(self.rpn)))
self.rpn += rpn_ref2d
elif (self.LA(1)==NAME) and (_tokenSet_0.member(self.LA(2))):
name_tok = self.LT(1)
self.match(NAME)
raise Exception("[formula] found unexpected NAME token (%r)" % name_tok.txt)
# #### TODO: handle references to defined names here
elif (self.LA(1)==NAME) and (self.LA(2)==LP):
func_tok = self.LT(1)
self.match(NAME)
func_toku = func_tok.text.upper()
if func_toku in all_funcs_by_name:
(opcode,
min_argc,
max_argc,
func_type,
arg_type_str) = all_funcs_by_name[func_toku]
arg_type_list = list(arg_type_str)
else:
raise Exception("[formula] unknown function (%s)" % func_tok.text)
# print "**func_tok1 %s %s" % (func_toku, func_type)
xcall = opcode < 0
if xcall:
# The name of the add-in function is passed as the 1st arg
# of the hidden XCALL function
self.xcall_references.append((func_toku, len(self.rpn) + 1))
self.rpn += struct.pack("<BHHH",
ptgNameXR,
0xadde, # ##PATCHME## index to REF entry in EXTERNSHEET record
0xefbe, # ##PATCHME## one-based index to EXTERNNAME record
0x0000) # unused
self.match(LP)
arg_count=self.expr_list(arg_type_list, min_argc, max_argc)
self.match(RP)
if arg_count > max_argc or arg_count < min_argc:
raise Exception("%d parameters for function: %s" % (arg_count, func_tok.text))
if xcall:
func_ptg = ptgFuncVarR + _RVAdelta[func_type]
self.rpn += struct.pack("<2BH", func_ptg, arg_count + 1, 255) # 255 is magic XCALL function
elif min_argc == max_argc:
func_ptg = ptgFuncR + _RVAdelta[func_type]
self.rpn += struct.pack("<BH", func_ptg, opcode)
elif arg_count == 1 and func_tok.text.upper() == "SUM":
self.rpn += struct.pack("<BBH", ptgAttr, 0x10, 0) # tAttrSum
else:
func_ptg = ptgFuncVarR + _RVAdelta[func_type]
self.rpn += struct.pack("<2BH", func_ptg, arg_count, opcode)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
def sheet(self):
ref = None
sheet_ref_name = None
sheet_ref_int = None
sheet_ref_quote = None
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [NAME]:
sheet_ref_name = self.LT(1)
self.match(NAME)
ref = sheet_ref_name.text
elif la1 and la1 in [INT_CONST]:
sheet_ref_int = self.LT(1)
self.match(INT_CONST)
ref = sheet_ref_int.text
elif la1 and la1 in [QUOTENAME]:
sheet_ref_quote = self.LT(1)
self.match(QUOTENAME)
ref = sheet_ref_quote.text[1:-1].replace("''", "'")
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
return ref
def expr_list(self,
arg_type_list, min_argc, max_argc
):
arg_cnt = None
arg_cnt = 0
arg_type = arg_type_list[arg_cnt]
# print "**expr_list1[%d] req=%s" % (arg_cnt, arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,SUB,LP,REF2D]:
pass
self.expr(arg_type)
arg_cnt += 1
while True:
if (self.LA(1)==COMMA or self.LA(1)==SEMICOLON):
pass
if arg_cnt < len(arg_type_list):
arg_type = arg_type_list[arg_cnt]
else:
arg_type = arg_type_list[-1]
if arg_type == "+":
arg_type = arg_type_list[-2]
# print "**expr_list2[%d] req=%s" % (arg_cnt, arg_type)
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [SEMICOLON]:
pass
self.match(SEMICOLON)
elif la1 and la1 in [COMMA]:
pass
self.match(COMMA)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
la1 = self.LA(1)
if False:
pass
elif la1 and la1 in [TRUE_CONST,FALSE_CONST,STR_CONST,NUM_CONST,INT_CONST,FUNC_IF,FUNC_CHOOSE,NAME,QUOTENAME,SUB,LP,REF2D]:
pass
self.expr(arg_type)
elif la1 and la1 in [RP,COMMA,SEMICOLON]:
pass
self.rpn += struct.pack("B", ptgMissArg)
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
arg_cnt += 1
else:
break
elif la1 and la1 in [RP]:
pass
else:
raise antlr.NoViableAltException(self.LT(1), self.getFilename())
return arg_cnt
_tokenNames = [
"<0>",
"EOF",
"<2>",
"NULL_TREE_LOOKAHEAD",
"TRUE_CONST",
"FALSE_CONST",
"STR_CONST",
"NUM_CONST",
"INT_CONST",
"FUNC_IF",
"FUNC_CHOOSE",
"NAME",
"QUOTENAME",
"EQ",
"NE",
"GT",
"LT",
"GE",
"LE",
"ADD",
"SUB",
"MUL",
"DIV",
"POWER",
"PERCENT",
"LP",
"RP",
"LB",
"RB",
"COLON",
"COMMA",
"SEMICOLON",
"REF2D",
"REF2D_R1C1",
"BANG",
"CONCAT"
]
### generate bit set
def mk_tokenSet_0():
### var1
data = [ 37681618946, 0]
return data
_tokenSet_0 = antlr.BitSet(mk_tokenSet_0())
-859
View File
@@ -1,859 +0,0 @@
""" lots of Excel Magic Numbers """
# Boundaries BIFF8+
MAX_ROW = 65536
MAX_COL = 256
biff_records = {
0x0000: "DIMENSIONS",
0x0001: "BLANK",
0x0002: "INTEGER",
0x0003: "NUMBER",
0x0004: "LABEL",
0x0005: "BOOLERR",
0x0006: "FORMULA",
0x0007: "STRING",
0x0008: "ROW",
0x0009: "BOF",
0x000A: "EOF",
0x000B: "INDEX",
0x000C: "CALCCOUNT",
0x000D: "CALCMODE",
0x000E: "PRECISION",
0x000F: "REFMODE",
0x0010: "DELTA",
0x0011: "ITERATION",
0x0012: "PROTECT",
0x0013: "PASSWORD",
0x0014: "HEADER",
0x0015: "FOOTER",
0x0016: "EXTERNCOUNT",
0x0017: "EXTERNSHEET",
0x0018: "NAME",
0x0019: "WINDOWPROTECT",
0x001A: "VERTICALPAGEBREAKS",
0x001B: "HORIZONTALPAGEBREAKS",
0x001C: "NOTE",
0x001D: "SELECTION",
0x001E: "FORMAT",
0x001F: "FORMATCOUNT",
0x0020: "COLUMNDEFAULT",
0x0021: "ARRAY",
0x0022: "1904",
0x0023: "EXTERNNAME",
0x0024: "COLWIDTH",
0x0025: "DEFAULTROWHEIGHT",
0x0026: "LEFTMARGIN",
0x0027: "RIGHTMARGIN",
0x0028: "TOPMARGIN",
0x0029: "BOTTOMMARGIN",
0x002A: "PRINTHEADERS",
0x002B: "PRINTGRIDLINES",
0x002F: "FILEPASS",
0x0031: "FONT",
0x0036: "TABLE",
0x003C: "CONTINUE",
0x003D: "WINDOW1",
0x003E: "WINDOW2",
0x0040: "BACKUP",
0x0041: "PANE",
0x0042: "CODEPAGE",
0x0043: "XF",
0x0044: "IXFE",
0x0045: "EFONT",
0x004D: "PLS",
0x0050: "DCON",
0x0051: "DCONREF",
0x0053: "DCONNAME",
0x0055: "DEFCOLWIDTH",
0x0056: "BUILTINFMTCNT",
0x0059: "XCT",
0x005A: "CRN",
0x005B: "FILESHARING",
0x005C: "WRITEACCESS",
0x005D: "OBJ",
0x005E: "UNCALCED",
0x005F: "SAFERECALC",
0x0060: "TEMPLATE",
0x0063: "OBJPROTECT",
0x007D: "COLINFO",
0x007E: "RK",
0x007F: "IMDATA",
0x0080: "GUTS",
0x0081: "WSBOOL",
0x0082: "GRIDSET",
0x0083: "HCENTER",
0x0084: "VCENTER",
0x0085: "BOUNDSHEET",
0x0086: "WRITEPROT",
0x0087: "ADDIN",
0x0088: "EDG",
0x0089: "PUB",
0x008C: "COUNTRY",
0x008D: "HIDEOBJ",
0x008E: "BUNDLESOFFSET",
0x008F: "BUNDLEHEADER",
0x0090: "SORT",
0x0091: "SUB",
0x0092: "PALETTE",
0x0093: "STYLE",
0x0094: "LHRECORD",
0x0095: "LHNGRAPH",
0x0096: "SOUND",
0x0098: "LPR",
0x0099: "STANDARDWIDTH",
0x009A: "FNGROUPNAME",
0x009B: "FILTERMODE",
0x009C: "FNGROUPCOUNT",
0x009D: "AUTOFILTERINFO",
0x009E: "AUTOFILTER",
0x00A0: "SCL",
0x00A1: "SETUP",
0x00A9: "COORDLIST",
0x00AB: "GCW",
0x00AE: "SCENMAN",
0x00AF: "SCENARIO",
0x00B0: "SXVIEW",
0x00B1: "SXVD",
0x00B2: "SXVI",
0x00B4: "SXIVD",
0x00B5: "SXLI",
0x00B6: "SXPI",
0x00B8: "DOCROUTE",
0x00B9: "RECIPNAME",
0x00BC: "SHRFMLA",
0x00BD: "MULRK",
0x00BE: "MULBLANK",
0x00C1: "MMS",
0x00C2: "ADDMENU",
0x00C3: "DELMENU",
0x00C5: "SXDI",
0x00C6: "SXDB",
0x00C7: "SXFIELD",
0x00C8: "SXINDEXLIST",
0x00C9: "SXDOUBLE",
0x00CD: "SXSTRING",
0x00CE: "SXDATETIME",
0x00D0: "SXTBL",
0x00D1: "SXTBRGITEM",
0x00D2: "SXTBPG",
0x00D3: "OBPROJ",
0x00D5: "SXIDSTM",
0x00D6: "RSTRING",
0x00D7: "DBCELL",
0x00DA: "BOOKBOOL",
0x00DC: "SXEXT|PARAMQRY",
0x00DD: "SCENPROTECT",
0x00DE: "OLESIZE",
0x00DF: "UDDESC",
0x00E0: "XF",
0x00E1: "INTERFACEHDR",
0x00E2: "INTERFACEEND",
0x00E3: "SXVS",
0x00E5: "MERGEDCELLS",
0x00E9: "BITMAP",
0x00EB: "MSODRAWINGGROUP",
0x00EC: "MSODRAWING",
0x00ED: "MSODRAWINGSELECTION",
0x00F0: "SXRULE",
0x00F1: "SXEX",
0x00F2: "SXFILT",
0x00F6: "SXNAME",
0x00F7: "SXSELECT",
0x00F8: "SXPAIR",
0x00F9: "SXFMLA",
0x00FB: "SXFORMAT",
0x00FC: "SST",
0x00FD: "LABELSST",
0x00FF: "EXTSST",
0x0100: "SXVDEX",
0x0103: "SXFORMULA",
0x0122: "SXDBEX",
0x0137: "CHTRINSERT",
0x0138: "CHTRINFO",
0x013B: "CHTRCELLCONTENT",
0x013D: "TABID",
0x0140: "CHTRMOVERANGE",
0x014D: "CHTRINSERTTAB",
0x015F: "LABELRANGES",
0x0160: "USESELFS",
0x0161: "DSF",
0x0162: "XL5MODIFY",
0x0196: "CHTRHEADER",
0x01A9: "USERBVIEW",
0x01AA: "USERSVIEWBEGIN",
0x01AB: "USERSVIEWEND",
0x01AD: "QSI",
0x01AE: "SUPBOOK",
0x01AF: "PROT4REV",
0x01B0: "CONDFMT",
0x01B1: "CF",
0x01B2: "DVAL",
0x01B5: "DCONBIN",
0x01B6: "TXO",
0x01B7: "REFRESHALL",
0x01B8: "HLINK",
0x01BA: "CODENAME",
0x01BB: "SXFDBTYPE",
0x01BC: "PROT4REVPASS",
0x01BE: "DV",
0x01C0: "XL9FILE",
0x01C1: "RECALCID",
0x0200: "DIMENSIONS",
0x0201: "BLANK",
0x0203: "NUMBER",
0x0204: "LABEL",
0x0205: "BOOLERR",
0x0206: "FORMULA",
0x0207: "STRING",
0x0208: "ROW",
0x0209: "BOF",
0x020B: "INDEX",
0x0218: "NAME",
0x0221: "ARRAY",
0x0223: "EXTERNNAME",
0x0225: "DEFAULTROWHEIGHT",
0x0231: "FONT",
0x0236: "TABLE",
0x023E: "WINDOW2",
0x0243: "XF",
0x027E: "RK",
0x0293: "STYLE",
0x0406: "FORMULA",
0x0409: "BOF",
0x041E: "FORMAT",
0x0443: "XF",
0x04BC: "SHRFMLA",
0x0800: "SCREENTIP",
0x0803: "WEBQRYSETTINGS",
0x0804: "WEBQRYTABLES",
0x0809: "BOF",
0x0862: "SHEETLAYOUT",
0x0867: "SHEETPROTECTION",
0x1001: "UNITS",
0x1002: "ChartChart",
0x1003: "ChartSeries",
0x1006: "ChartDataformat",
0x1007: "ChartLineformat",
0x1009: "ChartMarkerformat",
0x100A: "ChartAreaformat",
0x100B: "ChartPieformat",
0x100C: "ChartAttachedlabel",
0x100D: "ChartSeriestext",
0x1014: "ChartChartformat",
0x1015: "ChartLegend",
0x1016: "ChartSerieslist",
0x1017: "ChartBar",
0x1018: "ChartLine",
0x1019: "ChartPie",
0x101A: "ChartArea",
0x101B: "ChartScatter",
0x101C: "ChartChartline",
0x101D: "ChartAxis",
0x101E: "ChartTick",
0x101F: "ChartValuerange",
0x1020: "ChartCatserrange",
0x1021: "ChartAxislineformat",
0x1022: "ChartFormatlink",
0x1024: "ChartDefaulttext",
0x1025: "ChartText",
0x1026: "ChartFontx",
0x1027: "ChartObjectLink",
0x1032: "ChartFrame",
0x1033: "BEGIN",
0x1034: "END",
0x1035: "ChartPlotarea",
0x103A: "Chart3D",
0x103C: "ChartPicf",
0x103D: "ChartDropbar",
0x103E: "ChartRadar",
0x103F: "ChartSurface",
0x1040: "ChartRadararea",
0x1041: "ChartAxisparent",
0x1043: "ChartLegendxn",
0x1044: "ChartShtprops",
0x1045: "ChartSertocrt",
0x1046: "ChartAxesused",
0x1048: "ChartSbaseref",
0x104A: "ChartSerparent",
0x104B: "ChartSerauxtrend",
0x104E: "ChartIfmt",
0x104F: "ChartPos",
0x1050: "ChartAlruns",
0x1051: "ChartAI",
0x105B: "ChartSerauxerrbar",
0x105D: "ChartSerfmt",
0x105F: "Chart3DDataFormat",
0x1060: "ChartFbi",
0x1061: "ChartBoppop",
0x1062: "ChartAxcext",
0x1063: "ChartDat",
0x1064: "ChartPlotgrowth",
0x1065: "ChartSiindex",
0x1066: "ChartGelframe",
0x1067: "ChartBoppcustom",
0xFFFF: ""
}
all_funcs_by_name = {
# Includes Analysis ToolPak aka ATP aka add-in aka xcall functions,
# distinguished by -ve opcode.
# name: (opcode, min # args, max # args, func return type, func arg types)
# + in func arg types means more of the same.
'ABS' : ( 24, 1, 1, 'V', 'V'),
'ACCRINT' : ( -1, 6, 7, 'V', 'VVVVVVV'),
'ACCRINTM' : ( -1, 3, 5, 'V', 'VVVVV'),
'ACOS' : ( 99, 1, 1, 'V', 'V'),
'ACOSH' : (233, 1, 1, 'V', 'V'),
'ADDRESS' : (219, 2, 5, 'V', 'VVVVV'),
'AMORDEGRC' : ( -1, 7, 7, 'V', 'VVVVVVV'),
'AMORLINC' : ( -1, 7, 7, 'V', 'VVVVVVV'),
'AND' : ( 36, 1, 30, 'V', 'D+'),
'AREAS' : ( 75, 1, 1, 'V', 'R'),
'ASC' : (214, 1, 1, 'V', 'V'),
'ASIN' : ( 98, 1, 1, 'V', 'V'),
'ASINH' : (232, 1, 1, 'V', 'V'),
'ATAN' : ( 18, 1, 1, 'V', 'V'),
'ATAN2' : ( 97, 2, 2, 'V', 'VV'),
'ATANH' : (234, 1, 1, 'V', 'V'),
'AVEDEV' : (269, 1, 30, 'V', 'D+'),
'AVERAGE' : ( 5, 1, 30, 'V', 'D+'),
'AVERAGEA' : (361, 1, 30, 'V', 'D+'),
'BAHTTEXT' : (368, 1, 1, 'V', 'V'),
'BESSELI' : ( -1, 2, 2, 'V', 'VV'),
'BESSELJ' : ( -1, 2, 2, 'V', 'VV'),
'BESSELK' : ( -1, 2, 2, 'V', 'VV'),
'BESSELY' : ( -1, 2, 2, 'V', 'VV'),
'BETADIST' : (270, 3, 5, 'V', 'VVVVV'),
'BETAINV' : (272, 3, 5, 'V', 'VVVVV'),
'BIN2DEC' : ( -1, 1, 1, 'V', 'V'),
'BIN2HEX' : ( -1, 1, 2, 'V', 'VV'),
'BIN2OCT' : ( -1, 1, 2, 'V', 'VV'),
'BINOMDIST' : (273, 4, 4, 'V', 'VVVV'),
'CEILING' : (288, 2, 2, 'V', 'VV'),
'CELL' : (125, 1, 2, 'V', 'VR'),
'CHAR' : (111, 1, 1, 'V', 'V'),
'CHIDIST' : (274, 2, 2, 'V', 'VV'),
'CHIINV' : (275, 2, 2, 'V', 'VV'),
'CHITEST' : (306, 2, 2, 'V', 'AA'),
'CHOOSE' : (100, 2, 30, 'R', 'VR+'),
'CLEAN' : (162, 1, 1, 'V', 'V'),
'CODE' : (121, 1, 1, 'V', 'V'),
'COLUMN' : ( 9, 0, 1, 'V', 'R'),
'COLUMNS' : ( 77, 1, 1, 'V', 'R'),
'COMBIN' : (276, 2, 2, 'V', 'VV'),
'COMPLEX' : ( -1, 2, 3, 'V', 'VVV'),
'CONCATENATE' : (336, 1, 30, 'V', 'V+'),
'CONFIDENCE' : (277, 3, 3, 'V', 'VVV'),
'CONVERT' : ( -1, 3, 3, 'V', 'VVV'),
'CORREL' : (307, 2, 2, 'V', 'AA'),
'COS' : ( 16, 1, 1, 'V', 'V'),
'COSH' : (230, 1, 1, 'V', 'V'),
'COUNT' : ( 0, 1, 30, 'V', 'D+'),
'COUNTA' : (169, 1, 30, 'V', 'D+'),
'COUNTBLANK' : (347, 1, 1, 'V', 'R'),
'COUNTIF' : (346, 2, 2, 'V', 'RV'),
'COUPDAYBS' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPDAYS' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPDAYSNC' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPNCD' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPNUM' : ( -1, 3, 5, 'V', 'VVVVV'),
'COUPPCD' : ( -1, 3, 5, 'V', 'VVVVV'),
'COVAR' : (308, 2, 2, 'V', 'AA'),
'CRITBINOM' : (278, 3, 3, 'V', 'VVV'),
'CUMIPMT' : ( -1, 6, 6, 'V', 'VVVVVV'),
'CUMPRINC' : ( -1, 6, 6, 'V', 'VVVVVV'),
'DATE' : ( 65, 3, 3, 'V', 'VVV'),
'DATEDIF' : (351, 3, 3, 'V', 'VVV'),
'DATEVALUE' : (140, 1, 1, 'V', 'V'),
'DAVERAGE' : ( 42, 3, 3, 'V', 'RRR'),
'DAY' : ( 67, 1, 1, 'V', 'V'),
'DAYS360' : (220, 2, 3, 'V', 'VVV'),
'DB' : (247, 4, 5, 'V', 'VVVVV'),
'DBCS' : (215, 1, 1, 'V', 'V'),
'DCOUNT' : ( 40, 3, 3, 'V', 'RRR'),
'DCOUNTA' : (199, 3, 3, 'V', 'RRR'),
'DDB' : (144, 4, 5, 'V', 'VVVVV'),
'DEC2BIN' : ( -1, 1, 2, 'V', 'VV'),
'DEC2HEX' : ( -1, 1, 2, 'V', 'VV'),
'DEC2OCT' : ( -1, 1, 2, 'V', 'VV'),
'DEGREES' : (343, 1, 1, 'V', 'V'),
'DELTA' : ( -1, 1, 2, 'V', 'VV'),
'DEVSQ' : (318, 1, 30, 'V', 'D+'),
'DGET' : (235, 3, 3, 'V', 'RRR'),
'DISC' : ( -1, 4, 5, 'V', 'VVVVV'),
'DMAX' : ( 44, 3, 3, 'V', 'RRR'),
'DMIN' : ( 43, 3, 3, 'V', 'RRR'),
'DOLLAR' : ( 13, 1, 2, 'V', 'VV'),
'DOLLARDE' : ( -1, 2, 2, 'V', 'VV'),
'DOLLARFR' : ( -1, 2, 2, 'V', 'VV'),
'DPRODUCT' : (189, 3, 3, 'V', 'RRR'),
'DSTDEV' : ( 45, 3, 3, 'V', 'RRR'),
'DSTDEVP' : (195, 3, 3, 'V', 'RRR'),
'DSUM' : ( 41, 3, 3, 'V', 'RRR'),
'DURATION' : ( -1, 5, 6, 'V', 'VVVVVV'),
'DVAR' : ( 47, 3, 3, 'V', 'RRR'),
'DVARP' : (196, 3, 3, 'V', 'RRR'),
'EDATE' : ( -1, 2, 2, 'V', 'VV'),
'EFFECT' : ( -1, 2, 2, 'V', 'VV'),
'EOMONTH' : ( -1, 1, 2, 'V', 'VV'),
'ERF' : ( -1, 1, 2, 'V', 'VV'),
'ERFC' : ( -1, 1, 1, 'V', 'V'),
'ERROR.TYPE' : (261, 1, 1, 'V', 'V'),
'EVEN' : (279, 1, 1, 'V', 'V'),
'EXACT' : (117, 2, 2, 'V', 'VV'),
'EXP' : ( 21, 1, 1, 'V', 'V'),
'EXPONDIST' : (280, 3, 3, 'V', 'VVV'),
'FACT' : (184, 1, 1, 'V', 'V'),
'FACTDOUBLE' : ( -1, 1, 1, 'V', 'V'),
'FALSE' : ( 35, 0, 0, 'V', '-'),
'FDIST' : (281, 3, 3, 'V', 'VVV'),
'FIND' : (124, 2, 3, 'V', 'VVV'),
'FINDB' : (205, 2, 3, 'V', 'VVV'),
'FINV' : (282, 3, 3, 'V', 'VVV'),
'FISHER' : (283, 1, 1, 'V', 'V'),
'FISHERINV' : (284, 1, 1, 'V', 'V'),
'FIXED' : ( 14, 2, 3, 'V', 'VVV'),
'FLOOR' : (285, 2, 2, 'V', 'VV'),
'FORECAST' : (309, 3, 3, 'V', 'VAA'),
'FREQUENCY' : (252, 2, 2, 'A', 'RR'),
'FTEST' : (310, 2, 2, 'V', 'AA'),
'FV' : ( 57, 3, 5, 'V', 'VVVVV'),
'FVSCHEDULE' : ( -1, 2, 2, 'V', 'VA'),
'GAMMADIST' : (286, 4, 4, 'V', 'VVVV'),
'GAMMAINV' : (287, 3, 3, 'V', 'VVV'),
'GAMMALN' : (271, 1, 1, 'V', 'V'),
'GCD' : ( -1, 1, 29, 'V', 'V+'),
'GEOMEAN' : (319, 1, 30, 'V', 'D+'),
'GESTEP' : ( -1, 1, 2, 'V', 'VV'),
'GETPIVOTDATA': (358, 2, 30, 'A', 'VAV+'),
'GROWTH' : ( 52, 1, 4, 'A', 'RRRV'),
'HARMEAN' : (320, 1, 30, 'V', 'D+'),
'HEX2BIN' : ( -1, 1, 2, 'V', 'VV'),
'HEX2DEC' : ( -1, 1, 1, 'V', 'V'),
'HEX2OCT' : ( -1, 1, 2, 'V', 'VV'),
'HLOOKUP' : (101, 3, 4, 'V', 'VRRV'),
'HOUR' : ( 71, 1, 1, 'V', 'V'),
'HYPERLINK' : (359, 1, 2, 'V', 'VV'),
'HYPGEOMDIST' : (289, 4, 4, 'V', 'VVVV'),
'IF' : ( 1, 2, 3, 'R', 'VRR'),
'IMABS' : ( -1, 1, 1, 'V', 'V'),
'IMAGINARY' : ( -1, 1, 1, 'V', 'V'),
'IMARGUMENT' : ( -1, 1, 1, 'V', 'V'),
'IMCONJUGATE' : ( -1, 1, 1, 'V', 'V'),
'IMCOS' : ( -1, 1, 1, 'V', 'V'),
'IMDIV' : ( -1, 2, 2, 'V', 'VV'),
'IMEXP' : ( -1, 1, 1, 'V', 'V'),
'IMLN' : ( -1, 1, 1, 'V', 'V'),
'IMLOG10' : ( -1, 1, 1, 'V', 'V'),
'IMLOG2' : ( -1, 1, 1, 'V', 'V'),
'IMPOWER' : ( -1, 2, 2, 'V', 'VV'),
'IMPRODUCT' : ( -1, 2, 2, 'V', 'VV'),
'IMREAL' : ( -1, 1, 1, 'V', 'V'),
'IMSIN' : ( -1, 1, 1, 'V', 'V'),
'IMSQRT' : ( -1, 1, 1, 'V', 'V'),
'IMSUB' : ( -1, 2, 2, 'V', 'VV'),
'IMSUM' : ( -1, 1, 29, 'V', 'V+'),
'INDEX' : ( 29, 2, 4, 'R', 'RVVV'),
'INDIRECT' : (148, 1, 2, 'R', 'VV'),
'INFO' : (244, 1, 1, 'V', 'V'),
'INT' : ( 25, 1, 1, 'V', 'V'),
'INTERCEPT' : (311, 2, 2, 'V', 'AA'),
'INTRATE' : ( -1, 4, 5, 'V', 'VVVVV'),
'IPMT' : (167, 4, 6, 'V', 'VVVVVV'),
'IRR' : ( 62, 1, 2, 'V', 'RV'),
'ISBLANK' : (129, 1, 1, 'V', 'V'),
'ISERR' : (126, 1, 1, 'V', 'V'),
'ISERROR' : ( 3, 1, 1, 'V', 'V'),
'ISEVEN' : ( -1, 1, 1, 'V', 'V'),
'ISLOGICAL' : (198, 1, 1, 'V', 'V'),
'ISNA' : ( 2, 1, 1, 'V', 'V'),
'ISNONTEXT' : (190, 1, 1, 'V', 'V'),
'ISNUMBER' : (128, 1, 1, 'V', 'V'),
'ISODD' : ( -1, 1, 1, 'V', 'V'),
'ISPMT' : (350, 4, 4, 'V', 'VVVV'),
'ISREF' : (105, 1, 1, 'V', 'R'),
'ISTEXT' : (127, 1, 1, 'V', 'V'),
'KURT' : (322, 1, 30, 'V', 'D+'),
'LARGE' : (325, 2, 2, 'V', 'RV'),
'LCM' : ( -1, 1, 29, 'V', 'V+'),
'LEFT' : (115, 1, 2, 'V', 'VV'),
'LEFTB' : (208, 1, 2, 'V', 'VV'),
'LEN' : ( 32, 1, 1, 'V', 'V'),
'LENB' : (211, 1, 1, 'V', 'V'),
'LINEST' : ( 49, 1, 4, 'A', 'RRVV'),
'LN' : ( 22, 1, 1, 'V', 'V'),
'LOG' : (109, 1, 2, 'V', 'VV'),
'LOG10' : ( 23, 1, 1, 'V', 'V'),
'LOGEST' : ( 51, 1, 4, 'A', 'RRVV'),
'LOGINV' : (291, 3, 3, 'V', 'VVV'),
'LOGNORMDIST' : (290, 3, 3, 'V', 'VVV'),
'LOOKUP' : ( 28, 2, 3, 'V', 'VRR'),
'LOWER' : (112, 1, 1, 'V', 'V'),
'MATCH' : ( 64, 2, 3, 'V', 'VRR'),
'MAX' : ( 7, 1, 30, 'V', 'D+'),
'MAXA' : (362, 1, 30, 'V', 'D+'),
'MDETERM' : (163, 1, 1, 'V', 'A'),
'MDURATION' : ( -1, 5, 6, 'V', 'VVVVVV'),
'MEDIAN' : (227, 1, 30, 'V', 'D+'),
'MID' : ( 31, 3, 3, 'V', 'VVV'),
'MIDB' : (210, 3, 3, 'V', 'VVV'),
'MIN' : ( 6, 1, 30, 'V', 'D+'),
'MINA' : (363, 1, 30, 'V', 'D+'),
'MINUTE' : ( 72, 1, 1, 'V', 'V'),
'MINVERSE' : (164, 1, 1, 'A', 'A'),
'MIRR' : ( 61, 3, 3, 'V', 'RVV'),
'MMULT' : (165, 2, 2, 'A', 'AA'),
'MOD' : ( 39, 2, 2, 'V', 'VV'),
'MODE' : (330, 1, 30, 'V', 'A+'), ################ weird #################
'MONTH' : ( 68, 1, 1, 'V', 'V'),
'MROUND' : ( -1, 2, 2, 'V', 'VV'),
'MULTINOMIAL' : ( -1, 1, 29, 'V', 'V+'),
'N' : (131, 1, 1, 'V', 'R'),
'NA' : ( 10, 0, 0, 'V', '-'),
'NEGBINOMDIST': (292, 3, 3, 'V', 'VVV'),
'NETWORKDAYS' : ( -1, 2, 3, 'V', 'VVR'),
'NOMINAL' : ( -1, 2, 2, 'V', 'VV'),
'NORMDIST' : (293, 4, 4, 'V', 'VVVV'),
'NORMINV' : (295, 3, 3, 'V', 'VVV'),
'NORMSDIST' : (294, 1, 1, 'V', 'V'),
'NORMSINV' : (296, 1, 1, 'V', 'V'),
'NOT' : ( 38, 1, 1, 'V', 'V'),
'NOW' : ( 74, 0, 0, 'V', '-'),
'NPER' : ( 58, 3, 5, 'V', 'VVVVV'),
'NPV' : ( 11, 2, 30, 'V', 'VD+'),
'OCT2BIN' : ( -1, 1, 2, 'V', 'VV'),
'OCT2DEC' : ( -1, 1, 1, 'V', 'V'),
'OCT2HEX' : ( -1, 1, 2, 'V', 'VV'),
'ODD' : (298, 1, 1, 'V', 'V'),
'ODDFPRICE' : ( -1, 9, 9, 'V', 'VVVVVVVVV'),
'ODDFYIELD' : ( -1, 9, 9, 'V', 'VVVVVVVVV'),
'ODDLPRICE' : ( -1, 8, 8, 'V', 'VVVVVVVV'),
'ODDLYIELD' : ( -1, 8, 8, 'V', 'VVVVVVVV'),
'OFFSET' : ( 78, 3, 5, 'R', 'RVVVV'),
'OR' : ( 37, 1, 30, 'V', 'D+'),
'PEARSON' : (312, 2, 2, 'V', 'AA'),
'PERCENTILE' : (328, 2, 2, 'V', 'RV'),
'PERCENTRANK' : (329, 2, 3, 'V', 'RVV'),
'PERMUT' : (299, 2, 2, 'V', 'VV'),
'PHONETIC' : (360, 1, 1, 'V', 'R'),
'PI' : ( 19, 0, 0, 'V', '-'),
'PMT' : ( 59, 3, 5, 'V', 'VVVVV'),
'POISSON' : (300, 3, 3, 'V', 'VVV'),
'POWER' : (337, 2, 2, 'V', 'VV'),
'PPMT' : (168, 4, 6, 'V', 'VVVVVV'),
'PRICE' : ( -1, 6, 7, 'V', 'VVVVVVV'),
'PRICEDISC' : ( -1, 4, 5, 'V', 'VVVVV'),
'PRICEMAT' : ( -1, 5, 6, 'V', 'VVVVVV'),
'PROB' : (317, 3, 4, 'V', 'AAVV'),
'PRODUCT' : (183, 1, 30, 'V', 'D+'),
'PROPER' : (114, 1, 1, 'V', 'V'),
'PV' : ( 56, 3, 5, 'V', 'VVVVV'),
'QUARTILE' : (327, 2, 2, 'V', 'RV'),
'QUOTIENT' : ( -1, 2, 2, 'V', 'VV'),
'RADIANS' : (342, 1, 1, 'V', 'V'),
'RAND' : ( 63, 0, 0, 'V', '-'),
'RANDBETWEEN' : ( -1, 2, 2, 'V', 'VV'),
'RANK' : (216, 2, 3, 'V', 'VRV'),
'RATE' : ( 60, 3, 6, 'V', 'VVVVVV'),
'RECEIVED' : ( -1, 4, 5, 'V', 'VVVVV'),
'REPLACE' : (119, 4, 4, 'V', 'VVVV'),
'REPLACEB' : (207, 4, 4, 'V', 'VVVV'),
'REPT' : ( 30, 2, 2, 'V', 'VV'),
'RIGHT' : (116, 1, 2, 'V', 'VV'),
'RIGHTB' : (209, 1, 2, 'V', 'VV'),
'ROMAN' : (354, 1, 2, 'V', 'VV'),
'ROUND' : ( 27, 2, 2, 'V', 'VV'),
'ROUNDDOWN' : (213, 2, 2, 'V', 'VV'),
'ROUNDUP' : (212, 2, 2, 'V', 'VV'),
'ROW' : ( 8, 0, 1, 'V', 'R'),
'ROWS' : ( 76, 1, 1, 'V', 'R'),
'RSQ' : (313, 2, 2, 'V', 'AA'),
'RTD' : (379, 3, 30, 'A', 'VVV+'),
'SEARCH' : ( 82, 2, 3, 'V', 'VVV'),
'SEARCHB' : (206, 2, 3, 'V', 'VVV'),
'SECOND' : ( 73, 1, 1, 'V', 'V'),
'SERIESSUM' : ( -1, 4, 4, 'V', 'VVVA'),
'SIGN' : ( 26, 1, 1, 'V', 'V'),
'SIN' : ( 15, 1, 1, 'V', 'V'),
'SINH' : (229, 1, 1, 'V', 'V'),
'SKEW' : (323, 1, 30, 'V', 'D+'),
'SLN' : (142, 3, 3, 'V', 'VVV'),
'SLOPE' : (315, 2, 2, 'V', 'AA'),
'SMALL' : (326, 2, 2, 'V', 'RV'),
'SQRT' : ( 20, 1, 1, 'V', 'V'),
'SQRTPI' : ( -1, 1, 1, 'V', 'V'),
'STANDARDIZE' : (297, 3, 3, 'V', 'VVV'),
'STDEV' : ( 12, 1, 30, 'V', 'D+'),
'STDEVA' : (366, 1, 30, 'V', 'D+'),
'STDEVP' : (193, 1, 30, 'V', 'D+'),
'STDEVPA' : (364, 1, 30, 'V', 'D+'),
'STEYX' : (314, 2, 2, 'V', 'AA'),
'SUBSTITUTE' : (120, 3, 4, 'V', 'VVVV'),
'SUBTOTAL' : (344, 2, 30, 'V', 'VR+'),
'SUM' : ( 4, 1, 30, 'V', 'D+'),
'SUMIF' : (345, 2, 3, 'V', 'RVR'),
'SUMPRODUCT' : (228, 1, 30, 'V', 'A+'),
'SUMSQ' : (321, 1, 30, 'V', 'D+'),
'SUMX2MY2' : (304, 2, 2, 'V', 'AA'),
'SUMX2PY2' : (305, 2, 2, 'V', 'AA'),
'SUMXMY2' : (303, 2, 2, 'V', 'AA'),
'SYD' : (143, 4, 4, 'V', 'VVVV'),
'T' : (130, 1, 1, 'V', 'R'),
'TAN' : ( 17, 1, 1, 'V', 'V'),
'TANH' : (231, 1, 1, 'V', 'V'),
'TBILLEQ' : ( -1, 3, 3, 'V', 'VVV'),
'TBILLPRICE' : ( -1, 3, 3, 'V', 'VVV'),
'TBILLYIELD' : ( -1, 3, 3, 'V', 'VVV'),
'TDIST' : (301, 3, 3, 'V', 'VVV'),
'TEXT' : ( 48, 2, 2, 'V', 'VV'),
'TIME' : ( 66, 3, 3, 'V', 'VVV'),
'TIMEVALUE' : (141, 1, 1, 'V', 'V'),
'TINV' : (332, 2, 2, 'V', 'VV'),
'TODAY' : (221, 0, 0, 'V', '-'),
'TRANSPOSE' : ( 83, 1, 1, 'A', 'A'),
'TREND' : ( 50, 1, 4, 'A', 'RRRV'),
'TRIM' : (118, 1, 1, 'V', 'V'),
'TRIMMEAN' : (331, 2, 2, 'V', 'RV'),
'TRUE' : ( 34, 0, 0, 'V', '-'),
'TRUNC' : (197, 1, 2, 'V', 'VV'),
'TTEST' : (316, 4, 4, 'V', 'AAVV'),
'TYPE' : ( 86, 1, 1, 'V', 'V'),
'UPPER' : (113, 1, 1, 'V', 'V'),
'USDOLLAR' : (204, 1, 2, 'V', 'VV'),
'VALUE' : ( 33, 1, 1, 'V', 'V'),
'VAR' : ( 46, 1, 30, 'V', 'D+'),
'VARA' : (367, 1, 30, 'V', 'D+'),
'VARP' : (194, 1, 30, 'V', 'D+'),
'VARPA' : (365, 1, 30, 'V', 'D+'),
'VDB' : (222, 5, 7, 'V', 'VVVVVVV'),
'VLOOKUP' : (102, 3, 4, 'V', 'VRRV'),
'WEEKDAY' : ( 70, 1, 2, 'V', 'VV'),
'WEEKNUM' : ( -1, 1, 2, 'V', 'VV'),
'WEIBULL' : (302, 4, 4, 'V', 'VVVV'),
'WORKDAY' : ( -1, 2, 3, 'V', 'VVR'),
'XIRR' : ( -1, 2, 3, 'V', 'AAV'),
'XNPV' : ( -1, 3, 3, 'V', 'VAA'),
'YEAR' : ( 69, 1, 1, 'V', 'V'),
'YEARFRAC' : ( -1, 2, 3, 'V', 'VVV'),
'YIELD' : ( -1, 6, 7, 'V', 'VVVVVVV'),
'YIELDDISC' : ( -1, 4, 5, 'V', 'VVVVV'),
'YIELDMAT' : ( -1, 5, 6, 'V', 'VVVVVV'),
'ZTEST' : (324, 2, 3, 'V', 'RVV'),
}
# Formulas Parse things
ptgExp = 0x01
ptgTbl = 0x02
ptgAdd = 0x03
ptgSub = 0x04
ptgMul = 0x05
ptgDiv = 0x06
ptgPower = 0x07
ptgConcat = 0x08
ptgLT = 0x09
ptgLE = 0x0a
ptgEQ = 0x0b
ptgGE = 0x0c
ptgGT = 0x0d
ptgNE = 0x0e
ptgIsect = 0x0f
ptgUnion = 0x10
ptgRange = 0x11
ptgUplus = 0x12
ptgUminus = 0x13
ptgPercent = 0x14
ptgParen = 0x15
ptgMissArg = 0x16
ptgStr = 0x17
ptgExtend = 0x18
ptgAttr = 0x19
ptgSheet = 0x1a
ptgEndSheet = 0x1b
ptgErr = 0x1c
ptgBool = 0x1d
ptgInt = 0x1e
ptgNum = 0x1f
ptgArrayR = 0x20
ptgFuncR = 0x21
ptgFuncVarR = 0x22
ptgNameR = 0x23
ptgRefR = 0x24
ptgAreaR = 0x25
ptgMemAreaR = 0x26
ptgMemErrR = 0x27
ptgMemNoMemR = 0x28
ptgMemFuncR = 0x29
ptgRefErrR = 0x2a
ptgAreaErrR = 0x2b
ptgRefNR = 0x2c
ptgAreaNR = 0x2d
ptgMemAreaNR = 0x2e
ptgMemNoMemNR = 0x2f
ptgNameXR = 0x39
ptgRef3dR = 0x3a
ptgArea3dR = 0x3b
ptgRefErr3dR = 0x3c
ptgAreaErr3dR = 0x3d
ptgArrayV = 0x40
ptgFuncV = 0x41
ptgFuncVarV = 0x42
ptgNameV = 0x43
ptgRefV = 0x44
ptgAreaV = 0x45
ptgMemAreaV = 0x46
ptgMemErrV = 0x47
ptgMemNoMemV = 0x48
ptgMemFuncV = 0x49
ptgRefErrV = 0x4a
ptgAreaErrV = 0x4b
ptgRefNV = 0x4c
ptgAreaNV = 0x4d
ptgMemAreaNV = 0x4e
ptgMemNoMemNV = 0x4f
ptgFuncCEV = 0x58
ptgNameXV = 0x59
ptgRef3dV = 0x5a
ptgArea3dV = 0x5b
ptgRefErr3dV = 0x5c
ptgAreaErr3dV = 0x5d
ptgArrayA = 0x60
ptgFuncA = 0x61
ptgFuncVarA = 0x62
ptgNameA = 0x63
ptgRefA = 0x64
ptgAreaA = 0x65
ptgMemAreaA = 0x66
ptgMemErrA = 0x67
ptgMemNoMemA = 0x68
ptgMemFuncA = 0x69
ptgRefErrA = 0x6a
ptgAreaErrA = 0x6b
ptgRefNA = 0x6c
ptgAreaNA = 0x6d
ptgMemAreaNA = 0x6e
ptgMemNoMemNA = 0x6f
ptgFuncCEA = 0x78
ptgNameXA = 0x79
ptgRef3dA = 0x7a
ptgArea3dA = 0x7b
ptgRefErr3dA = 0x7c
ptgAreaErr3dA = 0x7d
PtgNames = {
ptgExp : "ptgExp",
ptgTbl : "ptgTbl",
ptgAdd : "ptgAdd",
ptgSub : "ptgSub",
ptgMul : "ptgMul",
ptgDiv : "ptgDiv",
ptgPower : "ptgPower",
ptgConcat : "ptgConcat",
ptgLT : "ptgLT",
ptgLE : "ptgLE",
ptgEQ : "ptgEQ",
ptgGE : "ptgGE",
ptgGT : "ptgGT",
ptgNE : "ptgNE",
ptgIsect : "ptgIsect",
ptgUnion : "ptgUnion",
ptgRange : "ptgRange",
ptgUplus : "ptgUplus",
ptgUminus : "ptgUminus",
ptgPercent : "ptgPercent",
ptgParen : "ptgParen",
ptgMissArg : "ptgMissArg",
ptgStr : "ptgStr",
ptgExtend : "ptgExtend",
ptgAttr : "ptgAttr",
ptgSheet : "ptgSheet",
ptgEndSheet : "ptgEndSheet",
ptgErr : "ptgErr",
ptgBool : "ptgBool",
ptgInt : "ptgInt",
ptgNum : "ptgNum",
ptgArrayR : "ptgArrayR",
ptgFuncR : "ptgFuncR",
ptgFuncVarR : "ptgFuncVarR",
ptgNameR : "ptgNameR",
ptgRefR : "ptgRefR",
ptgAreaR : "ptgAreaR",
ptgMemAreaR : "ptgMemAreaR",
ptgMemErrR : "ptgMemErrR",
ptgMemNoMemR : "ptgMemNoMemR",
ptgMemFuncR : "ptgMemFuncR",
ptgRefErrR : "ptgRefErrR",
ptgAreaErrR : "ptgAreaErrR",
ptgRefNR : "ptgRefNR",
ptgAreaNR : "ptgAreaNR",
ptgMemAreaNR : "ptgMemAreaNR",
ptgMemNoMemNR : "ptgMemNoMemNR",
ptgNameXR : "ptgNameXR",
ptgRef3dR : "ptgRef3dR",
ptgArea3dR : "ptgArea3dR",
ptgRefErr3dR : "ptgRefErr3dR",
ptgAreaErr3dR : "ptgAreaErr3dR",
ptgArrayV : "ptgArrayV",
ptgFuncV : "ptgFuncV",
ptgFuncVarV : "ptgFuncVarV",
ptgNameV : "ptgNameV",
ptgRefV : "ptgRefV",
ptgAreaV : "ptgAreaV",
ptgMemAreaV : "ptgMemAreaV",
ptgMemErrV : "ptgMemErrV",
ptgMemNoMemV : "ptgMemNoMemV",
ptgMemFuncV : "ptgMemFuncV",
ptgRefErrV : "ptgRefErrV",
ptgAreaErrV : "ptgAreaErrV",
ptgRefNV : "ptgRefNV",
ptgAreaNV : "ptgAreaNV",
ptgMemAreaNV : "ptgMemAreaNV",
ptgMemNoMemNV : "ptgMemNoMemNV",
ptgFuncCEV : "ptgFuncCEV",
ptgNameXV : "ptgNameXV",
ptgRef3dV : "ptgRef3dV",
ptgArea3dV : "ptgArea3dV",
ptgRefErr3dV : "ptgRefErr3dV",
ptgAreaErr3dV : "ptgAreaErr3dV",
ptgArrayA : "ptgArrayA",
ptgFuncA : "ptgFuncA",
ptgFuncVarA : "ptgFuncVarA",
ptgNameA : "ptgNameA",
ptgRefA : "ptgRefA",
ptgAreaA : "ptgAreaA",
ptgMemAreaA : "ptgMemAreaA",
ptgMemErrA : "ptgMemErrA",
ptgMemNoMemA : "ptgMemNoMemA",
ptgMemFuncA : "ptgMemFuncA",
ptgRefErrA : "ptgRefErrA",
ptgAreaErrA : "ptgAreaErrA",
ptgRefNA : "ptgRefNA",
ptgAreaNA : "ptgAreaNA",
ptgMemAreaNA : "ptgMemAreaNA",
ptgMemNoMemNA : "ptgMemNoMemNA",
ptgFuncCEA : "ptgFuncCEA",
ptgNameXA : "ptgNameXA",
ptgRef3dA : "ptgRef3dA",
ptgArea3dA : "ptgArea3dA",
ptgRefErr3dA : "ptgRefErr3dA",
ptgAreaErr3dA : "ptgAreaErr3dA"
}
error_msg_by_code = {
0x00: "#NULL!", # intersection of two cell ranges is empty
0x07: "#DIV/0!", # division by zero
0x0F: "#VALUE!", # wrong type of operand
0x17: "#REF!", # illegal or deleted cell reference
0x1D: "#NAME?", # wrong function or range name
0x24: "#NUM!", # value range overflow
0x2A: "#N/A!" # argument or function not available
}
-261
View File
@@ -1,261 +0,0 @@
#!/usr/bin/env python
'''
The XF record is able to store explicit cell formatting attributes or the
attributes of a cell style. Explicit formatting includes the reference to
a cell style XF record. This allows to extend a defined cell style with
some explicit attributes. The formatting attributes are divided into
6 groups:
Group Attributes
-------------------------------------
Number format Number format index (index to FORMAT record)
Font Font index (index to FONT record)
Alignment Horizontal and vertical alignment, text wrap, indentation,
orientation/rotation, text direction
Border Border line styles and colours
Background Background area style and colours
Protection Cell locked, formula hidden
For each group a flag in the cell XF record specifies whether to use the
attributes contained in that XF record or in the referenced style
XF record. In style XF records, these flags specify whether the attributes
will overwrite explicit cell formatting when the style is applied to
a cell. Changing a cell style (without applying this style to a cell) will
change all cells which already use that style and do not contain explicit
cell attributes for the changed style attributes. If a cell XF record does
not contain explicit attributes in a group (if the attribute group flag
is not set), it repeats the attributes of its style XF record.
'''
from . import BIFFRecords
class Font(object):
ESCAPEMENT_NONE = 0x00
ESCAPEMENT_SUPERSCRIPT = 0x01
ESCAPEMENT_SUBSCRIPT = 0x02
UNDERLINE_NONE = 0x00
UNDERLINE_SINGLE = 0x01
UNDERLINE_SINGLE_ACC = 0x21
UNDERLINE_DOUBLE = 0x02
UNDERLINE_DOUBLE_ACC = 0x22
FAMILY_NONE = 0x00
FAMILY_ROMAN = 0x01
FAMILY_SWISS = 0x02
FAMILY_MODERN = 0x03
FAMILY_SCRIPT = 0x04
FAMILY_DECORATIVE = 0x05
CHARSET_ANSI_LATIN = 0x00
CHARSET_SYS_DEFAULT = 0x01
CHARSET_SYMBOL = 0x02
CHARSET_APPLE_ROMAN = 0x4D
CHARSET_ANSI_JAP_SHIFT_JIS = 0x80
CHARSET_ANSI_KOR_HANGUL = 0x81
CHARSET_ANSI_KOR_JOHAB = 0x82
CHARSET_ANSI_CHINESE_GBK = 0x86
CHARSET_ANSI_CHINESE_BIG5 = 0x88
CHARSET_ANSI_GREEK = 0xA1
CHARSET_ANSI_TURKISH = 0xA2
CHARSET_ANSI_VIETNAMESE = 0xA3
CHARSET_ANSI_HEBREW = 0xB1
CHARSET_ANSI_ARABIC = 0xB2
CHARSET_ANSI_BALTIC = 0xBA
CHARSET_ANSI_CYRILLIC = 0xCC
CHARSET_ANSI_THAI = 0xDE
CHARSET_ANSI_LATIN_II = 0xEE
CHARSET_OEM_LATIN_I = 0xFF
def __init__(self):
# twip = 1/20 of a point = 1/1440 of a inch
# usually resolution == 96 pixels per 1 inch
# (rarely 120 pixels per 1 inch or another one)
self.height = 0x00C8 # 200: this is font with height 10 points
self.italic = False
self.struck_out = False
self.outline = False
self.shadow = False
self.colour_index = 0x7FFF
self.bold = False
self._weight = 0x0190 # 0x02BC gives bold font
self.escapement = self.ESCAPEMENT_NONE
self.underline = self.UNDERLINE_NONE
self.family = self.FAMILY_NONE
self.charset = self.CHARSET_SYS_DEFAULT
self.name = b'Arial'
def get_biff_record(self):
height = self.height
options = 0x00
if self.bold:
options |= 0x01
self._weight = 0x02BC
if self.italic:
options |= 0x02
if self.underline != self.UNDERLINE_NONE:
options |= 0x04
if self.struck_out:
options |= 0x08
if self.outline:
options |= 0x010
if self.shadow:
options |= 0x020
colour_index = self.colour_index
weight = self._weight
escapement = self.escapement
underline = self.underline
family = self.family
charset = self.charset
name = self.name
return BIFFRecords.FontRecord(height, options, colour_index, weight, escapement,
underline, family, charset,
name)
def _search_key(self):
return (
self.height,
self.italic,
self.struck_out,
self.outline,
self.shadow,
self.colour_index,
self.bold,
self._weight,
self.escapement,
self.underline,
self.family,
self.charset,
self.name,
)
class Alignment(object):
HORZ_GENERAL = 0x00
HORZ_LEFT = 0x01
HORZ_CENTER = 0x02
HORZ_RIGHT = 0x03
HORZ_FILLED = 0x04
HORZ_JUSTIFIED = 0x05 # BIFF4-BIFF8X
HORZ_CENTER_ACROSS_SEL = 0x06 # Centred across selection (BIFF4-BIFF8X)
HORZ_DISTRIBUTED = 0x07 # Distributed (BIFF8X)
VERT_TOP = 0x00
VERT_CENTER = 0x01
VERT_BOTTOM = 0x02
VERT_JUSTIFIED = 0x03 # Justified (BIFF5-BIFF8X)
VERT_DISTRIBUTED = 0x04 # Distributed (BIFF8X)
DIRECTION_GENERAL = 0x00 # BIFF8X
DIRECTION_LR = 0x01
DIRECTION_RL = 0x02
ORIENTATION_NOT_ROTATED = 0x00
ORIENTATION_STACKED = 0x01
ORIENTATION_90_CC = 0x02
ORIENTATION_90_CW = 0x03
ROTATION_0_ANGLE = 0x00
ROTATION_STACKED = 0xFF
WRAP_AT_RIGHT = 0x01
NOT_WRAP_AT_RIGHT = 0x00
SHRINK_TO_FIT = 0x01
NOT_SHRINK_TO_FIT = 0x00
def __init__(self):
self.horz = self.HORZ_GENERAL
self.vert = self.VERT_BOTTOM
self.dire = self.DIRECTION_GENERAL
self.orie = self.ORIENTATION_NOT_ROTATED
self.rota = self.ROTATION_0_ANGLE
self.wrap = self.NOT_WRAP_AT_RIGHT
self.shri = self.NOT_SHRINK_TO_FIT
self.inde = 0
self.merg = 0
def _search_key(self):
return (
self.horz, self.vert, self.dire, self.orie, self.rota,
self.wrap, self.shri, self.inde, self.merg,
)
class Borders(object):
NO_LINE = 0x00
THIN = 0x01
MEDIUM = 0x02
DASHED = 0x03
DOTTED = 0x04
THICK = 0x05
DOUBLE = 0x06
HAIR = 0x07
#The following for BIFF8
MEDIUM_DASHED = 0x08
THIN_DASH_DOTTED = 0x09
MEDIUM_DASH_DOTTED = 0x0A
THIN_DASH_DOT_DOTTED = 0x0B
MEDIUM_DASH_DOT_DOTTED = 0x0C
SLANTED_MEDIUM_DASH_DOTTED = 0x0D
NEED_DIAG1 = 0x01
NEED_DIAG2 = 0x01
NO_NEED_DIAG1 = 0x00
NO_NEED_DIAG2 = 0x00
def __init__(self):
self.left = self.NO_LINE
self.right = self.NO_LINE
self.top = self.NO_LINE
self.bottom = self.NO_LINE
self.diag = self.NO_LINE
self.left_colour = 0x40
self.right_colour = 0x40
self.top_colour = 0x40
self.bottom_colour = 0x40
self.diag_colour = 0x40
self.need_diag1 = self.NO_NEED_DIAG1
self.need_diag2 = self.NO_NEED_DIAG2
def _search_key(self):
return (
self.left, self.right, self.top, self.bottom, self.diag,
self.left_colour, self.right_colour, self.top_colour,
self.bottom_colour, self.diag_colour,
self.need_diag1, self.need_diag2,
)
class Pattern(object):
# patterns 0x00 - 0x12
NO_PATTERN = 0x00
SOLID_PATTERN = 0x01
def __init__(self):
self.pattern = self.NO_PATTERN
self.pattern_fore_colour = 0x40
self.pattern_back_colour = 0x41
def _search_key(self):
return (
self.pattern,
self.pattern_fore_colour,
self.pattern_back_colour,
)
class Protection(object):
def __init__(self):
self.cell_locked = 1
self.formula_hidden = 0
def _search_key(self):
return (
self.cell_locked,
self.formula_hidden,
)
-253
View File
@@ -1,253 +0,0 @@
# -*- coding: windows-1252 -*-
from . import BIFFRecords
from . import Style
from .Cell import StrCell, BlankCell, NumberCell, FormulaCell, MulBlankCell, BooleanCell, ErrorCell, \
_get_cells_biff_data_mul
from . import ExcelFormula
import datetime as dt
try:
from decimal import Decimal
except ImportError:
# Python 2.3: decimal not supported; create dummy Decimal class
class Decimal(object):
pass
class Row(object):
__slots__ = [# private variables
"__idx",
"__parent",
"__parent_wb",
"__cells",
"__min_col_idx",
"__max_col_idx",
"__xf_index",
"__has_default_xf_index",
"__height_in_pixels",
# public variables
"height",
"has_default_height",
"height_mismatch",
"level",
"collapse",
"hidden",
"space_above",
"space_below"]
def __init__(self, rowx, parent_sheet):
if not (isinstance(rowx, int) and 0 <= rowx <= 65535):
raise ValueError("row index (%r) not an int in range(65536)" % rowx)
self.__idx = rowx
self.__parent = parent_sheet
self.__parent_wb = parent_sheet.get_parent()
self.__cells = {}
self.__min_col_idx = 0
self.__max_col_idx = 0
self.__xf_index = 0x0F
self.__has_default_xf_index = 0
self.__height_in_pixels = 0x11
self.height = 0x00FF
self.has_default_height = 0x00
self.height_mismatch = 0
self.level = 0
self.collapse = 0
self.hidden = 0
self.space_above = 0
self.space_below = 0
def __adjust_height(self, style):
twips = style.font.height
points = float(twips)/20.0
# Cell height in pixels can be calcuted by following approx. formula:
# cell height in pixels = font height in points * 83/50 + 2/5
# It works when screen resolution is 96 dpi
pix = int(round(points*83.0/50.0 + 2.0/5.0))
if pix > self.__height_in_pixels:
self.__height_in_pixels = pix
def __adjust_bound_col_idx(self, *args):
for arg in args:
iarg = int(arg)
if not ((0 <= iarg <= 255) and arg == iarg):
raise ValueError("column index (%r) not an int in range(256)" % arg)
sheet = self.__parent
if iarg < self.__min_col_idx:
self.__min_col_idx = iarg
if iarg > self.__max_col_idx:
self.__max_col_idx = iarg
if iarg < sheet.first_used_col:
sheet.first_used_col = iarg
if iarg > sheet.last_used_col:
sheet.last_used_col = iarg
def __excel_date_dt(self, date):
if isinstance(date, dt.date) and (not isinstance(date, dt.datetime)):
epoch = dt.date(1899, 12, 31)
elif isinstance(date, dt.time):
date = dt.datetime.combine(dt.datetime(1900, 1, 1), date)
epoch = dt.datetime(1900, 1, 1, 0, 0, 0)
else:
epoch = dt.datetime(1899, 12, 31, 0, 0, 0)
delta = date - epoch
xldate = delta.days + float(delta.seconds) / (24*60*60)
# Add a day for Excel's missing leap day in 1900
if xldate > 59:
xldate += 1
return xldate
def get_height_in_pixels(self):
return self.__height_in_pixels
def set_style(self, style):
self.__adjust_height(style)
self.__xf_index = self.__parent_wb.add_style(style)
self.__has_default_xf_index = 1
def get_xf_index(self):
return self.__xf_index
def get_cells_count(self):
return len(self.__cells)
def get_min_col(self):
return self.__min_col_idx
def get_max_col(self):
return self.__max_col_idx
def get_row_biff_data(self):
height_options = (self.height & 0x07FFF)
height_options |= (self.has_default_height & 0x01) << 15
options = (self.level & 0x07) << 0
options |= (self.collapse & 0x01) << 4
options |= (self.hidden & 0x01) << 5
options |= (self.height_mismatch & 0x01) << 6
options |= (self.__has_default_xf_index & 0x01) << 7
options |= (0x01 & 0x01) << 8
options |= (self.__xf_index & 0x0FFF) << 16
options |= (self.space_above & 1) << 28
options |= (self.space_below & 1) << 29
return BIFFRecords.RowRecord(self.__idx, self.__min_col_idx,
self.__max_col_idx, height_options, options).get()
def insert_cell(self, col_index, cell_obj):
if col_index in self.__cells:
if not self.__parent._cell_overwrite_ok:
msg = "Attempt to overwrite cell: sheetname=%r rowx=%d colx=%d" \
% (self.__parent.name, self.__idx, col_index)
raise Exception(msg)
prev_cell_obj = self.__cells[col_index]
sst_idx = getattr(prev_cell_obj, 'sst_idx', None)
if sst_idx is not None:
self.__parent_wb.del_str(sst_idx)
self.__cells[col_index] = cell_obj
def insert_mulcells(self, colx1, colx2, cell_obj):
self.insert_cell(colx1, cell_obj)
for col_index in range(colx1+1, colx2+1):
self.insert_cell(col_index, None)
def get_cells_biff_data(self):
cell_items = [item for item in self.__cells.items() if item[1] is not None]
cell_items.sort() # in column order
return _get_cells_biff_data_mul(self.__idx, cell_items)
# previously:
# return ''.join([cell.get_biff_data() for colx, cell in cell_items])
def get_index(self):
return self.__idx
def set_cell_text(self, colx, value, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, StrCell(self.__idx, colx, xf_index, self.__parent_wb.add_str(value)))
def set_cell_blank(self, colx, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, BlankCell(self.__idx, colx, xf_index))
def set_cell_mulblanks(self, first_colx, last_colx, style=Style.default_style):
assert 0 <= first_colx <= last_colx <= 255
self.__adjust_height(style)
self.__adjust_bound_col_idx(first_colx, last_colx)
xf_index = self.__parent_wb.add_style(style)
# ncols = last_colx - first_colx + 1
self.insert_mulcells(first_colx, last_colx, MulBlankCell(self.__idx, first_colx, last_colx, xf_index))
def set_cell_number(self, colx, number, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, NumberCell(self.__idx, colx, xf_index, number))
def set_cell_date(self, colx, datetime_obj, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx,
NumberCell(self.__idx, colx, xf_index, self.__excel_date_dt(datetime_obj)))
def set_cell_formula(self, colx, formula, style=Style.default_style, calc_flags=0):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.__parent_wb.add_sheet_reference(formula)
self.insert_cell(colx, FormulaCell(self.__idx, colx, xf_index, formula, calc_flags=0))
def set_cell_boolean(self, colx, value, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, BooleanCell(self.__idx, colx, xf_index, bool(value)))
def set_cell_error(self, colx, error_string_or_code, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(colx)
xf_index = self.__parent_wb.add_style(style)
self.insert_cell(colx, ErrorCell(self.__idx, colx, xf_index, error_string_or_code))
def write(self, col, label, style=Style.default_style):
self.__adjust_height(style)
self.__adjust_bound_col_idx(col)
style_index = self.__parent_wb.add_style(style)
if isinstance(label, str):
if len(label) > 0:
self.insert_cell(col,
StrCell(self.__idx, col, style_index, self.__parent_wb.add_str(label))
)
else:
self.insert_cell(col, BlankCell(self.__idx, col, style_index))
elif isinstance(label, bool): # bool is subclass of int; test bool first
self.insert_cell(col, BooleanCell(self.__idx, col, style_index, label))
elif isinstance(label, (float, int, Decimal)):
self.insert_cell(col, NumberCell(self.__idx, col, style_index, label))
elif isinstance(label, (dt.datetime, dt.date, dt.time)):
date_number = self.__excel_date_dt(label)
self.insert_cell(col, NumberCell(self.__idx, col, style_index, date_number))
elif label is None:
self.insert_cell(col, BlankCell(self.__idx, col, style_index))
elif isinstance(label, ExcelFormula.Formula):
self.__parent_wb.add_sheet_reference(label)
self.insert_cell(col, FormulaCell(self.__idx, col, style_index, label))
else:
raise Exception("Unexpected data type %r" % type(label))
write_blanks = set_cell_mulblanks
-593
View File
@@ -1,593 +0,0 @@
# -*- coding: windows-1252 -*-
from . import Formatting
from .BIFFRecords import *
import collections
FIRST_USER_DEFINED_NUM_FORMAT_IDX = 164
class XFStyle(object):
def __init__(self):
self.num_format_str = 'General'
self.font = Formatting.Font()
self.alignment = Formatting.Alignment()
self.borders = Formatting.Borders()
self.pattern = Formatting.Pattern()
self.protection = Formatting.Protection()
default_style = XFStyle()
class StyleCollection(object):
_std_num_fmt_list = [
'general',
'0',
'0.00',
'#,##0',
'#,##0.00',
'"$"#,##0_);("$"#,##',
'"$"#,##0_);[Red]("$"#,##',
'"$"#,##0.00_);("$"#,##',
'"$"#,##0.00_);[Red]("$"#,##',
'0%',
'0.00%',
'0.00E+00',
'# ?/?',
'# ??/??',
'M/D/YY',
'D-MMM-YY',
'D-MMM',
'MMM-YY',
'h:mm AM/PM',
'h:mm:ss AM/PM',
'h:mm',
'h:mm:ss',
'M/D/YY h:mm',
'_(#,##0_);(#,##0)',
'_(#,##0_);[Red](#,##0)',
'_(#,##0.00_);(#,##0.00)',
'_(#,##0.00_);[Red](#,##0.00)',
'_("$"* #,##0_);_("$"* (#,##0);_("$"* "-"_);_(@_)',
'_(* #,##0_);_(* (#,##0);_(* "-"_);_(@_)',
'_("$"* #,##0.00_);_("$"* (#,##0.00);_("$"* "-"??_);_(@_)',
'_(* #,##0.00_);_(* (#,##0.00);_(* "-"??_);_(@_)',
'mm:ss',
'[h]:mm:ss',
'mm:ss.0',
'##0.0E+0',
'@'
]
def __init__(self, style_compression=0):
self.style_compression = style_compression
self.stats = [0, 0, 0, 0, 0, 0]
self._font_id2x = {}
self._font_x2id = {}
self._font_val2x = {}
for x in (0, 1, 2, 3, 5): # The font with index 4 is omitted in all BIFF versions
font = Formatting.Font()
search_key = font._search_key()
self._font_id2x[font] = x
self._font_x2id[x] = font
self._font_val2x[search_key] = x
self._xf_id2x = {}
self._xf_x2id = {}
self._xf_val2x = {}
self._num_formats = {}
for fmtidx, fmtstr in zip(list(range(0, 23)), StyleCollection._std_num_fmt_list[0:23]):
self._num_formats[fmtstr] = fmtidx
for fmtidx, fmtstr in zip(list(range(37, 50)), StyleCollection._std_num_fmt_list[23:]):
self._num_formats[fmtstr] = fmtidx
self.default_style = XFStyle()
self._default_xf = self._add_style(self.default_style)[0]
def add(self, style):
if style == None:
return 0x10
return self._add_style(style)[1]
def _add_style(self, style):
num_format_str = style.num_format_str
if num_format_str in self._num_formats:
num_format_idx = self._num_formats[num_format_str]
else:
num_format_idx = (
FIRST_USER_DEFINED_NUM_FORMAT_IDX
+ len(self._num_formats)
- len(StyleCollection._std_num_fmt_list)
)
self._num_formats[num_format_str] = num_format_idx
font = style.font
if font in self._font_id2x:
font_idx = self._font_id2x[font]
self.stats[0] += 1
elif self.style_compression:
search_key = font._search_key()
font_idx = self._font_val2x.get(search_key)
if font_idx is not None:
self._font_id2x[font] = font_idx
self.stats[1] += 1
else:
font_idx = len(self._font_x2id) + 1 # Why plus 1? Font 4 is missing
self._font_id2x[font] = font_idx
self._font_val2x[search_key] = font_idx
self._font_x2id[font_idx] = font
self.stats[2] += 1
else:
font_idx = len(self._font_id2x) + 1
self._font_id2x[font] = font_idx
self.stats[2] += 1
gof = (style.alignment, style.borders, style.pattern, style.protection)
xf = (font_idx, num_format_idx) + gof
if xf in self._xf_id2x:
xf_index = self._xf_id2x[xf]
self.stats[3] += 1
elif self.style_compression == 2:
xf_key = (font_idx, num_format_idx) + tuple([obj._search_key() for obj in gof])
xf_index = self._xf_val2x.get(xf_key)
if xf_index is not None:
self._xf_id2x[xf] = xf_index
self.stats[4] += 1
else:
xf_index = 0x10 + len(self._xf_x2id)
self._xf_id2x[xf] = xf_index
self._xf_val2x[xf_key] = xf_index
self._xf_x2id[xf_index] = xf
self.stats[5] += 1
else:
xf_index = 0x10 + len(self._xf_id2x)
self._xf_id2x[xf] = xf_index
self.stats[5] += 1
if xf_index >= 0xFFF:
# 12 bits allowed, 0xFFF is a sentinel value
raise ValueError("More than 4094 XFs (styles)")
return xf, xf_index
def get_biff_data(self):
result = b''
result += self._all_fonts()
result += self._all_num_formats()
result += self._all_cell_styles()
result += self._all_styles()
return result
def _all_fonts(self):
result = b''
if self.style_compression:
alist = list(self._font_x2id.items())
else:
alist = [(x, o) for o, x in list(self._font_id2x.items())]
alist.sort()
for font_idx, font in alist:
result += font.get_biff_record().get()
return result
def _all_num_formats(self):
result = b''
alist = [
(v, k)
for k, v in list(self._num_formats.items())
if v >= FIRST_USER_DEFINED_NUM_FORMAT_IDX
]
alist.sort()
for fmtidx, fmtstr in alist:
result += NumberFormatRecord(fmtidx, fmtstr).get()
return result
def _all_cell_styles(self):
result = b''
for i in range(0, 16):
result += XFRecord(self._default_xf, 'style').get()
if self.style_compression == 2:
alist = list(self._xf_x2id.items())
else:
alist = [(x, o) for o, x in list(self._xf_id2x.items())]
alist.sort()
for xf_idx, xf in alist:
result += XFRecord(xf).get()
return result
def _all_styles(self):
return StyleRecord().get()
# easyxf and its supporting objects ###################################
class EasyXFException(Exception):
pass
class EasyXFCallerError(EasyXFException):
pass
class EasyXFAuthorError(EasyXFException):
pass
class IntULim(object):
# If astring represents a valid unsigned integer ('123', '0xabcd', etc)
# and it is <= limit, return the int value; otherwise return None.
def __init__(self, limit):
self.limit = limit
def __call__(self, astring):
try:
value = int(astring, 0)
except ValueError:
return None
if not 0 <= value <= self.limit:
return None
return value
bool_map = {
# Text values for all Boolean attributes
'1': 1, 'yes': 1, 'true': 1, 'on': 1,
'0': 0, 'no': 0, 'false': 0, 'off': 0,
}
border_line_map = {
# Text values for these borders attributes:
# left, right, top, bottom and diag
'no_line': 0x00,
'thin': 0x01,
'medium': 0x02,
'dashed': 0x03,
'dotted': 0x04,
'thick': 0x05,
'double': 0x06,
'hair': 0x07,
'medium_dashed': 0x08,
'thin_dash_dotted': 0x09,
'medium_dash_dotted': 0x0a,
'thin_dash_dot_dotted': 0x0b,
'medium_dash_dot_dotted': 0x0c,
'slanted_medium_dash_dotted': 0x0d,
}
charset_map = {
# Text values for font.charset
'ansi_latin': 0x00,
'sys_default': 0x01,
'symbol': 0x02,
'apple_roman': 0x4d,
'ansi_jap_shift_jis': 0x80,
'ansi_kor_hangul': 0x81,
'ansi_kor_johab': 0x82,
'ansi_chinese_gbk': 0x86,
'ansi_chinese_big5': 0x88,
'ansi_greek': 0xa1,
'ansi_turkish': 0xa2,
'ansi_vietnamese': 0xa3,
'ansi_hebrew': 0xb1,
'ansi_arabic': 0xb2,
'ansi_baltic': 0xba,
'ansi_cyrillic': 0xcc,
'ansi_thai': 0xde,
'ansi_latin_ii': 0xee,
'oem_latin_i': 0xff,
}
# Text values for colour indices. "grey" is a synonym of "gray".
# The names are those given by Microsoft Excel 2003 to the colours
# in the default palette. There is no great correspondence with
# any W3C name-to-RGB mapping.
_colour_map_text = """\
aqua 0x31
black 0x08
blue 0x0C
blue_gray 0x36
bright_green 0x0B
brown 0x3C
coral 0x1D
cyan_ega 0x0F
dark_blue 0x12
dark_blue_ega 0x12
dark_green 0x3A
dark_green_ega 0x11
dark_purple 0x1C
dark_red 0x10
dark_red_ega 0x10
dark_teal 0x38
dark_yellow 0x13
gold 0x33
gray_ega 0x17
gray25 0x16
gray40 0x37
gray50 0x17
gray80 0x3F
green 0x11
ice_blue 0x1F
indigo 0x3E
ivory 0x1A
lavender 0x2E
light_blue 0x30
light_green 0x2A
light_orange 0x34
light_turquoise 0x29
light_yellow 0x2B
lime 0x32
magenta_ega 0x0E
ocean_blue 0x1E
olive_ega 0x13
olive_green 0x3B
orange 0x35
pale_blue 0x2C
periwinkle 0x18
pink 0x0E
plum 0x3D
purple_ega 0x14
red 0x0A
rose 0x2D
sea_green 0x39
silver_ega 0x16
sky_blue 0x28
tan 0x2F
teal 0x15
teal_ega 0x15
turquoise 0x0F
violet 0x14
white 0x09
yellow 0x0D"""
colour_map = {}
for _line in _colour_map_text.splitlines():
_name, _num = _line.split()
_num = int(_num, 0)
colour_map[_name] = _num
if 'gray' in _name:
colour_map[_name.replace('gray', 'grey')] = _num
del _colour_map_text, _line, _name, _num
pattern_map = {
# Text values for pattern.pattern
# xlwt/doc/pattern_examples.xls showcases all of these patterns.
'no_fill': 0,
'none': 0,
'solid': 1,
'solid_fill': 1,
'solid_pattern': 1,
'fine_dots': 2,
'alt_bars': 3,
'sparse_dots': 4,
'thick_horz_bands': 5,
'thick_vert_bands': 6,
'thick_backward_diag': 7,
'thick_forward_diag': 8,
'big_spots': 9,
'bricks': 10,
'thin_horz_bands': 11,
'thin_vert_bands': 12,
'thin_backward_diag': 13,
'thin_forward_diag': 14,
'squares': 15,
'diamonds': 16,
}
def any_str_func(s):
return s.strip()
def colour_index_func(s, maxval=0x7F):
try:
value = int(s, 0)
except ValueError:
return None
if not (0 <= value <= maxval):
return None
return value
colour_index_func_7 = colour_index_func
def colour_index_func_15(s):
return colour_index_func(s, maxval=0x7FFF)
def rotation_func(s):
try:
value = int(s, 0)
except ValueError:
return None
if not (-90 <= value <= 90):
raise EasyXFCallerError("rotation %d: should be -90 to +90 degrees" % value)
if value < 0:
value = 90 - value # encode as 91 to 180 (clockwise)
return value
xf_dict = {
'align': 'alignment', # synonym
'alignment': {
'dire': {
'general': 0,
'lr': 1,
'rl': 2,
},
'direction': 'dire',
'horiz': 'horz',
'horizontal': 'horz',
'horz': {
'general': 0,
'left': 1,
'center': 2,
'centre': 2, # "align: horiz centre" means xf.alignment.horz is set to 2
'right': 3,
'filled': 4,
'justified': 5,
'center_across_selection': 6,
'centre_across_selection': 6,
'distributed': 7,
},
'inde': IntULim(15), # restriction: 0 <= value <= 15
'indent': 'inde',
'rota': [{'stacked': 255, 'none': 0, }, rotation_func],
'rotation': 'rota',
'shri': bool_map,
'shrink': 'shri',
'shrink_to_fit': 'shri',
'vert': {
'top': 0,
'center': 1,
'centre': 1,
'bottom': 2,
'justified': 3,
'distributed': 4,
},
'vertical': 'vert',
'wrap': bool_map,
},
'border': 'borders',
'borders': {
'left': [border_line_map, IntULim(0x0d)],
'right': [border_line_map, IntULim(0x0d)],
'top': [border_line_map, IntULim(0x0d)],
'bottom': [border_line_map, IntULim(0x0d)],
'diag': [border_line_map, IntULim(0x0d)],
'top_colour': [colour_map, colour_index_func_7],
'bottom_colour': [colour_map, colour_index_func_7],
'left_colour': [colour_map, colour_index_func_7],
'right_colour': [colour_map, colour_index_func_7],
'diag_colour': [colour_map, colour_index_func_7],
'top_color': 'top_colour',
'bottom_color': 'bottom_colour',
'left_color': 'left_colour',
'right_color': 'right_colour',
'diag_color': 'diag-colour',
'need_diag_1': bool_map,
'need_diag_2': bool_map,
},
'font': {
'bold': bool_map,
'charset': charset_map,
'color': 'colour_index',
'color_index': 'colour_index',
'colour': 'colour_index',
'colour_index': [colour_map, colour_index_func_15],
'escapement': {'none': 0, 'superscript': 1, 'subscript': 2},
'family': {'none': 0, 'roman': 1, 'swiss': 2, 'modern': 3, 'script': 4, 'decorative': 5, },
'height': IntULim(0xFFFF), # practical limits are much narrower e.g. 160 to 1440 (8pt to 72pt)
'italic': bool_map,
'name': any_str_func,
'outline': bool_map,
'shadow': bool_map,
'struck_out': bool_map,
'underline': [bool_map, {'none': 0, 'single': 1, 'single_acc': 0x21, 'double': 2, 'double_acc': 0x22, }],
},
'pattern': {
'back_color': 'pattern_back_colour',
'back_colour': 'pattern_back_colour',
'fore_color': 'pattern_fore_colour',
'fore_colour': 'pattern_fore_colour',
'pattern': [pattern_map, IntULim(16)],
'pattern_back_color': 'pattern_back_colour',
'pattern_back_colour': [colour_map, colour_index_func_7],
'pattern_fore_color': 'pattern_fore_colour',
'pattern_fore_colour': [colour_map, colour_index_func_7],
},
'protection': {
'cell_locked' : bool_map,
'formula_hidden': bool_map,
},
}
def _esplit(s, split_char, esc_char="\\"):
escaped = False
olist = ['']
for c in s:
if escaped:
olist[-1] += c
escaped = False
elif c == esc_char:
escaped = True
elif c == split_char:
olist.append('')
else:
olist[-1] += c
return olist
def _parse_strg_to_obj(strg, obj, parse_dict,
field_sep=",", line_sep=";", intro_sep=":", esc_char="\\", debug=False):
for line in _esplit(strg, line_sep, esc_char):
line = line.strip()
if not line:
break
split_line = _esplit(line, intro_sep, esc_char)
if len(split_line) != 2:
raise EasyXFCallerError('line %r should have exactly 1 "%c"' % (line, intro_sep))
section, item_str = split_line
section = section.strip().lower()
for counter in range(2):
result = parse_dict.get(section)
if result is None:
raise EasyXFCallerError('section %r is unknown' % section)
if isinstance(result, dict):
break
if not isinstance(result, str):
raise EasyXFAuthorError(
'section %r should map to dict or str object; found %r' % (section, type(result)))
# synonym
old_section = section
section = result
else:
raise EasyXFAuthorError('Attempt to define synonym of synonym (%r: %r)' % (old_section, result))
section_dict = result
section_obj = getattr(obj, section, None)
if section_obj is None:
raise EasyXFAuthorError('instance of %s class has no attribute named %s' % (obj.__class__.__name__, section))
for kv_str in _esplit(item_str, field_sep, esc_char):
guff = kv_str.split()
if not guff:
continue
k = guff[0].lower().replace('-', '_')
v = ' '.join(guff[1:])
if not v:
raise EasyXFCallerError("no value supplied for %s.%s" % (section, k))
for counter in range(2):
result = section_dict.get(k)
if result is None:
raise EasyXFCallerError('%s.%s is not a known attribute' % (section, k))
if not isinstance(result, str):
break
# synonym
old_k = k
k = result
else:
raise EasyXFAuthorError('Attempt to define synonym of synonym (%r: %r)' % (old_k, result))
value_info = result
if not isinstance(value_info, list):
value_info = [value_info]
for value_rule in value_info:
if isinstance(value_rule, dict):
# dict maps strings to integer field values
vl = v.lower().replace('-', '_')
if vl in value_rule:
value = value_rule[vl]
break
elif isinstance(value_rule, collections.Callable):
value = value_rule(v)
if value is not None:
break
else:
raise EasyXFAuthorError("unknown value rule for attribute %r: %r" % (k, value_rule))
else:
raise EasyXFCallerError("unexpected value %r for %s.%s" % (v, section, k))
try:
orig = getattr(section_obj, k)
except AttributeError:
raise EasyXFAuthorError('%s.%s in dictionary but not in supplied object' % (section, k))
if debug: print("+++ %s.%s = %r # %s; was %r" % (section, k, value, v, orig))
setattr(section_obj, k, value)
def easyxf(strg_to_parse="", num_format_str=None,
field_sep=",", line_sep=";", intro_sep=":", esc_char="\\", debug=False):
xfobj = XFStyle()
if num_format_str is not None:
xfobj.num_format_str = num_format_str
if strg_to_parse:
_parse_strg_to_obj(strg_to_parse, xfobj, xf_dict,
field_sep=field_sep, line_sep=line_sep, intro_sep=intro_sep, esc_char=esc_char, debug=debug)
return xfobj
-79
View File
@@ -1,79 +0,0 @@
'''
From BIFF8 on, strings are always stored using UTF-16LE text encoding. The
character array is a sequence of 16-bit values4. Additionally it is
possible to use a compressed format, which omits the high bytes of all
characters, if they are all zero.
The following tables describe the standard format of the entire string, but
in many records the strings differ from this format. This will be mentioned
separately. It is possible (but not required) to store Rich-Text formatting
information and Asian phonetic information inside a Unicode string. This
results in four different ways to store a string. The character array
is not zero-terminated.
The string consists of the character count (as usual an 8-bit value or
a 16-bit value), option flags, the character array and optional formatting
information. If the string is empty, sometimes the option flags field will
not occur. This is mentioned at the respective place.
Offset Size Contents
0 1 or 2 Length of the string (character count, ln)
1 or 2 1 Option flags:
Bit Mask Contents
0 01H Character compression (ccompr):
0 = Compressed (8-bit characters)
1 = Uncompressed (16-bit characters)
2 04H Asian phonetic settings (phonetic):
0 = Does not contain Asian phonetic settings
1 = Contains Asian phonetic settings
3 08H Rich-Text settings (richtext):
0 = Does not contain Rich-Text settings
1 = Contains Rich-Text settings
[2 or 3] 2 (optional, only if richtext=1) Number of Rich-Text formatting runs (rt)
[var.] 4 (optional, only if phonetic=1) Size of Asian phonetic settings block (in bytes, sz)
var. ln or
2·ln Character array (8-bit characters or 16-bit characters, dependent on ccompr)
[var.] 4·rt (optional, only if richtext=1) List of rt formatting runs
[var.] sz (optional, only if phonetic=1) Asian Phonetic Settings Block
'''
from struct import pack
def upack2(s, encoding='ascii'):
# If not unicode, make it so.
if isinstance(s, str):
us = s
else:
us = str(s, encoding)
# Limit is based on number of content characters
# (not on number of bytes in packed result)
len_us = len(us)
if len_us > 65535:
raise Exception('String longer than 65535 characters')
try:
encs = us.encode('latin1')
# Success here means all chars are in U+0000 to U+00FF
# inclusive, meaning that we can use "compressed format".
flag = 0
except UnicodeEncodeError:
encs = us.encode('utf_16_le')
flag = 1
return pack('<HB', len_us, flag) + encs
def upack1(s, encoding='ascii'):
# Same as upack2(), but with a one-byte length field.
if isinstance(s, str):
us = s
else:
us = str(s, encoding)
len_us = len(us)
if len_us > 255:
raise Exception('String longer than 255 characters')
try:
encs = us.encode('latin1')
flag = 0
except UnicodeEncodeError:
encs = us.encode('utf_16_le')
flag = 1
return pack('<BB', len_us, flag) + encs
-196
View File
@@ -1,196 +0,0 @@
# pyXLWriter: A library for generating Excel Spreadsheets
# Copyright (c) 2004 Evgeny Filatov <fufff@users.sourceforge.net>
# Copyright (c) 2002-2004 John McNamara (Perl Spreadsheet::WriteExcel)
#
# This library is free software; you can redistribute it and/or modify it
# under the terms of the GNU Lesser General Public License as published by
# the Free Software Foundation; either version 2.1 of the License, or
# (at your option) any later version.
#
# This library is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser
# General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License
# along with this library; if not, write to the Free Software Foundation,
# Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#----------------------------------------------------------------------------
# This module was written/ported from PERL Spreadsheet::WriteExcel module
# The author of the PERL Spreadsheet::WriteExcel module is John McNamara
# <jmcnamara@cpan.org>
#----------------------------------------------------------------------------
# See the README.txt distributed with pyXLWriter for more details.
# Portions are (C) Roman V. Kiseliov, 2005
# Utilities for work with reference to cells and with sheetnames
__rev_id__ = """$Id: Utils.py 3844 2009-05-20 01:02:54Z sjmachin $"""
import re
from struct import pack
from .ExcelMagic import MAX_ROW, MAX_COL
_re_cell_ex = re.compile(r"(\$?)([A-I]?[A-Z])(\$?)(\d+)", re.IGNORECASE)
_re_row_range = re.compile(r"\$?(\d+):\$?(\d+)")
_re_col_range = re.compile(r"\$?([A-I]?[A-Z]):\$?([A-I]?[A-Z])", re.IGNORECASE)
_re_cell_range = re.compile(r"\$?([A-I]?[A-Z]\$?\d+):\$?([A-I]?[A-Z]\$?\d+)", re.IGNORECASE)
_re_cell_ref = re.compile(r"\$?([A-I]?[A-Z]\$?\d+)", re.IGNORECASE)
def col_by_name(colname):
"""
"""
col = 0
pow = 1
for i in range(len(colname)-1, -1, -1):
ch = colname[i]
col += (ord(ch) - ord('A') + 1) * pow
pow *= 26
return col - 1
def cell_to_rowcol(cell):
"""Convert an Excel cell reference string in A1 notation
to numeric row/col notation.
Returns: row, col, row_abs, col_abs
"""
m = _re_cell_ex.match(cell)
if not m:
raise Exception("Ill-formed single_cell reference: %s" % cell)
col_abs, col, row_abs, row = m.groups()
row_abs = bool(row_abs)
col_abs = bool(col_abs)
row = int(row) - 1
col = col_by_name(col.upper())
return row, col, row_abs, col_abs
def cell_to_rowcol2(cell):
"""Convert an Excel cell reference string in A1 notation
to numeric row/col notation.
Returns: row, col
"""
m = _re_cell_ex.match(cell)
if not m:
raise Exception("Error in cell format")
col_abs, col, row_abs, row = m.groups()
# Convert base26 column string to number
# All your Base are belong to us.
row = int(row) - 1
col = col_by_name(col.upper())
return row, col
def rowcol_to_cell(row, col, row_abs=False, col_abs=False):
"""Convert numeric row/col notation to an Excel cell reference string in
A1 notation.
"""
assert 0 <= row < MAX_ROW # MAX_ROW counts from 1
assert 0 <= col < MAX_COL # MAX_COL counts from 1
d = col // 26
m = col % 26
chr1 = "" # Most significant character in AA1
if row_abs:
row_abs = '$'
else:
row_abs = ''
if col_abs:
col_abs = '$'
else:
col_abs = ''
if d > 0:
chr1 = chr(ord('A') + d - 1)
chr2 = chr(ord('A') + m)
# Zero index to 1-index
return col_abs + chr1 + chr2 + row_abs + str(row + 1)
def rowcol_pair_to_cellrange(row1, col1, row2, col2,
row1_abs=False, col1_abs=False, row2_abs=False, col2_abs=False):
"""Convert two (row,column) pairs
into a cell range string in A1:B2 notation.
Returns: cell range string
"""
assert row1 <= row2
assert col1 <= col2
return (
rowcol_to_cell(row1, col1, row1_abs, col1_abs)
+ ":"
+ rowcol_to_cell(row2, col2, row2_abs, col2_abs)
)
def cellrange_to_rowcol_pair(cellrange):
"""Convert cell range string in A1 notation to numeric row/col
pair.
Returns: row1, col1, row2, col2
"""
cellrange = cellrange.upper()
# Convert a row range: '1:3'
res = _re_row_range.match(cellrange)
if res:
row1 = int(res.group(1)) - 1
col1 = 0
row2 = int(res.group(2)) - 1
col2 = -1
return row1, col1, row2, col2
# Convert a column range: 'A:A' or 'B:G'.
# A range such as A:A is equivalent to A1:A16384, so add rows as required
res = _re_col_range.match(cellrange)
if res:
col1 = col_by_name(res.group(1).upper())
row1 = 0
col2 = col_by_name(res.group(2).upper())
row2 = -1
return row1, col1, row2, col2
# Convert a cell range: 'A1:B7'
res = _re_cell_range.match(cellrange)
if res:
row1, col1 = cell_to_rowcol2(res.group(1))
row2, col2 = cell_to_rowcol2(res.group(2))
return row1, col1, row2, col2
# Convert a cell reference: 'A1' or 'AD2000'
res = _re_cell_ref.match(cellrange)
if res:
row1, col1 = cell_to_rowcol2(res.group(1))
return row1, col1, row1, col1
raise Exception("Unknown cell reference %s" % (cell))
def cell_to_packed_rowcol(cell):
""" pack row and column into the required 4 byte format """
row, col, row_abs, col_abs = cell_to_rowcol(cell)
if col >= MAX_COL:
raise Exception("Column %s greater than IV in formula" % cell)
if row >= MAX_ROW: # this for BIFF8. for BIFF7 available 2^14
raise Exception("Row %s greater than %d in formula" % (cell, MAX_ROW))
col |= int(not row_abs) << 15
col |= int(not col_abs) << 14
return row, col
# === sheetname functions ===
def valid_sheet_name(sheet_name):
if sheet_name == "" or sheet_name[0] == "'" or len(sheet_name) > 31:
return False
for c in sheet_name:
if c in "[]:\\?/*\x00":
return False
return True
def quote_sheet_name(unquoted_sheet_name):
if not valid_sheet_name(unquoted_sheet_name):
raise Exception(
'attempt to quote an invalid worksheet name %r' % unquoted_sheet_name)
return "'" + unquoted_sheet_name.replace("'", "''") + "'"
-635
View File
@@ -1,635 +0,0 @@
'''
Record Order in BIFF8
Workbook Globals Substream
BOF Type = workbook globals
Interface Header
MMS
Interface End
WRITEACCESS
CODEPAGE
DSF
TABID
FNGROUPCOUNT
Workbook Protection Block
WINDOWPROTECT
PROTECT
PASSWORD
PROT4REV
PROT4REVPASS
BACKUP
HIDEOBJ
WINDOW1
DATEMODE
PRECISION
REFRESHALL
BOOKBOOL
FONT +
FORMAT *
XF +
STYLE +
? PALETTE
USESELFS
BOUNDSHEET +
COUNTRY
? Link Table
SST
ExtSST
EOF
'''
from . import BIFFRecords
from . import Style
class Workbook(object):
#################################################################
## Constructor
#################################################################
def __init__(self, encoding='ascii', style_compression=0):
self.encoding = encoding
self.__owner = 'None'
self.__country_code = None # 0x07 is Russia :-)
self.__wnd_protect = 0
self.__obj_protect = 0
self.__protect = 0
self.__backup_on_save = 0
# for WINDOW1 record
self.__hpos_twips = 0x01E0
self.__vpos_twips = 0x005A
self.__width_twips = 0x3FCF
self.__height_twips = 0x2A4E
self.__active_sheet = 0
self.__first_tab_index = 0
self.__selected_tabs = 0x01
self.__tab_width_twips = 0x0258
self.__wnd_hidden = 0
self.__wnd_mini = 0
self.__hscroll_visible = 1
self.__vscroll_visible = 1
self.__tabs_visible = 1
self.__styles = Style.StyleCollection(style_compression)
self.__dates_1904 = 0
self.__use_cell_values = 1
self.__sst = BIFFRecords.SharedStringTable(self.encoding)
self.__worksheets = []
self.__worksheet_idx_from_name = {}
self.__sheet_refs = {}
self._supbook_xref = {}
self._xcall_xref = {}
self._ownbook_supbookx = None
self._ownbook_supbook_ref = None
self._xcall_supbookx = None
self._xcall_supbook_ref = None
#################################################################
## Properties, "getters", "setters"
#################################################################
def get_style_stats(self):
return self.__styles.stats[:]
def set_owner(self, value):
self.__owner = value
def get_owner(self):
return self.__owner
owner = property(get_owner, set_owner)
#################################################################
def set_country_code(self, value):
self.__country_code = value
def get_country_code(self):
return self.__country_code
country_code = property(get_country_code, set_country_code)
#################################################################
def set_wnd_protect(self, value):
self.__wnd_protect = int(value)
def get_wnd_protect(self):
return bool(self.__wnd_protect)
wnd_protect = property(get_wnd_protect, set_wnd_protect)
#################################################################
def set_obj_protect(self, value):
self.__obj_protect = int(value)
def get_obj_protect(self):
return bool(self.__obj_protect)
obj_protect = property(get_obj_protect, set_obj_protect)
#################################################################
def set_protect(self, value):
self.__protect = int(value)
def get_protect(self):
return bool(self.__protect)
protect = property(get_protect, set_protect)
#################################################################
def set_backup_on_save(self, value):
self.__backup_on_save = int(value)
def get_backup_on_save(self):
return bool(self.__backup_on_save)
backup_on_save = property(get_backup_on_save, set_backup_on_save)
#################################################################
def set_hpos(self, value):
self.__hpos_twips = value & 0xFFFF
def get_hpos(self):
return self.__hpos_twips
hpos = property(get_hpos, set_hpos)
#################################################################
def set_vpos(self, value):
self.__vpos_twips = value & 0xFFFF
def get_vpos(self):
return self.__vpos_twips
vpos = property(get_vpos, set_vpos)
#################################################################
def set_width(self, value):
self.__width_twips = value & 0xFFFF
def get_width(self):
return self.__width_twips
width = property(get_width, set_width)
#################################################################
def set_height(self, value):
self.__height_twips = value & 0xFFFF
def get_height(self):
return self.__height_twips
height = property(get_height, set_height)
#################################################################
def set_active_sheet(self, value):
self.__active_sheet = value & 0xFFFF
self.__first_tab_index = self.__active_sheet
def get_active_sheet(self):
return self.__active_sheet
active_sheet = property(get_active_sheet, set_active_sheet)
#################################################################
def set_tab_width(self, value):
self.__tab_width_twips = value & 0xFFFF
def get_tab_width(self):
return self.__tab_width_twips
tab_width = property(get_tab_width, set_tab_width)
#################################################################
def set_wnd_visible(self, value):
self.__wnd_hidden = int(not value)
def get_wnd_visible(self):
return not bool(self.__wnd_hidden)
wnd_visible = property(get_wnd_visible, set_wnd_visible)
#################################################################
def set_wnd_mini(self, value):
self.__wnd_mini = int(value)
def get_wnd_mini(self):
return bool(self.__wnd_mini)
wnd_mini = property(get_wnd_mini, set_wnd_mini)
#################################################################
def set_hscroll_visible(self, value):
self.__hscroll_visible = int(value)
def get_hscroll_visible(self):
return bool(self.__hscroll_visible)
hscroll_visible = property(get_hscroll_visible, set_hscroll_visible)
#################################################################
def set_vscroll_visible(self, value):
self.__vscroll_visible = int(value)
def get_vscroll_visible(self):
return bool(self.__vscroll_visible)
vscroll_visible = property(get_vscroll_visible, set_vscroll_visible)
#################################################################
def set_tabs_visible(self, value):
self.__tabs_visible = int(value)
def get_tabs_visible(self):
return bool(self.__tabs_visible)
tabs_visible = property(get_tabs_visible, set_tabs_visible)
#################################################################
def set_dates_1904(self, value):
self.__dates_1904 = int(value)
def get_dates_1904(self):
return bool(self.__dates_1904)
dates_1904 = property(get_dates_1904, set_dates_1904)
#################################################################
def set_use_cell_values(self, value):
self.__use_cell_values = int(value)
def get_use_cell_values(self):
return bool(self.__use_cell_values)
use_cell_values = property(get_use_cell_values, set_use_cell_values)
#################################################################
def get_default_style(self):
return self.__styles.default_style
default_style = property(get_default_style)
##################################################################
## Methods
##################################################################
def add_style(self, style):
return self.__styles.add(style)
def add_str(self, s):
return self.__sst.add_str(s)
def del_str(self, sst_idx):
self.__sst.del_str(sst_idx)
def str_index(self, s):
return self.__sst.str_index(s)
def add_sheet(self, sheetname, cell_overwrite_ok=False):
from . import Worksheet, Utils
if not isinstance(sheetname, str):
sheetname = sheetname.decode(self.encoding)
if not Utils.valid_sheet_name(sheetname):
raise Exception("invalid worksheet name %r" % sheetname)
lower_name = sheetname.lower()
if lower_name in self.__worksheet_idx_from_name:
raise Exception("duplicate worksheet name %r" % sheetname)
self.__worksheet_idx_from_name[lower_name] = len(self.__worksheets)
self.__worksheets.append(Worksheet(sheetname, self, cell_overwrite_ok))
return self.__worksheets[-1]
def get_sheet(self, sheetnum):
return self.__worksheets[sheetnum]
def raise_bad_sheetname(self, sheetname):
raise Exception("Formula: unknown sheet name %s" % sheetname)
def convert_sheetindex(self, strg_ref, n_sheets):
idx = int(strg_ref)
if 0 <= idx < n_sheets:
return idx
msg = "Formula: sheet index (%s) >= number of sheets (%d)" % (strg_ref, n_sheets)
raise Exception(msg)
def _get_supbook_index(self, tag):
if tag in self._supbook_xref:
return self._supbook_xref[tag]
self._supbook_xref[tag] = idx = len(self._supbook_xref)
return idx
def setup_ownbook(self):
self._ownbook_supbookx = self._get_supbook_index(('ownbook', 0))
self._ownbook_supbook_ref = None
reference = (self._ownbook_supbookx, 0xFFFE, 0xFFFE)
if reference in self.__sheet_refs:
raise Exception("can't happen")
self.__sheet_refs[reference] = self._ownbook_supbook_ref = len(self.__sheet_refs)
def setup_xcall(self):
self._xcall_supbookx = self._get_supbook_index(('xcall', 0))
self._xcall_supbook_ref = None
reference = (self._xcall_supbookx, 0xFFFE, 0xFFFE)
if reference in self.__sheet_refs:
raise Exception("can't happen")
self.__sheet_refs[reference] = self._xcall_supbook_ref = len(self.__sheet_refs)
def add_sheet_reference(self, formula):
patches = []
n_sheets = len(self.__worksheets)
sheet_refs, xcall_refs = formula.get_references()
for ref0, ref1, offset in sheet_refs:
if not ref0.isdigit():
try:
ref0n = self.__worksheet_idx_from_name[ref0.lower()]
except KeyError:
self.raise_bad_sheetname(ref0)
else:
ref0n = self.convert_sheetindex(ref0, n_sheets)
if ref1 == ref0:
ref1n = ref0n
elif not ref1.isdigit():
try:
ref1n = self.__worksheet_idx_from_name[ref1.lower()]
except KeyError:
self.raise_bad_sheetname(ref1)
else:
ref1n = self.convert_sheetindex(ref1, n_sheets)
if ref1n < ref0n:
msg = "Formula: sheets out of order; %r:%r -> (%d, %d)" \
% (ref0, ref1, ref0n, ref1n)
raise Exception(msg)
if self._ownbook_supbookx is None:
self.setup_ownbook()
reference = (self._ownbook_supbookx, ref0n, ref1n)
if reference in self.__sheet_refs:
patches.append((offset, self.__sheet_refs[reference]))
else:
nrefs = len(self.__sheet_refs)
if nrefs > 65535:
raise Exception('More than 65536 inter-sheet references')
self.__sheet_refs[reference] = nrefs
patches.append((offset, nrefs))
for funcname, offset in xcall_refs:
if self._ownbook_supbookx is None:
self.setup_ownbook()
if self._xcall_supbookx is None:
self.setup_xcall()
# print funcname, self._supbook_xref
patches.append((offset, self._xcall_supbook_ref))
if not isinstance(funcname, str):
funcname = funcname.decode(self.encoding)
if funcname in self._xcall_xref:
idx = self._xcall_xref[funcname]
else:
self._xcall_xref[funcname] = idx = len(self._xcall_xref)
patches.append((offset + 2, idx + 1))
formula.patch_references(patches)
##################################################################
## BIFF records generation
##################################################################
def __bof_rec(self):
return BIFFRecords.Biff8BOFRecord(BIFFRecords.Biff8BOFRecord.BOOK_GLOBAL).get()
def __eof_rec(self):
return BIFFRecords.EOFRecord().get()
def __intf_hdr_rec(self):
return BIFFRecords.InteraceHdrRecord().get()
def __intf_end_rec(self):
return BIFFRecords.InteraceEndRecord().get()
def __intf_mms_rec(self):
return BIFFRecords.MMSRecord().get()
def __write_access_rec(self):
return BIFFRecords.WriteAccessRecord(self.__owner).get()
def __wnd_protect_rec(self):
return BIFFRecords.WindowProtectRecord(self.__wnd_protect).get()
def __obj_protect_rec(self):
return BIFFRecords.ObjectProtectRecord(self.__obj_protect).get()
def __protect_rec(self):
return BIFFRecords.ProtectRecord(self.__protect).get()
def __password_rec(self):
return BIFFRecords.PasswordRecord().get()
def __prot4rev_rec(self):
return BIFFRecords.Prot4RevRecord().get()
def __prot4rev_pass_rec(self):
return BIFFRecords.Prot4RevPassRecord().get()
def __backup_rec(self):
return BIFFRecords.BackupRecord(self.__backup_on_save).get()
def __hide_obj_rec(self):
return BIFFRecords.HideObjRecord().get()
def __window1_rec(self):
flags = 0
flags |= (self.__wnd_hidden) << 0
flags |= (self.__wnd_mini) << 1
flags |= (self.__hscroll_visible) << 3
flags |= (self.__vscroll_visible) << 4
flags |= (self.__tabs_visible) << 5
return BIFFRecords.Window1Record(self.__hpos_twips, self.__vpos_twips,
self.__width_twips, self.__height_twips,
flags,
self.__active_sheet, self.__first_tab_index,
self.__selected_tabs, self.__tab_width_twips).get()
def __codepage_rec(self):
return BIFFRecords.CodepageBiff8Record().get()
def __country_rec(self):
if not self.__country_code:
return b''
return BIFFRecords.CountryRecord(self.__country_code, self.__country_code).get()
def __dsf_rec(self):
return BIFFRecords.DSFRecord().get()
def __tabid_rec(self):
return BIFFRecords.TabIDRecord(len(self.__worksheets)).get()
def __fngroupcount_rec(self):
return BIFFRecords.FnGroupCountRecord().get()
def __datemode_rec(self):
return BIFFRecords.DateModeRecord(self.__dates_1904).get()
def __precision_rec(self):
return BIFFRecords.PrecisionRecord(self.__use_cell_values).get()
def __refresh_all_rec(self):
return BIFFRecords.RefreshAllRecord().get()
def __bookbool_rec(self):
return BIFFRecords.BookBoolRecord().get()
def __all_fonts_num_formats_xf_styles_rec(self):
return self.__styles.get_biff_data()
def __palette_rec(self):
result = b''
return result
def __useselfs_rec(self):
return BIFFRecords.UseSelfsRecord().get()
def __boundsheets_rec(self, data_len_before, data_len_after, sheet_biff_lens):
# .................................
# BOUNDSEHEET0
# BOUNDSEHEET1
# BOUNDSEHEET2
# ..................................
# WORKSHEET0
# WORKSHEET1
# WORKSHEET2
boundsheets_len = 0
for sheet in self.__worksheets:
boundsheets_len += len(BIFFRecords.BoundSheetRecord(
0x00, sheet.visibility, sheet.name, self.encoding
).get())
start = data_len_before + boundsheets_len + data_len_after
result = b''
for sheet_biff_len, sheet in zip(sheet_biff_lens, self.__worksheets):
result += BIFFRecords.BoundSheetRecord(
start, sheet.visibility, sheet.name, self.encoding
).get()
start += sheet_biff_len
return result
def __all_links_rec(self):
pieces = []
temp = [(idx, tag) for tag, idx in list(self._supbook_xref.items())]
temp.sort()
for idx, tag in temp:
stype, snum = tag
if stype == 'ownbook':
rec = BIFFRecords.InternalReferenceSupBookRecord(len(self.__worksheets)).get()
pieces.append(rec)
elif stype == 'xcall':
rec = BIFFRecords.XcallSupBookRecord().get()
pieces.append(rec)
temp = [(idx, name) for name, idx in list(self._xcall_xref.items())]
temp.sort()
for idx, name in temp:
rec = BIFFRecords.ExternnameRecord(
options=0, index=0, name=name, fmla='\x02\x00\x1c\x17').get()
pieces.append(rec)
else:
raise Exception('unknown supbook stype %r' % stype)
if len(self.__sheet_refs) > 0:
# get references in index order
temp = [(idx, ref) for ref, idx in list(self.__sheet_refs.items())]
temp.sort()
temp = [ref for idx, ref in temp]
externsheet_record = BIFFRecords.ExternSheetRecord(temp).get()
pieces.append(externsheet_record)
return b''.join(pieces)
def __sst_rec(self):
return self.__sst.get_biff_record()
def __ext_sst_rec(self, abs_stream_pos):
return b''
#return BIFFRecords.ExtSSTRecord(abs_stream_pos, self.sst_record.str_placement,
#self.sst_record.portions_len).get()
def get_biff_data(self):
before = b''
before += self.__bof_rec()
before += self.__intf_hdr_rec()
before += self.__intf_mms_rec()
before += self.__intf_end_rec()
before += self.__write_access_rec()
before += self.__codepage_rec()
before += self.__dsf_rec()
before += self.__tabid_rec()
before += self.__fngroupcount_rec()
before += self.__wnd_protect_rec()
before += self.__protect_rec()
before += self.__obj_protect_rec()
before += self.__password_rec()
before += self.__prot4rev_rec()
before += self.__prot4rev_pass_rec()
before += self.__backup_rec()
before += self.__hide_obj_rec()
before += self.__window1_rec()
before += self.__datemode_rec()
before += self.__precision_rec()
before += self.__refresh_all_rec()
before += self.__bookbool_rec()
before += self.__all_fonts_num_formats_xf_styles_rec()
before += self.__palette_rec()
before += self.__useselfs_rec()
country = self.__country_rec()
all_links = self.__all_links_rec()
shared_str_table = self.__sst_rec()
after = country + all_links + shared_str_table
ext_sst = self.__ext_sst_rec(0) # need fake cause we need calc stream pos
eof = self.__eof_rec()
self.__worksheets[self.__active_sheet].selected = True
sheets = b''
sheet_biff_lens = []
for sheet in self.__worksheets:
data = sheet.get_biff_data()
sheets += data
sheet_biff_lens.append(len(data))
bundlesheets = self.__boundsheets_rec(len(before), len(after)+len(ext_sst)+len(eof), sheet_biff_lens)
sst_stream_pos = len(before) + len(bundlesheets) + len(country) + len(all_links)
ext_sst = self.__ext_sst_rec(sst_stream_pos)
return before + bundlesheets + after + ext_sst + eof + sheets
def save(self, filename):
from . import CompoundDoc
doc = CompoundDoc.XlsDoc()
doc.save(filename, self.get_biff_data())
File diff suppressed because it is too large Load Diff
-9
View File
@@ -1,9 +0,0 @@
import sys
from .Workbook import Workbook
from .Worksheet import Worksheet
from .Row import Row
from .Column import Column
from .Formatting import Font, Alignment, Borders, Pattern, Protection
from .Style import XFStyle, easyxf
from .ExcelFormula import *
File diff suppressed because it is too large Load Diff