XML pretty-print for ElementTree

LICENSE.txt

Copyright (c) 2013, Antti Kaihola
All rights reserved.

Redistribution and use in source and binary forms, with or without modification,
are permitted provided that the following conditions are met:

    1. Redistributions of source code must retain the above copyright notice,
       this list of conditions and the following disclaimer.
    
    2. Redistributions in binary form must reproduce the above copyright
       notice, this list of conditions and the following disclaimer in the
       documentation and/or other materials provided with the distribution.

    3. Neither the name of xmlprettyprint nor the names of its contributors
       may be used to endorse or promote products derived from this software
       without specific prior written permission.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

xmlprettyprint.py

"""XML pretty-print for ElementTree

MIT License, (c) Antti Kaihola 2013

"""

from xml.etree import ElementTree


def _xmlprettyprint(stringlist):
    indent = ''
    in_tag = False
    for token in stringlist:
        if token.startswith('</'):
            indent = indent[:-2]
            yield indent + token + '\n'
            in_tag = True
        elif token.startswith('<'):
            yield indent + token
            indent += '  '
            in_tag = True
        elif token == '>':
            yield '>' + '\n'
            in_tag = False
        elif in_tag:
            yield token
        else:
            yield indent + token + '\n'


def xmlprettyprint(element):
    return ''.join(_xmlprettyprint(ElementTree.tostringlist(element)))


if __name__ == '__main__':
    e = ElementTree.fromstring('<foo><bar>joe'
                               '<baz name="sue">eve</baz>'
                               '</bar></foo>')
    print xmlprettyprint(e)

Suggestion:

Adding the following fixes an issue with <tag attribute = "x"/> style tags.

        elif token.endswith('/>'):
            indent = indent[:-2]
            yield '/>' + '\n'
            in_tag = False

Why were xmlprettyprint() and _xmlprettyprint() split into separate methods?