Merge branch 'release/0.8.4'

Bolden headers and Separators.

AUTHORS

@@ -10,4 +10,5 @@ Development Lead
 Patches and Suggestions
 ```````````````````````
 
-- Luke Lee
+- Luke Lee
+- Josh Ourisman

HISTORY.rst

@@ -1,5 +1,24 @@
 History
 =======
+0.8.4 (2010-10-04)
+------------------
+
+* Upated XLS output: Only wrap if '\n' in cell.
+
+
+0.8.3 (2010-10-04)
+------------------
+
+* Ability to append new column passing a callable 
+  as the value that will be applied to every row.
+
+
+0.8.2 (2010-10-04)
+------------------
+
+* Added alignment wrapping to written cells.
+* Added separator support to XLS.
+
 
 0.8.1 (2010-09-28)
 ------------------

setup.py

@@ -17,7 +17,7 @@ if sys.argv[-1] == "publish":
 
 setup(
 	name='tablib',
-	version='0.8.1',
+	version='0.8.4',
 	description='Format agnostic tabular data library (XLS, JSON, YAML, CSV)',
 	long_description=open('README.rst').read() + '\n\n' +
 	                 open('HISTORY.rst').read(),

tabbed

@@ -0,0 +1,14 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+Tabbed -- CLI for Tablib
+Copyright (c) 2010 Kenneth Reitz. MIT License.
+"""
+
+import tablib.cli
+
+
+if __name__ == '__main__':
+	
+	tablib.cli.start()

tablib/__init__.py

@@ -2,7 +2,7 @@
 """
 
 from tablib.core import (
-	Databook, Dataset, InvalidDatasetType,
-	InvalidDimensions, UnsupportedFormat
+	Databook, Dataset, detect, import_set, 
+	InvalidDatasetType, InvalidDimensions, UnsupportedFormat
 )
 

tablib/cli.py

@@ -0,0 +1,84 @@
+#!/usr/bin/env python
+# encoding: utf-8
+
+""" Tabbed CLI Inteface Application
+"""
+
+import io
+import sys
+
+import argue
+
+import tablib
+from helpers import Struct, piped
+
+
+
+FORMATS = [fmt.title for fmt in tablib.formats.FORMATS]
+
+opts = []
+
+opts.append(('v', 'version', False, 'Report tabbed version'))
+
+for format in FORMATS:
+	opts.append(('', format, False, 'Output to %s' % (format.upper())))
+
+
+
+@argue.command(options=opts, usage='[FILE] [--FORMAT | FILE]')
+def start(in_file=None, out_file=None, **opts):
+	"""Covertly convert dataset formats"""
+	
+	opts = Struct(**opts)
+	
+	if opts.version:
+		print('Tabbed, Ver. %s' % tablib.core.__version__)
+		sys.exit(0)
+	
+	stdin = piped()
+	
+	if stdin:
+		data = tablib.import_set(stdin)
+	
+	elif in_file:
+		
+		try:
+			in_stream =- io.open(in_file, 'r').read()
+		except Exception, e:
+			print(' %s cannot be read.' % in_file)
+			sys.exit(65)
+		
+		try:
+			tablib.import_set(in_stream)
+		except Exception, e:
+			raise e
+			print('Import format not supported.')
+			sys.exit(65)
+	else:
+		print('Please provide input.')
+		sys.exit(65)
+		
+
+	_formats_sum = sum(opts[f] for f in FORMATS)
+	
+	# Multiple output formats given
+	if _formats_sum > 1:
+		print('Please specify a single output format.')
+		sys.exit(64)
+		
+	# No output formats given
+	elif _formats_sum < 1:
+		print('Please specify an output format.')
+		sys.exit(64)
+	
+	
+	# fetch options.formats list
+	# if sum(()) > 1
+	# log only one data format please
+	# if sum of formats == 0, specity format
+	
+	# look for filename
+	
+	# print opts.__dict__
+	# print in_file
+	# print out_file

tablib/core.py

@@ -7,8 +7,8 @@ from tablib.formats import FORMATS as formats
 
 
 __title__ = 'tablib'
-__version__ = '0.8.1'
-__build__ = 0x000801
+__version__ = '0.8.4'
+__build__ = 0x000804
 __author__ = 'Kenneth Reitz'
 __license__ = 'MIT'
 __copyright__ = 'Copyright 2010 Kenneth Reitz'
@@ -20,6 +20,9 @@ class Dataset(object):
 	def __init__(self, *args, **kwargs):
 		self._data = list(args)
 		self.__headers = None
+		
+		# ('title', index) tuples
+		self._separators = []
 
 		try:
 			self.headers = kwargs['headers']
@@ -33,6 +36,7 @@ class Dataset(object):
 
 		self._register_formats()
 
+		
 	def __len__(self):
 		return self.height
 
@@ -173,10 +177,19 @@ class Dataset(object):
 
 	def append(self, row=None, col=None):
 		"""Adds a row to the end of Dataset"""
-		if row:
+		if row is not None:
 			self._validate(row)
 			self._data.append(tuple(row))
-		elif col:
+		elif col is not None:
+			col = list(col)
+			if self.headers:
+				header = [col.pop(0)]
+			else:
+				header = []
+			if len(col) == 1 and callable(col[0]):
+				col = map(col[0], self._data)
+			col = tuple(header + col)
+				
 			self._validate(col=col)
 
 			if self.headers:
@@ -194,7 +207,26 @@ class Dataset(object):
 				self._data = [tuple([row]) for row in col]
 
 
-	def insert(self, i, row=None, col=None):
+	def insert_separator(self, index, text='-'):
+		"""Adds a separator to Dataset at given index."""
+
+		sep = (index, text)
+		self._separators.append(sep)
+
+
+	def append_separator(self, text='-'):
+		"""Adds a separator to Dataset."""
+
+		# change offsets if headers are or aren't defined
+		if not self.headers:
+			index = self.height if self.height else 0
+		else:
+			index = (self.height + 1) if self.height else 1
+
+		self.insert_separator(index, text)
+
+
+	def insert(self, i, row=None):
 		"""Inserts a row at given position in Dataset"""
 		if row:
 			self._validate(row)
@@ -225,9 +257,11 @@ class Databook(object):
 		except AttributeError:
 			return '<databook object>'
 
+
 	def wipe(self):
 		"""Wipe book clean."""
 		self._datasets = []
+
 		
 	@classmethod
 	def _register_formats(cls):
@@ -249,7 +283,7 @@ class Databook(object):
 			self._datasets.append(dataset)
 		else:
 			raise InvalidDatasetType
-
+		
 
 	def _package(self):
 		"""Packages Databook for delivery."""
@@ -268,6 +302,29 @@ class Databook(object):
 		return len(self._datasets)
 
 
+def detect(stream):
+	"""Return (format, stream) of given stream."""
+	for fmt in formats:
+		try:
+			if fmt.detect(stream):
+				return (fmt, stream) 
+		except AttributeError:
+			pass 
+	return (None, stream)
+	
+	
+def import_set(stream):
+	"""Return dataset of given stream."""
+	(format, stream) = detect(stream)
+
+	try:
+		data = Dataset()
+		format.import_set(data, stream)
+		return data
+		
+	except AttributeError, e:
+		return None
+
 
 class InvalidDatasetType(Exception):
 	"Only Datasets can be added to a DataBook"

tablib/formats/__init__.py

@@ -8,4 +8,4 @@ import _json as json
 import _xls as xls
 import _yaml as yaml
 
-FORMATS = (csv, json, xls, yaml)
+FORMATS = (json, xls, yaml, csv)

tablib/formats/_csv.py

@@ -40,3 +40,12 @@ def import_set(dset, in_stream, headers=True):
 			dset.headers = row
 		else:
 			dset.append(row)
+
+
+def detect(stream):
+	"""Returns True if given stream is valid CSV."""
+	try:
+		rows = dialect = csv.Sniffer().sniff(stream)
+		return True
+	except csv.Error:
+		return False

tablib/formats/_json.py

@@ -36,3 +36,12 @@ def import_book(dbook, in_stream):
 		data.title = sheet['title']
 		data.dict = sheet['data']
 		dbook.add_sheet(data)
+
+
+def detect(stream):
+	"""Returns True if given stream is valid JSON."""
+	try:
+		json.loads(stream)
+		return True
+	except json.decoder.JSONDecodeError:
+		return False

tablib/formats/_xls.py

@@ -10,6 +10,10 @@ import cStringIO
 title = 'xls'
 extentions = ('xls',)
 
+# special styles
+wrap = xlwt.easyxf("alignment: wrap on")
+bold = xlwt.easyxf("font: bold on")
+
 
 def export_set(dataset):
 	"""Returns XLS representation of Dataset."""
@@ -17,10 +21,8 @@ def export_set(dataset):
 	wb = xlwt.Workbook(encoding='utf8')
 	ws = wb.add_sheet(dataset.title if dataset.title else 'Tabbed Dataset')
 
-	for i, row in enumerate(dataset._package(dicts=False)):
-		for j, col in enumerate(row):
-			ws.write(i, j, col)
-
+	dset_sheet(dataset, ws)
+	
 	stream = cStringIO.StringIO()
 	wb.save(stream)
 	return stream.getvalue()
@@ -34,12 +36,38 @@ def export_book(databook):
 	for i, dset in enumerate(databook._datasets):
 		ws = wb.add_sheet(dset.title if dset.title else 'Sheet%s' % (i))
 
-		#for row in self._package(dicts=False):
-		for i, row in enumerate(dset._package(dicts=False)):
-			for j, col in enumerate(row):
-				ws.write(i, j, col)
+		dset_sheet(dset, ws)
 
 
 	stream = cStringIO.StringIO()
 	wb.save(stream)
-	return stream.getvalue()
+	return stream.getvalue()
+
+
+def dset_sheet(dataset, ws):
+	"""Completes given worksheet from given Dataset."""
+	_package = dataset._package(dicts=False)
+
+	for i, sep in enumerate(dataset._separators):
+		_offset = i
+		_package.insert((sep[0] + _offset), (sep[1],))
+
+	for i, row in enumerate(_package):
+		for j, col in enumerate(row):
+
+			# bold headers
+			if (i == 0) and dataset.headers:
+				ws.write(i, j, col, bold)
+
+			# bold separators
+			elif len(row) < dataset.width:
+				ws.write(i, j, col, bold)
+
+			# wrap the rest
+			else:
+				if '\n' in col:
+					ws.write(i, j, col, wrap)
+				else:
+					ws.write(i, j, col)
+
+	

tablib/formats/_yaml.py

@@ -39,4 +39,15 @@ def import_book(dbook, in_stream):
 		data = tablib.core.Dataset()
 		data.title = sheet['title']
 		data.dict = sheet['data']
-		dbook.add_sheet(data)
+		dbook.add_sheet(data)
+		
+def detect(stream):
+	"""Returns True if given stream is valid YAML."""
+	try:
+		_yaml = yaml.load(stream)
+		if isinstance(_yaml, (list, tuple, dict)):
+			return True
+		else:
+			return False
+	except yaml.parser.ParserError:
+		return False

test_tablib.py

@@ -102,6 +102,13 @@ class TablibTestCase(unittest.TestCase):
 
 		self.assertRaises(tablib.InvalidDimensions, data.append, col=new_col)
 
+	def test_add_callable_column(self):
+		"""Verify adding column with values specified as callable."""
+		new_col = ['first_again', lambda x: x[0]]
+		self.founders.append(col=new_col)
+
+		self.assertTrue(map(lambda x: x[0] == x[-1], self.founders))
+
 
 	def test_header_slicing(self):
 		"""Verify slicing by headers."""
@@ -261,6 +268,58 @@ class TablibTestCase(unittest.TestCase):
 
 		self.assertEqual(_csv, data.csv)
 
+	def test_csv_format_detect(self):
+		"""Test CSV format detection."""
+		
+		_csv = (
+			'1,2,3\n'
+			'4,5,6\n'
+			'7,8,9\n'
+		)
+		_bunk = (
+			'¡¡¡¡¡¡¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+		)
+		
+		self.assertTrue(tablib.formats.csv.detect(_csv))
+		self.assertFalse(tablib.formats.csv.detect(_bunk))
+
+	def test_json_format_detect(self):
+		"""Test JSON format detection."""
+
+		_json = '[{"last_name": "Adams","age": 90,"first_name": "John"}]'
+		_bunk = (
+			'¡¡¡¡¡¡¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+		)
+
+		self.assertTrue(tablib.formats.json.detect(_json))
+		self.assertFalse(tablib.formats.json.detect(_bunk))
+
+
+	def test_yaml_format_detect(self):
+		"""Test YAML format detection."""
+
+		_yaml = '- {age: 90, first_name: John, last_name: Adams}'
+		_bunk = (
+			'¡¡¡¡¡¡---///\n\n\n¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+		)
+
+		self.assertTrue(tablib.formats.yaml.detect(_yaml))
+		self.assertFalse(tablib.formats.yaml.detect(_bunk))
+
+
+	def test_auto_format_detect(self):
+		"""Test auto format detection."""
+
+		_yaml = '- {age: 90, first_name: John, last_name: Adams}'
+		_json = '[{"last_name": "Adams","age": 90,"first_name": "John"}]'
+		_csv = '1,2,3\n4,5,6\n7,8,9\n'
+		_bunk = '¡¡¡¡¡¡---///\n\n\n¡¡£™∞¢£§∞§¶•¶ª∞¶•ªº••ª–º§•†•§º¶•†¥ª–º•§ƒø¥¨©πƒø†ˆ¥ç©¨√øˆ¥≈†ƒ¥ç©ø¨çˆ¥ƒçø¶'
+
+		self.assertEqual(tablib.detect(_yaml)[0], tablib.formats.yaml)
+		self.assertEqual(tablib.detect(_csv)[0], tablib.formats.csv)
+		self.assertEqual(tablib.detect(_json)[0], tablib.formats.json)
+		self.assertEqual(tablib.detect(_bunk)[0], None)
+
 
 	def test_wipe(self):
 		"""Purge a dataset."""