SimpleXMLWriter for Python 3

SimpleXMLWriter.py

#
# SimpleXMLWriter
# $Id: SimpleXMLWriter.py 3225 2007-08-27 21:32:08Z fredrik $
#
# a simple XML writer
#
# history:
# 2001-12-28 fl   created
# 2002-11-25 fl   fixed attribute encoding
# 2002-12-02 fl   minor fixes for 1.5.2
# 2004-06-17 fl   added pythondoc markup
# 2004-07-23 fl   added flush method (from Jay Graves)
# 2004-10-03 fl   added declaration method
#
# Copyright (c) 2001-2004 by Fredrik Lundh
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The SimpleXMLWriter module is
#
# Copyright (c) 2001-2007 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS.  IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------

##
# Tools to write XML files, without having to deal with encoding
# issues, well-formedness, etc.
# <p>
# The current version does not provide built-in support for
# namespaces. To create files using namespaces, you have to provide
# "xmlns" attributes and explicitly add prefixes to tags and
# attributes.
#
# <h3>Patterns</h3>
#
# The following example generates a small XHTML document.
# <pre>
#
# from elementtree.SimpleXMLWriter import XMLWriter
# import sys
#
# w = XMLWriter(sys.stdout)
#
# html = w.start("html")
#
# w.start("head")
# w.element("title", "my document")
# w.element("meta", name="generator", value="my application 1.0")
# w.end()
#
# w.start("body")
# w.element("h1", "this is a heading")
# w.element("p", "this is a paragraph")
#
# w.start("p")
# w.data("this is ")
# w.element("b", "bold")
# w.data(" and ")
# w.element("i", "italic")
# w.data(".")
# w.end("p")
#
# w.close(html)
# </pre>
##

import re


_escape = re.compile(r"[&<>\"\x80-\xff]+")


def encode_entity(text, pattern=_escape):
    def escape_entities(m):
        out = []
        for char in m.group():
            out.append("&#%d;" % ord(char))
        return ''.join(out)

    return pattern.sub(escape_entities, text)


del _escape


def escape_cdata(s):
    s = s.replace('&', '&amp;')
    s = s.replace('<', '&lt;')
    s = s.replace('>', '&gt;')
    return s


def escape_attrib(s):
    s = s.replace('&', '&amp;')
    s = s.replace('\'', '&apos;')
    s = s.replace('"', '&quot;')
    s = s.replace('<', '&lt;')
    s = s.replace('>', '&gt;')
    return s


class XMLWriter:
    def __init__(self, file, encoding="us-ascii"):
        if not hasattr(file, "write"):
            file = open(file, "w")
        self.__write = file.write
        if hasattr(file, "flush"):
            self.flush = file.flush
        self.__open = 0
        self.__tags = []
        self.__data = []
        self.__encoding = encoding

    def __flush(self):
        if self.__open:
            self.__write(">")
            self.__open = 0
        if self.__data:
            data = ''.join(self.__data)
            self.__write(escape_cdata(data))
            self.__data = []

    def declaration(self):
        encoding = self.__encoding
        if encoding == "us-ascii" or encoding == "utf-8":
            self.__write("<?xml version='1.0'?>\n")
        else:
            self.__write("<?xml version='1.0' encoding='%s'?>\n" % encoding)

    def start(self, tag, **extra):
        self.__flush()
        tag = escape_cdata(tag)
        self.__data = []
        self.__tags.append(tag)
        self.__write("<%s" % tag)
        if extra:
            attrib = list(extra.items())
            attrib.sort()
            for k, v in attrib:
                k = escape_cdata(str(k))
                v = escape_attrib(str(v))
                self.__write(" %s=\"%s\"" % (k, v))
        self.__open = 1
        return len(self.__tags) - 1

    def comment(self, comment):
        self.__flush()
        self.__write("<!-- %s -->\n" % escape_cdata(comment))

    def data(self, text):
        self.__data.append(str(text))

    def end(self, tag=None):
        if tag:
            assert self.__tags, "unbalanced end(%s)" % tag
            assert escape_cdata(tag) == self.__tags[-1], \
                "expected end(%s), got %s" % (self.__tags[-1], tag)
        else:
            assert self.__tags, "unbalanced end()"
        tag = self.__tags.pop()
        if self.__data:
            self.__flush()
        elif self.__open:
            self.__open = 0
            self.__write(" />")
            return
        self.__write("</%s>" % tag)

    def close(self, id):
        while len(self.__tags) > id:
            self.end()

    def element(self, tag, text=None, **extra):
        self.start(tag, **extra)
        if text is not None:
            self.data(text)
        self.end()

    def flush(self):
        pass