def from_aligned_file(syllabus_name, aligned_file, output_file):
_log.start('Extracting gp-aligned words', nSteps=4)
_log.log('Building set of expected words')
include_set = set((w.surface, w.reading) for w in \
align_core.iter_words(syllabus_name))
_log.log('Loading alignments')
alignments = AlignedFile(aligned_file)
_log.log('Saving alignments')
o_stream = sopen(output_file, 'w')
for alignment in alignments:
key = (alignment.grapheme, alignment.phoneme)
if key in include_set:
print >> o_stream, alignment.to_line()
include_set.remove(key)
o_stream.close()
if include_set:
_log.finish('%d entries not found (see missing.log)' % len(include_set))
o_stream = sopen('missing.log', 'w')
for surface, reading in sorted(include_set):
print >> o_stream, '%s %s:%s %s' % (surface, reading, surface,
reading)
o_stream.close()
else:
_log.finish('All entries found')
def from_aligned_file(syllabus_name, aligned_file, output_file):
_log.start('Extracting gp-aligned words', nSteps=4)
_log.log('Building set of expected words')
include_set = set((w.surface, w.reading) for w in \
align_core.iter_words(syllabus_name))
_log.log('Loading alignments')
alignments = AlignedFile(aligned_file)
_log.log('Saving alignments')
o_stream = sopen(output_file, 'w')
for alignment in alignments:
key = (alignment.grapheme, alignment.phoneme)
if key in include_set:
print >> o_stream, alignment.to_line()
include_set.remove(key)
o_stream.close()
if include_set:
_log.finish('%d entries not found (see missing.log)' %
len(include_set))
o_stream = sopen('missing.log', 'w')
for surface, reading in sorted(include_set):
print >> o_stream, '%s %s:%s %s' % (surface, reading, surface,
reading)
o_stream.close()
else:
_log.finish('All entries found')
def to_alignment_format(syllabus_name, output_file):
o_stream = sopen(output_file, 'w')
for word in align_core.iter_words(syllabus_name):
if word.reading and word.has_kanji():
print >> o_stream, word.surface, word.reading
o_stream.close()