def main():
# for line in open('lahu_writing.txt','rU'):
# for word in line.split():
# print word,
# print transduce(word,decompose),
# print transduce(transduce(word,decompose),chinese),
# print transduce(transduce(word,decompose),baptist)
f = open('4testLahuTexts.xml','rt')
tree = ET.parse(f)
f.close()
for node in tree.findall('.//word/words/word/item'):
if node.attrib['type'] == 'txt':
form = codecs.encode(node.text,'utf8')
print form,
print [form],
print transduce(form,decompose),
print transduce(transduce(form,decompose),chinese),
print transduce(transduce(form,decompose),baptist)
phrases = text.findall('.//phrases')
print >> OutLaTeX, '\\begin{examples}'
sentences = []
for p in phrases:
for s in p.findall('.//word/words'):
# sentencenumber = s.find(".//item[@type='segnum']")
print >> OutLaTeX, "\\item\n"
print >> OutLaTeX, "\glll ",
BaptistSentence = ''
ChineseSentence = ''
for w in s.findall('.//word'):
for i in w.findall('.//item'):
if i.attrib['type'] in ['txt','punct']:
#form = codecs.encode(i.text,'utf8')
form = i.text
form = transduce(form,decompose)
form = escape(form)
BaptistSentence += ' %s' % transduce(form,baptist)
ChineseSentence += ' %s' % transduce(form,chinese)
for level in ['txt', 'msa', 'gls']:
for w in s.findall('.//word'):
itemToOutput = ' {}'
for i in w.findall('.//item'):
if i.attrib['type'] == 'punct':
if level in ['msa']:
form = ''
elif level in ['gls']:
form = ''
else:
form = str(i.text)
elif i.attrib['type'] == level:
