.org

🍰 @iurisilvio

.gitignore

@@ -22,4 +22,7 @@ coverage.xml
 nosetests.xml
 junit-py25.xml
 junit-py26.xml
-junit-py27.xml
+junit-py27.xml
+
+# tox noise
+.tox

.travis.yml

@@ -0,0 +1,9 @@
+language: python
+python:
+  - 2.6
+  - 2.7
+  - 3.2
+  - 3.3
+install:
+  - python setup.py install
+script: python test_tablib.py

AUTHORS

@@ -4,9 +4,14 @@ various contributors:
 Development Lead
 ````````````````
 
-- Kenneth Reitz <_@kennethreitz.com>
+- Kenneth Reitz <me@kennethreitz.org>
 
 
+Core Contributors
+`````````````````
+
+- Iuri de Silvio <iurisilvio@gmail.com>
+
 Patches and Suggestions
 ```````````````````````
 
@@ -16,4 +21,9 @@ Patches and Suggestions
 - Benjamin Wohlwend
 - Erik Youngren
 - Mark Rogers
-- Mark Walling
+- Mark Walling
+- Mike Waldner
+- Joel Friedly
+- Jakub Janoszek
+- Marc Abramowitz
+- Alex Gaynor

HISTORY.rst

@@ -1,6 +1,10 @@
 History
 -------
 
+++++
+
+* Unicode Column Headers
+
 0.9.11 (2011-06-30)
 +++++++++++++++++++
 
@@ -16,7 +20,7 @@ History
 
 * Dataset API Changes
 * ``stack_rows`` => ``stack``, ``stack_columns`` => ``stack_cols``
-* column operations have their own methods now (``apend_col``, ``insert_col``)
+* column operations have their own methods now (``append_col``, ``insert_col``)
 * List-style ``pop()``
 * Redis-style ``rpush``, ``lpush``, ``rpop``, ``lpop``, ``rpush_col``, and ``lpush_col``
 

MANIFEST.in

@@ -1 +1 @@
-include HISTORY.rst README.rst LICENSE AUTHORS 
+include HISTORY.rst README.rst LICENSE AUTHORS NOTICE test_tablib.py

NOTICE

@@ -1,5 +1,5 @@
-Tablib includes some vendorized python libraries: ordereddict, pyyaml,
-simplejson, unicodecsv, and xlwt.
+Tablib includes some vendorized python libraries: ordereddict, odfpy, pyyaml,
+simplejson, unicodecsv, xlrd, xlrd3, xlwt, and xlwt3.
 
 Markup License
 ==============
@@ -7,6 +7,213 @@ Markup License
 Markup is in the public domain.
 
 
+Odfpy License
+=============
+
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+
+
 
 OrderedDict License
 ===================
@@ -92,8 +299,8 @@ or implied, of Jeremy Dunck.
 
 
 
-XLWT License
-============
+XLWT (and XLWT3) License
+========================
 
 Portions copyright © 2007, Stephen John Machin, Lingfo Pty Ltd
 All rights reserved.
@@ -172,4 +379,81 @@ Libknecht St., 4
 +7(0712)56-09-83
 
 <roman@kiseliov.ru>
-Subject: pyExcelerator
+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.

README.rst

@@ -1,6 +1,9 @@
 Tablib: format-agnostic tabular dataset library
 ===============================================
 
+.. image:: https://travis-ci.org/kennethreitz/tablib.svg?branch=develop
+    :target: https://travis-ci.org/kennethreitz/tablib
+
 ::
 
 	_____         ______  ___________ ______
@@ -55,7 +58,7 @@ Intelligently add new rows: ::
 
 Intelligently add new columns: ::
 
-    >>> data.append(col=(90, 67, 83), header='age')
+    >>> data.append_col((90, 67, 83), header='age')
 
 Slice rows:  ::
 
@@ -117,7 +120,8 @@ EXCEL!
 ++++++
 ::
 
-	>>> open('people.xls', 'wb').write(data.xls)
+	>>> with open('people.xls', 'wb') as f:
+	...     f.write(data.xls)
 
 It's that easy.
 

docs/_templates/sidebarintro.html

@@ -1,4 +1,4 @@
-<h3><a href="http://tablib.org">About Tablib</a></h3>
+<h3><a href="http://docs.python-tablib.org">About Tablib</a></h3>
 <p>
   Tablib is an MIT Licensed format-agnostic tabular dataset library, written in Python. It allows you to import, export, and manipulate tabular data sets. Advanced features include, segregation, dynamic columns, tags & filtering, and seamless format import & export.
 </p>
@@ -13,7 +13,7 @@
 
 <h3>Useful Links</h3>
 <ul>
-  <li><a href="http://tablib.org/">The Tablib Website</a></li>
+  <li><a href="http://docs.python-tablib.org/">The Tablib Website</a></li>
   <li><a href="http://pypi.python.org/pypi/tablib">Tablib @ PyPI</a></li>
   <li><a href="http://github.com/kennethreitz/tablib">Tablib @ GitHub</a></li>
   <li><a href="http://github.com/kennethreitz/tablib/issues">Issue Tracker</a></li>

docs/_templates/sidebarlogo.html

@@ -1,4 +1,4 @@
-<h3><a href="http://tablib.org">About Tablib</a></h3>
+<h3><a href="http://docs.python-tablib.org/">About Tablib</a></h3>
 <p>
   Tablib is an MIT Licensed format-agnostic tabular dataset library, written in Python. It allows you to import, export, and manipulate tabular data sets. Advanced features include, segregation, dynamic columns, tags & filtering, and seamless format import & export.
 </p>

docs/_themes/kr/layout.html

@@ -15,6 +15,12 @@
     <a href="https://github.com/kennethreitz/tablib">
         <img style="position: absolute; top: 0; right: 0; border: 0;" src="http://s3.amazonaws.com/github/ribbons/forkme_right_darkblue_121621.png" alt="Fork me on GitHub" />
     </a>
+
+    <script type="text/javascript" src="//www.hellobar.com/hellobar.js"></script>
+    <script type="text/javascript">
+        new HelloBar(36402,48802);
+    </script>
+
     <script type="text/javascript">
 
       var _gaq = _gaq || [];

docs/development.rst

@@ -46,7 +46,7 @@ Source Control
 Tablib source is controlled with Git_, the lean, mean, distributed source
 control machine.
 
-The repository is publicly accessable.
+The repository is publicly accessible.
 
     ``git clone git://github.com/kennethreitz/tablib.git``
 
@@ -67,11 +67,11 @@ Feature / Hotfix / Release branches follow a `Successful Git Branching Model`_ .
 ``master``
     Current production release (|version|) on PyPi.
 ``gh-pages``
-    Current release of http://tablib.org.
+    Current release of http://docs.python-tablib.org.
 
 Each release is tagged.
 
-When submitting patches, please place your feature/change in its own branch prior to opening a pull reqeust on GitHub_.
+When submitting patches, please place your feature/change in its own branch prior to opening a pull request on GitHub_.
 
 
 .. _Git: http://git-scm.org
@@ -132,7 +132,7 @@ Tablib features a micro-framework for adding format support. The easiest way to
 
 2.
 
-    Add your new format module to the :class:`tablib.formats.avalable` tuple.
+    Add your new format module to the :class:`tablib.formats.available` tuple.
 
 3.
     Add a mock property to the :class:`Dataset <tablib.Dataset>` class with verbose `reStructured Text`_ docstring. This alleviates IDE confusion, and allows for pretty auto-generated Sphinx_ documentation.
@@ -174,20 +174,15 @@ This will generate a **nosetests.xml** file, which can then be analyzed.
 Continuous Integration
 ----------------------
 
-Every commit made to the **develop** branch is automatically tested and inspected upon receipt with `Jenkins CI`_. If you have access to the main repository and broke the build, you will receive an email accordingly.
+Every commit made to the **develop** branch is automatically tested and inspected upon receipt with `Travis CI`_. If you have access to the main repository and broke the build, you will receive an email accordingly.
 
 Anyone may view the build status and history at any time.
 
-    http://ci.kennethreitz.com/
-
-
-If you are trustworthy and plan to contribute to tablib on a regular basis, please contact `Kenneth Reitz`_ to get an account on the Jenkins Server.
-
+    https://travis-ci.org/kennethreitz/tablib
 
 Additional reports will also be included here in the future, including :pep:`8` checks and stress reports for extremely large datasets.
 
-.. _`Jenkins CI`: http://jenkins-ci.org/
-.. _`Kenneth Reitz`: http://kennethreitz.com/contact-me/
+.. _`Jenkins CI`: https://travis-ci.org/
 
 
 .. _docs:
@@ -210,13 +205,13 @@ Then, to build an HTML version of the docs, simply run the following from the **
 
 Your ``docs/_build/html`` directory will then contain an HTML representation of the documentation, ready for publication on most web servers.
 
-You can also generate the documentation in **ebpub**, **latex**, **json**, *&c* similarly.
+You can also generate the documentation in **epub**, **latex**, **json**, *&c* similarly.
 
 .. admonition:: GitHub Pages
 
 	To push the documentation up to `GitHub Pages`_, you will first need to run `sphinx-to-github`_ against your ``docs/_build/html`` directory.
 
-	GitHub Pages are powered by an HTML generation system called Jeckyl_, which is configured to ignore files and folders that begin with "``_``" (*ie.* **_static**).
+	GitHub Pages are powered by an HTML generation system called Jekyll_, which is configured to ignore files and folders that begin with "``_``" (*ie.* **_static**).
 
 
 
@@ -238,9 +233,9 @@ You can also generate the documentation in **ebpub**, **latex**, **json**, *&c*
 .. _`reStructured Text`: http://docutils.sourceforge.net/rst.html
 .. _Sphinx: http://sphinx.pocoo.org
 .. _`GitHub Pages`: http://pages.github.com
-.. _Jeckyl: http://github.com/mojombo/jekyll
+.. _Jekyll: http://github.com/mojombo/jekyll
 .. _`sphinx-to-github`: http://github.com/michaeljones/sphinx-to-github
 
 ----------
 
-Make sure to check out the :ref:`API Documentation <api>`.
+Make sure to check out the :ref:`API Documentation <api>`.

docs/index.rst

@@ -26,8 +26,8 @@ Tablib is an :ref:`MIT Licensed <mit>` format-agnostic tabular dataset library,
 
 ::
 
-   >>> data = tablib.Dataset(headers=['First Name', 'Last Name', 'Age'])
-   >>> map(data.append, [('Kenneth', 'Reitz', 22), ('Bessie', 'Monke', 21)])
+   >>> data = tablib.Dataset(*[('Kenneth', 'Reitz', 23), ('Bessie', 'Monke', 22)],
+                             headers=['First Name', 'Last Name', 'Age'])
 
    >>> data.json
    [{"Last Name": "Reitz", "First Name": "Kenneth", "Age": 22}, {"Last Name": "Monke", "First Name": "Bessie", "Age": 21}]
@@ -55,7 +55,7 @@ and `The Sunlight Foundation <http://sunlightfoundation.com/>`_ use Tablib inter
    Tablib by @kennethreitz saved my life. I had to consolidate like 5 huge poorly maintained lists of domains and data. It was a breeze!
 
 **Dave Coutts**
-   It's turning into one of my most used modules of 2010. You really hit a sweat spot for managing tabular data with a minimal amount of code and effort.
+   It's turning into one of my most used modules of 2010. You really hit a sweet spot for managing tabular data with a minimal amount of code and effort.
 
 **Joshua Ourisman**
    Tablib has made it so much easier to deal with the inevitable 'I want an Excel file!' requests from clients...
@@ -99,4 +99,4 @@ method, this part of the documentation is for you.
 .. toctree::
    :maxdepth: 2
 
-   api
+   api

docs/install.rst

@@ -2,7 +2,7 @@
 Installation
 ============
 
-This part of the documentation covers the installation of Tablib. The first step to using any software package is getting it properly installed. Please read this section carefully, or you may miss out on some nice  :ref:`speed enhancements <peed-extentions>`.
+This part of the documentation covers the installation of Tablib. The first step to using any software package is getting it properly installed. Please read this section carefully, or you may miss out on some nice  :ref:`speed enhancements <peed-extensions>`.
 
 
 .. _installing:
@@ -22,7 +22,7 @@ or, with `easy_install <http://pypi.python.org/pypi/setuptools>`_::
 
     $ easy_install tablib
 
-But, you really `shouldn't do that <http://www.pip-installer.org/en/latest/index.html#pip-compared-to-easy-install>`_.
+But, you really `shouldn't do that <http://www.pip-installer.org/en/latest/other-tools.html#pip-compared-to-easy-install>`_.
 
 
 
@@ -57,15 +57,15 @@ To download the full source history from Git, see :ref:`Source Control <scm>`.
 .. _zipball: http://github.com/kennethreitz/tablib/zipball/master
 
 
-.. _speed-extentions:
-Speed Extentions
+.. _speed-extensions:
+Speed Extensions
 ----------------
 
 .. versionadded:: 0.8.5
 
 Tablib is partially dependent on the **pyyaml**, **simplejson**, and **xlwt** modules. To reduce installation issues, fully integrated versions of all required libraries are included in Tablib.
 
-However, if performance is important to you (and it should be), you can install  **pyyaml** with C extentions from PyPi. ::
+However, if performance is important to you (and it should be), you can install  **pyyaml** with C extensions from PyPi. ::
 
     $ pip install PyYAML
 

docs/tutorial.rst

@@ -68,7 +68,7 @@ Adding Headers
 --------------
 
 
-It's time enhance our :class:`Dataset` by giving our columns some titles. To do so, set :class:`Dataset.headers`. ::
+It's time to enhance our :class:`Dataset` by giving our columns some titles. To do so, set :class:`Dataset.headers`. ::
 
     data.headers = ['First Name', 'Last Name']
 
@@ -146,6 +146,13 @@ To do so, we access the :class:`Dataset` as if it were a standard Python diction
     >>> data['First Name']
     ['Kenneth', 'Bessie']
 
+You can also access the column using its index. ::
+
+    >>> d.headers
+    ['Last Name', 'First Name', 'Age']
+    >>> d.get_col(1)
+    ['Kenneth', 'Bessie']
+
 Let's find the average age. ::
 
     >>> ages = data['Age']
@@ -244,7 +251,7 @@ Filtering Datasets with Tags
 
 
 When constructing a :class:`Dataset` object, you can add tags to rows by specifying the ``tags`` parameter.
-This allows you to filter your :class:`Dataset` later. This can be useful so separate rows of data based on
+This allows you to filter your :class:`Dataset` later. This can be useful to separate rows of data based on
 arbitrary criteria (*e.g.* origin) that you don't want to include in your :class:`Dataset`.
 
 Let's tag some students. ::
@@ -256,7 +263,7 @@ Let's tag some students. ::
     students.rpush(['Kenneth', 'Reitz'], tags=['male', 'technical'])
     students.rpush(['Bessie', 'Monke'], tags=['female', 'creative'])
 
-Now that we have extra meta-data on our rows, we can use easily filter our :class:`Dataset`. Let's just see Male students. ::
+Now that we have extra meta-data on our rows, we can easily filter our :class:`Dataset`. Let's just see Male students. ::
 
 
     >>> students.filter(['male']).yaml

setup.cfg

@@ -0,0 +1,2 @@
+[wheel]
+universal = 1

setup.py

@@ -7,18 +7,11 @@ import sys
 import tablib
 
 try:
-    from setuptools import setup, find_packages
+    from setuptools import setup
 except ImportError:
-    from distutils.core import setup, find_packages
+    from distutils.core import setup
 
 
-packages = find_packages(exclude=('docs',))
-
-if sys.version_info[:2] < (3,0):
-    packages = [p for p in packages if '3' not in p]
-else:
-    packages = [p for p in packages if '2' not in p]
-
 if sys.argv[-1] == 'publish':
     os.system("python setup.py sdist upload")
     sys.exit()
@@ -40,8 +33,8 @@ if sys.argv[-1] == 'test':
         print('py.test required.')
         sys.exit(1)
 
-    os.system('pytest test_tablib.py')
-    sys.exit()
+    errors = os.system('py.test test_tablib.py')
+    sys.exit(bool(errors))
 
 setup(
     name='tablib',
@@ -50,9 +43,30 @@ setup(
     long_description=(open('README.rst').read() + '\n\n' +
         open('HISTORY.rst').read()),
     author='Kenneth Reitz',
-    author_email='me@kennethreitz.com',
-    url='http://tablib.org',
-    packages=packages,
+    author_email='me@kennethreitz.org',
+    url='http://python-tablib.org',
+    packages=[
+        'tablib', 'tablib.formats',
+        'tablib.packages',
+        'tablib.packages.xlwt',
+        'tablib.packages.xlwt3',
+        'tablib.packages.xlrd',
+        'tablib.packages.xlrd3',
+        'tablib.packages.omnijson',
+        'tablib.packages.odf',
+        'tablib.packages.odf3',
+        'tablib.packages.openpyxl',
+        'tablib.packages.openpyxl.shared',
+        'tablib.packages.openpyxl.reader',
+        'tablib.packages.openpyxl.writer',
+        'tablib.packages.openpyxl3',
+        'tablib.packages.openpyxl3.shared',
+        'tablib.packages.openpyxl3.reader',
+        'tablib.packages.openpyxl3.writer',
+        'tablib.packages.yaml',
+        'tablib.packages.yaml3',
+        'tablib.packages.unicodecsv'
+    ],
     license='MIT',
     classifiers=(
         'Development Status :: 5 - Production/Stable',
@@ -66,5 +80,8 @@ setup(
         'Programming Language :: Python :: 3.0',
         'Programming Language :: Python :: 3.1',
         'Programming Language :: Python :: 3.2',
+        'Programming Language :: Python :: 3.3',
+        'Programming Language :: Python :: 3.4',
     ),
+    tests_require=['pytest'],
 )

tablib/__init__.py

@@ -1,7 +1,7 @@
 """ Tablib. """
 
 from tablib.core import (
-    Databook, Dataset, detect, import_set,
+    Databook, Dataset, detect, import_set, import_book,
     InvalidDatasetType, InvalidDimensions, UnsupportedFormat,
     __version__
 )

tablib/compat.py

@@ -23,6 +23,8 @@ 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 import openpyxl3 as openpyxl
     from tablib.packages.odf3 import opendocument, style, text, table
@@ -39,6 +41,8 @@ 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 import openpyxl
@@ -46,4 +50,4 @@ else:
 
     from tablib.packages import unicodecsv as csv
 
-    unicode = unicode
+    unicode = unicode

tablib/core.py

@@ -5,7 +5,7 @@
 
     This module implements the central Tablib objects.
 
-    :copyright: (c) 2011 by Kenneth Reitz.
+    :copyright: (c) 2014 by Kenneth Reitz.
     :license: MIT, see LICENSE for more details.
 """
 
@@ -14,22 +14,22 @@ from operator import itemgetter
 
 from tablib import formats
 
-from tablib.compat import OrderedDict
+from tablib.compat import OrderedDict, unicode
 
 
 __title__ = 'tablib'
-__version__ = '0.9.11'
-__build__ = 0x000911
+__version__ = '0.10.0'
+__build__ = 0x001000
 __author__ = 'Kenneth Reitz'
 __license__ = 'MIT'
-__copyright__ = 'Copyright 2011 Kenneth Reitz'
+__copyright__ = 'Copyright 2014 Kenneth Reitz'
 __docformat__ = 'restructuredtext'
 
 
 class Row(object):
     """Internal Row object. Mainly used for filtering."""
 
-    __slots__ = ['tuple', '_row', 'tags']
+    __slots__ = ['_row', 'tags']
 
     def __init__(self, row=list(), tags=list()):
         self._row = list(row)
@@ -57,7 +57,14 @@ class Row(object):
         del self._row[i]
 
     def __getstate__(self):
-        return {'slot': [getattr(self, slot) for slot in self.__slots__]}
+
+        slots = dict()
+
+        for slot in self.__slots__:
+            attribute = getattr(self, slot)
+            slots[slot] = attribute
+
+        return slots
 
     def __setstate__(self, state):
         for (k, v) in list(state.items()): setattr(self, k, v)
@@ -105,7 +112,7 @@ class Dataset(object):
     functionality.
 
     Usually you create a :class:`Dataset` instance in your main module, and append
-    rows and columns as you collect data. ::
+    rows as you collect data. ::
 
         data = tablib.Dataset()
         data.headers = ('name', 'age')
@@ -113,15 +120,27 @@ class Dataset(object):
         for (name, age) in some_collector():
             data.append((name, age))
 
-    You can also set rows and headers upon instantiation. This is useful if dealing
-    with dozens or hundres of :class:`Dataset` objects. ::
+
+    Setting columns is similar. The column data length must equal the
+    current height of the data and headers must be set ::
+
+        data = tablib.Dataset()
+        data.headers = ('first_name', 'last_name')
+
+        data.append(('John', 'Adams'))
+        data.append(('George', 'Washington'))
+
+        data.append_col((90, 67), header='age')
+
+
+    You can also set rows and headers upon instantiation. This is useful if
+    dealing with dozens or hundreds of :class:`Dataset` objects. ::
 
         headers = ('first_name', 'last_name')
         data = [('John', 'Adams'), ('George', 'Washington')]
 
         data = tablib.Dataset(*data, headers=headers)
 
-
     :param \*args: (optional) list of rows to populate Dataset
     :param headers: (optional) list strings for Dataset header row
 
@@ -162,7 +181,7 @@ class Dataset(object):
 
 
     def __getitem__(self, key):
-        if isinstance(key, str):
+        if isinstance(key, str) or isinstance(key, unicode):
             if key in self.headers:
                 pos = self.headers.index(key) # get 'key' index from each data
                 return [row[pos] for row in self._data]
@@ -175,14 +194,13 @@ class Dataset(object):
             else:
                 return [result.tuple for result in _results]
 
-
     def __setitem__(self, key, value):
         self._validate(value)
         self._data[key] = Row(value)
 
 
     def __delitem__(self, key):
-        if isinstance(key, str):
+        if isinstance(key, str) or isinstance(key, unicode):
 
             if key in self.headers:
 
@@ -205,6 +223,25 @@ class Dataset(object):
         except AttributeError:
             return '<dataset object>'
 
+    def __unicode__(self):
+        result = [self.__headers]
+
+        result.extend(list(map(unicode, row)) for row in self._data)
+
+        # here, we calculate max width for each column
+        lens = (list(map(len, row)) for row in result)
+        field_lens = list(map(max, zip(*lens)))
+
+        # delimiter between header and data
+        result.insert(1, ['-' * length for length in field_lens])
+
+        format_string = '|'.join('{%s:%s}' % item for item in enumerate(field_lens))
+
+        return '\n'.join(format_string.format(*row) for row in result)
+
+    def __str__(self):
+        return self.__unicode__()
+
 
     # ---------
     # Internals
@@ -410,7 +447,7 @@ class Dataset(object):
              :class:`Dataset.xls` contains binary data, so make sure to write in binary mode::
 
                 with open('output.xls', 'wb') as f:
-                    f.write(data.xls)'
+                    f.write(data.xls)
         """
         pass
 
@@ -423,7 +460,7 @@ class Dataset(object):
              :class:`Dataset.xlsx` contains binary data, so make sure to write in binary mode::
 
                 with open('output.xlsx', 'wb') as f:
-                    f.write(data.xlsx)'
+                    f.write(data.xlsx)
         """
         pass
 
@@ -433,10 +470,10 @@ class Dataset(object):
 
          .. admonition:: Binary Warning
 
-             :class:`Dataset.xlsx` contains binary data, so make sure to write in binary mode::
+             :class:`Dataset.ods` contains binary data, so make sure to write in binary mode::
 
                 with open('output.ods', 'wb') as f:
-                    f.write(data.ods)'
+                    f.write(data.ods)
         """
         pass
 
@@ -452,6 +489,17 @@ class Dataset(object):
             data.csv = 'age, first_name, last_name\\n90, John, Adams'
 
         Import assumes (for now) that headers exist.
+
+        .. admonition:: Binary Warning
+
+             :class:`Dataset.csv` uses \\r\\n line endings by default, so make
+             sure to write in binary mode::
+
+                 with open('output.csv', 'wb') as f:
+                     f.write(data.csv)
+
+             If you do not do this, and you export the file on Windows, your
+             CSV file will open in Excel with a blank line between each row.
         """
         pass
 
@@ -477,7 +525,7 @@ class Dataset(object):
         set, a YAML list of objects will be returned. If no headers have
         been set, a YAML list of lists (rows) will be returned instead.
 
-        A dataset object can also be imported by setting the :class:`Dataset.json` attribute: ::
+        A dataset object can also be imported by setting the :class:`Dataset.yaml` attribute: ::
 
             data = tablib.Dataset()
             data.yaml = '- {age: 90, first_name: John, last_name: Adams}'
@@ -500,6 +548,7 @@ class Dataset(object):
 
         Import assumes (for now) that headers exist.
         """
+        pass
 
     @property
     def html():
@@ -518,30 +567,11 @@ class Dataset(object):
     def insert(self, index, row, tags=list()):
         """Inserts a row to the :class:`Dataset` at the given index.
 
-        Rows and columns inserted must be the correct size (height or width).
+        Rows inserted must be the correct size (height or width).
 
         The default behaviour is to insert the given row to the :class:`Dataset`
-        object at the given index. If the ``col`` parameter is given, however,
-        a new column will be insert to the :class:`Dataset` object instead.
-
-        You can also insert a column of a single callable object, which will
-        add a new column with the return values of the callable each as an
-        item in the column. ::
-
-            data.append(col=random.randint)
-
-        See :ref:`dyncols` for an in-depth example.
-
-        .. versionchanged:: 0.9.0
-           If inserting a column, and :class:`Dataset.headers` is set, the
-           header attribute must be set, and will be considered the header for
-           that row.
-
-        .. versionadded:: 0.9.0
-           If inserting a row, you can add :ref:`tags <tags>` to the row you are inserting.
-           This gives you the ability to :class:`filter <Dataset.filter>` your
-           :class:`Dataset` later.
-        """
+        object at the given index.
+       """
 
         self._validate(row)
         self._data.insert(index, Row(row, tags=tags))
@@ -570,6 +600,14 @@ class Dataset(object):
 
         self.rpush(row, tags)
 
+    def extend(self, rows, tags=list()):
+        """Adds a list of rows to the :class:`Dataset` using
+        :class:`Dataset.append`
+        """
+
+        for row in rows:
+            self.append(row, tags)
+
 
     def lpop(self):
         """Removes and returns the first row of the :class:`Dataset`."""
@@ -615,8 +653,22 @@ class Dataset(object):
         that row.
 
         See :ref:`dyncols` for an in-depth example.
+
+        .. versionchanged:: 0.9.0
+           If inserting a column, and :class:`Dataset.headers` is set, the
+           header attribute must be set, and will be considered the header for
+           that row.
+
+        .. versionadded:: 0.9.0
+           If inserting a row, you can add :ref:`tags <tags>` to the row you are inserting.
+           This gives you the ability to :class:`filter <Dataset.filter>` your
+           :class:`Dataset` later.
+
         """
 
+        if col is None:
+            col = []
+
         # Callable Columns...
         if hasattr(col, '__call__'):
             col = list(map(col, self._data))
@@ -628,8 +680,14 @@ class Dataset(object):
             # pop the first item off, add to headers
             if not header:
                 raise HeadersNeeded()
+
+            # corner case - if header is set without data
+            elif header and self.height == 0 and len(col):
+                raise InvalidDimensions
+
             self.headers.insert(index, header)
 
+
         if self.height and self.width:
 
             for i, row in enumerate(self._data):
@@ -684,6 +742,12 @@ class Dataset(object):
         self.rpush_col(col, header)
 
 
+    def get_col(self, index):
+        """Returns the column from the :class:`Dataset` at the given index."""
+
+        return [row[index] for row in self._data]
+
+
     # ----
     # Misc
     # ----
@@ -730,13 +794,13 @@ class Dataset(object):
         sorted.
         """
 
-        if isinstance(col, str):
+        if isinstance(col, str) or isinstance(col, unicode):
 
             if not self.headers:
                 raise HeadersNeeded
 
             _sorted = sorted(self.dict, key=itemgetter(col), reverse=reverse)
-            _dset = Dataset(headers=self.headers)
+            _dset = Dataset(headers=self.headers, title=self.title)
 
             for item in _sorted:
                 row = [item[key] for key in self.headers]
@@ -747,7 +811,7 @@ class Dataset(object):
                 col = self.headers[col]
 
             _sorted = sorted(self.dict, key=itemgetter(col), reverse=reverse)
-            _dset = Dataset(headers=self.headers)
+            _dset = Dataset(headers=self.headers, title=self.title)
 
             for item in _sorted:
                 if self.headers:
@@ -891,10 +955,12 @@ class Databook(object):
             except AttributeError:
                 pass
 
+    def sheets(self):
+        return self._datasets
 
     def add_sheet(self, dataset):
         """Adds given :class:`Dataset` to the :class:`Databook`."""
-        if type(dataset) is Dataset:
+        if isinstance(dataset, Dataset):
             self._datasets.append(dataset)
         else:
             raise InvalidDatasetType
@@ -947,6 +1013,19 @@ def import_set(stream):
         return None
 
 
+def import_book(stream):
+    """Return dataset of given stream."""
+    (format, stream) = detect(stream)
+
+    try:
+        databook = Databook()
+        format.import_book(databook, stream)
+        return databook
+
+    except AttributeError:
+        return None
+
+
 class InvalidDatasetType(Exception):
     "Only Datasets can be added to a DataBook"
 

tablib/formats/_csv.py

@@ -7,7 +7,7 @@ from tablib.compat import is_py3, csv, StringIO
 
 
 title = 'csv'
-extentions = ('csv',)
+extensions = ('csv',)
 
 
 DEFAULT_ENCODING = 'utf-8'
@@ -35,9 +35,9 @@ def import_set(dset, in_stream, headers=True):
     dset.wipe()
 
     if is_py3:
-        rows = csv.reader(in_stream.splitlines())
+        rows = csv.reader(StringIO(in_stream))
     else:
-        rows = csv.reader(in_stream.splitlines(), encoding=DEFAULT_ENCODING)
+        rows = csv.reader(StringIO(in_stream), encoding=DEFAULT_ENCODING)
     for i, row in enumerate(rows):
 
         if (i == 0) and (headers):
@@ -49,7 +49,7 @@ def import_set(dset, in_stream, headers=True):
 def detect(stream):
     """Returns True if given stream is valid CSV."""
     try:
-        csv.Sniffer().sniff(stream)
+        csv.Sniffer().sniff(stream, delimiters=',')
         return True
-    except csv.Error:
-        return False
+    except (csv.Error, TypeError):
+        return False

tablib/formats/_html.py

@@ -5,20 +5,21 @@
 
 import sys
 
-
 if sys.version_info[0] > 2:
-    from io import StringIO
+    from io import BytesIO as StringIO
     from tablib.packages import markup3 as markup
 else:
     from cStringIO import StringIO
     from tablib.packages import markup
 
 import tablib
+from tablib.compat import unicode
+import codecs
 
 BOOK_ENDINGS = 'h3'
 
 title = 'html'
-extentions = ('html', )
+extensions = ('html', )
 
 
 def export_set(dataset):
@@ -30,20 +31,26 @@ def export_set(dataset):
 	page.table.open()
 
 	if dataset.headers is not None:
+		new_header = [item if item is not None else '' for item in dataset.headers] 
+
 		page.thead.open()
-		headers = markup.oneliner.th(dataset.headers)
+		headers = markup.oneliner.th(new_header)
 		page.tr(headers)
 		page.thead.close()
 
 	for row in dataset:
-		html_row = markup.oneliner.td(row)
+		new_row = [item if item is not None else '' for item in row] 
+
+		html_row = markup.oneliner.td(new_row)
 		page.tr(html_row)
 
 	page.table.close()
 
-	stream.writelines(str(page))
+    # Allow unicode characters in output
+	wrapper = codecs.getwriter("utf8")(stream)
+	wrapper.writelines(unicode(page))
 
-	return stream.getvalue()
+	return stream.getvalue().decode('utf-8')
 
 
 def export_book(databook):

tablib/formats/_json.py

@@ -10,7 +10,7 @@ from tablib.packages import omnijson as json
 
 
 title = 'json'
-extentions = ('json', 'jsn')
+extensions = ('json', 'jsn')
 
 
 def export_set(dataset):

tablib/formats/_ods.py

@@ -14,7 +14,7 @@ else:
 from tablib.compat import opendocument, style, table, text, unicode
 
 title = 'ods'
-extentions = ('ods',)
+extensions = ('ods',)
 
 bold = style.Style(name="bold", family="paragraph")
 bold.addElement(style.TextProperties(fontweight="bold", fontweightasian="bold", fontweightcomplex="bold"))

tablib/formats/_tsv.py

@@ -8,7 +8,7 @@ from tablib.compat import is_py3, csv, StringIO
 
 
 title = 'tsv'
-extentions = ('tsv',)
+extensions = ('tsv',)
 
 DEFAULT_ENCODING = 'utf-8'
 
@@ -34,9 +34,9 @@ def import_set(dset, in_stream, headers=True):
     dset.wipe()
 
     if is_py3:
-        rows = csv.reader(in_stream.split('\r\n'), delimiter='\t')
+        rows = csv.reader(in_stream.splitlines(), delimiter='\t')
     else:
-        rows = csv.reader(in_stream.split('\r\n'), delimiter='\t',
+        rows = csv.reader(in_stream.splitlines(), delimiter='\t',
                           encoding=DEFAULT_ENCODING)
 
     for i, row in enumerate(rows):
@@ -55,5 +55,5 @@ def detect(stream):
     try:
         csv.Sniffer().sniff(stream, delimiters='\t')
         return True
-    except csv.Error:
+    except (csv.Error, TypeError):
         return False

tablib/formats/_xls.py

@@ -5,17 +5,36 @@
 
 import sys
 
-from tablib.compat import BytesIO, xlwt
-
+from tablib.compat import BytesIO, xlwt, xlrd, XLRDError
+import tablib
 
 title = 'xls'
-extentions = ('xls',)
+extensions = ('xls',)
 
 # special styles
 wrap = xlwt.easyxf("alignment: wrap on")
 bold = xlwt.easyxf("font: bold on")
 
 
+def detect(stream):
+    """Returns True if given stream is a readable excel file."""
+    try:
+        xlrd.open_workbook(file_contents=stream)
+        return True
+    except (TypeError, XLRDError):
+        pass 
+    try:
+        xlrd.open_workbook(file_contents=stream.read())
+        return True
+    except (AttributeError, XLRDError):
+        pass
+    try:
+        xlrd.open_workbook(filename=stream)
+        return True
+    except:
+        return False
+
+
 def export_set(dataset):
     """Returns XLS representation of Dataset."""
 
@@ -45,6 +64,42 @@ def export_book(databook):
     return stream.getvalue()
 
 
+def import_set(dset, in_stream, headers=True):
+    """Returns databook from XLS stream."""
+
+    dset.wipe()
+
+    xls_book = xlrd.open_workbook(file_contents=in_stream)
+    sheet = xls_book.sheet_by_index(0)
+
+    dset.title = sheet.name
+
+    for i in xrange(sheet.nrows):
+        if (i == 0) and (headers):
+            dset.headers = sheet.row_values(0)
+        else:
+            dset.append(sheet.row_values(i))
+
+def import_book(dbook, in_stream, headers=True):
+    """Returns databook from XLS stream."""
+
+    dbook.wipe()
+
+    xls_book = xlrd.open_workbook(file_contents=in_stream)
+
+    for sheet in xls_book.sheets():
+        data = tablib.Dataset()
+        data.title = sheet.name
+
+        for i in xrange(sheet.nrows):
+            if (i == 0) and (headers):
+                data.headers = sheet.row_values(0)
+            else:
+                data.append(sheet.row_values(i))
+
+        dbook.add_sheet(data)
+
+
 def dset_sheet(dataset, ws):
     """Completes given worksheet from given Dataset."""
     _package = dataset._package(dicts=False)
@@ -78,5 +133,3 @@ def dset_sheet(dataset, ws):
                         ws.write(i, j, col)
                 except TypeError:
                     ws.write(i, j, col)
-
-

tablib/formats/_xlsx.py

@@ -12,6 +12,7 @@ else:
     from cStringIO import StringIO as BytesIO
 
 from tablib.compat import openpyxl
+import tablib
 
 Workbook = openpyxl.workbook.Workbook
 ExcelWriter = openpyxl.writer.excel.ExcelWriter
@@ -21,7 +22,16 @@ from tablib.compat import unicode
 
 
 title = 'xlsx'
-extentions = ('xlsx',)
+extensions = ('xlsx',)
+
+
+def detect(stream):
+    """Returns True if given stream is a readable excel file."""
+    try:
+        openpyxl.reader.excel.load_workbook(stream)
+        return True
+    except openpyxl.shared.exc.InvalidFileException:
+        pass
 
 def export_set(dataset):
     """Returns XLSX representation of Dataset."""
@@ -41,7 +51,7 @@ def export_book(databook):
     """Returns XLSX representation of DataBook."""
 
     wb = Workbook()
-    ew = ExcelWriter(workbook = wb)
+    wb.worksheets = []
     for i, dset in enumerate(databook._datasets):
         ws = wb.create_sheet()
         ws.title = dset.title if dset.title else 'Sheet%s' % (i)
@@ -50,10 +60,49 @@ def export_book(databook):
 
 
     stream = BytesIO()
-    ew.save(stream)
+    wb.save(stream)
     return stream.getvalue()
 
 
+def import_set(dset, in_stream, headers=True):
+    """Returns databook from XLS stream."""
+
+    dset.wipe()
+
+    xls_book = openpyxl.reader.excel.load_workbook(in_stream)
+    sheet = xls_book.get_active_sheet()
+
+    dset.title = sheet.title
+
+    for i, row in enumerate(sheet.rows):
+        row_vals = [c.value for c in row]
+        if (i == 0) and (headers):
+            dset.headers = row_vals
+        else:
+            dset.append(row_vals)
+
+
+def import_book(dbook, in_stream, headers=True):
+    """Returns databook from XLS stream."""
+
+    dbook.wipe()
+
+    xls_book = openpyxl.reader.excel.load_workbook(in_stream)
+
+    for sheet in xls_book.worksheets:
+        data = tablib.Dataset()
+        data.title = sheet.title
+
+        for i, row in enumerate(sheet.rows):
+            row_vals = [c.value for c in row]
+            if (i == 0) and (headers):
+                data.headers = row_vals
+            else:
+                data.append(row_vals)
+
+        dbook.add_sheet(data)
+
+
 def dset_sheet(dataset, ws):
     """Completes given worksheet from given Dataset."""
     _package = dataset._package(dicts=False)
@@ -66,6 +115,8 @@ def dset_sheet(dataset, ws):
         row_number = i + 1
         for j, col in enumerate(row):
             col_idx = get_column_letter(j + 1)
+            # We want to freeze the column after the last column
+            frzn_col_idx = get_column_letter(j + 2)
 
             # bold headers
             if (row_number == 1) and dataset.headers:
@@ -74,7 +125,7 @@ def dset_sheet(dataset, ws):
                 ws.cell('%s%s'%(col_idx, row_number)).value = unicode(col)
                 style = ws.get_style('%s%s' % (col_idx, row_number))
                 style.font.bold = True
-                ws.freeze_panes = '%s%s' % (col_idx, row_number)
+                ws.freeze_panes = '%s%s' % (frzn_col_idx, row_number)
 
 
             # bold separators

tablib/formats/_yaml.py

@@ -19,26 +19,26 @@ import tablib
 
 
 title = 'yaml'
-extentions = ('yaml', 'yml')
+extensions = ('yaml', 'yml')
 
 
 
 def export_set(dataset):
     """Returns YAML representation of Dataset."""
 
-    return yaml.dump(dataset._package(ordered=False))
+    return yaml.safe_dump(dataset._package(ordered=False))
 
 
 def export_book(databook):
     """Returns YAML representation of Databook."""
-    return yaml.dump(databook._package())
+    return yaml.safe_dump(databook._package(ordered=False))
 
 
 def import_set(dset, in_stream):
     """Returns dataset from YAML stream."""
 
     dset.wipe()
-    dset.dict = yaml.load(in_stream)
+    dset.dict = yaml.safe_load(in_stream)
 
 
 def import_book(dbook, in_stream):
@@ -55,10 +55,11 @@ def import_book(dbook, in_stream):
 def detect(stream):
     """Returns True if given stream is valid YAML."""
     try:
-        _yaml = yaml.load(stream)
+        _yaml = yaml.safe_load(stream)
         if isinstance(_yaml, (list, tuple, dict)):
             return True
         else:
             return False
-    except yaml.parser.ParserError:
-        return False
+    except (yaml.parser.ParserError, yaml.reader.ReaderError,
+            yaml.scanner.ScannerError):
+        return False

tablib/packages/markup.py

@@ -67,7 +67,7 @@ class element:
     def render( self, tag, single, between, kwargs ):
         """Append the actual tags to content."""
 
-        out = "<%s" % tag
+        out = u"<%s" % tag
         for key, value in kwargs.iteritems( ):
             if value is not None:               # when value is None that means stuff like <... checked>
                 key = key.strip('_')            # strip this so class_ will mean class, etc.
@@ -75,16 +75,16 @@ class element:
                     key = 'http-equiv'
                 elif key == 'accept_charset':
                     key = 'accept-charset'
-                out = "%s %s=\"%s\"" % ( out, key, escape( value ) )
+                out = u"%s %s=\"%s\"" % ( out, key, escape( value ) )
             else:
-                out = "%s %s" % ( out, key )
+                out = u"%s %s" % ( out, key )
         if between is not None:
-            out = "%s>%s</%s>" % ( out, between, tag )
+            out = u"%s>%s</%s>" % ( out, between, tag )
         else:
             if single:
-                out = "%s />" % out
+                out = u"%s />" % out
             else:
-                out = "%s>" % out
+                out = u"%s>" % out
         if self.parent is not None:
             self.parent.content.append( out )
         else:

tablib/packages/odf3/opendocument.py

@@ -39,7 +39,7 @@ UNIXPERMS = 0o100644 << 16  # -rw-r--r--
 IS_FILENAME = 0
 IS_IMAGE = 1
 # We need at least Python 2.2
-assert sys.version_info[0]>=2 and sys.version_info[1] >= 2
+assert sys.version_info[0]>=2
 
 #sys.setrecursionlimit(100)
 #The recursion limit is set conservative so mistakes like

tablib/packages/openpyxl3/reader/excel.py

@@ -58,11 +58,15 @@ def load_workbook(filename, use_iterators = False):
 
     """
 
-    if isinstance(filename, file):
+    try:
         # fileobject must have been opened with 'rb' flag
         # it is required by zipfile
         if 'b' not in filename.mode:
             raise OpenModeError("File-object must be opened in binary mode")
+    except AttributeError:
+        # filename is not an object
+        # it doesn't have mode attribute
+        pass
 
     try:
         archive = ZipFile(filename, 'r', ZIP_DEFLATED)

tablib/packages/xlrd/biffh.py

@@ -0,0 +1,639 @@
+# -*- 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]

tablib/packages/xlrd/compdoc.py

@@ -0,0 +1,358 @@
+# -*- 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)
+
+# ==========================================================================================

tablib/packages/xlrd/doc/compdoc.html

@@ -0,0 +1,69 @@
+<!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>

tablib/packages/xlrd/examples/xlrdnameAPIdemo.py

@@ -0,0 +1,178 @@
+# -*- 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)

tablib/packages/xlrd/licences.py

@@ -0,0 +1,77 @@
+# -*- 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.
+ */
+"""

tablib/packages/xlrd/timemachine.py

@@ -0,0 +1,44 @@
+# -*- 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

tablib/packages/xlrd/xldate.py

@@ -0,0 +1,171 @@
+# -*- 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:])
+        )

tablib/packages/xlrd3/biffh.py

@@ -0,0 +1,620 @@
+# 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)

tablib/packages/xlrd3/compdoc.py

@@ -0,0 +1,346 @@
+# 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)

tablib/packages/xlrd3/xfcell.py

@@ -0,0 +1,276 @@
+# 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)

tablib/packages/xlrd3/xfconst.py

@@ -0,0 +1,84 @@
+# 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
+
+
+
+
+

tablib/packages/xlrd3/xldate.py

@@ -0,0 +1,167 @@
+# 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:])
+        )

tablib/packages/xlwt3/ExcelFormula.py

@@ -4,7 +4,7 @@ from .antlr import ANTLRException
 
 
 class Formula(object):
-    __slots__ = ["__init__",  "__s", "__parser", "__sheet_refs", "__xcall_refs"]
+    __slots__ = ["__s", "__parser", "__sheet_refs", "__xcall_refs"]
 
 
     def __init__(self, s):

test_tablib.py

@@ -1,13 +1,14 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
-
 """Tests for Tablib."""
 
+import json
 import unittest
 import sys
-
+import os
 import tablib
-from tablib.compat import markup
+from tablib.compat import markup, unicode, is_py3
+
 
 
 
@@ -28,7 +29,7 @@ class TablibTestCase(unittest.TestCase):
         self.george = ('George', 'Washington', 67)
         self.tom = ('Thomas', 'Jefferson', 50)
 
-        self.founders = tablib.Dataset(headers=self.headers)
+        self.founders = tablib.Dataset(headers=self.headers, title='Founders')
         self.founders.append(self.john)
         self.founders.append(self.george)
         self.founders.append(self.tom)
@@ -58,6 +59,18 @@ class TablibTestCase(unittest.TestCase):
 
         self.assertRaises(tablib.InvalidDimensions, data.append, new_row)
 
+    def test_set_headers_with_incorrect_dimension(self):
+        """Verify headers correctly detects mismatch of number of
+        headers and data.
+        """
+
+        data.append(self.john)
+
+        def set_header_callable():
+            data.headers = ['first_name']
+
+        self.assertRaises(tablib.InvalidDimensions, set_header_callable)
+
 
     def test_add_column(self):
         """Verify adding column works with/without headers."""
@@ -92,10 +105,57 @@ class TablibTestCase(unittest.TestCase):
         self.assertEqual(data.height, len(new_col))
 
 
+    def test_add_column_with_header_ignored(self):
+        """Verify append_col() ignores the header if data.headers has
+        not previously been set
+        """
+
+        new_col = ('reitz', 'monke')
+
+        data.append_col(new_col, header='first_name')
+
+        self.assertEqual(data[0], tuple([new_col[0]]))
+        self.assertEqual(data.width, 1)
+        self.assertEqual(data.height, len(new_col))
+        self.assertEqual(data.headers, None)
+
+
+    def test_add_column_with_header_and_headers_only_exist(self):
+        """Verify append_col() with header correctly detects mismatch when
+        headers exist but there is no existing row data
+        """
+
+        data.headers = ['first_name']
+        #no data
+
+        new_col = ('allen')
+
+        def append_col_callable():
+            data.append_col(new_col, header='middle_name')
+
+        self.assertRaises(tablib.InvalidDimensions, append_col_callable)
+
+
+    def test_add_column_with_header_and_data_exists(self):
+        """Verify append_col() works when headers and rows exists"""
+
+        data.headers = self.headers
+        data.append(self.john)
+
+        new_col = [10];
+
+        data.append_col(new_col, header='age')
+
+        self.assertEqual(data.height, 1)
+        self.assertEqual(data.width, len(self.john) + 1)
+        self.assertEqual(data['age'], new_col)
+        self.assertEqual(len(data.headers), len(self.headers) + 1)
+
+
     def test_add_callable_column(self):
         """Verify adding column with values specified as callable."""
 
-        new_col = [lambda x: x[0]]
+        new_col = lambda x: x[0]
 
         self.founders.append_col(new_col, header='first_again')
 
@@ -113,6 +173,22 @@ class TablibTestCase(unittest.TestCase):
             [self.john[2], self.george[2], self.tom[2]])
 
 
+    def test_get_col(self):
+        """Verify getting columns by index"""
+
+        self.assertEqual(
+            self.founders.get_col(list(self.headers).index('first_name')),
+            [self.john[0], self.george[0], self.tom[0]])
+
+        self.assertEqual(
+            self.founders.get_col(list(self.headers).index('last_name')),
+            [self.john[1], self.george[1], self.tom[1]])
+
+        self.assertEqual(
+            self.founders.get_col(list(self.headers).index('gpa')),
+            [self.john[2], self.george[2], self.tom[2]])
+
+
     def test_data_slicing(self):
         """Verify slicing by data."""
 
@@ -172,9 +248,9 @@ class TablibTestCase(unittest.TestCase):
 
 
     def test_tsv_export(self):
-        """Verify exporting dataset object as CSV."""
+        """Verify exporting dataset object as TSV."""
 
-        # Build up the csv string with headers first, followed by each row
+        # Build up the tsv string with headers first, followed by each row
         tsv = ''
         for col in self.headers:
             tsv += col + '\t'
@@ -209,10 +285,36 @@ class TablibTestCase(unittest.TestCase):
         self.assertEqual(html, self.founders.html)
 
 
-    def test_unicode_append(self):
-        """Passes in a single unicode charecter and exports."""
+    def test_html_export_none_value(self):
+        """HTML export"""
+
+        html = markup.page()
+        html.table.open()
+        html.thead.open()
+
+        html.tr(markup.oneliner.th(['foo','', 'bar']))
+        html.thead.close()
+
+        html.tr(markup.oneliner.td(['foo','', 'bar']))
+
+        html.table.close()
+        html = str(html)
+
+        headers = ['foo', None, 'bar'];
+        d = tablib.Dataset(['foo', None, 'bar'], headers=headers)
+
+        self.assertEqual(html, d.html)
+
+
+    def test_unicode_append(self):
+        """Passes in a single unicode character and exports."""
+
+        if is_py3:
+            new_row = ('å', 'é')
+        else:
+            exec("new_row = (u'å', u'é')")
+
 
-        new_row = ('å', 'é')
         data.append(new_row)
 
         data.json
@@ -226,7 +328,7 @@ class TablibTestCase(unittest.TestCase):
 
 
     def test_book_export_no_exceptions(self):
-        """Test that varoius exports don't error out."""
+        """Test that various exports don't error out."""
 
         book = tablib.Databook()
         book.add_sheet(data)
@@ -248,7 +350,7 @@ class TablibTestCase(unittest.TestCase):
 
         data.json = _json
 
-        self.assertEqual(_json, data.json)
+        self.assertEqual(json.loads(_json), json.loads(data.json))
 
 
     def test_json_import_book(self):
@@ -262,7 +364,7 @@ class TablibTestCase(unittest.TestCase):
 
         book.json = _json
 
-        self.assertEqual(_json, book.json)
+        self.assertEqual(json.loads(_json), json.loads(book.json))
 
 
     def test_yaml_import_set(self):
@@ -319,6 +421,22 @@ class TablibTestCase(unittest.TestCase):
         self.assertEqual(_csv, data.csv)
 
 
+    def test_csv_import_set_with_newlines(self):
+        """Generate and import CSV set serialization when row values have
+        newlines."""
+        data.append(('Markdown\n=======',
+                     'A cool language\n\nwith paragraphs'))
+        data.append(('reStructedText\n==============',
+                     'Another cool language\n\nwith paragraphs'))
+        data.headers = ('title', 'body')
+
+        _csv = data.csv
+
+        data.csv = _csv
+
+        self.assertEqual(_csv, data.csv)
+
+
     def test_tsv_import_set(self):
         """Generate and import TSV set serialization."""
         data.append(self.john)
@@ -380,12 +498,14 @@ class TablibTestCase(unittest.TestCase):
         """Test YAML format detection."""
 
         _yaml = '- {age: 90, first_name: John, last_name: Adams}'
+        _tsv = 'foo\tbar'
         _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))
+        self.assertFalse(tablib.formats.yaml.detect(_tsv))
 
 
     def test_auto_format_detect(self):
@@ -394,10 +514,12 @@ class TablibTestCase(unittest.TestCase):
         _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'
+        _tsv = '1\t2\t3\n4\t5\t6\n7\t8\t9\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(_tsv)[0], tablib.formats.tsv)
         self.assertEqual(tablib.detect(_json)[0], tablib.formats.json)
         self.assertEqual(tablib.detect(_bunk)[0], None)
 
@@ -458,6 +580,7 @@ class TablibTestCase(unittest.TestCase):
         """Sort columns."""
 
         sorted_data = self.founders.sort(col="first_name")
+        self.assertEqual(sorted_data.title, 'Founders')
 
         first_row = sorted_data[0]
         second_row = sorted_data[2]
@@ -512,5 +635,89 @@ class TablibTestCase(unittest.TestCase):
 
         data.csv
 
+    def test_csv_column_select(self):
+        """Build up a CSV and test selecting a column"""
+
+        data = tablib.Dataset()
+        data.csv = self.founders.csv
+
+        headers = data.headers
+        self.assertTrue(isinstance(headers[0], unicode))
+
+        orig_first_name = self.founders[self.headers[0]]
+        csv_first_name = data[headers[0]]
+        self.assertEqual(orig_first_name, csv_first_name)
+
+
+    def test_csv_column_delete(self):
+        """Build up a CSV and test deleting a column"""
+
+        data = tablib.Dataset()
+        data.csv = self.founders.csv
+
+        target_header = data.headers[0]
+        self.assertTrue(isinstance(target_header, unicode))
+
+        del data[target_header]
+
+        self.assertTrue(target_header not in data.headers)
+
+    def test_csv_column_sort(self):
+        """Build up a CSV and test sorting a column by name"""
+
+        data = tablib.Dataset()
+        data.csv = self.founders.csv
+
+        orig_target_header = self.founders.headers[1]
+        target_header = data.headers[1]
+
+        self.founders.sort(orig_target_header)
+        data.sort(target_header)
+
+        self.assertEqual(self.founders[orig_target_header], data[target_header])
+
+    def test_unicode_renders_markdown_table(self):
+        # add another entry to test right field width for
+        # integer
+        self.founders.append(('Old', 'Man', 100500))
+
+        self.assertEqual(
+            """
+first_name|last_name |gpa   
+----------|----------|------
+John      |Adams     |90    
+George    |Washington|67    
+Thomas    |Jefferson |50    
+Old       |Man       |100500
+""".strip(),
+            unicode(self.founders)
+        )
+
+
+    def test_databook_add_sheet_accepts_only_dataset_instances(self):
+        class NotDataset(object):
+            def append(self, item):
+                pass
+
+        dataset = NotDataset()
+        dataset.append(self.john)
+
+        self.assertRaises(tablib.InvalidDatasetType, book.add_sheet, dataset)
+
+
+    def test_databook_add_sheet_accepts_dataset_subclasses(self):
+        class DatasetSubclass(tablib.Dataset):
+            pass
+
+        # just checking if subclass of tablib.Dataset can be added to Databook
+        dataset = DatasetSubclass()
+        dataset.append(self.john)
+        dataset.append(self.tom)
+
+        try:
+            book.add_sheet(dataset)
+        except tablib.InvalidDatasetType:
+            self.fail("Subclass of tablib.Dataset should be accepted by Databook.add_sheet")
+
 if __name__ == '__main__':
     unittest.main()

tox.ini

@@ -1,11 +1,15 @@
+# Tox (http://tox.testrun.org/) is a tool for running tests
+# in multiple virtualenvs. This configuration file will run the
+# test suite on all supported python versions. To use it, "pip install tox"
+# and then run "tox" from this directory.
+
 [tox]
-envlist = py25,py26,py27,py3
+envlist = py26, py27, py32, py33, pypy
 
 [testenv]
-commands=py.test --junitxml=junit-{envname}.xml
-deps = pytest
-
-
-[testenv:py3]
-basepython=/usr/bin/python3
-simplejson = pytest
+commands = python setup.py test
+deps =
+    pytest
+    PyYAML
+    xlrd
+    omnijson