Expose 'read_only' parameter for 'import_set' and 'import_book' (#483)

* Upload coverage from GHA

* Fix PytestConfigWarning: Unknown config option: python_paths

.coveragerc

@@ -0,0 +1,10 @@
+# .coveragerc to control coverage.py
+
+[report]
+# Regexes for lines to exclude from consideration
+exclude_lines =
+    # Have to re-enable the standard pragma:
+    pragma: no cover
+
+    # Don't complain if non-runnable code isn't run:
+    if __name__ == .__main__.:

.github/CONTRIBUTING.md

@@ -0,0 +1,10 @@
+[![Jazzband](https://jazzband.co/static/img/jazzband.svg)](https://jazzband.co/)
+
+This is a [Jazzband](https://jazzband.co/) project. By contributing you agree to abide
+by the [Contributor Code of Conduct](https://jazzband.co/about/conduct) and follow the
+[guidelines](https://jazzband.co/about/guidelines).
+
+If you'd like to contribute, simply fork 
+[the repository](https://github.com/jazzband/tablib), commit your changes to a feature
+branch, and send a pull request to `master`. Make sure you add yourself to
+[AUTHORS](https://github.com/jazzband/tablib/blob/master/AUTHORS).

.github/workflows/docs-lint.yml

@@ -0,0 +1,46 @@
+name: Docs and lint
+
+on: [push, pull_request]
+
+env:
+  FORCE_COLOR: 1
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        env:
+        - TOXENV: docs
+        - TOXENV: lint
+
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+
+      - name: Get pip cache dir
+        id: pip-cache
+        run: |
+          echo "::set-output name=dir::$(pip cache dir)"
+
+      - name: Cache
+        uses: actions/cache@v2
+        with:
+          path: ${{ steps.pip-cache.outputs.dir }}
+          key:
+            ${{ matrix.os }}-${{ matrix.python-version }}-v1-${{ hashFiles('**/setup.py') }}
+          restore-keys: |
+            ${{ matrix.os }}-${{ matrix.python-version }}-v1-
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install --upgrade tox
+
+      - name: Tox
+        run: tox
+        env: ${{ matrix.env }}

.github/workflows/release.yml

@@ -0,0 +1,56 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - master
+  release:
+    types:
+      - published
+
+jobs:
+  build:
+    if: github.repository == 'jazzband/tablib'
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+
+      - name: Get pip cache dir
+        id: pip-cache
+        run: |
+          echo "::set-output name=dir::$(pip cache dir)"
+
+      - name: Cache
+        uses: actions/cache@v2
+        with:
+          path: ${{ steps.pip-cache.outputs.dir }}
+          key: release-${{ hashFiles('**/setup.py') }}
+          restore-keys: |
+            release-
+
+      - name: Install dependencies
+        run: |
+          python -m pip install -U pip
+          python -m pip install -U setuptools twine wheel
+
+      - name: Build package
+        run: |
+          python setup.py --version
+          python setup.py sdist --format=gztar bdist_wheel
+          twine check dist/*
+
+      - name: Upload packages to Jazzband
+        if: github.event.action == 'published'
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          user: jazzband
+          password: ${{ secrets.JAZZBAND_RELEASE_KEY }}
+          repository_url: https://jazzband.co/projects/tablib/upload

.github/workflows/test.yml

@@ -0,0 +1,53 @@
+name: Test
+
+on: [push, pull_request]
+
+env:
+  FORCE_COLOR: 1
+
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: [3.6, 3.7, 3.8, 3.9]
+        os: [ubuntu-latest, macOS-latest, windows-latest]
+
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Get pip cache dir
+      id: pip-cache
+      run: |
+        echo "::set-output name=dir::$(pip cache dir)"
+
+    - name: Cache
+      uses: actions/cache@v2
+      with:
+        path: ${{ steps.pip-cache.outputs.dir }}
+        key:
+          ${{ matrix.os }}-${{ matrix.python-version }}-v1-${{ hashFiles('**/setup.py') }}
+        restore-keys: |
+          ${{ matrix.os }}-${{ matrix.python-version }}-v1-
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install --upgrade tox
+        python -m pip install  -e .
+
+    - name: Tox tests
+      shell: bash
+      run: |
+        tox -e py
+
+    - name: Upload coverage
+      uses: codecov/codecov-action@v1
+      with:
+        name: ${{ matrix.os }} Python ${{ matrix.python-version }}

.gitignore

@@ -29,3 +29,15 @@ junit-py27.xml
 
 # pyenv noise
 .python-version
+tablib.egg-info/*
+
+# Coverage
+.coverage
+htmlcov
+
+# setuptools noise
+.eggs
+*.egg-info
+
+# generated by setuptools-scm
+/src/tablib/_version.py

.pre-commit-config.yaml

@@ -0,0 +1,25 @@
+repos:
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.7.3
+    hooks:
+      - id: pyupgrade
+        args: ["--py36-plus"]
+
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.6.4
+    hooks:
+      - id: isort
+        additional_dependencies: [toml]
+
+  - repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.7.0
+    hooks:
+      - id: python-check-blanket-noqa
+      - id: rst-backticks
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.3.0
+    hooks:
+      - id: check-merge-conflict
+      - id: check-toml
+      - id: check-yaml

.travis.yml

@@ -1,10 +0,0 @@
-language: python
-cache: pip
-python:
-  - 2.7
-  - 3.4
-  - 3.5
-  - 3.6
-install:
-  - pip install -r requirements.txt
-script: python test_tablib.py

AUTHORS

@@ -1,38 +1,32 @@
-Tablib is written and maintained by Kenneth Reitz and
-various contributors:
+Tablib was originally written by Kenneth Reitz and is now maintained
+by the Jazzband GitHub team.
 
-Development Lead
-````````````````
+Here is a list of passed and present much-appreciated contributors:
 
-- Kenneth Reitz <me@kennethreitz.org>
-
-
-Core Contributors
-`````````````````
-
-- Iuri de Silvio <iurisilvio@gmail.com>
-
-Patches and Suggestions
-```````````````````````
-
-- Luke Lee
-- Josh Ourisman
-- Luca Beltrame
-- Benjamin Wohlwend
-- Erik Youngren
-- Mark Rogers
-- Mark Walling
-- Mike Waldner
-- Joel Friedly
-- Jakub Janoszek
-- Marc Abramowitz
-- Alex Gaynor
-- James Douglass
-- Tommy Anthony
-- Rabin Nankhwa
-- Marco Dallagiacoma
-- Mathias Loesch
-- Tushar Makkar
-- Andrii Soldatenko
-- Bruno Soares
-- Tsuyoshi Hombashi
+    Alex Gaynor
+    Andrii Soldatenko
+    Benjamin Wohlwend
+    Bruno Soares
+    Claude Paroz
+    Daniel Santos
+    Erik Youngren
+    Hugo van Kemenade
+    Iuri de Silvio
+    Jakub Janoszek
+    James Douglass
+    Joel Friedly
+    Josh Ourisman
+    Kenneth Reitz
+    Luca Beltrame
+    Luke Lee
+    Marc Abramowitz
+    Marco Dallagiacoma
+    Mark Rogers
+    Mark Walling
+    Mathias Loesch
+    Mike Waldner
+    Peyman Salehi
+    Rabin Nankhwa
+    Tommy Anthony
+    Tsuyoshi Hombashi
+    Tushar Makkar

HACKING

@@ -1,14 +0,0 @@
-Where possible, please follow PEP8 with regard to coding style. Sometimes the line
-length restriction is too hard to follow, so don't bend over backwards there.
-
-Triple-quotes should always be """, single quotes are ' unless using "
-would result in less escaping within the string.
-
-All modules, functions, and methods should be well documented reStructuredText for
-Sphinx AutoDoc.
-
-All functionality should be available in pure Python. Optional C (via Cython)
-implementations may be written for performance reasons, but should never
-replace the Python implementation.
-
-Lastly, don't take yourself too seriously :)

HISTORY.md

@@ -0,0 +1,341 @@
+# History
+
+## Unreleased
+
+### Breaking changes
+
+- Dropped Python 3.5 support
+
+### Improvements
+
+- Added Python 3.9 support
+- Added read_only option to xlsx file reader (#482).
+
+### Bugfixes
+
+- Prevented crash in rst export with only-space strings (#469).
+
+## 2.0.0 (2020-05-16)
+
+### Breaking changes
+
+- The `Row.lpush/rpush` logic was reversed. `lpush` was appending while `rpush`
+  and `append` were prepending. This was fixed (reversed behavior). If you
+  counted on the broken behavior, please update your code (#453).
+
+### Bugfixes
+
+- Fixed minimal openpyxl dependency version to 2.6.0 (#457).
+- Dates from xls files are now read as Python datetime objects (#373).
+- Allow import of "ragged" xlsx files (#465).
+
+### Improvements
+
+- When importing an xlsx file, Tablib will now read cell values instead of formulas (#462).
+
+## 1.1.0 (2020-02-13)
+
+### Deprecations
+
+- Upcoming breaking change in Tablib 2.0.0: the `Row.lpush/rpush` logic is reversed.
+  `lpush` is appending while `rpush` and `append` are prepending. The broken behavior
+  will remain in Tablib 1.x and will be fixed (reversed) in Tablib 2.0.0 (#453). If you
+  count on the broken behavior, please update your code when you upgrade to Tablib 2.x.
+
+### Improvements
+
+- Tablib is now able to import CSV content where not all rows have the same
+  length. Missing columns on any line receive the empty string (#226).
+
+## 1.0.0 (2020-01-13)
+
+### Breaking changes
+
+- Dropped Python 2 support
+- Dependencies are now all optional. To install `tablib` as before with all
+  possible supported formats, run `pip install tablib[all]`
+
+### Improvements
+
+- Formats can now be dynamically registered through the
+  `tablib.formats.registry.refister` API (#256).
+- Tablib methods expecting data input (`detect_format`, `import_set`,
+  `Dataset.load`, `Databook.load`) now accepts file-like objects in addition
+  to raw strings and bytestrings (#440).
+
+### Bugfixes
+
+- Fixed a crash when exporting an empty string with the ReST format (#368)
+- Error cells from imported .xls files contain now the error string (#202)
+
+## 0.14.0 (2019-10-19)
+
+### Deprecations
+
+- The 0.14.x series will be the last to support Python 2
+
+### Breaking changes
+
+- Dropped Python 3.4 support
+
+### Improvements
+
+- Added Python 3.7 and 3.8 support
+- The project is now maintained by the Jazzband team, https://jazzband.co
+- Improved format autodetection and added autodetection for the odf format.
+- Added search to all documentation pages
+- Open xlsx workbooks in read-only mode (#316)
+- Unpin requirements
+- Only install backports.csv on Python 2
+
+### Bugfixes
+
+- Fixed `DataBook().load` parameter ordering (first stream, then format).
+- Fixed a regression for xlsx exports where non-string values were forced to
+  strings (#314)
+- Fixed xlsx format detection (which was often detected as `xls` format)
+
+## 0.13.0 (2019-03-08)
+
+- Added reStructuredText output capability (#336)
+- Added Jira output capability
+- Stopped calling openpyxl deprecated methods (accessing cells, removing sheets)
+  (openpyxl minimal version is now 2.4.0)
+- Fixed a circular dependency issue in JSON output (#332)
+- Fixed Unicode error for the CSV export on Python 2 (#215)
+- Removed usage of optional `ujson` (#311)
+- Dropped Python 3.3 support
+
+## 0.12.1 (2017-09-01)
+
+- Favor `Dataset.export(<format>)` over `Dataset.<format>` syntax in docs
+- Make Panda dependency optional
+
+## 0.12.0 (2017-08-27)
+
+- Add initial Panda DataFrame support
+- Dropped Python 2.6 support
+
+## 0.11.5 (2017-06-13)
+
+- Use `yaml.safe_load` for importing yaml.
+
+## 0.11.4 (2017-01-23)
+
+- Use built-in `json` package if available
+- Support Python 3.5+ in classifiers
+
+### Bugfixes
+
+- Fixed textual representation for Dataset with no headers
+- Handle decimal types
+
+## 0.11.3 (2016-02-16)
+
+- Release fix.
+
+## 0.11.2 (2016-02-16)
+
+### Bugfixes
+
+- Fix export only formats.
+- Fix for xlsx output.
+
+## 0.11.1 (2016-02-07)
+
+### Bugfixes
+
+- Fixed packaging error on Python 3.
+
+
+## 0.11.0 (2016-02-07)
+
+### New Formats!
+
+- Added LaTeX table export format (`Dataset.latex`).
+- Support for dBase (DBF) files (`Dataset.dbf`).
+
+### Improvements
+
+- New import/export interface (`Dataset.export()`, `Dataset.load()`).
+- CSV custom delimiter support (`Dataset.export('csv', delimiter='$')`).
+- Adding ability to remove duplicates to all rows in a dataset (`Dataset.remove_duplicates()`).
+- Added a mechanism to avoid `datetime.datetime` issues when serializing data.
+- New `detect_format()` function (mostly for internal use).
+- Update the vendored unicodecsv to fix `None` handling.
+- Only freeze the headers row, not the headers columns (xls).
+
+### Breaking Changes
+
+- `detect()` function removed.
+
+### Bugfixes
+
+- Fix XLSX import.
+- Bugfix for `Dataset.transpose().transpose()`.
+
+
+## 0.10.0 (2014-05-27)
+
+* Unicode Column Headers
+* ALL the bugfixes!
+
+## 0.9.11 (2011-06-30)
+
+* Bugfixes
+
+## 0.9.10 (2011-06-22)
+
+* Bugfixes
+
+## 0.9.9 (2011-06-21)
+
+* Dataset API Changes
+* `stack_rows` => `stack`, `stack_columns` => `stack_cols`
+* 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`
+
+## 0.9.8 (2011-05-22)
+
+* OpenDocument Spreadsheet support (.ods)
+* Full Unicode TSV support
+
+
+## 0.9.7 (2011-05-12)
+
+* Full XLSX Support!
+* Pickling Bugfix
+* Compat Module
+
+
+## 0.9.6 (2011-05-12)
+
+* `seperators` renamed to `separators`
+* Full unicode CSV support
+
+
+## 0.9.5 (2011-03-24)
+
+* Python 3.1, Python 3.2 Support (same code base!)
+* Formatter callback support
+* Various bug fixes
+
+
+
+## 0.9.4 (2011-02-18)
+
+* Python 2.5 Support!
+* Tox Testing for 2.5, 2.6, 2.7
+* AnyJSON Integrated
+* OrderedDict support
+* Caved to community pressure (spaces)
+
+
+## 0.9.3 (2011-01-31)
+
+* Databook duplication leak fix.
+* HTML Table output.
+* Added column sorting.
+
+
+## 0.9.2 (2010-11-17)
+
+* Transpose method added to Datasets.
+* New frozen top row in Excel output.
+* Pickling support for Datasets and Rows.
+* Support for row/column stacking.
+
+
+## 0.9.1 (2010-11-04)
+
+* Minor reference shadowing bugfix.
+
+
+## 0.9.0 (2010-11-04)
+
+* Massive documentation update!
+* Tablib.org!
+* Row tagging and Dataset filtering!
+* Column insert/delete support
+* Column append API change (header required)
+* Internal Changes (Row object and use thereof)
+
+
+## 0.8.5 (2010-10-06)
+
+* New import system. All dependencies attempt to load from site-packages,
+  then fallback on tenderized modules.
+
+
+## 0.8.4 (2010-10-04)
+
+* Updated XLS output: Only wrap if '\\n' in cell.
+
+
+## 0.8.3 (2010-10-04)
+
+* Ability to append new column passing a callable
+  as the value that will be applied to every row.
+
+
+## 0.8.2 (2010-10-04)
+
+* Added alignment wrapping to written cells.
+* Added separator support to XLS.
+
+
+## 0.8.1 (2010-09-28)
+
+* Packaging Fix
+
+
+## 0.8.0 (2010-09-25)
+
+* New format plugin system!
+* Imports! ELEGANT Imports!
+* Tests. Lots of tests.
+
+
+## 0.7.1 (2010-09-20)
+
+* Reverting methods back to properties.
+* Windows bug compensated in documentation.
+
+
+## 0.7.0 (2010-09-20)
+
+* Renamed DataBook Databook for consistency.
+* Export properties changed to methods (XLS filename / StringIO bug).
+* Optional Dataset.xls(path='filename') support (for writing on windows).
+* Added utf-8 on the worksheet level.
+
+
+## 0.6.4 (2010-09-19)
+
+* Updated unicode export for XLS.
+* More exhaustive unit tests.
+
+
+## 0.6.3 (2010-09-14)
+
+* Added Dataset.append() support for columns.
+
+
+## 0.6.2 (2010-09-13)
+
+* Fixed Dataset.append() error on empty dataset.
+* Updated Dataset.headers property w/ validation.
+* Added Testing Fixtures.
+
+## 0.6.1 (2010-09-12)
+
+* Packaging hotfixes.
+
+
+## 0.6.0 (2010-09-11)
+
+* Public Release.
+* Export Support for XLS, JSON, YAML, and CSV.
+* DataBook Export for XLS, JSON, and YAML.
+* Python Dict Property Support.

HISTORY.rst

@@ -1,256 +0,0 @@
-History
--------
-
-0.11.5 (2017-06-13)
-+++++++++++++++++++
-
-- Use ``yaml.safe_load`` for importing yaml.
-
-0.11.4 (2017-01-23)
-+++++++++++++++++++
-
-- Use built-in `json` package if available
-- Support Python 3.5+ in classifiers
-
-** Bugfixes **
-
-- Fixed textual representation for Dataset with no headers
-- Handle decimal types
-
-0.11.3 (2016-02-16)
-+++++++++++++++++++
-
-- Release fix.
-
-0.11.2 (2016-02-16)
-+++++++++++++++++++
-
-**Bugfixes**
-
-- Fix export only formats.
-- Fix for xlsx output.
-
-0.11.1 (2016-02-07)
-+++++++++++++++++++
-
-**Bugfixes**
-
-- Fixed packaging error on Python 3.
-
-
-0.11.0 (2016-02-07)
-+++++++++++++++++++
-
-**New Formats!**
-
-- Added LaTeX table export format (``Dataset.latex``).
-- Support for dBase (DBF) files (``Dataset.dbf``).
-
-**Improvements**
-
-- New import/export interface (``Dataset.export()``, ``Dataset.load()``).
-- CSV custom delimiter support (``Dataset.export('csv', delimiter='$')``).
-- Adding ability to remove duplicates to all rows in a dataset (``Dataset.remove_duplicates()``).
-- Added a mechanism to avoid ``datetime.datetime`` issues when serializing data.
-- New ``detect_format()`` function (mostly for internal use).
-- Update the vendored unicodecsv to fix ``None`` handling.
-- Only freeze the headers row, not the headers columns (xls).
-
-**Breaking Changes**
-
-- ``detect()`` function removed.
-
-**Bugfixes**
-
-- Fix XLSX import.
-- Bugfix for ``Dataset.transpose().transpose()``.
-
-
-0.10.0 (2014-05-27)
-+++++++++++++++++++
-
-* Unicode Column Headers
-* ALL the bugfixes!
-
-0.9.11 (2011-06-30)
-+++++++++++++++++++
-
-* Bugfixes
-
-0.9.10 (2011-06-22)
-+++++++++++++++++++
-
-* Bugfixes
-
-0.9.9 (2011-06-21)
-++++++++++++++++++
-
-* Dataset API Changes
-* ``stack_rows`` => ``stack``, ``stack_columns`` => ``stack_cols``
-* 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``
-
-0.9.8 (2011-05-22)
-++++++++++++++++++
-
-* OpenDocument Spreadsheet support (.ods)
-* Full Unicode TSV support
-
-
-0.9.7 (2011-05-12)
-++++++++++++++++++
-
-* Full XLSX Support!
-* Pickling Bugfix
-* Compat Module
-
-
-0.9.6 (2011-05-12)
-++++++++++++++++++
-
-* ``seperators`` renamed to ``separators``
-* Full unicode CSV support
-
-
-0.9.5 (2011-03-24)
-++++++++++++++++++
-
-* Python 3.1, Python 3.2 Support (same code base!)
-* Formatter callback support
-* Various bug fixes
-
-
-
-0.9.4 (2011-02-18)
-++++++++++++++++++
-
-* Python 2.5 Support!
-* Tox Testing for 2.5, 2.6, 2.7
-* AnyJSON Integrated
-* OrderedDict support
-* Caved to community pressure (spaces)
-
-
-0.9.3 (2011-01-31)
-++++++++++++++++++
-
-* Databook duplication leak fix.
-* HTML Table output.
-* Added column sorting.
-
-
-0.9.2 (2010-11-17)
-++++++++++++++++++
-
-* Transpose method added to Datasets.
-* New frozen top row in Excel output.
-* Pickling support for Datasets and Rows.
-* Support for row/column stacking.
-
-
-0.9.1 (2010-11-04)
-++++++++++++++++++
-
-* Minor reference shadowing bugfix.
-
-
-0.9.0 (2010-11-04)
-++++++++++++++++++
-
-* Massive documentation update!
-* Tablib.org!
-* Row tagging and Dataset filtering!
-* Column insert/delete support
-* Column append API change (header required)
-* Internal Changes (Row object and use thereof)
-
-
-0.8.5 (2010-10-06)
-++++++++++++++++++
-
-* New import system. All dependencies attempt to load from site-packages,
-  then fallback on tenderized modules.
-
-
-0.8.4 (2010-10-04)
-++++++++++++++++++
-
-* Updated XLS output: Only wrap if '\\n' in cell.
-
-
-0.8.3 (2010-10-04)
-++++++++++++++++++
-
-* Ability to append new column passing a callable
-  as the value that will be applied to every row.
-
-
-0.8.2 (2010-10-04)
-++++++++++++++++++
-
-* Added alignment wrapping to written cells.
-* Added separator support to XLS.
-
-
-0.8.1 (2010-09-28)
-++++++++++++++++++
-
-* Packaging Fix
-
-
-0.8.0 (2010-09-25)
-++++++++++++++++++
-
-* New format plugin system!
-* Imports! ELEGANT Imports!
-* Tests. Lots of tests.
-
-
-0.7.1 (2010-09-20)
-++++++++++++++++++
-
-* Reverting methods back to properties.
-* Windows bug compensated in documentation.
-
-
-0.7.0 (2010-09-20)
-++++++++++++++++++
-
-* Renamed DataBook Databook for consistency.
-* Export properties changed to methods (XLS filename / StringIO bug).
-* Optional Dataset.xls(path='filename') support (for writing on windows).
-* Added utf-8 on the worksheet level.
-
-
-0.6.4 (2010-09-19)
-++++++++++++++++++
-
-* Updated unicode export for XLS.
-* More exhaustive unit tests.
-
-
-0.6.3 (2010-09-14)
-++++++++++++++++++
-* Added Dataset.append() support for columns.
-
-
-0.6.2 (2010-09-13)
-++++++++++++++++++
-* Fixed Dataset.append() error on empty dataset.
-* Updated Dataset.headers property w/ validation.
-* Added Testing Fixtures.
-
-0.6.1 (2010-09-12)
-++++++++++++++++++
-
-* Packaging hotfixes.
-
-
-0.6.0 (2010-09-11)
-++++++++++++++++++
-
-* Public Release.
-* Export Support for XLS, JSON, YAML, and CSV.
-* DataBook Export for XLS, JSON, and YAML.
-* Python Dict Property Support.

LICENSE

@@ -1,4 +1,5 @@
 Copyright 2016 Kenneth Reitz
+Copyright 2019 Jazzband
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -16,4 +17,4 @@ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
+THE SOFTWARE.

MANIFEST.in

@@ -1 +0,0 @@
-include HISTORY.rst README.rst LICENSE AUTHORS NOTICE test_tablib.py

Makefile

@@ -1,6 +0,0 @@
-test:
-	python test_tablib.py
-publish:
-	python setup.py register
-	python setup.py sdist upload
-	python setup.py bdist_wheel --universal upload

NOTICE

@@ -1,6 +0,0 @@
-Tablib includes some vendorized Python libraries: markup.
-
-Markup License
-==============
-
-Markup is in the public domain.

README.md

@@ -0,0 +1,44 @@
+# Tablib: format-agnostic tabular dataset library
+
+[![Jazzband](https://jazzband.co/static/img/badge.svg)](https://jazzband.co/)
+[![PyPI version](https://img.shields.io/pypi/v/tablib.svg)](https://pypi.org/project/tablib/)
+[![Supported Python versions](https://img.shields.io/pypi/pyversions/tablib.svg)](https://pypi.org/project/tablib/)
+[![PyPI downloads](https://img.shields.io/pypi/dm/tablib.svg)](https://pypistats.org/packages/tablib)
+[![GitHub Actions status](https://github.com/jazzband/tablib/workflows/Test/badge.svg)](https://github.com/jazzband/tablib/actions)
+[![codecov](https://codecov.io/gh/jazzband/tablib/branch/master/graph/badge.svg)](https://codecov.io/gh/jazzband/tablib)
+[![GitHub](https://img.shields.io/github/license/jazzband/tablib.svg)](LICENSE)
+
+    _____         ______  ___________ ______
+    __  /_______ ____  /_ ___  /___(_)___  /_
+    _  __/_  __ `/__  __ \__  / __  / __  __ \
+    / /_  / /_/ / _  /_/ /_  /  _  /  _  /_/ /
+    \__/  \__,_/  /_.___/ /_/   /_/   /_.___/
+
+
+Tablib is a format-agnostic tabular dataset library, written in Python.
+
+Output formats supported:
+
+- Excel (Sets + Books)
+- JSON (Sets + Books)
+- YAML (Sets + Books)
+- Pandas DataFrames (Sets)
+- HTML (Sets)
+- Jira (Sets)
+- TSV (Sets)
+- ODS (Sets)
+- CSV (Sets)
+- DBF (Sets)
+
+Note that tablib *purposefully* excludes XML support. It always will. (Note: This is a
+joke. Pull requests are welcome.)
+
+Tablib documentation is graciously hosted on https://tablib.readthedocs.io
+
+It is also available in the ``docs`` directory of the source distribution.
+
+Make sure to check out [Tablib on PyPI](https://pypi.org/project/tablib/)!
+
+## Contribute
+
+Please see the [contributing guide](https://github.com/jazzband/tablib/blob/master/.github/CONTRIBUTING.md).

README.rst

@@ -1,179 +0,0 @@
-Tablib: format-agnostic tabular dataset library
-===============================================
-
-.. image:: https://travis-ci.org/kennethreitz/tablib.svg?branch=master
-    :target: https://travis-ci.org/kennethreitz/tablib
-
-::
-
-    _____         ______  ___________ ______
-    __  /_______ ____  /_ ___  /___(_)___  /_
-    _  __/_  __ `/__  __ \__  / __  / __  __ \
-    / /_  / /_/ / _  /_/ /_  /  _  /  _  /_/ /
-    \__/  \__,_/  /_.___/ /_/   /_/   /_.___/
-
-
-
-Tablib is a format-agnostic tabular dataset library, written in Python.
-
-Output formats supported:
-
-- Excel (Sets + Books)
-- JSON (Sets + Books)
-- YAML (Sets + Books)
-- Pandas DataFrames (Sets)
-- HTML (Sets)
-- Jira (Sets)
-- TSV (Sets)
-- ODS (Sets)
-- CSV (Sets)
-- DBF (Sets)
-
-Note that tablib *purposefully* excludes XML support. It always will. (Note: This is a joke. Pull requests are welcome.)
-
-If you're interested in financially supporting Kenneth Reitz open source, consider `visiting this link <https://cash.me/$KennethReitz>`_. Your support helps tremendously with sustainability of motivation, as Open Source is no longer part of my day job.
-
-Overview
---------
-
-`tablib.Dataset()`
-    A Dataset is a table of tabular data.
-    It may or may not have a header row.
-    They can be build and manipulated as raw Python datatypes (Lists of tuples|dictionaries).
-    Datasets can be imported from JSON, YAML, DBF, and CSV;
-    they can be exported to XLSX, XLS, ODS, JSON, YAML, DBF, CSV, TSV, and HTML.
-
-`tablib.Databook()`
-    A Databook is a set of Datasets.
-    The most common form of a Databook is an Excel file with multiple spreadsheets.
-    Databooks can be imported from JSON and YAML;
-    they can be exported to XLSX, XLS, ODS, JSON, and YAML.
-
-Usage
------
-
-
-Populate fresh data files: ::
-
-    headers = ('first_name', 'last_name')
-
-    data = [
-        ('John', 'Adams'),
-        ('George', 'Washington')
-    ]
-
-    data = tablib.Dataset(*data, headers=headers)
-
-
-Intelligently add new rows: ::
-
-    >>> data.append(('Henry', 'Ford'))
-
-Intelligently add new columns: ::
-
-    >>> data.append_col((90, 67, 83), header='age')
-
-Slice rows:  ::
-
-    >>> print(data[:2])
-    [('John', 'Adams', 90), ('George', 'Washington', 67)]
-
-
-Slice columns by header: ::
-
-    >>> print(data['first_name'])
-    ['John', 'George', 'Henry']
-
-Easily delete rows: ::
-
-    >>> del data[1]
-
-Exports
--------
-
-Drumroll please...........
-
-JSON!
-+++++
-::
-
-	>>> print(data.export('json'))
-	[
-	  {
-	    "last_name": "Adams",
-	    "age": 90,
-	    "first_name": "John"
-	  },
-	  {
-	    "last_name": "Ford",
-	    "age": 83,
-	    "first_name": "Henry"
-	  }
-	]
-
-
-YAML!
-+++++
-::
-
-	>>> print(data.export('yaml'))
-	- {age: 90, first_name: John, last_name: Adams}
-	- {age: 83, first_name: Henry, last_name: Ford}
-
-CSV...
-++++++
-::
-
-	>>> print(data.export('csv'))
-	first_name,last_name,age
-	John,Adams,90
-	Henry,Ford,83
-
-EXCEL!
-++++++
-::
-
-	>>> with open('people.xls', 'wb') as f:
-	...     f.write(data.export('xls'))
-
-DBF!
-++++
-::
-
-    >>> with open('people.dbf', 'wb') as f:
-    ...     f.write(data.export('dbf'))
-
-Pandas DataFrame!
-+++++++++++++++++
-::
-
-    >>> print(data.export('df')):
-          first_name last_name  age
-    0       John     Adams   90
-    1      Henry      Ford   83
-
-It's that easy.
-
-
-Installation
-------------
-
-To install tablib, simply: ::
-
-	$ pip install tablib[pandas]
-
-Make sure to check out `Tablib on PyPi <https://pypi.python.org/pypi/tablib/>`_!
-
-
-Contribute
-----------
-
-If you'd like to contribute, simply fork `the repository`_, commit your
-changes to the **develop** branch (or branch off of it), and send a pull
-request. Make sure you add yourself to AUTHORS_.
-
-
-
-
-.. _`the repository`: http://github.com/kennethreitz/tablib
-.. _AUTHORS: http://github.com/kennethreitz/tablib/blob/master/AUTHORS

RELEASING.md

@@ -0,0 +1,29 @@
+# Release checklist
+
+Jazzband guidelines: https://jazzband.co/about/releases
+
+* [ ] Get master to the appropriate code release state.
+      [GitHub Actions](https://github.com/jazzband/tablib/actions)
+      should pass on master.
+      [![GitHub Actions status](https://github.com/jazzband/tablib/workflows/Test/badge.svg)](https://github.com/jazzband/tablib/actions)
+
+* [ ] Check [HISTORY.md](https://github.com/jazzband/tablib/blob/master/HISTORY.md),
+      update version number and release date
+
+* [ ] Tag with version number and push tag, for example:
+```bash
+git tag -a v0.14.0 -m v0.14.0
+git push --tags
+```
+
+* [ ] Once GitHub Actions has built and uploaded distributions, check files at
+      [Jazzband](https://jazzband.co/projects/tablib) and release to
+      [PyPI](https://pypi.org/pypi/tablib)
+
+* [ ] Check installation:
+```bash
+pip uninstall -y tablib && pip install -U tablib
+```
+
+* [ ] Create new GitHub release: https://github.com/jazzband/tablib/releases/new
+  * Tag: Pick existing tag "v0.14.0"

docs/_templates/sidebarintro.html

@@ -1,20 +1,12 @@
-<h3><a href="http://docs.python-tablib.org">About Tablib</a></h3>
+<h3><a href="https://tablib.readthedocs.io">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>
-
-<h3>Feedback</h3>
-<p>
-  Feedback is greatly appreciated. If you have any questions, comments,
-  random praise, or anonymous threats, <a href="mailto:me@kennethreitz.com">
-  shoot me an email</a>.
-</p>
-
-
 <h3>Useful Links</h3>
 <ul>
-  <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>
+  <li><a href="https://tablib.readthedocs.io">The Tablib Website</a></li>
+  <li><a href="https://pypi.org/project/tablib">Tablib @ PyPI</a></li>
+  <li><a href="https://github.com/jazzband/tablib">Tablib @ GitHub</a></li>
+  <li><a href="https://github.com/jazzband/tablib/issues">Issue Tracker</a></li>
+  <li><a href="https://github.com/jazzband/tablib/blob/master/HISTORY.md">Changelog</a></li>
 </ul>

docs/_templates/sidebarlogo.html

@@ -1,4 +1,4 @@
-<h3><a href="http://docs.python-tablib.org/">About Tablib</a></h3>
+<h3><a href="https://tablib.readthedocs.io">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>
+</p>

docs/_themes/.gitignore

@@ -1,3 +0,0 @@
-*.pyc
-*.pyo
-.DS_Store

docs/_themes/LICENSE

@@ -1,45 +0,0 @@
-Modifications:
-
-Copyright (c) 2011 Kenneth Reitz.
-
-
-Original Project:
-
-Copyright (c) 2010 by Armin Ronacher.
-
-
-Some rights reserved.
-
-Redistribution and use in source and binary forms of the theme, with or
-without modification, are permitted provided that the following conditions
-are met:
-
-* Redistributions of source code must retain the above copyright
-  notice, this list of conditions and the following disclaimer.
-
-* 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.
-
-* The names of the contributors may not be used to endorse or
-  promote products derived from this software without specific
-  prior written permission.
-
-We kindly ask you to only use these themes in an unmodified manner just
-for Flask and Flask-related products, not for unrelated projects.  If you
-like the visual style and want to use it for your own projects, please
-consider making some larger changes to the themes (such as changing
-font faces, sizes, colors or margins).
-
-THIS THEME 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 THEME, EVEN IF ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGE.

docs/_themes/README.rst

@@ -1,24 +0,0 @@
-krTheme Sphinx Style
-====================
-
-This repository contains sphinx styles Kenneth Reitz uses in most of
-his projects. It is a drivative of Mitsuhiko's themes for Flask and Flask related
-projects.  To use this style in your Sphinx documentation, follow
-this guide:
-
-1. put this folder as _themes into your docs folder.  Alternatively
-   you can also use git submodules to check out the contents there.
-
-2. add this to your conf.py: ::
-
-	sys.path.append(os.path.abspath('_themes'))
-	html_theme_path = ['_themes']
-	html_theme = 'flask'
-
-The following themes exist:
-
-**kr**
-	the standard flask documentation theme for large projects
-
-**kr_small**
-	small one-page theme.  Intended to be used by very small addon libraries.

docs/_themes/flask_theme_support.py

@@ -1,86 +0,0 @@
-# flasky extensions.  flasky pygments style based on tango style
-from pygments.style import Style
-from pygments.token import Keyword, Name, Comment, String, Error, \
-     Number, Operator, Generic, Whitespace, Punctuation, Other, Literal
-
-
-class FlaskyStyle(Style):
-    background_color = "#f8f8f8"
-    default_style = ""
-
-    styles = {
-        # No corresponding class for the following:
-        #Text:                     "", # class:  ''
-        Whitespace:                "underline #f8f8f8",      # class: 'w'
-        Error:                     "#a40000 border:#ef2929", # class: 'err'
-        Other:                     "#000000",                # class 'x'
-
-        Comment:                   "italic #8f5902", # class: 'c'
-        Comment.Preproc:           "noitalic",       # class: 'cp'
-
-        Keyword:                   "bold #004461",   # class: 'k'
-        Keyword.Constant:          "bold #004461",   # class: 'kc'
-        Keyword.Declaration:       "bold #004461",   # class: 'kd'
-        Keyword.Namespace:         "bold #004461",   # class: 'kn'
-        Keyword.Pseudo:            "bold #004461",   # class: 'kp'
-        Keyword.Reserved:          "bold #004461",   # class: 'kr'
-        Keyword.Type:              "bold #004461",   # class: 'kt'
-
-        Operator:                  "#582800",   # class: 'o'
-        Operator.Word:             "bold #004461",   # class: 'ow' - like keywords
-
-        Punctuation:               "bold #000000",   # class: 'p'
-
-        # because special names such as Name.Class, Name.Function, etc.
-        # are not recognized as such later in the parsing, we choose them
-        # to look the same as ordinary variables.
-        Name:                      "#000000",        # class: 'n'
-        Name.Attribute:            "#c4a000",        # class: 'na' - to be revised
-        Name.Builtin:              "#004461",        # class: 'nb'
-        Name.Builtin.Pseudo:       "#3465a4",        # class: 'bp'
-        Name.Class:                "#000000",        # class: 'nc' - to be revised
-        Name.Constant:             "#000000",        # class: 'no' - to be revised
-        Name.Decorator:            "#888",           # class: 'nd' - to be revised
-        Name.Entity:               "#ce5c00",        # class: 'ni'
-        Name.Exception:            "bold #cc0000",   # class: 'ne'
-        Name.Function:             "#000000",        # class: 'nf'
-        Name.Property:             "#000000",        # class: 'py'
-        Name.Label:                "#f57900",        # class: 'nl'
-        Name.Namespace:            "#000000",        # class: 'nn' - to be revised
-        Name.Other:                "#000000",        # class: 'nx'
-        Name.Tag:                  "bold #004461",   # class: 'nt' - like a keyword
-        Name.Variable:             "#000000",        # class: 'nv' - to be revised
-        Name.Variable.Class:       "#000000",        # class: 'vc' - to be revised
-        Name.Variable.Global:      "#000000",        # class: 'vg' - to be revised
-        Name.Variable.Instance:    "#000000",        # class: 'vi' - to be revised
-
-        Number:                    "#990000",        # class: 'm'
-
-        Literal:                   "#000000",        # class: 'l'
-        Literal.Date:              "#000000",        # class: 'ld'
-
-        String:                    "#4e9a06",        # class: 's'
-        String.Backtick:           "#4e9a06",        # class: 'sb'
-        String.Char:               "#4e9a06",        # class: 'sc'
-        String.Doc:                "italic #8f5902", # class: 'sd' - like a comment
-        String.Double:             "#4e9a06",        # class: 's2'
-        String.Escape:             "#4e9a06",        # class: 'se'
-        String.Heredoc:            "#4e9a06",        # class: 'sh'
-        String.Interpol:           "#4e9a06",        # class: 'si'
-        String.Other:              "#4e9a06",        # class: 'sx'
-        String.Regex:              "#4e9a06",        # class: 'sr'
-        String.Single:             "#4e9a06",        # class: 's1'
-        String.Symbol:             "#4e9a06",        # class: 'ss'
-
-        Generic:                   "#000000",        # class: 'g'
-        Generic.Deleted:           "#a40000",        # class: 'gd'
-        Generic.Emph:              "italic #000000", # class: 'ge'
-        Generic.Error:             "#ef2929",        # class: 'gr'
-        Generic.Heading:           "bold #000080",   # class: 'gh'
-        Generic.Inserted:          "#00A000",        # class: 'gi'
-        Generic.Output:            "#888",           # class: 'go'
-        Generic.Prompt:            "#745334",        # class: 'gp'
-        Generic.Strong:            "bold #000000",   # class: 'gs'
-        Generic.Subheading:        "bold #800080",   # class: 'gu'
-        Generic.Traceback:         "bold #a40000",   # class: 'gt'
-    }

docs/_themes/kr/layout.html

@@ -1,54 +0,0 @@
-{%- extends "basic/layout.html" %}
-{%- block extrahead %}
-  {{ super() }}
-  {% if theme_touch_icon %}
-  <link rel="apple-touch-icon" href="{{ pathto('_static/' ~ theme_touch_icon, 1) }}" />
-  {% endif %}
-  <link media="only screen and (max-device-width: 480px)" href="{{
-    pathto('_static/small_flask.css', 1) }}" type= "text/css" rel="stylesheet" />
-{% endblock %}
-{%- block relbar2 %}{% endblock %}
-{%- block footer %}
-  <div class="footer">
-      &copy; Copyright {{ copyright }}.
-    </div>
-    <a href="https://github.com/kennethreitz/tablib">
-        <img style="position: absolute; top: 0; right: 0; border: 0;" src="//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 || [];
-      _gaq.push(['_setAccount', 'UA-8742933-9']);
-      _gaq.push(['_setDomainName', 'none']);
-      _gaq.push(['_setAllowLinker', true]);
-      _gaq.push(['_trackPageview']);
-
-      (function() {
-        var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
-        ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
-        var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
-      })();
-
-    </script>
-
-    <script type="text/javascript">
-      (function() {
-        var t   = document.createElement('script');
-        t.type  = 'text/javascript';
-        t.async = true;
-        t.id    = 'gauges-tracker';
-        t.setAttribute('data-site-id',
-                       '4ddc284f613f5d2f1a000001');
-        t.src = '//secure.gaug.es/track.js';
-        var s = document.getElementsByTagName('script')[0];
-        s.parentNode.insertBefore(t, s);
-      })();
-    </script>
-
-{%- endblock %}

docs/_themes/kr/relations.html

@@ -1,19 +0,0 @@
-<h3>Related Topics</h3>
-<ul>
-  <li><a href="{{ pathto(master_doc) }}">Documentation overview</a><ul>
-  {%- for parent in parents %}
-  <li><a href="{{ parent.link|e }}">{{ parent.title }}</a><ul>
-  {%- endfor %}
-    {%- if prev %}
-      <li>Previous: <a href="{{ prev.link|e }}" title="{{ _('previous chapter')
-        }}">{{ prev.title }}</a></li>
-    {%- endif %}
-    {%- if next %}
-      <li>Next: <a href="{{ next.link|e }}" title="{{ _('next chapter')
-        }}">{{ next.title }}</a></li>
-    {%- endif %}
-  {%- for parent in parents %}
-  </ul></li>
-  {%- endfor %}
-  </ul></li>
-</ul>

docs/_themes/kr/static/flasky.css_t

@@ -1,470 +0,0 @@
-/*
- * flasky.css_t
- * ~~~~~~~~~~~~
- *
- * :copyright: Copyright 2010 by Armin Ronacher. Modifications by Kenneth Reitz.
- * :license: Flask Design License, see LICENSE for details.
- */
-
-{% set page_width = '940px' %}
-{% set sidebar_width = '220px' %}
-
-@import url("basic.css");
-
-/* -- page layout ----------------------------------------------------------- */
-
-body {
-    font-family: 'goudy old style', 'minion pro', 'bell mt', Georgia, 'Hiragino Mincho Pro';
-    font-size: 17px;
-    background-color: white;
-    color: #000;
-    margin: 0;
-    padding: 0;
-}
-
-div.document {
-    width: {{ page_width }};
-    margin: 30px auto 0 auto;
-}
-
-div.documentwrapper {
-    float: left;
-    width: 100%;
-}
-
-div.bodywrapper {
-    margin: 0 0 0 {{ sidebar_width }};
-}
-
-div.sphinxsidebar {
-    width: {{ sidebar_width }};
-}
-
-hr {
-    border: 1px solid #B1B4B6;
-}
-
-div.body {
-    background-color: #ffffff;
-    color: #3E4349;
-    padding: 0 30px 0 30px;
-}
-
-img.floatingflask {
-    padding: 0 0 10px 10px;
-    float: right;
-}
-
-div.footer {
-    width: {{ page_width }};
-    margin: 20px auto 30px auto;
-    font-size: 14px;
-    color: #888;
-    text-align: right;
-}
-
-div.footer a {
-    color: #888;
-}
-
-div.related {
-    display: none;
-}
-
-div.sphinxsidebar a {
-    color: #444;
-    text-decoration: none;
-    border-bottom: 1px dotted #999;
-}
-
-div.sphinxsidebar a:hover {
-    border-bottom: 1px solid #999;
-}
-
-div.sphinxsidebar {
-    font-size: 14px;
-    line-height: 1.5;
-}
-
-div.sphinxsidebarwrapper {
-    padding: 18px 10px;
-}
-
-div.sphinxsidebarwrapper p.logo {
-    padding: 0 0 20px 0;
-    margin: 0;
-    text-align: center;
-}
-
-div.sphinxsidebar h3,
-div.sphinxsidebar h4 {
-    font-family: 'Garamond', 'Georgia', serif;
-    color: #444;
-    font-size: 24px;
-    font-weight: normal;
-    margin: 0 0 5px 0;
-    padding: 0;
-}
-
-div.sphinxsidebar h4 {
-    font-size: 20px;
-}
-
-div.sphinxsidebar h3 a {
-    color: #444;
-}
-
-div.sphinxsidebar p.logo a,
-div.sphinxsidebar h3 a,
-div.sphinxsidebar p.logo a:hover,
-div.sphinxsidebar h3 a:hover {
-    border: none;
-}
-
-div.sphinxsidebar p {
-    color: #555;
-    margin: 10px 0;
-}
-
-div.sphinxsidebar ul {
-    margin: 10px 0;
-    padding: 0;
-    color: #000;
-}
-
-div.sphinxsidebar input {
-    border: 1px solid #ccc;
-    font-family: 'Georgia', serif;
-    font-size: 1em;
-}
-
-/* -- body styles ----------------------------------------------------------- */
-
-a {
-    color: #004B6B;
-    text-decoration: underline;
-}
-
-a:hover {
-    color: #6D4100;
-    text-decoration: underline;
-}
-
-div.body h1,
-div.body h2,
-div.body h3,
-div.body h4,
-div.body h5,
-div.body h6 {
-    font-family: 'Garamond', 'Georgia', serif;
-    font-weight: normal;
-    margin: 30px 0px 10px 0px;
-    padding: 0;
-}
-
-div.body h1 { margin-top: 0; padding-top: 0; font-size: 240%; }
-div.body h2 { font-size: 180%; }
-div.body h3 { font-size: 150%; }
-div.body h4 { font-size: 130%; }
-div.body h5 { font-size: 100%; }
-div.body h6 { font-size: 100%; }
-
-a.headerlink {
-    color: #ddd;
-    padding: 0 4px;
-    text-decoration: none;
-}
-
-a.headerlink:hover {
-    color: #444;
-    background: #eaeaea;
-}
-
-div.body p, div.body dd, div.body li {
-    line-height: 1.4em;
-}
-
-div.admonition {
-    background: #fafafa;
-    margin: 20px -30px;
-    padding: 10px 30px;
-    border-top: 1px solid #ccc;
-    border-bottom: 1px solid #ccc;
-}
-
-div.admonition tt.xref, div.admonition a tt {
-    border-bottom: 1px solid #fafafa;
-}
-
-dd div.admonition {
-    margin-left: -60px;
-    padding-left: 60px;
-}
-
-div.admonition p.admonition-title {
-    font-family: 'Garamond', 'Georgia', serif;
-    font-weight: normal;
-    font-size: 24px;
-    margin: 0 0 10px 0;
-    padding: 0;
-    line-height: 1;
-}
-
-div.admonition p.last {
-    margin-bottom: 0;
-}
-
-div.highlight {
-    background-color: white;
-}
-
-dt:target, .highlight {
-    background: #FAF3E8;
-}
-
-div.note {
-    background-color: #eee;
-    border: 1px solid #ccc;
-}
-
-div.seealso {
-    background-color: #ffc;
-    border: 1px solid #ff6;
-}
-
-div.topic {
-    background-color: #eee;
-}
-
-p.admonition-title {
-    display: inline;
-}
-
-p.admonition-title:after {
-    content: ":";
-}
-
-pre, tt {
-    font-family: 'Consolas', 'Menlo', 'Deja Vu Sans Mono', 'Bitstream Vera Sans Mono', monospace;
-    font-size: 0.9em;
-}
-
-img.screenshot {
-}
-
-tt.descname, tt.descclassname {
-    font-size: 0.95em;
-}
-
-tt.descname {
-    padding-right: 0.08em;
-}
-
-img.screenshot {
-    -moz-box-shadow: 2px 2px 4px #eee;
-    -webkit-box-shadow: 2px 2px 4px #eee;
-    box-shadow: 2px 2px 4px #eee;
-}
-
-table.docutils {
-    border: 1px solid #888;
-    -moz-box-shadow: 2px 2px 4px #eee;
-    -webkit-box-shadow: 2px 2px 4px #eee;
-    box-shadow: 2px 2px 4px #eee;
-}
-
-table.docutils td, table.docutils th {
-    border: 1px solid #888;
-    padding: 0.25em 0.7em;
-}
-
-table.field-list, table.footnote {
-    border: none;
-    -moz-box-shadow: none;
-    -webkit-box-shadow: none;
-    box-shadow: none;
-}
-
-table.footnote {
-    margin: 15px 0;
-    width: 100%;
-    border: 1px solid #eee;
-    background: #fdfdfd;
-    font-size: 0.9em;
-}
-
-table.footnote + table.footnote {
-    margin-top: -15px;
-    border-top: none;
-}
-
-table.field-list th {
-    padding: 0 0.8em 0 0;
-}
-
-table.field-list td {
-    padding: 0;
-}
-
-table.footnote td.label {
-    width: 0px;
-    padding: 0.3em 0 0.3em 0.5em;
-}
-
-table.footnote td {
-    padding: 0.3em 0.5em;
-}
-
-dl {
-    margin: 0;
-    padding: 0;
-}
-
-dl dd {
-    margin-left: 30px;
-}
-
-blockquote {
-    margin: 0 0 0 30px;
-    padding: 0;
-}
-
-ul, ol {
-    margin: 10px 0 10px 30px;
-    padding: 0;
-}
-
-pre {
-    background: #eee;
-    padding: 7px 30px;
-    margin: 15px -30px;
-    line-height: 1.3em;
-}
-
-dl pre, blockquote pre, li pre {
-    margin-left: -60px;
-    padding-left: 60px;
-}
-
-dl dl pre {
-    margin-left: -90px;
-    padding-left: 90px;
-}
-
-tt {
-    background-color: #ecf0f3;
-    color: #222;
-    /* padding: 1px 2px; */
-}
-
-tt.xref, a tt {
-    background-color: #FBFBFB;
-    border-bottom: 1px solid white;
-}
-
-a.reference {
-    text-decoration: none;
-    border-bottom: 1px dotted #004B6B;
-}
-
-a.reference:hover {
-    border-bottom: 1px solid #6D4100;
-}
-
-a.footnote-reference {
-    text-decoration: none;
-    font-size: 0.7em;
-    vertical-align: top;
-    border-bottom: 1px dotted #004B6B;
-}
-
-a.footnote-reference:hover {
-    border-bottom: 1px solid #6D4100;
-}
-
-a:hover tt {
-    background: #EEE;
-}
-
-
-@media screen and (max-width: 600px) {
-
-    div.sphinxsidebar {
-    	display: none;
-    }
-
-    div.documentwrapper {
-    	margin-left: 0;
-    	margin-top: 0;
-    	margin-right: 0;
-    	margin-bottom: 0;
-    }
-
-    div.bodywrapper {
-    	margin-top: 0;
-    	margin-right: 0;
-    	margin-bottom: 0;
-    	margin-left: 0;
-    }
-
-    ul {
-    	margin-left: 0;
-    }
-
-    .document {
-    	width: auto;
-    }
-
-    .bodywrapper {
-    	margin: 0;
-    }
-
-    .footer {
-    	width: auto;
-    }
-
-
-
-}
-
-
-
-/* scrollbars */
-
-::-webkit-scrollbar {
-    width: 6px;
-    height: 6px;
-}
-
-::-webkit-scrollbar-button:start:decrement,
-::-webkit-scrollbar-button:end:increment {
-    display: block;
-    height: 10px;
-}
-
-::-webkit-scrollbar-button:vertical:increment {
-    background-color: #fff;
-}
-
-::-webkit-scrollbar-track-piece {
-    background-color: #eee;
-    -webkit-border-radius: 3px;
-}
-
-::-webkit-scrollbar-thumb:vertical {
-    height: 50px;
-    background-color: #ccc;
-    -webkit-border-radius: 3px;
-}
-
-::-webkit-scrollbar-thumb:horizontal {
-    width: 50px;
-    background-color: #ccc;
-    -webkit-border-radius: 3px;
-}
-
-/* misc. */
-
-.revsys-inline {
-    display: none!important;
-}

docs/_themes/kr/static/small_flask.css

@@ -1,70 +0,0 @@
-/*
- * small_flask.css_t
- * ~~~~~~~~~~~~~~~~~
- *
- * :copyright: Copyright 2010 by Armin Ronacher.
- * :license: Flask Design License, see LICENSE for details.
- */
-
-body {
-    margin: 0;
-    padding: 20px 30px;
-}
-
-div.documentwrapper {
-    float: none;
-    background: white;
-}
-
-div.sphinxsidebar {
-    display: block;
-    float: none;
-    width: 102.5%;
-    margin: 50px -30px -20px -30px;
-    padding: 10px 20px;
-    background: #333;
-    color: white;
-}
-
-div.sphinxsidebar h3, div.sphinxsidebar h4, div.sphinxsidebar p,
-div.sphinxsidebar h3 a {
-    color: white;
-}
-
-div.sphinxsidebar a {
-    color: #aaa;
-}
-
-div.sphinxsidebar p.logo {
-    display: none;
-}
-
-div.document {
-    width: 100%;
-    margin: 0;
-}
-
-div.related {
-    display: block;
-    margin: 0;
-    padding: 10px 0 20px 0;
-}
-
-div.related ul,
-div.related ul li {
-    margin: 0;
-    padding: 0;
-}
-
-div.footer {
-    display: none;
-}
-
-div.bodywrapper {
-    margin: 0;
-}
-
-div.body {
-    min-height: 0;
-    padding: 0;
-}

docs/_themes/kr/theme.conf

@@ -1,7 +0,0 @@
-[theme]
-inherit = basic
-stylesheet = flasky.css
-pygments_style = flask_theme_support.FlaskyStyle
-
-[options]
-touch_icon =

docs/_themes/kr_small/layout.html

@@ -1,22 +0,0 @@
-{% extends "basic/layout.html" %}
-{% block header %}
-  {{ super() }}
-  {% if pagename == 'index' %}
-  <div class=indexwrapper>
-  {% endif %}
-{% endblock %}
-{% block footer %}
-  {% if pagename == 'index' %}
-  </div>
-  {% endif %}
-{% endblock %}
-{# do not display relbars #}
-{% block relbar1 %}{% endblock %}
-{% block relbar2 %}
-  {% if theme_github_fork %}
-    <a href="https://github.com/{{ theme_github_fork }}"><img style="position: fixed; top: 0; right: 0; border: 0;"
-    src="//s3.amazonaws.com/github/ribbons/forkme_right_darkblue_121621.png" alt="Fork me on GitHub" /></a>
-  {% endif %}
-{% endblock %}
-{% block sidebar1 %}{% endblock %}
-{% block sidebar2 %}{% endblock %}

docs/_themes/kr_small/static/flasky.css_t

@@ -1,287 +0,0 @@
-/*
- * flasky.css_t
- * ~~~~~~~~~~~~
- *
- * Sphinx stylesheet -- flasky theme based on nature theme.
- *
- * :copyright: Copyright 2007-2010 by the Sphinx team, see AUTHORS.
- * :license: BSD, see LICENSE for details.
- *
- */
-
-@import url("basic.css");
-
-/* -- page layout ----------------------------------------------------------- */
-
-body {
-    font-family: 'Georgia', serif;
-    font-size: 17px;
-    color: #000;
-    background: white;
-    margin: 0;
-    padding: 0;
-}
-
-div.documentwrapper {
-    float: left;
-    width: 100%;
-}
-
-div.bodywrapper {
-    margin: 40px auto 0 auto;
-    width: 700px;
-}
-
-hr {
-    border: 1px solid #B1B4B6;
-}
-
-div.body {
-    background-color: #ffffff;
-    color: #3E4349;
-    padding: 0 30px 30px 30px;
-}
-
-img.floatingflask {
-    padding: 0 0 10px 10px;
-    float: right;
-}
-
-div.footer {
-    text-align: right;
-    color: #888;
-    padding: 10px;
-    font-size: 14px;
-    width: 650px;
-    margin: 0 auto 40px auto;
-}
-
-div.footer a {
-    color: #888;
-    text-decoration: underline;
-}
-
-div.related {
-    line-height: 32px;
-    color: #888;
-}
-
-div.related ul {
-    padding: 0 0 0 10px;
-}
-
-div.related a {
-    color: #444;
-}
-
-/* -- body styles ----------------------------------------------------------- */
-
-a {
-    color: #004B6B;
-    text-decoration: underline;
-}
-
-a:hover {
-    color: #6D4100;
-    text-decoration: underline;
-}
-
-div.body {
-    padding-bottom: 40px; /* saved for footer */
-}
-
-div.body h1,
-div.body h2,
-div.body h3,
-div.body h4,
-div.body h5,
-div.body h6 {
-    font-family: 'Garamond', 'Georgia', serif;
-    font-weight: normal;
-    margin: 30px 0px 10px 0px;
-    padding: 0;
-}
-
-{% if theme_index_logo %}
-div.indexwrapper h1 {
-    text-indent: -999999px;
-    background: url({{ theme_index_logo }}) no-repeat center center;
-    height: {{ theme_index_logo_height }};
-}
-{% endif %}
-
-div.body h2 { font-size: 180%; }
-div.body h3 { font-size: 150%; }
-div.body h4 { font-size: 130%; }
-div.body h5 { font-size: 100%; }
-div.body h6 { font-size: 100%; }
-
-a.headerlink {
-    color: white;
-    padding: 0 4px;
-    text-decoration: none;
-}
-
-a.headerlink:hover {
-    color: #444;
-    background: #eaeaea;
-}
-
-div.body p, div.body dd, div.body li {
-    line-height: 1.4em;
-}
-
-div.admonition {
-    background: #fafafa;
-    margin: 20px -30px;
-    padding: 10px 30px;
-    border-top: 1px solid #ccc;
-    border-bottom: 1px solid #ccc;
-}
-
-div.admonition p.admonition-title {
-    font-family: 'Garamond', 'Georgia', serif;
-    font-weight: normal;
-    font-size: 24px;
-    margin: 0 0 10px 0;
-    padding: 0;
-    line-height: 1;
-}
-
-div.admonition p.last {
-    margin-bottom: 0;
-}
-
-div.highlight{
-    background-color: white;
-}
-
-dt:target, .highlight {
-    background: #FAF3E8;
-}
-
-div.note {
-    background-color: #eee;
-    border: 1px solid #ccc;
-}
-
-div.seealso {
-    background-color: #ffc;
-    border: 1px solid #ff6;
-}
-
-div.topic {
-    background-color: #eee;
-}
-
-div.warning {
-    background-color: #ffe4e4;
-    border: 1px solid #f66;
-}
-
-p.admonition-title {
-    display: inline;
-}
-
-p.admonition-title:after {
-    content: ":";
-}
-
-pre, tt {
-    font-family: 'Consolas', 'Menlo', 'Deja Vu Sans Mono', 'Bitstream Vera Sans Mono', monospace;
-    font-size: 0.85em;
-}
-
-img.screenshot {
-}
-
-tt.descname, tt.descclassname {
-    font-size: 0.95em;
-}
-
-tt.descname {
-    padding-right: 0.08em;
-}
-
-img.screenshot {
-    -moz-box-shadow: 2px 2px 4px #eee;
-    -webkit-box-shadow: 2px 2px 4px #eee;
-    box-shadow: 2px 2px 4px #eee;
-}
-
-table.docutils {
-    border: 1px solid #888;
-    -moz-box-shadow: 2px 2px 4px #eee;
-    -webkit-box-shadow: 2px 2px 4px #eee;
-    box-shadow: 2px 2px 4px #eee;
-}
-
-table.docutils td, table.docutils th {
-    border: 1px solid #888;
-    padding: 0.25em 0.7em;
-}
-
-table.field-list, table.footnote {
-    border: none;
-    -moz-box-shadow: none;
-    -webkit-box-shadow: none;
-    box-shadow: none;
-}
-
-table.footnote {
-    margin: 15px 0;
-    width: 100%;
-    border: 1px solid #eee;
-}
-
-table.field-list th {
-    padding: 0 0.8em 0 0;
-}
-
-table.field-list td {
-    padding: 0;
-}
-
-table.footnote td {
-    padding: 0.5em;
-}
-
-dl {
-    margin: 0;
-    padding: 0;
-}
-
-dl dd {
-    margin-left: 30px;
-}
-
-pre {
-    padding: 0;
-    margin: 15px -30px;
-    padding: 8px;
-    line-height: 1.3em;
-    padding: 7px 30px;
-    background: #eee;
-    border-radius: 2px;
-    -moz-border-radius: 2px;
-    -webkit-border-radius: 2px;
-}
-
-dl pre {
-    margin-left: -60px;
-    padding-left: 60px;
-}
-
-tt {
-    background-color: #ecf0f3;
-    color: #222;
-    /* padding: 1px 2px; */
-}
-
-tt.xref, a tt {
-    background-color: #FBFBFB;
-}
-
-a:hover tt {
-    background: #EEE;
-}

docs/_themes/kr_small/theme.conf

@@ -1,10 +0,0 @@
-[theme]
-inherit = basic
-stylesheet = flasky.css
-nosidebar = true
-pygments_style = flask_theme_support.FlaskyStyle
-
-[options]
-index_logo = ''
-index_logo_height = 120px
-github_fork = ''

docs/api.rst

@@ -36,7 +36,7 @@ Functions
 ---------
 
 
-.. autofunction:: detect
+.. autofunction:: detect_format
 
 .. autofunction:: import_set
 
@@ -61,4 +61,4 @@ Exceptions
     You're trying to add something that doesn't quite taste right.
 
 
-Now, go start some :ref:`Tablib Development <development>`.
+Now, go start some :ref:`Tablib Development <development>`.

docs/conf.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # Tablib documentation build configuration file, created by
 # sphinx-quickstart on Tue Oct  5 15:25:21 2010.
@@ -10,22 +9,24 @@
 #
 # All configuration values have a default; values that are commented out
 # serve to show the default.
-
-import sys, os
+import tablib
 
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
-sys.path.insert(0, os.path.abspath('..'))
-import tablib
+# sys.path.insert(0, os.path.abspath('..'))
 # -- General configuration -----------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
-#needs_sphinx = '1.0'
+# needs_sphinx = '1.0'
 
 # Add any Sphinx extension module names here, as strings. They can be extensions
 # coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
-extensions = ['sphinx.ext.autodoc', 'sphinx.ext.todo', 'sphinx.ext.coverage', 'sphinx.ext.viewcode']
+extensions = [
+    'sphinx.ext.autodoc', 'sphinx.ext.todo', 'sphinx.ext.coverage',
+    'sphinx.ext.viewcode', 'sphinx.ext.intersphinx'
+]
+intersphinx_mapping = {'python': ('https://docs.python.org/3', None)}
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -40,17 +41,18 @@ source_suffix = '.rst'
 master_doc = 'index'
 
 # General information about the project.
-project = u'Tablib'
-copyright = u'2016. A <a href="http://kennethreitz.org/">Kenneth Reitz</a> Project'
+project = 'Tablib'
+copyright = '2019 Jazzband'
 
 # The version info for the project you're documenting, acts as replacement for
 # |version| and |release|, also used in various other places throughout the
 # built documents.
 #
-# The short X.Y version.
-version = tablib.__version__
 # The full version, including alpha/beta/rc tags.
-release = version
+release = tablib.__version__
+# The short X.Y version.
+version = '.'.join(tablib.__version__.split('.')[:2])
+# for example take major/minor
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -81,7 +83,7 @@ add_function_parentheses = True
 #show_authors = False
 
 # The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'flask_theme_support.FlaskyStyle'
+# pygments_style = ''
 
 # A list of ignored prefixes for module index sorting.
 #modindex_common_prefix = []
@@ -91,7 +93,7 @@ pygments_style = 'flask_theme_support.FlaskyStyle'
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
-html_theme = 'default'
+html_theme = 'alabaster'
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -120,7 +122,7 @@ html_theme = 'default'
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['static']
+# html_static_path = ['static']
 
 # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
 # using the given strftime format.
@@ -182,24 +184,18 @@ htmlhelp_basename = 'Tablibdoc'
 # Grouping the document tree into LaTeX files. List of tuples
 # (source start file, target name, title, author, documentclass [howto/manual]).
 latex_documents = [
-  ('index', 'Tablib.tex', u'Tablib Documentation',
-   u'Kenneth Reitz', 'manual'),
+  ('index', 'Tablib.tex', 'Tablib Documentation',
+   'Jazzband', 'manual'),
 ]
 
 latex_use_modindex = False
 
 latex_elements = {
-    'fontpkg':      r'\usepackage{mathpazo}',
     'papersize':    'a4paper',
     'pointsize':    '12pt',
-    'preamble':     r'\usepackage{krstyle}'
 }
 latex_use_parts = True
 
-latex_additional_files = ['krstyle.sty']
-
-
-
 # The name of an image file (relative to this directory) to place at the top of
 # the title page.
 #latex_logo = None
@@ -229,10 +225,6 @@ latex_additional_files = ['krstyle.sty']
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
 man_pages = [
-    ('index', 'tablib', u'Tablib Documentation',
-     [u'Kenneth Reitz'], 1)
+    ('index', 'tablib', 'Tablib Documentation',
+     ['Jazzband'], 1)
 ]
-
-sys.path.append(os.path.abspath('_themes'))
-html_theme_path = ['_themes']
-html_theme = 'kr'

docs/development.rst

@@ -8,7 +8,7 @@ Tablib is under active development, and contributors are welcome.
 If you have a feature request, suggestion, or bug report, please open a new
 issue on GitHub_. To submit patches, please send a pull request on GitHub_.
 
-.. _GitHub: http://github.com/kennethreitz/tablib/
+.. _GitHub: https://github.com/jazzband/tablib/
 
 
 
@@ -45,12 +45,12 @@ The repository is publicly accessible.
 
 .. code-block:: console
 
-    git clone git://github.com/kennethreitz/tablib.git
+    git clone git://github.com/jazzband/tablib.git
 
 The project is hosted on **GitHub**.
 
     GitHub:
-        http://github.com/kennethreitz/tablib
+        https://github.com/jazzband/tablib
 
 
 Git Branch Structure
@@ -67,9 +67,9 @@ Each release is tagged.
 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
-.. _`Successful Git Branching Model`: http://nvie.com/posts/a-successful-git-branching-model/
-.. _git-flow: http://github.com/nvie/gitflow
+.. _Git: https://git-scm.org
+.. _`Successful Git Branching Model`: https://nvie.com/posts/a-successful-git-branching-model/
+.. _git-flow: https://github.com/nvie/gitflow
 
 
 .. _newformats:
@@ -90,32 +90,36 @@ Tablib features a micro-framework for adding format support.
 The easiest way to understand it is to use it.
 So, let's define our own format, named *xxx*.
 
-1. Write a new format interface.
+From version 1.0, Tablib formats are class-based and can be dynamically
+registered.
 
-    :class:`tablib.core` follows a simple pattern for automatically utilizing your format throughout Tablib.
-    Function names are crucial.
-
-    Example **tablib/formats/_xxx.py**: ::
+1. Write your custom format class::
 
+    class MyXXXFormatClass:
         title = 'xxx'
 
-        def export_set(dset):
+        @classmethod
+        def export_set(cls, dset):
             ....
             # returns string representation of given dataset
 
-        def export_book(dbook):
+        @classmethod
+        def export_book(cls, dbook):
             ....
             # returns string representation of given databook
 
-        def import_set(dset, in_stream):
+        @classmethod
+        def import_set(cls, dset, in_stream):
             ...
             # populates given Dataset with given datastream
 
-        def import_book(dbook, in_stream):
+        @classmethod
+        def import_book(cls, dbook, in_stream):
             ...
             # returns Databook instance
 
-        def detect(stream):
+        @classmethod
+        def detect(cls, stream):
             ...
             # returns True if given stream is parsable as xxx
 
@@ -124,15 +128,18 @@ So, let's define our own format, named *xxx*.
        If the format excludes support for an import/export mechanism (*e.g.* 
        :class:`csv <tablib.Dataset.csv>` excludes 
        :class:`Databook <tablib.Databook>` support),
-       simply don't define the respective functions.
+       simply don't define the respective class methods.
        Appropriate errors will be raised.
 
-2. Add your new format module to the :class:`tablib.formats.available` tuple.
+2. Register your class::
 
-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.
+    from tablib.formats import registry
 
-4. Write respective :ref:`tests <testing>`.
+    registry.register('xxx', MyXXXFormatClass())
+
+3. From then on, you should be able to use your new custom format as if it were
+a built-in Tablib format, e.g. using ``dataset.export('xxx')`` will use the 
+``MyXXXFormatClass.export_set`` method.
 
 .. _testing:
 
@@ -150,47 +157,22 @@ the easiest way to test your changes for potential issues is to simply run the t
 
 .. code-block:: console
 
-    $ ./test_tablib.py
-
-
-`Jenkins CI`_, amongst other tools, supports Java's xUnit testing report format.
-Nose_ allows us to generate our own xUnit reports.
-
-Installing nose is simple.
-
-.. code-block:: console
-
-    $ pip install nose
-
-Once installed, we can generate our xUnit report with a single command.
-
-.. code-block:: console
-
-    $ nosetests test_tablib.py --with-xunit
-
-This will generate a **nosetests.xml** file, which can then be analyzed.
-
-.. _Nose: http://somethingaboutorange.com/mrl/projects/nose/
-
-
-
-.. _jenkins:
+    $ tox
 
 ----------------------
 Continuous Integration
 ----------------------
 
-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.
+Every pull request is automatically tested and inspected upon receipt with `GitHub Actions`_.
+If you broke the build, you will receive an email accordingly.
 
 Anyone may view the build status and history at any time.
 
-    https://travis-ci.org/kennethreitz/tablib
+    https://github.com/jazzband/tablib/actions
 
 Additional reports will also be included here in the future, including :pep:`8` checks and stress reports for extremely large datasets.
 
-.. _`Jenkins CI`: https://travis-ci.org/
+.. _`GitHub Actions`: https://github.com/jazzband/tablib/actions
 
 
 .. _docs:
@@ -225,7 +207,7 @@ You can also generate the documentation in **epub**, **latex**, **json**, *&c* s
 
 .. _`reStructured Text`: http://docutils.sourceforge.net/rst.html
 .. _Sphinx: http://sphinx.pocoo.org
-.. _`GitHub Pages`: http://pages.github.com
+.. _`GitHub Pages`: https://pages.github.com
 
 ----------
 

docs/formats.rst

@@ -0,0 +1,247 @@
+.. _formats:
+
+=======
+Formats
+=======
+
+Tablib supports a wide variety of different tabular formats, both for input and
+output. Moreover, you can :ref:`register your own formats <newformats>`.
+
+cli
+===
+
+The ``cli`` format is currently export-only. The exports produce a representation
+table suited to a terminal.
+
+When exporting to a CLI you can pass the table format  with the ``tablefmt``
+parameter, the supported formats are::
+
+    >>> import tabulate
+    >>> list(tabulate._table_formats)
+    ['simple', 'plain', 'grid', 'fancy_grid', 'github', 'pipe', 'orgtbl',
+     'jira', 'presto', 'psql', 'rst', 'mediawiki', 'moinmoin', 'youtrack',
+     'html', 'latex', 'latex_raw', 'latex_booktabs', 'tsv', 'textile']
+
+For example::
+
+    dataset.export("cli", tablefmt="github")
+    dataset.export("cli", tablefmt="grid")
+
+This format is optional, install Tablib with ``pip install "tablib[cli]"`` to
+make the format available.
+
+csv
+===
+
+When you import CSV data, you can specify if the first line of your data source
+is headers with the ``headers`` boolean parameter (defaults to ``True``)::
+
+    import tablib
+
+    tablib.import_set(your_data_stream, format='csv', headers=False)
+
+When exporting with the ``csv`` format, the top row will contain headers, if
+they have been set. Otherwise, the top row will contain the first row of the
+dataset.
+
+When importing a CSV data source or exporting a dataset as CSV, you can pass any
+parameter supported by the :py:func:`csv.reader` and :py:func:`csv.writer`
+functions. For example::
+
+    tablib.import_set(your_data_stream, format='csv', dialect='unix')
+
+    dataset.export('csv', delimiter=' ', quotechar='|')
+
+.. admonition:: Line endings
+
+     Exporting uses \\r\\n line endings by default so, make sure to include
+     ``newline=''`` otherwise you will get a blank line between each row
+     when you open the file in Excel::
+
+         with open('output.csv', 'w', newline='') as f:
+             f.write(dataset.export('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.
+
+dbf
+===
+
+Import/export using the dBASE_ format.
+
+.. admonition:: Binary Warning
+
+    The ``dbf`` format contains binary data, so make sure to write in binary
+    mode::
+
+        with open('output.dbf', 'wb') as f:
+            f.write(dataset.export('dbf')
+
+.. _dBASE: https://en.wikipedia.org/wiki/DBase
+
+df (DataFrame)
+==============
+
+Import/export using the pandas_ DataFrame format. This format is optional,
+install Tablib with ``pip install "tablib[pandas]"`` to make the format available.
+
+.. _pandas: https://pandas.pydata.org/
+
+html
+====
+
+The ``html`` format is currently export-only. The exports produce an HTML page
+with the data in a ``<table>``. If headers have been set, they will be used as
+table headers.
+
+This format is optional, install Tablib with ``pip install "tablib[html]"`` to
+make the format available.
+
+jira
+====
+
+The ``jira`` format is currently export-only. Exports format the dataset
+according to the Jira table syntax::
+
+    ||heading 1||heading 2||heading 3||
+    |col A1|col A2|col A3|
+    |col B1|col B2|col B3|
+
+json
+====
+
+Import/export using the JSON_ format. If headers have been set, a JSON list of
+objects will be returned. If no headers have been set, a JSON list of lists
+(rows) will be returned instead.
+
+Import assumes (for now) that headers exist.
+
+.. _JSON: http://json.org/
+
+latex
+=====
+
+Import/export using the LaTeX_ format. This format is export-only.
+If a title has been set, it will be exported as the table caption.
+
+.. _LaTeX: https://www.latex-project.org/
+
+ods
+===
+
+Export data in OpenDocument Spreadsheet format. The ``ods`` format is currently
+export-only.
+
+This format is optional, install Tablib with ``pip install "tablib[ods]"`` to
+make the format available.
+
+.. admonition:: Binary Warning
+
+    :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)
+
+rst
+===
+
+Export data as a reStructuredText_ table representation of a dataset. The
+``rst`` format is export-only.
+
+Exporting returns a simple table if the text in the first column is never
+wrapped, otherwise returns a grid table::
+
+    >>> from tablib import Dataset
+    >>> bits = ((0, 0), (1, 0), (0, 1), (1, 1))
+    >>> data = Dataset()
+    >>> data.headers = ['A', 'B', 'A and B']
+    >>> for a, b in bits:
+    ...     data.append([bool(a), bool(b), bool(a * b)])
+    >>> table = data.export('rst')
+    >>> table.split('\\n') == [
+    ...     '=====  =====  =====',
+    ...     '  A      B    A and',
+    ...     '                B  ',
+    ...     '=====  =====  =====',
+    ...     'False  False  False',
+    ...     'True   False  False',
+    ...     'False  True   False',
+    ...     'True   True   True ',
+    ...     '=====  =====  =====',
+    ... ]
+    True
+
+.. _reStructuredText: http://docutils.sourceforge.net/rst.html
+
+tsv
+===
+
+A variant of the csv_ format with tabulators as fields separators.
+
+xls
+===
+
+Import/export data in Legacy Excel Spreadsheet representation.
+
+This format is optional, install Tablib with ``pip install "tablib[xls]"`` to
+make the format available.
+
+.. note::
+
+    XLS files are limited to a maximum of 65,000 rows. Use xlsx_ to avoid this
+    limitation.
+
+.. admonition:: Binary Warning
+
+    The ``xls`` file format is binary, so make sure to write in binary mode::
+
+        with open('output.xls', 'wb') as f:
+            f.write(data.export('xls'))
+
+xlsx
+====
+
+Import/export data in Excel 07+ Spreadsheet representation.
+
+This format is optional, install Tablib with ``pip install "tablib[xlsx]"`` to
+make the format available.
+
+The ``import_set()`` and ``import_book()`` methods accept keyword
+argument ``read_only``.  If its value is ``True`` (the default), the
+XLSX data source is read lazily.  Lazy reading generally reduces time
+and memory consumption, especially for large spreadsheets.  However,
+it relies on the XLSX data source declaring correct dimensions.  Some
+programs generate XLSX files with incorrect dimensions.  Such files
+may need to be loaded with this optimization turned off by passing
+``read_only=False``.
+
+.. note::
+
+    When reading an ``xlsx`` file containing formulas in its cells, Tablib will
+    read the cell values, not the cell formulas.
+
+.. versionchanged:: 2.0.0
+
+    Reads cell values instead of formulas.
+
+.. admonition:: Binary Warning
+
+    The ``xlsx`` file format is binary, so make sure to write in binary mode::
+
+        with open('output.xlsx', 'wb') as f:
+            f.write(data.export('xlsx'))
+
+yaml
+====
+
+Import/export data in the YAML_ format.
+When exporting, if headers have been 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.
+
+Import assumes (for now) that headers exist.
+
+This format is optional, install Tablib with ``pip install "tablib[yaml]"`` to
+make the format available.
+
+.. _YAML: https://yaml.org

docs/index.rst

@@ -1,7 +1,7 @@
 .. Tablib documentation master file, created by
    sphinx-quickstart on Tue Oct  5 15:25:21 2010.
    You can adapt this file completely to your liking, but it should at least
-   contain the root `toctree` directive.
+   contain the root ``toctree`` directive.
 
 Tablib: Pythonic Tabular Datasets
 =================================
@@ -53,11 +53,11 @@ and seamless format import & export.
 Testimonials
 ------------
 
-`National Geographic <http://www.nationalgeographic.com/>`_,
-`Digg, Inc <http://digg.com/>`_,
-`Northrop Grumman <http://www.northropgrumman.com/>`_,
-`Discovery Channel <http://dsc.discovery.com/>`_,
-and `The Sunlight Foundation <http://sunlightfoundation.com/>`_ use Tablib internally.
+`National Geographic <https://www.nationalgeographic.com/>`_,
+`Digg, Inc <https://digg.com/>`_,
+`Northrop Grumman <https://www.northropgrumman.com/>`_,
+`Discovery Channel <https://dsc.discovery.com/>`_,
+and `The Sunlight Foundation <https://sunlightfoundation.com/>`_ use Tablib internally.
 
 
 
@@ -98,6 +98,11 @@ This part of the documentation, which is mostly prose, begins with some backgrou
 
    tutorial
 
+.. toctree::
+   :maxdepth: 2
+
+   formats
+
 .. toctree::
    :maxdepth: 2
 

docs/install.rst

@@ -15,18 +15,36 @@ Installing Tablib
 Distribute & Pip
 ----------------
 
-Of course, the recommended way to install Tablib is with `pip <http://www.pip-installer.org/>`_:
+Of course, the recommended way to install Tablib is with `pip <https://pip.pypa.io>`_:
 
 .. code-block:: console
 
-    $ pip install tablib[pandas]
+    $ pip install tablib
 
+You can also choose to install more dependencies to have more import/export
+formats available:
+
+.. code-block:: console
+
+    $ pip install "tablib[xlsx]"
+
+Or all possible formats:
+
+.. code-block:: console
+
+    $ pip install "tablib[all]"
+
+which is equivalent to:
+
+.. code-block:: console
+
+    $ pip install "tablib[html, pandas, ods, xls, xlsx, yaml]"
 
 -------------------
 Download the Source
 -------------------
 
-You can also install tablib from source.
+You can also install Tablib from source.
 The latest release (|version|) is available from GitHub.
 
 * tarball_
@@ -45,8 +63,8 @@ or install it into your site-packages easily.
 
 To download the full source history from Git, see :ref:`Source Control <scm>`.
 
-.. _tarball: http://github.com/kennethreitz/tablib/tarball/master
-.. _zipball: http://github.com/kennethreitz/tablib/zipball/master
+.. _tarball: https://github.com/jazzband/tablib/tarball/master
+.. _zipball: https://github.com/jazzband/tablib/zipball/master
 
 
 .. _updates:
@@ -56,8 +74,8 @@ Staying Updated
 
 The latest version of Tablib will always be available here:
 
-* PyPI: http://pypi.python.org/pypi/tablib/
-* GitHub: http://github.com/kennethreitz/tablib/
+* PyPI: https://pypi.org/project/tablib/
+* GitHub: https://github.com/jazzband/tablib/
 
 When a new version is available, upgrading is simple::
 

docs/intro.rst

@@ -6,7 +6,7 @@ Introduction
 This part of the documentation covers all the interfaces of Tablib.
 Tablib is a format-agnostic tabular dataset library, written in Python.
 It allows you to Pythonically import, export, and manipulate tabular data sets.
-Advanced features include segregation, dynamic columns, tags / filtering, and
+Advanced features include segregation, dynamic columns, tags/filtering, and
 seamless format import/export.
 
 
@@ -23,31 +23,13 @@ Tablib was developed with a few :pep:`20` idioms in mind.
 
 All contributions to Tablib should keep these important rules in mind.
 
-.. mit:
-
-MIT License
------------
-
-A large number of open source projects you find today are `GPL Licensed`_.
-While the GPL has its time and place, it should most certainly not be your
-go-to license for your next open source project.
-
-A project that is released as GPL cannot be used in any commercial product
-without the product itself also being offered as open source. The MIT, BSD, and
-ISC licenses are great alternatives to the GPL that allow your open-source
-software to be used in proprietary, closed-source software.
-
-Tablib is released under terms of `The MIT License`_.
-
-.. _`GPL Licensed`: http://www.opensource.org/licenses/gpl-license.php
-.. _`The MIT License`: http://www.opensource.org/licenses/mit-license.php
-
-
 .. _license:
 
 Tablib License
 --------------
 
+Tablib is released under terms of `The MIT License`_.
+
 Copyright 2017 Kenneth Reitz
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
@@ -68,23 +50,14 @@ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 THE SOFTWARE.
 
+.. _`The MIT License`: https://opensource.org/licenses/mit-license.php
 
 .. _pythonsupport:
 
 Pythons Supported
 -----------------
 
-At this time, the following Python platforms are officially supported:
+Python 3.6+ is officially supported.
 
-* cPython 2.7
-* cPython 3.3
-* cPython 3.4
-* cPython 3.5
-* cPython 3.6
+Now, go :ref:`install Tablib <install>`.
 
-Support for other Pythons will be rolled out soon.
-
-
-
-
-Now, go :ref:`Install Tablib <install>`.

docs/tutorial.rst

@@ -5,9 +5,6 @@ Quickstart
 ==========
 
 
-.. module:: tablib
-
-
 Eager to get started?
 This page gives a good introduction in how to get started with Tablib.
 This assumes you already have Tablib installed.
@@ -38,7 +35,7 @@ You can now start filling this :class:`Dataset <tablib.Dataset>` object with dat
 
 .. admonition:: Example Context
 
-    From here on out, if you see ``data``, assume that it's a fresh 
+    From here on out, if you see ``data``, assume that it's a fresh
     :class:`Dataset <tablib.Dataset>` object.
 
 
@@ -109,10 +106,18 @@ Importing Data
 --------------
 Creating a :class:`tablib.Dataset` object by importing a pre-existing file is simple. ::
 
-   imported_data = Dataset().load(open('data.csv').read())
+    with open('data.csv', 'r') as fh:
+        imported_data = Dataset().load(fh)
 
 This detects what sort of data is being passed in, and uses an appropriate formatter to do the import. So you can import from a variety of different file types.
 
+.. admonition:: Source without headers
+
+    When the format is :class:`csv <Dataset.csv>`, :class:`tsv <Dataset.tsv>`, :class:`dbf <Dataset.dbf>`, :class:`xls <Dataset.xls>` or :class:`xlsx <Dataset.xlsx>`, and the data source does not have headers, the import should be done as follows ::
+
+    with open('data.csv', 'r') as fh:
+        imported_data = Dataset().load(fh, headers=False)
+
 --------------
 Exporting Data
 --------------
@@ -203,7 +208,7 @@ Delete a range of rows::
 Advanced Usage
 ==============
 
-This part of the documentation services to give you an idea that are otherwise hard to extract from the :ref:`API Documentation <api>`
+This part of the documentation services to give you an idea that are otherwise hard to extract from the :ref:`API Documentation <api>`.
 
 And now for something completely different.
 
@@ -290,24 +295,36 @@ Let's tag some students. ::
     students.headers = ['first', 'last']
 
     students.rpush(['Kenneth', 'Reitz'], tags=['male', 'technical'])
+    students.rpush(['Daniel', 'Dupont'], tags=['male', 'creative' ])
     students.rpush(['Bessie', 'Monke'], tags=['female', 'creative'])
 
-Now that we have extra meta-data on our rows, we can 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 Female students. ::
 
+    >>> students.filter(['female']).yaml
+    - {first: Bessie, Last: Monke}
 
-    >>> students.filter(['male']).yaml
-    - {first: Kenneth, Last: Reitz}
+By default, when you pass a list of tags you get filter type or. :: 
+
+    >>> students.filter(['female', 'creative']).yaml
+    - {first: Daniel, Last: Dupont}
+    - {first: Bessie, Last: Monke}
+
+Using chaining you can get a filter type and. ::
+
+    >>> students.filter(['female']).filter(['creative']).yaml
+    - {first: Bessie, Last: Monke}
 
 It's that simple. The original :class:`Dataset` is untouched.
 
 Open an Excel Workbook and read first sheet
---------------------------------
+-------------------------------------------
 
-To open an Excel 2007 and later workbook with a single sheet (or a workbook with multiple sheets but you just want the first sheet), use the following:
+Open an Excel 2007 and later workbook with a single sheet (or a workbook with multiple sheets but you just want the first sheet). ::
 
-data = tablib.Dataset()
-data.xlsx = open('my_excel_file.xlsx', 'rb').read()
-print(data)
+    data = tablib.Dataset()
+    with open('my_excel_file.xlsx', 'rb') as fh:
+        data.load(fh, 'xlsx')
+    print(data)
 
 Excel Workbook With Multiple Sheets
 ------------------------------------
@@ -324,7 +341,7 @@ All we have to do is add them to a :class:`Databook` object... ::
 ... and export to Excel just like :class:`Datasets <Dataset>`. ::
 
     with open('students.xls', 'wb') as f:
-        f.write(book.xls)
+        f.write(book.export('xls'))
 
 The resulting ``students.xls`` file will contain a separate spreadsheet for each :class:`Dataset` object in the :class:`Databook`.
 

pyproject.toml

@@ -0,0 +1,2 @@
+[tool.isort]
+profile = "black"

pytest.ini

@@ -0,0 +1,3 @@
+[pytest]
+norecursedirs = .git .*
+addopts = -rsxX --showlocals --tb=native --cov=tablib --cov=tests --cov-report xml --cov-report term --cov-report html

requirements.txt

@@ -1,22 +0,0 @@
-backports.csv==1.0.6
-certifi==2017.7.27.1
-chardet==3.0.4
-et-xmlfile==1.0.1
-idna==2.6
-jdcal==1.3
-numpy==1.13.1
-odfpy==1.3.5
-openpyxl==2.4.8
-pandas==0.20.3
-pkginfo==1.4.1
-python-dateutil==2.6.1
-pytz==2017.2
-PyYAML==3.12
-requests==2.18.4
-requests-toolbelt==0.8.0
-six==1.10.0
-tqdm==4.15.0
-unicodecsv==0.14.1
-urllib3==1.22
-xlrd==1.1.0
-xlwt==1.3.0

setup.py

@@ -1,61 +1,29 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
-import os
-import re
-import sys
-
-try:
-    from setuptools import setup
-except ImportError:
-    from distutils.core import setup
-
-if sys.argv[-1] == 'publish':
-    os.system("python setup.py sdist upload")
-    sys.exit()
-
-
-if sys.argv[-1] == 'test':
-    try:
-        __import__('py')
-    except ImportError:
-        print('py.test required.')
-        sys.exit(1)
-
-    errors = os.system('py.test test_tablib.py')
-    sys.exit(bool(errors))
-
-packages = [
-    'tablib', 'tablib.formats',
-    'tablib.packages',
-    'tablib.packages.dbfpy',
-    'tablib.packages.dbfpy3'
-]
-
-install = [
-    'odfpy',
-    'openpyxl>=2.4.0',
-    'backports.csv',
-    'xlrd',
-    'xlwt',
-    'pyyaml',
-]
-
-
-with open('tablib/core.py', 'r') as fd:
-    version = re.search(r'^__version__\s*=\s*[\'"]([^\'"]*)[\'"]',
-                        fd.read(), re.MULTILINE).group(1)
+from setuptools import find_packages, setup
 
 setup(
     name='tablib',
-    version=version,
+    use_scm_version={
+        'write_to': 'src/tablib/_version.py',
+    },
+    setup_requires=['setuptools_scm'],
     description='Format agnostic tabular data library (XLS, JSON, YAML, CSV)',
-    long_description=(open('README.rst').read() + '\n\n' +
-        open('HISTORY.rst').read()),
+    long_description=(
+        open('README.md').read() + '\n\n' + open('HISTORY.md').read()
+    ),
+    long_description_content_type="text/markdown",
     author='Kenneth Reitz',
     author_email='me@kennethreitz.org',
-    url='http://python-tablib.org',
-    packages=packages,
+    maintainer='Jazzband',
+    maintainer_email='roadies@jazzband.co',
+    url='https://tablib.readthedocs.io',
+    project_urls={
+        "Documentation": "https://tablib.readthedocs.io",
+        "Source": "https://github.com/jazzband/tablib",
+    },
+    packages=find_packages(where="src"),
+    package_dir={"": "src"},
     license='MIT',
     classifiers=[
         'Development Status :: 5 - Production/Stable',
@@ -63,14 +31,22 @@ setup(
         'Natural Language :: English',
         'License :: OSI Approved :: MIT License',
         'Programming Language :: Python',
-        'Programming Language :: Python :: 2.7',
-        'Programming Language :: Python :: 3.4',
-        'Programming Language :: Python :: 3.5',
+        'Programming Language :: Python :: 3 :: Only',
+        'Programming Language :: Python :: 3',
         'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
+        'Programming Language :: Python :: 3.9',
     ],
-    tests_require=['pytest'],
-    install_requires=install,
+    python_requires='>=3.6',
     extras_require={
+        'all': ['markuppy', 'odfpy', 'openpyxl>=2.6.0', 'pandas', 'pyyaml', 'tabulate', 'xlrd', 'xlwt'],
+        'cli': ['tabulate'],
+        'html': ['markuppy'],
+        'ods': ['odfpy'],
         'pandas': ['pandas'],
+        'xls': ['xlrd', 'xlwt'],
+        'xlsx': ['openpyxl>=2.6.0'],
+        'yaml': ['pyyaml'],
     },
 )

src/tablib/__init__.py

@@ -0,0 +1,19 @@
+""" Tablib. """
+try:
+    # Generated by setuptools-scm.
+    from ._version import version as __version__
+except ImportError:
+    # Some broken installation.
+    __version__ = None
+
+
+from tablib.core import (  # noqa: F401
+    Databook,
+    Dataset,
+    InvalidDatasetType,
+    InvalidDimensions,
+    UnsupportedFormat,
+    detect_format,
+    import_book,
+    import_set,
+)

src/tablib/core.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
 """
     tablib.core
     ~~~~~~~~~~~
 
     This module implements the central Tablib objects.
 
-    :copyright: (c) 2016 by Kenneth Reitz.
+    :copyright: (c) 2016 by Kenneth Reitz. 2019 Jazzband.
     :license: MIT, see LICENSE for more details.
 """
 
@@ -13,21 +12,24 @@ from collections import OrderedDict
 from copy import copy
 from operator import itemgetter
 
-from tablib import formats
-
-from tablib.compat import unicode
-
+from tablib.exceptions import (
+    HeadersNeeded,
+    InvalidDatasetIndex,
+    InvalidDatasetType,
+    InvalidDimensions,
+    UnsupportedFormat,
+)
+from tablib.formats import registry
+from tablib.utils import normalize_input
 
 __title__ = 'tablib'
-__version__ = '0.13.0'
-__build__ = 0x001201
 __author__ = 'Kenneth Reitz'
 __license__ = 'MIT'
-__copyright__ = 'Copyright 2017 Kenneth Reitz'
+__copyright__ = 'Copyright 2017 Kenneth Reitz. 2019 Jazzband.'
 __docformat__ = 'restructuredtext'
 
 
-class Row(object):
+class Row:
     """Internal Row object. Mainly used for filtering."""
 
     __slots__ = ['_row', 'tags']
@@ -45,9 +47,6 @@ class Row(object):
     def __repr__(self):
         return repr(self._row)
 
-    def __getslice__(self, i, j):
-        return self._row[i:j]
-
     def __getitem__(self, i):
         return self._row[i]
 
@@ -58,23 +57,16 @@ class Row(object):
         del self._row[i]
 
     def __getstate__(self):
-
-        slots = dict()
-
-        for slot in self.__slots__:
-            attribute = getattr(self, slot)
-            slots[slot] = attribute
-
-        return slots
+        return self._row, self.tags
 
     def __setstate__(self, state):
-        for (k, v) in list(state.items()): setattr(self, k, v)
+        self._row, self.tags = state
 
     def rpush(self, value):
-        self.insert(0, value)
+        self.insert(len(self._row), value)
 
     def lpush(self, value):
-        self.insert(len(value), value)
+        self.insert(0, value)
 
     def append(self, value):
         self.rpush(value)
@@ -98,7 +90,7 @@ class Row(object):
     def has_tag(self, tag):
         """Returns true if current row contains tag."""
 
-        if tag == None:
+        if tag is None:
             return False
         elif isinstance(tag, str):
             return (tag in self.tags)
@@ -106,9 +98,7 @@ class Row(object):
             return bool(len(set(tag) & set(self.tags)))
 
 
-
-
-class Dataset(object):
+class Dataset:
     """The :class:`Dataset` object is the heart of Tablib. It provides all core
     functionality.
 
@@ -123,7 +113,7 @@ class Dataset(object):
 
 
     Setting columns is similar. The column data length must equal the
-    current height of the data and headers must be set ::
+    current height of the data and headers must be set. ::
 
         data = tablib.Dataset()
         data.headers = ('first_name', 'last_name')
@@ -142,21 +132,19 @@ class Dataset(object):
 
         data = tablib.Dataset(*data, headers=headers)
 
-    :param \*args: (optional) list of rows to populate Dataset
+    :param \\*args: (optional) list of rows to populate Dataset
     :param headers: (optional) list strings for Dataset header row
     :param title: (optional) string to use as title of the Dataset
 
 
     .. admonition:: Format Attributes Definition
 
-     If you look at the code, the various output/import formats are not
-     defined within the :class:`Dataset` object. To add support for a new format, see
-     :ref:`Adding New Formats <newformats>`.
+    If you look at the code, the various output/import formats are not
+    defined within the :class:`Dataset` object. To add support for a new format, see
+    :ref:`Adding New Formats <newformats>`.
 
     """
 
-    _formats = {}
-
     def __init__(self, *args, **kwargs):
         self._data = list(Row(arg) for arg in args)
         self.__headers = None
@@ -171,17 +159,13 @@ class Dataset(object):
 
         self.title = kwargs.get('title')
 
-        self._register_formats()
-
-
     def __len__(self):
         return self.height
 
-
     def __getitem__(self, key):
-        if isinstance(key, (str, unicode)):
+        if isinstance(key, str):
             if key in self.headers:
-                pos = self.headers.index(key) # get 'key' index from each data
+                pos = self.headers.index(key)  # get 'key' index from each data
                 return [row[pos] for row in self._data]
             else:
                 raise KeyError
@@ -196,9 +180,8 @@ class Dataset(object):
         self._validate(value)
         self._data[key] = Row(value)
 
-
     def __delitem__(self, key):
-        if isinstance(key, (str, unicode)):
+        if isinstance(key, str):
 
             if key in self.headers:
 
@@ -214,22 +197,21 @@ class Dataset(object):
         else:
             del self._data[key]
 
-
     def __repr__(self):
         try:
             return '<%s dataset>' % (self.title.lower())
         except AttributeError:
             return '<dataset object>'
 
-    def __unicode__(self):
+    def __str__(self):
         result = []
 
-        # Add unicode representation of headers.
+        # Add str representation of headers.
         if self.__headers:
-            result.append([unicode(h) for h in self.__headers])
+            result.append([str(h) for h in self.__headers])
 
-        # Add unicode representation of rows.
-        result.extend(list(map(unicode, row)) for row in self._data)
+        # Add str representation of rows.
+        result.extend(list(map(str, row)) for row in self._data)
 
         lens = [list(map(len, row)) for row in result]
         field_lens = list(map(max, zip(*lens)))
@@ -242,31 +224,16 @@ class Dataset(object):
 
         return '\n'.join(format_string.format(*row) for row in result)
 
-    def __str__(self):
-        return self.__unicode__()
-
     # ---------
     # Internals
     # ---------
 
-    @classmethod
-    def _register_formats(cls):
-        """Adds format properties."""
-        for fmt in formats.available:
-            try:
-                try:
-                    setattr(cls, fmt.title, property(fmt.export_set, fmt.import_set))
-                    setattr(cls, 'get_%s' % fmt.title, fmt.export_set)
-                    setattr(cls, 'set_%s' % fmt.title, fmt.import_set)
-                    cls._formats[fmt.title] = (fmt.export_set, fmt.import_set)
-                except AttributeError:
-                    setattr(cls, fmt.title, property(fmt.export_set))
-                    setattr(cls, 'get_%s' % fmt.title, fmt.export_set)
-                    cls._formats[fmt.title] = (fmt.export_set, None)
-
-            except AttributeError:
-                cls._formats[fmt.title] = (None, None)
+    def _get_in_format(self, fmt_key, **kwargs):
+        return registry.get_format(fmt_key).export_set(self, **kwargs)
 
+    def _set_in_format(self, fmt_key, in_stream, **kwargs):
+        in_stream = normalize_input(in_stream)
+        return registry.get_format(fmt_key).import_set(self, in_stream, **kwargs)
 
     def _validate(self, row=None, col=None, safety=False):
         """Assures size of every row in dataset is of proper proportions."""
@@ -278,7 +245,7 @@ class Dataset(object):
             else:
                 is_valid = (len(col) == self.height) if self.height else True
         else:
-            is_valid = all((len(x) == self.width for x in self._data))
+            is_valid = all(len(x) == self.width for x in self._data)
 
         if is_valid:
             return True
@@ -287,7 +254,6 @@ class Dataset(object):
                 raise InvalidDimensions
             return False
 
-
     def _package(self, dicts=True, ordered=True):
         """Packages Dataset into lists of dictionaries for transmission."""
         # TODO: Dicts default to false?
@@ -312,7 +278,6 @@ class Dataset(object):
                     except IndexError:
                         raise InvalidDatasetIndex
 
-
         if self.headers:
             if dicts:
                 data = [dict_pack(list(zip(self.headers, data_row))) for data_row in _data]
@@ -323,17 +288,14 @@ class Dataset(object):
 
         return data
 
-
-
     def _get_headers(self):
         """An *optional* list of strings to be used for header rows and attribute names.
 
-        This must be set manually. The given list length must equal :class:`Dataset.width`.
+        This must be set manually. The given list length must equal :attr:`Dataset.width`.
 
         """
         return self.__headers
 
-
     def _set_headers(self, collection):
         """Validating headers setter."""
         self._validate(collection)
@@ -347,7 +309,6 @@ class Dataset(object):
 
     headers = property(_get_headers, _set_headers)
 
-
     def _get_dict(self):
         """A native Python representation of the :class:`Dataset` object. If headers have
         been set, a list of Python dictionaries will be returned. If no headers have been set,
@@ -361,13 +322,12 @@ class Dataset(object):
         """
         return self._package()
 
-
     def _set_dict(self, pickle):
         """A native Python representation of the Dataset object. If headers have been
         set, a list of Python dictionaries will be returned. If no headers have been
         set, a list of tuples (rows) will be returned instead.
 
-        A dataset object can also be imported by setting the :class:`Dataset.dict` attribute. ::
+        A dataset object can also be imported by setting the :attr:`Dataset.dict` attribute. ::
 
             data = tablib.Dataset()
             data.dict = [{'age': 90, 'first_name': 'Kenneth', 'last_name': 'Reitz'}]
@@ -394,7 +354,6 @@ class Dataset(object):
 
     dict = property(_get_dict, _set_dict)
 
-
     def _clean_col(self, col):
         """Prepares the given column for insert/append."""
 
@@ -412,7 +371,6 @@ class Dataset(object):
 
         return col
 
-
     @property
     def height(self):
         """The number of rows currently in the :class:`Dataset`.
@@ -420,7 +378,6 @@ class Dataset(object):
         """
         return len(self._data)
 
-
     @property
     def width(self):
         """The number of columns currently in the :class:`Dataset`.
@@ -435,231 +392,39 @@ class Dataset(object):
             except TypeError:
                 return 0
 
-
     def load(self, in_stream, format=None, **kwargs):
         """
         Import `in_stream` to the :class:`Dataset` object using the `format`.
+        `in_stream` can be a file-like object, a string, or a bytestring.
 
-        :param \*\*kwargs: (optional) custom configuration to the format `import_set`.
+        :param \\*\\*kwargs: (optional) custom configuration to the format `import_set`.
         """
 
+        stream = normalize_input(in_stream)
         if not format:
-            format = detect_format(in_stream)
+            format = detect_format(stream)
+
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'import_set'):
+            raise UnsupportedFormat(f'Format {format} cannot be imported.')
 
-        export_set, import_set = self._formats.get(format, (None, None))
         if not import_set:
-            raise UnsupportedFormat('Format {0} cannot be imported.'.format(format))
+            raise UnsupportedFormat(f'Format {format} cannot be imported.')
 
-        import_set(self, in_stream, **kwargs)
+        fmt.import_set(self, stream, **kwargs)
         return self
 
-
-
     def export(self, format, **kwargs):
         """
         Export :class:`Dataset` object to `format`.
 
-        :param \*\*kwargs: (optional) custom configuration to the format `export_set`.
+        :param \\*\\*kwargs: (optional) custom configuration to the format `export_set`.
         """
-        export_set, import_set = self._formats.get(format, (None, None))
-        if not export_set:
-            raise UnsupportedFormat('Format {0} cannot be exported.'.format(format))
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'export_set'):
+            raise UnsupportedFormat(f'Format {format} cannot be exported.')
 
-        return export_set(self, **kwargs)
-
-    # -------
-    # Formats
-    # -------
-
-    @property
-    def xls():
-        """A Legacy Excel Spreadsheet representation of the :class:`Dataset` object, with :ref:`separators`. Cannot be set.
-
-        .. note::
-
-            XLS files are limited to a maximum of 65,000 rows. Use :class:`Dataset.xlsx` to avoid this limitation.
-
-         .. admonition:: Binary Warning
-
-             :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)
-        """
-        pass
-
-    @property
-    def xlsx():
-        """An Excel '07+ Spreadsheet representation of the :class:`Dataset` object, with :ref:`separators`. Cannot be set.
-
-         .. admonition:: Binary Warning
-
-             :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)
-        """
-        pass
-
-    @property
-    def ods():
-        """An OpenDocument Spreadsheet representation of the :class:`Dataset` object, with :ref:`separators`. Cannot be set.
-
-         .. admonition:: Binary Warning
-
-             :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)
-        """
-        pass
-
-    @property
-    def csv():
-        """A CSV representation of the :class:`Dataset` object. The top row will contain
-        headers, if they have been set. Otherwise, the top row will contain
-        the first row of the dataset.
-
-        A dataset object can also be imported by setting the :class:`Dataset.csv` attribute. ::
-
-            data = tablib.Dataset()
-            data.csv = 'age, first_name, last_name\\n90, John, Adams'
-
-        Import assumes (for now) that headers exist.
-
-        .. admonition:: Binary Warning for Python 2
-
-             :class:`Dataset.csv` uses \\r\\n line endings by default so, in Python 2, 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.
-
-        .. admonition:: Line endings for Python 3
-
-             :class:`Dataset.csv` uses \\r\\n line endings by default so, in Python 3, make
-             sure to include newline='' otherwise you will get a blank line between each row
-             when you open the file in Excel::
-
-                 with open('output.csv', 'w', newline='') 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
-
-
-    @property
-    def tsv():
-        """A TSV representation of the :class:`Dataset` object. The top row will contain
-        headers, if they have been set. Otherwise, the top row will contain
-        the first row of the dataset.
-
-        A dataset object can also be imported by setting the :class:`Dataset.tsv` attribute. ::
-
-            data = tablib.Dataset()
-            data.tsv = 'age\tfirst_name\tlast_name\\n90\tJohn\tAdams'
-
-        Import assumes (for now) that headers exist.
-        """
-        pass
-
-    @property
-    def yaml():
-        """A YAML representation of the :class:`Dataset` object. If headers have been
-        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.yaml` attribute: ::
-
-            data = tablib.Dataset()
-            data.yaml = '- {age: 90, first_name: John, last_name: Adams}'
-
-        Import assumes (for now) that headers exist.
-        """
-        pass
-
-    @property
-    def df():
-        """A DataFrame representation of the :class:`Dataset` object.
-
-        A dataset object can also be imported by setting the :class:`Dataset.df` attribute: ::
-
-            data = tablib.Dataset()
-            data.df = DataFrame(np.random.randn(6,4))
-
-        Import assumes (for now) that headers exist.
-        """
-        pass
-
-    @property
-    def json():
-        """A JSON representation of the :class:`Dataset` object. If headers have been
-        set, a JSON list of objects will be returned. If no headers have
-        been set, a JSON list of lists (rows) will be returned instead.
-
-        A dataset object can also be imported by setting the :class:`Dataset.json` attribute: ::
-
-            data = tablib.Dataset()
-            data.json = '[{"age": 90, "first_name": "John", "last_name": "Adams"}]'
-
-        Import assumes (for now) that headers exist.
-        """
-        pass
-
-    @property
-    def html():
-        """A HTML table representation of the :class:`Dataset` object. If
-        headers have been set, they will be used as table headers.
-
-        ..notice:: This method can be used for export only.
-        """
-        pass
-
-    @property
-    def dbf():
-        """A dBASE representation of the :class:`Dataset` object.
-
-        A dataset object can also be imported by setting the
-        :class:`Dataset.dbf` attribute. ::
-
-            # To import data from an existing DBF file:
-            data = tablib.Dataset()
-            data.dbf = open('existing_table.dbf').read()
-
-            # to import data from an ASCII-encoded bytestring:
-            data = tablib.Dataset()
-            data.dbf = '<bytestring of tabular data>'
-
-        .. admonition:: Binary Warning
-
-            :class:`Dataset.dbf` contains binary data, so make sure to write in binary mode::
-
-                with open('output.dbf', 'wb') as f:
-                    f.write(data.dbf)
-        """
-        pass
-
-    @property
-    def latex():
-        """A LaTeX booktabs representation of the :class:`Dataset` object. If a
-        title has been set, it will be exported as the table caption.
-
-        .. note:: This method can be used for export only.
-        """
-        pass
-
-    @property
-    def jira():
-        """A Jira table representation of the :class:`Dataset` object.
-
-        .. note:: This method can be used for export only.
-        """
-        pass
+        return fmt.export_set(self, **kwargs)
 
     # ----
     # Rows
@@ -677,39 +442,35 @@ class Dataset(object):
         self._validate(row)
         self._data.insert(index, Row(row, tags=tags))
 
-
     def rpush(self, row, tags=list()):
         """Adds a row to the end of the :class:`Dataset`.
-        See :class:`Dataset.insert` for additional documentation.
+        See :method:`Dataset.insert` for additional documentation.
         """
 
         self.insert(self.height, row=row, tags=tags)
 
-
     def lpush(self, row, tags=list()):
         """Adds a row to the top of the :class:`Dataset`.
-        See :class:`Dataset.insert` for additional documentation.
+        See :method:`Dataset.insert` for additional documentation.
         """
 
         self.insert(0, row=row, tags=tags)
 
-
     def append(self, row, tags=list()):
         """Adds a row to the :class:`Dataset`.
-        See :class:`Dataset.insert` for additional documentation.
+        See :method:`Dataset.insert` for additional documentation.
         """
 
         self.rpush(row, tags)
 
     def extend(self, rows, tags=list()):
         """Adds a list of rows to the :class:`Dataset` using
-        :class:`Dataset.append`
+        :method:`Dataset.append`
         """
 
         for row in rows:
             self.append(row, tags)
 
-
     def lpop(self):
         """Removes and returns the first row of the :class:`Dataset`."""
 
@@ -718,7 +479,6 @@ class Dataset(object):
 
         return cache
 
-
     def rpop(self):
         """Removes and returns the last row of the :class:`Dataset`."""
 
@@ -727,13 +487,11 @@ class Dataset(object):
 
         return cache
 
-
     def pop(self):
         """Removes and returns the last row of the :class:`Dataset`."""
 
         return self.rpop()
 
-
     # -------
     # Columns
     # -------
@@ -749,20 +507,20 @@ class Dataset(object):
 
             data.append_col(col=random.randint)
 
-        If inserting a column, and :class:`Dataset.headers` is set, the
+        If inserting a column, and :attr:`Dataset.headers` is set, the
         header attribute must be set, and will be considered the header for
         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
+           If inserting a column, and :attr:`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
+           This gives you the ability to :method:`filter <Dataset.filter>` your
            :class:`Dataset` later.
 
         """
@@ -788,7 +546,6 @@ class Dataset(object):
 
             self.headers.insert(index, header)
 
-
         if self.height and self.width:
 
             for i, row in enumerate(self._data):
@@ -798,31 +555,26 @@ class Dataset(object):
         else:
             self._data = [Row([row]) for row in col]
 
-
-
     def rpush_col(self, col, header=None):
         """Adds a column to the end of the :class:`Dataset`.
-        See :class:`Dataset.insert` for additional documentation.
+        See :method:`Dataset.insert` for additional documentation.
         """
 
         self.insert_col(self.width, col, header=header)
 
-
     def lpush_col(self, col, header=None):
         """Adds a column to the top of the :class:`Dataset`.
-        See :class:`Dataset.insert` for additional documentation.
+        See :method:`Dataset.insert` for additional documentation.
         """
 
         self.insert_col(0, col, header=header)
 
-
     def insert_separator(self, index, text='-'):
         """Adds a separator to :class:`Dataset` at given index."""
 
         sep = (index, text)
         self._separators.append(sep)
 
-
     def append_separator(self, text='-'):
         """Adds a :ref:`separator <separators>` to the :class:`Dataset`."""
 
@@ -834,37 +586,35 @@ class Dataset(object):
 
         self.insert_separator(index, text)
 
-
     def append_col(self, col, header=None):
         """Adds a column to the :class:`Dataset`.
-        See :class:`Dataset.insert_col` for additional documentation.
+        See :method:`Dataset.insert_col` for additional documentation.
         """
 
         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
     # ----
 
     def add_formatter(self, col, handler):
-        """Adds a :ref:`formatter` to the :class:`Dataset`.
+        """Adds a formatter to the :class:`Dataset`.
 
         .. versionadded:: 0.9.5
-           :param col: column to. Accepts index int or header str.
-           :param handler: reference to callback function to execute
-           against each cell value.
+
+        :param col: column to. Accepts index int or header str.
+        :param handler: reference to callback function to execute against
+                        each cell value.
         """
 
-        if isinstance(col, unicode):
+        if isinstance(col, str):
             if col in self.headers:
-                col = self.headers.index(col) # get 'key' index from each data
+                col = self.headers.index(col)  # get 'key' index from each data
             else:
                 raise KeyError
 
@@ -875,7 +625,6 @@ class Dataset(object):
 
         return True
 
-
     def filter(self, tag):
         """Returns a new instance of the :class:`Dataset`, excluding any rows
         that do not contain the given :ref:`tags <tags>`.
@@ -885,7 +634,6 @@ class Dataset(object):
 
         return _dset
 
-
     def sort(self, col, reverse=False):
         """Sort a :class:`Dataset` by a specific column, given string (for
         header) or integer (for column index). The order can be reversed by
@@ -895,7 +643,7 @@ class Dataset(object):
         sorted.
         """
 
-        if isinstance(col, (str, unicode)):
+        if isinstance(col, str):
 
             if not self.headers:
                 raise HeadersNeeded
@@ -921,10 +669,8 @@ class Dataset(object):
                     row = item
                 _dset.append(row=row)
 
-
         return _dset
 
-
     def transpose(self):
         """Transpose a :class:`Dataset`, turning rows into columns and vice
         versa, returning a new ``Dataset`` instance. The first row of the
@@ -953,7 +699,6 @@ class Dataset(object):
             _dset.append(row=row_data)
         return _dset
 
-
     def stack(self, other):
         """Stack two :class:`Dataset` instances together by
         joining at the row level, and return new combined
@@ -976,7 +721,6 @@ class Dataset(object):
 
         return _dset
 
-
     def stack_cols(self, other):
         """Stack two :class:`Dataset` instances together by
         joining at the column level, and return a new
@@ -1010,20 +754,17 @@ class Dataset(object):
 
         return _dset
 
-
     def remove_duplicates(self):
         """Removes all duplicate rows from the :class:`Dataset` object
         while maintaining the original order."""
         seen = set()
         self._data[:] = [row for row in self._data if not (tuple(row) in seen or seen.add(tuple(row)))]
 
-
     def wipe(self):
         """Removes all content and headers from the :class:`Dataset` object."""
         self._data = list()
         self.__headers = None
 
-
     def subset(self, rows=None, cols=None):
         """Returns a new instance of the :class:`Dataset`,
         including only specified rows and columns.
@@ -1039,13 +780,13 @@ class Dataset(object):
         if cols is None:
             cols = list(self.headers)
 
-        #filter out impossible rows and columns
+        # filter out impossible rows and columns
         rows = [row for row in rows if row in range(self.height)]
         cols = [header for header in cols if header in self.headers]
 
         _dset = Dataset()
 
-        #filtering rows and columns
+        # filtering rows and columns
         _dset.headers = list(cols)
 
         _dset._data = []
@@ -1064,21 +805,12 @@ class Dataset(object):
         return _dset
 
 
-
-class Databook(object):
+class Databook:
     """A book of :class:`Dataset` objects.
     """
 
-    _formats = {}
-
     def __init__(self, sets=None):
-
-        if sets is None:
-            self._datasets = list()
-        else:
-            self._datasets = sets
-
-        self._register_formats()
+        self._datasets = sets or []
 
     def __repr__(self):
         try:
@@ -1090,22 +822,6 @@ class Databook(object):
         """Removes all :class:`Dataset` objects from the :class:`Databook`."""
         self._datasets = []
 
-
-    @classmethod
-    def _register_formats(cls):
-        """Adds format properties."""
-        for fmt in formats.available:
-            try:
-                try:
-                    setattr(cls, fmt.title, property(fmt.export_book, fmt.import_book))
-                    cls._formats[fmt.title] = (fmt.export_book, fmt.import_book)
-                except AttributeError:
-                    setattr(cls, fmt.title, property(fmt.export_book))
-                    cls._formats[fmt.title] = (fmt.export_book, None)
-
-            except AttributeError:
-                cls._formats[fmt.title] = (None, None)
-
     def sheets(self):
         return self._datasets
 
@@ -1116,7 +832,6 @@ class Databook(object):
         else:
             raise InvalidDatasetType
 
-
     def _package(self, ordered=True):
         """Packages :class:`Databook` for delivery."""
         collector = []
@@ -1128,80 +843,75 @@ class Databook(object):
 
         for dset in self._datasets:
             collector.append(dict_pack(
-                title = dset.title,
-                data = dset._package(ordered=ordered)
+                title=dset.title,
+                data=dset._package(ordered=ordered)
             ))
         return collector
 
-
     @property
     def size(self):
         """The number of the :class:`Dataset` objects within :class:`Databook`."""
         return len(self._datasets)
 
-    def load(self, format, in_stream, **kwargs):
+    def load(self, in_stream, format, **kwargs):
         """
         Import `in_stream` to the :class:`Databook` object using the `format`.
+        `in_stream` can be a file-like object, a string, or a bytestring.
 
-        :param \*\*kwargs: (optional) custom configuration to the format `import_book`.
+        :param \\*\\*kwargs: (optional) custom configuration to the format `import_book`.
         """
 
+        stream = normalize_input(in_stream)
         if not format:
-            format = detect_format(in_stream)
+            format = detect_format(stream)
 
-        export_book, import_book = self._formats.get(format, (None, None))
-        if not import_book:
-            raise UnsupportedFormat('Format {0} cannot be loaded.'.format(format))
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'import_book'):
+            raise UnsupportedFormat(f'Format {format} cannot be loaded.')
 
-        import_book(self, in_stream, **kwargs)
+        fmt.import_book(self, stream, **kwargs)
         return self
 
     def export(self, format, **kwargs):
         """
         Export :class:`Databook` object to `format`.
 
-        :param \*\*kwargs: (optional) custom configuration to the format `export_book`.
+        :param \\*\\*kwargs: (optional) custom configuration to the format `export_book`.
         """
-        export_book, import_book = self._formats.get(format, (None, None))
-        if not export_book:
-            raise UnsupportedFormat('Format {0} cannot be exported.'.format(format))
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'export_book'):
+            raise UnsupportedFormat(f'Format {format} cannot be exported.')
 
-        return export_book(self, **kwargs)
+        return fmt.export_book(self, **kwargs)
 
 
 def detect_format(stream):
-    """Return format name of given stream."""
-    for fmt in formats.available:
+    """Return format name of given stream (file-like object, string, or bytestring)."""
+    stream = normalize_input(stream)
+    fmt_title = None
+    for fmt in registry.formats():
         try:
             if fmt.detect(stream):
-                return fmt.title
+                fmt_title = fmt.title
+                break
         except AttributeError:
             pass
+        finally:
+            if hasattr(stream, 'seek'):
+                stream.seek(0)
+    return fmt_title
+
 
 def import_set(stream, format=None, **kwargs):
-    """Return dataset of given stream."""
+    """Return dataset of given stream (file-like object, string, or bytestring)."""
 
-    return Dataset().load(stream, format, **kwargs)
+    return Dataset().load(normalize_input(stream), format, **kwargs)
 
 
 def import_book(stream, format=None, **kwargs):
-    """Return dataset of given stream."""
+    """Return dataset of given stream (file-like object, string, or bytestring)."""
 
-    return Databook().load(stream, format, **kwargs)
+    return Databook().load(normalize_input(stream), format, **kwargs)
 
 
-class InvalidDatasetType(Exception):
-    "Only Datasets can be added to a DataBook"
-
-
-class InvalidDimensions(Exception):
-    "Invalid size"
-
-class InvalidDatasetIndex(Exception):
-    "Outside of Dataset size"
-
-class HeadersNeeded(Exception):
-    "Header parameter must be given when appending a column in this Dataset."
-
-class UnsupportedFormat(NotImplementedError):
-    "Format is not supported"
+registry.register_builtins()

src/tablib/exceptions.py

@@ -0,0 +1,18 @@
+class InvalidDatasetType(Exception):
+    "Only Datasets can be added to a DataBook"
+
+
+class InvalidDimensions(Exception):
+    "Invalid size"
+
+
+class InvalidDatasetIndex(Exception):
+    "Outside of Dataset size"
+
+
+class HeadersNeeded(Exception):
+    "Header parameter must be given when appending a column in this Dataset."
+
+
+class UnsupportedFormat(NotImplementedError):
+    "Format is not supported"

src/tablib/formats/__init__.py

@@ -0,0 +1,135 @@
+""" Tablib - formats
+"""
+from collections import OrderedDict
+from functools import partialmethod
+from importlib import import_module
+from importlib.util import find_spec
+
+from tablib.exceptions import UnsupportedFormat
+from tablib.utils import normalize_input
+
+from ._csv import CSVFormat
+from ._json import JSONFormat
+from ._tsv import TSVFormat
+
+uninstalled_format_messages = {
+    "cli": {"package_name": "tabulate package", "extras_name": "cli"},
+    "df": {"package_name": "pandas package", "extras_name": "pandas"},
+    "html": {"package_name": "MarkupPy package", "extras_name": "html"},
+    "ods": {"package_name": "odfpy package", "extras_name": "ods"},
+    "xls": {"package_name": "xlrd and xlwt packages", "extras_name": "xls"},
+    "xlsx": {"package_name": "openpyxl package", "extras_name": "xlsx"},
+    "yaml": {"package_name": "pyyaml package", "extras_name": "yaml"},
+}
+
+
+def load_format_class(dotted_path):
+    try:
+        module_path, class_name = dotted_path.rsplit('.', 1)
+        return getattr(import_module(module_path), class_name)
+    except (ValueError, AttributeError) as err:
+        raise ImportError(f"Unable to load format class '{dotted_path}' ({err})")
+
+
+class FormatDescriptorBase:
+    def __init__(self, key, format_or_path):
+        self.key = key
+        self._format_path = None
+        if isinstance(format_or_path, str):
+            self._format = None
+            self._format_path = format_or_path
+        else:
+            self._format = format_or_path
+
+    def ensure_format_loaded(self):
+        if self._format is None:
+            self._format = load_format_class(self._format_path)
+
+
+class ImportExportBookDescriptor(FormatDescriptorBase):
+    def __get__(self, obj, cls, **kwargs):
+        self.ensure_format_loaded()
+        return self._format.export_book(obj, **kwargs)
+
+    def __set__(self, obj, val):
+        self.ensure_format_loaded()
+        return self._format.import_book(obj, normalize_input(val))
+
+
+class ImportExportSetDescriptor(FormatDescriptorBase):
+    def __get__(self, obj, cls, **kwargs):
+        self.ensure_format_loaded()
+        return self._format.export_set(obj, **kwargs)
+
+    def __set__(self, obj, val):
+        self.ensure_format_loaded()
+        return self._format.import_set(obj, normalize_input(val))
+
+
+class Registry:
+    _formats = OrderedDict()
+
+    def register(self, key, format_or_path):
+        from tablib.core import Databook, Dataset
+
+        # Create Databook.<format> read or read/write properties
+        setattr(Databook, key, ImportExportBookDescriptor(key, format_or_path))
+
+        # Create Dataset.<format> read or read/write properties,
+        # and Dataset.get_<format>/set_<format> methods.
+        setattr(Dataset, key, ImportExportSetDescriptor(key, format_or_path))
+        try:
+            setattr(Dataset, 'get_%s' % key, partialmethod(Dataset._get_in_format, key))
+            setattr(Dataset, 'set_%s' % key, partialmethod(Dataset._set_in_format, key))
+        except AttributeError:
+            setattr(Dataset, 'get_%s' % key, partialmethod(Dataset._get_in_format, key))
+
+        self._formats[key] = format_or_path
+
+    def register_builtins(self):
+        # Registration ordering matters for autodetection.
+        self.register('json', JSONFormat())
+        # xlsx before as xls (xlrd) can also read xlsx
+        if find_spec('openpyxl'):
+            self.register('xlsx', 'tablib.formats._xlsx.XLSXFormat')
+        if find_spec('xlrd') and find_spec('xlwt'):
+            self.register('xls', 'tablib.formats._xls.XLSFormat')
+        if find_spec('yaml'):
+            self.register('yaml', 'tablib.formats._yaml.YAMLFormat')
+        self.register('csv', CSVFormat())
+        self.register('tsv', TSVFormat())
+        if find_spec('odf'):
+            self.register('ods', 'tablib.formats._ods.ODSFormat')
+        self.register('dbf', 'tablib.formats._dbf.DBFFormat')
+        if find_spec('MarkupPy'):
+            self.register('html', 'tablib.formats._html.HTMLFormat')
+        self.register('jira', 'tablib.formats._jira.JIRAFormat')
+        self.register('latex', 'tablib.formats._latex.LATEXFormat')
+        if find_spec('pandas'):
+            self.register('df', 'tablib.formats._df.DataFrameFormat')
+        self.register('rst', 'tablib.formats._rst.ReSTFormat')
+        if find_spec('tabulate'):
+            self.register('cli', 'tablib.formats._cli.CLIFormat')
+
+    def formats(self):
+        for key, frm in self._formats.items():
+            if isinstance(frm, str):
+                self._formats[key] = load_format_class(frm)
+            yield self._formats[key]
+
+    def get_format(self, key):
+        if key not in self._formats:
+            if key in uninstalled_format_messages:
+                raise UnsupportedFormat(
+                    "The '{key}' format is not available. You may want to install the "
+                    "{package_name} (or `pip install \"tablib[{extras_name}]\"`).".format(
+                        **uninstalled_format_messages[key], key=key
+                    )
+                )
+            raise UnsupportedFormat("Tablib has no format '%s' or it is not registered." % key)
+        if isinstance(self._formats[key], str):
+            self._formats[key] = load_format_class(self._formats[key])
+        return self._formats[key]
+
+
+registry = Registry()

src/tablib/formats/_cli.py

@@ -0,0 +1,20 @@
+"""Tablib - Command-line Interface table export support.
+
+   Generates a representation for CLI from the dataset.
+   Wrapper for tabulate library.
+"""
+from tabulate import tabulate as Tabulate
+
+
+class CLIFormat:
+    """ Class responsible to export to CLI Format """
+    title = 'cli'
+    DEFAULT_FMT = 'plain'
+
+    @classmethod
+    def export_set(cls, dataset, **kwargs):
+        """Returns CLI representation of a Dataset."""
+        if dataset.headers:
+            kwargs.setdefault('headers', dataset.headers)
+        kwargs.setdefault('tablefmt', cls.DEFAULT_FMT)
+        return Tabulate(dataset, **kwargs)

src/tablib/formats/_csv.py

@@ -0,0 +1,60 @@
+""" Tablib - *SV Support.
+"""
+
+import csv
+from io import StringIO
+
+
+class CSVFormat:
+    title = 'csv'
+    extensions = ('csv',)
+
+    DEFAULT_DELIMITER = ','
+
+    @classmethod
+    def export_stream_set(cls, dataset, **kwargs):
+        """Returns CSV representation of Dataset as file-like."""
+        stream = StringIO()
+
+        kwargs.setdefault('delimiter', cls.DEFAULT_DELIMITER)
+
+        _csv = csv.writer(stream, **kwargs)
+
+        for row in dataset._package(dicts=False):
+            _csv.writerow(row)
+
+        stream.seek(0)
+        return stream
+
+    @classmethod
+    def export_set(cls, dataset, **kwargs):
+        """Returns CSV representation of Dataset."""
+        stream = cls.export_stream_set(dataset, **kwargs)
+        return stream.getvalue()
+
+    @classmethod
+    def import_set(cls, dset, in_stream, headers=True, **kwargs):
+        """Returns dataset from CSV stream."""
+
+        dset.wipe()
+
+        kwargs.setdefault('delimiter', cls.DEFAULT_DELIMITER)
+
+        rows = csv.reader(in_stream, **kwargs)
+        for i, row in enumerate(rows):
+
+            if (i == 0) and (headers):
+                dset.headers = row
+            elif row:
+                if i > 0 and len(row) < dset.width:
+                    row += [''] * (dset.width - len(row))
+                dset.append(row)
+
+    @classmethod
+    def detect(cls, stream, delimiter=None):
+        """Returns True if given stream is valid CSV."""
+        try:
+            csv.Sniffer().sniff(stream.read(1024), delimiters=delimiter or cls.DEFAULT_DELIMITER)
+            return True
+        except Exception:
+            return False

src/tablib/formats/_dbf.py

@@ -0,0 +1,66 @@
+""" Tablib - DBF Support.
+"""
+import io
+import os
+import tempfile
+
+from tablib.packages.dbfpy import dbf, dbfnew
+from tablib.packages.dbfpy import record as dbfrecord
+
+
+class DBFFormat:
+    title = 'dbf'
+    extensions = ('csv',)
+
+    DEFAULT_ENCODING = 'utf-8'
+
+    @classmethod
+    def export_set(cls, dataset):
+        """Returns DBF representation of a Dataset"""
+        new_dbf = dbfnew.dbf_new()
+        temp_file, temp_uri = tempfile.mkstemp()
+
+        # create the appropriate fields based on the contents of the first row
+        first_row = dataset[0]
+        for fieldname, field_value in zip(dataset.headers, first_row):
+            if type(field_value) in [int, float]:
+                new_dbf.add_field(fieldname, 'N', 10, 8)
+            else:
+                new_dbf.add_field(fieldname, 'C', 80)
+
+        new_dbf.write(temp_uri)
+
+        dbf_file = dbf.Dbf(temp_uri, readOnly=0)
+        for row in dataset:
+            record = dbfrecord.DbfRecord(dbf_file)
+            for fieldname, field_value in zip(dataset.headers, row):
+                record[fieldname] = field_value
+            record.store()
+
+        dbf_file.close()
+        dbf_stream = open(temp_uri, 'rb')
+        stream = io.BytesIO(dbf_stream.read())
+        dbf_stream.close()
+        os.close(temp_file)
+        os.remove(temp_uri)
+        return stream.getvalue()
+
+    @classmethod
+    def import_set(cls, dset, in_stream, headers=True):
+        """Returns a dataset from a DBF stream."""
+
+        dset.wipe()
+        _dbf = dbf.Dbf(in_stream)
+        dset.headers = _dbf.fieldNames
+        for record in range(_dbf.recordCount):
+            row = [_dbf[record][f] for f in _dbf.fieldNames]
+            dset.append(row)
+
+    @classmethod
+    def detect(cls, stream):
+        """Returns True if the given stream is valid DBF"""
+        try:
+            _dbf = dbf.Dbf(stream, readOnly=True)
+            return True
+        except Exception:
+            return False

src/tablib/formats/_df.py

@@ -0,0 +1,41 @@
+""" Tablib - DataFrame Support.
+"""
+
+try:
+    from pandas import DataFrame
+except ImportError:
+    DataFrame = None
+
+
+class DataFrameFormat:
+    title = 'df'
+    extensions = ('df',)
+
+    @classmethod
+    def detect(cls, stream):
+        """Returns True if given stream is a DataFrame."""
+        if DataFrame is None:
+            return False
+        elif isinstance(stream, DataFrame):
+            return True
+        try:
+            DataFrame(stream.read())
+            return True
+        except ValueError:
+            return False
+
+    @classmethod
+    def export_set(cls, dset, index=None):
+        """Returns DataFrame representation of DataBook."""
+        if DataFrame is None:
+            raise NotImplementedError(
+                'DataFrame Format requires `pandas` to be installed.'
+                ' Try `pip install "tablib[pandas]"`.')
+        dataframe = DataFrame(dset.dict, columns=dset.headers)
+        return dataframe
+
+    @classmethod
+    def import_set(cls, dset, in_stream):
+        """Returns dataset from DataFrame."""
+        dset.wipe()
+        dset.dict = in_stream.to_dict(orient='records')

src/tablib/formats/_html.py

@@ -0,0 +1,62 @@
+""" Tablib - HTML export support.
+"""
+
+import codecs
+from io import BytesIO
+
+from MarkupPy import markup
+
+
+class HTMLFormat:
+    BOOK_ENDINGS = 'h3'
+
+    title = 'html'
+    extensions = ('html', )
+
+    @classmethod
+    def export_set(cls, dataset):
+        """HTML representation of a Dataset."""
+
+        stream = BytesIO()
+
+        page = markup.page()
+        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(new_header)
+            page.tr(headers)
+            page.thead.close()
+
+        for row in dataset:
+            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()
+
+        # Allow unicode characters in output
+        wrapper = codecs.getwriter("utf8")(stream)
+        wrapper.writelines(str(page))
+
+        return stream.getvalue().decode('utf-8')
+
+    @classmethod
+    def export_book(cls, databook):
+        """HTML representation of a Databook."""
+
+        stream = BytesIO()
+
+        # Allow unicode characters in output
+        wrapper = codecs.getwriter("utf8")(stream)
+
+        for i, dset in enumerate(databook._datasets):
+            title = (dset.title if dset.title else 'Set %s' % (i))
+            wrapper.write(f'<{cls.BOOK_ENDINGS}>{title}</{cls.BOOK_ENDINGS}>\n')
+            wrapper.write(dset.html)
+            wrapper.write('\n')
+
+        return stream.getvalue().decode('utf-8')

src/tablib/formats/_jira.py

@@ -0,0 +1,40 @@
+"""Tablib - Jira table export support.
+
+   Generates a Jira table from the dataset.
+"""
+
+
+class JIRAFormat:
+    title = 'jira'
+
+    @classmethod
+    def export_set(cls, dataset):
+        """Formats the dataset according to the Jira table syntax:
+
+        ||heading 1||heading 2||heading 3||
+        |col A1|col A2|col A3|
+        |col B1|col B2|col B3|
+
+        :param dataset: dataset to serialize
+        :type dataset: tablib.core.Dataset
+        """
+
+        header = cls._get_header(dataset.headers) if dataset.headers else ''
+        body = cls._get_body(dataset)
+        return f'{header}\n{body}' if header else body
+
+    @classmethod
+    def _get_body(cls, dataset):
+        return '\n'.join([cls._serialize_row(row) for row in dataset])
+
+    @classmethod
+    def _get_header(cls, headers):
+        return cls._serialize_row(headers, delimiter='||')
+
+    @classmethod
+    def _serialize_row(cls, row, delimiter='|'):
+        return '{}{}{}'.format(
+            delimiter,
+            delimiter.join([str(item) if item else ' ' for item in row]),
+            delimiter
+        )

src/tablib/formats/_json.py

@@ -0,0 +1,58 @@
+""" Tablib - JSON Support
+"""
+import decimal
+import json
+from uuid import UUID
+
+import tablib
+
+
+def serialize_objects_handler(obj):
+    if isinstance(obj, (decimal.Decimal, UUID)):
+        return str(obj)
+    elif hasattr(obj, 'isoformat'):
+        return obj.isoformat()
+    else:
+        return obj
+
+
+class JSONFormat:
+    title = 'json'
+    extensions = ('json', 'jsn')
+
+    @classmethod
+    def export_set(cls, dataset):
+        """Returns JSON representation of Dataset."""
+        return json.dumps(dataset.dict, default=serialize_objects_handler)
+
+    @classmethod
+    def export_book(cls, databook):
+        """Returns JSON representation of Databook."""
+        return json.dumps(databook._package(), default=serialize_objects_handler)
+
+    @classmethod
+    def import_set(cls, dset, in_stream):
+        """Returns dataset from JSON stream."""
+
+        dset.wipe()
+        dset.dict = json.load(in_stream)
+
+    @classmethod
+    def import_book(cls, dbook, in_stream):
+        """Returns databook from JSON stream."""
+
+        dbook.wipe()
+        for sheet in json.load(in_stream):
+            data = tablib.Dataset()
+            data.title = sheet['title']
+            data.dict = sheet['data']
+            dbook.add_sheet(data)
+
+    @classmethod
+    def detect(cls, stream):
+        """Returns True if given stream is valid JSON."""
+        try:
+            json.load(stream)
+            return True
+        except (TypeError, ValueError):
+            return False

src/tablib/formats/_latex.py

@@ -0,0 +1,132 @@
+"""Tablib - LaTeX table export support.
+
+   Generates a LaTeX booktabs-style table from the dataset.
+"""
+import re
+
+
+class LATEXFormat:
+    title = 'latex'
+    extensions = ('tex',)
+
+    TABLE_TEMPLATE = """\
+%% Note: add \\usepackage{booktabs} to your preamble
+%%
+\\begin{table}[!htbp]
+  \\centering
+  %(CAPTION)s
+  \\begin{tabular}{%(COLSPEC)s}
+    \\toprule
+%(HEADER)s
+    %(MIDRULE)s
+%(BODY)s
+    \\bottomrule
+  \\end{tabular}
+\\end{table}
+"""
+
+    TEX_RESERVED_SYMBOLS_MAP = dict([
+        ('\\', '\\textbackslash{}'),
+        ('{', '\\{'),
+        ('}', '\\}'),
+        ('$', '\\$'),
+        ('&', '\\&'),
+        ('#', '\\#'),
+        ('^', '\\textasciicircum{}'),
+        ('_', '\\_'),
+        ('~', '\\textasciitilde{}'),
+        ('%', '\\%'),
+    ])
+
+    TEX_RESERVED_SYMBOLS_RE = re.compile(
+        '(%s)' % '|'.join(map(re.escape, TEX_RESERVED_SYMBOLS_MAP.keys())))
+
+    @classmethod
+    def export_set(cls, dataset):
+        """Returns LaTeX representation of dataset
+
+        :param dataset: dataset to serialize
+        :type dataset: tablib.core.Dataset
+        """
+
+        caption = '\\caption{%s}' % dataset.title if dataset.title else '%'
+        colspec = cls._colspec(dataset.width)
+        header = cls._serialize_row(dataset.headers) if dataset.headers else ''
+        midrule = cls._midrule(dataset.width)
+        body = '\n'.join([cls._serialize_row(row) for row in dataset])
+        return cls.TABLE_TEMPLATE % dict(CAPTION=caption, COLSPEC=colspec,
+                                     HEADER=header, MIDRULE=midrule, BODY=body)
+
+    @classmethod
+    def _colspec(cls, dataset_width):
+        """Generates the column specification for the LaTeX `tabular` environment
+        based on the dataset width.
+
+        The first column is justified to the left, all further columns are aligned
+        to the right.
+
+        .. note:: This is only a heuristic and most probably has to be fine-tuned
+        post export. Column alignment should depend on the data type, e.g., textual
+        content should usually be aligned to the left while numeric content almost
+        always should be aligned to the right.
+
+        :param dataset_width: width of the dataset
+        """
+
+        spec = 'l'
+        for _ in range(1, dataset_width):
+            spec += 'r'
+        return spec
+
+    @classmethod
+    def _midrule(cls, dataset_width):
+        """Generates the table `midrule`, which may be composed of several
+        `cmidrules`.
+
+        :param dataset_width: width of the dataset to serialize
+        """
+
+        if not dataset_width or dataset_width == 1:
+            return '\\midrule'
+        return ' '.join([cls._cmidrule(colindex, dataset_width) for colindex in
+                         range(1, dataset_width + 1)])
+
+    @classmethod
+    def _cmidrule(cls, colindex, dataset_width):
+        """Generates the `cmidrule` for a single column with appropriate trimming
+        based on the column position.
+
+        :param colindex: Column index
+        :param dataset_width: width of the dataset
+        """
+
+        rule = '\\cmidrule(%s){%d-%d}'
+        if colindex == 1:
+            # Rule of first column is trimmed on the right
+            return rule % ('r', colindex, colindex)
+        if colindex == dataset_width:
+            # Rule of last column is trimmed on the left
+            return rule % ('l', colindex, colindex)
+        # Inner columns are trimmed on the left and right
+        return rule % ('lr', colindex, colindex)
+
+    @classmethod
+    def _serialize_row(cls, row):
+        """Returns string representation of a single row.
+
+        :param row: single dataset row
+        """
+
+        new_row = [cls._escape_tex_reserved_symbols(str(item)) if item else ''
+                   for item in row]
+        return 6 * ' ' + ' & '.join(new_row) + ' \\\\'
+
+    @classmethod
+    def _escape_tex_reserved_symbols(cls, input):
+        """Escapes all TeX reserved symbols ('_', '~', etc.) in a string.
+
+        :param input: String to escape
+        """
+        def replace(match):
+            return cls.TEX_RESERVED_SYMBOLS_MAP[match.group()]
+        return cls.TEX_RESERVED_SYMBOLS_RE.sub(replace, input)

src/tablib/formats/_ods.py

@@ -0,0 +1,105 @@
+""" Tablib - ODF Support.
+"""
+
+from io import BytesIO
+
+from odf import opendocument, style, table, text
+
+bold = style.Style(name="bold", family="paragraph")
+bold.addElement(style.TextProperties(fontweight="bold", fontweightasian="bold", fontweightcomplex="bold"))
+
+
+class ODSFormat:
+    title = 'ods'
+    extensions = ('ods',)
+
+    @classmethod
+    def export_set(cls, dataset):
+        """Returns ODF representation of Dataset."""
+
+        wb = opendocument.OpenDocumentSpreadsheet()
+        wb.automaticstyles.addElement(bold)
+
+        ws = table.Table(name=dataset.title if dataset.title else 'Tablib Dataset')
+        wb.spreadsheet.addElement(ws)
+        cls.dset_sheet(dataset, ws)
+
+        stream = BytesIO()
+        wb.save(stream)
+        return stream.getvalue()
+
+    @classmethod
+    def export_book(cls, databook):
+        """Returns ODF representation of DataBook."""
+
+        wb = opendocument.OpenDocumentSpreadsheet()
+        wb.automaticstyles.addElement(bold)
+
+        for i, dset in enumerate(databook._datasets):
+            ws = table.Table(name=dset.title if dset.title else 'Sheet%s' % (i))
+            wb.spreadsheet.addElement(ws)
+            cls.dset_sheet(dset, ws)
+
+        stream = BytesIO()
+        wb.save(stream)
+        return stream.getvalue()
+
+    @classmethod
+    def dset_sheet(cls, dataset, ws):
+        """Completes given worksheet from given Dataset."""
+        _package = dataset._package(dicts=False)
+
+        for i, sep in enumerate(dataset._separators):
+            _offset = i
+            _package.insert((sep[0] + _offset), (sep[1],))
+
+        for i, row in enumerate(_package):
+            row_number = i + 1
+            odf_row = table.TableRow(stylename=bold, defaultcellstylename='bold')
+            for j, col in enumerate(row):
+                try:
+                    col = str(col, errors='ignore')
+                except TypeError:
+                    # col is already str
+                    pass
+                ws.addElement(table.TableColumn())
+
+                # bold headers
+                if (row_number == 1) and dataset.headers:
+                    odf_row.setAttribute('stylename', bold)
+                    ws.addElement(odf_row)
+                    cell = table.TableCell()
+                    p = text.P()
+                    p.addElement(text.Span(text=col, stylename=bold))
+                    cell.addElement(p)
+                    odf_row.addElement(cell)
+
+                # wrap the rest
+                else:
+                    try:
+                        if '\n' in col:
+                            ws.addElement(odf_row)
+                            cell = table.TableCell()
+                            cell.addElement(text.P(text=col))
+                            odf_row.addElement(cell)
+                        else:
+                            ws.addElement(odf_row)
+                            cell = table.TableCell()
+                            cell.addElement(text.P(text=col))
+                            odf_row.addElement(cell)
+                    except TypeError:
+                        ws.addElement(odf_row)
+                        cell = table.TableCell()
+                        cell.addElement(text.P(text=col))
+                        odf_row.addElement(cell)
+
+    @classmethod
+    def detect(cls, stream):
+        if isinstance(stream, bytes):
+            # load expects a file-like object.
+            stream = BytesIO(stream)
+        try:
+            opendocument.load(stream)
+            return True
+        except Exception:
+            return False

src/tablib/formats/_rst.py

@@ -0,0 +1,265 @@
+""" Tablib - reStructuredText Support
+"""
+
+from itertools import zip_longest
+from statistics import median
+from textwrap import TextWrapper
+
+JUSTIFY_LEFT = 'left'
+JUSTIFY_CENTER = 'center'
+JUSTIFY_RIGHT = 'right'
+JUSTIFY_VALUES = (JUSTIFY_LEFT, JUSTIFY_CENTER, JUSTIFY_RIGHT)
+
+
+def to_str(value):
+    if isinstance(value, bytes):
+        return value.decode('utf-8')
+    return str(value)
+
+
+def _max_word_len(text):
+    """
+    Return the length of the longest word in `text`.
+
+    >>> _max_word_len('Python Module for Tabular Datasets')
+    8
+    """
+    return max([len(word) for word in text.split()], default=0) if text else 0
+
+
+class ReSTFormat:
+    title = 'rst'
+    extensions = ('rst',)
+
+    MAX_TABLE_WIDTH = 80  # Roughly. It may be wider to avoid breaking words.
+
+    @classmethod
+    def _get_column_string_lengths(cls, dataset):
+        """
+        Returns a list of string lengths of each column, and a list of
+        maximum word lengths.
+        """
+        if dataset.headers:
+            column_lengths = [[len(h)] for h in dataset.headers]
+            word_lens = [_max_word_len(h) for h in dataset.headers]
+        else:
+            column_lengths = [[] for _ in range(dataset.width)]
+            word_lens = [0 for _ in range(dataset.width)]
+        for row in dataset.dict:
+            values = iter(row.values() if hasattr(row, 'values') else row)
+            for i, val in enumerate(values):
+                text = to_str(val)
+                column_lengths[i].append(len(text))
+                word_lens[i] = max(word_lens[i], _max_word_len(text))
+        return column_lengths, word_lens
+
+    @classmethod
+    def _row_to_lines(cls, values, widths, wrapper, sep='|', justify=JUSTIFY_LEFT):
+        """
+        Returns a table row of wrapped values as a list of lines
+        """
+        if justify not in JUSTIFY_VALUES:
+            raise ValueError('Value of "justify" must be one of "{}"'.format(
+                '", "'.join(JUSTIFY_VALUES)
+            ))
+        if justify == JUSTIFY_LEFT:
+            just = lambda text, width: text.ljust(width)
+        elif justify == JUSTIFY_CENTER:
+            just = lambda text, width: text.center(width)
+        else:
+            just = lambda text, width: text.rjust(width)
+        lpad = sep + ' ' if sep else ''
+        rpad = ' ' + sep if sep else ''
+        pad = ' ' + sep + ' '
+        cells = []
+        for value, width in zip(values, widths):
+            wrapper.width = width
+            text = to_str(value)
+            cell = wrapper.wrap(text)
+            cells.append(cell)
+        lines = zip_longest(*cells, fillvalue='')
+        lines = (
+            (just(cell_line, widths[i]) for i, cell_line in enumerate(line))
+            for line in lines
+        )
+        lines = [''.join((lpad, pad.join(line), rpad)) for line in lines]
+        return lines
+
+    @classmethod
+    def _get_column_widths(cls, dataset, max_table_width=MAX_TABLE_WIDTH, pad_len=3):
+        """
+        Returns a list of column widths proportional to the median length
+        of the text in their cells.
+        """
+        str_lens, word_lens = cls._get_column_string_lengths(dataset)
+        median_lens = [int(median(lens)) for lens in str_lens]
+        total = sum(median_lens)
+        if total > max_table_width - (pad_len * len(median_lens)):
+            column_widths = (max_table_width * l // total for l in median_lens)
+        else:
+            column_widths = (l for l in median_lens)
+        # Allow for separator and padding:
+        column_widths = (w - pad_len if w > pad_len else w for w in column_widths)
+        # Rather widen table than break words:
+        column_widths = [max(w, l) for w, l in zip(column_widths, word_lens)]
+        return column_widths
+
+    @classmethod
+    def export_set_as_simple_table(cls, dataset, column_widths=None):
+        """
+        Returns reStructuredText grid table representation of dataset.
+        """
+        lines = []
+        wrapper = TextWrapper()
+        if column_widths is None:
+            column_widths = cls._get_column_widths(dataset, pad_len=2)
+        border = '  '.join(['=' * w for w in column_widths])
+
+        lines.append(border)
+        if dataset.headers:
+            lines.extend(cls._row_to_lines(
+                dataset.headers,
+                column_widths,
+                wrapper,
+                sep='',
+                justify=JUSTIFY_CENTER,
+            ))
+            lines.append(border)
+        for row in dataset.dict:
+            values = iter(row.values() if hasattr(row, 'values') else row)
+            lines.extend(cls._row_to_lines(values, column_widths, wrapper, ''))
+        lines.append(border)
+        return '\n'.join(lines)
+
+    @classmethod
+    def export_set_as_grid_table(cls, dataset, column_widths=None):
+        """
+        Returns reStructuredText grid table representation of dataset.
+
+
+        >>> from tablib import Dataset
+        >>> from tablib.formats import registry
+        >>> bits = ((0, 0), (1, 0), (0, 1), (1, 1))
+        >>> data = Dataset()
+        >>> data.headers = ['A', 'B', 'A and B']
+        >>> for a, b in bits:
+        ...     data.append([bool(a), bool(b), bool(a * b)])
+        >>> rst = registry.get_format('rst')
+        >>> print(rst.export_set(data, force_grid=True))
+        +-------+-------+-------+
+        |   A   |   B   | A and |
+        |       |       |   B   |
+        +=======+=======+=======+
+        | False | False | False |
+        +-------+-------+-------+
+        | True  | False | False |
+        +-------+-------+-------+
+        | False | True  | False |
+        +-------+-------+-------+
+        | True  | True  | True  |
+        +-------+-------+-------+
+
+        """
+        lines = []
+        wrapper = TextWrapper()
+        if column_widths is None:
+            column_widths = cls._get_column_widths(dataset)
+        header_sep = '+=' + '=+='.join(['=' * w for w in column_widths]) + '=+'
+        row_sep = '+-' + '-+-'.join(['-' * w for w in column_widths]) + '-+'
+
+        lines.append(row_sep)
+
+        if dataset.headers:
+            lines.extend(cls._row_to_lines(
+                dataset.headers,
+                column_widths,
+                wrapper,
+                justify=JUSTIFY_CENTER,
+            ))
+            lines.append(header_sep)
+        for row in dataset.dict:
+            values = iter(row.values() if hasattr(row, 'values') else row)
+            lines.extend(cls._row_to_lines(values, column_widths, wrapper))
+            lines.append(row_sep)
+        return '\n'.join(lines)
+
+    @classmethod
+    def _use_simple_table(cls, head0, col0, width0):
+        """
+        Use a simple table if the text in the first column is never wrapped
+
+
+        >>> from tablib.formats import registry
+        >>> rst = registry.get_format('rst')
+        >>> rst._use_simple_table('menu', ['egg', 'bacon'], 10)
+        True
+        >>> rst._use_simple_table(None, ['lobster thermidor', 'spam'], 10)
+        False
+
+        """
+        if head0 is not None:
+            head0 = to_str(head0)
+            if len(head0) > width0:
+                return False
+        for cell in col0:
+            cell = to_str(cell)
+            if len(cell) > width0:
+                return False
+        return True
+
+    @classmethod
+    def export_set(cls, dataset, **kwargs):
+        """
+        Returns reStructuredText table representation of dataset.
+
+        Returns a simple table if the text in the first column is never
+        wrapped, otherwise returns a grid table.
+
+
+        >>> from tablib import Dataset
+        >>> bits = ((0, 0), (1, 0), (0, 1), (1, 1))
+        >>> data = Dataset()
+        >>> data.headers = ['A', 'B', 'A and B']
+        >>> for a, b in bits:
+        ...     data.append([bool(a), bool(b), bool(a * b)])
+        >>> table = data.rst
+        >>> table.split('\\n') == [
+        ...     '=====  =====  =====',
+        ...     '  A      B    A and',
+        ...     '                B  ',
+        ...     '=====  =====  =====',
+        ...     'False  False  False',
+        ...     'True   False  False',
+        ...     'False  True   False',
+        ...     'True   True   True ',
+        ...     '=====  =====  =====',
+        ... ]
+        True
+
+        """
+        if not dataset.dict:
+            return ''
+        force_grid = kwargs.get('force_grid', False)
+        max_table_width = kwargs.get('max_table_width', cls.MAX_TABLE_WIDTH)
+        column_widths = cls._get_column_widths(dataset, max_table_width)
+
+        use_simple_table = cls._use_simple_table(
+            dataset.headers[0] if dataset.headers else None,
+            dataset.get_col(0),
+            column_widths[0],
+        )
+        if use_simple_table and not force_grid:
+            return cls.export_set_as_simple_table(dataset, column_widths)
+        else:
+            return cls.export_set_as_grid_table(dataset, column_widths)
+
+    @classmethod
+    def export_book(cls, databook):
+        """
+        reStructuredText representation of a Databook.
+
+        Tables are separated by a blank line. All tables use the grid
+        format.
+        """
+        return '\n\n'.join(cls.export_set(dataset, force_grid=True)
+                           for dataset in databook._datasets)

src/tablib/formats/_tsv.py

@@ -0,0 +1,11 @@
+""" Tablib - TSV (Tab Separated Values) Support.
+"""
+
+from ._csv import CSVFormat
+
+
+class TSVFormat(CSVFormat):
+    title = 'tsv'
+    extensions = ('tsv',)
+
+    DEFAULT_DELIMITER = '\t'

src/tablib/formats/_xls.py

@@ -0,0 +1,147 @@
+""" Tablib - XLS Support.
+"""
+
+from io import BytesIO
+
+import xlrd
+import xlwt
+from xlrd.xldate import xldate_as_datetime
+
+import tablib
+
+# special styles
+wrap = xlwt.easyxf("alignment: wrap on")
+bold = xlwt.easyxf("font: bold on")
+
+
+class XLSFormat:
+    title = 'xls'
+    extensions = ('xls',)
+
+    @classmethod
+    def detect(cls, stream):
+        """Returns True if given stream is a readable excel file."""
+        try:
+            xlrd.open_workbook(file_contents=stream)
+            return True
+        except Exception:
+            pass
+        try:
+            xlrd.open_workbook(file_contents=stream.read())
+            return True
+        except Exception:
+            pass
+        try:
+            xlrd.open_workbook(filename=stream)
+            return True
+        except Exception:
+            return False
+
+    @classmethod
+    def export_set(cls, dataset):
+        """Returns XLS representation of Dataset."""
+
+        wb = xlwt.Workbook(encoding='utf8')
+        ws = wb.add_sheet(dataset.title if dataset.title else 'Tablib Dataset')
+
+        cls.dset_sheet(dataset, ws)
+
+        stream = BytesIO()
+        wb.save(stream)
+        return stream.getvalue()
+
+    @classmethod
+    def export_book(cls, databook):
+        """Returns XLS representation of DataBook."""
+
+        wb = xlwt.Workbook(encoding='utf8')
+
+        for i, dset in enumerate(databook._datasets):
+            ws = wb.add_sheet(dset.title if dset.title else 'Sheet%s' % (i))
+
+            cls.dset_sheet(dset, ws)
+
+        stream = BytesIO()
+        wb.save(stream)
+        return stream.getvalue()
+
+    @classmethod
+    def import_set(cls, dset, in_stream, headers=True):
+        """Returns databook from XLS stream."""
+
+        dset.wipe()
+
+        xls_book = xlrd.open_workbook(file_contents=in_stream.read())
+        sheet = xls_book.sheet_by_index(0)
+
+        dset.title = sheet.name
+
+        def cell_value(value, type_):
+            if type_ == xlrd.XL_CELL_ERROR:
+                return xlrd.error_text_from_code[value]
+            elif type_ == xlrd.XL_CELL_DATE:
+                return xldate_as_datetime(value, xls_book.datemode)
+            return value
+
+        for i in range(sheet.nrows):
+            if i == 0 and headers:
+                dset.headers = sheet.row_values(0)
+            else:
+                dset.append([
+                    cell_value(val, typ)
+                    for val, typ in zip(sheet.row_values(i), sheet.row_types(i))
+                ])
+
+    @classmethod
+    def import_book(cls, 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 range(sheet.nrows):
+                if i == 0 and headers:
+                    data.headers = sheet.row_values(0)
+                else:
+                    data.append(sheet.row_values(i))
+
+            dbook.add_sheet(data)
+
+    @classmethod
+    def dset_sheet(cls, dataset, ws):
+        """Completes given worksheet from given Dataset."""
+        _package = dataset._package(dicts=False)
+
+        for i, sep in enumerate(dataset._separators):
+            _offset = i
+            _package.insert((sep[0] + _offset), (sep[1],))
+
+        for i, row in enumerate(_package):
+            for j, col in enumerate(row):
+
+                # bold headers
+                if (i == 0) and dataset.headers:
+                    ws.write(i, j, col, bold)
+
+                    # frozen header row
+                    ws.panes_frozen = True
+                    ws.horz_split_pos = 1
+
+                # bold separators
+                elif len(row) < dataset.width:
+                    ws.write(i, j, col, bold)
+
+                # wrap the rest
+                else:
+                    try:
+                        if '\n' in col:
+                            ws.write(i, j, col, wrap)
+                        else:
+                            ws.write(i, j, col)
+                    except TypeError:
+                        ws.write(i, j, col)

src/tablib/formats/_xlsx.py

@@ -0,0 +1,143 @@
+""" Tablib - XLSX Support.
+"""
+
+from io import BytesIO
+
+from openpyxl.reader.excel import ExcelReader, load_workbook
+from openpyxl.styles import Alignment, Font
+from openpyxl.utils import get_column_letter
+from openpyxl.workbook import Workbook
+from openpyxl.writer.excel import ExcelWriter
+
+import tablib
+
+
+class XLSXFormat:
+    title = 'xlsx'
+    extensions = ('xlsx',)
+
+    @classmethod
+    def detect(cls, stream):
+        """Returns True if given stream is a readable excel file."""
+        try:
+            # No need to fully load the file, it should be enough to be able to
+            # read the manifest.
+            reader = ExcelReader(stream, read_only=False)
+            reader.read_manifest()
+            return True
+        except Exception:
+            return False
+
+    @classmethod
+    def export_set(cls, dataset, freeze_panes=True):
+        """Returns XLSX representation of Dataset."""
+        wb = Workbook()
+        ws = wb.worksheets[0]
+        ws.title = dataset.title if dataset.title else 'Tablib Dataset'
+
+        cls.dset_sheet(dataset, ws, freeze_panes=freeze_panes)
+
+        stream = BytesIO()
+        wb.save(stream)
+        return stream.getvalue()
+
+    @classmethod
+    def export_book(cls, databook, freeze_panes=True):
+        """Returns XLSX representation of DataBook."""
+
+        wb = Workbook()
+        for sheet in wb.worksheets:
+            wb.remove(sheet)
+        for i, dset in enumerate(databook._datasets):
+            ws = wb.create_sheet()
+            ws.title = dset.title if dset.title else 'Sheet%s' % (i)
+
+            cls.dset_sheet(dset, ws, freeze_panes=freeze_panes)
+
+        stream = BytesIO()
+        wb.save(stream)
+        return stream.getvalue()
+
+    @classmethod
+    def import_set(cls, dset, in_stream, headers=True, read_only=True):
+        """Returns databook from XLS stream."""
+
+        dset.wipe()
+
+        xls_book = load_workbook(in_stream, read_only=read_only, data_only=True)
+        sheet = xls_book.active
+
+        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)
+
+    @classmethod
+    def import_book(cls, dbook, in_stream, headers=True, read_only=True):
+        """Returns databook from XLS stream."""
+
+        dbook.wipe()
+
+        xls_book = load_workbook(in_stream, read_only=read_only, data_only=True)
+
+        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:
+                    if i > 0 and len(row_vals) < data.width:
+                        row_vals += [''] * (data.width - len(row_vals))
+                    data.append(row_vals)
+
+            dbook.add_sheet(data)
+
+    @classmethod
+    def dset_sheet(cls, dataset, ws, freeze_panes=True):
+        """Completes given worksheet from given Dataset."""
+        _package = dataset._package(dicts=False)
+
+        for i, sep in enumerate(dataset._separators):
+            _offset = i
+            _package.insert((sep[0] + _offset), (sep[1],))
+
+        bold = Font(bold=True)
+        wrap_text = Alignment(wrap_text=True)
+
+        for i, row in enumerate(_package):
+            row_number = i + 1
+            for j, col in enumerate(row):
+                col_idx = get_column_letter(j + 1)
+                cell = ws[f'{col_idx}{row_number}']
+
+                # bold headers
+                if (row_number == 1) and dataset.headers:
+                    cell.font = bold
+                    if freeze_panes:
+                        #  Export Freeze only after first Line
+                        ws.freeze_panes = 'A2'
+
+                # bold separators
+                elif len(row) < dataset.width:
+                    cell.font = bold
+
+                # wrap the rest
+                else:
+                    try:
+                        str_col_value = str(col)
+                    except TypeError:
+                        str_col_value = ''
+                    if '\n' in str_col_value:
+                        cell.alignment = wrap_text
+
+                try:
+                    cell.value = col
+                except (ValueError, TypeError):
+                    cell.value = str(col)

src/tablib/formats/_yaml.py

@@ -0,0 +1,54 @@
+""" Tablib - YAML Support.
+"""
+
+import yaml
+
+import tablib
+
+
+class YAMLFormat:
+    title = 'yaml'
+    extensions = ('yaml', 'yml')
+
+    @classmethod
+    def export_set(cls, dataset):
+        """Returns YAML representation of Dataset."""
+
+        return yaml.safe_dump(dataset._package(ordered=False), default_flow_style=None)
+
+    @classmethod
+    def export_book(cls, databook):
+        """Returns YAML representation of Databook."""
+        return yaml.safe_dump(databook._package(ordered=False), default_flow_style=None)
+
+    @classmethod
+    def import_set(cls, dset, in_stream):
+        """Returns dataset from YAML stream."""
+
+        dset.wipe()
+        dset.dict = yaml.safe_load(in_stream)
+
+    @classmethod
+    def import_book(cls, dbook, in_stream):
+        """Returns databook from YAML stream."""
+
+        dbook.wipe()
+
+        for sheet in yaml.safe_load(in_stream):
+            data = tablib.Dataset()
+            data.title = sheet['title']
+            data.dict = sheet['data']
+            dbook.add_sheet(data)
+
+    @classmethod
+    def detect(cls, stream):
+        """Returns True if given stream is valid YAML."""
+        try:
+            _yaml = yaml.safe_load(stream)
+            if isinstance(_yaml, (list, tuple, dict)):
+                return True
+            else:
+                return False
+        except (yaml.parser.ParserError, yaml.reader.ReaderError,
+                yaml.scanner.ScannerError):
+            return False

src/tablib/packages/dbfpy/dbf.py

@@ -31,9 +31,9 @@ Examples:
         dbf = Dbf(filename, True)
         for rec in dbf:
             for fldName in dbf.fieldNames:
-                print '%s:\t %s (%s)' % (fldName, rec[fldName],
-                    type(rec[fldName]))
-            print
+                print('%s:\t %s (%s)' % (fldName, rec[fldName],
+                    type(rec[fldName])))
+            print()
         dbf.close()
 
 """
@@ -62,12 +62,11 @@ __author__ = "Jeff Kunce <kuncej@mail.conservation.state.mo.us>"
 
 __all__ = ["Dbf"]
 
-from . import header
-from . import record
+from . import header, record
 from .utils import INVALID_VALUE
 
 
-class Dbf(object):
+class Dbf:
     """DBF accessor.
 
     FIXME:
@@ -122,7 +121,7 @@ class Dbf(object):
                 # created or opened and truncated)
                 self.stream = open(f, "w+b")
             else:
-                # tabe file must exist
+                # table file must exist
                 self.stream = open(f, ("r+b", "rb")[bool(readOnly)])
         else:
             # a stream
@@ -187,7 +186,7 @@ class Dbf(object):
             raise IndexError("Record index out of range")
         return index
 
-    # iterface methods
+    # interface methods
 
     def close(self):
         self.flush()

src/tablib/packages/dbfpy/dbfnew.py

@@ -6,7 +6,7 @@ Note: this is a legacy interface.  New code should use Dbf class
 
 TODO:
   - handle Memo fields.
-  - check length of the fields accoring to the
+  - check length of the fields according to the
     `http://www.clicketyclick.dk/databases/xbase/format/data_types.html`
 
 """
@@ -30,14 +30,14 @@ from .header import *
 from .record import *
 
 
-class _FieldDefinition(object):
+class _FieldDefinition:
     """Field definition.
 
     This is a simple structure, which contains ``name``, ``type``,
     ``len``, ``dec`` and ``cls`` fields.
 
     Objects also implement get/setitem magic functions, so fields
-    could be accessed via sequence iterface, where 'name' has
+    could be accessed via sequence interface, where 'name' has
     index 0, 'type' index 1, 'len' index 2, 'dec' index 3 and
     'cls' could be located at index 4.
 
@@ -87,7 +87,7 @@ class _FieldDefinition(object):
         dbfh.addField(_dbff)
 
 
-class dbf_new(object):
+class dbf_new:
     """New .DBF creation helper.
 
     Example Usage:
@@ -176,7 +176,7 @@ if __name__ == '__main__':
     for i1 in range(len(dbft)):
         rec = dbft[i1]
         for fldName in dbft.fieldNames:
-            print('%s:\t %s' % (fldName, rec[fldName]))
+            print('{}:\t {}'.format(fldName, rec[fldName]))
         print()
     dbft.close()
 

src/tablib/packages/dbfpy/fields.py

@@ -28,37 +28,38 @@ TODO:
 __version__ = "$Revision: 1.14 $"[11:-2]
 __date__ = "$Date: 2009/05/26 05:16:51 $"[7:-2]
 
-__all__ = ["lookupFor",] # field classes added at the end of the module
+__all__ = ["lookupFor"]  # field classes added at the end of the module
 
 import datetime
 import struct
 import sys
+from functools import total_ordering
 
 from . import utils
 
-## abstract definitions
+# abstract definitions
 
-class DbfFieldDef(object):
+
+@total_ordering
+class DbfFieldDef:
     """Abstract field definition.
 
     Child classes must override ``type`` class attribute to provide datatype
-    infromation of the field definition. For more info about types visit
+    information of the field definition. For more info about types visit
     `http://www.clicketyclick.dk/databases/xbase/format/data_types.html`
 
     Also child classes must override ``defaultValue`` field to provide
     default value for the field value.
 
     If child class has fixed length ``length`` class attribute must be
-    overriden and set to the valid value. None value means, that field
+    overridden and set to the valid value. None value means, that field
     isn't of fixed length.
 
     Note: ``name`` field must not be changed after instantiation.
 
     """
 
-
-    __slots__ = ("name", "decimalCount",
-        "start", "end", "ignoreErrors")
+    __slots__ = ("name", "decimalCount", "start", "end", "ignoreErrors")
 
     # length of the field, None in case of variable-length field,
     # or a number if this field is a fixed-length field
@@ -66,21 +67,20 @@ class DbfFieldDef(object):
 
     # field type. for more information about fields types visit
     # `http://www.clicketyclick.dk/databases/xbase/format/data_types.html`
-    # must be overriden in child classes
+    # must be overridden in child classes
     typeCode = None
 
     # default value for the field. this field must be
-    # overriden in child classes
+    # overridden in child classes
     defaultValue = None
 
     def __init__(self, name, length=None, decimalCount=None,
-        start=None, stop=None, ignoreErrors=False,
-    ):
+                 start=None, stop=None, ignoreErrors=False):
         """Initialize instance."""
-        assert self.typeCode is not None, "Type code must be overriden"
-        assert self.defaultValue is not None, "Default value must be overriden"
-        ## fix arguments
-        if len(name) >10:
+        assert self.typeCode is not None, "Type code must be overridden"
+        assert self.defaultValue is not None, "Default value must be overridden"
+        # fix arguments
+        if len(name) > 10:
             raise ValueError("Field name \"%s\" is too long" % name)
         name = str(name).upper()
         if self.__class__.length is None:
@@ -88,13 +88,12 @@ class DbfFieldDef(object):
                 raise ValueError("[%s] Length isn't specified" % name)
             length = int(length)
             if length <= 0:
-                raise ValueError("[%s] Length must be a positive integer"
-                    % name)
+                raise ValueError("[%s] Length must be a positive integer" % name)
         else:
             length = self.length
         if decimalCount is None:
             decimalCount = 0
-        ## set fields
+        # set fields
         self.name = name
         # FIXME: validate length according to the specification at
         # http://www.clicketyclick.dk/databases/xbase/format/data_types.html
@@ -104,8 +103,14 @@ class DbfFieldDef(object):
         self.start = start
         self.end = stop
 
-    def __cmp__(self, other):
-        return cmp(self.name, str(other).upper())
+    def __eq__(self, other):
+        return repr(self) == repr(other)
+
+    def __ne__(self, other):
+        return repr(self) != repr(other)
+
+    def __lt__(self, other):
+        return repr(self) < repr(other)
 
     def __hash__(self):
         return hash(self.name)
@@ -137,15 +142,11 @@ class DbfFieldDef(object):
             definition of this field.
 
         """
-        if sys.version_info < (2, 4):
-            # earlier versions did not support padding character
-            _name = self.name[:11] + "\0" * (11 - len(self.name))
-        else:
-            _name = self.name.ljust(11, '\0')
+        _name = self.name.ljust(11, '\0')
         return (
             _name +
             self.typeCode +
-            #data address
+            # data address
             chr(0) * 4 +
             chr(self.length) +
             chr(self.decimalCount) +
@@ -172,7 +173,7 @@ class DbfFieldDef(object):
         """Return decoded field value from the record string."""
         try:
             return self.decodeValue(self.rawFromRecord(record))
-        except:
+        except Exception:
             if self.ignoreErrors:
                 return utils.INVALID_VALUE
             else:
@@ -191,11 +192,12 @@ class DbfFieldDef(object):
     def encodeValue(self, value):
         """Return str object containing encoded field value.
 
-        This is an abstract method and it must be overriden in child classes.
+        This is an abstract method and it must be overridden in child classes.
         """
         raise NotImplementedError
 
-## real classes
+# real classes
+
 
 class DbfCharacterFieldDef(DbfFieldDef):
     """Definition of the character field."""
@@ -258,11 +260,13 @@ class DbfNumericFieldDef(DbfFieldDef):
                     % (self.name, _rv, self.length))
         return _rv
 
+
 class DbfFloatFieldDef(DbfNumericFieldDef):
     """Definition of the float field - same as numeric."""
 
     typeCode = "F"
 
+
 class DbfIntegerFieldDef(DbfFieldDef):
     """Definition of the integer field."""
 
@@ -278,6 +282,7 @@ class DbfIntegerFieldDef(DbfFieldDef):
         """Return string containing encoded ``value``."""
         return struct.pack("<i", int(value))
 
+
 class DbfCurrencyFieldDef(DbfFieldDef):
     """Definition of the currency field."""
 
@@ -293,6 +298,7 @@ class DbfCurrencyFieldDef(DbfFieldDef):
         """Return string containing encoded ``value``."""
         return struct.pack("<q", round(value * 10000))
 
+
 class DbfLogicalFieldDef(DbfFieldDef):
     """Definition of the logical field."""
 
@@ -309,7 +315,7 @@ class DbfLogicalFieldDef(DbfFieldDef):
             return False
         if value in "YyTt":
             return True
-        raise ValueError("[%s] Invalid logical value %r" % (self.name, value))
+        raise ValueError(f"[{self.name}] Invalid logical value {value!r}")
 
     def encodeValue(self, value):
         """Return a character from the "TF?" set.
@@ -329,7 +335,7 @@ class DbfLogicalFieldDef(DbfFieldDef):
 class DbfMemoFieldDef(DbfFieldDef):
     """Definition of the memo field.
 
-    Note: memos aren't currenly completely supported.
+    Note: memos aren't currently completely supported.
 
     """
 
@@ -339,7 +345,7 @@ class DbfMemoFieldDef(DbfFieldDef):
 
     def decodeValue(self, value):
         """Return int .dbt block number decoded from the string object."""
-        #return int(value)
+        # return int(value)
         raise NotImplementedError
 
     def encodeValue(self, value):
@@ -348,7 +354,7 @@ class DbfMemoFieldDef(DbfFieldDef):
         Note: this is an internal method.
 
         """
-        #return str(value)[:self.length].ljust(self.length)
+        # return str(value)[:self.length].ljust(self.length)
         raise NotImplementedError
 
 
@@ -424,6 +430,7 @@ class DbfDateTimeFieldDef(DbfFieldDef):
 
 _fieldsRegistry = {}
 
+
 def registerField(fieldCls):
     """Register field definition class.
 
@@ -455,11 +462,12 @@ def lookupFor(typeCode):
     # forget to look to the same comment in ``registerField``
     return _fieldsRegistry[chr(typeCode)]
 
-## register generic types
+# register generic types
+
 
 for (_name, _val) in list(globals().items()):
     if isinstance(_val, type) and issubclass(_val, DbfFieldDef) \
-    and (_name != "DbfFieldDef"):
+       and (_name != "DbfFieldDef"):
         __all__.append(_name)
         registerField(_val)
 del _name, _val

src/tablib/packages/dbfpy/header.py

@@ -19,17 +19,16 @@ __date__ = "$Date: 2010/09/16 05:06:39 $"[7:-2]
 
 __all__ = ["DbfHeader"]
 
-import io
 import datetime
+import io
 import struct
-import time
 import sys
 
 from . import fields
 from .utils import getDate
 
 
-class DbfHeader(object):
+class DbfHeader:
     """Dbf header definition.
 
     For more information about dbf header format visit
@@ -51,13 +50,12 @@ class DbfHeader(object):
     """
 
     __slots__ = ("signature", "fields", "lastUpdate", "recordLength",
-        "recordCount", "headerLength", "changed", "_ignore_errors")
+                 "recordCount", "headerLength", "changed", "_ignore_errors")
 
-    ## instance construction and initialization methods
+    # instance construction and initialization methods
 
     def __init__(self, fields=None, headerLength=0, recordLength=0,
-        recordCount=0, signature=0x03, lastUpdate=None, ignoreErrors=False,
-    ):
+                 recordCount=0, signature=0x03, lastUpdate=None, ignoreErrors=False):
         """Initialize instance.
 
         Arguments:
@@ -111,7 +109,7 @@ class DbfHeader(object):
             _data = bytes(first_32, sys.getfilesystemencoding())
         _data = first_32
         (_cnt, _hdrLen, _recLen) = struct.unpack("<I2H", _data[4:12])
-        #reserved = _data[12:32]
+        # reserved = _data[12:32]
         _year = _data[1]
         if _year < 80:
             # dBase II started at 1980.  It is quite unlikely
@@ -119,10 +117,10 @@ class DbfHeader(object):
             _year += 2000
         else:
             _year += 1900
-        ## create header object
+        # create header object
         _obj = cls(None, _hdrLen, _recLen, _cnt, _data[0],
-            (_year, _data[2], _data[3]))
-        ## append field definitions
+                   (_year, _data[2], _data[3]))
+        # append field definitions
         # position 0 is for the deletion flag
         _pos = 1
         _data = stream.read(1)
@@ -135,7 +133,7 @@ class DbfHeader(object):
         return _obj
     fromStream = classmethod(fromStream)
 
-    ## properties
+    # properties
 
     year = property(lambda self: self.lastUpdate.year)
     month = property(lambda self: self.lastUpdate.month)
@@ -156,7 +154,7 @@ class DbfHeader(object):
 
         """)
 
-    ## object representation
+    # object representation
 
     def __repr__(self):
         _rv = """\
@@ -173,7 +171,7 @@ Version (signature): 0x%02x
         )
         return _rv
 
-    ## internal methods
+    # internal methods
 
     def _addField(self, *defs):
         """Internal variant of the `addField` method.
@@ -197,8 +195,7 @@ Version (signature): 0x%02x
             else:
                 (_name, _type, _len, _dec) = (tuple(_def) + (None,) * 4)[:4]
                 _cls = fields.lookupFor(_type)
-                _obj = _cls(_name, _len, _dec,
-                    ignoreErrors=self._ignore_errors)
+                _obj = _cls(_name, _len, _dec, ignoreErrors=self._ignore_errors)
             _recordLength += _obj.length
             _defs.append(_obj)
         # and now extend field definitions and
@@ -206,7 +203,7 @@ Version (signature): 0x%02x
         self.fields += _defs
         return _recordLength
 
-    ## interface methods
+    # interface methods
 
     def addField(self, *defs):
         """Add field definition to the header.
@@ -251,7 +248,7 @@ Version (signature): 0x%02x
             self.recordCount,
             self.headerLength,
             self.recordLength) + (b'\x00' * 20)
-        #TODO: figure out if bytes(utf-8) is correct here.
+        # TODO: figure out if bytes(utf-8) is correct here.
 
     def setCurrentDate(self):
         """Update ``self.lastUpdate`` field with current date value."""

src/tablib/packages/dbfpy/record.py

@@ -20,15 +20,16 @@ import sys
 
 from . import utils
 
-class DbfRecord(object):
+
+class DbfRecord:
     """DBF record.
 
-    Instances of this class shouldn't be created manualy,
+    Instances of this class shouldn't be created manually,
     use `dbf.Dbf.newRecord` instead.
 
     Class implements mapping/sequence interface, so
     fields could be accessed via their names or indexes
-    (names is a preffered way to access fields).
+    (names is a preferred way to access fields).
 
     Hint:
         Use `store` method to save modified record.
@@ -52,14 +53,14 @@ class DbfRecord(object):
 
     __slots__ = "dbf", "index", "deleted", "fieldData"
 
-    ## creation and initialization
+    # creation and initialization
 
     def __init__(self, dbf, index=None, deleted=False, data=None):
-        """Instance initialiation.
+        """Instance initialization.
 
         Arguments:
             dbf:
-                A `Dbf.Dbf` instance this record belonogs to.
+                A `Dbf.Dbf` instance this record belongs to.
             index:
                 An integer record index or None. If this value is
                 None, record will be appended to the DBF.
@@ -82,7 +83,7 @@ class DbfRecord(object):
 
     # XXX: validate self.index before calculating position?
     position = property(lambda self: self.dbf.header.headerLength + \
-        self.index * self.dbf.header.recordLength)
+                        self.index * self.dbf.header.recordLength)
 
     def rawFromStream(cls, dbf, index):
         """Return raw record contents read from the stream.
@@ -137,10 +138,10 @@ class DbfRecord(object):
 
         """
         return cls(dbf, index, string[0]=="*",
-            [_fd.decodeFromRecord(string) for _fd in dbf.header.fields])
+                   [_fd.decodeFromRecord(string) for _fd in dbf.header.fields])
     fromString = classmethod(fromString)
 
-    ## object representation
+    # object representation
 
     def __repr__(self):
         _template = "%%%ds: %%s (%%s)" % max([len(_fld)
@@ -155,14 +156,14 @@ class DbfRecord(object):
                 _rv.append(_template % (_fld, _val, type(_val)))
         return "\n".join(_rv)
 
-    ## protected methods
+    # protected methods
 
     def _write(self):
         """Write data to the dbf stream.
 
         Note:
             This isn't a public method, it's better to
-            use 'store' instead publically.
+            use 'store' instead publicly.
             Be design ``_write`` method should be called
             only from the `Dbf` instance.
 
@@ -171,7 +172,7 @@ class DbfRecord(object):
         self._validateIndex(False)
         self.dbf.stream.seek(self.position)
         self.dbf.stream.write(bytes(self.toString(),
-            sys.getfilesystemencoding()))
+                              sys.getfilesystemencoding()))
         # FIXME: may be move this write somewhere else?
         # why we should check this condition for each record?
         if self.index == len(self.dbf):
@@ -179,7 +180,7 @@ class DbfRecord(object):
             # we should write SUB (ASCII 26)
             self.dbf.stream.write(b"\x1A")
 
-    ## utility methods
+    # utility methods
 
     def _validateIndex(self, allowUndefined=True, checkRange=False):
         """Valid ``self.index`` value.
@@ -195,9 +196,9 @@ class DbfRecord(object):
             raise ValueError("Index can't be negative (%s)" % self.index)
         elif checkRange and self.index <= self.dbf.header.recordCount:
             raise ValueError("There are only %d records in the DBF" %
-                self.dbf.header.recordCount)
+                             self.dbf.header.recordCount)
 
-    ## interface methods
+    # interface methods
 
     def store(self):
         """Store current record in the DBF.

src/tablib/packages/dbfpy/utils.py

@@ -20,7 +20,7 @@ import time
 def unzfill(str):
     """Return a string without ASCII NULs.
 
-    This function searchers for the first NUL (ASCII 0) occurance
+    This function searchers for the first NUL (ASCII 0) occurrence
     and truncates string till that position.
 
     """
@@ -48,7 +48,7 @@ def getDate(date=None):
         sequence:
             assuming (year, month, day, ...) sequence;
 
-    Additionaly, if ``date`` has callable ``ticks`` attribute,
+    Additionally, if ``date`` has callable ``ticks`` attribute,
     it will be used and result of the called would be treated
     as a timestamp value.
 
@@ -95,7 +95,7 @@ def getDateTime(value=None):
         sequence:
             assuming (year, month, day, ...) sequence;
 
-    Additionaly, if ``value`` has callable ``ticks`` attribute,
+    Additionally, if ``value`` has callable ``ticks`` attribute,
     it will be used and result of the called would be treated
     as a timestamp value.
 
@@ -125,7 +125,7 @@ class classproperty(property):
         return self.fget(cls)
 
 
-class _InvalidValue(object):
+class _InvalidValue:
 
     """Value returned from DBF records when field validation fails
 
@@ -158,12 +158,10 @@ class _InvalidValue(object):
     def __str__(self):
         return ""
 
-    def __unicode__(self):
-        return ""
-
     def __repr__(self):
         return "<INVALID>"
 
+
 # invalid value is a constant singleton
 INVALID_VALUE = _InvalidValue()
 

src/tablib/utils.py

@@ -0,0 +1,13 @@
+from io import BytesIO, StringIO
+
+
+def normalize_input(stream):
+    """
+    Accept either a str/bytes stream or a file-like object and always return a
+    file-like object.
+    """
+    if isinstance(stream, str):
+        return StringIO(stream)
+    elif isinstance(stream, bytes):
+        return BytesIO(stream)
+    return stream

tablib/__init__.py

@@ -1,7 +0,0 @@
-""" Tablib. """
-
-from tablib.core import (
-    Databook, Dataset, detect_format, import_set, import_book,
-    InvalidDatasetType, InvalidDimensions, UnsupportedFormat,
-    __version__
-)

tablib/compat.py

@@ -1,38 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""
-tablib.compat
-~~~~~~~~~~~~~
-
-Tablib compatiblity module.
-
-"""
-
-import sys
-
-is_py3 = (sys.version_info[0] > 2)
-
-
-if is_py3:
-    from io import BytesIO
-    from io import StringIO
-    from tablib.packages import markup3 as markup
-    from statistics import median
-    from itertools import zip_longest as izip_longest
-    import csv
-    import tablib.packages.dbfpy3 as dbfpy
-
-    unicode = str
-    xrange = range
-
-else:
-    from cStringIO import StringIO as BytesIO
-    from StringIO import StringIO
-    from tablib.packages import markup
-    from tablib.packages.statistics import median
-    from itertools import izip_longest
-    from backports import csv
-    import tablib.packages.dbfpy as dbfpy
-
-    unicode = unicode
-    xrange = xrange

tablib/formats/__init__.py

@@ -1,20 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - formats
-"""
-
-from . import _csv as csv
-from . import _json as json
-from . import _xls as xls
-from . import _yaml as yaml
-from . import _tsv as tsv
-from . import _html as html
-from . import _xlsx as xlsx
-from . import _ods as ods
-from . import _dbf as dbf
-from . import _latex as latex
-from . import _df as df
-from . import _rst as rst
-from . import _jira as jira
-
-available = (json, xls, yaml, csv, dbf, tsv, html, jira, latex, xlsx, ods, df, rst)

tablib/formats/_csv.py

@@ -1,52 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - *SV Support.
-"""
-
-from tablib.compat import csv, StringIO, unicode
-
-
-title = 'csv'
-extensions = ('csv',)
-
-
-DEFAULT_DELIMITER = unicode(',')
-
-
-def export_set(dataset, **kwargs):
-    """Returns CSV representation of Dataset."""
-    stream = StringIO()
-
-    kwargs.setdefault('delimiter', DEFAULT_DELIMITER)
-
-    _csv = csv.writer(stream, **kwargs)
-
-    for row in dataset._package(dicts=False):
-        _csv.writerow(row)
-
-    return stream.getvalue()
-
-
-def import_set(dset, in_stream, headers=True, **kwargs):
-    """Returns dataset from CSV stream."""
-
-    dset.wipe()
-
-    kwargs.setdefault('delimiter', DEFAULT_DELIMITER)
-
-    rows = csv.reader(StringIO(in_stream), **kwargs)
-    for i, row in enumerate(rows):
-
-        if (i == 0) and (headers):
-            dset.headers = row
-        elif row:
-            dset.append(row)
-
-
-def detect(stream, delimiter=DEFAULT_DELIMITER):
-    """Returns True if given stream is valid CSV."""
-    try:
-        csv.Sniffer().sniff(stream, delimiters=delimiter)
-        return True
-    except (csv.Error, TypeError):
-        return False

tablib/formats/_dbf.py

@@ -1,91 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - DBF Support.
-"""
-import tempfile
-import struct
-import os
-
-from tablib.compat import StringIO
-from tablib.compat import dbfpy
-from tablib.compat import is_py3
-
-if is_py3:
-    from tablib.packages.dbfpy3 import dbf
-    from tablib.packages.dbfpy3 import dbfnew
-    from tablib.packages.dbfpy3 import record as dbfrecord
-    import io
-else:
-    from tablib.packages.dbfpy import dbf
-    from tablib.packages.dbfpy import dbfnew
-    from tablib.packages.dbfpy import record as dbfrecord
-
-
-title = 'dbf'
-extensions = ('csv',)
-
-DEFAULT_ENCODING = 'utf-8'
-
-def export_set(dataset):
-    """Returns DBF representation of a Dataset"""
-    new_dbf = dbfnew.dbf_new()
-    temp_file, temp_uri = tempfile.mkstemp()
-
-    # create the appropriate fields based on the contents of the first row
-    first_row = dataset[0]
-    for fieldname, field_value in zip(dataset.headers, first_row):
-        if type(field_value) in [int, float]:
-            new_dbf.add_field(fieldname, 'N', 10, 8)
-        else:
-            new_dbf.add_field(fieldname, 'C', 80)
-
-    new_dbf.write(temp_uri)
-
-    dbf_file = dbf.Dbf(temp_uri, readOnly=0)
-    for row in dataset:
-        record = dbfrecord.DbfRecord(dbf_file)
-        for fieldname, field_value in zip(dataset.headers, row):
-            record[fieldname] = field_value
-        record.store()
-
-    dbf_file.close()
-    dbf_stream = open(temp_uri, 'rb')
-    if is_py3:
-        stream = io.BytesIO(dbf_stream.read())
-    else:
-        stream = StringIO(dbf_stream.read())
-    dbf_stream.close()
-    os.close(temp_file)
-    os.remove(temp_uri)
-    return stream.getvalue()
-
-def import_set(dset, in_stream, headers=True):
-    """Returns a dataset from a DBF stream."""
-
-    dset.wipe()
-    if is_py3:
-        _dbf = dbf.Dbf(io.BytesIO(in_stream))
-    else:
-        _dbf = dbf.Dbf(StringIO(in_stream))
-    dset.headers = _dbf.fieldNames
-    for record in range(_dbf.recordCount):
-        row = [_dbf[record][f] for f in _dbf.fieldNames]
-        dset.append(row)
-
-def detect(stream):
-    """Returns True if the given stream is valid DBF"""
-    #_dbf = dbf.Table(StringIO(stream))
-    try:
-        if is_py3:
-            if type(stream) is not bytes:
-                stream = bytes(stream, 'utf-8')
-            _dbf = dbf.Dbf(io.BytesIO(stream), readOnly=True)
-        else:
-            _dbf = dbf.Dbf(StringIO(stream), readOnly=True)
-        return True
-    except (ValueError, struct.error):
-        # When we try to open up a file that's not a DBF, dbfpy raises a
-        # ValueError.
-        # When unpacking a string argument with less than 8 chars, struct.error is
-        # raised.
-        return False

tablib/formats/_df.py

@@ -1,49 +0,0 @@
-""" Tablib - DataFrame Support.
-"""
-
-
-import sys
-
-
-if sys.version_info[0] > 2:
-    from io import BytesIO
-else:
-    from cStringIO import StringIO as BytesIO
-
-try:
-    from pandas import DataFrame
-except ImportError:
-    DataFrame = None
-
-import tablib
-
-from tablib.compat import unicode
-
-title = 'df'
-extensions = ('df', )
-
-def detect(stream):
-    """Returns True if given stream is a DataFrame."""
-    if DataFrame is None:
-        return False
-    try:
-        DataFrame(stream)
-        return True
-    except ValueError:
-        return False
-
-
-def export_set(dset, index=None):
-    """Returns DataFrame representation of DataBook."""
-    if DataFrame is None:
-        raise NotImplementedError(
-            'DataFrame Format requires `pandas` to be installed.'
-            ' Try `pip install tablib[pandas]`.')
-    dataframe = DataFrame(dset.dict, columns=dset.headers)
-    return dataframe
-
-
-def import_set(dset, in_stream):
-    """Returns dataset from DataFrame."""
-    dset.wipe()
-    dset.dict = in_stream.to_dict(orient='records')

tablib/formats/_html.py

@@ -1,70 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - HTML export support.
-"""
-
-import sys
-
-if sys.version_info[0] > 2:
-    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'
-extensions = ('html', )
-
-
-def export_set(dataset):
-    """HTML representation of a Dataset."""
-
-    stream = StringIO()
-
-    page = markup.page()
-    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(new_header)
-        page.tr(headers)
-        page.thead.close()
-
-    for row in dataset:
-        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()
-
-    # Allow unicode characters in output
-    wrapper = codecs.getwriter("utf8")(stream)
-    wrapper.writelines(unicode(page))
-
-    return stream.getvalue().decode('utf-8')
-
-
-def export_book(databook):
-    """HTML representation of a Databook."""
-
-    stream = StringIO()
-
-    # Allow unicode characters in output
-    wrapper = codecs.getwriter("utf8")(stream)
-
-    for i, dset in enumerate(databook._datasets):
-        title = (dset.title if dset.title else 'Set %s' % (i))
-        wrapper.write('<%s>%s</%s>\n' % (BOOK_ENDINGS, title, BOOK_ENDINGS))
-        wrapper.write(dset.html)
-        wrapper.write('\n')
-
-    return stream.getvalue().decode('utf-8')

tablib/formats/_jira.py

@@ -1,39 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""Tablib - Jira table export support.
-
-   Generates a Jira table from the dataset.
-"""
-from tablib.compat import unicode
-
-title = 'jira'
-
-
-def export_set(dataset):
-    """Formats the dataset according to the Jira table syntax:
-
-    ||heading 1||heading 2||heading 3||
-    |col A1|col A2|col A3|
-    |col B1|col B2|col B3|
-
-    :param dataset: dataset to serialize
-    :type dataset: tablib.core.Dataset
-    """
-
-    header = _get_header(dataset.headers) if dataset.headers else ''
-    body = _get_body(dataset)
-    return '%s\n%s' % (header, body) if header else body
-
-
-def _get_body(dataset):
-    return '\n'.join([_serialize_row(row) for row in dataset])
-
-
-def _get_header(headers):
-    return _serialize_row(headers, delimiter='||')
-
-
-def _serialize_row(row, delimiter='|'):
-    return '%s%s%s' % (delimiter,
-                       delimiter.join([unicode(item) if item else ' ' for item in row]),
-                       delimiter)

tablib/formats/_json.py

@@ -1,59 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - JSON Support
-"""
-import decimal
-import json
-from uuid import UUID
-
-import tablib
-
-
-title = 'json'
-extensions = ('json', 'jsn')
-
-
-def serialize_objects_handler(obj):
-    if isinstance(obj, (decimal.Decimal, UUID)):
-        return str(obj)
-    elif hasattr(obj, 'isoformat'):
-        return obj.isoformat()
-    else:
-        return obj
-
-
-def export_set(dataset):
-    """Returns JSON representation of Dataset."""
-    return json.dumps(dataset.dict, default=serialize_objects_handler)
-
-
-def export_book(databook):
-    """Returns JSON representation of Databook."""
-    return json.dumps(databook._package(), default=serialize_objects_handler)
-
-
-def import_set(dset, in_stream):
-    """Returns dataset from JSON stream."""
-
-    dset.wipe()
-    dset.dict = json.loads(in_stream)
-
-
-def import_book(dbook, in_stream):
-    """Returns databook from JSON stream."""
-
-    dbook.wipe()
-    for sheet in json.loads(in_stream):
-        data = tablib.Dataset()
-        data.title = sheet['title']
-        data.dict = sheet['data']
-        dbook.add_sheet(data)
-
-
-def detect(stream):
-    """Returns True if given stream is valid JSON."""
-    try:
-        json.loads(stream)
-        return True
-    except ValueError:
-        return False

tablib/formats/_latex.py

@@ -1,134 +0,0 @@
-# -*- coding: utf-8 -*-
-
-"""Tablib - LaTeX table export support.
-
-   Generates a LaTeX booktabs-style table from the dataset.
-"""
-import re
-
-from tablib.compat import unicode
-
-title = 'latex'
-extensions = ('tex',)
-
-TABLE_TEMPLATE = """\
-%% Note: add \\usepackage{booktabs} to your preamble
-%%
-\\begin{table}[!htbp]
-  \\centering
-  %(CAPTION)s
-  \\begin{tabular}{%(COLSPEC)s}
-    \\toprule
-%(HEADER)s
-    %(MIDRULE)s
-%(BODY)s
-    \\bottomrule
-  \\end{tabular}
-\\end{table}
-"""
-
-TEX_RESERVED_SYMBOLS_MAP = dict([
-    ('\\', '\\textbackslash{}'),
-    ('{', '\\{'),
-    ('}', '\\}'),
-    ('$', '\\$'),
-    ('&', '\\&'),
-    ('#', '\\#'),
-    ('^', '\\textasciicircum{}'),
-    ('_', '\\_'),
-    ('~', '\\textasciitilde{}'),
-    ('%', '\\%'),
-])
-
-TEX_RESERVED_SYMBOLS_RE = re.compile(
-    '(%s)' % '|'.join(map(re.escape, TEX_RESERVED_SYMBOLS_MAP.keys())))
-
-
-def export_set(dataset):
-    """Returns LaTeX representation of dataset
-
-    :param dataset: dataset to serialize
-    :type dataset: tablib.core.Dataset
-    """
-
-    caption = '\\caption{%s}' % dataset.title if dataset.title else '%'
-    colspec = _colspec(dataset.width)
-    header = _serialize_row(dataset.headers) if dataset.headers else ''
-    midrule = _midrule(dataset.width)
-    body = '\n'.join([_serialize_row(row) for row in dataset])
-    return TABLE_TEMPLATE % dict(CAPTION=caption, COLSPEC=colspec,
-                                 HEADER=header, MIDRULE=midrule, BODY=body)
-
-
-def _colspec(dataset_width):
-    """Generates the column specification for the LaTeX `tabular` environment
-    based on the dataset width.
-
-    The first column is justified to the left, all further columns are aligned
-    to the right.
-
-    .. note:: This is only a heuristic and most probably has to be fine-tuned
-    post export. Column alignment should depend on the data type, e.g., textual
-    content should usually be aligned to the left while numeric content almost
-    always should be aligned to the right.
-
-    :param dataset_width: width of the dataset
-    """
-
-    spec = 'l'
-    for _ in range(1, dataset_width):
-        spec += 'r'
-    return spec
-
-
-def _midrule(dataset_width):
-    """Generates the table `midrule`, which may be composed of several
-    `cmidrules`.
-
-    :param dataset_width: width of the dataset to serialize
-    """
-
-    if not dataset_width or dataset_width == 1:
-        return '\\midrule'
-    return ' '.join([_cmidrule(colindex, dataset_width) for colindex in
-                     range(1, dataset_width + 1)])
-
-
-def _cmidrule(colindex, dataset_width):
-    """Generates the `cmidrule` for a single column with appropriate trimming
-    based on the column position.
-
-    :param colindex: Column index
-    :param dataset_width: width of the dataset
-    """
-
-    rule = '\\cmidrule(%s){%d-%d}'
-    if colindex == 1:
-        # Rule of first column is trimmed on the right
-        return rule % ('r', colindex, colindex)
-    if colindex == dataset_width:
-        # Rule of last column is trimmed on the left
-        return rule % ('l', colindex, colindex)
-    # Inner columns are trimmed on the left and right
-    return rule % ('lr', colindex, colindex)
-
-
-def _serialize_row(row):
-    """Returns string representation of a single row.
-
-    :param row: single dataset row
-    """
-
-    new_row = [_escape_tex_reserved_symbols(unicode(item)) if item else '' for
-               item in row]
-    return 6 * ' ' + ' & '.join(new_row) + ' \\\\'
-
-
-def _escape_tex_reserved_symbols(input):
-    """Escapes all TeX reserved symbols ('_', '~', etc.) in a string.
-
-    :param input: String to escape
-    """
-    def replace(match):
-        return TEX_RESERVED_SYMBOLS_MAP[match.group()]
-    return TEX_RESERVED_SYMBOLS_RE.sub(replace, input)

tablib/formats/_ods.py

@@ -1,93 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - ODF Support.
-"""
-
-from odf import opendocument, style, table, text
-from tablib.compat import BytesIO, unicode
-
-title = 'ods'
-extensions = ('ods',)
-
-bold = style.Style(name="bold", family="paragraph")
-bold.addElement(style.TextProperties(fontweight="bold", fontweightasian="bold", fontweightcomplex="bold"))
-
-def export_set(dataset):
-    """Returns ODF representation of Dataset."""
-
-    wb = opendocument.OpenDocumentSpreadsheet()
-    wb.automaticstyles.addElement(bold)
-
-    ws = table.Table(name=dataset.title if dataset.title else 'Tablib Dataset')
-    wb.spreadsheet.addElement(ws)
-    dset_sheet(dataset, ws)
-
-    stream = BytesIO()
-    wb.save(stream)
-    return stream.getvalue()
-
-
-def export_book(databook):
-    """Returns ODF representation of DataBook."""
-
-    wb = opendocument.OpenDocumentSpreadsheet()
-    wb.automaticstyles.addElement(bold)
-
-    for i, dset in enumerate(databook._datasets):
-        ws = table.Table(name=dset.title if dset.title else 'Sheet%s' % (i))
-        wb.spreadsheet.addElement(ws)
-        dset_sheet(dset, ws)
-
-
-    stream = BytesIO()
-    wb.save(stream)
-    return stream.getvalue()
-
-
-def dset_sheet(dataset, ws):
-    """Completes given worksheet from given Dataset."""
-    _package = dataset._package(dicts=False)
-
-    for i, sep in enumerate(dataset._separators):
-        _offset = i
-        _package.insert((sep[0] + _offset), (sep[1],))
-
-    for i, row in enumerate(_package):
-        row_number = i + 1
-        odf_row = table.TableRow(stylename=bold, defaultcellstylename='bold')
-        for j, col in enumerate(row):
-            try:
-                col = unicode(col, errors='ignore')
-            except TypeError:
-                ## col is already unicode
-                pass
-            ws.addElement(table.TableColumn())
-
-            # bold headers
-            if (row_number == 1) and dataset.headers:
-                odf_row.setAttribute('stylename', bold)
-                ws.addElement(odf_row)
-                cell = table.TableCell()
-                p = text.P()
-                p.addElement(text.Span(text=col, stylename=bold))
-                cell.addElement(p)
-                odf_row.addElement(cell)
-
-            # wrap the rest
-            else:
-                try:
-                    if '\n' in col:
-                        ws.addElement(odf_row)
-                        cell = table.TableCell()
-                        cell.addElement(text.P(text=col))
-                        odf_row.addElement(cell)
-                    else:
-                        ws.addElement(odf_row)
-                        cell = table.TableCell()
-                        cell.addElement(text.P(text=col))
-                        odf_row.addElement(cell)
-                except TypeError:
-                    ws.addElement(odf_row)
-                    cell = table.TableCell()
-                    cell.addElement(text.P(text=col))
-                    odf_row.addElement(cell)

tablib/formats/_rst.py

@@ -1,273 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - reStructuredText Support
-"""
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-
-from textwrap import TextWrapper
-
-from tablib.compat import (
-    median,
-    unicode,
-    izip_longest,
-)
-
-
-title = 'rst'
-extensions = ('rst',)
-
-
-MAX_TABLE_WIDTH = 80  # Roughly. It may be wider to avoid breaking words.
-
-
-JUSTIFY_LEFT = 'left'
-JUSTIFY_CENTER = 'center'
-JUSTIFY_RIGHT = 'right'
-JUSTIFY_VALUES = (JUSTIFY_LEFT, JUSTIFY_CENTER, JUSTIFY_RIGHT)
-
-
-def to_unicode(value):
-    if isinstance(value, bytes):
-        return value.decode('utf-8')
-    return unicode(value)
-
-
-def _max_word_len(text):
-    """
-    Return the length of the longest word in `text`.
-
-
-    >>> _max_word_len('Python Module for Tabular Datasets')
-    8
-
-    """
-    return max((len(word) for word in text.split()))
-
-
-def _get_column_string_lengths(dataset):
-    """
-    Returns a list of string lengths of each column, and a list of
-    maximum word lengths.
-    """
-    if dataset.headers:
-        column_lengths = [[len(h)] for h in dataset.headers]
-        word_lens = [_max_word_len(h) for h in dataset.headers]
-    else:
-        column_lengths = [[] for _ in range(dataset.width)]
-        word_lens = [0 for _ in range(dataset.width)]
-    for row in dataset.dict:
-        values = iter(row.values() if hasattr(row, 'values') else row)
-        for i, val in enumerate(values):
-            text = to_unicode(val)
-            column_lengths[i].append(len(text))
-            word_lens[i] = max(word_lens[i], _max_word_len(text))
-    return column_lengths, word_lens
-
-
-def _row_to_lines(values, widths, wrapper, sep='|', justify=JUSTIFY_LEFT):
-    """
-    Returns a table row of wrapped values as a list of lines
-    """
-    if justify not in JUSTIFY_VALUES:
-        raise ValueError('Value of "justify" must be one of "{}"'.format(
-            '", "'.join(JUSTIFY_VALUES)
-        ))
-    if justify == JUSTIFY_LEFT:
-        just = lambda text, width: text.ljust(width)
-    elif justify == JUSTIFY_CENTER:
-        just = lambda text, width: text.center(width)
-    else:
-        just = lambda text, width: text.rjust(width)
-    lpad = sep + ' ' if sep else ''
-    rpad = ' ' + sep if sep else ''
-    pad = ' ' + sep + ' '
-    cells = []
-    for value, width in zip(values, widths):
-        wrapper.width = width
-        text = to_unicode(value)
-        cell = wrapper.wrap(text)
-        cells.append(cell)
-    lines = izip_longest(*cells, fillvalue='')
-    lines = (
-        (just(cell_line, widths[i]) for i, cell_line in enumerate(line))
-        for line in lines
-    )
-    lines = [''.join((lpad, pad.join(line), rpad)) for line in lines]
-    return lines
-
-
-def _get_column_widths(dataset, max_table_width=MAX_TABLE_WIDTH, pad_len=3):
-    """
-    Returns a list of column widths proportional to the median length
-    of the text in their cells.
-    """
-    str_lens, word_lens = _get_column_string_lengths(dataset)
-    median_lens = [int(median(lens)) for lens in str_lens]
-    total = sum(median_lens)
-    if total > max_table_width - (pad_len * len(median_lens)):
-        column_widths = (max_table_width * l // total for l in median_lens)
-    else:
-        column_widths = (l for l in median_lens)
-    # Allow for separator and padding:
-    column_widths = (w - pad_len if w > pad_len else w for w in column_widths)
-    # Rather widen table than break words:
-    column_widths = [max(w, l) for w, l in zip(column_widths, word_lens)]
-    return column_widths
-
-
-def export_set_as_simple_table(dataset, column_widths=None):
-    """
-    Returns reStructuredText grid table representation of dataset.
-    """
-    lines = []
-    wrapper = TextWrapper()
-    if column_widths is None:
-        column_widths = _get_column_widths(dataset, pad_len=2)
-    border = '  '.join(['=' * w for w in column_widths])
-
-    lines.append(border)
-    if dataset.headers:
-        lines.extend(_row_to_lines(
-            dataset.headers,
-            column_widths,
-            wrapper,
-            sep='',
-            justify=JUSTIFY_CENTER,
-        ))
-        lines.append(border)
-    for row in dataset.dict:
-        values = iter(row.values() if hasattr(row, 'values') else row)
-        lines.extend(_row_to_lines(values, column_widths, wrapper, ''))
-    lines.append(border)
-    return '\n'.join(lines)
-
-
-def export_set_as_grid_table(dataset, column_widths=None):
-    """
-    Returns reStructuredText grid table representation of dataset.
-
-
-    >>> from tablib import Dataset
-    >>> from tablib.formats import rst
-    >>> bits = ((0, 0), (1, 0), (0, 1), (1, 1))
-    >>> data = Dataset()
-    >>> data.headers = ['A', 'B', 'A and B']
-    >>> for a, b in bits:
-    ...     data.append([bool(a), bool(b), bool(a * b)])
-    >>> print(rst.export_set(data, force_grid=True))
-    +-------+-------+-------+
-    |   A   |   B   | A and |
-    |       |       |   B   |
-    +=======+=======+=======+
-    | False | False | False |
-    +-------+-------+-------+
-    | True  | False | False |
-    +-------+-------+-------+
-    | False | True  | False |
-    +-------+-------+-------+
-    | True  | True  | True  |
-    +-------+-------+-------+
-
-    """
-    lines = []
-    wrapper = TextWrapper()
-    if column_widths is None:
-        column_widths = _get_column_widths(dataset)
-    header_sep = '+=' + '=+='.join(['=' * w for w in column_widths]) + '=+'
-    row_sep = '+-' + '-+-'.join(['-' * w for w in column_widths]) + '-+'
-
-    lines.append(row_sep)
-    if dataset.headers:
-        lines.extend(_row_to_lines(
-            dataset.headers,
-            column_widths,
-            wrapper,
-            justify=JUSTIFY_CENTER,
-        ))
-        lines.append(header_sep)
-    for row in dataset.dict:
-        values = iter(row.values() if hasattr(row, 'values') else row)
-        lines.extend(_row_to_lines(values, column_widths, wrapper))
-        lines.append(row_sep)
-    return '\n'.join(lines)
-
-
-def _use_simple_table(head0, col0, width0):
-    """
-    Use a simple table if the text in the first column is never wrapped
-
-
-    >>> _use_simple_table('menu', ['egg', 'bacon'], 10)
-    True
-    >>> _use_simple_table(None, ['lobster thermidor', 'spam'], 10)
-    False
-
-    """
-    if head0 is not None:
-        head0 = to_unicode(head0)
-        if len(head0) > width0:
-            return False
-    for cell in col0:
-        cell = to_unicode(cell)
-        if len(cell) > width0:
-            return False
-    return True
-
-
-def export_set(dataset, **kwargs):
-    """
-    Returns reStructuredText table representation of dataset.
-
-    Returns a simple table if the text in the first column is never
-    wrapped, otherwise returns a grid table.
-
-
-    >>> from tablib import Dataset
-    >>> bits = ((0, 0), (1, 0), (0, 1), (1, 1))
-    >>> data = Dataset()
-    >>> data.headers = ['A', 'B', 'A and B']
-    >>> for a, b in bits:
-    ...     data.append([bool(a), bool(b), bool(a * b)])
-    >>> table = data.rst
-    >>> table.split('\\n') == [
-    ...     '=====  =====  =====',
-    ...     '  A      B    A and',
-    ...     '                B  ',
-    ...     '=====  =====  =====',
-    ...     'False  False  False',
-    ...     'True   False  False',
-    ...     'False  True   False',
-    ...     'True   True   True ',
-    ...     '=====  =====  =====',
-    ... ]
-    True
-
-    """
-    if not dataset.dict:
-        return ''
-    force_grid = kwargs.get('force_grid', False)
-    max_table_width = kwargs.get('max_table_width', MAX_TABLE_WIDTH)
-    column_widths = _get_column_widths(dataset, max_table_width)
-
-    use_simple_table = _use_simple_table(
-        dataset.headers[0] if dataset.headers else None,
-        dataset.get_col(0),
-        column_widths[0],
-    )
-    if use_simple_table and not force_grid:
-        return export_set_as_simple_table(dataset, column_widths)
-    else:
-        return export_set_as_grid_table(dataset, column_widths)
-
-
-def export_book(databook):
-    """
-    reStructuredText representation of a Databook.
-
-    Tables are separated by a blank line. All tables use the grid
-    format.
-    """
-    return '\n\n'.join(export_set(dataset, force_grid=True)
-                       for dataset in databook._datasets)

tablib/formats/_tsv.py

@@ -1,30 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - TSV (Tab Separated Values) Support.
-"""
-
-from tablib.compat import unicode
-from tablib.formats._csv import (
-    export_set as export_set_wrapper,
-    import_set as import_set_wrapper,
-    detect as detect_wrapper,
-)
-
-title = 'tsv'
-extensions = ('tsv',)
-
-DELIMITER = unicode('\t')
-
-def export_set(dataset):
-    """Returns TSV representation of Dataset."""
-    return export_set_wrapper(dataset, delimiter=DELIMITER)
-
-
-def import_set(dset, in_stream, headers=True):
-    """Returns dataset from TSV stream."""
-    return import_set_wrapper(dset, in_stream, headers=headers, delimiter=DELIMITER)
-
-
-def detect(stream):
-    """Returns True if given stream is valid TSV."""
-    return detect_wrapper(stream, delimiter=DELIMITER)

tablib/formats/_xls.py

@@ -1,138 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - XLS Support.
-"""
-
-import sys
-
-from tablib.compat import BytesIO, xrange
-import tablib
-import xlrd
-import xlwt
-from xlrd.biffh import XLRDError
-
-title = '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."""
-
-    wb = xlwt.Workbook(encoding='utf8')
-    ws = wb.add_sheet(dataset.title if dataset.title else 'Tablib Dataset')
-
-    dset_sheet(dataset, ws)
-
-    stream = BytesIO()
-    wb.save(stream)
-    return stream.getvalue()
-
-
-def export_book(databook):
-    """Returns XLS representation of DataBook."""
-
-    wb = xlwt.Workbook(encoding='utf8')
-
-    for i, dset in enumerate(databook._datasets):
-        ws = wb.add_sheet(dset.title if dset.title else 'Sheet%s' % (i))
-
-        dset_sheet(dset, ws)
-
-
-    stream = BytesIO()
-    wb.save(stream)
-    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)
-
-    for i, sep in enumerate(dataset._separators):
-        _offset = i
-        _package.insert((sep[0] + _offset), (sep[1],))
-
-    for i, row in enumerate(_package):
-        for j, col in enumerate(row):
-
-            # bold headers
-            if (i == 0) and dataset.headers:
-                ws.write(i, j, col, bold)
-
-                # frozen header row
-                ws.panes_frozen = True
-                ws.horz_split_pos = 1
-
-
-            # bold separators
-            elif len(row) < dataset.width:
-                ws.write(i, j, col, bold)
-
-            # wrap the rest
-            else:
-                try:
-                    if '\n' in col:
-                        ws.write(i, j, col, wrap)
-                    else:
-                        ws.write(i, j, col)
-                except TypeError:
-                    ws.write(i, j, col)

tablib/formats/_xlsx.py

@@ -1,147 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - XLSX Support.
-"""
-
-import sys
-
-
-if sys.version_info[0] > 2:
-    from io import BytesIO
-else:
-    from cStringIO import StringIO as BytesIO
-
-import openpyxl
-import tablib
-
-Workbook = openpyxl.workbook.Workbook
-ExcelWriter = openpyxl.writer.excel.ExcelWriter
-get_column_letter = openpyxl.utils.get_column_letter
-
-from tablib.compat import unicode
-
-
-title = '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, freeze_panes=True):
-    """Returns XLSX representation of Dataset."""
-
-    wb = Workbook()
-    ws = wb.worksheets[0]
-    ws.title = dataset.title if dataset.title else 'Tablib Dataset'
-
-    dset_sheet(dataset, ws, freeze_panes=freeze_panes)
-
-    stream = BytesIO()
-    wb.save(stream)
-    return stream.getvalue()
-
-
-def export_book(databook, freeze_panes=True):
-    """Returns XLSX representation of DataBook."""
-
-    wb = Workbook()
-    for sheet in wb.worksheets:
-        wb.remove(sheet)
-    for i, dset in enumerate(databook._datasets):
-        ws = wb.create_sheet()
-        ws.title = dset.title if dset.title else 'Sheet%s' % (i)
-
-        dset_sheet(dset, ws, freeze_panes=freeze_panes)
-
-
-    stream = BytesIO()
-    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(BytesIO(in_stream))
-    sheet = xls_book.active
-
-    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(BytesIO(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, freeze_panes=True):
-    """Completes given worksheet from given Dataset."""
-    _package = dataset._package(dicts=False)
-
-    for i, sep in enumerate(dataset._separators):
-        _offset = i
-        _package.insert((sep[0] + _offset), (sep[1],))
-
-    bold = openpyxl.styles.Font(bold=True)
-    wrap_text = openpyxl.styles.Alignment(wrap_text=True)
-
-    for i, row in enumerate(_package):
-        row_number = i + 1
-        for j, col in enumerate(row):
-            col_idx = get_column_letter(j + 1)
-            cell = ws['%s%s' % (col_idx, row_number)]
-
-            # bold headers
-            if (row_number == 1) and dataset.headers:
-                # cell.value = unicode('%s' % col, errors='ignore')
-                cell.value = unicode(col)
-                cell.font = bold
-                if freeze_panes:
-                    #  Export Freeze only after first Line
-                    ws.freeze_panes = 'A2'
-
-            # bold separators
-            elif len(row) < dataset.width:
-                cell.value = unicode('%s' % col, errors='ignore')
-                cell.font = bold
-
-            # wrap the rest
-            else:
-                try:
-                    if '\n' in col:
-                        cell.value = unicode('%s' % col, errors='ignore')
-                        cell.alignment = wrap_text
-                    else:
-                        cell.value = unicode('%s' % col, errors='ignore')
-                except TypeError:
-                    cell.value = unicode(col)

tablib/formats/_yaml.py

@@ -1,53 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - YAML Support.
-"""
-
-import tablib
-import yaml
-
-title = 'yaml'
-extensions = ('yaml', 'yml')
-
-
-def export_set(dataset):
-    """Returns YAML representation of Dataset."""
-
-    return yaml.safe_dump(dataset._package(ordered=False))
-
-
-def export_book(databook):
-    """Returns YAML representation of Databook."""
-    return yaml.safe_dump(databook._package(ordered=False))
-
-
-def import_set(dset, in_stream):
-    """Returns dataset from YAML stream."""
-
-    dset.wipe()
-    dset.dict = yaml.safe_load(in_stream)
-
-
-def import_book(dbook, in_stream):
-    """Returns databook from YAML stream."""
-
-    dbook.wipe()
-
-    for sheet in yaml.safe_load(in_stream):
-        data = tablib.Dataset()
-        data.title = sheet['title']
-        data.dict = sheet['data']
-        dbook.add_sheet(data)
-
-
-def detect(stream):
-    """Returns True if given stream is valid YAML."""
-    try:
-        _yaml = yaml.safe_load(stream)
-        if isinstance(_yaml, (list, tuple, dict)):
-            return True
-        else:
-            return False
-    except (yaml.parser.ParserError, yaml.reader.ReaderError,
-            yaml.scanner.ScannerError):
-        return False

tablib/packages/dbfpy/dbf.py

@@ -1,297 +0,0 @@
-#! /usr/bin/env python
-"""DBF accessing helpers.
-
-FIXME: more documentation needed
-
-Examples:
-
-    Create new table, setup structure, add records:
-
-        dbf = Dbf(filename, new=True)
-        dbf.addField(
-            ("NAME", "C", 15),
-            ("SURNAME", "C", 25),
-            ("INITIALS", "C", 10),
-            ("BIRTHDATE", "D"),
-        )
-        for (n, s, i, b) in (
-            ("John", "Miller", "YC", (1980, 10, 11)),
-            ("Andy", "Larkin", "", (1980, 4, 11)),
-        ):
-            rec = dbf.newRecord()
-            rec["NAME"] = n
-            rec["SURNAME"] = s
-            rec["INITIALS"] = i
-            rec["BIRTHDATE"] = b
-            rec.store()
-        dbf.close()
-
-    Open existed dbf, read some data:
-
-        dbf = Dbf(filename, True)
-        for rec in dbf:
-            for fldName in dbf.fieldNames:
-                print '%s:\t %s (%s)' % (fldName, rec[fldName],
-                    type(rec[fldName]))
-            print
-        dbf.close()
-
-"""
-"""History (most recent first):
-11-feb-2007 [als]   export INVALID_VALUE;
-                    Dbf: added .ignoreErrors, .INVALID_VALUE
-04-jul-2006 [als]   added export declaration
-20-dec-2005 [yc]    removed fromStream and newDbf methods:
-                    use argument of __init__ call must be used instead;
-                    added class fields pointing to the header and
-                    record classes.
-17-dec-2005 [yc]    split to several modules; reimplemented
-13-dec-2005 [yc]    adapted to the changes of the `strutil` module.
-13-sep-2002 [als]   support FoxPro Timestamp datatype
-15-nov-1999 [jjk]   documentation updates, add demo
-24-aug-1998 [jjk]   add some encodeValue methods (not tested), other tweaks
-08-jun-1998 [jjk]   fix problems, add more features
-20-feb-1998 [jjk]   fix problems, add more features
-19-feb-1998 [jjk]   add create/write capabilities
-18-feb-1998 [jjk]   from dbfload.py
-"""
-
-__version__ = "$Revision: 1.7 $"[11:-2]
-__date__ = "$Date: 2007/02/11 09:23:13 $"[7:-2]
-__author__ = "Jeff Kunce <kuncej@mail.conservation.state.mo.us>"
-
-__all__ = ["Dbf"]
-
-from . import header
-from . import record
-from utils import INVALID_VALUE
-
-
-class Dbf(object):
-    """DBF accessor.
-
-    FIXME:
-        docs and examples needed (dont' forget to tell
-        about problems adding new fields on the fly)
-
-    Implementation notes:
-        ``_new`` field is used to indicate whether this is
-        a new data table. `addField` could be used only for
-        the new tables! If at least one record was appended
-        to the table it's structure couldn't be changed.
-
-    """
-
-    __slots__ = ("name", "header", "stream",
-                 "_changed", "_new", "_ignore_errors")
-
-    HeaderClass = header.DbfHeader
-    RecordClass = record.DbfRecord
-    INVALID_VALUE = INVALID_VALUE
-
-    # initialization and creation helpers
-
-    def __init__(self, f, readOnly=False, new=False, ignoreErrors=False):
-        """Initialize instance.
-
-        Arguments:
-            f:
-                Filename or file-like object.
-            new:
-                True if new data table must be created. Assume
-                data table exists if this argument is False.
-            readOnly:
-                if ``f`` argument is a string file will
-                be opend in read-only mode; in other cases
-                this argument is ignored. This argument is ignored
-                even if ``new`` argument is True.
-            headerObj:
-                `header.DbfHeader` instance or None. If this argument
-                is None, new empty header will be used with the
-                all fields set by default.
-            ignoreErrors:
-                if set, failing field value conversion will return
-                ``INVALID_VALUE`` instead of raising conversion error.
-
-        """
-        if isinstance(f, basestring):
-            # a filename
-            self.name = f
-            if new:
-                # new table (table file must be
-                # created or opened and truncated)
-                self.stream = file(f, "w+b")
-            else:
-                # tabe file must exist
-                self.stream = file(f, ("r+b", "rb")[bool(readOnly)])
-        else:
-            # a stream
-            self.name = getattr(f, "name", "")
-            self.stream = f
-        if new:
-            # if this is a new table, header will be empty
-            self.header = self.HeaderClass()
-        else:
-            # or instantiated using stream
-            self.header = self.HeaderClass.fromStream(self.stream)
-        self.ignoreErrors = ignoreErrors
-        self._new = bool(new)
-        self._changed = False
-
-    # properties
-
-    closed = property(lambda self: self.stream.closed)
-    recordCount = property(lambda self: self.header.recordCount)
-    fieldNames = property(
-        lambda self: [_fld.name for _fld in self.header.fields])
-    fieldDefs = property(lambda self: self.header.fields)
-    changed = property(lambda self: self._changed or self.header.changed)
-
-    def ignoreErrors(self, value):
-        """Update `ignoreErrors` flag on the header object and self"""
-        self.header.ignoreErrors = self._ignore_errors = bool(value)
-
-    ignoreErrors = property(
-        lambda self: self._ignore_errors,
-        ignoreErrors,
-        doc="""Error processing mode for DBF field value conversion
-
-        if set, failing field value conversion will return
-        ``INVALID_VALUE`` instead of raising conversion error.
-
-        """)
-
-    # protected methods
-
-    def _fixIndex(self, index):
-        """Return fixed index.
-
-        This method fails if index isn't a numeric object
-        (long or int). Or index isn't in a valid range
-        (less or equal to the number of records in the db).
-
-        If ``index`` is a negative number, it will be
-        treated as a negative indexes for list objects.
-
-        Return:
-            Return value is numeric object maning valid index.
-
-        """
-        if not isinstance(index, (int, long)):
-            raise TypeError("Index must be a numeric object")
-        if index < 0:
-            # index from the right side
-            # fix it to the left-side index
-            index += len(self) + 1
-        if index >= len(self):
-            raise IndexError("Record index out of range")
-        return index
-
-    # iterface methods
-
-    def close(self):
-        self.flush()
-        self.stream.close()
-
-    def flush(self):
-        """Flush data to the associated stream."""
-        if self.changed:
-            self.header.setCurrentDate()
-            self.header.write(self.stream)
-            self.stream.flush()
-            self._changed = False
-
-    def indexOfFieldName(self, name):
-        """Index of field named ``name``."""
-        # FIXME: move this to header class
-        return self.header.fields.index(name)
-
-    def newRecord(self):
-        """Return new record, which belong to this table."""
-        return self.RecordClass(self)
-
-    def append(self, record):
-        """Append ``record`` to the database."""
-        record.index = self.header.recordCount
-        record._write()
-        self.header.recordCount += 1
-        self._changed = True
-        self._new = False
-
-    def addField(self, *defs):
-        """Add field definitions.
-
-        For more information see `header.DbfHeader.addField`.
-
-        """
-        if self._new:
-            self.header.addField(*defs)
-        else:
-            raise TypeError("At least one record was added, "
-                            "structure can't be changed")
-
-    # 'magic' methods (representation and sequence interface)
-
-    def __repr__(self):
-        return "Dbf stream '%s'\n" % self.stream + repr(self.header)
-
-    def __len__(self):
-        """Return number of records."""
-        return self.recordCount
-
-    def __getitem__(self, index):
-        """Return `DbfRecord` instance."""
-        return self.RecordClass.fromStream(self, self._fixIndex(index))
-
-    def __setitem__(self, index, record):
-        """Write `DbfRecord` instance to the stream."""
-        record.index = self._fixIndex(index)
-        record._write()
-        self._changed = True
-        self._new = False
-
-        # def __del__(self):
-        #    """Flush stream upon deletion of the object."""
-        #    self.flush()
-
-
-def demo_read(filename):
-    _dbf = Dbf(filename, True)
-    for _rec in _dbf:
-        print
-        print(repr(_rec))
-    _dbf.close()
-
-
-def demo_create(filename):
-    _dbf = Dbf(filename, new=True)
-    _dbf.addField(
-        ("NAME", "C", 15),
-        ("SURNAME", "C", 25),
-        ("INITIALS", "C", 10),
-        ("BIRTHDATE", "D"),
-    )
-    for (_n, _s, _i, _b) in (
-            ("John", "Miller", "YC", (1981, 1, 2)),
-            ("Andy", "Larkin", "AL", (1982, 3, 4)),
-            ("Bill", "Clinth", "", (1983, 5, 6)),
-            ("Bobb", "McNail", "", (1984, 7, 8)),
-    ):
-        _rec = _dbf.newRecord()
-        _rec["NAME"] = _n
-        _rec["SURNAME"] = _s
-        _rec["INITIALS"] = _i
-        _rec["BIRTHDATE"] = _b
-        _rec.store()
-    print(repr(_dbf))
-    _dbf.close()
-
-
-if __name__ == '__main__':
-    import sys
-
-    _name = len(sys.argv) > 1 and sys.argv[1] or "county.dbf"
-    demo_create(_name)
-    demo_read(_name)
-
-    # vim: set et sw=4 sts=4 :

tablib/packages/dbfpy/dbfnew.py

@@ -1,189 +0,0 @@
-#!/usr/bin/python
-""".DBF creation helpers.
-
-Note: this is a legacy interface.  New code should use Dbf class
-    for table creation (see examples in dbf.py)
-
-TODO:
-  - handle Memo fields.
-  - check length of the fields accoring to the
-    `http://www.clicketyclick.dk/databases/xbase/format/data_types.html`
-
-"""
-"""History (most recent first)
-04-jul-2006 [als]   added export declaration;
-                    updated for dbfpy 2.0
-15-dec-2005 [yc]    define dbf_new.__slots__
-14-dec-2005 [yc]    added vim modeline; retab'd; added doc-strings;
-                    dbf_new now is a new class (inherited from object)
-??-jun-2000 [--]    added by Hans Fiby
-"""
-
-__version__ = "$Revision: 1.4 $"[11:-2]
-__date__ = "$Date: 2006/07/04 08:18:18 $"[7:-2]
-
-__all__ = ["dbf_new"]
-
-from dbf import *
-from fields import *
-from header import *
-from record import *
-
-
-class _FieldDefinition(object):
-    """Field definition.
-
-    This is a simple structure, which contains ``name``, ``type``,
-    ``len``, ``dec`` and ``cls`` fields.
-
-    Objects also implement get/setitem magic functions, so fields
-    could be accessed via sequence iterface, where 'name' has
-    index 0, 'type' index 1, 'len' index 2, 'dec' index 3 and
-    'cls' could be located at index 4.
-
-    """
-
-    __slots__ = "name", "type", "len", "dec", "cls"
-
-    # WARNING: be attentive - dictionaries are mutable!
-    FLD_TYPES = {
-        # type: (cls, len)
-        "C": (DbfCharacterFieldDef, None),
-        "N": (DbfNumericFieldDef, None),
-        "L": (DbfLogicalFieldDef, 1),
-        # FIXME: support memos
-        # "M": (DbfMemoFieldDef),
-        "D": (DbfDateFieldDef, 8),
-        # FIXME: I'm not sure length should be 14 characters!
-        # but temporary I use it, cuz date is 8 characters
-        # and time 6 (hhmmss)
-        "T": (DbfDateTimeFieldDef, 14),
-    }
-
-    def __init__(self, name, type, len=None, dec=0):
-        _cls, _len = self.FLD_TYPES[type]
-        if _len is None:
-            if len is None:
-                raise ValueError("Field length must be defined")
-            _len = len
-        self.name = name
-        self.type = type
-        self.len = _len
-        self.dec = dec
-        self.cls = _cls
-
-    def getDbfField(self):
-        "Return `DbfFieldDef` instance from the current definition."
-        return self.cls(self.name, self.len, self.dec)
-
-    def appendToHeader(self, dbfh):
-        """Create a `DbfFieldDef` instance and append it to the dbf header.
-
-        Arguments:
-            dbfh: `DbfHeader` instance.
-
-        """
-        _dbff = self.getDbfField()
-        dbfh.addField(_dbff)
-
-
-class dbf_new(object):
-    """New .DBF creation helper.
-
-    Example Usage:
-
-        dbfn = dbf_new()
-        dbfn.add_field("name",'C',80)
-        dbfn.add_field("price",'N',10,2)
-        dbfn.add_field("date",'D',8)
-        dbfn.write("tst.dbf")
-
-    Note:
-        This module cannot handle Memo-fields,
-        they are special.
-
-    """
-
-    __slots__ = ("fields",)
-
-    FieldDefinitionClass = _FieldDefinition
-
-    def __init__(self):
-        self.fields = []
-
-    def add_field(self, name, typ, len, dec=0):
-        """Add field definition.
-
-        Arguments:
-            name:
-                field name (str object). field name must not
-                contain ASCII NULs and it's length shouldn't
-                exceed 10 characters.
-            typ:
-                type of the field. this must be a single character
-                from the "CNLMDT" set meaning character, numeric,
-                logical, memo, date and date/time respectively.
-            len:
-                length of the field. this argument is used only for
-                the character and numeric fields. all other fields
-                have fixed length.
-                FIXME: use None as a default for this argument?
-            dec:
-                decimal precision. used only for the numric fields.
-
-        """
-        self.fields.append(self.FieldDefinitionClass(name, typ, len, dec))
-
-    def write(self, filename):
-        """Create empty .DBF file using current structure."""
-        _dbfh = DbfHeader()
-        _dbfh.setCurrentDate()
-        for _fldDef in self.fields:
-            _fldDef.appendToHeader(_dbfh)
-        _dbfStream = file(filename, "wb")
-        _dbfh.write(_dbfStream)
-        _dbfStream.close()
-
-    def write_stream(self, stream):
-        _dbfh = DbfHeader()
-        _dbfh.setCurrentDate()
-        for _fldDef in self.fields:
-            _fldDef.appendToHeader(_dbfh)
-        _dbfh.write(stream)
-
-
-if __name__ == '__main__':
-    # create a new DBF-File
-    dbfn = dbf_new()
-    dbfn.add_field("name", 'C', 80)
-    dbfn.add_field("price", 'N', 10, 2)
-    dbfn.add_field("date", 'D', 8)
-    dbfn.write("tst.dbf")
-    # test new dbf
-    print "*** created tst.dbf: ***"
-    dbft = Dbf('tst.dbf', readOnly=0)
-    print repr(dbft)
-    # add a record
-    rec = DbfRecord(dbft)
-    rec['name'] = 'something'
-    rec['price'] = 10.5
-    rec['date'] = (2000, 1, 12)
-    rec.store()
-    # add another record
-    rec = DbfRecord(dbft)
-    rec['name'] = 'foo and bar'
-    rec['price'] = 12234
-    rec['date'] = (1992, 7, 15)
-    rec.store()
-
-    # show the records
-    print "*** inserted 2 records into tst.dbf: ***"
-    print repr(dbft)
-    for i1 in range(len(dbft)):
-        rec = dbft[i1]
-        for fldName in dbft.fieldNames:
-            print '%s:\t %s' % (fldName, rec[fldName])
-        print
-    dbft.close()
-
-    # vim: set et sts=4 sw=4 :

tablib/packages/dbfpy/fields.py

@@ -1,466 +0,0 @@
-"""DBF fields definitions.
-
-TODO:
-  - make memos work
-"""
-"""History (most recent first):
-26-may-2009 [als]   DbfNumericFieldDef.decodeValue: strip zero bytes
-05-feb-2009 [als]   DbfDateFieldDef.encodeValue: empty arg produces empty date
-16-sep-2008 [als]   DbfNumericFieldDef decoding looks for decimal point
-                    in the value to select float or integer return type
-13-mar-2008 [als]   check field name length in constructor
-11-feb-2007 [als]   handle value conversion errors
-10-feb-2007 [als]   DbfFieldDef: added .rawFromRecord()
-01-dec-2006 [als]   Timestamp columns use None for empty values
-31-oct-2006 [als]   support field types 'F' (float), 'I' (integer)
-                    and 'Y' (currency);
-                    automate export and registration of field classes
-04-jul-2006 [als]   added export declaration
-10-mar-2006 [als]   decode empty values for Date and Logical fields;
-                    show field name in errors
-10-mar-2006 [als]   fix Numeric value decoding: according to spec,
-                    value always is string representation of the number;
-                    ensure that encoded Numeric value fits into the field
-20-dec-2005 [yc]    use field names in upper case
-15-dec-2005 [yc]    field definitions moved from `dbf`.
-"""
-
-__version__ = "$Revision: 1.14 $"[11:-2]
-__date__ = "$Date: 2009/05/26 05:16:51 $"[7:-2]
-
-__all__ = ["lookupFor",] # field classes added at the end of the module
-
-import datetime
-import struct
-import sys
-
-from . import utils
-
-## abstract definitions
-
-class DbfFieldDef(object):
-    """Abstract field definition.
-
-    Child classes must override ``type`` class attribute to provide datatype
-    infromation of the field definition. For more info about types visit
-    `http://www.clicketyclick.dk/databases/xbase/format/data_types.html`
-
-    Also child classes must override ``defaultValue`` field to provide
-    default value for the field value.
-
-    If child class has fixed length ``length`` class attribute must be
-    overriden and set to the valid value. None value means, that field
-    isn't of fixed length.
-
-    Note: ``name`` field must not be changed after instantiation.
-
-    """
-
-    __slots__ = ("name", "length", "decimalCount",
-        "start", "end", "ignoreErrors")
-
-    # length of the field, None in case of variable-length field,
-    # or a number if this field is a fixed-length field
-    length = None
-
-    # field type. for more information about fields types visit
-    # `http://www.clicketyclick.dk/databases/xbase/format/data_types.html`
-    # must be overriden in child classes
-    typeCode = None
-
-    # default value for the field. this field must be
-    # overriden in child classes
-    defaultValue = None
-
-    def __init__(self, name, length=None, decimalCount=None,
-        start=None, stop=None, ignoreErrors=False,
-    ):
-        """Initialize instance."""
-        assert self.typeCode is not None, "Type code must be overriden"
-        assert self.defaultValue is not None, "Default value must be overriden"
-        ## fix arguments
-        if len(name) >10:
-            raise ValueError("Field name \"%s\" is too long" % name)
-        name = str(name).upper()
-        if self.__class__.length is None:
-            if length is None:
-                raise ValueError("[%s] Length isn't specified" % name)
-            length = int(length)
-            if length <= 0:
-                raise ValueError("[%s] Length must be a positive integer"
-                    % name)
-        else:
-            length = self.length
-        if decimalCount is None:
-            decimalCount = 0
-        ## set fields
-        self.name = name
-        # FIXME: validate length according to the specification at
-        # http://www.clicketyclick.dk/databases/xbase/format/data_types.html
-        self.length = length
-        self.decimalCount = decimalCount
-        self.ignoreErrors = ignoreErrors
-        self.start = start
-        self.end = stop
-
-    def __cmp__(self, other):
-        return cmp(self.name, str(other).upper())
-
-    def __hash__(self):
-        return hash(self.name)
-
-    def fromString(cls, string, start, ignoreErrors=False):
-        """Decode dbf field definition from the string data.
-
-        Arguments:
-            string:
-                a string, dbf definition is decoded from. length of
-                the string must be 32 bytes.
-            start:
-                position in the database file.
-            ignoreErrors:
-                initial error processing mode for the new field (boolean)
-
-        """
-        assert len(string) == 32
-        _length = ord(string[16])
-        return cls(utils.unzfill(string)[:11], _length, ord(string[17]),
-            start, start + _length, ignoreErrors=ignoreErrors)
-    fromString = classmethod(fromString)
-
-    def toString(self):
-        """Return encoded field definition.
-
-        Return:
-            Return value is a string object containing encoded
-            definition of this field.
-
-        """
-        if sys.version_info < (2, 4):
-            # earlier versions did not support padding character
-            _name = self.name[:11] + "\0" * (11 - len(self.name))
-        else:
-            _name = self.name.ljust(11, '\0')
-        return (
-            _name +
-            self.typeCode +
-            #data address
-            chr(0) * 4 +
-            chr(self.length) +
-            chr(self.decimalCount) +
-            chr(0) * 14
-        )
-
-    def __repr__(self):
-        return "%-10s %1s %3d %3d" % self.fieldInfo()
-
-    def fieldInfo(self):
-        """Return field information.
-
-        Return:
-            Return value is a (name, type, length, decimals) tuple.
-
-        """
-        return (self.name, self.typeCode, self.length, self.decimalCount)
-
-    def rawFromRecord(self, record):
-        """Return a "raw" field value from the record string."""
-        return record[self.start:self.end]
-
-    def decodeFromRecord(self, record):
-        """Return decoded field value from the record string."""
-        try:
-            return self.decodeValue(self.rawFromRecord(record))
-        except:
-            if self.ignoreErrors:
-                return utils.INVALID_VALUE
-            else:
-                raise
-
-    def decodeValue(self, value):
-        """Return decoded value from string value.
-
-        This method shouldn't be used publicly. It's called from the
-        `decodeFromRecord` method.
-
-        This is an abstract method and it must be overridden in child classes.
-        """
-        raise NotImplementedError
-
-    def encodeValue(self, value):
-        """Return str object containing encoded field value.
-
-        This is an abstract method and it must be overriden in child classes.
-        """
-        raise NotImplementedError
-
-## real classes
-
-class DbfCharacterFieldDef(DbfFieldDef):
-    """Definition of the character field."""
-
-    typeCode = "C"
-    defaultValue = ""
-
-    def decodeValue(self, value):
-        """Return string object.
-
-        Return value is a ``value`` argument with stripped right spaces.
-
-        """
-        return value.rstrip(" ")
-
-    def encodeValue(self, value):
-        """Return raw data string encoded from a ``value``."""
-        return str(value)[:self.length].ljust(self.length)
-
-
-class DbfNumericFieldDef(DbfFieldDef):
-    """Definition of the numeric field."""
-
-    typeCode = "N"
-    # XXX: now I'm not sure it was a good idea to make a class field
-    # `defaultValue` instead of a generic method as it was implemented
-    # previously -- it's ok with all types except number, cuz
-    # if self.decimalCount is 0, we should return 0 and 0.0 otherwise.
-    defaultValue = 0
-
-    def decodeValue(self, value):
-        """Return a number decoded from ``value``.
-
-        If decimals is zero, value will be decoded as an integer;
-        or as a float otherwise.
-
-        Return:
-            Return value is a int (long) or float instance.
-
-        """
-        value = value.strip(" \0")
-        if "." in value:
-            # a float (has decimal separator)
-            return float(value)
-        elif value:
-            # must be an integer
-            return int(value)
-        else:
-            return 0
-
-    def encodeValue(self, value):
-        """Return string containing encoded ``value``."""
-        _rv = ("%*.*f" % (self.length, self.decimalCount, value))
-        if len(_rv) > self.length:
-            _ppos = _rv.find(".")
-            if 0 <= _ppos <= self.length:
-                _rv = _rv[:self.length]
-            else:
-                raise ValueError("[%s] Numeric overflow: %s (field width: %i)"
-                    % (self.name, _rv, self.length))
-        return _rv
-
-class DbfFloatFieldDef(DbfNumericFieldDef):
-    """Definition of the float field - same as numeric."""
-
-    typeCode = "F"
-
-class DbfIntegerFieldDef(DbfFieldDef):
-    """Definition of the integer field."""
-
-    typeCode = "I"
-    length = 4
-    defaultValue = 0
-
-    def decodeValue(self, value):
-        """Return an integer number decoded from ``value``."""
-        return struct.unpack("<i", value)[0]
-
-    def encodeValue(self, value):
-        """Return string containing encoded ``value``."""
-        return struct.pack("<i", int(value))
-
-class DbfCurrencyFieldDef(DbfFieldDef):
-    """Definition of the currency field."""
-
-    typeCode = "Y"
-    length = 8
-    defaultValue = 0.0
-
-    def decodeValue(self, value):
-        """Return float number decoded from ``value``."""
-        return struct.unpack("<q", value)[0] / 10000.
-
-    def encodeValue(self, value):
-        """Return string containing encoded ``value``."""
-        return struct.pack("<q", round(value * 10000))
-
-class DbfLogicalFieldDef(DbfFieldDef):
-    """Definition of the logical field."""
-
-    typeCode = "L"
-    defaultValue = -1
-    length = 1
-
-    def decodeValue(self, value):
-        """Return True, False or -1 decoded from ``value``."""
-        # Note: value always is 1-char string
-        if value == "?":
-            return -1
-        if value in "NnFf ":
-            return False
-        if value in "YyTt":
-            return True
-        raise ValueError("[%s] Invalid logical value %r" % (self.name, value))
-
-    def encodeValue(self, value):
-        """Return a character from the "TF?" set.
-
-        Return:
-            Return value is "T" if ``value`` is True
-            "?" if value is -1 or False otherwise.
-
-        """
-        if value is True:
-            return "T"
-        if value == -1:
-            return "?"
-        return "F"
-
-
-class DbfMemoFieldDef(DbfFieldDef):
-    """Definition of the memo field.
-
-    Note: memos aren't currenly completely supported.
-
-    """
-
-    typeCode = "M"
-    defaultValue = " " * 10
-    length = 10
-
-    def decodeValue(self, value):
-        """Return int .dbt block number decoded from the string object."""
-        #return int(value)
-        raise NotImplementedError
-
-    def encodeValue(self, value):
-        """Return raw data string encoded from a ``value``.
-
-        Note: this is an internal method.
-
-        """
-        #return str(value)[:self.length].ljust(self.length)
-        raise NotImplementedError
-
-
-class DbfDateFieldDef(DbfFieldDef):
-    """Definition of the date field."""
-
-    typeCode = "D"
-    defaultValue = utils.classproperty(lambda cls: datetime.date.today())
-    # "yyyymmdd" gives us 8 characters
-    length = 8
-
-    def decodeValue(self, value):
-        """Return a ``datetime.date`` instance decoded from ``value``."""
-        if value.strip():
-            return utils.getDate(value)
-        else:
-            return None
-
-    def encodeValue(self, value):
-        """Return a string-encoded value.
-
-        ``value`` argument should be a value suitable for the
-        `utils.getDate` call.
-
-        Return:
-            Return value is a string in format "yyyymmdd".
-
-        """
-        if value:
-            return utils.getDate(value).strftime("%Y%m%d")
-        else:
-            return " " * self.length
-
-
-class DbfDateTimeFieldDef(DbfFieldDef):
-    """Definition of the timestamp field."""
-
-    # a difference between JDN (Julian Day Number)
-    # and GDN (Gregorian Day Number). note, that GDN < JDN
-    JDN_GDN_DIFF = 1721425
-    typeCode = "T"
-    defaultValue = utils.classproperty(lambda cls: datetime.datetime.now())
-    # two 32-bits integers representing JDN and amount of
-    # milliseconds respectively gives us 8 bytes.
-    # note, that values must be encoded in LE byteorder.
-    length = 8
-
-    def decodeValue(self, value):
-        """Return a `datetime.datetime` instance."""
-        assert len(value) == self.length
-        # LE byteorder
-        _jdn, _msecs = struct.unpack("<2I", value)
-        if _jdn >= 1:
-            _rv = datetime.datetime.fromordinal(_jdn - self.JDN_GDN_DIFF)
-            _rv += datetime.timedelta(0, _msecs / 1000.0)
-        else:
-            # empty date
-            _rv = None
-        return _rv
-
-    def encodeValue(self, value):
-        """Return a string-encoded ``value``."""
-        if value:
-            value = utils.getDateTime(value)
-            # LE byteorder
-            _rv = struct.pack("<2I", value.toordinal() + self.JDN_GDN_DIFF,
-                (value.hour * 3600 + value.minute * 60 + value.second) * 1000)
-        else:
-            _rv = "\0" * self.length
-        assert len(_rv) == self.length
-        return _rv
-
-
-_fieldsRegistry = {}
-
-def registerField(fieldCls):
-    """Register field definition class.
-
-    ``fieldCls`` should be subclass of the `DbfFieldDef`.
-
-    Use `lookupFor` to retrieve field definition class
-    by the type code.
-
-    """
-    assert fieldCls.typeCode is not None, "Type code isn't defined"
-    # XXX: use fieldCls.typeCode.upper()? in case of any decign
-    # don't forget to look to the same comment in ``lookupFor`` method
-    _fieldsRegistry[fieldCls.typeCode] = fieldCls
-
-
-def lookupFor(typeCode):
-    """Return field definition class for the given type code.
-
-    ``typeCode`` must be a single character. That type should be
-    previously registered.
-
-    Use `registerField` to register new field class.
-
-    Return:
-        Return value is a subclass of the `DbfFieldDef`.
-
-    """
-    # XXX: use typeCode.upper()? in case of any decign don't
-    # forget to look to the same comment in ``registerField``
-    return _fieldsRegistry[typeCode]
-
-## register generic types
-
-for (_name, _val) in globals().items():
-    if isinstance(_val, type) and issubclass(_val, DbfFieldDef) \
-    and (_name != "DbfFieldDef"):
-        __all__.append(_name)
-        registerField(_val)
-del _name, _val
-
-# vim: et sts=4 sw=4 :

tablib/packages/dbfpy/header.py

@@ -1,275 +0,0 @@
-"""DBF header definition.
-
-TODO:
-  - handle encoding of the character fields
-    (encoding information stored in the DBF header)
-
-"""
-"""History (most recent first):
-16-sep-2010 [als]   fromStream: fix century of the last update field
-11-feb-2007 [als]   added .ignoreErrors
-10-feb-2007 [als]   added __getitem__: return field definitions
-                    by field name or field number (zero-based)
-04-jul-2006 [als]   added export declaration
-15-dec-2005 [yc]    created
-"""
-
-__version__ = "$Revision: 1.6 $"[11:-2]
-__date__ = "$Date: 2010/09/16 05:06:39 $"[7:-2]
-
-__all__ = ["DbfHeader"]
-
-try:
-    import cStringIO
-except ImportError:
-    # when we're in python3, we cStringIO has been replaced by io.StringIO
-    import io as cStringIO
-import datetime
-import struct
-import time
-
-from . import fields
-from . import utils
-
-
-class DbfHeader(object):
-    """Dbf header definition.
-
-    For more information about dbf header format visit
-    `http://www.clicketyclick.dk/databases/xbase/format/dbf.html#DBF_STRUCT`
-
-    Examples:
-        Create an empty dbf header and add some field definitions:
-            dbfh = DbfHeader()
-            dbfh.addField(("name", "C", 10))
-            dbfh.addField(("date", "D"))
-            dbfh.addField(DbfNumericFieldDef("price", 5, 2))
-        Create a dbf header with field definitions:
-            dbfh = DbfHeader([
-                ("name", "C", 10),
-                ("date", "D"),
-                DbfNumericFieldDef("price", 5, 2),
-            ])
-
-    """
-
-    __slots__ = ("signature", "fields", "lastUpdate", "recordLength",
-        "recordCount", "headerLength", "changed", "_ignore_errors")
-
-    ## instance construction and initialization methods
-
-    def __init__(self, fields=None, headerLength=0, recordLength=0,
-        recordCount=0, signature=0x03, lastUpdate=None, ignoreErrors=False,
-    ):
-        """Initialize instance.
-
-        Arguments:
-            fields:
-                a list of field definitions;
-            recordLength:
-                size of the records;
-            headerLength:
-                size of the header;
-            recordCount:
-                number of records stored in DBF;
-            signature:
-                version number (aka signature). using 0x03 as a default meaning
-                "File without DBT". for more information about this field visit
-                ``http://www.clicketyclick.dk/databases/xbase/format/dbf.html#DBF_NOTE_1_TARGET``
-            lastUpdate:
-                date of the DBF's update. this could be a string ('yymmdd' or
-                'yyyymmdd'), timestamp (int or float), datetime/date value,
-                a sequence (assuming (yyyy, mm, dd, ...)) or an object having
-                callable ``ticks`` field.
-            ignoreErrors:
-                error processing mode for DBF fields (boolean)
-
-        """
-        self.signature = signature
-        if fields is None:
-            self.fields = []
-        else:
-            self.fields = list(fields)
-        self.lastUpdate = utils.getDate(lastUpdate)
-        self.recordLength = recordLength
-        self.headerLength = headerLength
-        self.recordCount = recordCount
-        self.ignoreErrors = ignoreErrors
-        # XXX: I'm not sure this is safe to
-        # initialize `self.changed` in this way
-        self.changed = bool(self.fields)
-
-    # @classmethod
-    def fromString(cls, string):
-        """Return header instance from the string object."""
-        return cls.fromStream(cStringIO.StringIO(str(string)))
-    fromString = classmethod(fromString)
-
-    # @classmethod
-    def fromStream(cls, stream):
-        """Return header object from the stream."""
-        stream.seek(0)
-        _data = stream.read(32)
-        (_cnt, _hdrLen, _recLen) = struct.unpack("<I2H", _data[4:12])
-        #reserved = _data[12:32]
-        _year = ord(_data[1])
-        if _year < 80:
-            # dBase II started at 1980.  It is quite unlikely
-            # that actual last update date is before that year.
-            _year += 2000
-        else:
-            _year += 1900
-        ## create header object
-        _obj = cls(None, _hdrLen, _recLen, _cnt, ord(_data[0]),
-            (_year, ord(_data[2]), ord(_data[3])))
-        ## append field definitions
-        # position 0 is for the deletion flag
-        _pos = 1
-        _data = stream.read(1)
-
-        # The field definitions are ended either by \x0D OR a newline
-        # character, so we need to handle both when reading from a stream.
-        # When writing, dbfpy appears to write newlines instead of \x0D.
-        while _data[0] not in ["\x0D", "\n"]:
-            _data += stream.read(31)
-            _fld = fields.lookupFor(_data[11]).fromString(_data, _pos)
-            _obj._addField(_fld)
-            _pos = _fld.end
-            _data = stream.read(1)
-        return _obj
-    fromStream = classmethod(fromStream)
-
-    ## properties
-
-    year = property(lambda self: self.lastUpdate.year)
-    month = property(lambda self: self.lastUpdate.month)
-    day = property(lambda self: self.lastUpdate.day)
-
-    def ignoreErrors(self, value):
-        """Update `ignoreErrors` flag on self and all fields"""
-        self._ignore_errors = value = bool(value)
-        for _field in self.fields:
-            _field.ignoreErrors = value
-    ignoreErrors = property(
-        lambda self: self._ignore_errors,
-        ignoreErrors,
-        doc="""Error processing mode for DBF field value conversion
-
-        if set, failing field value conversion will return
-        ``INVALID_VALUE`` instead of raising conversion error.
-
-        """)
-
-    ## object representation
-
-    def __repr__(self):
-        _rv = """\
-Version (signature): 0x%02x
-        Last update: %s
-      Header length: %d
-      Record length: %d
-       Record count: %d
- FieldName Type Len Dec
-""" % (self.signature, self.lastUpdate, self.headerLength,
-    self.recordLength, self.recordCount)
-        _rv += "\n".join(
-            ["%10s %4s %3s %3s" % _fld.fieldInfo() for _fld in self.fields]
-        )
-        return _rv
-
-    ## internal methods
-
-    def _addField(self, *defs):
-        """Internal variant of the `addField` method.
-
-        This method doesn't set `self.changed` field to True.
-
-        Return value is a length of the appended records.
-        Note: this method doesn't modify ``recordLength`` and
-        ``headerLength`` fields. Use `addField` instead of this
-        method if you don't exactly know what you're doing.
-
-        """
-        # insure we have dbf.DbfFieldDef instances first (instantiation
-        # from the tuple could raise an error, in such a case I don't
-        # wanna add any of the definitions -- all will be ignored)
-        _defs = []
-        _recordLength = 0
-        for _def in defs:
-            if isinstance(_def, fields.DbfFieldDef):
-                _obj = _def
-            else:
-                (_name, _type, _len, _dec) = (tuple(_def) + (None,) * 4)[:4]
-                _cls = fields.lookupFor(_type)
-                _obj = _cls(_name, _len, _dec,
-                    ignoreErrors=self._ignore_errors)
-            _recordLength += _obj.length
-            _defs.append(_obj)
-        # and now extend field definitions and
-        # update record length
-        self.fields += _defs
-        return _recordLength
-
-    ## interface methods
-
-    def addField(self, *defs):
-        """Add field definition to the header.
-
-        Examples:
-            dbfh.addField(
-                ("name", "C", 20),
-                dbf.DbfCharacterFieldDef("surname", 20),
-                dbf.DbfDateFieldDef("birthdate"),
-                ("member", "L"),
-            )
-            dbfh.addField(("price", "N", 5, 2))
-            dbfh.addField(dbf.DbfNumericFieldDef("origprice", 5, 2))
-
-        """
-        _oldLen = self.recordLength
-        self.recordLength += self._addField(*defs)
-        if not _oldLen:
-            self.recordLength += 1
-            # XXX: may be just use:
-            # self.recordeLength += self._addField(*defs) + bool(not _oldLen)
-        # recalculate headerLength
-        self.headerLength = 32 + (32 * len(self.fields)) + 1
-        self.changed = True
-
-    def write(self, stream):
-        """Encode and write header to the stream."""
-        stream.seek(0)
-        stream.write(self.toString())
-        stream.write("".join([_fld.toString() for _fld in self.fields]))
-        stream.write(chr(0x0D))   # cr at end of all hdr data
-        self.changed = False
-
-    def toString(self):
-        """Returned 32 chars length string with encoded header."""
-        return struct.pack("<4BI2H",
-            self.signature,
-            self.year - 1900,
-            self.month,
-            self.day,
-            self.recordCount,
-            self.headerLength,
-            self.recordLength) + "\0" * 20
-
-    def setCurrentDate(self):
-        """Update ``self.lastUpdate`` field with current date value."""
-        self.lastUpdate = datetime.date.today()
-
-    def __getitem__(self, item):
-        """Return a field definition by numeric index or name string"""
-        if isinstance(item, basestring):
-            _name = item.upper()
-            for _field in self.fields:
-                if _field.name == _name:
-                    return _field
-            else:
-                raise KeyError(item)
-        else:
-            # item must be field index
-            return self.fields[item]
-
-# vim: et sts=4 sw=4 :

tablib/packages/dbfpy/record.py

@@ -1,262 +0,0 @@
-"""DBF record definition.
-
-"""
-"""History (most recent first):
-11-feb-2007 [als]   __repr__: added special case for invalid field values
-10-feb-2007 [als]   added .rawFromStream()
-30-oct-2006 [als]   fix record length in .fromStream()
-04-jul-2006 [als]   added export declaration
-20-dec-2005 [yc]    DbfRecord.write() -> DbfRecord._write();
-                    added delete() method.
-16-dec-2005 [yc]    record definition moved from `dbf`.
-"""
-
-__version__ = "$Revision: 1.7 $"[11:-2]
-__date__ = "$Date: 2007/02/11 09:05:49 $"[7:-2]
-
-__all__ = ["DbfRecord"]
-
-from itertools import izip
-
-import utils
-
-class DbfRecord(object):
-    """DBF record.
-
-    Instances of this class shouldn't be created manualy,
-    use `dbf.Dbf.newRecord` instead.
-
-    Class implements mapping/sequence interface, so
-    fields could be accessed via their names or indexes
-    (names is a preffered way to access fields).
-
-    Hint:
-        Use `store` method to save modified record.
-
-    Examples:
-        Add new record to the database:
-            db = Dbf(filename)
-            rec = db.newRecord()
-            rec["FIELD1"] = value1
-            rec["FIELD2"] = value2
-            rec.store()
-        Or the same, but modify existed
-        (second in this case) record:
-            db = Dbf(filename)
-            rec = db[2]
-            rec["FIELD1"] = value1
-            rec["FIELD2"] = value2
-            rec.store()
-
-    """
-
-    __slots__ = "dbf", "index", "deleted", "fieldData"
-
-    ## creation and initialization
-
-    def __init__(self, dbf, index=None, deleted=False, data=None):
-        """Instance initialiation.
-
-        Arguments:
-            dbf:
-                A `Dbf.Dbf` instance this record belonogs to.
-            index:
-                An integer record index or None. If this value is
-                None, record will be appended to the DBF.
-            deleted:
-                Boolean flag indicating whether this record
-                is a deleted record.
-            data:
-                A sequence or None. This is a data of the fields.
-                If this argument is None, default values will be used.
-
-        """
-        self.dbf = dbf
-        # XXX: I'm not sure ``index`` is necessary
-        self.index = index
-        self.deleted = deleted
-        if data is None:
-            self.fieldData = [_fd.defaultValue for _fd in dbf.header.fields]
-        else:
-            self.fieldData = list(data)
-
-    # XXX: validate self.index before calculating position?
-    position = property(lambda self: self.dbf.header.headerLength + \
-        self.index * self.dbf.header.recordLength)
-
-    def rawFromStream(cls, dbf, index):
-        """Return raw record contents read from the stream.
-
-        Arguments:
-            dbf:
-                A `Dbf.Dbf` instance containing the record.
-            index:
-                Index of the record in the records' container.
-                This argument can't be None in this call.
-
-        Return value is a string containing record data in DBF format.
-
-        """
-        # XXX: may be write smth assuming, that current stream
-        # position is the required one? it could save some
-        # time required to calculate where to seek in the file
-        dbf.stream.seek(dbf.header.headerLength +
-            index * dbf.header.recordLength)
-        return dbf.stream.read(dbf.header.recordLength)
-    rawFromStream = classmethod(rawFromStream)
-
-    def fromStream(cls, dbf, index):
-        """Return a record read from the stream.
-
-        Arguments:
-            dbf:
-                A `Dbf.Dbf` instance new record should belong to.
-            index:
-                Index of the record in the records' container.
-                This argument can't be None in this call.
-
-        Return value is an instance of the current class.
-
-        """
-        return cls.fromString(dbf, cls.rawFromStream(dbf, index), index)
-    fromStream = classmethod(fromStream)
-
-    def fromString(cls, dbf, string, index=None):
-        """Return record read from the string object.
-
-        Arguments:
-            dbf:
-                A `Dbf.Dbf` instance new record should belong to.
-            string:
-                A string new record should be created from.
-            index:
-                Index of the record in the container. If this
-                argument is None, record will be appended.
-
-        Return value is an instance of the current class.
-
-        """
-        return cls(dbf, index, string[0]=="*",
-            [_fd.decodeFromRecord(string) for _fd in dbf.header.fields])
-    fromString = classmethod(fromString)
-
-    ## object representation
-
-    def __repr__(self):
-        _template = "%%%ds: %%s (%%s)" % max([len(_fld)
-            for _fld in self.dbf.fieldNames])
-        _rv = []
-        for _fld in self.dbf.fieldNames:
-            _val = self[_fld]
-            if _val is utils.INVALID_VALUE:
-                _rv.append(_template %
-                    (_fld, "None", "value cannot be decoded"))
-            else:
-                _rv.append(_template % (_fld, _val, type(_val)))
-        return "\n".join(_rv)
-
-    ## protected methods
-
-    def _write(self):
-        """Write data to the dbf stream.
-
-        Note:
-            This isn't a public method, it's better to
-            use 'store' instead publically.
-            Be design ``_write`` method should be called
-            only from the `Dbf` instance.
-
-
-        """
-        self._validateIndex(False)
-        self.dbf.stream.seek(self.position)
-        self.dbf.stream.write(self.toString())
-        # FIXME: may be move this write somewhere else?
-        # why we should check this condition for each record?
-        if self.index == len(self.dbf):
-            # this is the last record,
-            # we should write SUB (ASCII 26)
-            self.dbf.stream.write("\x1A")
-
-    ## utility methods
-
-    def _validateIndex(self, allowUndefined=True, checkRange=False):
-        """Valid ``self.index`` value.
-
-        If ``allowUndefined`` argument is True functions does nothing
-        in case of ``self.index`` pointing to None object.
-
-        """
-        if self.index is None:
-            if not allowUndefined:
-                raise ValueError("Index is undefined")
-        elif self.index < 0:
-            raise ValueError("Index can't be negative (%s)" % self.index)
-        elif checkRange and self.index <= self.dbf.header.recordCount:
-            raise ValueError("There are only %d records in the DBF" %
-                self.dbf.header.recordCount)
-
-    ## interface methods
-
-    def store(self):
-        """Store current record in the DBF.
-
-        If ``self.index`` is None, this record will be appended to the
-        records of the DBF this records belongs to; or replaced otherwise.
-
-        """
-        self._validateIndex()
-        if self.index is None:
-            self.index = len(self.dbf)
-            self.dbf.append(self)
-        else:
-            self.dbf[self.index] = self
-
-    def delete(self):
-        """Mark method as deleted."""
-        self.deleted = True
-
-    def toString(self):
-        """Return string packed record values."""
-        return "".join([" *"[self.deleted]] + [
-            _def.encodeValue(_dat)
-            for (_def, _dat) in izip(self.dbf.header.fields, self.fieldData)
-        ])
-
-    def asList(self):
-        """Return a flat list of fields.
-
-        Note:
-            Change of the list's values won't change
-            real values stored in this object.
-
-        """
-        return self.fieldData[:]
-
-    def asDict(self):
-        """Return a dictionary of fields.
-
-        Note:
-            Change of the dicts's values won't change
-            real values stored in this object.
-
-        """
-        return dict([_i for _i in izip(self.dbf.fieldNames, self.fieldData)])
-
-    def __getitem__(self, key):
-        """Return value by field name or field index."""
-        if isinstance(key, (long, int)):
-            # integer index of the field
-            return self.fieldData[key]
-        # assuming string field name
-        return self.fieldData[self.dbf.indexOfFieldName(key)]
-
-    def __setitem__(self, key, value):
-        """Set field value by integer index of the field or string name."""
-        if isinstance(key, (int, long)):
-            # integer index of the field
-            return self.fieldData[key]
-        # assuming string field name
-        self.fieldData[self.dbf.indexOfFieldName(key)] = value
-
-# vim: et sts=4 sw=4 :

tablib/packages/dbfpy/utils.py

@@ -1,170 +0,0 @@
-"""String utilities.
-
-TODO:
-  - allow strings in getDateTime routine;
-"""
-"""History (most recent first):
-11-feb-2007 [als]   added INVALID_VALUE
-10-feb-2007 [als]   allow date strings padded with spaces instead of zeroes
-20-dec-2005 [yc]    handle long objects in getDate/getDateTime
-16-dec-2005 [yc]    created from ``strutil`` module.
-"""
-
-__version__ = "$Revision: 1.4 $"[11:-2]
-__date__ = "$Date: 2007/02/11 08:57:17 $"[7:-2]
-
-import datetime
-import time
-
-
-def unzfill(str):
-    """Return a string without ASCII NULs.
-
-    This function searchers for the first NUL (ASCII 0) occurance
-    and truncates string till that position.
-
-    """
-    try:
-        return str[:str.index('\0')]
-    except ValueError:
-        return str
-
-
-def getDate(date=None):
-    """Return `datetime.date` instance.
-
-    Type of the ``date`` argument could be one of the following:
-        None:
-            use current date value;
-        datetime.date:
-            this value will be returned;
-        datetime.datetime:
-            the result of the date.date() will be returned;
-        string:
-            assuming "%Y%m%d" or "%y%m%dd" format;
-        number:
-            assuming it's a timestamp (returned for example
-            by the time.time() call;
-        sequence:
-            assuming (year, month, day, ...) sequence;
-
-    Additionaly, if ``date`` has callable ``ticks`` attribute,
-    it will be used and result of the called would be treated
-    as a timestamp value.
-
-    """
-    if date is None:
-        # use current value
-        return datetime.date.today()
-    if isinstance(date, datetime.date):
-        return date
-    if isinstance(date, datetime.datetime):
-        return date.date()
-    if isinstance(date, (int, long, float)):
-        # date is a timestamp
-        return datetime.date.fromtimestamp(date)
-    if isinstance(date, basestring):
-        date = date.replace(" ", "0")
-        if len(date) == 6:
-            # yymmdd
-            return datetime.date(*time.strptime(date, "%y%m%d")[:3])
-        # yyyymmdd
-        return datetime.date(*time.strptime(date, "%Y%m%d")[:3])
-    if hasattr(date, "__getitem__"):
-        # a sequence (assuming date/time tuple)
-        return datetime.date(*date[:3])
-    return datetime.date.fromtimestamp(date.ticks())
-
-
-def getDateTime(value=None):
-    """Return `datetime.datetime` instance.
-
-    Type of the ``value`` argument could be one of the following:
-        None:
-            use current date value;
-        datetime.date:
-            result will be converted to the `datetime.datetime` instance
-            using midnight;
-        datetime.datetime:
-            ``value`` will be returned as is;
-        string:
-            *** CURRENTLY NOT SUPPORTED ***;
-        number:
-            assuming it's a timestamp (returned for example
-            by the time.time() call;
-        sequence:
-            assuming (year, month, day, ...) sequence;
-
-    Additionaly, if ``value`` has callable ``ticks`` attribute,
-    it will be used and result of the called would be treated
-    as a timestamp value.
-
-    """
-    if value is None:
-        # use current value
-        return datetime.datetime.today()
-    if isinstance(value, datetime.datetime):
-        return value
-    if isinstance(value, datetime.date):
-        return datetime.datetime.fromordinal(value.toordinal())
-    if isinstance(value, (int, long, float)):
-        # value is a timestamp
-        return datetime.datetime.fromtimestamp(value)
-    if isinstance(value, basestring):
-        raise NotImplementedError("Strings aren't currently implemented")
-    if hasattr(value, "__getitem__"):
-        # a sequence (assuming date/time tuple)
-        return datetime.datetime(*tuple(value)[:6])
-    return datetime.datetime.fromtimestamp(value.ticks())
-
-
-class classproperty(property):
-    """Works in the same way as a ``property``, but for the classes."""
-
-    def __get__(self, obj, cls):
-        return self.fget(cls)
-
-
-class _InvalidValue(object):
-
-    """Value returned from DBF records when field validation fails
-
-    The value is not equal to anything except for itself
-    and equal to all empty values: None, 0, empty string etc.
-    In other words, invalid value is equal to None and not equal
-    to None at the same time.
-
-    This value yields zero upon explicit conversion to a number type,
-    empty string for string types, and False for boolean.
-
-    """
-
-    def __eq__(self, other):
-        return not other
-
-    def __ne__(self, other):
-        return not (other is self)
-
-    def __nonzero__(self):
-        return False
-
-    def __int__(self):
-        return 0
-    __long__ = __int__
-
-    def __float__(self):
-        return 0.0
-
-    def __str__(self):
-        return ""
-
-    def __unicode__(self):
-        return u""
-
-    def __repr__(self):
-        return "<INVALID>"
-
-# invalid value is a constant singleton
-INVALID_VALUE = _InvalidValue()
-
-# vim: set et sts=4 sw=4 :

tablib/packages/markup.py

@@ -1,482 +0,0 @@
-# This code is in the public domain, it comes
-# with absolutely no warranty and you can do
-# absolutely whatever you want with it.
-
-__date__ = '17 May 2007'
-__version__ = '1.7'
-__doc__= """
-This is markup.py - a Python module that attempts to
-make it easier to generate HTML/XML from a Python program
-in an intuitive, lightweight, customizable and pythonic way.
-
-The code is in the public domain.
-
-Version: %s as of %s.
-
-Documentation and further info is at http://markup.sourceforge.net/
-
-Please send bug reports, feature requests, enhancement
-ideas or questions to nogradi at gmail dot com.
-
-Installation: drop markup.py somewhere into your Python path.
-""" % ( __version__, __date__ )
-
-import string
-
-class element:
-    """This class handles the addition of a new element."""
-
-    def __init__( self, tag, case='lower', parent=None ):
-        self.parent = parent
-
-        if case == 'lower':
-            self.tag = tag.lower( )
-        else:
-            self.tag = tag.upper( )
-
-    def __call__( self, *args, **kwargs ):
-        if len( args ) > 1:
-            raise ArgumentError( self.tag )
-
-        # if class_ was defined in parent it should be added to every element
-        if self.parent is not None and self.parent.class_ is not None:
-            if 'class_' not in kwargs:
-                kwargs['class_'] = self.parent.class_
-
-        if self.parent is None and len( args ) == 1:
-            x = [ self.render( self.tag, False, myarg, mydict ) for myarg, mydict in _argsdicts( args, kwargs ) ]
-            return '\n'.join( x )
-        elif self.parent is None and len( args ) == 0:
-            x = [ self.render( self.tag, True, myarg, mydict ) for myarg, mydict in _argsdicts( args, kwargs ) ]
-            return '\n'.join( x )
-
-        if self.tag in self.parent.twotags:
-            for myarg, mydict in _argsdicts( args, kwargs ):
-                self.render( self.tag, False, myarg, mydict )
-        elif self.tag in self.parent.onetags:
-            if len( args ) == 0:
-                for myarg, mydict in _argsdicts( args, kwargs ):
-                    self.render( self.tag, True, myarg, mydict )    # here myarg is always None, because len( args ) = 0
-            else:
-                raise ClosingError( self.tag )
-        elif self.parent.mode == 'strict_html' and self.tag in self.parent.deptags:
-            raise DeprecationError( self.tag )
-        else:
-            raise InvalidElementError( self.tag, self.parent.mode )
-
-    def render( self, tag, single, between, kwargs ):
-        """Append the actual tags to content."""
-
-        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.
-                if key in ['http_equiv', 'accept_charset']:
-                    key.replace('_','-')
-                out = u"%s %s=\"%s\"" % ( out, key, escape( value ) )
-            else:
-                out = u"%s %s" % ( out, key )
-        if between is not None:
-            out = u"%s>%s</%s>" % ( out, between, tag )
-        else:
-            if single:
-                out = u"%s />" % out
-            else:
-                out = u"%s>" % out
-        if self.parent is not None:
-            self.parent.content.append( out )
-        else:
-            return out
-
-    def close( self ):
-        """Append a closing tag unless element has only opening tag."""
-
-        if self.tag in self.parent.twotags:
-            self.parent.content.append( "</%s>" % self.tag )
-        elif self.tag in self.parent.onetags:
-            raise ClosingError( self.tag )
-        elif self.parent.mode == 'strict_html' and self.tag in self.parent.deptags:
-            raise DeprecationError( self.tag )
-
-    def open( self, **kwargs ):
-        """Append an opening tag."""
-
-        if self.tag in self.parent.twotags or self.tag in self.parent.onetags:
-            self.render( self.tag, False, None, kwargs )
-        elif self.mode == 'strict_html' and self.tag in self.parent.deptags:
-            raise DeprecationError( self.tag )
-
-class page:
-    """This is our main class representing a document. Elements are added
-    as attributes of an instance of this class."""
-
-    def __init__( self, mode='strict_html', case='lower', onetags=None, twotags=None, separator='\n', class_=None ):
-        """Stuff that effects the whole document.
-
-        mode -- 'strict_html'   for HTML 4.01 (default)
-                'html'          alias for 'strict_html'
-                'loose_html'    to allow some deprecated elements
-                'xml'           to allow arbitrary elements
-
-        case -- 'lower'         element names will be printed in lower case (default)
-                'upper'         they will be printed in upper case
-
-        onetags --              list or tuple of valid elements with opening tags only
-        twotags --              list or tuple of valid elements with both opening and closing tags
-                                these two keyword arguments may be used to select
-                                the set of valid elements in 'xml' mode
-                                invalid elements will raise appropriate exceptions
-
-        separator --            string to place between added elements, defaults to newline
-
-        class_ --               a class that will be added to every element if defined"""
-
-        valid_onetags = [ "AREA", "BASE", "BR", "COL", "FRAME", "HR", "IMG", "INPUT", "LINK", "META", "PARAM" ]
-        valid_twotags = [ "A", "ABBR", "ACRONYM", "ADDRESS", "B", "BDO", "BIG", "BLOCKQUOTE", "BODY", "BUTTON",
-                "CAPTION", "CITE", "CODE", "COLGROUP", "DD", "DEL", "DFN", "DIV", "DL", "DT", "EM", "FIELDSET",
-                "FORM", "FRAMESET", "H1", "H2", "H3", "H4", "H5", "H6", "HEAD", "HTML", "I", "IFRAME", "INS",
-                "KBD", "LABEL", "LEGEND", "LI", "MAP", "NOFRAMES", "NOSCRIPT", "OBJECT", "OL", "OPTGROUP",
-                "OPTION", "P", "PRE", "Q", "SAMP", "SCRIPT", "SELECT", "SMALL", "SPAN", "STRONG", "STYLE",
-                "SUB", "SUP", "TABLE", "TBODY", "TD", "TEXTAREA", "TFOOT", "TH", "THEAD", "TITLE", "TR",
-                "TT", "UL", "VAR" ]
-        deprecated_onetags = [ "BASEFONT", "ISINDEX" ]
-        deprecated_twotags = [ "APPLET", "CENTER", "DIR", "FONT", "MENU", "S", "STRIKE", "U" ]
-
-        self.header = [ ]
-        self.content = [ ]
-        self.footer = [ ]
-        self.case = case
-        self.separator = separator
-
-        # init( ) sets it to True so we know that </body></html> has to be printed at the end
-        self._full = False
-        self.class_= class_
-
-        if mode == 'strict_html' or mode == 'html':
-            self.onetags = valid_onetags
-            self.onetags += map( string.lower, self.onetags )
-            self.twotags = valid_twotags
-            self.twotags += map( string.lower, self.twotags )
-            self.deptags = deprecated_onetags + deprecated_twotags
-            self.deptags += map( string.lower, self.deptags )
-            self.mode = 'strict_html'
-        elif mode == 'loose_html':
-            self.onetags = valid_onetags + deprecated_onetags
-            self.onetags += map( string.lower, self.onetags )
-            self.twotags = valid_twotags + deprecated_twotags
-            self.twotags += map( string.lower, self.twotags )
-            self.mode = mode
-        elif mode == 'xml':
-            if onetags and twotags:
-                self.onetags = onetags
-                self.twotags = twotags
-            elif ( onetags and not twotags ) or ( twotags and not onetags ):
-                raise CustomizationError( )
-            else:
-                self.onetags = russell( )
-                self.twotags = russell( )
-            self.mode = mode
-        else:
-            raise ModeError( mode )
-
-    def __getattr__( self, attr ):
-        if attr.startswith("__") and attr.endswith("__"):
-            raise AttributeError(attr)
-        return element( attr, case=self.case, parent=self )
-
-    def __str__( self ):
-
-        if self._full and ( self.mode == 'strict_html' or self.mode == 'loose_html' ):
-            end = [ '</body>', '</html>' ]
-        else:
-            end = [ ]
-
-        return self.separator.join( self.header + self.content + self.footer + end )
-
-    def __call__( self, escape=False ):
-        """Return the document as a string.
-
-        escape --   False   print normally
-                    True    replace < and > by &lt; and &gt;
-                            the default escape sequences in most browsers"""
-
-        if escape:
-            return _escape( self.__str__( ) )
-        else:
-            return self.__str__( )
-
-    def add( self, text ):
-        """This is an alias to addcontent."""
-        self.addcontent( text )
-
-    def addfooter( self, text ):
-        """Add some text to the bottom of the document"""
-        self.footer.append( text )
-
-    def addheader( self, text ):
-        """Add some text to the top of the document"""
-        self.header.append( text )
-
-    def addcontent( self, text ):
-        """Add some text to the main part of the document"""
-        self.content.append( text )
-
-
-    def init( self, lang='en', css=None, metainfo=None, title=None, header=None,
-              footer=None, charset=None, encoding=None, doctype=None, bodyattrs=None, script=None ):
-        """This method is used for complete documents with appropriate
-        doctype, encoding, title, etc information. For an HTML/XML snippet
-        omit this method.
-
-        lang --     language, usually a two character string, will appear
-                    as <html lang='en'> in html mode (ignored in xml mode)
-
-        css --      Cascading Style Sheet filename as a string or a list of
-                    strings for multiple css files (ignored in xml mode)
-
-        metainfo -- a dictionary in the form { 'name':'content' } to be inserted
-                    into meta element(s) as <meta name='name' content='content'>
-                    (ignored in xml mode)
-
-        bodyattrs --a dictionary in the form { 'key':'value', ... } which will be added
-                    as attributes of the <body> element as <body key='value' ... >
-                    (ignored in xml mode)
-
-        script --   dictionary containing src:type pairs, <script type='text/type' src=src></script>
-
-        title --    the title of the document as a string to be inserted into
-                    a title element as <title>my title</title> (ignored in xml mode)
-
-        header --   some text to be inserted right after the <body> element
-                    (ignored in xml mode)
-
-        footer --   some text to be inserted right before the </body> element
-                    (ignored in xml mode)
-
-        charset --  a string defining the character set, will be inserted into a
-                    <meta http-equiv='Content-Type' content='text/html; charset=myset'>
-                    element (ignored in xml mode)
-
-        encoding -- a string defining the encoding, will be put into to first line of
-                    the document as <?xml version='1.0' encoding='myencoding' ?> in
-                    xml mode (ignored in html mode)
-
-        doctype --  the document type string, defaults to
-                    <!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Transitional//EN'>
-                    in html mode (ignored in xml mode)"""
-
-        self._full = True
-
-        if self.mode == 'strict_html' or self.mode == 'loose_html':
-            if doctype is None:
-                doctype = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Transitional//EN'>"
-            self.header.append( doctype )
-            self.html( lang=lang )
-            self.head( )
-            if charset is not None:
-                self.meta( http_equiv='Content-Type', content="text/html; charset=%s" % charset )
-            if metainfo is not None:
-                self.metainfo( metainfo )
-            if css is not None:
-                self.css( css )
-            if title is not None:
-                self.title( title )
-            if script is not None:
-                self.scripts( script )
-            self.head.close()
-            if bodyattrs is not None:
-                self.body( **bodyattrs )
-            else:
-                self.body( )
-            if header is not None:
-                self.content.append( header )
-            if footer is not None:
-                self.footer.append( footer )
-
-        elif self.mode == 'xml':
-            if doctype is None:
-                if encoding is not None:
-                    doctype = "<?xml version='1.0' encoding='%s' ?>" % encoding
-                else:
-                    doctype = "<?xml version='1.0' ?>"
-            self.header.append( doctype )
-
-    def css( self, filelist ):
-        """This convenience function is only useful for html.
-        It adds css stylesheet(s) to the document via the <link> element."""
-
-        if isinstance( filelist, basestring ):
-            self.link( href=filelist, rel='stylesheet', type='text/css', media='all' )
-        else:
-            for file in filelist:
-                self.link( href=file, rel='stylesheet', type='text/css', media='all' )
-
-    def metainfo( self, mydict ):
-        """This convenience function is only useful for html.
-        It adds meta information via the <meta> element, the argument is
-        a dictionary of the form { 'name':'content' }."""
-
-        if isinstance( mydict, dict ):
-            for name, content in mydict.iteritems( ):
-                self.meta( name=name, content=content )
-        else:
-            raise TypeError ("Metainfo should be called with a dictionary argument of name:content pairs.")
-
-    def scripts( self, mydict ):
-        """Only useful in html, mydict is dictionary of src:type pairs will
-        be rendered as <script type='text/type' src=src></script>"""
-
-        if isinstance( mydict, dict ):
-            for src, type in mydict.iteritems( ):
-                self.script( '', src=src, type='text/%s' % type )
-        else:
-            raise TypeError ("Script should be given a dictionary of src:type pairs.")
-
-
-class _oneliner:
-    """An instance of oneliner returns a string corresponding to one element.
-    This class can be used to write 'oneliners' that return a string
-    immediately so there is no need to instantiate the page class."""
-
-    def __init__( self, case='lower' ):
-        self.case = case
-
-    def __getattr__( self, attr ):
-        if attr.startswith("__") and attr.endswith("__"):
-            raise AttributeError(attr)
-        return element( attr, case=self.case, parent=None )
-
-oneliner = _oneliner( case='lower' )
-upper_oneliner = _oneliner( case='upper' )
-
-def _argsdicts( args, mydict ):
-    """A utility generator that pads argument list and dictionary values, will only be called with len( args ) = 0, 1."""
-
-    if len( args ) == 0:
-        args = None,
-    elif len( args ) == 1:
-        args = _totuple( args[0] )
-    else:
-        raise Exception("We should have never gotten here.")
-
-    mykeys = mydict.keys( )
-    myvalues = map( _totuple, mydict.values( ) )
-
-    maxlength = max( map( len, [ args ] + myvalues ) )
-
-    for i in xrange( maxlength ):
-        thisdict = { }
-        for key, value in zip( mykeys, myvalues ):
-            try:
-                thisdict[ key ] = value[i]
-            except IndexError:
-                thisdict[ key ] = value[-1]
-        try:
-            thisarg = args[i]
-        except IndexError:
-            thisarg = args[-1]
-
-        yield thisarg, thisdict
-
-def _totuple( x ):
-    """Utility stuff to convert string, int, float, None or anything to a usable tuple."""
-
-    if isinstance( x, basestring ):
-        out = x,
-    elif isinstance( x, ( int, float ) ):
-        out = str( x ),
-    elif x is None:
-        out = None,
-    else:
-        out = tuple( x )
-
-    return out
-
-def escape( text, newline=False ):
-    """Escape special html characters."""
-
-    if isinstance( text, basestring ):
-        if '&' in text:
-            text = text.replace( '&', '&amp;' )
-        if '>' in text:
-            text = text.replace( '>', '&gt;' )
-        if '<' in text:
-            text = text.replace( '<', '&lt;' )
-        if '\"' in text:
-            text = text.replace( '\"', '&quot;' )
-        if '\'' in text:
-            text = text.replace( '\'', '&quot;' )
-        if newline:
-            if '\n' in text:
-                text = text.replace( '\n', '<br>' )
-
-    return text
-
-_escape = escape
-
-def unescape( text ):
-    """Inverse of escape."""
-
-    if isinstance( text, basestring ):
-        if '&amp;' in text:
-            text = text.replace( '&amp;', '&' )
-        if '&gt;' in text:
-            text = text.replace( '&gt;', '>' )
-        if '&lt;' in text:
-            text = text.replace( '&lt;', '<' )
-        if '&quot;' in text:
-            text = text.replace( '&quot;', '\"' )
-
-    return text
-
-class dummy:
-    """A dummy class for attaching attributes."""
-    pass
-
-doctype = dummy( )
-doctype.frameset = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Frameset//EN' 'http://www.w3.org/TR/html4/frameset.dtd'>"
-doctype.strict = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01//EN' 'http://www.w3.org/TR/html4/strict.dtd'>"
-doctype.loose = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Transitional//EN' 'http://www.w3.org/TR/html4/loose.dtd'>"
-
-class russell:
-    """A dummy class that contains anything."""
-
-    def __contains__( self, item ):
-        return True
-
-
-class MarkupError( Exception ):
-    """All our exceptions subclass this."""
-    def __str__( self ):
-        return self.message
-
-class ClosingError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' does not accept non-keyword arguments (has no closing tag)." % tag
-
-class OpeningError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' can not be opened." % tag
-
-class ArgumentError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' was called with more than one non-keyword argument." % tag
-
-class InvalidElementError( MarkupError ):
-    def __init__( self, tag, mode ):
-        self.message = "The element '%s' is not valid for your mode '%s'." % ( tag, mode )
-
-class DeprecationError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' is deprecated, instantiate markup.page with mode='loose_html' to allow it." % tag
-
-class ModeError( MarkupError ):
-    def __init__( self, mode ):
-        self.message = "Mode '%s' is invalid, possible values: strict_html, loose_html, xml." % mode
-
-class CustomizationError( MarkupError ):
-    def __init__( self ):
-        self.message = "If you customize the allowed elements, you must define both types 'onetags' and 'twotags'."
-
-if __name__ == '__main__':
-    print (__doc__)

tablib/packages/markup3.py

@@ -1,484 +0,0 @@
-# This code is in the public domain, it comes
-# with absolutely no warranty and you can do
-# absolutely whatever you want with it.
-
-__date__ = '17 May 2007'
-__version__ = '1.7'
-__doc__= """
-This is markup.py - a Python module that attempts to
-make it easier to generate HTML/XML from a Python program
-in an intuitive, lightweight, customizable and pythonic way.
-
-The code is in the public domain.
-
-Version: %s as of %s.
-
-Documentation and further info is at http://markup.sourceforge.net/
-
-Please send bug reports, feature requests, enhancement
-ideas or questions to nogradi at gmail dot com.
-
-Installation: drop markup.py somewhere into your Python path.
-""" % ( __version__, __date__ )
-
-import string
-
-class element:
-    """This class handles the addition of a new element."""
-
-    def __init__( self, tag, case='lower', parent=None ):
-        self.parent = parent
-
-        if case == 'lower':
-            self.tag = tag.lower( )
-        else:
-            self.tag = tag.upper( )
-
-    def __call__( self, *args, **kwargs ):
-        if len( args ) > 1:
-            raise ArgumentError( self.tag )
-
-        # if class_ was defined in parent it should be added to every element
-        if self.parent is not None and self.parent.class_ is not None:
-            if 'class_' not in kwargs:
-                kwargs['class_'] = self.parent.class_
-
-        if self.parent is None and len( args ) == 1:
-            x = [ self.render( self.tag, False, myarg, mydict ) for myarg, mydict in _argsdicts( args, kwargs ) ]
-            return '\n'.join( x )
-        elif self.parent is None and len( args ) == 0:
-            x = [ self.render( self.tag, True, myarg, mydict ) for myarg, mydict in _argsdicts( args, kwargs ) ]
-            return '\n'.join( x )
-
-        if self.tag in self.parent.twotags:
-            for myarg, mydict in _argsdicts( args, kwargs ):
-                self.render( self.tag, False, myarg, mydict )
-        elif self.tag in self.parent.onetags:
-            if len( args ) == 0:
-                for myarg, mydict in _argsdicts( args, kwargs ):
-                    self.render( self.tag, True, myarg, mydict )    # here myarg is always None, because len( args ) = 0
-            else:
-                raise ClosingError( self.tag )
-        elif self.parent.mode == 'strict_html' and self.tag in self.parent.deptags:
-            raise DeprecationError( self.tag )
-        else:
-            raise InvalidElementError( self.tag, self.parent.mode )
-
-    def render( self, tag, single, between, kwargs ):
-        """Append the actual tags to content."""
-
-        out = "<%s" % tag
-        for key, value in kwargs.items( ):
-            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.
-                if key == 'http_equiv':         # special cases, maybe change _ to - overall?
-                    key = 'http-equiv'
-                elif key == 'accept_charset':
-                    key = 'accept-charset'
-                out = "%s %s=\"%s\"" % ( out, key, escape( value ) )
-            else:
-                out = "%s %s" % ( out, key )
-        if between is not None:
-            out = "%s>%s</%s>" % ( out, between, tag )
-        else:
-            if single:
-                out = "%s />" % out
-            else:
-                out = "%s>" % out
-        if self.parent is not None:
-            self.parent.content.append( out )
-        else:
-            return out
-
-    def close( self ):
-        """Append a closing tag unless element has only opening tag."""
-
-        if self.tag in self.parent.twotags:
-            self.parent.content.append( "</%s>" % self.tag )
-        elif self.tag in self.parent.onetags:
-            raise ClosingError( self.tag )
-        elif self.parent.mode == 'strict_html' and self.tag in self.parent.deptags:
-            raise DeprecationError( self.tag )
-
-    def open( self, **kwargs ):
-        """Append an opening tag."""
-
-        if self.tag in self.parent.twotags or self.tag in self.parent.onetags:
-            self.render( self.tag, False, None, kwargs )
-        elif self.mode == 'strict_html' and self.tag in self.parent.deptags:
-            raise DeprecationError( self.tag )
-
-class page:
-    """This is our main class representing a document. Elements are added
-    as attributes of an instance of this class."""
-
-    def __init__( self, mode='strict_html', case='lower', onetags=None, twotags=None, separator='\n', class_=None ):
-        """Stuff that effects the whole document.
-
-        mode -- 'strict_html'   for HTML 4.01 (default)
-                'html'          alias for 'strict_html'
-                'loose_html'    to allow some deprecated elements
-                'xml'           to allow arbitrary elements
-
-        case -- 'lower'         element names will be printed in lower case (default)
-                'upper'         they will be printed in upper case
-
-        onetags --              list or tuple of valid elements with opening tags only
-        twotags --              list or tuple of valid elements with both opening and closing tags
-                                these two keyword arguments may be used to select
-                                the set of valid elements in 'xml' mode
-                                invalid elements will raise appropriate exceptions
-
-        separator --            string to place between added elements, defaults to newline
-
-        class_ --               a class that will be added to every element if defined"""
-
-        valid_onetags = [ "AREA", "BASE", "BR", "COL", "FRAME", "HR", "IMG", "INPUT", "LINK", "META", "PARAM" ]
-        valid_twotags = [ "A", "ABBR", "ACRONYM", "ADDRESS", "B", "BDO", "BIG", "BLOCKQUOTE", "BODY", "BUTTON",
-                "CAPTION", "CITE", "CODE", "COLGROUP", "DD", "DEL", "DFN", "DIV", "DL", "DT", "EM", "FIELDSET",
-                "FORM", "FRAMESET", "H1", "H2", "H3", "H4", "H5", "H6", "HEAD", "HTML", "I", "IFRAME", "INS",
-                "KBD", "LABEL", "LEGEND", "LI", "MAP", "NOFRAMES", "NOSCRIPT", "OBJECT", "OL", "OPTGROUP",
-                "OPTION", "P", "PRE", "Q", "SAMP", "SCRIPT", "SELECT", "SMALL", "SPAN", "STRONG", "STYLE",
-                "SUB", "SUP", "TABLE", "TBODY", "TD", "TEXTAREA", "TFOOT", "TH", "THEAD", "TITLE", "TR",
-                "TT", "UL", "VAR" ]
-        deprecated_onetags = [ "BASEFONT", "ISINDEX" ]
-        deprecated_twotags = [ "APPLET", "CENTER", "DIR", "FONT", "MENU", "S", "STRIKE", "U" ]
-
-        self.header = [ ]
-        self.content = [ ]
-        self.footer = [ ]
-        self.case = case
-        self.separator = separator
-
-        # init( ) sets it to True so we know that </body></html> has to be printed at the end
-        self._full = False
-        self.class_= class_
-
-        if mode == 'strict_html' or mode == 'html':
-            self.onetags = valid_onetags
-            self.onetags += list(map( str.lower, self.onetags ))
-            self.twotags = valid_twotags
-            self.twotags += list(map( str.lower, self.twotags ))
-            self.deptags = deprecated_onetags + deprecated_twotags
-            self.deptags += list(map( str.lower, self.deptags ))
-            self.mode = 'strict_html'
-        elif mode == 'loose_html':
-            self.onetags = valid_onetags + deprecated_onetags
-            self.onetags += list(map( str.lower, self.onetags ))
-            self.twotags = valid_twotags + deprecated_twotags
-            self.twotags += list(map( str.lower, self.twotags ))
-            self.mode = mode
-        elif mode == 'xml':
-            if onetags and twotags:
-                self.onetags = onetags
-                self.twotags = twotags
-            elif ( onetags and not twotags ) or ( twotags and not onetags ):
-                raise CustomizationError( )
-            else:
-                self.onetags = russell( )
-                self.twotags = russell( )
-            self.mode = mode
-        else:
-            raise ModeError( mode )
-
-    def __getattr__( self, attr ):
-        if attr.startswith("__") and attr.endswith("__"):
-            raise AttributeError(attr)
-        return element( attr, case=self.case, parent=self )
-
-    def __str__( self ):
-
-        if self._full and ( self.mode == 'strict_html' or self.mode == 'loose_html' ):
-            end = [ '</body>', '</html>' ]
-        else:
-            end = [ ]
-
-        return self.separator.join( self.header + self.content + self.footer + end )
-
-    def __call__( self, escape=False ):
-        """Return the document as a string.
-
-        escape --   False   print normally
-                    True    replace < and > by &lt; and &gt;
-                            the default escape sequences in most browsers"""
-
-        if escape:
-            return _escape( self.__str__( ) )
-        else:
-            return self.__str__( )
-
-    def add( self, text ):
-        """This is an alias to addcontent."""
-        self.addcontent( text )
-
-    def addfooter( self, text ):
-        """Add some text to the bottom of the document"""
-        self.footer.append( text )
-
-    def addheader( self, text ):
-        """Add some text to the top of the document"""
-        self.header.append( text )
-
-    def addcontent( self, text ):
-        """Add some text to the main part of the document"""
-        self.content.append( text )
-
-
-    def init( self, lang='en', css=None, metainfo=None, title=None, header=None,
-              footer=None, charset=None, encoding=None, doctype=None, bodyattrs=None, script=None ):
-        """This method is used for complete documents with appropriate
-        doctype, encoding, title, etc information. For an HTML/XML snippet
-        omit this method.
-
-        lang --     language, usually a two character string, will appear
-                    as <html lang='en'> in html mode (ignored in xml mode)
-
-        css --      Cascading Style Sheet filename as a string or a list of
-                    strings for multiple css files (ignored in xml mode)
-
-        metainfo -- a dictionary in the form { 'name':'content' } to be inserted
-                    into meta element(s) as <meta name='name' content='content'>
-                    (ignored in xml mode)
-
-        bodyattrs --a dictionary in the form { 'key':'value', ... } which will be added
-                    as attributes of the <body> element as <body key='value' ... >
-                    (ignored in xml mode)
-
-        script --   dictionary containing src:type pairs, <script type='text/type' src=src></script>
-
-        title --    the title of the document as a string to be inserted into
-                    a title element as <title>my title</title> (ignored in xml mode)
-
-        header --   some text to be inserted right after the <body> element
-                    (ignored in xml mode)
-
-        footer --   some text to be inserted right before the </body> element
-                    (ignored in xml mode)
-
-        charset --  a string defining the character set, will be inserted into a
-                    <meta http-equiv='Content-Type' content='text/html; charset=myset'>
-                    element (ignored in xml mode)
-
-        encoding -- a string defining the encoding, will be put into to first line of
-                    the document as <?xml version='1.0' encoding='myencoding' ?> in
-                    xml mode (ignored in html mode)
-
-        doctype --  the document type string, defaults to
-                    <!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Transitional//EN'>
-                    in html mode (ignored in xml mode)"""
-
-        self._full = True
-
-        if self.mode == 'strict_html' or self.mode == 'loose_html':
-            if doctype is None:
-                doctype = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Transitional//EN'>"
-            self.header.append( doctype )
-            self.html( lang=lang )
-            self.head( )
-            if charset is not None:
-                self.meta( http_equiv='Content-Type', content="text/html; charset=%s" % charset )
-            if metainfo is not None:
-                self.metainfo( metainfo )
-            if css is not None:
-                self.css( css )
-            if title is not None:
-                self.title( title )
-            if script is not None:
-                self.scripts( script )
-            self.head.close()
-            if bodyattrs is not None:
-                self.body( **bodyattrs )
-            else:
-                self.body( )
-            if header is not None:
-                self.content.append( header )
-            if footer is not None:
-                self.footer.append( footer )
-
-        elif self.mode == 'xml':
-            if doctype is None:
-                if encoding is not None:
-                    doctype = "<?xml version='1.0' encoding='%s' ?>" % encoding
-                else:
-                    doctype = "<?xml version='1.0' ?>"
-            self.header.append( doctype )
-
-    def css( self, filelist ):
-        """This convenience function is only useful for html.
-        It adds css stylesheet(s) to the document via the <link> element."""
-
-        if isinstance( filelist, str ):
-            self.link( href=filelist, rel='stylesheet', type='text/css', media='all' )
-        else:
-            for file in filelist:
-                self.link( href=file, rel='stylesheet', type='text/css', media='all' )
-
-    def metainfo( self, mydict ):
-        """This convenience function is only useful for html.
-        It adds meta information via the <meta> element, the argument is
-        a dictionary of the form { 'name':'content' }."""
-
-        if isinstance( mydict, dict ):
-            for name, content in mydict.items( ):
-                self.meta( name=name, content=content )
-        else:
-            raise TypeError("Metainfo should be called with a dictionary argument of name:content pairs.")
-
-    def scripts( self, mydict ):
-        """Only useful in html, mydict is dictionary of src:type pairs will
-        be rendered as <script type='text/type' src=src></script>"""
-
-        if isinstance( mydict, dict ):
-            for src, type in mydict.items( ):
-                self.script( '', src=src, type='text/%s' % type )
-        else:
-            raise TypeError("Script should be given a dictionary of src:type pairs.")
-
-
-class _oneliner:
-    """An instance of oneliner returns a string corresponding to one element.
-    This class can be used to write 'oneliners' that return a string
-    immediately so there is no need to instantiate the page class."""
-
-    def __init__( self, case='lower' ):
-        self.case = case
-
-    def __getattr__( self, attr ):
-        if attr.startswith("__") and attr.endswith("__"):
-            raise AttributeError(attr)
-        return element( attr, case=self.case, parent=None )
-
-oneliner = _oneliner( case='lower' )
-upper_oneliner = _oneliner( case='upper' )
-
-def _argsdicts( args, mydict ):
-    """A utility generator that pads argument list and dictionary values, will only be called with len( args ) = 0, 1."""
-
-    if len( args ) == 0:
-        args = None,
-    elif len( args ) == 1:
-        args = _totuple( args[0] )
-    else:
-        raise Exception("We should have never gotten here.")
-
-    mykeys = list(mydict.keys( ))
-    myvalues = list(map( _totuple, list(mydict.values( )) ))
-
-    maxlength = max( list(map( len, [ args ] + myvalues )) )
-
-    for i in range( maxlength ):
-        thisdict = { }
-        for key, value in zip( mykeys, myvalues ):
-            try:
-                thisdict[ key ] = value[i]
-            except IndexError:
-                thisdict[ key ] = value[-1]
-        try:
-            thisarg = args[i]
-        except IndexError:
-            thisarg = args[-1]
-
-        yield thisarg, thisdict
-
-def _totuple( x ):
-    """Utility stuff to convert string, int, float, None or anything to a usable tuple."""
-
-    if isinstance( x, str ):
-        out = x,
-    elif isinstance( x, ( int, float ) ):
-        out = str( x ),
-    elif x is None:
-        out = None,
-    else:
-        out = tuple( x )
-
-    return out
-
-def escape( text, newline=False ):
-    """Escape special html characters."""
-
-    if isinstance( text, str ):
-        if '&' in text:
-            text = text.replace( '&', '&amp;' )
-        if '>' in text:
-            text = text.replace( '>', '&gt;' )
-        if '<' in text:
-            text = text.replace( '<', '&lt;' )
-        if '\"' in text:
-            text = text.replace( '\"', '&quot;' )
-        if '\'' in text:
-            text = text.replace( '\'', '&quot;' )
-        if newline:
-            if '\n' in text:
-                text = text.replace( '\n', '<br>' )
-
-    return text
-
-_escape = escape
-
-def unescape( text ):
-    """Inverse of escape."""
-
-    if isinstance( text, str ):
-        if '&amp;' in text:
-            text = text.replace( '&amp;', '&' )
-        if '&gt;' in text:
-            text = text.replace( '&gt;', '>' )
-        if '&lt;' in text:
-            text = text.replace( '&lt;', '<' )
-        if '&quot;' in text:
-            text = text.replace( '&quot;', '\"' )
-
-    return text
-
-class dummy:
-    """A dummy class for attaching attributes."""
-    pass
-
-doctype = dummy( )
-doctype.frameset = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Frameset//EN' 'http://www.w3.org/TR/html4/frameset.dtd'>"
-doctype.strict = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01//EN' 'http://www.w3.org/TR/html4/strict.dtd'>"
-doctype.loose = "<!DOCTYPE HTML PUBLIC '-//W3C//DTD HTML 4.01 Transitional//EN' 'http://www.w3.org/TR/html4/loose.dtd'>"
-
-class russell:
-    """A dummy class that contains anything."""
-
-    def __contains__( self, item ):
-        return True
-
-
-class MarkupError( Exception ):
-    """All our exceptions subclass this."""
-    def __str__( self ):
-        return self.message
-
-class ClosingError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' does not accept non-keyword arguments (has no closing tag)." % tag
-
-class OpeningError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' can not be opened." % tag
-
-class ArgumentError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' was called with more than one non-keyword argument." % tag
-
-class InvalidElementError( MarkupError ):
-    def __init__( self, tag, mode ):
-        self.message = "The element '%s' is not valid for your mode '%s'." % ( tag, mode )
-
-class DeprecationError( MarkupError ):
-    def __init__( self, tag ):
-        self.message = "The element '%s' is deprecated, instantiate markup.page with mode='loose_html' to allow it." % tag
-
-class ModeError( MarkupError ):
-    def __init__( self, mode ):
-        self.message = "Mode '%s' is invalid, possible values: strict_html, loose_html, xml." % mode
-
-class CustomizationError( MarkupError ):
-    def __init__( self ):
-        self.message = "If you customize the allowed elements, you must define both types 'onetags' and 'twotags'."
-
-if __name__ == '__main__':
-    print(__doc__)

tablib/packages/statistics.py

@@ -1,24 +0,0 @@
-from __future__ import division
-
-
-def median(data):
-    """
-    Return the median (middle value) of numeric data, using the common
-    "mean of middle two" method. If data is empty, ValueError is raised.
-
-    Mimics the behaviour of Python3's statistics.median
-
-    >>> median([1, 3, 5])
-    3
-    >>> median([1, 3, 5, 7])
-    4.0
-
-    """
-    data = sorted(data)
-    n = len(data)
-    if not n:
-        raise ValueError("No median for empty data")
-    i = n // 2
-    if n % 2:
-        return data[i]
-    return (data[i - 1] + data[i]) / 2