├── .gitignore
├── .travis.yml
├── AUTHORS.rst
├── CONTRIBUTING.rst
├── HISTORY.rst
├── LICENSE
├── MANIFEST.in
├── Makefile
├── README.rst
├── docs
    ├── Makefile
    ├── _shared_static
    │   ├── custom.css
    │   └── logo.jpg
    ├── _themes
    │   └── alabaster
    │   │   ├── __init__.py
    │   │   ├── _version.py
    │   │   ├── about.html
    │   │   ├── donate.html
    │   │   ├── layout.html
    │   │   ├── navigation.html
    │   │   ├── relations.html
    │   │   ├── static
    │   │       ├── alabaster.css_t
    │   │       └── custom.css
    │   │   ├── support.py
    │   │   └── theme.conf
    ├── authors.rst
    ├── conf.py
    ├── contributing.rst
    ├── history.rst
    ├── index.rst
    ├── installation.rst
    ├── make.bat
    ├── master.zip
    ├── modules.rst
    ├── quickstart.rst
    ├── readme.rst
    ├── usage.rst
    └── xmldataset.rst
├── examples
    ├── example1.py
    ├── example10.py
    ├── example2.py
    ├── example3.py
    ├── example4.py
    ├── example5.py
    ├── example6.py
    ├── example7.py
    ├── example8.py
    └── example9.py
├── requirements.txt
├── setup.cfg
├── setup.py
├── tests
    ├── __init__.py
    └── test_xmldataset.py
├── tox.ini
└── xmldataset
    ├── __init__.py
    └── __main__.py


/.gitignore:
--------------------------------------------------------------------------------
 1 | *.py[cod]
 2 | 
 3 | # C extensions
 4 | *.so
 5 | 
 6 | # Packages
 7 | *.egg
 8 | *.egg-info
 9 | dist
10 | build
11 | eggs
12 | parts
13 | bin
14 | var
15 | sdist
16 | develop-eggs
17 | .installed.cfg
18 | lib
19 | lib64
20 | 
21 | # Installer logs
22 | pip-log.txt
23 | 
24 | # Unit test / coverage reports
25 | .coverage
26 | .tox
27 | nosetests.xml
28 | htmlcov
29 | 
30 | # Translations
31 | *.mo
32 | 
33 | # Mr Developer
34 | .mr.developer.cfg
35 | .project
36 | .pydevproject
37 | 
38 | # Complexity
39 | output/*.html
40 | output/*/index.html
41 | 
42 | # Sphinx
43 | docs/_build


--------------------------------------------------------------------------------
/.travis.yml:
--------------------------------------------------------------------------------
 1 | # Config file for automatic testing at travis-ci.org
 2 | 
 3 | language: python
 4 | 
 5 | python:
 6 |   - "nightly"
 7 |   - "3.8"
 8 |   - "3.7"
 9 |   - "3.6"
10 |   - "3.5"
11 |   - "3.4"
12 |   - "2.7"
13 |   - "pypy"
14 | 
15 | # command to install dependencies, e.g. pip install -r requirements.txt --use-mirrors
16 | install: 
17 |     - if [[ $TRAVIS_PYTHON_VERSION == '2.6' ]]; then pip install unittest2; fi
18 |     - pip install -r requirements.txt
19 | 
20 | # command to run tests, e.g. python setup.py test
21 | script: python setup.py test
22 | 


--------------------------------------------------------------------------------
/AUTHORS.rst:
--------------------------------------------------------------------------------
1 | =======
2 | Credits
3 | =======
4 | 
5 | Development Lead
6 | ----------------
7 | 
8 | * James Spurin <james@spurin.com>
9 | 


--------------------------------------------------------------------------------
/CONTRIBUTING.rst:
--------------------------------------------------------------------------------
  1 | ============
  2 | Contributing
  3 | ============
  4 | 
  5 | Contributions are welcome, and they are greatly appreciated! Every
  6 | little bit helps, and credit will always be given. 
  7 | 
  8 | You can contribute in many ways:
  9 | 
 10 | Types of Contributions
 11 | ----------------------
 12 | 
 13 | Report Bugs
 14 | ~~~~~~~~~~~
 15 | 
 16 | Report bugs at https://github.com/spurin/xmldataset/issues.
 17 | 
 18 | If you are reporting a bug, please include:
 19 | 
 20 | * Your operating system name and version.
 21 | * Any details about your local setup that might be helpful in troubleshooting.
 22 | * Detailed steps to reproduce the bug.
 23 | 
 24 | Fix Bugs
 25 | ~~~~~~~~
 26 | 
 27 | Look through the GitHub issues for bugs. Anything tagged with "bug"
 28 | is open to whoever wants to implement it.
 29 | 
 30 | Implement Features
 31 | ~~~~~~~~~~~~~~~~~~
 32 | 
 33 | Look through the GitHub issues for features. Anything tagged with "feature"
 34 | is open to whoever wants to implement it.
 35 | 
 36 | Write Documentation
 37 | ~~~~~~~~~~~~~~~~~~~
 38 | 
 39 | XML Dataset could always use more documentation, whether as part of the 
 40 | official XML Dataset docs, in docstrings, or even on the web in blog posts,
 41 | articles, and such.
 42 | 
 43 | Submit Feedback
 44 | ~~~~~~~~~~~~~~~
 45 | 
 46 | The best way to send feedback is to file an issue at https://github.com/spurin/xmldataset/issues.
 47 | 
 48 | If you are proposing a feature:
 49 | 
 50 | * Explain in detail how it would work.
 51 | * Keep the scope as narrow as possible, to make it easier to implement.
 52 | * Remember that this is a volunteer-driven project, and that contributions
 53 |   are welcome :)
 54 | 
 55 | Get Started!
 56 | ------------
 57 | 
 58 | Ready to contribute? Here's how to set up `xmldataset` for local development.
 59 | 
 60 | 1. Fork the `xmldataset` repo on GitHub.
 61 | 2. Clone your fork locally::
 62 | 
 63 |     $ git clone git@github.com:your_name_here/xmldataset.git
 64 | 
 65 | 3. Install your local copy into a virtualenv. Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development::
 66 | 
 67 |     $ mkvirtualenv xmldataset
 68 |     $ cd xmldataset/
 69 |     $ python setup.py develop
 70 | 
 71 | 4. Create a branch for local development::
 72 | 
 73 |     $ git checkout -b name-of-your-bugfix-or-feature
 74 |    
 75 |    Now you can make your changes locally.
 76 | 
 77 | 5. When you're done making changes, check that your changes pass flake8 and the tests, including testing other Python versions with tox::
 78 | 
 79 |     $ flake8 xmldataset tests
 80 |     $ python setup.py test
 81 |     $ tox
 82 | 
 83 |    To get flake8 and tox, just pip install them into your virtualenv. 
 84 | 
 85 | 6. Commit your changes and push your branch to GitHub::
 86 | 
 87 |     $ git add .
 88 |     $ git commit -m "Your detailed description of your changes."
 89 |     $ git push origin name-of-your-bugfix-or-feature
 90 | 
 91 | 7. Submit a pull request through the GitHub website.
 92 | 
 93 | Pull Request Guidelines
 94 | -----------------------
 95 | 
 96 | Before you submit a pull request, check that it meets these guidelines:
 97 | 
 98 | 1. The pull request should include tests.
 99 | 2. If the pull request adds functionality, the docs should be updated. Put
100 |    your new functionality into a function with a docstring, and add the
101 |    feature to the list in README.rst.
102 | 3. The pull request should work for Python 2.6, 2.7, and 3.3, and for PyPy. Check 
103 |    https://travis-ci.org/spurin/xmldataset/pull_requests
104 |    and make sure that the tests pass for all supported Python versions.
105 | 
106 | Tips
107 | ----
108 | 
109 | To run a subset of tests::
110 | 
111 | 	$ python -m unittest tests.test_xmldataset
112 | 


--------------------------------------------------------------------------------
/HISTORY.rst:
--------------------------------------------------------------------------------
 1 | .. :changelog:
 2 | 
 3 | History
 4 | -------
 5 | 
 6 | 0.1.0 (2014-08-17)
 7 | ++++++++++++++++++
 8 | 
 9 | * First release on PyPI.
10 | 
11 | 0.1.1 (2014-08-17)
12 | ++++++++++++++++++
13 | 
14 | * Minor updates to supporting documents
15 | 
16 | 0.1.2 (2014-08-17)
17 | ++++++++++++++++++
18 | 
19 | * Minor updates to supporting documents
20 | 
21 | 0.1.3 (2014-08-17)
22 | ++++++++++++++++++
23 | 
24 | * Minor updates to supporting documents
25 | 
26 | 0.1.4 (2014-08-27)
27 | ++++++++++++++++++
28 | 
29 | * Added default option to profile markup, allows a default value to be
30 |   be set in the event that the context is missing from the XML, usage
31 |   default:           Results in a string of '' for missing entries
32 |   default:Missing    Results in a string of 'Missing' for missing entries
33 | 
34 | 0.1.5 (2014-09-08)
35 | ++++++++++++++++++
36 | 
37 | * Added an option of __DATASET_PROCESSING__ which allows datasets
38 |   to be processed against a function, usage
39 |   __DATASET_PROCESSING__ = dataset:process
40 | 
41 |   The process needs to be parsed as an object parameter as per the
42 |   existing dataset process functionality
43 | 
44 | 0.1.6 (2014-09-24)
45 | ++++++++++++++++++
46 | 
47 | * Updated the default option so that it works with nested defaults
48 | 
49 |   If there is a level in the XML structure that is not
50 |   traversed but contains defaults, we may still want these
51 |   default values to be reflected in the dataset.  The parser
52 |   now understands the optional syntax -
53 | 
54 |   __ALWAYS_FOLLOW__ entry
55 | 
56 |   To allow the parser to follow the profile entry and set defaults
57 | 
58 | 0.1.7 (2015-06-02)
59 | ++++++++++++++++++
60 | 
61 | * Added an option for parse_using_profile of global_values
62 | 
63 |   When supplied as a dictionary, all entries in the dictionary
64 |   are merged into new datasets.  For example -
65 |   
66 |   parse_using_profile(xml, profile, global_values = { 'location' : 'Chorleywood'})
67 | 
68 | 1.0.0 (2016-06-18)
69 | ++++++++++++++++++
70 | 
71 | * First official release, revamped documentation
72 | 
73 | 1.0.1 (2016-10-14)
74 | ++++++++++++++++++
75 | 
76 | * Tidied up core for main execution example (use python -m xmldataset to use the inbuilt example)
77 | * Added use of pandas to quick start
78 | * Added 3.4 to tox.ini, updated .travis.yml to include 3.4 and current
79 | 
80 | 1.0.2 (2020-05-30)
81 | ++++++++++++++++++
82 | 
83 | * Added 3.7, 3.8 to tox.ini, updated .travis.yml to include 3.7 and 3.8, removed 2.6 and 3.3 (no longer supported)
84 | * Implemented fix for duplicate results, thanks @davidmarcano
85 | * Code passed through black for standardisation
86 | 
87 | 1.0.3 (2020-05-30)
88 | ++++++++++++++++++
89 | 
90 | * Documentation, awesome badge
91 | 
92 | 1.0.4 (2020-05-30)
93 | ++++++++++++++++++
94 | 
95 | * History update
96 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | Copyright (c) 2015, James Spurin
 2 | All rights reserved.
 3 | 
 4 | Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
 5 | 
 6 | * Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
 7 | 
 8 | * Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
 9 | 
10 | * Neither the name of XML Dataset nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
11 | 
12 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
13 | 


--------------------------------------------------------------------------------
/MANIFEST.in:
--------------------------------------------------------------------------------
1 | include AUTHORS.rst
2 | include CONTRIBUTING.rst
3 | include HISTORY.rst
4 | include LICENSE
5 | include README.rst


--------------------------------------------------------------------------------
/Makefile:
--------------------------------------------------------------------------------
 1 | .PHONY: clean-pyc clean-build docs clean
 2 | 
 3 | help:
 4 | 	@echo "clean-build - remove build artifacts"
 5 | 	@echo "clean-pyc - remove Python file artifacts"
 6 | 	@echo "lint - check style with flake8"
 7 | 	@echo "test - run tests quickly with the default Python"
 8 | 	@echo "test-all - run tests on every Python version with tox"
 9 | 	@echo "coverage - check code coverage quickly with the default Python"
10 | 	@echo "docs - generate Sphinx HTML documentation, including API docs"
11 | 	@echo "release - package and upload a release"
12 | 	@echo "sdist - package"
13 | 
14 | clean: clean-build clean-pyc
15 | 	rm -fr htmlcov/
16 | 
17 | clean-build:
18 | 	rm -fr build/
19 | 	rm -fr dist/
20 | 	rm -fr *.egg-info
21 | 
22 | clean-pyc:
23 | 	find . -name '*.pyc' -exec rm -f {} +
24 | 	find . -name '*.pyo' -exec rm -f {} +
25 | 	find . -name '*~' -exec rm -f {} +
26 | 
27 | lint:
28 | 	flake8 xmldataset tests
29 | 
30 | test:
31 | 	python setup.py test
32 | 
33 | test-all:
34 | 	tox
35 | 
36 | coverage:
37 | 	coverage run --source xmldataset setup.py test
38 | 	coverage report -m
39 | 	coverage html
40 | 	open htmlcov/index.html
41 | 
42 | docs:
43 | 	rm -f docs/xmldataset.rst
44 | 	rm -f docs/modules.rst
45 | 	sphinx-apidoc -o docs/ xmldataset
46 | 	$(MAKE) -C docs clean
47 | 	$(MAKE) -C docs html
48 | 	open docs/_build/html/index.html
49 | 
50 | release: clean
51 | 	python setup.py sdist upload
52 | 	python setup.py bdist_wheel upload
53 | 
54 | dist: clean
55 | 	python setup.py sdist
56 | 	python setup.py bdist_wheel
57 | 	ls -l dist
58 | 


--------------------------------------------------------------------------------
/README.rst:
--------------------------------------------------------------------------------
 1 | ==================================
 2 | xmldataset: simple xml parsing 🗃️
 3 | ==================================
 4 | 
 5 | .. image:: https://camo.githubusercontent.com/13c4e50d88df7178ae1882a203ed57b641674f94/68747470733a2f2f63646e2e7261776769742e636f6d2f73696e647265736f726875732f617765736f6d652f643733303566333864323966656437386661383536353265336136336531353464643865383832392f6d656469612f62616467652e737667
 6 |     :target: https://github.com/sindresorhus/awesome
 7 | 
 8 | .. image:: https://travis-ci.org/spurin/xmldataset.png?branch=master
 9 |     :target: https://travis-ci.org/spurin/xmldataset
10 | 
11 | .. image:: https://badge.fury.io/py/xmldataset.png
12 |     :target: http://badge.fury.io/py/xmldataset
13 | 
14 | XML Dataset: simple xml parsing
15 | 
16 | .. image:: https://xmldataset.readthedocs.io/en/latest/_static/logo.jpg
17 | 
18 | * Documentation: https://xmldataset.readthedocs.io
19 | 
20 | A Python library that simplifies the extraction of datasets from XML content.
21 | 
22 | XML is a simple markup format. Whilst simple, extracting data of interest is often more complicated than it needs to be.
23 | 
24 | xmldataset addresses this through an easy to use plaintext declaration that follows the structure of the XML document. The declaration is indented, matching the XML structure, the data we are interested in is tagged against a dataset.
25 | 
26 | Features
27 | 
28 | * Handles missing data from the XML structure, if it’s missing in the XML it is not populated in the dataset
29 | * Handles both XML Elements and Attributes using the plaintext collection schema (attributes are depicted as a sublevel of an element)
30 | * Easy to rename XML attributes/elements during processing to meet your requirements
31 | * Inline manipulation of XML content through the process mechanism
32 | * Dispatch mechanism, allows datasets to be dispatched for every N instance to allow asynchronous processing
33 | 


--------------------------------------------------------------------------------
/docs/Makefile:
--------------------------------------------------------------------------------
  1 | # Makefile for Sphinx documentation
  2 | #
  3 | 
  4 | # You can set these variables from the command line.
  5 | SPHINXOPTS    =
  6 | SPHINXBUILD   = sphinx-build
  7 | PAPER         =
  8 | BUILDDIR      = _build
  9 | 
 10 | # User-friendly check for sphinx-build
 11 | ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1)
 12 | $(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/)
 13 | endif
 14 | 
 15 | # Internal variables.
 16 | PAPEROPT_a4     = -D latex_paper_size=a4
 17 | PAPEROPT_letter = -D latex_paper_size=letter
 18 | ALLSPHINXOPTS   = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
 19 | # the i18n builder cannot share the environment and doctrees with the others
 20 | I18NSPHINXOPTS  = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
 21 | 
 22 | .PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext
 23 | 
 24 | help:
 25 | 	@echo "Please use \`make <target>' where <target> is one of"
 26 | 	@echo "  html       to make standalone HTML files"
 27 | 	@echo "  dirhtml    to make HTML files named index.html in directories"
 28 | 	@echo "  singlehtml to make a single large HTML file"
 29 | 	@echo "  pickle     to make pickle files"
 30 | 	@echo "  json       to make JSON files"
 31 | 	@echo "  htmlhelp   to make HTML files and a HTML help project"
 32 | 	@echo "  qthelp     to make HTML files and a qthelp project"
 33 | 	@echo "  devhelp    to make HTML files and a Devhelp project"
 34 | 	@echo "  epub       to make an epub"
 35 | 	@echo "  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
 36 | 	@echo "  latexpdf   to make LaTeX files and run them through pdflatex"
 37 | 	@echo "  latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
 38 | 	@echo "  text       to make text files"
 39 | 	@echo "  man        to make manual pages"
 40 | 	@echo "  texinfo    to make Texinfo files"
 41 | 	@echo "  info       to make Texinfo files and run them through makeinfo"
 42 | 	@echo "  gettext    to make PO message catalogs"
 43 | 	@echo "  changes    to make an overview of all changed/added/deprecated items"
 44 | 	@echo "  xml        to make Docutils-native XML files"
 45 | 	@echo "  pseudoxml  to make pseudoxml-XML files for display purposes"
 46 | 	@echo "  linkcheck  to check all external links for integrity"
 47 | 	@echo "  doctest    to run all doctests embedded in the documentation (if enabled)"
 48 | 
 49 | clean:
 50 | 	rm -rf $(BUILDDIR)/*
 51 | 
 52 | html:
 53 | 	$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
 54 | 	@echo
 55 | 	@echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
 56 | 
 57 | dirhtml:
 58 | 	$(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
 59 | 	@echo
 60 | 	@echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
 61 | 
 62 | singlehtml:
 63 | 	$(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
 64 | 	@echo
 65 | 	@echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
 66 | 
 67 | pickle:
 68 | 	$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
 69 | 	@echo
 70 | 	@echo "Build finished; now you can process the pickle files."
 71 | 
 72 | json:
 73 | 	$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
 74 | 	@echo
 75 | 	@echo "Build finished; now you can process the JSON files."
 76 | 
 77 | htmlhelp:
 78 | 	$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
 79 | 	@echo
 80 | 	@echo "Build finished; now you can run HTML Help Workshop with the" \
 81 | 	      ".hhp project file in $(BUILDDIR)/htmlhelp."
 82 | 
 83 | qthelp:
 84 | 	$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
 85 | 	@echo
 86 | 	@echo "Build finished; now you can run "qcollectiongenerator" with the" \
 87 | 	      ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
 88 | 	@echo "# qcollectiongenerator $(BUILDDIR)/qthelp/complexity.qhcp"
 89 | 	@echo "To view the help file:"
 90 | 	@echo "# assistant -collectionFile $(BUILDDIR)/qthelp/complexity.qhc"
 91 | 
 92 | devhelp:
 93 | 	$(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
 94 | 	@echo
 95 | 	@echo "Build finished."
 96 | 	@echo "To view the help file:"
 97 | 	@echo "# mkdir -p $$HOME/.local/share/devhelp/complexity"
 98 | 	@echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/complexity"
 99 | 	@echo "# devhelp"
100 | 
101 | epub:
102 | 	$(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
103 | 	@echo
104 | 	@echo "Build finished. The epub file is in $(BUILDDIR)/epub."
105 | 
106 | latex:
107 | 	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
108 | 	@echo
109 | 	@echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
110 | 	@echo "Run \`make' in that directory to run these through (pdf)latex" \
111 | 	      "(use \`make latexpdf' here to do that automatically)."
112 | 
113 | latexpdf:
114 | 	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
115 | 	@echo "Running LaTeX files through pdflatex..."
116 | 	$(MAKE) -C $(BUILDDIR)/latex all-pdf
117 | 	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
118 | 
119 | latexpdfja:
120 | 	$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
121 | 	@echo "Running LaTeX files through platex and dvipdfmx..."
122 | 	$(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
123 | 	@echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
124 | 
125 | text:
126 | 	$(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
127 | 	@echo
128 | 	@echo "Build finished. The text files are in $(BUILDDIR)/text."
129 | 
130 | man:
131 | 	$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
132 | 	@echo
133 | 	@echo "Build finished. The manual pages are in $(BUILDDIR)/man."
134 | 
135 | texinfo:
136 | 	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
137 | 	@echo
138 | 	@echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
139 | 	@echo "Run \`make' in that directory to run these through makeinfo" \
140 | 	      "(use \`make info' here to do that automatically)."
141 | 
142 | info:
143 | 	$(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
144 | 	@echo "Running Texinfo files through makeinfo..."
145 | 	make -C $(BUILDDIR)/texinfo info
146 | 	@echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
147 | 
148 | gettext:
149 | 	$(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
150 | 	@echo
151 | 	@echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
152 | 
153 | changes:
154 | 	$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
155 | 	@echo
156 | 	@echo "The overview file is in $(BUILDDIR)/changes."
157 | 
158 | linkcheck:
159 | 	$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
160 | 	@echo
161 | 	@echo "Link check complete; look for any errors in the above output " \
162 | 	      "or in $(BUILDDIR)/linkcheck/output.txt."
163 | 
164 | doctest:
165 | 	$(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
166 | 	@echo "Testing of doctests in the sources finished, look at the " \
167 | 	      "results in $(BUILDDIR)/doctest/output.txt."
168 | 
169 | xml:
170 | 	$(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
171 | 	@echo
172 | 	@echo "Build finished. The XML files are in $(BUILDDIR)/xml."
173 | 
174 | pseudoxml:
175 | 	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
176 | 	@echo
177 | 	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."


--------------------------------------------------------------------------------
/docs/_shared_static/custom.css:
--------------------------------------------------------------------------------
  1 | {% set theme_sidebar_header = theme_sidebar_header or theme_gray_1 %}
  2 | {% set theme_sidebar_link = theme_sidebar_link or theme_gray_1 %}
  3 | {% set theme_anchor_hover_fg = theme_anchor_hover_fg or theme_gray_1 %}
  4 | 
  5 | {% set theme_note_bg = theme_note_bg or theme_gray_2 %}
  6 | {% set theme_footnote_border = theme_footnote_border or theme_gray_2 %}
  7 | {% set theme_pre_bg = theme_pre_bg or theme_gray_2 %}
  8 | 
  9 | {% set theme_warn_bg = theme_warn_bg or theme_pink_1 %}
 10 | {% set theme_warn_border = theme_warn_border or theme_pink_2 %}
 11 | 
 12 | {% set theme_seealso_bg = theme_seealso_bg or theme_gray_2 %}
 13 | 
 14 | {% set theme_narrow_sidebar_link = theme_narrow_sidebar_link or theme_gray_3 %}
 15 | {% set theme_sidebar_hr = theme_sidebar_hr or theme_gray_3 %}
 16 | 
 17 | 
 18 | @import url("basic.css");
 19 | 
 20 | /* -- page layout ----------------------------------------------------------- */
 21 | 
 22 | body {
 23 |     font-family: "Georgia", "Open Sans", OpenSansRegular, sans-serif;
 24 |     font-size: 16px;
 25 |     background-color: white;
 26 |     color: #000;
 27 |     margin: 0;
 28 |     padding: 0;
 29 | }
 30 | 
 31 | 
 32 | div.document {
 33 |     width: {{ theme_page_width }};
 34 |     margin: 30px auto 0 auto;
 35 | }
 36 | 
 37 | div.documentwrapper {
 38 |     float: left;
 39 |     width: 100%;
 40 | }
 41 | 
 42 | div.bodywrapper {
 43 |     margin: 0 0 0 260px;
 44 | }
 45 | 
 46 | div.sphinxsidebar {
 47 |     width: 260px;
 48 |     font-size: 14px;
 49 |     line-height: 1.5;
 50 | }
 51 | 
 52 | hr {
 53 |     border: 1px solid #B1B4B6;
 54 | }
 55 | 
 56 | div.body {
 57 |     background-color: #ffffff;
 58 |     color: {{ theme_body_text }};
 59 |     padding: 0 30px 0 30px;
 60 | }
 61 | 
 62 | div.body > .section {
 63 |     text-align: {{ theme_body_text_align }};
 64 | }
 65 | 
 66 | div.footer {
 67 |     width: {{ theme_page_width }};
 68 |     margin: 20px auto 30px auto;
 69 |     font-size: 14px;
 70 |     color: {{ theme_footer_text }};
 71 |     text-align: right;
 72 | }
 73 | 
 74 | div.footer a {
 75 |     color: {{ theme_footer_text }};
 76 | }
 77 | 
 78 | p.caption {
 79 |     font-family: {{ theme_cation_font_family }};
 80 |     font-size: {{ theme_caption_font_size }};
 81 | }
 82 | 
 83 | {% if theme_show_related|lower == 'false' %}
 84 | div.relations {
 85 |     display: none;
 86 | }
 87 | {% endif %}
 88 | 
 89 | div.sphinxsidebar a {
 90 |     color: {{ theme_sidebar_link }};
 91 |     text-decoration: none;
 92 |     border-bottom: 1px dotted {{ theme_sidebar_link_underscore }};
 93 | }
 94 | 
 95 | div.sphinxsidebar a:hover {
 96 |     border-bottom: 1px solid {{ theme_sidebar_link_underscore }};
 97 | }
 98 | 
 99 | div.sphinxsidebarwrapper {
100 |     padding: 18px 10px;
101 | }
102 | 
103 | div.sphinxsidebarwrapper p.logo {
104 |     padding: 0;
105 |     margin: -10px 0 0 0px;
106 |     text-align: center;
107 | }
108 | 
109 | div.sphinxsidebarwrapper h1.logo {
110 |     margin-top: -10px;
111 |     text-align: center;
112 |     margin-bottom: 5px;
113 |     text-align: {{ theme_logo_text_align }};
114 | }
115 | 
116 | div.sphinxsidebarwrapper h1.logo-name {
117 |     margin-top: 0px;
118 | }
119 | 
120 | div.sphinxsidebarwrapper p.blurb {
121 |     margin-top: 0;
122 |     //font-style: {{ theme_description_font_style }};
123 |     font-style:italic;font-size:0.9em; text-align:center; margin-bottom:1.5em
124 | }
125 | 
126 | div.sphinxsidebar h3,
127 | div.sphinxsidebar h4 {
128 |     font-family: 'Antic Slab' ,'Garamond', 'Georgia', serif;
129 |     color: #000;
130 |     font-size: 24px;
131 |     font-weight: normal;
132 |     margin: 30px 0 5px 0;
133 |     padding: 0;
134 | }
135 | 
136 | div.sphinxsidebar h4 {
137 |     font-size: 20px;
138 | }
139 | 
140 | div.sphinxsidebar h3 a {
141 |     color: {{ theme_sidebar_link }};
142 | }
143 | 
144 | div.sphinxsidebar p.logo a,
145 | div.sphinxsidebar h3 a,
146 | div.sphinxsidebar p.logo a:hover,
147 | div.sphinxsidebar h3 a:hover {
148 |     border: none;
149 | }
150 | 
151 | div.sphinxsidebar p {
152 |     color: {{ theme_sidebar_text }};
153 |     margin: 10px 0;
154 | }
155 | 
156 | div.sphinxsidebar ul {
157 |     margin: 10px 0;
158 |     padding: 0;
159 |     color: {{ theme_sidebar_list }};
160 | }
161 | 
162 | div.sphinxsidebar ul li.toctree-l1 > a {
163 |     font-size: 120%;
164 | }
165 | 
166 | div.sphinxsidebar ul li.toctree-l2 > a {
167 |     font-size: 110%;
168 | }
169 | 
170 | div.sphinxsidebar input {
171 |     border: 1px solid {{ theme_sidebar_search_button }};
172 |     font-family: {{ theme_font_family }};
173 |     font-size: 1em;
174 | }
175 | 
176 | div.sphinxsidebar hr {
177 |     border: none;
178 |     height: 1px;
179 |     color: {{ theme_sidebar_hr }};
180 |     background: {{ theme_sidebar_hr }};
181 | 
182 |     text-align: left;
183 |     margin-left: 0;
184 |     width: 50%;
185 | }
186 | 
187 | /* -- body styles ----------------------------------------------------------- */
188 | 
189 | a {
190 |     color: {{ theme_link }};
191 |     text-decoration: underline;
192 | }
193 | 
194 | a:hover {
195 |     color: {{ theme_link_hover }};
196 |     text-decoration: underline;
197 | }
198 | 
199 | div.body h1,
200 | div.body h2,
201 | div.body h3,
202 | div.body h4,
203 | div.body h5,
204 | div.body h6 {
205 |     font-family: 'Antic Slab', serif;
206 |     font-weight: normal;
207 |     margin: 30px 0px 10px 0px;
208 |     padding: 0;
209 |     text-shadow: 1px 1px 3px #ddd;
210 |     color: #000;
211 | }
212 | 
213 | div.body h1 { margin-top: 0; padding-top: 0; font-size: 240%; }
214 | div.body h2 { font-size: 180%; }
215 | div.body h3 { font-size: 150%; }
216 | div.body h4 { font-size: 130%; }
217 | div.body h5 { font-size: 100%; }
218 | div.body h6 { font-size: 100%; }
219 | 
220 | a.headerlink {
221 |     color: {{ theme_anchor }};
222 |     padding: 0 4px;
223 |     text-decoration: none;
224 | }
225 | 
226 | a.headerlink:hover {
227 |     color: {{ theme_anchor_hover_fg }};
228 |     background: {{ theme_anchor_hover_bg }};
229 | }
230 | 
231 | div.body p, div.body dd, div.body li {
232 |     line-height: 1.4em;
233 | }
234 | 
235 | div.admonition {
236 |     margin: 20px 0px;
237 |     padding: 10px 30px;
238 |     background-color: {{ theme_warn_bg }};
239 |     border: 1px solid {{ theme_warn_border }};
240 | }
241 | 
242 | div.admonition tt.xref, div.admonition a tt {
243 |     border-bottom: 1px solid #fafafa;
244 | }
245 | 
246 | dd div.admonition {
247 |     margin-left: -60px;
248 |     padding-left: 60px;
249 | }
250 | 
251 | div.admonition p.admonition-title {
252 |     font-family: {{ theme_head_font_family }};
253 |     font-weight: normal;
254 |     font-size: 24px;
255 |     margin: 0 0 10px 0;
256 |     padding: 0;
257 |     line-height: 1;
258 | }
259 | 
260 | div.admonition p.last {
261 |     margin-bottom: 0;
262 | }
263 | 
264 | div.highlight {
265 |     background-color: white;
266 | }
267 | 
268 | dt:target, .highlight {
269 |     background: #FAF3E8;
270 | }
271 | 
272 | div.note {
273 |     background-color: {{ theme_note_bg }};
274 |     border: 1px solid {{ theme_note_border }};
275 | }
276 | 
277 | div.seealso {
278 |     background-color: {{ theme_seealso_bg }};
279 |     border: 1px solid {{ theme_seealso_border }};
280 | }
281 | 
282 | div.topic {
283 |     background-color: #eee;
284 | }
285 | 
286 | p.admonition-title {
287 |     display: inline;
288 | }
289 | 
290 | p.admonition-title:after {
291 |     content: ":";
292 | }
293 | 
294 | pre, tt, code {
295 |     font-family: {{theme_code_font_family}};
296 |     font-size: {{ theme_code_font_size }};
297 | }
298 | 
299 | .hll {
300 |     background-color: {{theme_code_highlight}};
301 |     margin: 0 -12px;
302 |     padding: 0 12px;
303 |     display: block;
304 | }
305 | 
306 | img.screenshot {
307 | }
308 | 
309 | tt.descname, tt.descclassname, code.descname, code.descclassname {
310 |     font-size: 0.95em;
311 | }
312 | 
313 | tt.descname, code.descname {
314 |     padding-right: 0.08em;
315 | }
316 | 
317 | img.screenshot {
318 |     -moz-box-shadow: 2px 2px 4px #eee;
319 |     -webkit-box-shadow: 2px 2px 4px #eee;
320 |     box-shadow: 2px 2px 4px #eee;
321 | }
322 | 
323 | table.docutils {
324 |     border: 1px solid #888;
325 |     -moz-box-shadow: 2px 2px 4px #eee;
326 |     -webkit-box-shadow: 2px 2px 4px #eee;
327 |     box-shadow: 2px 2px 4px #eee;
328 | }
329 | 
330 | table.docutils td, table.docutils th {
331 |     border: 1px solid #888;
332 |     padding: 0.25em 0.7em;
333 | }
334 | 
335 | table.field-list, table.footnote {
336 |     border: none;
337 |     -moz-box-shadow: none;
338 |     -webkit-box-shadow: none;
339 |     box-shadow: none;
340 | }
341 | 
342 | table.footnote {
343 |     margin: 15px 0;
344 |     width: 100%;
345 |     border: 1px solid {{ theme_footnote_border }};
346 |     background: {{ theme_footnote_bg }};
347 |     font-size: 0.9em;
348 | }
349 | 
350 | table.footnote + table.footnote {
351 |     margin-top: -15px;
352 |     border-top: none;
353 | }
354 | 
355 | table.field-list th {
356 |     padding: 0 0.8em 0 0;
357 | }
358 | 
359 | table.field-list td {
360 |     padding: 0;
361 | }
362 | 
363 | table.field-list p {
364 |     margin-bottom: 0.8em;
365 | }
366 | 
367 | table.footnote td.label {
368 |     width: .1px;
369 |     padding: 0.3em 0 0.3em 0.5em;
370 | }
371 | 
372 | table.footnote td {
373 |     padding: 0.3em 0.5em;
374 | }
375 | 
376 | dl {
377 |     margin: 0;
378 |     padding: 0;
379 | }
380 | 
381 | dl dd {
382 |     margin-left: 30px;
383 | }
384 | 
385 | blockquote {
386 |     margin: 0 0 0 30px;
387 |     padding: 0;
388 | }
389 | 
390 | ul, ol {
391 |     /* Matches the 30px from the narrow-screen "li > ul" selector below */
392 |     margin: 10px 0 10px 30px;
393 |     padding: 0;
394 | }
395 | 
396 | pre {
397 |     background: {{ theme_pre_bg }};
398 |     padding: 7px 30px;
399 |     margin: 15px 0px;
400 |     line-height: 1.3em;
401 | }
402 | 
403 | dl pre, blockquote pre, li pre {
404 |     margin-left: 0;
405 |     padding-left: 30px;
406 | }
407 | 
408 | dl dl pre {
409 |     margin-left: -90px;
410 |     padding-left: 90px;
411 | }
412 | 
413 | tt, code {
414 |     background-color: #ecf0f3;
415 |     color: #222;
416 |     /* padding: 1px 2px; */
417 | }
418 | 
419 | tt.xref, code.xref, a tt {
420 |     background-color: #FBFBFB;
421 |     border-bottom: 1px solid white;
422 | }
423 | 
424 | a.reference {
425 |     text-decoration: none;
426 |     border-bottom: 1px dotted {{ theme_link }};
427 | }
428 | 
429 | /* Don't put an underline on images */
430 | a.image-reference, a.image-reference:hover {
431 |     border-bottom: none;
432 | }
433 | 
434 | a.reference:hover {
435 |     border-bottom: 1px solid {{ theme_link_hover }};
436 | }
437 | 
438 | a.footnote-reference {
439 |     text-decoration: none;
440 |     font-size: 0.7em;
441 |     vertical-align: top;
442 |     border-bottom: 1px dotted {{ theme_link }};
443 | }
444 | 
445 | a.footnote-reference:hover {
446 |     border-bottom: 1px solid {{ theme_link_hover }};
447 | }
448 | 
449 | a:hover tt, a:hover code {
450 |     background: #EEE;
451 | }
452 | 
453 | 
454 | @media screen and (max-width: 870px) {
455 | 
456 |     div.sphinxsidebar {
457 |         display: none;
458 |     }
459 | 
460 |     div.document {
461 |        width: 100%;
462 | 
463 |     }
464 | 
465 |     div.documentwrapper {
466 |         margin-left: 0;
467 |         margin-top: 0;
468 |         margin-right: 0;
469 |         margin-bottom: 0;
470 |     }
471 | 
472 |     div.bodywrapper {
473 |         margin-top: 0;
474 |         margin-right: 0;
475 |         margin-bottom: 0;
476 |         margin-left: 0;
477 |     }
478 | 
479 |     ul {
480 |         margin-left: 0;
481 |     }
482 | 
483 |     li > ul {
484 |         /* Matches the 30px from the "ul, ol" selector above */
485 |         margin-left: 30px;
486 |     }
487 | 
488 |     .document {
489 |         width: auto;
490 |     }
491 | 
492 |     .footer {
493 |         width: auto;
494 |     }
495 | 
496 |     .bodywrapper {
497 |         margin: 0;
498 |     }
499 | 
500 |     .footer {
501 |         width: auto;
502 |     }
503 | 
504 |     .github {
505 |         display: none;
506 |     }
507 | 
508 | 
509 | 
510 | }
511 | 
512 | 
513 | 
514 | @media screen and (max-width: 875px) {
515 | 
516 |     body {
517 |         margin: 0;
518 |         padding: 20px 30px;
519 |     }
520 | 
521 |     div.documentwrapper {
522 |         float: none;
523 |         background: white;
524 |     }
525 | 
526 |     div.sphinxsidebar {
527 |         display: block;
528 |         float: none;
529 |         width: 102.5%;
530 |         {%- if theme_fixed_sidebar|lower == 'true' %}
531 |         margin: -20px -30px 20px -30px;
532 |         {%- else %}
533 |         margin: 50px -30px -20px -30px;
534 |         {%- endif %}
535 |         padding: 10px 20px;
536 |         background: {{ theme_narrow_sidebar_bg }};
537 |         color: {{ theme_narrow_sidebar_fg }};
538 |     }
539 | 
540 |     div.sphinxsidebar h3, div.sphinxsidebar h4, div.sphinxsidebar p,
541 |     div.sphinxsidebar h3 a {
542 |         color: white;
543 |     }
544 | 
545 |     div.sphinxsidebar a {
546 |         color: {{ theme_narrow_sidebar_link }};
547 |     }
548 | 
549 |     div.sphinxsidebar p.logo {
550 |         display: none;
551 |     }
552 | 
553 |     div.document {
554 |         width: 100%;
555 |         margin: 0;
556 |     }
557 | 
558 |     div.footer {
559 |         display: none;
560 |     }
561 | 
562 |     div.bodywrapper {
563 |         margin: 0;
564 |     }
565 | 
566 |     div.body {
567 |         min-height: 0;
568 |         padding: 0;
569 |     }
570 | 
571 |     .rtd_doc_footer {
572 |         display: none;
573 |     }
574 | 
575 |     .document {
576 |         width: auto;
577 |     }
578 | 
579 |     .footer {
580 |         width: auto;
581 |     }
582 | 
583 |     .footer {
584 |         width: auto;
585 |     }
586 | 
587 |     .github {
588 |         display: none;
589 |     }
590 | }
591 | 
592 | {%- if theme_fixed_sidebar|lower == 'true' %}
593 | @media screen and (min-width: 876px) {
594 |     div.sphinxsidebar {
595 |         position: fixed;
596 |         margin-left: 0;
597 |     }
598 | }
599 | {%- endif %}
600 | 
601 | 
602 | /* misc. */
603 | 
604 | .revsys-inline {
605 |     display: none!important;
606 | }
607 | 
608 | /* Make nested-list/multi-paragraph items look better in Releases changelog
609 |  * pages. Without this, docutils' magical list fuckery causes inconsistent
610 |  * formatting between different release sub-lists.
611 |  */
612 | div#changelog > div.section > ul > li > p:only-child {
613 |     margin-bottom: 0;
614 | }
615 | 
616 | /* Hide fugly table cell borders in ..bibliography:: directive output */
617 | table.docutils.citation, table.docutils.citation td, table.docutils.citation th {
618 |   border: none;
619 |   /* Below needed in some edge cases; if not applied, bottom shadows appear */
620 |   -moz-box-shadow: none;
621 |   -webkit-box-shadow: none;
622 |   box-shadow: none;
623 | }
624 | 


--------------------------------------------------------------------------------
/docs/_shared_static/logo.jpg:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/spurin/xmldataset/958a4884a46c950f331546bae02ecb0a7cbbc77a/docs/_shared_static/logo.jpg


--------------------------------------------------------------------------------
/docs/_themes/alabaster/__init__.py:
--------------------------------------------------------------------------------
 1 | import os
 2 | 
 3 | from alabaster import _version as version
 4 | 
 5 | 
 6 | def get_path():
 7 |     """
 8 |     Shortcut for users whose theme is next to their conf.py.
 9 |     """
10 |     # Theme directory is defined as our parent directory
11 |     return os.path.abspath(os.path.dirname(os.path.dirname(__file__)))
12 | 
13 | 
14 | def update_context(app, pagename, templatename, context, doctree):
15 |     context['alabaster_version'] = version.__version__
16 | 
17 | def setup(app):
18 |     app.connect('html-page-context', update_context)
19 |     return {'version': version.__version__,
20 |             'parallel_read_safe': True}
21 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/_version.py:
--------------------------------------------------------------------------------
1 | __version_info__ = (0, 7, 8)
2 | __version__ = '.'.join(map(str, __version_info__))
3 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/about.html:
--------------------------------------------------------------------------------
 1 | {% if theme_logo %}
 2 | <p class="logo">
 3 |   <a href="{{ pathto(master_doc) }}">
 4 |     <img class="logo" src="{{ pathto('_static/' ~ theme_logo, 1) }}" alt="Logo"/>
 5 |   </a>
 6 | </p>
 7 | {% else %}
 8 | <h1 class="logo"><a href="{{ pathto(master_doc) }}">{{ project }}</a></h1>
 9 | {% endif %}
10 | 
11 | {% if theme_description %}
12 | <p class="blurb">{{ theme_description }}</p>
13 | {% endif %}
14 | 
15 | {% if theme_github_user and theme_github_repo %}
16 | {% if theme_github_button|lower == 'true' %}
17 | <p>
18 | <iframe src="https://ghbtns.com/github-btn.html?user={{ theme_github_user }}&repo={{ theme_github_repo }}&type=star&count={{ theme_github_count }}&size=large&v=2"
19 |   allowtransparency="true" frameborder="0" scrolling="0" width="160px" height="30px"></iframe>
20 | </p>
21 | {% endif %}
22 | {% endif %}
23 | 
24 | {% if theme_travis_button|lower != 'false' %}
25 | {% if theme_travis_button|lower == 'true' %}
26 |     {% set path = theme_github_user + '/' + theme_github_repo %}
27 | {% else %}
28 |     {% set path = theme_travis_button %}
29 | {% endif %}
30 | <p>
31 | <a href="https://travis-ci.org/{{ path }}">
32 |     <img
33 |         alt="https://secure.travis-ci.org/{{ path }}.svg?branch=master"
34 |         src="https://secure.travis-ci.org/{{ path }}.svg?branch=master"
35 |     />
36 | </a>
37 | </p>
38 | {% endif %}
39 | 
40 | {% if theme_codecov_button|lower != 'false' %}
41 | {% if theme_codecov_button|lower == 'true' %}
42 |     {% set path = theme_github_user + '/' + theme_github_repo %}
43 | {% else %}
44 |     {% set path = theme_codecov_button %}
45 | {% endif %}
46 | <p>
47 | <a href="https://codecov.io/github/{{ path }}">
48 |     <img
49 |     alt="https://codecov.io/github/{{ path }}/coverage.svg?branch=master"
50 |     src="https://codecov.io/github/{{ path }}/coverage.svg?branch=master"
51 |     />
52 | </a>
53 | </p>
54 | {% endif %}
55 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/donate.html:
--------------------------------------------------------------------------------
 1 | {% if theme_gratipay_user or theme_gittip_user %}
 2 | <h3>Donate</h3>
 3 | <p>
 4 | Consider supporting the authors on <a href="https://www.gratipay.com/">Gratipay</a>:
 5 | <script data-gratipay-username="{{ theme_gratipay_user or theme_gittip_user }}"
 6 |         data-gratipay-widget="button"
 7 |         src="//gttp.co/v1.js"></script>
 8 | </p>
 9 | {% endif %}
10 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/layout.html:
--------------------------------------------------------------------------------
 1 | {%- extends "basic/layout.html" %}
 2 | 
 3 | {%- block extrahead %}
 4 | {{ super() }}
 5 |   <link rel="stylesheet" href="{{ pathto('_static/custom.css', 1) }}" type="text/css" />
 6 |   <link href="https://fonts.googleapis.com/css?family=Open+Sans:400|Antic+Slab" rel="stylesheet" type="text/css">
 7 |   {% if theme_touch_icon %}
 8 |     <link rel="apple-touch-icon" href="{{ pathto('_static/' ~ theme_touch_icon, 1) }}" />
 9 |   {% endif %}
10 |   <meta name="viewport" content="width=device-width, initial-scale=0.9, maximum-scale=0.9" />
11 | {% endblock %}
12 | 
13 | {# Disable base theme's top+bottom related navs; we have our own in sidebar #}
14 | {%- block relbar1 %}{% endblock %}
15 | {%- block relbar2 %}{% endblock %}
16 | 
17 | {# Nav should appear before content, not after #}
18 | {%- block content %}
19 | {%- if theme_fixed_sidebar|lower == 'true' %}
20 |   <div class="document">
21 |     {{ sidebar() }}
22 |     {%- block document %}
23 |       <div class="documentwrapper">
24 |       {%- if render_sidebar %}
25 |         <div class="bodywrapper">
26 |       {%- endif %}
27 |           <div class="body" role="main">
28 |             {% block body %} {% endblock %}
29 |           </div>
30 |       {%- if render_sidebar %}
31 |         </div>
32 |       {%- endif %}
33 |       </div>
34 |     {%- endblock %}
35 |     <div class="clearer"></div>
36 |   </div>
37 | {%- else %}
38 | {{ super() }}
39 | {%- endif %}
40 | {%- endblock %}
41 | 
42 | {%- block footer %}
43 |     <div class="footer">
44 |       {% if show_copyright %}&copy;{{ copyright }}.{% endif %}
45 |       {% if theme_show_powered_by|lower == 'true' %}
46 |       {% if show_copyright %}|{% endif %}
47 |       Powered by <a href="http://sphinx-doc.org/">Sphinx {{ sphinx_version }}</a>
48 |       &amp; <a href="https://github.com/bitprophet/alabaster">Alabaster {{ alabaster_version }}</a>
49 |       {% endif %}
50 |       {%- if show_source and has_source and sourcename %}
51 |       {% if show_copyright or theme_show_powered_by %}|{% endif %}
52 |       <a href="{{ pathto('_sources/' + sourcename, true)|e }}"
53 |           rel="nofollow">{{ _('Page source') }}</a>
54 |       {%- endif %}
55 |     </div>
56 | 
57 |     {% if theme_github_banner|lower != 'false' %}
58 |     <a href="https://github.com/{{ theme_github_user }}/{{ theme_github_repo }}" class="github">
59 |         <img style="position: absolute; top: 0; right: 0; border: 0;" src="{{ pathto('_static/' ~ theme_github_banner, 1) if theme_github_banner|lower != 'true' else 'https://s3.amazonaws.com/github/ribbons/forkme_right_darkblue_121621.png' }}" alt="Fork me on GitHub"  class="github"/>
60 |     </a>
61 |     {% endif %}
62 | 
63 |     {% if theme_analytics_id %}
64 |     <script type="text/javascript">
65 | 
66 |       var _gaq = _gaq || [];
67 |       _gaq.push(['_setAccount', '{{ theme_analytics_id }}']);
68 |       _gaq.push(['_setDomainName', 'none']);
69 |       _gaq.push(['_setAllowLinker', true]);
70 |       _gaq.push(['_trackPageview']);
71 | 
72 |       (function() {
73 |         var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
74 |         ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
75 |         var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
76 |       })();
77 | 
78 |     </script>
79 |     {% endif %}
80 | {%- endblock %}
81 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/navigation.html:
--------------------------------------------------------------------------------
 1 | <h3>{{ _('Overview') }}</h3>
 2 | {{ toctree(includehidden=theme_sidebar_includehidden) }}
 3 | {% if theme_extra_nav_links %}
 4 | <hr />
 5 | <ul>
 6 |     {% for text, uri in theme_extra_nav_links.items() %}
 7 |     <li class="toctree-l1"><a href="{{ uri }}">{{ text }}</a></li>
 8 |     {% endfor %}
 9 | </ul>
10 | {% endif %}
11 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/relations.html:
--------------------------------------------------------------------------------
 1 | <div class="relations">
 2 | <h3>Related Topics</h3>
 3 | <ul>
 4 |   <li><a href="{{ pathto(master_doc) }}">Documentation overview</a><ul>
 5 |   {%- for parent in parents %}
 6 |   <li><a href="{{ parent.link|e }}">{{ parent.title }}</a><ul>
 7 |   {%- endfor %}
 8 |     {%- if prev %}
 9 |       <li>Previous: <a href="{{ prev.link|e }}" title="{{ _('previous chapter')
10 |         }}">{{ prev.title }}</a></li>
11 |     {%- endif %}
12 |     {%- if next %}
13 |       <li>Next: <a href="{{ next.link|e }}" title="{{ _('next chapter')
14 |         }}">{{ next.title }}</a></li>
15 |     {%- endif %}
16 |   {%- for parent in parents %}
17 |   </ul></li>
18 |   {%- endfor %}
19 |   </ul></li>
20 | </ul>
21 | </div>
22 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/static/alabaster.css_t:
--------------------------------------------------------------------------------
  1 | {% set theme_sidebar_header = theme_sidebar_header or theme_gray_1 %}
  2 | {% set theme_sidebar_link = theme_sidebar_link or theme_gray_1 %}
  3 | {% set theme_anchor_hover_fg = theme_anchor_hover_fg or theme_gray_1 %}
  4 | 
  5 | {% set theme_note_bg = theme_note_bg or theme_gray_2 %}
  6 | {% set theme_footnote_border = theme_footnote_border or theme_gray_2 %}
  7 | {% set theme_pre_bg = theme_pre_bg or theme_gray_2 %}
  8 | 
  9 | {% set theme_warn_bg = theme_warn_bg or theme_pink_1 %}
 10 | {% set theme_warn_border = theme_warn_border or theme_pink_2 %}
 11 | 
 12 | {% set theme_seealso_bg = theme_seealso_bg or theme_gray_2 %}
 13 | 
 14 | {% set theme_narrow_sidebar_link = theme_narrow_sidebar_link or theme_gray_3 %}
 15 | {% set theme_sidebar_hr = theme_sidebar_hr or theme_gray_3 %}
 16 | 
 17 | 
 18 | @import url("basic.css");
 19 | 
 20 | /* -- page layout ----------------------------------------------------------- */
 21 | 
 22 | body {
 23 |     font-family: {{ theme_font_family }};
 24 |     font-size: {{ theme_font_size }};
 25 |     background-color: white;
 26 |     color: #000;
 27 |     margin: 0;
 28 |     padding: 0;
 29 | }
 30 | 
 31 | 
 32 | div.document {
 33 |     width: {{ theme_page_width }};
 34 |     margin: 30px auto 0 auto;
 35 | }
 36 | 
 37 | div.documentwrapper {
 38 |     float: left;
 39 |     width: 100%;
 40 | }
 41 | 
 42 | div.bodywrapper {
 43 |     margin: 0 0 0 {{ theme_sidebar_width }};
 44 | }
 45 | 
 46 | div.sphinxsidebar {
 47 |     width: {{ theme_sidebar_width }};
 48 |     font-size: 14px;
 49 |     line-height: 1.5;
 50 | }
 51 | 
 52 | hr {
 53 |     border: 1px solid #B1B4B6;
 54 | }
 55 | 
 56 | div.body {
 57 |     background-color: #ffffff;
 58 |     color: {{ theme_body_text }};
 59 |     padding: 0 30px 0 30px;
 60 | }
 61 | 
 62 | div.body > .section {
 63 |     text-align: {{ theme_body_text_align }};
 64 | }
 65 | 
 66 | div.footer {
 67 |     width: {{ theme_page_width }};
 68 |     margin: 20px auto 30px auto;
 69 |     font-size: 14px;
 70 |     color: {{ theme_footer_text }};
 71 |     text-align: right;
 72 | }
 73 | 
 74 | div.footer a {
 75 |     color: {{ theme_footer_text }};
 76 | }
 77 | 
 78 | p.caption {
 79 |     font-family: {{ theme_cation_font_family }};
 80 |     font-size: {{ theme_caption_font_size }};
 81 | }
 82 | 
 83 | {% if theme_show_related|lower == 'false' %}
 84 | div.relations {
 85 |     display: none;
 86 | }
 87 | {% endif %}
 88 | 
 89 | div.sphinxsidebar a {
 90 |     color: {{ theme_sidebar_link }};
 91 |     text-decoration: none;
 92 |     border-bottom: 1px dotted {{ theme_sidebar_link_underscore }};
 93 | }
 94 | 
 95 | div.sphinxsidebar a:hover {
 96 |     border-bottom: 1px solid {{ theme_sidebar_link_underscore }};
 97 | }
 98 | 
 99 | div.sphinxsidebarwrapper {
100 |     padding: 18px 10px;
101 | }
102 | 
103 | div.sphinxsidebarwrapper p.logo {
104 |     padding: 0;
105 |     margin: -10px 0 0 0px;
106 |     text-align: center;
107 | }
108 | 
109 | div.sphinxsidebarwrapper h1.logo {
110 |     margin-top: -10px;
111 |     text-align: center;
112 |     margin-bottom: 5px;
113 |     text-align: {{ theme_logo_text_align }};
114 | }
115 | 
116 | div.sphinxsidebarwrapper h1.logo-name {
117 |     margin-top: 0px;
118 | }
119 | 
120 | div.sphinxsidebarwrapper p.blurb {
121 |     margin-top: 0;
122 |     font-style: {{ theme_description_font_style }};
123 | }
124 | 
125 | div.sphinxsidebar h3,
126 | div.sphinxsidebar h4 {
127 |     font-family: {{ theme_head_font_family }};
128 |     color: {{ theme_sidebar_header }};
129 |     font-size: 24px;
130 |     font-weight: normal;
131 |     margin: 0 0 5px 0;
132 |     padding: 0;
133 | }
134 | 
135 | div.sphinxsidebar h4 {
136 |     font-size: 20px;
137 | }
138 | 
139 | div.sphinxsidebar h3 a {
140 |     color: {{ theme_sidebar_link }};
141 | }
142 | 
143 | div.sphinxsidebar p.logo a,
144 | div.sphinxsidebar h3 a,
145 | div.sphinxsidebar p.logo a:hover,
146 | div.sphinxsidebar h3 a:hover {
147 |     border: none;
148 | }
149 | 
150 | div.sphinxsidebar p {
151 |     color: {{ theme_sidebar_text }};
152 |     margin: 10px 0;
153 | }
154 | 
155 | div.sphinxsidebar ul {
156 |     margin: 10px 0;
157 |     padding: 0;
158 |     color: {{ theme_sidebar_list }};
159 | }
160 | 
161 | div.sphinxsidebar ul li.toctree-l1 > a {
162 |     font-size: 120%;
163 | }
164 | 
165 | div.sphinxsidebar ul li.toctree-l2 > a {
166 |     font-size: 110%;
167 | }
168 | 
169 | div.sphinxsidebar input {
170 |     border: 1px solid {{ theme_sidebar_search_button }};
171 |     font-family: {{ theme_font_family }};
172 |     font-size: 1em;
173 | }
174 | 
175 | div.sphinxsidebar hr {
176 |     border: none;
177 |     height: 1px;
178 |     color: {{ theme_sidebar_hr }};
179 |     background: {{ theme_sidebar_hr }};
180 | 
181 |     text-align: left;
182 |     margin-left: 0;
183 |     width: 50%;
184 | }
185 | 
186 | /* -- body styles ----------------------------------------------------------- */
187 | 
188 | a {
189 |     color: {{ theme_link }};
190 |     text-decoration: underline;
191 | }
192 | 
193 | a:hover {
194 |     color: {{ theme_link_hover }};
195 |     text-decoration: underline;
196 | }
197 | 
198 | div.body h1,
199 | div.body h2,
200 | div.body h3,
201 | div.body h4,
202 | div.body h5,
203 | div.body h6 {
204 |     font-family: {{ theme_head_font_family }};
205 |     font-weight: normal;
206 |     margin: 30px 0px 10px 0px;
207 |     padding: 0;
208 | }
209 | 
210 | div.body h1 { margin-top: 0; padding-top: 0; font-size: 240%; }
211 | div.body h2 { font-size: 180%; }
212 | div.body h3 { font-size: 150%; }
213 | div.body h4 { font-size: 130%; }
214 | div.body h5 { font-size: 100%; }
215 | div.body h6 { font-size: 100%; }
216 | 
217 | a.headerlink {
218 |     color: {{ theme_anchor }};
219 |     padding: 0 4px;
220 |     text-decoration: none;
221 | }
222 | 
223 | a.headerlink:hover {
224 |     color: {{ theme_anchor_hover_fg }};
225 |     background: {{ theme_anchor_hover_bg }};
226 | }
227 | 
228 | div.body p, div.body dd, div.body li {
229 |     line-height: 1.4em;
230 | }
231 | 
232 | div.admonition {
233 |     margin: 20px 0px;
234 |     padding: 10px 30px;
235 |     background-color: {{ theme_warn_bg }};
236 |     border: 1px solid {{ theme_warn_border }};
237 | }
238 | 
239 | div.admonition tt.xref, div.admonition a tt {
240 |     border-bottom: 1px solid #fafafa;
241 | }
242 | 
243 | dd div.admonition {
244 |     margin-left: -60px;
245 |     padding-left: 60px;
246 | }
247 | 
248 | div.admonition p.admonition-title {
249 |     font-family: {{ theme_head_font_family }};
250 |     font-weight: normal;
251 |     font-size: 24px;
252 |     margin: 0 0 10px 0;
253 |     padding: 0;
254 |     line-height: 1;
255 | }
256 | 
257 | div.admonition p.last {
258 |     margin-bottom: 0;
259 | }
260 | 
261 | div.highlight {
262 |     background-color: white;
263 | }
264 | 
265 | dt:target, .highlight {
266 |     background: #FAF3E8;
267 | }
268 | 
269 | div.note {
270 |     background-color: {{ theme_note_bg }};
271 |     border: 1px solid {{ theme_note_border }};
272 | }
273 | 
274 | div.seealso {
275 |     background-color: {{ theme_seealso_bg }};
276 |     border: 1px solid {{ theme_seealso_border }};
277 | }
278 | 
279 | div.topic {
280 |     background-color: #eee;
281 | }
282 | 
283 | p.admonition-title {
284 |     display: inline;
285 | }
286 | 
287 | p.admonition-title:after {
288 |     content: ":";
289 | }
290 | 
291 | pre, tt, code {
292 |     font-family: {{theme_code_font_family}};
293 |     font-size: {{ theme_code_font_size }};
294 | }
295 | 
296 | .hll {
297 |     background-color: {{theme_code_highlight}};
298 |     margin: 0 -12px;
299 |     padding: 0 12px;
300 |     display: block;
301 | }
302 | 
303 | img.screenshot {
304 | }
305 | 
306 | tt.descname, tt.descclassname, code.descname, code.descclassname {
307 |     font-size: 0.95em;
308 | }
309 | 
310 | tt.descname, code.descname {
311 |     padding-right: 0.08em;
312 | }
313 | 
314 | img.screenshot {
315 |     -moz-box-shadow: 2px 2px 4px #eee;
316 |     -webkit-box-shadow: 2px 2px 4px #eee;
317 |     box-shadow: 2px 2px 4px #eee;
318 | }
319 | 
320 | table.docutils {
321 |     border: 1px solid #888;
322 |     -moz-box-shadow: 2px 2px 4px #eee;
323 |     -webkit-box-shadow: 2px 2px 4px #eee;
324 |     box-shadow: 2px 2px 4px #eee;
325 | }
326 | 
327 | table.docutils td, table.docutils th {
328 |     border: 1px solid #888;
329 |     padding: 0.25em 0.7em;
330 | }
331 | 
332 | table.field-list, table.footnote {
333 |     border: none;
334 |     -moz-box-shadow: none;
335 |     -webkit-box-shadow: none;
336 |     box-shadow: none;
337 | }
338 | 
339 | table.footnote {
340 |     margin: 15px 0;
341 |     width: 100%;
342 |     border: 1px solid {{ theme_footnote_border }};
343 |     background: {{ theme_footnote_bg }};
344 |     font-size: 0.9em;
345 | }
346 | 
347 | table.footnote + table.footnote {
348 |     margin-top: -15px;
349 |     border-top: none;
350 | }
351 | 
352 | table.field-list th {
353 |     padding: 0 0.8em 0 0;
354 | }
355 | 
356 | table.field-list td {
357 |     padding: 0;
358 | }
359 | 
360 | table.field-list p {
361 |     margin-bottom: 0.8em;
362 | }
363 | 
364 | table.footnote td.label {
365 |     width: .1px;
366 |     padding: 0.3em 0 0.3em 0.5em;
367 | }
368 | 
369 | table.footnote td {
370 |     padding: 0.3em 0.5em;
371 | }
372 | 
373 | dl {
374 |     margin: 0;
375 |     padding: 0;
376 | }
377 | 
378 | dl dd {
379 |     margin-left: 30px;
380 | }
381 | 
382 | blockquote {
383 |     margin: 0 0 0 30px;
384 |     padding: 0;
385 | }
386 | 
387 | ul, ol {
388 |     /* Matches the 30px from the narrow-screen "li > ul" selector below */
389 |     margin: 10px 0 10px 30px;
390 |     padding: 0;
391 | }
392 | 
393 | pre {
394 |     background: {{ theme_pre_bg }};
395 |     padding: 7px 30px;
396 |     margin: 15px 0px;
397 |     line-height: 1.3em;
398 | }
399 | 
400 | dl pre, blockquote pre, li pre {
401 |     margin-left: 0;
402 |     padding-left: 30px;
403 | }
404 | 
405 | dl dl pre {
406 |     margin-left: -90px;
407 |     padding-left: 90px;
408 | }
409 | 
410 | tt, code {
411 |     background-color: #ecf0f3;
412 |     color: #222;
413 |     /* padding: 1px 2px; */
414 | }
415 | 
416 | tt.xref, code.xref, a tt {
417 |     background-color: #FBFBFB;
418 |     border-bottom: 1px solid white;
419 | }
420 | 
421 | a.reference {
422 |     text-decoration: none;
423 |     border-bottom: 1px dotted {{ theme_link }};
424 | }
425 | 
426 | /* Don't put an underline on images */
427 | a.image-reference, a.image-reference:hover {
428 |     border-bottom: none;
429 | }
430 | 
431 | a.reference:hover {
432 |     border-bottom: 1px solid {{ theme_link_hover }};
433 | }
434 | 
435 | a.footnote-reference {
436 |     text-decoration: none;
437 |     font-size: 0.7em;
438 |     vertical-align: top;
439 |     border-bottom: 1px dotted {{ theme_link }};
440 | }
441 | 
442 | a.footnote-reference:hover {
443 |     border-bottom: 1px solid {{ theme_link_hover }};
444 | }
445 | 
446 | a:hover tt, a:hover code {
447 |     background: #EEE;
448 | }
449 | 
450 | 
451 | @media screen and (max-width: 870px) {
452 | 
453 |     div.sphinxsidebar {
454 |     	display: none;
455 |     }
456 | 
457 |     div.document {
458 |        width: 100%;
459 | 
460 |     }
461 | 
462 |     div.documentwrapper {
463 |     	margin-left: 0;
464 |     	margin-top: 0;
465 |     	margin-right: 0;
466 |     	margin-bottom: 0;
467 |     }
468 | 
469 |     div.bodywrapper {
470 |     	margin-top: 0;
471 |     	margin-right: 0;
472 |     	margin-bottom: 0;
473 |     	margin-left: 0;
474 |     }
475 | 
476 |     ul {
477 |     	margin-left: 0;
478 |     }
479 | 
480 | 	li > ul {
481 |         /* Matches the 30px from the "ul, ol" selector above */
482 | 		margin-left: 30px;
483 | 	}
484 | 
485 |     .document {
486 |     	width: auto;
487 |     }
488 | 
489 |     .footer {
490 |     	width: auto;
491 |     }
492 | 
493 |     .bodywrapper {
494 |     	margin: 0;
495 |     }
496 | 
497 |     .footer {
498 |     	width: auto;
499 |     }
500 | 
501 |     .github {
502 |         display: none;
503 |     }
504 | 
505 | 
506 | 
507 | }
508 | 
509 | 
510 | 
511 | @media screen and (max-width: 875px) {
512 | 
513 |     body {
514 |         margin: 0;
515 |         padding: 20px 30px;
516 |     }
517 | 
518 |     div.documentwrapper {
519 |         float: none;
520 |         background: white;
521 |     }
522 | 
523 |     div.sphinxsidebar {
524 |         display: block;
525 |         float: none;
526 |         width: 102.5%;
527 |         {%- if theme_fixed_sidebar|lower == 'true' %}
528 |         margin: -20px -30px 20px -30px;
529 |         {%- else %}
530 |         margin: 50px -30px -20px -30px;
531 |         {%- endif %}
532 |         padding: 10px 20px;
533 |         background: {{ theme_narrow_sidebar_bg }};
534 |         color: {{ theme_narrow_sidebar_fg }};
535 |     }
536 | 
537 |     div.sphinxsidebar h3, div.sphinxsidebar h4, div.sphinxsidebar p,
538 |     div.sphinxsidebar h3 a {
539 |         color: white;
540 |     }
541 | 
542 |     div.sphinxsidebar a {
543 |         color: {{ theme_narrow_sidebar_link }};
544 |     }
545 | 
546 |     div.sphinxsidebar p.logo {
547 |         display: none;
548 |     }
549 | 
550 |     div.document {
551 |         width: 100%;
552 |         margin: 0;
553 |     }
554 | 
555 |     div.footer {
556 |         display: none;
557 |     }
558 | 
559 |     div.bodywrapper {
560 |         margin: 0;
561 |     }
562 | 
563 |     div.body {
564 |         min-height: 0;
565 |         padding: 0;
566 |     }
567 | 
568 |     .rtd_doc_footer {
569 |         display: none;
570 |     }
571 | 
572 |     .document {
573 |         width: auto;
574 |     }
575 | 
576 |     .footer {
577 |         width: auto;
578 |     }
579 | 
580 |     .footer {
581 |         width: auto;
582 |     }
583 | 
584 |     .github {
585 |         display: none;
586 |     }
587 | }
588 | 
589 | {%- if theme_fixed_sidebar|lower == 'true' %}
590 | @media screen and (min-width: 876px) {
591 |     div.sphinxsidebar {
592 |         position: fixed;
593 |         margin-left: 0;
594 |     }
595 | }
596 | {%- endif %}
597 | 
598 | 
599 | /* misc. */
600 | 
601 | .revsys-inline {
602 |     display: none!important;
603 | }
604 | 
605 | /* Make nested-list/multi-paragraph items look better in Releases changelog
606 |  * pages. Without this, docutils' magical list fuckery causes inconsistent
607 |  * formatting between different release sub-lists.
608 |  */
609 | div#changelog > div.section > ul > li > p:only-child {
610 |     margin-bottom: 0;
611 | }
612 | 
613 | /* Hide fugly table cell borders in ..bibliography:: directive output */
614 | table.docutils.citation, table.docutils.citation td, table.docutils.citation th {
615 |   border: none;
616 |   /* Below needed in some edge cases; if not applied, bottom shadows appear */
617 |   -moz-box-shadow: none;
618 |   -webkit-box-shadow: none;
619 |   box-shadow: none;
620 | }
621 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/static/custom.css:
--------------------------------------------------------------------------------
1 | /* This file intentionally left blank. */
2 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/support.py:
--------------------------------------------------------------------------------
 1 | from pygments.style import Style
 2 | from pygments.token import Keyword, Name, Comment, String, Error, \
 3 |      Number, Operator, Generic, Whitespace, Punctuation, Other, Literal
 4 | 
 5 | 
 6 | # Originally based on FlaskyStyle which was based on 'tango'.
 7 | class Alabaster(Style):
 8 |     background_color = "#f8f8f8" # doesn't seem to override CSS 'pre' styling?
 9 |     default_style = ""
10 | 
11 |     styles = {
12 |         # No corresponding class for the following:
13 |         #Text:                     "", # class:  ''
14 |         Whitespace:                "underline #f8f8f8",      # class: 'w'
15 |         Error:                     "#a40000 border:#ef2929", # class: 'err'
16 |         Other:                     "#000000",                # class 'x'
17 | 
18 |         Comment:                   "italic #8f5902", # class: 'c'
19 |         Comment.Preproc:           "noitalic",       # class: 'cp'
20 | 
21 |         Keyword:                   "bold #004461",   # class: 'k'
22 |         Keyword.Constant:          "bold #004461",   # class: 'kc'
23 |         Keyword.Declaration:       "bold #004461",   # class: 'kd'
24 |         Keyword.Namespace:         "bold #004461",   # class: 'kn'
25 |         Keyword.Pseudo:            "bold #004461",   # class: 'kp'
26 |         Keyword.Reserved:          "bold #004461",   # class: 'kr'
27 |         Keyword.Type:              "bold #004461",   # class: 'kt'
28 | 
29 |         Operator:                  "#582800",   # class: 'o'
30 |         Operator.Word:             "bold #004461",   # class: 'ow' - like keywords
31 | 
32 |         Punctuation:               "bold #000000",   # class: 'p'
33 | 
34 |         # because special names such as Name.Class, Name.Function, etc.
35 |         # are not recognized as such later in the parsing, we choose them
36 |         # to look the same as ordinary variables.
37 |         Name:                      "#000000",        # class: 'n'
38 |         Name.Attribute:            "#c4a000",        # class: 'na' - to be revised
39 |         Name.Builtin:              "#004461",        # class: 'nb'
40 |         Name.Builtin.Pseudo:       "#3465a4",        # class: 'bp'
41 |         Name.Class:                "#000000",        # class: 'nc' - to be revised
42 |         Name.Constant:             "#000000",        # class: 'no' - to be revised
43 |         Name.Decorator:            "#888",           # class: 'nd' - to be revised
44 |         Name.Entity:               "#ce5c00",        # class: 'ni'
45 |         Name.Exception:            "bold #cc0000",   # class: 'ne'
46 |         Name.Function:             "#000000",        # class: 'nf'
47 |         Name.Property:             "#000000",        # class: 'py'
48 |         Name.Label:                "#f57900",        # class: 'nl'
49 |         Name.Namespace:            "#000000",        # class: 'nn' - to be revised
50 |         Name.Other:                "#000000",        # class: 'nx'
51 |         Name.Tag:                  "bold #004461",   # class: 'nt' - like a keyword
52 |         Name.Variable:             "#000000",        # class: 'nv' - to be revised
53 |         Name.Variable.Class:       "#000000",        # class: 'vc' - to be revised
54 |         Name.Variable.Global:      "#000000",        # class: 'vg' - to be revised
55 |         Name.Variable.Instance:    "#000000",        # class: 'vi' - to be revised
56 | 
57 |         Number:                    "#990000",        # class: 'm'
58 | 
59 |         Literal:                   "#000000",        # class: 'l'
60 |         Literal.Date:              "#000000",        # class: 'ld'
61 | 
62 |         String:                    "#4e9a06",        # class: 's'
63 |         String.Backtick:           "#4e9a06",        # class: 'sb'
64 |         String.Char:               "#4e9a06",        # class: 'sc'
65 |         String.Doc:                "italic #8f5902", # class: 'sd' - like a comment
66 |         String.Double:             "#4e9a06",        # class: 's2'
67 |         String.Escape:             "#4e9a06",        # class: 'se'
68 |         String.Heredoc:            "#4e9a06",        # class: 'sh'
69 |         String.Interpol:           "#4e9a06",        # class: 'si'
70 |         String.Other:              "#4e9a06",        # class: 'sx'
71 |         String.Regex:              "#4e9a06",        # class: 'sr'
72 |         String.Single:             "#4e9a06",        # class: 's1'
73 |         String.Symbol:             "#4e9a06",        # class: 'ss'
74 | 
75 |         Generic:                   "#000000",        # class: 'g'
76 |         Generic.Deleted:           "#a40000",        # class: 'gd'
77 |         Generic.Emph:              "italic #000000", # class: 'ge'
78 |         Generic.Error:             "#ef2929",        # class: 'gr'
79 |         Generic.Heading:           "bold #000080",   # class: 'gh'
80 |         Generic.Inserted:          "#00A000",        # class: 'gi'
81 |         Generic.Output:            "#888",           # class: 'go'
82 |         Generic.Prompt:            "#745334",        # class: 'gp'
83 |         Generic.Strong:            "bold #000000",   # class: 'gs'
84 |         Generic.Subheading:        "bold #800080",   # class: 'gu'
85 |         Generic.Traceback:         "bold #a40000",   # class: 'gt'
86 |     }
87 | 


--------------------------------------------------------------------------------
/docs/_themes/alabaster/theme.conf:
--------------------------------------------------------------------------------
 1 | [theme]
 2 | inherit = basic
 3 | stylesheet = alabaster.css
 4 | pygments_style = alabaster.support.Alabaster
 5 | 
 6 | [options]
 7 | logo =
 8 | logo_name = false
 9 | logo_text_align = left
10 | description =
11 | description_font_style = normal
12 | github_user =
13 | github_repo =
14 | github_button = true
15 | github_banner = false
16 | github_type = watch
17 | github_count = true
18 | travis_button = false
19 | codecov_button = false
20 | gratipay_user =
21 | gittip_user =
22 | analytics_id =
23 | touch_icon =
24 | extra_nav_links =
25 | sidebar_includehidden = true
26 | show_powered_by = true
27 | show_related = false
28 | 
29 | gray_1 = #444
30 | gray_2 = #EEE
31 | gray_3 = #AAA
32 | 
33 | pink_1 = #FCC
34 | pink_2 = #FAA
35 | 
36 | body_text = #3E4349
37 | body_text_align = left
38 | footer_text = #888
39 | link = #004B6B
40 | link_hover = #6D4100
41 | sidebar_header =
42 | sidebar_text = #555
43 | sidebar_link =
44 | sidebar_link_underscore = #999
45 | sidebar_search_button = #CCC
46 | sidebar_list = #000
47 | sidebar_hr =
48 | anchor = #DDD
49 | anchor_hover_fg =
50 | anchor_hover_bg = #EAEAEA
51 | note_bg =
52 | note_border = #CCC
53 | seealso_bg =
54 | seealso_border = #CCC
55 | warn_bg =
56 | warn_border =
57 | footnote_bg = #FDFDFD
58 | footnote_border =
59 | pre_bg =
60 | narrow_sidebar_bg = #333
61 | narrow_sidebar_fg = #FFF
62 | narrow_sidebar_link =
63 | font_size = 17px
64 | caption_font_size = inherit
65 | code_font_size = 0.9em
66 | code_font_family = 'Consolas', 'Menlo', 'Deja Vu Sans Mono', 'Bitstream Vera Sans Mono', monospace
67 | font_family = 'goudy old style', 'minion pro', 'bell mt', Georgia, 'Hiragino Mincho Pro', serif
68 | head_font_family = 'Garamond', 'Georgia', serif
69 | caption_font_family = inherit
70 | code_highlight = #FFC
71 | page_width = 940px
72 | sidebar_width = 220px
73 | fixed_sidebar = false
74 | 


--------------------------------------------------------------------------------
/docs/authors.rst:
--------------------------------------------------------------------------------
1 | .. include:: ../AUTHORS.rst


--------------------------------------------------------------------------------
/docs/conf.py:
--------------------------------------------------------------------------------
 1 | from os.path import join
 2 | from datetime import datetime
 3 | 
 4 | import sys
 5 | import os
 6 | 
 7 | # Alabaster theme + mini-extension
 8 | sys.path.append(os.path.abspath('_themes'))
 9 | html_theme_path = ['_themes']
10 | extensions = ['alabaster']
11 | 
12 | # Paths relative to invoking conf.py - not this shared file
13 | html_static_path = ['_shared_static']
14 | html_theme = 'alabaster'
15 | html_theme_options = {
16 |     'logo': 'logo.jpg',
17 |     'logo_name': True,
18 |     'logo_text_align': 'center',
19 |     'description': "Simplifying the process of extracting data from XML, so you can get on with more useful stuff",
20 |     'github_user': 'spurin',
21 |     'github_repo': 'xmldataset',
22 |     'github_type': 'star',
23 |     'github_banner': True,
24 |     'travis_button': True,
25 | 
26 |     'link': '#3782BE',
27 |     'link_hover': '#3782BE',
28 | }
29 | html_sidebars = {
30 |     '**': [
31 |         'about.html',
32 |         'navigation.html',
33 |         'searchbox.html',
34 |         'donate.html',
35 |     ]
36 | }
37 | 
38 | # Regular settings
39 | project = 'xmldataset'
40 | year = datetime.now().year
41 | copyright = '%d James Spurin' % year
42 | master_doc = 'index'
43 | templates_path = ['_templates']
44 | exclude_trees = ['_build']
45 | source_suffix = '.rst'
46 | default_role = 'obj'
47 | 


--------------------------------------------------------------------------------
/docs/contributing.rst:
--------------------------------------------------------------------------------
1 | .. include:: ../CONTRIBUTING.rst


--------------------------------------------------------------------------------
/docs/history.rst:
--------------------------------------------------------------------------------
1 | .. include:: ../HISTORY.rst


--------------------------------------------------------------------------------
/docs/index.rst:
--------------------------------------------------------------------------------
  1 | .. complexity documentation master file, created by
  2 |    sphinx-quickstart on Tue Jul  9 22:26:36 2013.
  3 |    You can adapt this file completely to your liking, but it should at least
  4 |    contain the root `toctree` directive.
  5 | 
  6 | xmldataset: simple xml parsing
  7 | ======================================
  8 | 
  9 | .. toctree::
 10 |    :hidden:
 11 | 
 12 | A Python library that simplifies the extraction of datasets from XML content.
 13 | 
 14 | XML is a simple markup format.  Whilst simple, extracting data of interest is often more complicated than it needs to be.
 15 | 
 16 | **xmldataset** addresses this through an easy to use plaintext declaration that follows the structure of the XML document.  The declaration is indented, matching the XML structure, the data we are interested in is tagged against a dataset.
 17 | 
 18 | Take for example, an XML document that lists colleagues:
 19 | 
 20 | ::
 21 | 
 22 |    # Declare XML
 23 |    xml = """<?xml version="1.0"?>
 24 |    <colleagues>
 25 |        <colleague>
 26 |            <title>The Boss</title>
 27 |            <phone>+1 202-663-9108</phone>
 28 |            <email>boss@the_company.com</email>
 29 |        </colleague>
 30 |        <colleague>
 31 |            <title>Admin Assistant</title>
 32 |            <phone>+1 347-999-5454</phone>
 33 |            <email>admin@the_company.com</email>
 34 |        </colleague>
 35 |        <colleague>
 36 |            <title>Minion</title>
 37 |            <phone>+1 792-123-4109</phone>
 38 |            <email>minion@the_company.com</email>
 39 |        </colleague>
 40 |    </colleagues>"""
 41 | 
 42 | 
 43 | To capture the title, email and phone for each colleague, it is simple, using xmldataset:
 44 | 
 45 | ::
 46 | 
 47 |    import xmldataset
 48 | 
 49 |    # xmldataset declaration
 50 |    profile = """
 51 |    colleagues
 52 |        colleague
 53 |            title = dataset:colleagues
 54 |            phone = dataset:colleagues
 55 |            email = dataset:colleagues"""
 56 | 
 57 |    # Print the output
 58 |    print(xmldataset.parse_using_profile(xml, profile))
 59 | 
 60 | Resulting in the following output:
 61 | 
 62 | ::
 63 | 
 64 |    {   'colleagues': [   {   'email': 'boss@the_company.com',
 65 |                              'phone': '+1 202-663-9108',
 66 |                              'title': 'The Boss'},
 67 |                          {   'email': 'admin@the_company.com',
 68 |                              'phone': '+1 347-999-5454',
 69 |                              'title': 'Admin Assistant'},
 70 |                          {   'email': 'minion@the_company.com',
 71 |                              'phone': '+1 792-123-4109',
 72 |                              'title': 'Minion'}]}
 73 | 
 74 | Features
 75 | --------
 76 | 
 77 | * Handles missing data from the XML structure, if it's missing in the XML it is not populated in the dataset
 78 | * Handles both XML Elements and Attributes using the plaintext collection schema (attributes are depicted as a sublevel of an element)
 79 | * Easy to rename XML attributes/elements during processing to meet your requirements
 80 | * Inline manipulation of XML content through the process mechanism
 81 | * Dispatch mechanism, allows datasets to be dispatched for every N instance to allow asynchronous processing
 82 | 
 83 | 
 84 | Contents
 85 | --------
 86 | 
 87 | .. toctree::
 88 |    :maxdepth: 2
 89 | 
 90 |    installation
 91 |    quickstart
 92 |    contributing
 93 |    authors
 94 |    history
 95 | 
 96 | Contributors
 97 | ============
 98 | 
 99 | ``xmldataset`` is written and maintained by `James Spurin <https://github.com/james.spurin>`_,  The module stands on the shoulders of giants with it's use of ElementTree and cElementTree as the core XML parser.
100 | 
101 | Thanks go to the following for their feedback and improvements:
102 | 
103 | * KleinerNull
104 | * keluc
105 | * basaldella
106 | * davidmarcano
107 | * href
108 | 


--------------------------------------------------------------------------------
/docs/installation.rst:
--------------------------------------------------------------------------------
1 | ============
2 | Installation
3 | ============
4 | 
5 | At the command line::
6 | 
7 |     $ pip install xmldataset
8 | 


--------------------------------------------------------------------------------
/docs/make.bat:
--------------------------------------------------------------------------------
  1 | @ECHO OFF
  2 | 
  3 | REM Command file for Sphinx documentation
  4 | 
  5 | if "%SPHINXBUILD%" == "" (
  6 | 	set SPHINXBUILD=sphinx-build
  7 | )
  8 | set BUILDDIR=_build
  9 | set ALLSPHINXOPTS=-d %BUILDDIR%/doctrees %SPHINXOPTS% .
 10 | set I18NSPHINXOPTS=%SPHINXOPTS% .
 11 | if NOT "%PAPER%" == "" (
 12 | 	set ALLSPHINXOPTS=-D latex_paper_size=%PAPER% %ALLSPHINXOPTS%
 13 | 	set I18NSPHINXOPTS=-D latex_paper_size=%PAPER% %I18NSPHINXOPTS%
 14 | )
 15 | 
 16 | if "%1" == "" goto help
 17 | 
 18 | if "%1" == "help" (
 19 | 	:help
 20 | 	echo.Please use `make ^<target^>` where ^<target^> is one of
 21 | 	echo.  html       to make standalone HTML files
 22 | 	echo.  dirhtml    to make HTML files named index.html in directories
 23 | 	echo.  singlehtml to make a single large HTML file
 24 | 	echo.  pickle     to make pickle files
 25 | 	echo.  json       to make JSON files
 26 | 	echo.  htmlhelp   to make HTML files and a HTML help project
 27 | 	echo.  qthelp     to make HTML files and a qthelp project
 28 | 	echo.  devhelp    to make HTML files and a Devhelp project
 29 | 	echo.  epub       to make an epub
 30 | 	echo.  latex      to make LaTeX files, you can set PAPER=a4 or PAPER=letter
 31 | 	echo.  text       to make text files
 32 | 	echo.  man        to make manual pages
 33 | 	echo.  texinfo    to make Texinfo files
 34 | 	echo.  gettext    to make PO message catalogs
 35 | 	echo.  changes    to make an overview over all changed/added/deprecated items
 36 | 	echo.  xml        to make Docutils-native XML files
 37 | 	echo.  pseudoxml  to make pseudoxml-XML files for display purposes
 38 | 	echo.  linkcheck  to check all external links for integrity
 39 | 	echo.  doctest    to run all doctests embedded in the documentation if enabled
 40 | 	goto end
 41 | )
 42 | 
 43 | if "%1" == "clean" (
 44 | 	for /d %%i in (%BUILDDIR%\*) do rmdir /q /s %%i
 45 | 	del /q /s %BUILDDIR%\*
 46 | 	goto end
 47 | )
 48 | 
 49 | 
 50 | %SPHINXBUILD% 2> nul
 51 | if errorlevel 9009 (
 52 | 	echo.
 53 | 	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
 54 | 	echo.installed, then set the SPHINXBUILD environment variable to point
 55 | 	echo.to the full path of the 'sphinx-build' executable. Alternatively you
 56 | 	echo.may add the Sphinx directory to PATH.
 57 | 	echo.
 58 | 	echo.If you don't have Sphinx installed, grab it from
 59 | 	echo.http://sphinx-doc.org/
 60 | 	exit /b 1
 61 | )
 62 | 
 63 | if "%1" == "html" (
 64 | 	%SPHINXBUILD% -b html %ALLSPHINXOPTS% %BUILDDIR%/html
 65 | 	if errorlevel 1 exit /b 1
 66 | 	echo.
 67 | 	echo.Build finished. The HTML pages are in %BUILDDIR%/html.
 68 | 	goto end
 69 | )
 70 | 
 71 | if "%1" == "dirhtml" (
 72 | 	%SPHINXBUILD% -b dirhtml %ALLSPHINXOPTS% %BUILDDIR%/dirhtml
 73 | 	if errorlevel 1 exit /b 1
 74 | 	echo.
 75 | 	echo.Build finished. The HTML pages are in %BUILDDIR%/dirhtml.
 76 | 	goto end
 77 | )
 78 | 
 79 | if "%1" == "singlehtml" (
 80 | 	%SPHINXBUILD% -b singlehtml %ALLSPHINXOPTS% %BUILDDIR%/singlehtml
 81 | 	if errorlevel 1 exit /b 1
 82 | 	echo.
 83 | 	echo.Build finished. The HTML pages are in %BUILDDIR%/singlehtml.
 84 | 	goto end
 85 | )
 86 | 
 87 | if "%1" == "pickle" (
 88 | 	%SPHINXBUILD% -b pickle %ALLSPHINXOPTS% %BUILDDIR%/pickle
 89 | 	if errorlevel 1 exit /b 1
 90 | 	echo.
 91 | 	echo.Build finished; now you can process the pickle files.
 92 | 	goto end
 93 | )
 94 | 
 95 | if "%1" == "json" (
 96 | 	%SPHINXBUILD% -b json %ALLSPHINXOPTS% %BUILDDIR%/json
 97 | 	if errorlevel 1 exit /b 1
 98 | 	echo.
 99 | 	echo.Build finished; now you can process the JSON files.
100 | 	goto end
101 | )
102 | 
103 | if "%1" == "htmlhelp" (
104 | 	%SPHINXBUILD% -b htmlhelp %ALLSPHINXOPTS% %BUILDDIR%/htmlhelp
105 | 	if errorlevel 1 exit /b 1
106 | 	echo.
107 | 	echo.Build finished; now you can run HTML Help Workshop with the ^
108 | .hhp project file in %BUILDDIR%/htmlhelp.
109 | 	goto end
110 | )
111 | 
112 | if "%1" == "qthelp" (
113 | 	%SPHINXBUILD% -b qthelp %ALLSPHINXOPTS% %BUILDDIR%/qthelp
114 | 	if errorlevel 1 exit /b 1
115 | 	echo.
116 | 	echo.Build finished; now you can run "qcollectiongenerator" with the ^
117 | .qhcp project file in %BUILDDIR%/qthelp, like this:
118 | 	echo.^> qcollectiongenerator %BUILDDIR%\qthelp\complexity.qhcp
119 | 	echo.To view the help file:
120 | 	echo.^> assistant -collectionFile %BUILDDIR%\qthelp\complexity.ghc
121 | 	goto end
122 | )
123 | 
124 | if "%1" == "devhelp" (
125 | 	%SPHINXBUILD% -b devhelp %ALLSPHINXOPTS% %BUILDDIR%/devhelp
126 | 	if errorlevel 1 exit /b 1
127 | 	echo.
128 | 	echo.Build finished.
129 | 	goto end
130 | )
131 | 
132 | if "%1" == "epub" (
133 | 	%SPHINXBUILD% -b epub %ALLSPHINXOPTS% %BUILDDIR%/epub
134 | 	if errorlevel 1 exit /b 1
135 | 	echo.
136 | 	echo.Build finished. The epub file is in %BUILDDIR%/epub.
137 | 	goto end
138 | )
139 | 
140 | if "%1" == "latex" (
141 | 	%SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex
142 | 	if errorlevel 1 exit /b 1
143 | 	echo.
144 | 	echo.Build finished; the LaTeX files are in %BUILDDIR%/latex.
145 | 	goto end
146 | )
147 | 
148 | if "%1" == "latexpdf" (
149 | 	%SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex
150 | 	cd %BUILDDIR%/latex
151 | 	make all-pdf
152 | 	cd %BUILDDIR%/..
153 | 	echo.
154 | 	echo.Build finished; the PDF files are in %BUILDDIR%/latex.
155 | 	goto end
156 | )
157 | 
158 | if "%1" == "latexpdfja" (
159 | 	%SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex
160 | 	cd %BUILDDIR%/latex
161 | 	make all-pdf-ja
162 | 	cd %BUILDDIR%/..
163 | 	echo.
164 | 	echo.Build finished; the PDF files are in %BUILDDIR%/latex.
165 | 	goto end
166 | )
167 | 
168 | if "%1" == "text" (
169 | 	%SPHINXBUILD% -b text %ALLSPHINXOPTS% %BUILDDIR%/text
170 | 	if errorlevel 1 exit /b 1
171 | 	echo.
172 | 	echo.Build finished. The text files are in %BUILDDIR%/text.
173 | 	goto end
174 | )
175 | 
176 | if "%1" == "man" (
177 | 	%SPHINXBUILD% -b man %ALLSPHINXOPTS% %BUILDDIR%/man
178 | 	if errorlevel 1 exit /b 1
179 | 	echo.
180 | 	echo.Build finished. The manual pages are in %BUILDDIR%/man.
181 | 	goto end
182 | )
183 | 
184 | if "%1" == "texinfo" (
185 | 	%SPHINXBUILD% -b texinfo %ALLSPHINXOPTS% %BUILDDIR%/texinfo
186 | 	if errorlevel 1 exit /b 1
187 | 	echo.
188 | 	echo.Build finished. The Texinfo files are in %BUILDDIR%/texinfo.
189 | 	goto end
190 | )
191 | 
192 | if "%1" == "gettext" (
193 | 	%SPHINXBUILD% -b gettext %I18NSPHINXOPTS% %BUILDDIR%/locale
194 | 	if errorlevel 1 exit /b 1
195 | 	echo.
196 | 	echo.Build finished. The message catalogs are in %BUILDDIR%/locale.
197 | 	goto end
198 | )
199 | 
200 | if "%1" == "changes" (
201 | 	%SPHINXBUILD% -b changes %ALLSPHINXOPTS% %BUILDDIR%/changes
202 | 	if errorlevel 1 exit /b 1
203 | 	echo.
204 | 	echo.The overview file is in %BUILDDIR%/changes.
205 | 	goto end
206 | )
207 | 
208 | if "%1" == "linkcheck" (
209 | 	%SPHINXBUILD% -b linkcheck %ALLSPHINXOPTS% %BUILDDIR%/linkcheck
210 | 	if errorlevel 1 exit /b 1
211 | 	echo.
212 | 	echo.Link check complete; look for any errors in the above output ^
213 | or in %BUILDDIR%/linkcheck/output.txt.
214 | 	goto end
215 | )
216 | 
217 | if "%1" == "doctest" (
218 | 	%SPHINXBUILD% -b doctest %ALLSPHINXOPTS% %BUILDDIR%/doctest
219 | 	if errorlevel 1 exit /b 1
220 | 	echo.
221 | 	echo.Testing of doctests in the sources finished, look at the ^
222 | results in %BUILDDIR%/doctest/output.txt.
223 | 	goto end
224 | )
225 | 
226 | if "%1" == "xml" (
227 | 	%SPHINXBUILD% -b xml %ALLSPHINXOPTS% %BUILDDIR%/xml
228 | 	if errorlevel 1 exit /b 1
229 | 	echo.
230 | 	echo.Build finished. The XML files are in %BUILDDIR%/xml.
231 | 	goto end
232 | )
233 | 
234 | if "%1" == "pseudoxml" (
235 | 	%SPHINXBUILD% -b pseudoxml %ALLSPHINXOPTS% %BUILDDIR%/pseudoxml
236 | 	if errorlevel 1 exit /b 1
237 | 	echo.
238 | 	echo.Build finished. The pseudo-XML files are in %BUILDDIR%/pseudoxml.
239 | 	goto end
240 | )
241 | 
242 | :end


--------------------------------------------------------------------------------
/docs/master.zip:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/spurin/xmldataset/958a4884a46c950f331546bae02ecb0a7cbbc77a/docs/master.zip


--------------------------------------------------------------------------------
/docs/modules.rst:
--------------------------------------------------------------------------------
1 | xmldataset
2 | ==========
3 | 
4 | .. toctree::
5 |    :maxdepth: 4
6 | 
7 |    xmldataset
8 | 


--------------------------------------------------------------------------------
/docs/quickstart.rst:
--------------------------------------------------------------------------------
  1 | 
  2 | Quickstart
  3 | ==========
  4 | 
  5 | 
  6 | Hi, welcome to the quick-start tutorial.
  7 | 
  8 | Installing xmldataset
  9 | ----------------------
 10 | 
 11 | Use pip to install xmldataset ::
 12 | 
 13 |    pip install xmldataset
 14 | 
 15 | Configuring xmldataset
 16 | ----------------------
 17 | 
 18 | To get started, you need to import the xmldataset package :) ::
 19 | 
 20 |    import xmldataset
 21 | 
 22 | Configuring pretty print
 23 | ------------------------
 24 | 
 25 | For these examples, it is worth using the pretty print module as this provides a great way of validating the returned results.  Configure this as follows:
 26 | 
 27 | ::
 28 | 
 29 |    import pprint
 30 | 
 31 |    # Setup Pretty Printing
 32 |    ppsetup = pprint.PrettyPrinter(indent=4)
 33 |    pp = ppsetup.pprint
 34 | 
 35 | Adding XML content
 36 | ------------------
 37 | 
 38 | We need some XML to work with, all of the examples will use the same XML although the profile will change to depict different behaviour.  Set the XML
 39 | up as follows:
 40 | 
 41 | ::
 42 | 
 43 |    xml = """<?xml version="1.0"?>
 44 |      <catalog>
 45 |         <shop number="1">
 46 |            <book id="bk101">
 47 |               <author>Gambardella, Matthew</author>
 48 |               <title>XML Developer's Guide</title>
 49 |               <genre>Computer</genre>
 50 |               <price>44.95</price>
 51 |               <publish_date>2000-10-01</publish_date>
 52 |               <description>An in-depth look at creating applications 
 53 |               with XML.</description>
 54 |            </book>
 55 |            <book id="bk102">
 56 |               <author>Ralls, Kim</author>
 57 |               <title>Midnight Rain</title>
 58 |               <genre>Fantasy</genre>
 59 |               <price>5.95</price>
 60 |               <publish_date>2000-12-16</publish_date>
 61 |               <description>A former architect battles corporate zombies, 
 62 |               an evil sorceress, and her own childhood to become queen 
 63 |               of the world.</description>
 64 |            </book>
 65 |         </shop>
 66 |         <shop number="2">
 67 |            <book id="bk103">
 68 |               <author>Corets, Eva</author>
 69 |               <title>Maeve Ascendant</title>
 70 |               <genre>Fantasy</genre>
 71 |               <price>5.95</price>
 72 |               <publish_date>2000-11-17</publish_date>
 73 |               <description>After the collapse of a nanotechnology 
 74 |               society in England, the young survivors lay the 
 75 |               foundation for a new society.</description>
 76 |            </book>
 77 |            <book id="bk104">
 78 |               <author>Corets, Eva</author>
 79 |               <title>Oberon's Legacy</title>
 80 |               <genre>Fantasy</genre>
 81 |               <price>5.95</price>
 82 |               <publish_date>2001-03-10</publish_date>
 83 |               <description>In post-apocalypse England, the mysterious 
 84 |               agent known only as Oberon helps to create a new life 
 85 |               for the inhabitants of London. Sequel to Maeve 
 86 |               Ascendant.</description>
 87 |            </book>
 88 |         </shop>
 89 |      </catalog>"""
 90 | 
 91 | Example 1 - Extracting the title and author from the dataset
 92 | ------------------------------------------------------------
 93 | 
 94 | Configure the profile, according to the XML, we need to step down past
 95 | the element catalog, shop and book before we reach author and title.
 96 | 
 97 | We can then specify that author and title are stored in the dataset **title_and_author**:
 98 | 
 99 | ::
100 | 
101 |    profile="""
102 |    catalog
103 |        shop
104 |            book
105 |                author = dataset:title_and_author
106 |                title  = dataset:title_and_author"""
107 | 
108 | Running this results in the following output:
109 | 
110 | ::
111 | 
112 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
113 |                                    'title': "XML Developer's Guide"},
114 |                                {   'author': 'Ralls, Kim',
115 |                                    'title': 'Midnight Rain'},
116 |                                {   'author': 'Corets, Eva',
117 |                                    'title': 'Maeve Ascendant'},
118 |                                {   'author': 'Corets, Eva',
119 |                                    'title': "Oberon's Legacy"}]}
120 | 
121 | Example 2 - Working with multiple datasets
122 | ------------------------------------------
123 | 
124 | Let's say we want to expand our collection so that we also capture the
125 | title and genre.  This can be done quite simply by updating the profile
126 | to include an additional dataset for title and a definition for genre:
127 | 
128 | ::
129 | 
130 |    profile="""
131 |    catalog
132 |        shop
133 |            book
134 |                author = dataset:title_and_author
135 |                title  = dataset:title_and_author dataset:title_and_genre
136 |                genre  = dataset:title_and_genre"""
137 | 
138 | With this executed, we now have an additional dataset of title_and_genre as
139 | well as the original title_and_author:
140 | 
141 | ::
142 | 
143 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
144 |                                 'title': "XML Developer's Guide"},
145 |                             {   'author': 'Ralls, Kim',
146 |                                 'title': 'Midnight Rain'},
147 |                             {   'author': 'Corets, Eva',
148 |                                 'title': 'Maeve Ascendant'},
149 |                             {   'author': 'Corets, Eva',
150 |                                 'title': "Oberon's Legacy"}],
151 |     'title_and_genre': [   {   'genre': 'Computer',
152 |                                'title': "XML Developer's Guide"},
153 |                            {   'genre': 'Fantasy', 'title': 'Midnight Rain'},
154 |                            {   'genre': 'Fantasy', 'title': 'Maeve Ascendant'},
155 |                            {   'genre': 'Fantasy', 'title': "Oberon's Legacy"}]}
156 | 
157 | Example 3 - Handling XML attributes
158 | -----------------------------------
159 | 
160 | XML Attributes are treated in the profile as a sub level key/value in the profile. The following example depicts the inclusion of the attribute 'id' in the returned datasets. Note how id is indented under book and on the same level as author, title, genre etc:
161 | 
162 | ::
163 | 
164 |    profile="""
165 |    catalog
166 |        shop
167 |            book
168 |                id     = dataset:title_and_author dataset:title_and_genre
169 |                author = dataset:title_and_author
170 |                title  = dataset:title_and_author dataset:title_and_genre
171 |                genre  = dataset:title_and_genre"""
172 | 
173 | With the following output:
174 | 
175 | ::
176 | 
177 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
178 |                                    'id': 'bk101',
179 |                                    'title': "XML Developer's Guide"},
180 |                                {   'author': 'Ralls, Kim',
181 |                                    'id': 'bk102',
182 |                                    'title': 'Midnight Rain'},
183 |                                {   'author': 'Corets, Eva',
184 |                                    'id': 'bk103',
185 |                                    'title': 'Maeve Ascendant'},
186 |                                {   'author': 'Corets, Eva',
187 |                                    'id': 'bk104',
188 |                                    'title': "Oberon's Legacy"}],
189 |        'title_and_genre': [   {   'genre': 'Computer',
190 |                                   'id': 'bk101',
191 |                                   'title': "XML Developer's Guide"},
192 |                               {   'genre': 'Fantasy',
193 |                                   'id': 'bk102',
194 |                                   'title': 'Midnight Rain'},
195 |                               {   'genre': 'Fantasy',
196 |                                   'id': 'bk103',
197 |                                   'title': 'Maeve Ascendant'},
198 |                               {   'genre': 'Fantasy',
199 |                                   'id': 'bk104',
200 |                                   'title': "Oberon's Legacy"}]}
201 | 
202 | Example 4 - Using higher level data across datasets
203 | ---------------------------------------------------
204 | 
205 | Note how the 'number' attribute is at a higher level than the existing data that we have captured.  Owning to it's hierachial position, this data may be of relevence to the datasets formed below.
206 | 
207 | Information that is available at a higher level to that of the specified dataset information can be referenced and included in datasets using a combination of the external_dataset and __EXTERNAL_VALUE__ markers.
208 | 
209 | The external_dataset marker informs the parser to store the information for later use. It follows the format of external_dataset:<target> where <target> is a reference name that identifies the external store.
210 | 
211 | The __EXTERNAL_VALUE__ marker informs the parser to reference a value that is or will be stored externally. It follows the format of __EXTERNAL_VALUE__ = <external_store>:<external_value>:<target_dataset>
212 | 
213 | ::
214 | 
215 |    profile="""
216 |    catalog
217 |        shop
218 |            number     = external_dataset:shop_information
219 |            book
220 |                id     = dataset:title_and_author dataset:title_and_genre
221 |                author = dataset:title_and_author
222 |                title  = dataset:title_and_author dataset:title_and_genre
223 |                genre  = dataset:title_and_genre
224 |                __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
225 | 
226 | Produces the following, n.b. the change of number for books 3 and 4 on each dataset:
227 | 
228 | ::
229 | 
230 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
231 |                                    'id': 'bk101',
232 |                                    'number': '1',
233 |                                    'title': "XML Developer's Guide"},
234 |                                {   'author': 'Ralls, Kim',
235 |                                    'id': 'bk102',
236 |                                    'number': '1',
237 |                                    'title': 'Midnight Rain'},
238 |                                {   'author': 'Corets, Eva',
239 |                                    'id': 'bk103',
240 |                                    'number': '2',
241 |                                    'title': 'Maeve Ascendant'},
242 |                                {   'author': 'Corets, Eva',
243 |                                    'id': 'bk104',
244 |                                    'number': '2',
245 |                                    'title': "Oberon's Legacy"}],
246 |        'title_and_genre': [   {   'genre': 'Computer',
247 |                                   'id': 'bk101',
248 |                                   'number': '1',
249 |                                   'title': "XML Developer's Guide"},
250 |                               {   'genre': 'Fantasy',
251 |                                   'id': 'bk102',
252 |                                   'number': '1',
253 |                                   'title': 'Midnight Rain'},
254 |                               {   'genre': 'Fantasy',
255 |                                   'id': 'bk103',
256 |                                   'number': '2',
257 |                                   'title': 'Maeve Ascendant'},
258 |                               {   'genre': 'Fantasy',
259 |                                   'id': 'bk104',
260 |                                   'number': '2',
261 |                                   'title': "Oberon's Legacy"}]}
262 | 
263 | Example 5 - Optional Dataset Parameters: name
264 | ---------------------------------------------
265 | 
266 | Dataset declarations can receive additional parameters through comma seperated inclusions. In this example the XML element of 'genre' is renamed to 'style' during processing using the name declaration.
267 | 
268 | ::
269 | 
270 |    profile="""
271 |    catalog
272 |        shop
273 |            number     = external_dataset:shop_information
274 |            book
275 |                id     = dataset:title_and_author dataset:title_and_genre
276 |                author = dataset:title_and_author
277 |                title  = dataset:title_and_author dataset:title_and_genre
278 |                genre  = dataset:title_and_genre,name:style
279 |                __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
280 | 
281 | Within the dataset title_and_genre, the keyword 'genre' is now changed to 'style':
282 | 
283 | ::
284 |    
285 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
286 |                                    'id': 'bk101',
287 |                                    'number': '1',
288 |                                    'title': "XML Developer's Guide"},
289 |                                {   'author': 'Ralls, Kim',
290 |                                    'id': 'bk102',
291 |                                    'number': '1',
292 |                                    'title': 'Midnight Rain'},
293 |                                {   'author': 'Corets, Eva',
294 |                                    'id': 'bk103',
295 |                                    'number': '2',
296 |                                    'title': 'Maeve Ascendant'},
297 |                                {   'author': 'Corets, Eva',
298 |                                    'id': 'bk104',
299 |                                    'number': '2',
300 |                                    'title': "Oberon's Legacy"}],
301 |        'title_and_genre': [   {   'id': 'bk101',
302 |                                   'number': '1',
303 |                                   'style': 'Computer',
304 |                                   'title': "XML Developer's Guide"},
305 |                               {   'id': 'bk102',
306 |                                   'number': '1',
307 |                                   'style': 'Fantasy',
308 |                                   'title': 'Midnight Rain'},
309 |                               {   'id': 'bk103',
310 |                                   'number': '2',
311 |                                   'style': 'Fantasy',
312 |                                   'title': 'Maeve Ascendant'},
313 |                               {   'id': 'bk104',
314 |                                   'number': '2',
315 |                                   'style': 'Fantasy',
316 |                                   'title': "Oberon's Legacy"}]}
317 | 
318 | Example 6 - Optional Dataset Parameters: prefix
319 | -----------------------------------------------
320 | 
321 | The prefix declaration assigns a prefix to the assignment name, for example genre with a prefix of shop_information_ will become shop_information_genre
322 | 
323 | For consistency, in this example, the external information of name uses the additional optional parameter of :<override_name> as mentioned in Example 4 to override the external name
324 | 
325 | ::
326 | 
327 |    profile="""
328 |    catalog
329 |        shop
330 |            number     = external_dataset:shop_information
331 |            book
332 |                id     = dataset:title_and_author,prefix:shop_information_ dataset:title_and_genre,prefix:shop_information_
333 |                author = dataset:title_and_author,prefix:shop_information_
334 |                title  = dataset:title_and_author,prefix:shop_information_ dataset:title_and_genre,prefix:shop_information_,prefix:shop_information_
335 |                genre  = dataset:title_and_genre,prefix:shop_information_
336 |                __EXTERNAL_VALUE__ = shop_information:number:title_and_author:shop_information_number shop_information:number:title_and_genre:shop_information_number"""
337 | 
338 | 
339 | Resulting in the following:
340 | 
341 | ::
342 |    
343 |    {   'title_and_author': [   {   'shop_information_author': 'Gambardella, Matthew',
344 |                                    'shop_information_id': 'bk101',
345 |                                    'shop_information_number': '1',
346 |                                    'shop_information_title': "XML Developer's Guide"},
347 |                                {   'shop_information_author': 'Ralls, Kim',
348 |                                    'shop_information_id': 'bk102',
349 |                                    'shop_information_number': '1',
350 |                                    'shop_information_title': 'Midnight Rain'},
351 |                                {   'shop_information_author': 'Corets, Eva',
352 |                                    'shop_information_id': 'bk103',
353 |                                    'shop_information_number': '2',
354 |                                    'shop_information_title': 'Maeve Ascendant'},
355 |                                {   'shop_information_author': 'Corets, Eva',
356 |                                    'shop_information_id': 'bk104',
357 |                                    'shop_information_number': '2',
358 |                                    'shop_information_title': "Oberon's Legacy"}],
359 |        'title_and_genre': [   {   'shop_information_genre': 'Computer',
360 |                                   'shop_information_id': 'bk101',
361 |                                   'shop_information_number': '1',
362 |                                   'shop_information_title': "XML Developer's Guide"},
363 |                               {   'shop_information_genre': 'Fantasy',
364 |                                   'shop_information_id': 'bk102',
365 |                                   'shop_information_number': '1',
366 |                                   'shop_information_title': 'Midnight Rain'},
367 |                               {   'shop_information_genre': 'Fantasy',
368 |                                   'shop_information_id': 'bk103',
369 |                                   'shop_information_number': '2',
370 |                                   'shop_information_title': 'Maeve Ascendant'},
371 |                               {   'shop_information_genre': 'Fantasy',
372 |                                   'shop_information_id': 'bk104',
373 |                                   'shop_information_number': '2',
374 |                                   'shop_information_title': "Oberon's Legacy"}]}
375 | 
376 | Example 7 - Optional Dataset Parameters: process
377 | ------------------------------------------------
378 | 
379 | The process parameter can be used for inline manipulation of data. In this example the author is passed through a simple subroutine that returns an uppercase value.
380 | 
381 | The parser expects methods specified by the process to be passed by the parse_using_profile method as per the example:
382 | 
383 | ::
384 | 
385 |    def to_upper(value):
386 |        return value.upper()
387 | 
388 |    profile="""
389 |    catalog
390 |        shop
391 |            number     = external_dataset:shop_information
392 |            book
393 |                id     = dataset:title_and_author dataset:title_and_genre
394 |                author = dataset:title_and_author,process:to_upper
395 |                title  = dataset:title_and_author dataset:title_and_genre
396 |                genre  = dataset:title_and_genre,name:style
397 |                __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
398 | 
399 |    # Pretty Print the output
400 |    output = xmldataset.parse_using_profile(xml,profile, process = { 'to_upper' : to_upper })
401 |    pp(output)
402 | 
403 | We've specifically targetted the dataset title_and_author for the author value to be processed through **to_upper**:
404 | 
405 | ::
406 | 
407 |    {   'title_and_author': [   {   'author': 'GAMBARDELLA, MATTHEW',
408 |                                    'id': 'bk101',
409 |                                    'number': '1',
410 |                                    'title': "XML Developer's Guide"},
411 |                                {   'author': 'RALLS, KIM',
412 |                                    'id': 'bk102',
413 |                                    'number': '1',
414 |                                    'title': 'Midnight Rain'},
415 |                                {   'author': 'CORETS, EVA',
416 |                                    'id': 'bk103',
417 |                                    'number': '2',
418 |                                    'title': 'Maeve Ascendant'},
419 |                                {   'author': 'CORETS, EVA',
420 |                                    'id': 'bk104',
421 |                                    'number': '2',
422 |                                    'title': "Oberon's Legacy"}],
423 |        'title_and_genre': [   {   'id': 'bk101',
424 |                                   'number': '1',
425 |                                   'style': 'Computer',
426 |                                   'title': "XML Developer's Guide"},
427 |                               {   'id': 'bk102',
428 |                                   'number': '1',
429 |                                   'style': 'Fantasy',
430 |                                   'title': 'Midnight Rain'},
431 |                               {   'id': 'bk103',
432 |                                   'number': '2',
433 |                                   'style': 'Fantasy',
434 |                                   'title': 'Maeve Ascendant'},
435 |                               {   'id': 'bk104',
436 |                                   'number': '2',
437 |                                   'style': 'Fantasy',
438 |                                   'title': "Oberon's Legacy"}]}
439 | 
440 | Example 8 - Hinting for new datasets
441 | ------------------------------------
442 | 
443 | During processing, the parser looks for indicators that it should create a new dataset. As an example, when new data is encountered rather than overriding the existing data, a new dataset is created. Unfortunately this may lead to unexpected results when working with poorly structured input where subsets of information may be missing from the XML structure.
444 | 
445 | To mitigate this, the hint __NEW_DATASET__ = <dataset> is available to force the creation of a new dataset upon entering a block.
446 | 
447 | If there are any concerns about the consistency of the XML document then it is recommended that the __NEW_DATASET__ declaration is made within all respective blocks as part of the profile definition.
448 | 
449 | ::
450 | 
451 |    profile="""
452 |    catalog
453 |        shop
454 |            number     = external_dataset:shop_information
455 |            book
456 |                __NEW_DATASET__ = title_and_author title_and_genre
457 |                id     = dataset:title_and_author dataset:title_and_genre
458 |                author = dataset:title_and_author
459 |                title  = dataset:title_and_author dataset:title_and_genre
460 |                genre  = dataset:title_and_genre,name:style
461 |                __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
462 | 
463 | Output as follows:
464 | 
465 | ::
466 | 
467 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
468 |                                    'id': 'bk101',
469 |                                    'number': '1',
470 |                                    'title': "XML Developer's Guide"},
471 |                                {   'author': 'Ralls, Kim',
472 |                                    'id': 'bk102',
473 |                                    'number': '1',
474 |                                    'title': 'Midnight Rain'},
475 |                                {   'author': 'Corets, Eva',
476 |                                    'id': 'bk103',
477 |                                    'number': '2',
478 |                                    'title': 'Maeve Ascendant'},
479 |                                {   'author': 'Corets, Eva',
480 |                                    'id': 'bk104',
481 |                                    'number': '2',
482 |                                    'title': "Oberon's Legacy"}],
483 |        'title_and_genre': [   {   'id': 'bk101',
484 |                                   'number': '1',
485 |                                   'style': 'Computer',
486 |                                   'title': "XML Developer's Guide"},
487 |                               {   'id': 'bk102',
488 |                                   'number': '1',
489 |                                   'style': 'Fantasy',
490 |                                   'title': 'Midnight Rain'},
491 |                               {   'id': 'bk103',
492 |                                   'number': '2',
493 |                                   'style': 'Fantasy',
494 |                                   'title': 'Maeve Ascendant'},
495 |                               {   'id': 'bk104',
496 |                                   'number': '2',
497 |                                   'style': 'Fantasy',
498 |                                   'title': "Oberon's Legacy"}]}
499 | 
500 | Example 9 - Dispatching datasets
501 | --------------------------------
502 | 
503 | Datasets can be dispatched during processing.  This is beneficial especially where memory is concerned as the datasets can be handed off to another method and processed as opposed to filling up
504 | memory before being returned.  The __generic__ keyword allows you to target all datasets:
505 | 
506 | ::
507 | 
508 |    profile="""
509 |    catalog
510 |        shop
511 |            number     = external_dataset:shop_information
512 |            book
513 |                id     = dataset:title_and_author dataset:title_and_genre
514 |                author = dataset:title_and_author
515 |                title  = dataset:title_and_author dataset:title_and_genre
516 |                genre  = dataset:title_and_genre,name:style
517 |                __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
518 | 
519 |    def print_dataset(value):
520 |        pp(value)
521 | 
522 |    # Pretty Print the output
523 |    output = xmldataset.parse_using_profile(xml,profile, dispatch = { 
524 |            '__generic__' : { 
525 |                    'counter' : 2, 
526 |                    'coderef' : print_dataset 
527 |            } 
528 |    })
529 | 
530 | 
531 | As the counter is set to 2, every dataset is passed as an object to the print_dataset method, note how each array now holds 2 entries:
532 | 
533 | 
534 | ::
535 |    
536 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
537 |                                    'id': 'bk101',
538 |                                    'number': '1',
539 |                                    'title': "XML Developer's Guide"},
540 |                                {   'author': 'Ralls, Kim',
541 |                                    'id': 'bk102',
542 |                                    'number': '1',
543 |                                    'title': 'Midnight Rain'}]}
544 |    {   'title_and_genre': [   {   'id': 'bk101',
545 |                                   'number': '1',
546 |                                   'style': 'Computer',
547 |                                   'title': "XML Developer's Guide"},
548 |                               {   'id': 'bk102',
549 |                                   'number': '1',
550 |                                   'style': 'Fantasy',
551 |                                   'title': 'Midnight Rain'}]}
552 |    {   'title_and_genre': [   {   'id': 'bk103',
553 |                                   'number': '2',
554 |                                   'style': 'Fantasy',
555 |                                   'title': 'Maeve Ascendant'},
556 |                               {   'id': 'bk104',
557 |                                   'number': '2',
558 |                                   'style': 'Fantasy',
559 |                                   'title': "Oberon's Legacy"}]}
560 |    {   'title_and_author': [   {   'author': 'Corets, Eva',
561 |                                    'id': 'bk103',
562 |                                    'number': '2',
563 |                                    'title': 'Maeve Ascendant'},
564 |                                {   'author': 'Corets, Eva',
565 |                                    'id': 'bk104',
566 |                                    'number': '2',
567 |                                    'title': "Oberon's Legacy"}]}
568 | 
569 | Example 10 - Dispatching multiple datasets
570 | ------------------------------------------
571 | 
572 | It is possible to dispatch datasets to different methods or to specify dataset specific counters:
573 | 
574 | ::
575 | 
576 |    profile="""
577 |    catalog
578 |        shop
579 |            number     = external_dataset:shop_information
580 |            book
581 |                id     = dataset:title_and_author dataset:title_and_genre
582 |                author = dataset:title_and_author
583 |                title  = dataset:title_and_author dataset:title_and_genre
584 |                genre  = dataset:title_and_genre,name:style
585 |                __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
586 | 
587 |    def print_dataset(value):
588 |        pp(value)
589 | 
590 |    # Pretty Print the output
591 |    output = xmldataset.parse_using_profile(xml,profile, dispatch = { 
592 |            'title_and_author' : { 
593 |                    'counter' : 2, 
594 |                    'coderef' : print_dataset 
595 |            }, 
596 |            'title_and_genre' : { 
597 |                    'counter' : 3, 
598 |                    'coderef' : print_dataset 
599 |            } 
600 |    })
601 | 
602 | 
603 | As the title_and_genre is now dispatching 3 datasets, it's final dump is of a single dataset for the remaining entry:
604 | 
605 | :: 
606 | 
607 |    {   'title_and_author': [   {   'author': 'Gambardella, Matthew',
608 |                                    'id': 'bk101',
609 |                                    'number': '1',
610 |                                    'title': "XML Developer's Guide"},
611 |                                {   'author': 'Ralls, Kim',
612 |                                    'id': 'bk102',
613 |                                    'number': '1',
614 |                                    'title': 'Midnight Rain'}]}
615 |    {   'title_and_genre': [   {   'id': 'bk101',
616 |                                   'number': '1',
617 |                                   'style': 'Computer',
618 |                                   'title': "XML Developer's Guide"},
619 |                               {   'id': 'bk102',
620 |                                   'number': '1',
621 |                                   'style': 'Fantasy',
622 |                                   'title': 'Midnight Rain'},
623 |                               {   'id': 'bk103',
624 |                                   'number': '2',
625 |                                   'style': 'Fantasy',
626 |                                   'title': 'Maeve Ascendant'}]}
627 |    {   'title_and_genre': [   {   'id': 'bk104',
628 |                                   'number': '2',
629 |                                   'style': 'Fantasy',
630 |                                   'title': "Oberon's Legacy"}]}
631 |    {   'title_and_author': [   {   'author': 'Corets, Eva',
632 |                                    'id': 'bk103',
633 |                                    'number': '2',
634 |                                    'title': 'Maeve Ascendant'},
635 |                                {   'author': 'Corets, Eva',
636 |                                    'id': 'bk104',
637 |                                    'number': '2',
638 |                                    'title': "Oberon's Legacy"}]}
639 | 
640 | Example 11 - Using xmldataset as an input to pandas
641 | ------------------------------------------
642 | 
643 | Thanks to keluc for this one, xmldataset works well as an input to pandas with the from_records method
644 | 
645 | ::
646 | 
647 |    result = xmldataset.parse_using_profile(xml, profile)
648 |    df = pd.DataFrame.from_records(result['...'])
649 | 


--------------------------------------------------------------------------------
/docs/readme.rst:
--------------------------------------------------------------------------------
1 | .. include:: ../README.rst


--------------------------------------------------------------------------------
/docs/usage.rst:
--------------------------------------------------------------------------------
1 | ========
2 | Usage
3 | ========
4 | 
5 | To use XML Dataset in a project::
6 | 
7 | 	import xmldataset


--------------------------------------------------------------------------------
/docs/xmldataset.rst:
--------------------------------------------------------------------------------
 1 | xmldataset package
 2 | ==================
 3 | 
 4 | Module contents
 5 | ---------------
 6 | 
 7 | .. automodule:: xmldataset
 8 |     :members:
 9 |     :undoc-members:
10 |     :show-inheritance:
11 | 


--------------------------------------------------------------------------------
/examples/example1.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         book
60 |             author = dataset:title_and_author
61 |             title  = dataset:title_and_author""" 
62 | 
63 | # Pretty Print the output
64 | output = xmldataset.parse_using_profile(xml,profile)
65 | pp(output)
66 | 


--------------------------------------------------------------------------------
/examples/example10.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         number     = external_dataset:shop_information
60 |         book
61 |             __NEW_DATASET__ = title_and_author title_and_genre
62 |             id     = dataset:title_and_author dataset:title_and_genre
63 |             author = dataset:title_and_author
64 |             title  = dataset:title_and_author dataset:title_and_genre
65 |             genre  = dataset:title_and_genre,name:style
66 |             __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
67 | 
68 | def print_dataset(value):
69 |     pp(value)
70 | 
71 | # Pretty Print the output
72 | output = xmldataset.parse_using_profile(xml,profile, dispatch = { 
73 |         'title_and_author' : { 
74 |                 'counter' : 2, 
75 |                 'coderef' : print_dataset 
76 |         }, 
77 |         'title_and_genre' : { 
78 |                 'counter' : 3, 
79 |                 'coderef' : print_dataset 
80 |         } 
81 | })
82 | 


--------------------------------------------------------------------------------
/examples/example2.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         book
60 |             author = dataset:title_and_author
61 |             title  = dataset:title_and_author dataset:title_and_genre
62 |             genre  = dataset:title_and_genre"""
63 | 
64 | # Pretty Print the output
65 | output = xmldataset.parse_using_profile(xml,profile)
66 | pp(output)
67 | 


--------------------------------------------------------------------------------
/examples/example3.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         book
60 |             id     = dataset:title_and_author dataset:title_and_genre
61 |             author = dataset:title_and_author
62 |             title  = dataset:title_and_author dataset:title_and_genre
63 |             genre  = dataset:title_and_genre"""
64 | 
65 | # Pretty Print the output
66 | output = xmldataset.parse_using_profile(xml,profile)
67 | pp(output)
68 | 


--------------------------------------------------------------------------------
/examples/example4.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         number     = external_dataset:shop_information
60 |         book
61 |             id     = dataset:title_and_author dataset:title_and_genre
62 |             author = dataset:title_and_author
63 |             title  = dataset:title_and_author dataset:title_and_genre
64 |             genre  = dataset:title_and_genre
65 |             __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
66 | 
67 | # Pretty Print the output
68 | output = xmldataset.parse_using_profile(xml,profile)
69 | pp(output)
70 | 


--------------------------------------------------------------------------------
/examples/example5.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         number     = external_dataset:shop_information
60 |         book
61 |             id     = dataset:title_and_author dataset:title_and_genre
62 |             author = dataset:title_and_author
63 |             title  = dataset:title_and_author dataset:title_and_genre
64 |             genre  = dataset:title_and_genre,name:style
65 |             __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
66 | 
67 | # Pretty Print the output
68 | output = xmldataset.parse_using_profile(xml,profile)
69 | pp(output)
70 | 


--------------------------------------------------------------------------------
/examples/example6.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         number     = external_dataset:shop_information
60 |         book
61 |             id     = dataset:title_and_author,prefix:shop_information_ dataset:title_and_genre,prefix:shop_information_
62 |             author = dataset:title_and_author,prefix:shop_information_
63 |             title  = dataset:title_and_author,prefix:shop_information_ dataset:title_and_genre,prefix:shop_information_,prefix:shop_information_
64 |             genre  = dataset:title_and_genre,prefix:shop_information_
65 |             __EXTERNAL_VALUE__ = shop_information:number:title_and_author:shop_information_number shop_information:number:title_and_genre:shop_information_number"""
66 | 
67 | # Pretty Print the output
68 | output = xmldataset.parse_using_profile(xml,profile)
69 | pp(output)
70 | 


--------------------------------------------------------------------------------
/examples/example7.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | def to_upper(value):
57 |     return value.upper()
58 | 
59 | profile="""
60 | catalog
61 |     shop
62 |         number     = external_dataset:shop_information
63 |         book
64 |             id     = dataset:title_and_author dataset:title_and_genre
65 |             author = dataset:title_and_author,process:to_upper
66 |             title  = dataset:title_and_author dataset:title_and_genre
67 |             genre  = dataset:title_and_genre,name:style
68 |             __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
69 | 
70 | # Pretty Print the output
71 | output = xmldataset.parse_using_profile(xml,profile, process = { 'to_upper' : to_upper })
72 | pp(output)
73 | 


--------------------------------------------------------------------------------
/examples/example8.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         number     = external_dataset:shop_information
60 |         book
61 |             __NEW_DATASET__ = title_and_author title_and_genre
62 |             id     = dataset:title_and_author dataset:title_and_genre
63 |             author = dataset:title_and_author
64 |             title  = dataset:title_and_author dataset:title_and_genre
65 |             genre  = dataset:title_and_genre,name:style
66 |             __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
67 | 
68 | # Pretty Print the output
69 | output = xmldataset.parse_using_profile(xml,profile)
70 | pp(output)
71 | 


--------------------------------------------------------------------------------
/examples/example9.py:
--------------------------------------------------------------------------------
 1 | import xmldataset
 2 | import pprint
 3 | 
 4 | # Setup Pretty Printing
 5 | ppsetup = pprint.PrettyPrinter(indent=4)
 6 | pp = ppsetup.pprint
 7 | 
 8 | xml = """<?xml version="1.0"?>
 9 |   <catalog>
10 |      <shop number="1">
11 |         <book id="bk101">
12 |            <author>Gambardella, Matthew</author>
13 |            <title>XML Developer's Guide</title>
14 |            <genre>Computer</genre>
15 |            <price>44.95</price>
16 |            <publish_date>2000-10-01</publish_date>
17 |            <description>An in-depth look at creating applications
18 |            with XML.</description>
19 |         </book>
20 |         <book id="bk102">
21 |            <author>Ralls, Kim</author>
22 |            <title>Midnight Rain</title>
23 |            <genre>Fantasy</genre>
24 |            <price>5.95</price>
25 |            <publish_date>2000-12-16</publish_date>
26 |            <description>A former architect battles corporate zombies,
27 |            an evil sorceress, and her own childhood to become queen
28 |            of the world.</description>
29 |         </book>
30 |      </shop>
31 |      <shop number="2">
32 |         <book id="bk103">
33 |            <author>Corets, Eva</author>
34 |            <title>Maeve Ascendant</title>
35 |            <genre>Fantasy</genre>
36 |            <price>5.95</price>
37 |            <publish_date>2000-11-17</publish_date>
38 |            <description>After the collapse of a nanotechnology
39 |            society in England, the young survivors lay the
40 |            foundation for a new society.</description>
41 |         </book>
42 |         <book id="bk104">
43 |            <author>Corets, Eva</author>
44 |            <title>Oberon's Legacy</title>
45 |            <genre>Fantasy</genre>
46 |            <price>5.95</price>
47 |            <publish_date>2001-03-10</publish_date>
48 |            <description>In post-apocalypse England, the mysterious
49 |            agent known only as Oberon helps to create a new life
50 |            for the inhabitants of London. Sequel to Maeve
51 |            Ascendant.</description>
52 |         </book>
53 |      </shop>
54 |   </catalog>"""
55 | 
56 | profile="""
57 | catalog
58 |     shop
59 |         number     = external_dataset:shop_information
60 |         book
61 |             __NEW_DATASET__ = title_and_author title_and_genre
62 |             id     = dataset:title_and_author dataset:title_and_genre
63 |             author = dataset:title_and_author
64 |             title  = dataset:title_and_author dataset:title_and_genre
65 |             genre  = dataset:title_and_genre,name:style
66 |             __EXTERNAL_VALUE__ = shop_information:number:title_and_author shop_information:number:title_and_genre"""
67 | 
68 | def print_dataset(value):
69 |     pp(value)
70 | 
71 | # Pretty Print the output
72 | output = xmldataset.parse_using_profile(xml,profile, dispatch = { 
73 |         '__generic__' : { 
74 |                 'counter' : 2, 
75 |                 'coderef' : print_dataset 
76 |         } 
77 | })
78 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | wheel
2 | 


--------------------------------------------------------------------------------
/setup.cfg:
--------------------------------------------------------------------------------
1 | [wheel]
2 | universal = 1


--------------------------------------------------------------------------------
/setup.py:
--------------------------------------------------------------------------------
 1 | #!/usr/bin/env python
 2 | # -*- coding: utf-8 -*-
 3 | 
 4 | import os
 5 | import sys
 6 | 
 7 | try:
 8 |     from setuptools import setup
 9 | except ImportError:
10 |     from distutils.core import setup
11 | 
12 | if sys.argv[-1] == 'publish':
13 |     os.system('python setup.py sdist upload')
14 |     sys.exit()
15 | 
16 | readme = open('README.rst').read()
17 | history = open('HISTORY.rst').read().replace('.. :changelog:', '')
18 | 
19 | setup(
20 |     name='xmldataset',
21 |     version='1.0.4',
22 |     description='XML Dataset: xml parsing made easy',
23 |     long_description=readme + '\n\n' + history,
24 |     author='James Spurin',
25 |     author_email='james@spurin.com',
26 |     url='https://github.com/spurin/xmldataset',
27 |     packages=[
28 |         'xmldataset',
29 |     ],
30 |     package_dir={'xmldataset': 'xmldataset'},
31 |     include_package_data=True,
32 |     install_requires=[
33 |     ],
34 |     license="BSD",
35 |     zip_safe=False,
36 |     keywords='xmldataset',
37 |     classifiers=[
38 |         'Development Status :: 5 - Production/Stable',
39 |         'Intended Audience :: Developers',
40 |         'License :: OSI Approved :: BSD License',
41 |         'Natural Language :: English',
42 |         "Programming Language :: Python :: 2",
43 |         'Programming Language :: Python :: 3',
44 |     ],
45 |     test_suite='tests',
46 | )
47 | 


--------------------------------------------------------------------------------
/tests/__init__.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python
2 | # -*- coding: utf-8 -*-
3 | 


--------------------------------------------------------------------------------
/tox.ini:
--------------------------------------------------------------------------------
 1 | [tox]
 2 | envlist = py26, py27, py31, py32, py33, py34, py35, py36, py37, py38, pypy
 3 | 
 4 | [testenv]
 5 | setenv =
 6 |     PYTHONPATH = {toxinidir}:{toxinidir}/xmldataset
 7 | commands = 
 8 |         python setup.py test
 9 | deps =
10 |     -r{toxinidir}/requirements.txt
11 | 
12 | [testenv:py26]
13 | setenv =
14 |     PYTHONPATH = {toxinidir}:{toxinidir}/xmldataset
15 | deps =
16 |     -r{toxinidir}/requirements.txt
17 |     unittest2
18 | 
19 | [testenv:coverage]
20 | basepython = python2.7
21 | setenv =
22 |     PYTHONPATH = {toxinidir}:{toxinidir}/xmldataset
23 | commands = 
24 |         coverage run --source xmldataset setup.py test
25 |         coverage combine
26 |         coverage report --include=* -m
27 | deps =
28 |     coverage
29 | 


--------------------------------------------------------------------------------
/xmldataset/__init__.py:
--------------------------------------------------------------------------------
  1 | """ Extracts XML into Python Datasets based upon a simple text profile markup language """
  2 | 
  3 | # -*- coding: utf-8 -*-
  4 | # pylint: disable=line-too-long
  5 | 
  6 | __author__ = "James Spurin"
  7 | __email__ = "james@spurin.com"
  8 | __version__ = "1.0.1"
  9 | 
 10 | import re
 11 | import logging
 12 | 
 13 | # Attempt to use cElementTree, otherwise fall back on ElementTree
 14 | try:
 15 |     import xml.etree.cElementTree as ET
 16 | except ImportError:
 17 |     import xml.etree.ElementTree as ET
 18 | 
 19 | # class _XMLDataset
 20 | class _XMLDataset:  # pylint: disable=R0902,R0903
 21 |     """Internal class used as parsing handler"""
 22 | 
 23 |     def __init__(self, options):
 24 |         """Object initialisation"""
 25 | 
 26 |         # Store supplied options in object
 27 |         self.__dict__ = options
 28 | 
 29 |         # Create an internal logging object
 30 |         self.logger = logging.getLogger("default")
 31 |         self.logger.setLevel(logging.DEBUG)
 32 | 
 33 |         # Set the depth as 0, used to track the depth of the XML position
 34 |         self._depth = 0
 35 | 
 36 |         # Store for Profiles
 37 |         self._profiles = []
 38 | 
 39 |         # Store for Current Data
 40 |         self.current_data = {}
 41 | 
 42 |         # Store for Data Structure
 43 |         self.data_structure = {}
 44 | 
 45 |         # Store for External Data
 46 |         self.external_data = {}
 47 | 
 48 |     def _expand_profile(self, profile_input):
 49 |         """Expands the supplied profile to a python data structure"""
 50 | 
 51 |         # Declare the Indentation History as starting at 0
 52 |         indentation_history = [0]
 53 | 
 54 |         # Profile holders
 55 |         complex_profile = {}
 56 |         complex_profile_history = [complex_profile]
 57 |         current_profile_position = complex_profile_history[-1]
 58 | 
 59 |         # Capture available tokens from the profile input using a carriage return
 60 |         # as a separator
 61 |         tokens = profile_input.split("\n")
 62 | 
 63 |         # Process each token
 64 |         for token in tokens:
 65 | 
 66 |             # Declare holders for the length_indentation and token_data
 67 |             length_indentation = None
 68 |             token_data = None
 69 | 
 70 |             # Attempt to match token with indentation
 71 |             match = re.search("(\s+)(.*)", token)  # pylint: disable=W1401
 72 | 
 73 |             # If a match is found capture the indentation and the token_data
 74 |             if match:
 75 |                 length_indentation = len(match.group(1))
 76 |                 token_data = match.group(2).strip()
 77 |             # Otherwise mark the indentation as 0 and remove any carriage returns from
 78 |             # the token_data
 79 |             else:
 80 |                 length_indentation = 0
 81 |                 token_data = token.strip()
 82 | 
 83 |             # If token data is available
 84 |             if token_data:
 85 | 
 86 |                 # Store the previous_indentation information
 87 |                 previous_indentation = indentation_history[-1]
 88 | 
 89 |                 # If the indentation has increased, store the indentation in the history
 90 |                 if length_indentation > previous_indentation:
 91 |                     indentation_history.append(length_indentation)
 92 | 
 93 |                 # Otherwise if the indentation has decreased
 94 |                 elif previous_indentation > length_indentation:
 95 | 
 96 |                     # Step back through the indentation
 97 |                     while previous_indentation > length_indentation:
 98 |                         indentation_history.pop()
 99 |                         previous_indentation = indentation_history[-1]
100 | 
101 |                         # ... And the associated history
102 |                         complex_profile_history.pop()
103 |                         current_profile_position = complex_profile_history[-1]
104 | 
105 |                 # If the token contains a value ( signified by an = sign )
106 |                 if "=" in token_data:
107 | 
108 |                     # Capture the key and the record_holder
109 |                     key, record_holder = token_data.split("=")
110 | 
111 |                     # Remove leading and ending space using strip() for the key and record_holder
112 |                     key = key.strip()
113 |                     record_holder = record_holder.strip()
114 | 
115 |                     # Check for an Ignore marker
116 |                     if record_holder == "__IGNORE__":
117 | 
118 |                         if key not in current_profile_position:
119 |                             current_profile_position[key] = {}
120 | 
121 |                         current_profile_position[key]["__IGNORE__"] = 1
122 | 
123 |                     # Otherwise continue
124 |                     else:
125 | 
126 |                         # Split unprocessed records
127 |                         records_unprocessed = record_holder.split(" ")
128 | 
129 |                         # Capture New Dataset markers where available
130 |                         if key == "__NEW_DATASET__":
131 |                             current_profile_position[
132 |                                 "__NEW_DATASET__"
133 |                             ] = records_unprocessed
134 | 
135 |                         # Otherwise Capture External Values where available
136 |                         elif key == "__EXTERNAL_VALUE__":
137 |                             current_profile_position[
138 |                                 "__EXTERNAL_VALUE__"
139 |                             ] = records_unprocessed
140 | 
141 |                         # Otherwise Capture New External Values where available
142 |                         elif key == "__NEW_EXTERNAL_VALUE_HOLDER__":
143 |                             current_profile_position[
144 |                                 "__NEW_EXTERNAL_VALUE_HOLDER__"
145 |                             ] = records_unprocessed
146 | 
147 |                         # Otherwise Capture Processing markers where available
148 |                         elif key == "__DATASET_PROCESSING__":
149 |                             current_profile_position[
150 |                                 "__DATASET_PROCESSING__"
151 |                             ] = records_unprocessed
152 | 
153 |                         # Otherwise Capture Always Follow markers where available
154 |                         elif key == "__ALWAYS_FOLLOW__":
155 |                             current_profile_position[
156 |                                 "__ALWAYS_FOLLOW__"
157 |                             ] = records_unprocessed
158 | 
159 |                         # Otherwise ....
160 |                         else:
161 | 
162 |                             # Add an order processing sequence to the profile, create where necessary
163 |                             # or append
164 |                             if "__order__" not in current_profile_position:
165 |                                 current_profile_position["__order__"] = [key]
166 |                             else:
167 |                                 if key not in current_profile_position["__order__"]:
168 |                                     current_profile_position["__order__"].append(key)
169 | 
170 |                             # Process records_unprocessed
171 |                             for record_unprocessed in records_unprocessed:
172 | 
173 |                                 # Add the key
174 |                                 if key not in current_profile_position:
175 |                                     current_profile_position[key] = {}
176 | 
177 |                                 # Create the record holder or append a new record
178 |                                 if "__record__" not in current_profile_position[key]:
179 |                                     current_profile_position[key]["__record__"] = [{}]
180 |                                 else:
181 |                                     current_profile_position[key]["__record__"].append(
182 |                                         {}
183 |                                     )
184 | 
185 |                                 # Process each record
186 |                                 for record in record_unprocessed.split(","):
187 |                                     record_key, record_value = record.split(":")
188 |                                     current_profile_position[key]["__record__"][-1][
189 |                                         record_key
190 |                                     ] = record_value
191 | 
192 |                 # If the token does not contain an = sign
193 |                 else:
194 | 
195 |                     # Create a named dictionary
196 |                     holder = {}
197 | 
198 |                     # Store the named dictionary as the current token
199 |                     current_profile_position[token_data] = holder
200 | 
201 |                     # Add an order processing sequence
202 |                     if "__order__" not in current_profile_position:
203 |                         current_profile_position["__order__"] = [token_data]
204 |                     else:
205 |                         if token_data not in current_profile_position["__order__"]:
206 |                             current_profile_position["__order__"].append(token_data)
207 | 
208 |                     # Update the current position to the named dict
209 |                     current_profile_position = holder
210 | 
211 |                     # Add to the current history
212 |                     complex_profile_history.append(holder)
213 | 
214 |         # Return the complex profile
215 |         return complex_profile
216 | 
217 |     def _process_record(self, record, name, value):
218 |         """Logic for processing each record"""
219 | 
220 |         # If a custom name has been provided use accordingly, otherwise use name
221 |         name = record["name"] if "name" in record else name
222 | 
223 |         # If a prefix has been provided use accordingly
224 |         name = record["prefix"] + name if "prefix" in record else name
225 | 
226 |         # If a process handler has been specified call accordingly
227 |         if "process" in record:
228 | 
229 |             # Capture the coderef from the object
230 |             coderef = None
231 | 
232 |             if hasattr(self, "process"):
233 |                 if record["process"] in self.process:
234 |                     value = self.process[record["process"]](value)
235 |                 else:
236 |                     raise Exception("process coderef " + record["process"] + " missing")
237 |             else:
238 |                 raise Exception("process definition not supplied as argument")
239 | 
240 |         # If the record contains a dataset
241 |         if "dataset" in record:
242 | 
243 |             # Check if the current dataset doesn't exist or if the key in question already exists
244 |             # If so, create a new data_structure holder
245 |             if (
246 |                 not record["dataset"] in self.data_structure
247 |                 or name in self.data_structure[record["dataset"]][-1]
248 |             ):
249 | 
250 |                 # Dispatch existing data
251 |                 self._dispatch_dataset(record["dataset"])
252 | 
253 |                 # If the current dataset does not exist in the data structure add
254 |                 # a new entry holder
255 |                 if record["dataset"] not in self.data_structure:
256 |                     self.data_structure[record["dataset"]] = [{}]
257 |                 else:
258 |                     self.data_structure[record["dataset"]].append({})
259 | 
260 |                 # If global_values are defined, add them to the dataset
261 |                 if hasattr(self, "global_values"):
262 |                     self.data_structure[record["dataset"]][-1].update(
263 |                         self.global_values
264 |                     )
265 | 
266 |             # Add the value to the holder
267 |             self.data_structure[record["dataset"]][-1][name] = value
268 | 
269 |         # If the record contains an external_dataset
270 |         if "external_dataset" in record:
271 | 
272 |             # If the external dataset doesn't exist in the data structure add accordingly
273 |             if record["external_dataset"] not in self.external_data:
274 |                 self.external_data[record["external_dataset"]] = {}
275 | 
276 |             # If the holder doesn't exist, add accordingly, add a default value of ''
277 |             if name not in self.external_data[record["external_dataset"]]:
278 |                 self.external_data[record["external_dataset"]][name] = [""]
279 | 
280 |             # Store the data, if the last entry equals '', update otherwise append as
281 |             # a new value
282 |             if self.external_data[record["external_dataset"]][name][-1] == "":
283 |                 self.external_data[record["external_dataset"]][name][-1] = value
284 |             else:
285 |                 self.external_data[record["external_dataset"]][name].append(value)
286 | 
287 |     def _dispatch_all(self):
288 |         """Dispatch all datasets"""
289 | 
290 |         if hasattr(self, "dispatch"):
291 |             dataset_list = []
292 | 
293 |             # Make a list of dataset keys without referencing the original values
294 |             for dataset in self.data_structure.keys():
295 |                 dataset_list.append(str(dataset))
296 | 
297 |             # Dispatch each dataset.  This approach of separately capturing keys prior to
298 |             # processing was taken as the iterator complains about the list changing
299 |             # during processing ( owing to the del method used in _dispatch_dataset )
300 |             for dataset in dataset_list:
301 |                 self._dispatch_dataset(dataset, flush=1)
302 | 
303 |     def _dispatch_dataset(self, dataset, flush=0):
304 |         """Dispatch datasets"""
305 | 
306 |         # Set a default trigger and code holder
307 |         counter_trigger = 0
308 |         counter_coderef = None
309 | 
310 |         # If the object contains dispatch logic
311 |         if hasattr(self, "dispatch"):
312 | 
313 |             # Check for dataset specific dispatch
314 |             if dataset in self.dispatch:
315 |                 if "counter" in self.dispatch[dataset]:
316 |                     counter_trigger = self.dispatch[dataset]["counter"]
317 | 
318 |             # Check for a generic dispatch counter
319 |             elif "__generic__" in self.dispatch:
320 |                 if "counter" in self.dispatch["__generic__"]:
321 |                     counter_trigger = self.dispatch["__generic__"]["counter"]
322 | 
323 |             # Check for dataset specific code
324 |             if dataset in self.dispatch:
325 |                 if "coderef" in self.dispatch[dataset]:
326 |                     counter_coderef = self.dispatch[dataset]["coderef"]
327 | 
328 |             # Check for a generic dispatch code
329 |             elif "__generic__" in self.dispatch:
330 |                 if "coderef" in self.dispatch["__generic__"]:
331 |                     counter_coderef = self.dispatch["__generic__"]["coderef"]
332 | 
333 |             # If we have enough records, dispatch accordingly
334 |             if dataset in self.data_structure:
335 |                 if len(self.data_structure[dataset]) >= counter_trigger or flush:
336 | 
337 |                     # Call the coderef with the payload, send as dict with dataset value
338 |                     counter_coderef({dataset: self.data_structure[dataset]})
339 | 
340 |                     # Delete the datastructure
341 |                     del self.data_structure[dataset]
342 | 
343 |     def _process_data(self, xml_root):
344 |         """Process data"""
345 | 
346 |         def process_element():
347 |             """ Process Elements """
348 | 
349 |             # Store the previous element if applicable
350 |             self._previous_key = (
351 |                 self._current_key if hasattr(self, "_current_key") else ""
352 |             )
353 | 
354 |             # Store the current element name
355 |             self._current_key = xml_root.tag
356 | 
357 |             # Move to the appropriate profile for the correct depth
358 |             while self._profiles and len(self._profiles) > self._depth:
359 |                 self._profile = self._profiles.pop()
360 | 
361 |             # Check if the key is in the profile
362 |             if self._current_key in self._profile:
363 | 
364 |                 # Store the old profile
365 |                 self._profiles.append(self._profile)
366 | 
367 |                 # Update the profile to the current key
368 |                 self._profile = self._profile[self._current_key]
369 | 
370 |                 # Skip if __IGNORE__
371 |                 if "__IGNORE__" in self._profile:
372 |                     next
373 | 
374 |                 # Otherwise continue
375 |                 else:
376 | 
377 |                     # If an external value has been specified
378 |                     if "__NEW_EXTERNAL_VALUE_HOLDER__" in self._profile:
379 |                         for dataset in self._profile["__NEW_EXTERNAL_VALUE_HOLDER__"]:
380 | 
381 |                             # Holder for __EXTERNAL_REFERENCES__
382 |                             values = dataset.split(":")
383 |                             ext_dataset = values[0]
384 |                             ext_name = values[1]
385 | 
386 |                             # Delete the existing value
387 |                             if ext_dataset in self.external_data:
388 |                                 if ext_name in self.external_data[ext_dataset]:
389 |                                     del self.external_data[ext_dataset][ext_name]
390 |                                     # self.external_data[ext_dataset][ext_name].append('')
391 | 
392 |                     # If a new dataset has been specified
393 |                     if "__NEW_DATASET__" in self._profile:
394 |                         for dataset in self._profile["__NEW_DATASET__"]:
395 | 
396 |                             # Dispatch existing datasets
397 |                             self._dispatch_dataset(dataset)
398 | 
399 |                             # Create the dataset if it doesn't already exist
400 |                             if dataset not in self.data_structure:
401 |                                 self.data_structure[dataset] = [{}]
402 |                             else:
403 |                                 self.data_structure[dataset].append({})
404 | 
405 |                     # Process records where available, i.e. found in the same layer
406 |                     if "__record__" in self._profile:
407 | 
408 |                         # Process each record
409 |                         for record in self._profile["__record__"]:
410 |                             self._process_record(record, xml_root.tag, xml_root.text)
411 | 
412 |                     # Walk path based on order
413 |                     if "__order__" in self._profile:
414 |                         for order_value in self._profile["__order__"]:
415 | 
416 |                             # Match Marker
417 |                             match = 0
418 | 
419 |                             # Check attributes against order_value
420 |                             if order_value in xml_root.attrib:
421 |                                 match = 1
422 | 
423 |                                 # If the attribute has a profile entry, process each record
424 |                                 if order_value in self._profile:
425 |                                     if "__record__" in self._profile[order_value]:
426 | 
427 |                                         # Process each record
428 |                                         for record in self._profile[order_value][
429 |                                             "__record__"
430 |                                         ]:
431 |                                             self._process_record(
432 |                                                 record,
433 |                                                 order_value,
434 |                                                 xml_root.attrib[order_value],
435 |                                             )
436 | 
437 |                             # List all available elements and look for a match against order_value
438 |                             for element in xml_root:
439 |                                 if order_value == element.tag:
440 |                                     match = 1
441 | 
442 |                                     # Increase the depth as we follow
443 |                                     self._depth += 1
444 | 
445 |                                     # Follow Element
446 |                                     self._process_data(element)
447 | 
448 |                                     # Decrease the depth as we exit
449 |                                     self._depth -= 1
450 | 
451 |                                     # Pop the last profile
452 |                                     self._profile = self._profiles.pop()
453 | 
454 |                             # If there is not a match, check for defaults
455 |                             if not match:
456 | 
457 |                                 def extract_defaults(order_value, profile_loop):
458 | 
459 |                                     # If its a record, process it if a default value is set
460 |                                     if "__record__" in profile_loop[order_value]:
461 |                                         for record in profile_loop[order_value][
462 |                                             "__record__"
463 |                                         ]:
464 |                                             if "default" in record:
465 |                                                 self._process_record(
466 |                                                     record,
467 |                                                     order_value,
468 |                                                     record["default"],
469 |                                                 )
470 | 
471 |                                     # Otherwise, follow if the item is declared in __ALWAYS_FOLLOW__
472 |                                     elif "__ALWAYS_FOLLOW__" in profile_loop:
473 |                                         if (
474 |                                             order_value
475 |                                             in profile_loop["__ALWAYS_FOLLOW__"]
476 |                                         ):
477 |                                             if order_value in profile_loop:
478 |                                                 if (
479 |                                                     "__order__"
480 |                                                     in profile_loop[order_value]
481 |                                                 ):
482 |                                                     for entry in profile_loop[
483 |                                                         order_value
484 |                                                     ]["__order__"]:
485 |                                                         if (
486 |                                                             entry
487 |                                                             in profile_loop[order_value]
488 |                                                         ):
489 |                                                             extract_defaults(
490 |                                                                 order_value=entry,
491 |                                                                 profile_loop=profile_loop[
492 |                                                                     order_value
493 |                                                                 ],
494 |                                                             )
495 | 
496 |                                 # Call recursive definition to process the tree for defaults wherever applicable
497 |                                 extract_defaults(
498 |                                     order_value=order_value, profile_loop=self._profile
499 |                                 )
500 | 
501 |                     # If an external value has been specified
502 |                     if "__EXTERNAL_VALUE__" in self._profile:
503 |                         for dataset in self._profile["__EXTERNAL_VALUE__"]:
504 | 
505 |                             # Holder for __EXTERNAL_REFERENCES__
506 |                             values = dataset.split(":")
507 |                             ext_dataset = values[0]
508 |                             ext_name = values[1]
509 |                             forward_dataset = values[2]
510 |                             forward_name = values[3] if len(values) > 3 else ext_name
511 | 
512 |                             # Create a new dataset holder if one doesn't exist
513 |                             if forward_dataset not in self.data_structure:
514 |                                 self.data_structure[forward_dataset] = [{}]
515 | 
516 |                             # Otherwise if the value already exists
517 |                             elif (
518 |                                 forward_name in self.data_structure[forward_dataset][-1]
519 |                             ):
520 | 
521 |                                 # Dispatch dataset where applicable
522 |                                 self._dispatch_dataset(forward_dataset)
523 | 
524 |                                 # Recreate the holder or add a new position ( dependant on whether or not
525 |                                 # the data was dispatched as per the object dispatch attribute
526 |                                 if forward_dataset not in self.data_structure:
527 |                                     self.data_structure[forward_dataset] = [{}]
528 |                                 else:
529 |                                     self.data_structure[forward_dataset].append({})
530 | 
531 |                             # Verify that the external data does not already exist within the dataset,
532 |                             # If it doesn't store accordingly
533 |                             if ext_dataset not in self.external_data:
534 |                                 self.external_data[ext_dataset] = {}
535 |                             if ext_name not in self.external_data[ext_dataset]:
536 |                                 self.external_data[ext_dataset][ext_name] = [""]
537 |                             else:
538 |                                 # Update the Alias
539 |                                 self.data_structure[forward_dataset][-1][
540 |                                     forward_name
541 |                                 ] = self.external_data[ext_dataset][ext_name][-1]
542 | 
543 |                     # If dataset processing has been specified ... n.b. it is important that
544 |                     # this is processed last
545 |                     if "__DATASET_PROCESSING__" in self._profile:
546 |                         for process_entry in self._profile["__DATASET_PROCESSING__"]:
547 | 
548 |                             # Holder for __DATASET_PROCESSING__
549 |                             values = process_entry.split(":")
550 |                             process = values[0]
551 |                             dataset = values[1]
552 | 
553 |                             if hasattr(self, "process"):
554 |                                 if process in self.process:
555 | 
556 |                                     # Inline processing of the dataset_list
557 |                                     self.process[process](
558 |                                         self.data_structure[dataset][-1]
559 |                                     )
560 | 
561 |                                 else:
562 |                                     raise Exception(
563 |                                         "process coderef "
564 |                                         + record[process]
565 |                                         + " missing"
566 |                                     )
567 |                             else:
568 |                                 raise Exception(
569 |                                     "process definition not supplied as argument"
570 |                                 )
571 | 
572 |         # Type Lookup Dictionary to Code
573 |         tokenDict = {
574 |             "<class 'xml.etree.ElementTree.Element'>": process_element,
575 |             "<class 'xml.etree.ElementTree._ElementInterface'>": process_element,
576 |             "<class 'Element'>": process_element,
577 |             "<type 'Element'>": process_element,
578 |             "<type 'instance'>": process_element,
579 |         }
580 | 
581 |         # Dispatch accordingly based on the type
582 |         tokenDict[str(type(xml_root))]()
583 | 
584 | 
585 | def parse_using_profile(xml, profile, **options):
586 |     """Parses XML based upon the profile"""
587 | 
588 |     # Create an object, passing the options to the object
589 |     obj = _XMLDataset(options)
590 | 
591 |     # Convert the source input profile to a python structure
592 |     obj._profile = obj._expand_profile(profile)
593 | 
594 |     # Capture an ElementTree.Element from an XML String ( Equivalent to
595 |     # getroot() on parse file )
596 |     xml_root = ET.fromstring(xml)
597 | 
598 |     # Process XML Data
599 |     obj._process_data(xml_root)
600 | 
601 |     # If the object has dispatch parameters, flush any remaining records
602 |     if hasattr(obj, "dispatch"):
603 |         obj._dispatch_all()
604 | 
605 |     else:
606 |         # Otherwise return the data structure
607 |         return obj.data_structure
608 | 


--------------------------------------------------------------------------------
/xmldataset/__main__.py:
--------------------------------------------------------------------------------
  1 | from xmldataset import parse_using_profile
  2 | import pprint
  3 | 
  4 | # ------------------------------------------------------------------------------
  5 | #    Define Profile
  6 | # ------------------------------------------------------------------------------
  7 | profile = """
  8 | catalog
  9 |     lowest
 10 |         book
 11 |             author = dataset:title_and_author
 12 |             title  = dataset:title_and_author
 13 |             missing  = dataset:title_and_author
 14 | """
 15 | 
 16 | # ------------------------------------------------------------------------------
 17 | #    Define XML
 18 | # ------------------------------------------------------------------------------
 19 | xml = """<?xml version="1.0"?>
 20 | <catalog>
 21 |    <lowest number="123">
 22 |       <specificbefore>
 23 |          <specificvalue>123</specificvalue>
 24 |       </specificbefore>
 25 |       <book id="bk101">
 26 |          <optionalexternal>
 27 |             <externaldata>external_value1</externaldata>
 28 |          </optionalexternal>
 29 |          <author>Gambardella, Matthew</author>
 30 |          <title>XML Developer's Guide</title>
 31 |          <genre>Computer</genre>
 32 |          <price>44.95</price>
 33 |          <publish_date>2000-10-01</publish_date>
 34 |          <description>An in-depth look at creating applications
 35 |          with XML.</description>
 36 |       </book>
 37 |       <book id="bk102">
 38 |          <author>Ralls, Kim</author>
 39 |          <title>Midnight Rain</title>
 40 |          <genre>Fantasy</genre>
 41 |          <price>5.95</price>
 42 |          <publish_date>2000-12-16</publish_date>
 43 |          <description>A former architect battles corporate zombies,
 44 |          an evil sorceress, and her own childhood to become queen
 45 |          of the world.</description>
 46 |       </book>
 47 |       <book id="bk103">
 48 |          <optionalexternal>
 49 |             <externaldata>external_value2</externaldata>
 50 |          </optionalexternal>
 51 |          <author>Corets, Eva</author>
 52 |          <title>Maeve Ascendant</title>
 53 |          <genre>Fantasy</genre>
 54 |          <price>5.95</price>
 55 |          <publish_date>2000-11-17</publish_date>
 56 |          <description>After the collapse of a nanotechnology
 57 |          society in England, the young survivors lay the
 58 |          foundation for a new society.</description>
 59 |       </book>
 60 |       <book id="bk104">
 61 |          <author>Corets, Eva</author>
 62 |          <title>Oberon's Legacy</title>
 63 |          <genre>Fantasy</genre>
 64 |          <price>5.95</price>
 65 |          <publish_date>2001-03-10</publish_date>
 66 |          <description>In post-apocalypse England, the mysterious
 67 |          agent known only as Oberon helps to create a new life
 68 |          for the inhabitants of London. Sequel to Maeve
 69 |          Ascendant.</description>
 70 |       </book>
 71 |       <book id="bk105">
 72 |          <optionalexternal>
 73 |             <externaldata>external_value3</externaldata>
 74 |          </optionalexternal>
 75 |          <author>Corets, Eva</author>
 76 |          <title>The Sundered Grail</title>
 77 |          <genre>Fantasy</genre>
 78 |          <price>5.95</price>
 79 |          <publish_date>2001-09-10</publish_date>
 80 |          <description>The two daughters of Maeve, half-sisters,
 81 |          battle one another for control of England. Sequel to
 82 |          Oberon's Legacy.</description>
 83 |       </book>
 84 |       <book id="bk106">
 85 |          <author>Randall, Cynthia</author>
 86 |          <title>Lover Birds</title>
 87 |          <genre>Romance</genre>
 88 |          <price>4.95</price>
 89 |          <publish_date>2000-09-02</publish_date>
 90 |          <description>When Carla meets Paul at an ornithology
 91 |          conference, tempers fly as feathers get ruffled.</description>
 92 |       </book>
 93 |       <book id="bk107">
 94 |          <optionalexternal>
 95 |             <externaldata>external_value4</externaldata>
 96 |          </optionalexternal>
 97 |          <author>Thurman, Paula</author>
 98 |          <title>Splish Splash</title>
 99 |          <genre>Romance</genre>
100 |          <price>4.95</price>
101 |          <publish_date>2000-11-02</publish_date>
102 |          <description>A deep sea diver finds true love twenty
103 |          thousand leagues beneath the sea.</description>
104 |       </book>
105 |       <book id="bk108">
106 |          <author>Knorr, Stefan</author>
107 |          <title>Creepy Crawlies</title>
108 |          <genre>Horror</genre>
109 |          <price>4.95</price>
110 |          <publish_date>2000-12-06</publish_date>
111 |          <description>An anthology of horror stories about roaches,
112 |          centipedes, scorpions  and other insects.</description>
113 |       </book>
114 |       <book id="bk109">
115 |          <optionalexternal>
116 |             <externaldata>external_value5</externaldata>
117 |          </optionalexternal>
118 |          <author>Kress, Peter</author>
119 |          <title>Paradox Lost</title>
120 |          <genre>Science Fiction</genre>
121 |          <price>6.95</price>
122 |          <publish_date>2000-11-02</publish_date>
123 |          <description>After an inadvertant trip through a Heisenberg
124 |          Uncertainty Device, James Salway discovers the problems
125 |          of being quantum.</description>
126 |       </book>
127 |       <book id="bk110">
128 |          <author>O'Brien, Tim</author>
129 |          <title>Microsoft .NET: The Programming Bible</title>
130 |          <genre>Computer</genre>
131 |          <price>36.95</price>
132 |          <publish_date>2000-12-09</publish_date>
133 |          <description>Microsoft's .NET initiative is explored in
134 |          detail in this deep programmer's reference.</description>
135 |       </book>
136 |       <book id="bk111">
137 |          <optionalexternal>
138 |             <externaldata>external_value6</externaldata>
139 |          </optionalexternal>
140 |          <author>O'Brien, Tim</author>
141 |          <title>MSXML3: A Comprehensive Guide</title>
142 |          <genre>Computer</genre>
143 |          <price>36.95</price>
144 |          <publish_date>2000-12-01</publish_date>
145 |          <description>The Microsoft MSXML3 parser is covered in
146 |          detail, with attention to XML DOM interfaces, XSLT processing,
147 |          SAX and more.</description>
148 |       </book>
149 |       <book id="bk112">
150 |          <author>Galos, Mike</author>
151 |          <title>Visual Studio 7: A Comprehensive Guide</title>
152 |          <genre>Computer</genre>
153 |          <price>49.95</price>
154 |          <publish_date>2001-04-16</publish_date>
155 |          <description>Microsoft Visual Studio 7 is explored in depth,
156 |          looking at how Visual Basic, Visual C++, C#, and ASP+ are
157 |          integrated into a comprehensive development
158 |          environment.</description>
159 |       </book>
160 |       <specificafter>
161 |          <specificvalue>123</specificvalue>
162 |       </specificafter>
163 |    </lowest>
164 | </catalog>"""
165 | 
166 | # ------------------------------------------------------------------------------
167 | #    Setup Pretty Printing
168 | # ------------------------------------------------------------------------------
169 | ppsetup = pprint.PrettyPrinter(indent=4)
170 | pp = ppsetup.pprint
171 | 
172 | # ------------------------------------------------------------------------------
173 | #    Call parse_using_profile
174 | # ------------------------------------------------------------------------------
175 | print(parse_using_profile(xml, profile))
176 | 


--------------------------------------------------------------------------------