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

@@ -17,3 +17,27 @@ profile
 
 # vi noise
 *.swp
+docs/_build/*
+coverage.xml
+nosetests.xml
+junit-py25.xml
+junit-py26.xml
+junit-py27.xml
+
+# tox noise
+.tox
+
+# 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

AUTHORS

@@ -1,13 +1,32 @@
-Tablib is written and maintained by Kenneth Reitz and
+Tablib was originally written by Kenneth Reitz and is now maintained
-various contributors:
+by the Jazzband GitHub team.
 
-Development Lead
+Here is a list of passed and present much-appreciated contributors:
-````````````````
 
-- Kenneth Reitz <me@kennethreitz.com>
+    Alex Gaynor
-
+    Andrii Soldatenko
-
+    Benjamin Wohlwend
-Patches and Suggestions
+    Bruno Soares
-```````````````````````
+    Claude Paroz
-
+    Daniel Santos
-- Luke Lee
+    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

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

@@ -1,63 +0,0 @@
-History
-=======
-
-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 compenated in documentation.
-
-
-0.7.0 (2010-09-20)
-------------------
-
-* Renamed DataBook Databook for consistiency.
-* 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 (c) 2010 Kenneth Reitz.
+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 

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

@@ -1,188 +0,0 @@
-Tablib: format-agnostic tabular dataset library
-===============================================
-
-::
-
-	_____         ______  ___________ ______  
-	__  /_______ ____  /_ ___  /___(_)___  /_ 
-	_  __/_  __ `/__  __ \__  / __  / __  __ \
-	/ /_  / /_/ / _  /_/ /_  /  _  /  _  /_/ /
-	\__/  \__,_/  /_.___/ /_/   /_/   /_.___/
-
-
-
-Tablib is a format-agnostic tabular dataset library, written in Python. 
-
-Output formats supported:
-
-- Excel (Sets + Books)
-- JSON (Sets + Books)
-- YAML (Sets + Books)
-- CSV (Sets)
-
-Import formats supported:
-
-- JSON (Sets + Books)
-- YAML (Sets + Books)
-- CSV (Sets)
-
-Note that tablib *purposefully* excludes XML support. It always will.
-
-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 maniuplated as raw Python datatypes (Lists of tuples|dictonaries). Datasets can be imported from JSON, YAML, and CSV; they can be exported to Excel (XLS), JSON, YAML, and CSV.
-	
-`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 Excel (XLS), 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=('age', 90, 67, 83))
-    
-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.json
-	[
-	  {
-	    "last_name": "Adams",
-	    "age": 90,
-	    "first_name": "John"
-	  },
-	  {
-	    "last_name": "Ford",
-	    "age": 83,
-	    "first_name": "Henry"
-	  }
-	]
-	
-
-YAML! 
-+++++
-::
-
-	>>> print data.yaml
-	- {age: 90, first_name: John, last_name: Adams}
-	- {age: 83, first_name: Henry, last_name: Ford}
-	
-CSV... 
-++++++
-::
-
-	>>> print data.csv
-	first_name,last_name,age 
-	John,Adams,90 
-	Henry,Ford,83 
-	
-EXCEL! 
-++++++
-::
-
-	>>> open('people.xls', 'wb').write(data.xls)
-
-It's that easy.
-
-Imports!
---------
-
-JSON
-++++
-
-::
-
-	>>> data.json = '[{"last_name": "Adams","age": 90,"first_name": "John"}]'
-	>>> print data[0]
-	('John', 'Adams', 90)
-
-
-YAML
-++++
-::
-
-	>>> data.yaml = '- {age: 90, first_name: John, last_name: Adams}'
-	>>> print data[0]
-	('John', 'Adams', 90)
-
-CSV
-+++
-::
-
-	>>> data.yaml = 'age, first_name, last_name\n90, John, Adams'
-	>>> print data[0]
-	('John', 'Adams', 90)
-	
-	>>> print data.yaml
-	- {age: 90, first_name: John, last_name: Adams}
-	
-
-
-Installation
-------------
-
-To install tablib, simply: ::
-
-	$ pip install tablib
-	
-Or, if you absolutely must: ::
-
-	$ easy_install 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_.
-
-
-Roadmap
--------
-- Release CLI Interface
-- Auto-detect import format
-- Add possible other exports (SQL?)
-- Ability to assign types to rows (set, regex=, &c.)
-
-.. _`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/Makefile

@@ -0,0 +1,130 @@
+# Makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+PAPER         =
+BUILDDIR      = _build
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
+
+.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest
+
+help:
+	@echo "Please use \`make <target>' where <target> is one of"
+	@echo "  html       to make standalone HTML files"
+	@echo "  dirhtml    to make HTML files named index.html in directories"
+	@echo "  singlehtml to make a single large HTML file"
+	@echo "  pickle     to make pickle files"
+	@echo "  json       to make JSON files"
+	@echo "  htmlhelp   to make HTML files and a HTML help project"
+	@echo "  qthelp     to make HTML files and a qthelp project"
+	@echo "  devhelp    to make HTML files and a Devhelp project"
+	@echo "  epub       to make an epub"
+	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
+	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
+	@echo "  text       to make text files"
+	@echo "  man        to make manual pages"
+	@echo "  changes    to make an overview of all changed/added/deprecated items"
+	@echo "  linkcheck  to check all external links for integrity"
+	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
+
+clean:
+	-rm -rf $(BUILDDIR)/*
+
+html:
+	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
+
+dirhtml:
+	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
+	@echo
+	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
+
+singlehtml:
+	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
+	@echo
+	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
+
+pickle:
+	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
+	@echo
+	@echo "Build finished; now you can process the pickle files."
+
+json:
+	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
+	@echo
+	@echo "Build finished; now you can process the JSON files."
+
+htmlhelp:
+	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
+	@echo
+	@echo "Build finished; now you can run HTML Help Workshop with the" \
+	      ".hhp project file in $(BUILDDIR)/htmlhelp."
+
+qthelp:
+	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
+	@echo
+	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
+	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
+	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/Tablib.qhcp"
+	@echo "To view the help file:"
+	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/Tablib.qhc"
+
+devhelp:
+	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
+	@echo
+	@echo "Build finished."
+	@echo "To view the help file:"
+	@echo "# mkdir -p $$HOME/.local/share/devhelp/Tablib"
+	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/Tablib"
+	@echo "# devhelp"
+
+epub:
+	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
+	@echo
+	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
+
+latex:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo
+	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
+	@echo "Run \`make' in that directory to run these through (pdf)latex" \
+	      "(use \`make latexpdf' here to do that automatically)."
+
+latexpdf:
+	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
+	@echo "Running LaTeX files through pdflatex..."
+	make -C $(BUILDDIR)/latex all-pdf
+	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
+
+text:
+	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
+	@echo
+	@echo "Build finished. The text files are in $(BUILDDIR)/text."
+
+man:
+	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
+	@echo
+	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
+
+changes:
+	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
+	@echo
+	@echo "The overview file is in $(BUILDDIR)/changes."
+
+linkcheck:
+	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
+	@echo
+	@echo "Link check complete; look for any errors in the above output " \
+	      "or in $(BUILDDIR)/linkcheck/output.txt."
+
+doctest:
+	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
+	@echo "Testing of doctests in the sources finished, look at the " \
+	      "results in $(BUILDDIR)/doctest/output.txt."

docs/_templates/sidebarintro.html

@@ -0,0 +1,12 @@
+<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>Useful Links</h3>
+<ul>
+  <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

@@ -0,0 +1,4 @@
+<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>

docs/api.rst

@@ -0,0 +1,64 @@
+.. _api:
+
+===
+API
+===
+
+
+.. module:: tablib
+
+This part of the documentation covers all the interfaces of Tablib.  For
+parts where Tablib depends on external libraries, we document the most
+important right here and provide links to the canonical documentation.
+
+
+--------------
+Dataset Object
+--------------
+
+
+.. autoclass:: Dataset
+   :inherited-members:
+
+
+---------------
+Databook Object
+---------------
+
+
+.. autoclass:: Databook
+   :inherited-members:
+
+
+
+---------
+Functions
+---------
+
+
+.. autofunction:: detect_format
+
+.. autofunction:: import_set
+
+
+----------
+Exceptions
+----------
+
+
+.. class:: InvalidDatasetType
+
+    You're trying to add something that doesn't quite look right.
+
+
+.. class:: InvalidDimensions
+
+    You're trying to add something that doesn't quite fit right.
+
+
+.. class:: UnsupportedFormat
+
+    You're trying to add something that doesn't quite taste right.
+
+
+Now, go start some :ref:`Tablib Development <development>`.

docs/conf.py

@@ -0,0 +1,230 @@
+#
+# Tablib documentation build configuration file, created by
+# sphinx-quickstart on Tue Oct  5 15:25:21 2010.
+#
+# This file is execfile()d with the current directory set to its containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+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('..'))
+# -- General configuration -----------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+# 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', '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']
+
+# The suffix of source filenames.
+source_suffix = '.rst'
+
+# The encoding of source files.
+#source_encoding = 'utf-8-sig'
+
+# The master toctree document.
+master_doc = 'index'
+
+# General information about the 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 full version, including alpha/beta/rc tags.
+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.
+#language = None
+
+# There are two options for replacing |today|: either, you set today to some
+# non-false value, then it is used:
+#today = ''
+# Else, today_fmt is used as the format for a strftime call.
+#today_fmt = '%B %d, %Y'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+exclude_patterns = ['_build']
+
+# The reST default role (used for this markup: `text`) to use for all documents.
+#default_role = None
+
+# If true, '()' will be appended to :func: etc. cross-reference text.
+add_function_parentheses = True
+
+# If true, the current module name will be prepended to all description
+# unit titles (such as .. function::).
+# add_module_names = True
+
+# If true, sectionauthor and moduleauthor directives will be shown in the
+# output. They are ignored by default.
+#show_authors = False
+
+# The name of the Pygments (syntax highlighting) style to use.
+# pygments_style = ''
+
+# A list of ignored prefixes for module index sorting.
+#modindex_common_prefix = []
+
+
+# -- Options for HTML output ---------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+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
+# documentation.
+#html_theme_options = {}
+
+# Add any paths that contain custom themes here, relative to this directory.
+#html_theme_path = []
+
+# The name for this set of Sphinx documents.  If None, it defaults to
+# "<project> v<release> documentation".
+#html_title = None
+
+# A shorter title for the navigation bar.  Default is the same as html_title.
+#html_short_title = None
+
+# The name of an image file (relative to this directory) to place at the top
+# of the sidebar.
+#html_logo = None
+
+# The name of an image file (within the static path) to use as favicon of the
+# docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
+# pixels large.
+#html_favicon = None
+
+# 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']
+
+# If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
+# using the given strftime format.
+#html_last_updated_fmt = '%b %d, %Y'
+
+# If true, SmartyPants will be used to convert quotes and dashes to
+# typographically correct entities.
+html_use_smartypants = True
+
+# Custom sidebar templates, maps document names to template names.
+html_sidebars = {
+    'index':    ['sidebarintro.html', 'sourcelink.html', 'searchbox.html'],
+    '**':       ['sidebarlogo.html', 'localtoc.html', 'relations.html',
+                 'sourcelink.html', 'searchbox.html']
+}
+
+# Additional templates that should be rendered to pages, maps page names to
+# template names.
+#html_additional_pages = {}
+
+# If false, no module index is generated.
+#html_domain_indices = True
+
+# If false, no index is generated.
+#html_use_index = True
+
+# If true, the index is split into individual pages for each letter.
+#html_split_index = False
+
+# If true, links to the reST sources are added to the pages.
+html_show_sourcelink = True
+
+# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
+html_show_sphinx = False
+
+# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
+#html_show_copyright = True
+
+# If true, an OpenSearch description file will be output, and all pages will
+# contain a <link> tag referring to it.  The value of this option must be the
+# base URL from which the finished HTML is served.
+#html_use_opensearch = ''
+
+# This is the file name suffix for HTML files (e.g. ".xhtml").
+#html_file_suffix = None
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'Tablibdoc'
+
+
+# -- Options for LaTeX output --------------------------------------------------
+
+# The paper size ('letter' or 'a4').
+#latex_paper_size = 'letter'
+
+# The font size ('10pt', '11pt' or '12pt').
+#latex_font_size = '10pt'
+
+# 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', 'Tablib Documentation',
+   'Jazzband', 'manual'),
+]
+
+latex_use_modindex = False
+
+latex_elements = {
+    'papersize':    'a4paper',
+    'pointsize':    '12pt',
+}
+latex_use_parts = True
+
+# The name of an image file (relative to this directory) to place at the top of
+# the title page.
+#latex_logo = None
+
+# For "manual" documents, if this is true, then toplevel headings are parts,
+# not chapters.
+#latex_use_parts = False
+
+# If true, show page references after internal links.
+#latex_show_pagerefs = False
+
+# If true, show URL addresses after external links.
+#latex_show_urls = False
+
+# Additional stuff for the LaTeX preamble.
+#latex_preamble = ''
+
+# Documents to append as an appendix to all manuals.
+#latex_appendices = []
+
+# If false, no module index is generated.
+#latex_domain_indices = True
+
+
+# -- Options for manual page output --------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    ('index', 'tablib', 'Tablib Documentation',
+     ['Jazzband'], 1)
+]

docs/development.rst

@@ -0,0 +1,214 @@
+.. _development:
+
+Development
+===========
+
+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: https://github.com/jazzband/tablib/
+
+
+
+.. _design:
+
+---------------------
+Design Considerations
+---------------------
+
+Tablib was developed with a few :pep:`20` idioms in mind.
+
+#. Beautiful is better than ugly.
+#. Explicit is better than implicit.
+#. Simple is better than complex.
+#. Complex is better than complicated.
+#. Readability counts.
+
+A few other things to keep in mind:
+
+#. Keep your code DRY.
+#. Strive to be as simple (to use) as possible.
+
+.. _scm:
+
+--------------
+Source Control
+--------------
+
+
+Tablib source is controlled with Git_, the lean, mean, distributed source
+control machine.
+
+The repository is publicly accessible.
+
+.. code-block:: console
+
+    git clone git://github.com/jazzband/tablib.git
+
+The project is hosted on **GitHub**.
+
+    GitHub:
+        https://github.com/jazzband/tablib
+
+
+Git Branch Structure
+++++++++++++++++++++
+
+Feature / Hotfix / Release branches follow a `Successful Git Branching Model`_ .
+Git-flow_ is a great tool for managing the repository. I highly recommend it.
+
+``master``
+    Current production release (|version|) on PyPi.
+
+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: 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:
+
+------------------
+Adding New Formats
+------------------
+
+Tablib welcomes new format additions! Format suggestions include:
+
+* MySQL Dump
+
+
+Coding by Convention
+++++++++++++++++++++
+
+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*.
+
+From version 1.0, Tablib formats are class-based and can be dynamically
+registered.
+
+1. Write your custom format class::
+
+    class MyXXXFormatClass:
+        title = 'xxx'
+
+        @classmethod
+        def export_set(cls, dset):
+            ....
+            # returns string representation of given dataset
+
+        @classmethod
+        def export_book(cls, dbook):
+            ....
+            # returns string representation of given databook
+
+        @classmethod
+        def import_set(cls, dset, in_stream):
+            ...
+            # populates given Dataset with given datastream
+
+        @classmethod
+        def import_book(cls, dbook, in_stream):
+            ...
+            # returns Databook instance
+
+        @classmethod
+        def detect(cls, stream):
+            ...
+            # returns True if given stream is parsable as xxx
+
+   .. admonition:: Excluding Support
+
+       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 class methods.
+       Appropriate errors will be raised.
+
+2. Register your class::
+
+    from tablib.formats import registry
+
+    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:
+
+--------------
+Testing Tablib
+--------------
+
+Testing is crucial to Tablib's stability.
+This stable project is used in production by many companies and developers,
+so it is important to be certain that every version released is fully operational.
+When developing a new feature for Tablib, be sure to write proper tests for it as well.
+
+When developing a feature for Tablib,
+the easiest way to test your changes for potential issues is to simply run the test suite directly.
+
+.. code-block:: console
+
+    $ tox
+
+----------------------
+Continuous Integration
+----------------------
+
+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://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.
+
+.. _`GitHub Actions`: https://github.com/jazzband/tablib/actions
+
+
+.. _docs:
+
+-----------------
+Building the Docs
+-----------------
+
+Documentation is written in the powerful, flexible,
+and standard Python documentation format, `reStructured Text`_.
+Documentation builds are powered by the powerful Pocoo project, Sphinx_.
+The :ref:`API Documentation <api>` is mostly documented inline throughout the module.
+
+The Docs live in ``tablib/docs``.
+In order to build them, you will first need to install Sphinx.
+
+.. code-block:: console
+
+    $ pip install sphinx
+
+
+Then, to build an HTML version of the docs, simply run the following from the ``docs`` directory:
+
+.. code-block:: console
+
+    $ make html
+
+Your ``docs/_build/html`` directory will then contain an HTML representation of the documentation,
+ready for publication on most web servers.
+
+You can also generate the documentation in **epub**, **latex**, **json**, *&c* similarly.
+
+.. _`reStructured Text`: http://docutils.sourceforge.net/rst.html
+.. _Sphinx: http://sphinx.pocoo.org
+.. _`GitHub Pages`: https://pages.github.com
+
+----------
+
+Make sure to check out the :ref:`API Documentation <api>`.

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

@@ -0,0 +1,121 @@
+.. 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.
+
+Tablib: Pythonic Tabular Datasets
+=================================
+
+Release v\ |version|. (:ref:`Installation <install>`)
+
+.. Contents:
+..
+.. .. toctree::
+..    :maxdepth: 2
+..
+
+.. Indices and tables
+.. ==================
+..
+.. * :ref:`genindex`
+.. * :ref:`modindex`
+.. * :ref:`search`
+
+
+Tablib is an `MIT Licensed <https://mit-license.org/>`_ 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.
+
+::
+
+   >>> data = tablib.Dataset(headers=['First Name', 'Last Name', 'Age'])
+   >>> for i in [('Kenneth', 'Reitz', 22), ('Bessie', 'Monke', 21)]:
+   ...     data.append(i)
+
+
+   >>> print(data.export('json'))
+   [{"Last Name": "Reitz", "First Name": "Kenneth", "Age": 22}, {"Last Name": "Monke", "First Name": "Bessie", "Age": 21}]
+
+   >>> print(data.export('yaml'))
+   - {Age: 22, First Name: Kenneth, Last Name: Reitz}
+   - {Age: 21, First Name: Bessie, Last Name: Monke}
+
+   >>> data.export('xlsx')
+   <redacted binary data>
+
+   >>> data.export('df')
+     First Name Last Name  Age
+   0    Kenneth     Reitz   22
+   1     Bessie     Monke   21
+
+
+Testimonials
+------------
+
+`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.
+
+
+
+**Greg Thorton**
+   Tablib by @kennethreitz saved my life.
+   I had to consolidate like 5 huge poorly maintained lists of domains and data.
+   It was a breeze!
+
+**Dave Coutts**
+   It's turning into one of my most used modules of 2010.
+   You really hit a sweet spot for managing tabular data with a minimal amount of code and effort.
+
+**Joshua Ourisman**
+   Tablib has made it so much easier to deal with the inevitable 'I want an Excel file!' requests from clients...
+
+**Brad Montgomery**
+    I think you nailed the "Python Zen" with tablib.
+    Thanks again for an awesome lib!
+
+
+User's Guide
+------------
+
+This part of the documentation, which is mostly prose, begins with some background information about Tablib, then focuses on step-by-step instructions for getting the most out of your datasets.
+
+.. toctree::
+   :maxdepth: 2
+
+   intro
+
+.. toctree::
+   :maxdepth: 2
+
+   install
+
+.. toctree::
+   :maxdepth: 2
+
+   tutorial
+
+.. toctree::
+   :maxdepth: 2
+
+   formats
+
+.. toctree::
+   :maxdepth: 2
+
+   development
+
+
+API Reference
+-------------
+
+If you are looking for information on a specific function, class or
+method, this part of the documentation is for you.
+
+.. toctree::
+   :maxdepth: 2
+
+   api

docs/install.rst

@@ -0,0 +1,85 @@
+.. _install:
+
+Installation
+============
+
+This part of the documentation covers the installation of Tablib. The first step to using any software package is getting it properly installed.
+
+
+.. _installing:
+
+-----------------
+Installing Tablib
+-----------------
+
+Distribute & Pip
+----------------
+
+Of course, the recommended way to install Tablib is with `pip <https://pip.pypa.io>`_:
+
+.. code-block:: console
+
+    $ 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.
+The latest release (|version|) is available from GitHub.
+
+* tarball_
+* zipball_
+
+.. _
+
+Once you have a copy of the source,
+you can embed it in your Python package,
+or install it into your site-packages easily.
+
+.. code-block:: console
+
+    $ python setup.py install
+
+
+To download the full source history from Git, see :ref:`Source Control <scm>`.
+
+.. _tarball: https://github.com/jazzband/tablib/tarball/master
+.. _zipball: https://github.com/jazzband/tablib/zipball/master
+
+
+.. _updates:
+
+Staying Updated
+---------------
+
+The latest version of Tablib will always be available here:
+
+* PyPI: https://pypi.org/project/tablib/
+* GitHub: https://github.com/jazzband/tablib/
+
+When a new version is available, upgrading is simple::
+
+    $ pip install tablib --upgrade
+
+
+Now, go get a :ref:`Quick Start <quickstart>`.

docs/intro.rst

@@ -0,0 +1,63 @@
+.. _intro:
+
+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
+seamless format import/export.
+
+
+Philosophy
+----------
+
+Tablib was developed with a few :pep:`20` idioms in mind.
+
+#. Beautiful is better than ugly.
+#. Explicit is better than implicit.
+#. Simple is better than complex.
+#. Complex is better than complicated.
+#. Readability counts.
+
+All contributions to Tablib should keep these important rules in mind.
+
+.. _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
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+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 MIT License`: https://opensource.org/licenses/mit-license.php
+
+.. _pythonsupport:
+
+Pythons Supported
+-----------------
+
+Python 3.6+ is officially supported.
+
+Now, go :ref:`install Tablib <install>`.
+

docs/krstyle.sty

@@ -0,0 +1,118 @@
+\definecolor{TitleColor}{rgb}{0,0,0}
+\definecolor{InnerLinkColor}{rgb}{0,0,0}
+
+\renewcommand{\maketitle}{%
+  \begin{titlepage}%
+    \let\footnotesize\small
+    \let\footnoterule\relax
+    \ifsphinxpdfoutput
+      \begingroup
+      % This \def is required to deal with multi-line authors; it
+      % changes \\ to ', ' (comma-space), making it pass muster for
+      % generating document info in the PDF file.
+      \def\\{, }
+      \pdfinfo{
+        /Author (\@author)
+        /Title (\@title)
+      }
+      \endgroup
+    \fi
+    \begin{flushright}%
+      %\sphinxlogo%
+      {\center
+        \vspace*{3cm}
+      	\includegraphics{logo.pdf}
+        \vspace{3cm}
+	\par
+        {\rm\Huge \@title \par}%
+        {\em\LARGE \py@release\releaseinfo \par}
+        {\large
+         \@date \par
+         \py@authoraddress \par
+        }}%
+    \end{flushright}%\par
+    \@thanks
+  \end{titlepage}%
+  \cleardoublepage%
+  \setcounter{footnote}{0}%
+  \let\thanks\relax\let\maketitle\relax
+  %\gdef\@thanks{}\gdef\@author{}\gdef\@title{}
+}
+
+\fancypagestyle{normal}{
+  \fancyhf{}
+  \fancyfoot[LE,RO]{{\thepage}}
+  \fancyfoot[LO]{{\nouppercase{\rightmark}}}
+  \fancyfoot[RE]{{\nouppercase{\leftmark}}}
+  \fancyhead[LE,RO]{{ \@title, \py@release}}
+  \renewcommand{\headrulewidth}{0.4pt}
+  \renewcommand{\footrulewidth}{0.4pt}
+}
+
+\fancypagestyle{plain}{
+  \fancyhf{}
+  \fancyfoot[LE,RO]{{\thepage}}
+  \renewcommand{\headrulewidth}{0pt}
+  \renewcommand{\footrulewidth}{0.4pt}
+}
+
+\titleformat{\section}{\Large}%
+            {\py@TitleColor\thesection}{0.5em}{\py@TitleColor}{\py@NormalColor}
+\titleformat{\subsection}{\large}%
+            {\py@TitleColor\thesubsection}{0.5em}{\py@TitleColor}{\py@NormalColor}
+\titleformat{\subsubsection}{}%
+            {\py@TitleColor\thesubsubsection}{0.5em}{\py@TitleColor}{\py@NormalColor}
+\titleformat{\paragraph}{\large}%
+            {\py@TitleColor}{0em}{\py@TitleColor}{\py@NormalColor}
+
+\ChNameVar{\raggedleft\normalsize}
+\ChNumVar{\raggedleft \bfseries\Large}
+\ChTitleVar{\raggedleft \rm\Huge}
+
+\renewcommand\thepart{\@Roman\c@part}
+\renewcommand\part{%
+   \pagestyle{empty}
+   \if@noskipsec \leavevmode \fi
+   \cleardoublepage
+   \vspace*{6cm}%
+   \@afterindentfalse
+   \secdef\@part\@spart}
+
+\def\@part[#1]#2{%
+    \ifnum \c@secnumdepth >\m@ne
+      \refstepcounter{part}%
+      \addcontentsline{toc}{part}{\thepart\hspace{1em}#1}%
+    \else
+      \addcontentsline{toc}{part}{#1}%
+    \fi
+    {\parindent \z@ %\center
+     \interlinepenalty \@M
+     \normalfont
+     \ifnum \c@secnumdepth >\m@ne
+       \rm\Large \partname~\thepart
+       \par\nobreak
+     \fi
+     \MakeUppercase{\rm\Huge #2}%
+     \markboth{}{}\par}%
+    \nobreak
+    \vskip 8ex
+    \@afterheading}
+\def\@spart#1{%
+    {\parindent \z@ %\center
+     \interlinepenalty \@M
+     \normalfont
+     \huge \bfseries #1\par}%
+     \nobreak
+     \vskip 3ex
+     \@afterheading}
+
+% use inconsolata font
+\usepackage{inconsolata}
+
+% fix single quotes, for inconsolata. (does not work)
+%%\usepackage{textcomp}
+%%\begingroup
+%%  \catcode`'=\active
+%%  \g@addto@macro\@noligs{\let'\textsinglequote}
+%%  \endgroup
+%%\endinput

docs/tutorial.rst

@@ -0,0 +1,415 @@
+.. _quickstart:
+
+==========
+Quickstart
+==========
+
+
+Eager to get started?
+This page gives a good introduction in how to get started with Tablib.
+This assumes you already have Tablib installed.
+If you do not, head over to the :ref:`Installation <install>` section.
+
+First, make sure that:
+
+* Tablib is :ref:`installed <install>`
+* Tablib is :ref:`up-to-date <updates>`
+
+
+Let's get started with some simple use cases and examples.
+
+
+
+------------------
+Creating a Dataset
+------------------
+
+
+A :class:`Dataset <tablib.Dataset>` is nothing more than what its name implies—a set of data.
+
+Creating your own instance of the :class:`tablib.Dataset` object is simple. ::
+
+    data = tablib.Dataset()
+
+You can now start filling this :class:`Dataset <tablib.Dataset>` object with data.
+
+.. admonition:: Example Context
+
+    From here on out, if you see ``data``, assume that it's a fresh
+    :class:`Dataset <tablib.Dataset>` object.
+
+
+
+-----------
+Adding Rows
+-----------
+
+
+Let's say you want to collect a simple list of names. ::
+
+    # collection of names
+    names = ['Kenneth Reitz', 'Bessie Monke']
+
+    for name in names:
+        # split name appropriately
+        fname, lname = name.split()
+
+        # add names to Dataset
+        data.append([fname, lname])
+
+You can get a nice, Pythonic view of the dataset at any time with :class:`Dataset.dict`::
+
+    >>> data.dict
+    [('Kenneth', 'Reitz'), ('Bessie', 'Monke')]
+
+
+
+--------------
+Adding Headers
+--------------
+
+
+It's time to enhance our :class:`Dataset` by giving our columns some titles.
+To do so, set :class:`Dataset.headers`. ::
+
+    data.headers = ['First Name', 'Last Name']
+
+Now our data looks a little different. ::
+
+    >>> data.dict
+    [{'Last Name': 'Reitz', 'First Name': 'Kenneth'},
+     {'Last Name': 'Monke', 'First Name': 'Bessie'}]
+
+
+
+
+--------------
+Adding Columns
+--------------
+
+
+Now that we have a basic :class:`Dataset` in place, let's add a column of **ages** to it. ::
+
+    data.append_col([22, 20], header='Age')
+
+Let's view the data now. ::
+
+    >>> data.dict
+    [{'Last Name': 'Reitz', 'First Name': 'Kenneth', 'Age': 22},
+     {'Last Name': 'Monke', 'First Name': 'Bessie', 'Age': 20}]
+
+It's that easy.
+
+
+--------------
+Importing Data
+--------------
+Creating a :class:`tablib.Dataset` object by importing a pre-existing file is simple. ::
+
+    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
+--------------
+
+Tablib's killer feature is the ability to export your :class:`Dataset` objects into a number of formats.
+
+**Comma-Separated Values** ::
+
+    >>> data.export('csv')
+    Last Name,First Name,Age
+    Reitz,Kenneth,22
+    Monke,Bessie,20
+
+**JavaScript Object Notation** ::
+
+    >>> data.export('json')
+    [{"Last Name": "Reitz", "First Name": "Kenneth", "Age": 22}, {"Last Name": "Monke", "First Name": "Bessie", "Age": 20}]
+
+
+**YAML Ain't Markup Language** ::
+
+    >>> data.export('yaml')
+    - {Age: 22, First Name: Kenneth, Last Name: Reitz}
+    - {Age: 20, First Name: Bessie, Last Name: Monke}
+
+
+**Microsoft Excel** ::
+
+    >>> data.export('xls')
+    <redacted binary data>
+
+
+**Pandas DataFrame** ::
+
+    >>> data.export('df')
+      First Name Last Name  Age
+    0    Kenneth     Reitz   22
+    1     Bessie     Monke   21
+
+
+------------------------
+Selecting Rows & Columns
+------------------------
+
+
+You can slice and dice your data, just like a standard Python list. ::
+
+    >>> data[0]
+    ('Kenneth', 'Reitz', 22)
+
+
+If we had a set of data consisting of thousands of rows,
+it could be useful to get a list of values in a column.
+To do so, we access the :class:`Dataset` as if it were a standard Python dictionary.  ::
+
+    >>> data['First Name']
+    ['Kenneth', 'Bessie']
+
+You can also access the column using its index. ::
+
+    >>> data.headers
+    ['Last Name', 'First Name', 'Age']
+    >>> data.get_col(1)
+    ['Kenneth', 'Bessie']
+
+Let's find the average age. ::
+
+    >>> ages = data['Age']
+    >>> float(sum(ages)) / len(ages)
+    21.0
+
+
+
+-----------------------
+Removing Rows & Columns
+-----------------------
+
+It's easier than you could imagine. Delete a column::
+
+    >>> del data['Col Name']
+
+Delete a range of rows::
+
+    >>> del data[0:12]
+
+
+==============
+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>`.
+
+And now for something completely different.
+
+
+.. _dyncols:
+
+---------------
+Dynamic Columns
+---------------
+
+.. versionadded:: 0.8.3
+
+Thanks to Josh Ourisman, Tablib now supports adding dynamic columns.
+A dynamic column is a single callable object (*e.g.* a function).
+
+Let's add a dynamic column to our :class:`Dataset` object.
+In this example, we have a function that generates a random grade for our students. ::
+
+    import random
+
+    def random_grade(row):
+        """Returns a random integer for entry."""
+        return (random.randint(60,100)/100.0)
+
+    data.append_col(random_grade, header='Grade')
+
+Let's have a look at our data. ::
+
+    >>> data.export('yaml')
+    - {Age: 22, First Name: Kenneth, Grade: 0.6, Last Name: Reitz}
+    - {Age: 20, First Name: Bessie, Grade: 0.75, Last Name: Monke}
+
+
+Let's remove that column.  ::
+
+    >>> del data['Grade']
+
+
+When you add a dynamic column, the first argument that is passed in to the given callable is the current data row.
+You can use this to perform calculations against your data row.
+
+For example, we can use the data available in the row to guess the gender of a student. ::
+
+    def guess_gender(row):
+        """Calculates gender of given student data row."""
+        m_names = ('Kenneth', 'Mike', 'Yuri')
+        f_names = ('Bessie', 'Samantha', 'Heather')
+
+        name = row[0]
+
+        if name in m_names:
+            return 'Male'
+        elif name in f_names:
+            return 'Female'
+        else:
+            return 'Unknown'
+
+Adding this function to our dataset as a dynamic column would result in: ::
+
+    >>> data.export('yaml')
+    - {Age: 22, First Name: Kenneth, Gender: Male, Last Name: Reitz}
+    - {Age: 20, First Name: Bessie, Gender: Female, Last Name: Monke}
+
+
+.. _tags:
+
+----------------------------
+Filtering Datasets with Tags
+----------------------------
+
+.. versionadded:: 0.9.0
+
+
+When constructing a :class:`Dataset` object,
+you can add tags to rows by specifying the ``tags`` parameter.
+This allows you to filter your :class:`Dataset` later.
+This can be useful to separate rows of data based on arbitrary criteria
+(*e.g.* origin) that you don't want to include in your :class:`Dataset`.
+
+Let's tag some students. ::
+
+    students = tablib.Dataset()
+
+    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 Female students. ::
+
+    >>> students.filter(['female']).yaml
+    - {first: Bessie, Last: Monke}
+
+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
+-------------------------------------------
+
+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()
+    with open('my_excel_file.xlsx', 'rb') as fh:
+        data.load(fh, 'xlsx')
+    print(data)
+
+Excel Workbook With Multiple Sheets
+------------------------------------
+
+When dealing with a large number of :class:`Datasets <Dataset>` in spreadsheet format,
+it's quite common to group multiple spreadsheets into a single Excel file, known as a Workbook.
+Tablib makes it extremely easy to build workbooks with the handy :class:`Databook` class.
+
+Let's say we have 3 different :class:`Datasets <Dataset>`.
+All we have to do is add them to a :class:`Databook` object... ::
+
+    book = tablib.Databook((data1, data2, data3))
+
+... and export to Excel just like :class:`Datasets <Dataset>`. ::
+
+    with open('students.xls', 'wb') as f:
+        f.write(book.export('xls'))
+
+The resulting ``students.xls`` file will contain a separate spreadsheet for each :class:`Dataset` object in the :class:`Databook`.
+
+.. admonition:: Binary Warning
+
+    Make sure to open the output file in binary mode.
+
+
+.. _separators:
+
+----------
+Separators
+----------
+
+.. versionadded:: 0.8.2
+
+When constructing a spreadsheet,
+it's often useful to create a blank row containing information on the upcoming data. So,
+
+::
+
+    daniel_tests = [
+        ('11/24/09', 'Math 101 Mid-term Exam', 56.),
+        ('05/24/10', 'Math 101 Final Exam', 62.)
+    ]
+
+    suzie_tests = [
+        ('11/24/09', 'Math 101 Mid-term Exam', 56.),
+        ('05/24/10', 'Math 101 Final Exam', 62.)
+    ]
+
+    # Create new dataset
+    tests = tablib.Dataset()
+    tests.headers = ['Date', 'Test Name', 'Grade']
+
+    # Daniel's Tests
+    tests.append_separator('Daniel\'s Scores')
+
+    for test_row in daniel_tests:
+       tests.append(test_row)
+
+    # Susie's Tests
+    tests.append_separator('Susie\'s Scores')
+
+    for test_row in suzie_tests:
+       tests.append(test_row)
+
+    # Write spreadsheet to disk
+    with open('grades.xls', 'wb') as f:
+        f.write(tests.export('xls'))
+
+The resulting **tests.xls** will have the following layout:
+
+
+    Daniel's Scores:
+        * '11/24/09', 'Math 101 Mid-term Exam', 56.
+        * '05/24/10', 'Math 101 Final Exam', 62.
+
+    Suzie's Scores:
+        * '11/24/09', 'Math 101 Mid-term Exam', 56.
+        * '05/24/10', 'Math 101 Final Exam', 62.
+
+
+
+.. admonition:: Format Support
+
+    At this time, only :class:`Excel <Dataset.xls>` output supports separators.
+
+----
+
+Now, go check out the :ref:`API Documentation <api>` or begin :ref:`Tablib Development <development>`.

fabfile.py

@@ -1,7 +0,0 @@
-from fabric.api import *
-
-
-def scrub():
-	""" Death to the bytecode! """
-	local("rm -fr dist build")
-	local("find . -name \"*.pyc\" -exec rm '{}' ';'")

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

reqs.txt

@@ -1,3 +0,0 @@
-xlwt
-simplejson
-PyYAML

setup.py

@@ -1,43 +1,52 @@
 #!/usr/bin/env python
-# -*- coding: utf-8 -*-
 
-import os
+from setuptools import find_packages, setup
-import sys
-
-from distutils.core import setup
-
-
-def publish():
-	"""Publish to PyPi"""
-	os.system("python setup.py sdist upload")
-
-if sys.argv[-1] == "publish":
-	publish()
-	sys.exit()
 
 setup(
-	name='tablib',
+    name='tablib',
-	version='0.8.1',
+    use_scm_version={
-	description='Format agnostic tabular data library (XLS, JSON, YAML, CSV)',
+        'write_to': 'src/tablib/_version.py',
-	long_description=open('README.rst').read() + '\n\n' +
+    },
-	                 open('HISTORY.rst').read(),
+    setup_requires=['setuptools_scm'],
-	author='Kenneth Reitz',
+    description='Format agnostic tabular data library (XLS, JSON, YAML, CSV)',
-	author_email='me@kennethreitz.com',
+    long_description=(
-	url='http://github.com/kennethreitz/tablib',
+        open('README.md').read() + '\n\n' + open('HISTORY.md').read()
-	packages=['tablib', 'tablib.formats'],
+    ),
-	install_requires=['xlwt', 'simplejson', 'PyYAML'],
+    long_description_content_type="text/markdown",
-	license='MIT',
+    author='Kenneth Reitz',
-	classifiers=(
+    author_email='me@kennethreitz.org',
-		'Development Status :: 4 - Beta',
+    maintainer='Jazzband',
-		'License :: OSI Approved :: MIT License',
+    maintainer_email='roadies@jazzband.co',
-		'Programming Language :: Python',
+    url='https://tablib.readthedocs.io',
-        # 'Programming Language :: Python :: 2.5',
+    project_urls={
-        'Programming Language :: Python :: 2.6',
+        "Documentation": "https://tablib.readthedocs.io",
-		'Programming Language :: Python :: 2.7',
+        "Source": "https://github.com/jazzband/tablib",
-	),
+    },
-    # entry_points={
+    packages=find_packages(where="src"),
-    #   'console_scripts': [
+    package_dir={"": "src"},
-    #       'tabbed = tablib.cli:start',
+    license='MIT',
-    #   ],
+    classifiers=[
-    # }
+        'Development Status :: 5 - Production/Stable',
+        'Intended Audience :: Developers',
+        'Natural Language :: English',
+        'License :: OSI Approved :: MIT License',
+        'Programming Language :: Python',
+        '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',
+    ],
+    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

@@ -0,0 +1,917 @@
+"""
+    tablib.core
+    ~~~~~~~~~~~
+
+    This module implements the central Tablib objects.
+
+    :copyright: (c) 2016 by Kenneth Reitz. 2019 Jazzband.
+    :license: MIT, see LICENSE for more details.
+"""
+
+from collections import OrderedDict
+from copy import copy
+from operator import itemgetter
+
+from tablib.exceptions import (
+    HeadersNeeded,
+    InvalidDatasetIndex,
+    InvalidDatasetType,
+    InvalidDimensions,
+    UnsupportedFormat,
+)
+from tablib.formats import registry
+from tablib.utils import normalize_input
+
+__title__ = 'tablib'
+__author__ = 'Kenneth Reitz'
+__license__ = 'MIT'
+__copyright__ = 'Copyright 2017 Kenneth Reitz. 2019 Jazzband.'
+__docformat__ = 'restructuredtext'
+
+
+class Row:
+    """Internal Row object. Mainly used for filtering."""
+
+    __slots__ = ['_row', 'tags']
+
+    def __init__(self, row=list(), tags=list()):
+        self._row = list(row)
+        self.tags = list(tags)
+
+    def __iter__(self):
+        return (col for col in self._row)
+
+    def __len__(self):
+        return len(self._row)
+
+    def __repr__(self):
+        return repr(self._row)
+
+    def __getitem__(self, i):
+        return self._row[i]
+
+    def __setitem__(self, i, value):
+        self._row[i] = value
+
+    def __delitem__(self, i):
+        del self._row[i]
+
+    def __getstate__(self):
+        return self._row, self.tags
+
+    def __setstate__(self, state):
+        self._row, self.tags = state
+
+    def rpush(self, value):
+        self.insert(len(self._row), value)
+
+    def lpush(self, value):
+        self.insert(0, value)
+
+    def append(self, value):
+        self.rpush(value)
+
+    def insert(self, index, value):
+        self._row.insert(index, value)
+
+    def __contains__(self, item):
+        return (item in self._row)
+
+    @property
+    def tuple(self):
+        """Tuple representation of :class:`Row`."""
+        return tuple(self._row)
+
+    @property
+    def list(self):
+        """List representation of :class:`Row`."""
+        return list(self._row)
+
+    def has_tag(self, tag):
+        """Returns true if current row contains tag."""
+
+        if tag is None:
+            return False
+        elif isinstance(tag, str):
+            return (tag in self.tags)
+        else:
+            return bool(len(set(tag) & set(self.tags)))
+
+
+class Dataset:
+    """The :class:`Dataset` object is the heart of Tablib. It provides all core
+    functionality.
+
+    Usually you create a :class:`Dataset` instance in your main module, and append
+    rows as you collect data. ::
+
+        data = tablib.Dataset()
+        data.headers = ('name', 'age')
+
+        for (name, age) in some_collector():
+            data.append((name, age))
+
+
+    Setting columns is similar. The column data length must equal the
+    current height of the data and headers must be set. ::
+
+        data = tablib.Dataset()
+        data.headers = ('first_name', 'last_name')
+
+        data.append(('John', 'Adams'))
+        data.append(('George', 'Washington'))
+
+        data.append_col((90, 67), header='age')
+
+
+    You can also set rows and headers upon instantiation. This is useful if
+    dealing with dozens or hundreds of :class:`Dataset` objects. ::
+
+        headers = ('first_name', 'last_name')
+        data = [('John', 'Adams'), ('George', 'Washington')]
+
+        data = tablib.Dataset(*data, headers=headers)
+
+    :param \\*args: (optional) list of rows to populate Dataset
+    :param headers: (optional) list strings for Dataset header row
+    :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>`.
+
+    """
+
+    def __init__(self, *args, **kwargs):
+        self._data = list(Row(arg) for arg in args)
+        self.__headers = None
+
+        # ('title', index) tuples
+        self._separators = []
+
+        # (column, callback) tuples
+        self._formatters = []
+
+        self.headers = kwargs.get('headers')
+
+        self.title = kwargs.get('title')
+
+    def __len__(self):
+        return self.height
+
+    def __getitem__(self, key):
+        if isinstance(key, str):
+            if key in self.headers:
+                pos = self.headers.index(key)  # get 'key' index from each data
+                return [row[pos] for row in self._data]
+            else:
+                raise KeyError
+        else:
+            _results = self._data[key]
+            if isinstance(_results, Row):
+                return _results.tuple
+            else:
+                return [result.tuple for result in _results]
+
+    def __setitem__(self, key, value):
+        self._validate(value)
+        self._data[key] = Row(value)
+
+    def __delitem__(self, key):
+        if isinstance(key, str):
+
+            if key in self.headers:
+
+                pos = self.headers.index(key)
+                del self.headers[pos]
+
+                for i, row in enumerate(self._data):
+
+                    del row[pos]
+                    self._data[i] = row
+            else:
+                raise KeyError
+        else:
+            del self._data[key]
+
+    def __repr__(self):
+        try:
+            return '<%s dataset>' % (self.title.lower())
+        except AttributeError:
+            return '<dataset object>'
+
+    def __str__(self):
+        result = []
+
+        # Add str representation of headers.
+        if self.__headers:
+            result.append([str(h) for h in self.__headers])
+
+        # 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)))
+
+        # delimiter between header and data
+        if self.__headers:
+            result.insert(1, ['-' * length for length in field_lens])
+
+        format_string = '|'.join('{%s:%s}' % item for item in enumerate(field_lens))
+
+        return '\n'.join(format_string.format(*row) for row in result)
+
+    # ---------
+    # Internals
+    # ---------
+
+    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."""
+        if row:
+            is_valid = (len(row) == self.width) if self.width else True
+        elif col:
+            if len(col) < 1:
+                is_valid = True
+            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)
+
+        if is_valid:
+            return True
+        else:
+            if not safety:
+                raise InvalidDimensions
+            return False
+
+    def _package(self, dicts=True, ordered=True):
+        """Packages Dataset into lists of dictionaries for transmission."""
+        # TODO: Dicts default to false?
+
+        _data = list(self._data)
+
+        if ordered:
+            dict_pack = OrderedDict
+        else:
+            dict_pack = dict
+
+        # Execute formatters
+        if self._formatters:
+            for row_i, row in enumerate(_data):
+                for col, callback in self._formatters:
+                    try:
+                        if col is None:
+                            for j, c in enumerate(row):
+                                _data[row_i][j] = callback(c)
+                        else:
+                            _data[row_i][col] = callback(row[col])
+                    except IndexError:
+                        raise InvalidDatasetIndex
+
+        if self.headers:
+            if dicts:
+                data = [dict_pack(list(zip(self.headers, data_row))) for data_row in _data]
+            else:
+                data = [list(self.headers)] + list(_data)
+        else:
+            data = [list(row) for row in _data]
+
+        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 :attr:`Dataset.width`.
+
+        """
+        return self.__headers
+
+    def _set_headers(self, collection):
+        """Validating headers setter."""
+        self._validate(collection)
+        if collection:
+            try:
+                self.__headers = list(collection)
+            except TypeError:
+                raise TypeError
+        else:
+            self.__headers = None
+
+    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,
+        a list of tuples (rows) will be returned instead.
+
+        A dataset object can also be imported by setting the `Dataset.dict` attribute: ::
+
+            data = tablib.Dataset()
+            data.dict = [{'age': 90, 'first_name': 'Kenneth', 'last_name': 'Reitz'}]
+
+        """
+        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 :attr:`Dataset.dict` attribute. ::
+
+            data = tablib.Dataset()
+            data.dict = [{'age': 90, 'first_name': 'Kenneth', 'last_name': 'Reitz'}]
+
+        """
+
+        if not len(pickle):
+            return
+
+        # if list of rows
+        if isinstance(pickle[0], list):
+            self.wipe()
+            for row in pickle:
+                self.append(Row(row))
+
+        # if list of objects
+        elif isinstance(pickle[0], dict):
+            self.wipe()
+            self.headers = list(pickle[0].keys())
+            for row in pickle:
+                self.append(Row(list(row.values())))
+        else:
+            raise UnsupportedFormat
+
+    dict = property(_get_dict, _set_dict)
+
+    def _clean_col(self, col):
+        """Prepares the given column for insert/append."""
+
+        col = list(col)
+
+        if self.headers:
+            header = [col.pop(0)]
+        else:
+            header = []
+
+        if len(col) == 1 and hasattr(col[0], '__call__'):
+
+            col = list(map(col[0], self._data))
+        col = tuple(header + col)
+
+        return col
+
+    @property
+    def height(self):
+        """The number of rows currently in the :class:`Dataset`.
+           Cannot be directly modified.
+        """
+        return len(self._data)
+
+    @property
+    def width(self):
+        """The number of columns currently in the :class:`Dataset`.
+           Cannot be directly modified.
+        """
+
+        try:
+            return len(self._data[0])
+        except IndexError:
+            try:
+                return len(self.headers)
+            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`.
+        """
+
+        stream = normalize_input(in_stream)
+        if not format:
+            format = detect_format(stream)
+
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'import_set'):
+            raise UnsupportedFormat(f'Format {format} cannot be imported.')
+
+        if not import_set:
+            raise UnsupportedFormat(f'Format {format} cannot be imported.')
+
+        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`.
+        """
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'export_set'):
+            raise UnsupportedFormat(f'Format {format} cannot be exported.')
+
+        return fmt.export_set(self, **kwargs)
+
+    # ----
+    # Rows
+    # ----
+
+    def insert(self, index, row, tags=list()):
+        """Inserts a row to the :class:`Dataset` at the given index.
+
+        Rows inserted must be the correct size (height or width).
+
+        The default behaviour is to insert the given row to the :class:`Dataset`
+        object at the given index.
+       """
+
+        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 :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 :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 :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
+        :method:`Dataset.append`
+        """
+
+        for row in rows:
+            self.append(row, tags)
+
+    def lpop(self):
+        """Removes and returns the first row of the :class:`Dataset`."""
+
+        cache = self[0]
+        del self[0]
+
+        return cache
+
+    def rpop(self):
+        """Removes and returns the last row of the :class:`Dataset`."""
+
+        cache = self[-1]
+        del self[-1]
+
+        return cache
+
+    def pop(self):
+        """Removes and returns the last row of the :class:`Dataset`."""
+
+        return self.rpop()
+
+    # -------
+    # Columns
+    # -------
+
+    def insert_col(self, index, col=None, header=None):
+        """Inserts a column to the :class:`Dataset` at the given index.
+
+        Columns inserted must be the correct height.
+
+        You can also insert a column of a single callable object, which will
+        add a new column with the return values of the callable each as an
+        item in the column. ::
+
+            data.append_col(col=random.randint)
+
+        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 :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 :method:`filter <Dataset.filter>` your
+           :class:`Dataset` later.
+
+        """
+
+        if col is None:
+            col = []
+
+        # Callable Columns...
+        if hasattr(col, '__call__'):
+            col = list(map(col, self._data))
+
+        col = self._clean_col(col)
+        self._validate(col=col)
+
+        if self.headers:
+            # pop the first item off, add to headers
+            if not header:
+                raise HeadersNeeded()
+
+            # corner case - if header is set without data
+            elif header and self.height == 0 and len(col):
+                raise InvalidDimensions
+
+            self.headers.insert(index, header)
+
+        if self.height and self.width:
+
+            for i, row in enumerate(self._data):
+
+                row.insert(index, col[i])
+                self._data[i] = row
+        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 :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 :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`."""
+
+        # change offsets if headers are or aren't defined
+        if not self.headers:
+            index = self.height if self.height else 0
+        else:
+            index = (self.height + 1) if self.height else 1
+
+        self.insert_separator(index, text)
+
+    def append_col(self, col, header=None):
+        """Adds a column to the :class:`Dataset`.
+        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 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.
+        """
+
+        if isinstance(col, str):
+            if col in self.headers:
+                col = self.headers.index(col)  # get 'key' index from each data
+            else:
+                raise KeyError
+
+        if not col > self.width:
+            self._formatters.append((col, handler))
+        else:
+            raise InvalidDatasetIndex
+
+        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>`.
+        """
+        _dset = copy(self)
+        _dset._data = [row for row in _dset._data if row.has_tag(tag)]
+
+        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
+        setting ``reverse`` to ``True``.
+
+        Returns a new :class:`Dataset` instance where columns have been
+        sorted.
+        """
+
+        if isinstance(col, str):
+
+            if not self.headers:
+                raise HeadersNeeded
+
+            _sorted = sorted(self.dict, key=itemgetter(col), reverse=reverse)
+            _dset = Dataset(headers=self.headers, title=self.title)
+
+            for item in _sorted:
+                row = [item[key] for key in self.headers]
+                _dset.append(row=row)
+
+        else:
+            if self.headers:
+                col = self.headers[col]
+
+            _sorted = sorted(self.dict, key=itemgetter(col), reverse=reverse)
+            _dset = Dataset(headers=self.headers, title=self.title)
+
+            for item in _sorted:
+                if self.headers:
+                    row = [item[key] for key in self.headers]
+                else:
+                    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
+        original instance becomes the new header row."""
+
+        # Don't transpose if there is no data
+        if not self:
+            return
+
+        _dset = Dataset()
+        # The first element of the headers stays in the headers,
+        # it is our "hinge" on which we rotate the data
+        new_headers = [self.headers[0]] + self[self.headers[0]]
+
+        _dset.headers = new_headers
+        for index, column in enumerate(self.headers):
+
+            if column == self.headers[0]:
+                # It's in the headers, so skip it
+                continue
+
+            # Adding the column name as now they're a regular column
+            # Use `get_col(index)` in case there are repeated values
+            row_data = [column] + self.get_col(index)
+            row_data = Row(row_data)
+            _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
+        ``Dataset`` instance."""
+
+        if not isinstance(other, Dataset):
+            return
+
+        if self.width != other.width:
+            raise InvalidDimensions
+
+        # Copy the source data
+        _dset = copy(self)
+
+        rows_to_stack = [row for row in _dset._data]
+        other_rows = [row for row in other._data]
+
+        rows_to_stack.extend(other_rows)
+        _dset._data = rows_to_stack
+
+        return _dset
+
+    def stack_cols(self, other):
+        """Stack two :class:`Dataset` instances together by
+        joining at the column level, and return a new
+        combined ``Dataset`` instance. If either ``Dataset``
+        has headers set, than the other must as well."""
+
+        if not isinstance(other, Dataset):
+            return
+
+        if self.headers or other.headers:
+            if not self.headers or not other.headers:
+                raise HeadersNeeded
+
+        if self.height != other.height:
+            raise InvalidDimensions
+
+        try:
+            new_headers = self.headers + other.headers
+        except TypeError:
+            new_headers = None
+
+        _dset = Dataset()
+
+        for column in self.headers:
+            _dset.append_col(col=self[column])
+
+        for column in other.headers:
+            _dset.append_col(col=other[column])
+
+        _dset.headers = new_headers
+
+        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.
+        """
+
+        # Don't return if no data
+        if not self:
+            return
+
+        if rows is None:
+            rows = list(range(self.height))
+
+        if cols is None:
+            cols = list(self.headers)
+
+        # 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
+        _dset.headers = list(cols)
+
+        _dset._data = []
+        for row_no, row in enumerate(self._data):
+            data_row = []
+            for key in _dset.headers:
+                if key in self.headers:
+                    pos = self.headers.index(key)
+                    data_row.append(row[pos])
+                else:
+                    raise KeyError
+
+            if row_no in rows:
+                _dset.append(row=Row(data_row))
+
+        return _dset
+
+
+class Databook:
+    """A book of :class:`Dataset` objects.
+    """
+
+    def __init__(self, sets=None):
+        self._datasets = sets or []
+
+    def __repr__(self):
+        try:
+            return '<%s databook>' % (self.title.lower())
+        except AttributeError:
+            return '<databook object>'
+
+    def wipe(self):
+        """Removes all :class:`Dataset` objects from the :class:`Databook`."""
+        self._datasets = []
+
+    def sheets(self):
+        return self._datasets
+
+    def add_sheet(self, dataset):
+        """Adds given :class:`Dataset` to the :class:`Databook`."""
+        if isinstance(dataset, Dataset):
+            self._datasets.append(dataset)
+        else:
+            raise InvalidDatasetType
+
+    def _package(self, ordered=True):
+        """Packages :class:`Databook` for delivery."""
+        collector = []
+
+        if ordered:
+            dict_pack = OrderedDict
+        else:
+            dict_pack = dict
+
+        for dset in self._datasets:
+            collector.append(dict_pack(
+                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, 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`.
+        """
+
+        stream = normalize_input(in_stream)
+        if not format:
+            format = detect_format(stream)
+
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'import_book'):
+            raise UnsupportedFormat(f'Format {format} cannot be loaded.')
+
+        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`.
+        """
+        fmt = registry.get_format(format)
+        if not hasattr(fmt, 'export_book'):
+            raise UnsupportedFormat(f'Format {format} cannot be exported.')
+
+        return fmt.export_book(self, **kwargs)
+
+
+def detect_format(stream):
+    """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):
+                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 (file-like object, string, or bytestring)."""
+
+    return Dataset().load(normalize_input(stream), format, **kwargs)
+
+
+def import_book(stream, format=None, **kwargs):
+    """Return dataset of given stream (file-like object, string, or bytestring)."""
+
+    return Databook().load(normalize_input(stream), format, **kwargs)
+
+
+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

@@ -0,0 +1,297 @@
+#! /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, record
+from .utils import INVALID_VALUE
+
+
+class Dbf:
+    """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, str):
+            # a filename
+            self.name = f
+            if new:
+                # new table (table file must be
+                # created or opened and truncated)
+                self.stream = open(f, "w+b")
+            else:
+                # table file must exist
+                self.stream = open(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):
+            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
+
+    # interface 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
+        names = [f.name for f in self.header.fields]
+        return names.index(name.upper())
+
+    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 :

src/tablib/packages/dbfpy/dbfnew.py

@@ -0,0 +1,183 @@
+#!/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 according 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:
+    """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 interface, 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:
+    """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 = open(filename, "wb")
+        _dbfh.write(_dbfStream)
+        _dbfStream.close()
+
+
+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('{}:\t {}'.format(fldName, rec[fldName]))
+        print()
+    dbft.close()
+
+# vim: set et sts=4 sw=4 :

src/tablib/packages/dbfpy/fields.py

@@ -0,0 +1,475 @@
+"""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 functools import total_ordering
+
+from . import utils
+
+# abstract definitions
+
+
+@total_ordering
+class DbfFieldDef:
+    """Abstract field definition.
+
+    Child classes must override ``type`` class attribute to provide datatype
+    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
+    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")
+
+    # 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 overridden in child classes
+    typeCode = None
+
+    # default value for the field. this field must be
+    # overridden 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 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:
+            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 __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)
+
+    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 = string[16]
+        return cls(utils.unzfill(string)[:11].decode('utf-8'), _length,
+            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.
+
+        """
+        _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 Exception:
+            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 overridden in child classes.
+        """
+        raise NotImplementedError
+
+# real classes
+
+
+class DbfCharacterFieldDef(DbfFieldDef):
+    """Definition of the character field."""
+
+    typeCode = "C"
+    defaultValue = b''
+
+    def decodeValue(self, value):
+        """Return string object.
+
+        Return value is a ``value`` argument with stripped right spaces.
+
+        """
+        return value.rstrip(b' ').decode('utf-8')
+
+    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(b' \0')
+        if b'.' 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(f"[{self.name}] Invalid logical value {value!r}")
+
+    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 currently 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[chr(typeCode)]
+
+# register generic types
+
+
+for (_name, _val) in list(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 :

src/tablib/packages/dbfpy/header.py

@@ -0,0 +1,270 @@
+"""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"]
+
+import datetime
+import io
+import struct
+import sys
+
+from . import fields
+from .utils import getDate
+
+
+class DbfHeader:
+    """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 = 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(io.StringIO(str(string)))
+    fromString = classmethod(fromString)
+
+    # @classmethod
+    def fromStream(cls, stream):
+        """Return header object from the stream."""
+        stream.seek(0)
+        first_32 = stream.read(32)
+        if type(first_32) != bytes:
+            _data = bytes(first_32, sys.getfilesystemencoding())
+        _data = first_32
+        (_cnt, _hdrLen, _recLen) = struct.unpack("<I2H", _data[4:12])
+        # reserved = _data[12:32]
+        _year = _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, _data[0],
+                   (_year, _data[2], _data[3]))
+        # append field definitions
+        # position 0 is for the deletion flag
+        _pos = 1
+        _data = stream.read(1)
+        while _data != b'\r':
+            _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())
+        fields = [_fld.toString() for _fld in self.fields]
+        stream.write(''.join(fields).encode(sys.getfilesystemencoding()))
+        stream.write(b'\x0D')   # cr at end of all header 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) + (b'\x00' * 20)
+        # TODO: figure out if bytes(utf-8) is correct here.
+
+    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, str):
+            _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 :

src/tablib/packages/dbfpy/record.py

@@ -0,0 +1,267 @@
+"""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"]
+
+import sys
+
+from . import utils
+
+
+class DbfRecord:
+    """DBF record.
+
+    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 preferred 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 initialization.
+
+        Arguments:
+            dbf:
+                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.
+            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 publicly.
+            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(bytes(self.toString(),
+                              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):
+            # this is the last record,
+            # we should write SUB (ASCII 26)
+            self.dbf.stream.write(b"\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."""
+#        for (_def, _dat) in zip(self.dbf.header.fields, self.fieldData):
+#
+
+        return "".join([" *"[self.deleted]] + [
+           _def.encodeValue(_dat)
+            for (_def, _dat) in zip(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 zip(self.dbf.fieldNames, self.fieldData)])
+
+    def __getitem__(self, key):
+        """Return value by field name or field index."""
+        if isinstance(key, 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):
+            # 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 :

src/tablib/packages/dbfpy/utils.py

@@ -0,0 +1,168 @@
+"""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) occurrence
+    and truncates string till that position.
+
+    """
+    try:
+        return str[:str.index(b'\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;
+
+    Additionally, 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, float)):
+        # date is a timestamp
+        return datetime.date.fromtimestamp(date)
+    if isinstance(date, str):
+        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;
+
+    Additionally, 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, float)):
+        # value is a timestamp
+        return datetime.datetime.fromtimestamp(value)
+    if isinstance(value, str):
+        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:
+
+    """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 __bool__(self):
+        return False
+
+    def __int__(self):
+        return 0
+    __long__ = __int__
+
+    def __float__(self):
+        return 0.0
+
+    def __str__(self):
+        return ""
+
+    def __repr__(self):
+        return "<INVALID>"
+
+
+# invalid value is a constant singleton
+INVALID_VALUE = _InvalidValue()
+
+# vim: set et sts=4 sw=4 :

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

@@ -1,8 +0,0 @@
-""" Tablib.
-"""
-
-from tablib.core import (
-	Databook, Dataset, InvalidDatasetType,
-	InvalidDimensions, UnsupportedFormat
-)
-

tablib/core.py

@@ -1,281 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - Core Library.
-"""
-
-from tablib.formats import FORMATS as formats
-
-
-__title__ = 'tablib'
-__version__ = '0.8.1'
-__build__ = 0x000801
-__author__ = 'Kenneth Reitz'
-__license__ = 'MIT'
-__copyright__ = 'Copyright 2010 Kenneth Reitz'
-
-
-class Dataset(object):
-	"""Epic Tabular-Dataset object. """
-
-	def __init__(self, *args, **kwargs):
-		self._data = list(args)
-		self.__headers = None
-
-		try:
-			self.headers = kwargs['headers']
-		except KeyError:
-			self.headers = None
-
-		try:
-			self.title = kwargs['title']
-		except KeyError:
-			self.title = None
-
-		self._register_formats()
-
-	def __len__(self):
-		return self.height
-
-
-	def __getitem__(self, key):
-		if isinstance(key, basestring):
-			if key in self.headers:
-				pos = self.headers.index(key) # get 'key' index from each data
-				return [row[pos] for row in self._data]
-			else:
-				raise KeyError
-		else:
-			return self._data[key]
-
-
-	def __setitem__(self, key, value):
-		self._validate(value)
-		self._data[key] = tuple(value)
-
-
-	def __delitem__(self, key):
-		del self._data[key]
-
-
-	def __repr__(self):
-		try:
-			return '<%s dataset>' % (self.title.lower())
-		except AttributeError:
-			return '<dataset object>'
-
-	
-	@classmethod
-	def _register_formats(cls):
-		"""Adds format properties."""
-		for fmt in formats:
-			try:
-				try:
-					setattr(cls, fmt.title, property(fmt.export_set, fmt.import_set))
-				except AttributeError:
-					setattr(cls, fmt.title, property(fmt.export_set))
-					
-			except AttributeError:
-				pass
-
-
-	def _validate(self, row=None, col=None, safety=False):
-		"""Assures size of every row in dataset is of proper proportions."""
-		if row:
-			is_valid = (len(row) == self.width) if self.width else True
-		elif col:
-			if self.headers:
-				is_valid = (len(col) - 1) == self.height
-			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))
-
-		if is_valid:
-			return True
-		else:
-			if not safety:
-				raise InvalidDimensions
-			return False
-
-
-	def _package(self, dicts=True):
-		"""Packages Dataset into lists of dictionaries for transmission."""
-
-		if self.headers:
-			if dicts:
-				data = [dict(zip(self.headers, data_row)) for data_row in self ._data]
-			else:
-				data = [list(self.headers)] + list(self._data)
-		else:
-			data = [list(row) for row in self._data]
-
-		return data
-
-	
-	@property
-	def height(self):
-		"""Returns the height of the Dataset."""
-		return len(self._data)
-
-
-	@property
-	def width(self):
-		"""Returns the width of the Dataset."""
-		try:
-			return len(self._data[0])
-		except IndexError:
-			try:
-				return len(self.headers)
-			except TypeError:
-				return 0
-
-
-	@property
-	def headers(self):
-		"""Headers property."""
-		return self.__headers
-
-
-	@headers.setter
-	def headers(self, collection):
-		"""Validating headers setter."""
-		self._validate(collection)
-		if collection:
-			try:
-				self.__headers = list(collection)
-			except TypeError:
-				raise TypeError
-		else:
-			self.__headers = None
-
-
-	@property
-	def dict(self):
-		"""Returns python dict of Dataset."""
-		return self._package()
-
-	
-	@dict.setter
-	def dict(self, pickle):
-		"""Returns python dict of Dataset."""
-		if not len(pickle):
-			return
-		if isinstance(pickle[0], list):
-			for row in pickle:
-				self.append(row)
-		elif isinstance(pickle[0], dict):
-			self.headers = pickle[0].keys()
-			for row in pickle:
-				self.append(row.values())
-		else:
-			raise UnsupportedFormat
-
-
-	def append(self, row=None, col=None):
-		"""Adds a row to the end of Dataset"""
-		if row:
-			self._validate(row)
-			self._data.append(tuple(row))
-		elif col:
-			self._validate(col=col)
-
-			if self.headers:
-				# pop the first item off, add to headers
-				self.headers.append(col[0])
-				col = col[1:]
-		
-			if self.height and self.width:
-
-				for i, row in enumerate(self._data):
-					_row = list(row)
-					_row.append(col[i])
-					self._data[i] = tuple(_row)
-			else:
-				self._data = [tuple([row]) for row in col]
-
-
-	def insert(self, i, row=None, col=None):
-		"""Inserts a row at given position in Dataset"""
-		if row:
-			self._validate(row)
-			self._data.insert(i, tuple(row))
-		elif col:
-			pass
-			
-	
-	def wipe(self):
-		"""Erases all data from Dataset."""
-		self._data = list()
-		self.__headers = None
-
-
-class Databook(object):
-	"""A book of Dataset objects.
-	   Currently, this exists only for XLS workbook support.
-	"""
-
-	def __init__(self, sets=[]):
-		self._datasets = sets
-		self._register_formats()
-
-
-	def __repr__(self):
-		try:
-			return '<%s databook>' % (self.title.lower())
-		except AttributeError:
-			return '<databook object>'
-
-	def wipe(self):
-		"""Wipe book clean."""
-		self._datasets = []
-		
-	@classmethod
-	def _register_formats(cls):
-		"""Adds format properties."""
-		for fmt in formats:
-			try:
-				try:
-					setattr(cls, fmt.title, property(fmt.export_book, fmt.import_book))
-				except AttributeError:
-					setattr(cls, fmt.title, property(fmt.export_book))
-					
-			except AttributeError:
-				pass
-
-
-	def add_sheet(self, dataset):
-		"""Adds given dataset."""
-		if type(dataset) is Dataset:
-			self._datasets.append(dataset)
-		else:
-			raise InvalidDatasetType
-
-
-	def _package(self):
-		"""Packages Databook for delivery."""
-		collector = []
-		for dset in self._datasets:
-			collector.append(dict(
-				title = dset.title,
-				data = dset.dict
-			))
-		return collector
-
-
-	@property
-	def size(self):
-		"""The number of the Datasets within DataBook."""
-		return len(self._datasets)
-
-
-
-class InvalidDatasetType(Exception):
-	"Only Datasets can be added to a DataBook"
-
-
-class InvalidDimensions(Exception):
-	"Invalid size"
-
-	
-class UnsupportedFormat(NotImplementedError):
-	"Format is not supported"

tablib/formats/__init__.py

@@ -1,11 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - formats
-"""
-
-import _csv as csv
-import _json as json
-import _xls as xls
-import _yaml as yaml
-
-FORMATS = (csv, json, xls, yaml)

tablib/formats/_csv.py

@@ -1,42 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - CSV Support.
-"""
-
-import cStringIO
-import csv
-import os
-
-import simplejson as json
-
-import tablib
-
-
-title = 'csv'
-extentions = ('csv',)
-
-
-
-def export_set(dataset):
-	"""Returns CSV representation of Dataset."""
-	stream = cStringIO.StringIO()
-	_csv = csv.writer(stream)
-
-	for row in dataset._package(dicts=False):
-		_csv.writerow(row)
-
-	return stream.getvalue()
-
-
-def import_set(dset, in_stream, headers=True):
-	"""Returns dataset from CSV stream."""
-
-	dset.wipe()
-
-	rows = csv.reader(in_stream.split())
-	for i, row in enumerate(rows):
-
-		if (i == 0) and (headers):
-			dset.headers = row
-		else:
-			dset.append(row)

tablib/formats/_json.py

@@ -1,38 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - JSON Support
-"""
-
-import simplejson as json
-import tablib.core
-
-title = 'json'
-extentions = ('json', 'jsn')
-
-
-def export_set(dataset):
-	"""Returns JSON representation of Dataset."""
-	return json.dumps(dataset.dict)
-
-
-def export_book(databook):
-	"""Returns JSON representation of Databook."""
-	return json.dumps(databook._package())
-	
-
-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.core.Dataset()
-		data.title = sheet['title']
-		data.dict = sheet['data']
-		dbook.add_sheet(data)

tablib/formats/_xls.py

@@ -1,45 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - XLS Support.
-"""
-
-import xlwt
-import cStringIO
-
-
-title = 'xls'
-extentions = ('xls',)
-
-
-def export_set(dataset):
-	"""Returns XLS representation of Dataset."""
-
-	wb = xlwt.Workbook(encoding='utf8')
-	ws = wb.add_sheet(dataset.title if dataset.title else 'Tabbed Dataset')
-
-	for i, row in enumerate(dataset._package(dicts=False)):
-		for j, col in enumerate(row):
-			ws.write(i, j, col)
-
-	stream = cStringIO.StringIO()
-	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))
-
-		#for row in self._package(dicts=False):
-		for i, row in enumerate(dset._package(dicts=False)):
-			for j, col in enumerate(row):
-				ws.write(i, j, col)
-
-
-	stream = cStringIO.StringIO()
-	wb.save(stream)
-	return stream.getvalue()

tablib/formats/_yaml.py

@@ -1,42 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - YAML Support.
-"""
-
-import yaml
-import tablib
-
-
-
-title = 'yaml'
-extentions = ('yaml', 'yml')
-
-
-
-def export_set(dataset):
-	"""Returns YAML representation of Dataset."""
-	return yaml.dump(dataset.dict)
-
-
-def export_book(databook):
-	"""Returns YAML representation of Databook."""
-	return yaml.dump(databook._package())
-
-
-def import_set(dset, in_stream):
-	"""Returns dataset from YAML stream."""
-
-	dset.wipe()
-	dset.dict = yaml.load(in_stream)
-
-
-def import_book(dbook, in_stream):
-	"""Returns databook from YAML stream."""
-
-	dbook.wipe()
-
-	for sheet in yaml.load(in_stream):
-		data = tablib.core.Dataset()
-		data.title = sheet['title']
-		data.dict = sheet['data']
-		dbook.add_sheet(data)

tablib/helpers.py

@@ -1,37 +0,0 @@
-# -*- coding: utf-8 -*-
-
-""" Tablib - General Helpers.
-"""
-
-import sys
-
-
-class Struct(object):
-	"""Your attributes are belong to us."""
-	
-	def __init__(self, **entries): 
-		self.__dict__.update(entries)
-		
-	def __getitem__(self, key):
-		return getattr(self, key, None)
-
-	def dictionary(self):
-		"""Returns dictionary representation of object."""
-		return self.__dict__
-
-	def items(self):
-		"""Returns items within object."""
-		return self.__dict__.items()
-
-	def keys(self):
-		"""Returns keys within object."""
-		return self.__dict__.keys()
-
-
-
-def piped():
-	"""Returns piped input via stdin, else False."""
-	with sys.stdin as stdin:
-		# TTY is only way to detect if stdin contains data
-		return stdin.read() if not stdin.isatty() else None
-

test_tablib.py

@@ -1,283 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-"""Tests for tablib."""
-
-import unittest
-
-import tablib
-
-
-class TablibTestCase(unittest.TestCase):
-	"""Tablib test cases."""
-
-	def setUp(self):
-		"""Create simple data set with headers."""
-
-		global data, book
-		data = tablib.Dataset()
-		book = tablib.Databook()
-
-		self.headers = ('first_name', 'last_name', 'gpa')
-		self.john = ('John', 'Adams', 90)
-		self.george = ('George', 'Washington', 67)
-		self.tom = ('Thomas', 'Jefferson', 50)
-
-		self.founders = tablib.Dataset(headers=self.headers)
-		self.founders.append(self.john)
-		self.founders.append(self.george)
-		self.founders.append(self.tom)
-
-
-	def tearDown(self):
-		"""Teardown."""
-		pass
-
-
-	def test_empty_append(self):
-		"""Verify append() correctly adds tuple with no headers."""
-		new_row = (1, 2, 3)
-		data.append(new_row)
-
-		# Verify width/data
-		self.assertTrue(data.width == len(new_row))
-		self.assertTrue(data[0] == new_row)
-
-
-	def test_empty_append_with_headers(self):
-		"""Verify append() correctly detects mismatch of number of
-		headers and data.
-		"""
-		data.headers = ['first', 'second']
-		new_row = (1, 2, 3, 4)
-
-		self.assertRaises(tablib.InvalidDimensions, data.append, new_row)
-
-
-	def test_add_column(self):
-		"""Verify adding column works with/without headers."""
-
-		data.append(['kenneth'])
-		data.append(['bessie'])
-
-		new_col = ['reitz', 'monke']
-
-		data.append(col=new_col)
-
-		self.assertEquals(data[0], ('kenneth', 'reitz'))
-		self.assertEquals(data.width, 2)
-
-		# With Headers
-		data.headers = ('fname', 'lname')
-		new_col = ['age', 21, 22]
-		data.append(col=new_col)
-
-		self.assertEquals(data[new_col[0]], new_col[1:])
-
-
-	def test_add_column_no_data_no_headers(self):
-		"""Verify adding new column with no headers."""
-
-		new_col = ('reitz', 'monke')
-
-		data.append(col=new_col)
-
-		self.assertEquals(data[0], tuple([new_col[0]]))
-		self.assertEquals(data.width, 1)
-		self.assertEquals(data.height, len(new_col))
-
-
-	def test_add_column_no_data_with_headers(self):
-		"""Verify adding new column with headers."""
-
-		data.headers = ('first', 'last')
-
-		new_col = ('age',)
-		data.append(col=new_col)
-
-		self.assertEquals(len(data.headers), 3)
-		self.assertEquals(data.width, 3)
-
-		new_col = ('foo', 'bar')
-
-		self.assertRaises(tablib.InvalidDimensions, data.append, col=new_col)
-
-
-	def test_header_slicing(self):
-		"""Verify slicing by headers."""
-
-		self.assertEqual(self.founders['first_name'],
-						[self.john[0], self.george[0], self.tom[0]])
-		self.assertEqual(self.founders['last_name'],
-						[self.john[1], self.george[1], self.tom[1]])
-		self.assertEqual(self.founders['gpa'],
-						[self.john[2], self.george[2], self.tom[2]])
-
-
-	def test_data_slicing(self):
-		"""Verify slicing by data."""
-
-		# Slice individual rows
-		self.assertEqual(self.founders[0], self.john)
-		self.assertEqual(self.founders[:1], [self.john])
-		self.assertEqual(self.founders[1:2], [self.george])
-		self.assertEqual(self.founders[-1], self.tom)
-		self.assertEqual(self.founders[3:], [])
-
-		# Slice multiple rows
-		self.assertEqual(self.founders[:], [self.john, self.george, self.tom])
-		self.assertEqual(self.founders[0:2], [self.john, self.george])
-		self.assertEqual(self.founders[1:3], [self.george, self.tom])
-		self.assertEqual(self.founders[2:], [self.tom])
-
-
-	def test_delete(self):
-		"""Verify deleting from dataset works."""
-
-		# Delete from front of object
-		del self.founders[0]
-		self.assertEqual(self.founders[:], [self.george, self.tom])
-
-		# Verify dimensions, width should NOT change
-		self.assertEqual(self.founders.height, 2)
-		self.assertEqual(self.founders.width, 3)
-
-		# Delete from back of object
-		del self.founders[1]
-		self.assertEqual(self.founders[:], [self.george])
-
-		# Verify dimensions, width should NOT change
-		self.assertEqual(self.founders.height, 1)
-		self.assertEqual(self.founders.width, 3)
-
-		# Delete from invalid index
-		self.assertRaises(IndexError, self.founders.__delitem__, 3)
-
-
-	def test_csv_export(self):
-		"""Verify exporting dataset object as CSV."""
-
-		# Build up the csv string with headers first, followed by each row
-		csv = ''
-		for col in self.headers:
-			csv += col + ','
-
-		csv = csv.strip(',') + '\r\n'
-
-		for founder in self.founders:
-			for col in founder:
-				csv += str(col) + ','
-			csv = csv.strip(',') + '\r\n'
-
-		self.assertEqual(csv, self.founders.csv)
-
-
-	def test_unicode_append(self):
-		"""Passes in a single unicode charecter and exports."""
-
-		new_row = ('å', 'é')
-		data.append(new_row)
-
-		data.json
-		data.yaml
-		data.csv
-		data.xls
-
- 
-	def test_book_export_no_exceptions(self):
-		"""Test that varoius exports don't error out."""
-
-		book = tablib.Databook()
-		book.add_sheet(data)
-
-		book.json
-		book.yaml
-		book.xls
-
-
-	def test_json_import_set(self):
-		"""Generate and import JSON set serialization."""
-		data.append(self.john)
-		data.append(self.george)
-		data.headers = self.headers
-
-		_json = data.json
-
-		data.json = _json
-
-		self.assertEqual(_json, data.json)
-
-
-	def test_json_import_book(self):
-		"""Generate and import JSON book serialization."""
-		data.append(self.john)
-		data.append(self.george)
-		data.headers = self.headers
-
-		book.add_sheet(data)
-		_json = book.json
-
-		book.json = _json
-
-		self.assertEqual(_json, book.json)
-
-
-	def test_yaml_import_set(self):
-		"""Generate and import YAML set serialization."""
-		data.append(self.john)
-		data.append(self.george)
-		data.headers = self.headers
-
-		_yaml = data.yaml
-
-		data.yaml = _yaml
-
-		self.assertEqual(_yaml, data.yaml)
-
-		
-	def test_yaml_import_book(self):
-		"""Generate and import YAML book serialization."""
-		data.append(self.john)
-		data.append(self.george)
-		data.headers = self.headers
-
-		book.add_sheet(data)
-		_yaml = book.yaml
-
-		book.yaml = _yaml
-
-		self.assertEqual(_yaml, book.yaml)
-		
-
-	def test_csv_import_set(self):
-		"""Generate and import CSV set serialization."""
-		data.append(self.john)
-		data.append(self.george)
-		data.headers = self.headers
-
-		_csv = data.csv
-
-		data.csv = _csv
-
-		self.assertEqual(_csv, data.csv)
-
-
-	def test_wipe(self):
-		"""Purge a dataset."""
-		
-		new_row = (1, 2, 3)
-		data.append(new_row)
-
-		# Verify width/data
-		self.assertTrue(data.width == len(new_row))
-		self.assertTrue(data[0] == new_row)
-		
-		data.wipe()
-		new_row = (1, 2, 3, 4)
-		data.append(new_row)
-		self.assertTrue(data.width == len(new_row))
-		self.assertTrue(data[0] == new_row)
-	
-		
-if __name__ == '__main__':
-	unittest.main()

tests/requirements.txt

@@ -0,0 +1,10 @@
+pytest
+pytest-cov
+MarkupPy
+odfpy
+openpyxl>=2.6.0
+pandas
+pyyaml
+tabulate
+xlrd
+xlwt

tests/test_tablib_dbfpy_packages_fields.py

@@ -0,0 +1,42 @@
+#!/usr/bin/env python
+"""Tests for tablib.packages.dbfpy."""
+
+import unittest
+
+from tablib.packages.dbfpy import fields
+
+
+class DbfFieldDefTestCompareCase(unittest.TestCase):
+    """dbfpy.fields.DbfFieldDef comparison test cases, via child classes."""
+
+    def setUp(self) -> None:
+        self.length = 10
+        self.a = fields.DbfCharacterFieldDef("abc", self.length)
+        self.z = fields.DbfCharacterFieldDef("xyz", self.length)
+        self.a2 = fields.DbfCharacterFieldDef("abc", self.length)
+
+    def test_compare__eq__(self):
+        # Act / Assert
+        self.assertEqual(self.a, self.a2)
+
+    def test_compare__ne__(self):
+        # Act / Assert
+        self.assertNotEqual(self.a, self.z)
+
+    def test_compare__lt__(self):
+        # Act / Assert
+        self.assertLess(self.a, self.z)
+
+    def test_compare__le__(self):
+        # Act / Assert
+        self.assertLessEqual(self.a, self.a2)
+        self.assertLessEqual(self.a, self.z)
+
+    def test_compare__gt__(self):
+        # Act / Assert
+        self.assertGreater(self.z, self.a)
+
+    def test_compare__ge__(self):
+        # Act / Assert
+        self.assertGreaterEqual(self.a2, self.a)
+        self.assertGreaterEqual(self.z, self.a)

tests/test_tablib_dbfpy_packages_utils.py

@@ -0,0 +1,170 @@
+#!/usr/bin/env python
+"""Tests for tablib.packages.dbfpy."""
+
+import datetime
+import unittest
+
+from tablib.packages.dbfpy import utils
+
+
+class UtilsUnzfillTestCase(unittest.TestCase):
+    """dbfpy.utils.unzfill test cases."""
+
+    def test_unzfill_with_nul(self):
+        # Arrange
+        text = b"abc\0xyz"
+
+        # Act
+        output = utils.unzfill(text)
+
+        # Assert
+        self.assertEqual(output, b"abc")
+
+    def test_unzfill_without_nul(self):
+        # Arrange
+        text = b"abcxyz"
+
+        # Act
+        output = utils.unzfill(text)
+
+        # Assert
+        self.assertEqual(output, b"abcxyz")
+
+
+class UtilsGetDateTestCase(unittest.TestCase):
+    """dbfpy.utils.getDate test cases."""
+
+    def test_getDate_none(self):
+        # Arrange
+        value = None
+
+        # Act
+        output = utils.getDate(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+
+    def test_getDate_datetime_date(self):
+        # Arrange
+        value = datetime.date(2019, 10, 19)
+
+        # Act
+        output = utils.getDate(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+        self.assertEqual(output, value)
+
+    def test_getDate_datetime_datetime(self):
+        # Arrange
+        value = datetime.datetime(2019, 10, 19, 12, 00, 00)
+
+        # Act
+        output = utils.getDate(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+        self.assertEqual(output, value)
+
+    def test_getDate_datetime_timestamp(self):
+        # Arrange
+        value = 1571515306
+
+        # Act
+        output = utils.getDate(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+        self.assertEqual(output, datetime.date(2019, 10, 19))
+
+    def test_getDate_datetime_string_yyyy_mm_dd(self):
+        # Arrange
+        value = "20191019"
+
+        # Act
+        output = utils.getDate(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+        self.assertEqual(output, datetime.date(2019, 10, 19))
+
+    def test_getDate_datetime_string_yymmdd(self):
+        # Arrange
+        value = "191019"
+
+        # Act
+        output = utils.getDate(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+        self.assertEqual(output, datetime.date(2019, 10, 19))
+
+
+class UtilsGetDateTimeTestCase(unittest.TestCase):
+    """dbfpy.utils.getDateTime test cases."""
+
+    def test_getDateTime_none(self):
+        # Arrange
+        value = None
+
+        # Act
+        output = utils.getDateTime(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.datetime)
+
+    def test_getDateTime_datetime_datetime(self):
+        # Arrange
+        value = datetime.datetime(2019, 10, 19, 12, 00, 00)
+
+        # Act
+        output = utils.getDateTime(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+        self.assertEqual(output, value)
+
+    def test_getDateTime_datetime_date(self):
+        # Arrange
+        value = datetime.date(2019, 10, 19)
+
+        # Act
+        output = utils.getDateTime(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.date)
+        self.assertEqual(output, datetime.datetime(2019, 10, 19, 00, 00))
+
+    def test_getDateTime_datetime_timestamp(self):
+        # Arrange
+        value = 1571515306
+
+        # Act
+        output = utils.getDateTime(value)
+
+        # Assert
+        self.assertIsInstance(output, datetime.datetime)
+
+    def test_getDateTime_datetime_string(self):
+        # Arrange
+        value = "20191019"
+
+        # Act / Assert
+        with self.assertRaises(NotImplementedError):
+            output = utils.getDateTime(value)
+
+
+class InvalidValueTestCase(unittest.TestCase):
+    """dbfpy.utils._InvalidValue test cases."""
+
+    def test_sanity(self):
+        # Arrange
+        INVALID_VALUE = utils.INVALID_VALUE
+
+        # Act / Assert
+        self.assertEqual(INVALID_VALUE, INVALID_VALUE)
+        self.assertNotEqual(INVALID_VALUE, 123)
+        self.assertEqual(int(INVALID_VALUE), 0)
+        self.assertEqual(float(INVALID_VALUE), 0.0)
+        self.assertEqual(str(INVALID_VALUE), "")
+        self.assertEqual(repr(INVALID_VALUE), "<INVALID>")

tox.ini

@@ -0,0 +1,39 @@
+[tox]
+usedevelop = true
+minversion = 2.4
+envlist =
+    docs
+    lint
+    py{36,37,38,39}
+
+[testenv]
+deps =
+    -rtests/requirements.txt
+extras = pandas
+passenv =
+    FORCE_COLOR
+commands =
+    pytest {posargs:tests}
+
+[testenv:docs]
+deps =
+    sphinx
+commands =
+    sphinx-build -b html -d {envtmpdir}/doctrees docs {envtmpdir}/html
+
+[testenv:lint]
+deps =
+    flake8
+    # flake8-black
+    pre-commit
+    twine
+commands =
+    # flake8 src/tablib tests/
+    pre-commit run --all-files
+    python setup.py sdist
+    twine check dist/*
+skip_install = true
+
+[flake8]
+exclude =
+    .tox