# $Id$
# text extraction demo

import cElementTree as ET
# import elementtree.ElementTree as ET

#
# original implementation

def flatten(elem, include_tail=0):
    text = elem.text or ""
    for e in elem:
        text += flatten(e, 1)
    if include_tail and elem.tail: text += elem.tail
    return text

#
# alternate implementation, from
# http://effbot.org/zone/element-bits-and-pieces.htm
# appears to be a little bit (10-20%) faster

# rename to inner_text instead ?

def gettext(elem):
    text = elem.text or ""
    for e in elem:
        text += gettext(e)
        if e.tail:
            text += e.tail
    return text

#
# alternate implementation, using string.join pattern.  this is a lot
# slower (not sure why)

def gettext_join(elem):
    data = []
    append = data.append
    def process(elem):
        if elem.text:
            append(elem.text)
        for e in elem:
            process(e)
            if e.tail:
                append(e.tail)
    process(elem)
    return "".join(data)

# --------------------------------------------------------------------
# demo

DOC2 = """\
<root xmlns='namespace'>
   <element key='value'>text</element>
   <element>text</element>tail
   <empty-element/>
</root>
"""

tree = ET.XML(DOC2)

def test1():
    return flatten(tree)

def test2():
    return gettext(tree)

def test3():
    return gettext_join(tree)

print repr(test1())
print repr(test2())
print repr(test3())