def compare_hlds_variants():
"""
TODO: kill bugs
BUG1: sentence001-original-test contains 2(!) <item> sentences.
"""
hlds_reader = hlds.HLDSReader(hlds.testbed_file)
for i, sentence in enumerate(hlds_reader.sentences):
xml_sentence_test = hlds.create_hlds_file(sentence, mode="test",
output="xml")
util.write_to_file(xml_sentence_test,
"xmltest/sentence{0}-converted-test.xml".format(str(i).zfill(3)))
xml_sentence_realize = hlds.create_hlds_file(sentence, mode="test",
output="xml")
util.write_to_file(xml_sentence_test,
"xmltest/sentence{0}-converted-realize.xml".format(str(i).zfill(3)))
for i, item_etree in enumerate(hlds_reader.xml_sentences):
root = etree.Element("regression")
doc = etree.ElementTree(root)
root.insert(0, item_etree)
xml_sentence_original = hlds.etreeprint(doc)
util.write_to_file(xml_sentence_original,
"xmltest/sentence{0}-original-test.xml".format(str(i).zfill(3)))
def compare_hlds_variants():
"""
TODO: kill bugs
BUG1: sentence001-original-test contains 2(!) <item> sentences.
"""
hlds_reader = hlds.HLDSReader(hlds.testbed_file)
for i, sentence in enumerate(hlds_reader.sentences):
xml_sentence_test = hlds.create_hlds_file(sentence,
mode="test",
output="xml")
util.write_to_file(
xml_sentence_test,
"xmltest/sentence{0}-converted-test.xml".format(str(i).zfill(3)))
xml_sentence_realize = hlds.create_hlds_file(sentence,
mode="test",
output="xml")
util.write_to_file(
xml_sentence_test,
"xmltest/sentence{0}-converted-realize.xml".format(
str(i).zfill(3)))
for i, item_etree in enumerate(hlds_reader.xml_sentences):
root = etree.Element("regression")
doc = etree.ElementTree(root)
root.insert(0, item_etree)
xml_sentence_original = hlds.etreeprint(doc)
util.write_to_file(
xml_sentence_original,
"xmltest/sentence{0}-original-test.xml".format(str(i).zfill(3)))
def test_textplan2xml_conversion():
"""
test text plan to XML conversion with all the text plans that were
generated for all test queries with debug.gen_all_textplans().
"""
import cPickle
atp = cPickle.load(open("data/alltextplans.pickle", "r"))
print """### Output: One XML file per query ###\n\n"""
for atp_count, textplans in enumerate(atp):
xml_plan = textplans2xml(textplans)
print "All text plans generated" " for test query #{0}:\n".format(atp_count)
print etreeprint(xml_plan, debug=False), "\n\n\n"
print """### Output: One XML file per text plan ###\n\n"""
for atp_count, tp in enumerate(atp):
for tp_count, docplan in enumerate(tp.document_plans):
xml_plan = textplan2xml(docplan)
print "Text plan {0} for " "test query {1}:\n".format(atp_count, tp_count)
print etreeprint(xml_plan, debug=False), "\n\n\n"
def test_textplan2xml_conversion():
"""
test text plan to XML conversion with all the text plans that were
generated for all test queries with debug.gen_all_textplans().
"""
import cPickle
atp = cPickle.load(open("data/alltextplans.pickle", "r"))
print """### Output: One XML file per query ###\n\n"""
for atp_count, textplans in enumerate(atp):
xml_plan = textplans2xml(textplans)
print "All text plans generated" \
" for test query #{0}:\n".format(atp_count)
print etreeprint(xml_plan, debug=False), "\n\n\n"
print """### Output: One XML file per text plan ###\n\n"""
for atp_count, tp in enumerate(atp):
for tp_count, docplan in enumerate(tp.document_plans):
xml_plan = textplan2xml(docplan)
print "Text plan {0} for " \
"test query {1}:\n".format(atp_count, tp_count)
print etreeprint(xml_plan, debug=False), "\n\n\n"
"as follows:\n".format(msg_block[Feature("msgType")])
for lexicalized_phrase in lexicalized_msg_block:
lexicalized_sentence = phrase2sentence(lexicalized_phrase)
# TODO: refactor to avoid duplication w/ OpenCCG.realize
temp_sentence = deepcopy(lexicalized_sentence)
if isinstance(lexicalized_sentence, Diamond):
temp_sentence = diamond2sentence(temp_sentence)
add_nom_prefixes(temp_sentence)
print create_hlds_file(temp_sentence,
mode="realize", output="xml")
except NotImplementedError, err:
print err
print "The message block contains these messages:\n", msg_block, \
"\n\n**********\n\n"
elif output_format == 'textplan-featstruct':
for i, textplan in enumerate(textplans.document_plans):
print "Text plan #%i:\n" % i
print textplan, "\n\n"
else: # output_format == 'textplan-xml'
etreeprint(textplans2xml(textplans))
if __name__ == "__main__":
main()
"as follows:\n".format(msg_block[Feature("msgType")])
for lexicalized_phrase in lexicalized_msg_block:
lexicalized_sentence = phrase2sentence(lexicalized_phrase)
# TODO: refactor to avoid duplication w/ OpenCCG.realize
temp_sentence = deepcopy(lexicalized_sentence)
if isinstance(lexicalized_sentence, Diamond):
temp_sentence = diamond2sentence(temp_sentence)
add_nom_prefixes(temp_sentence)
print create_hlds_file(temp_sentence,
mode="realize", output="xml")
except NotImplementedError, err:
print err
print "The message block contains these messages:\n", msg_block, \
"\n\n**********\n\n"
elif output_format == 'textplan-featstruct':
for i, textplan in enumerate(textplans.document_plans):
print "Text plan #%i:\n" % i
print textplan, "\n\n"
else: # output_format == 'textplan-xml'
etreeprint(textplans2xml(textplans))
if __name__ == "__main__":
main()