def parse_chunk_analysis_result(lines):
lines_list = NLP40.split_into_lines_list(lines)
map_list = []
for lines_list_elem in lines_list:
m = make_chunk_list_from(lines_list_elem)
map_list.append(m)
pass
return map_list
morphs = []
for i_s in dst.srcs():
last_morph_of_src = oneline[i_s].morphs()[-1]
if NLP45.is_particle(last_morph_of_src):
particles.append(last_morph_of_src.surface())
morphs.append(oneline[i_s].morphs())
key_base = dst.morphs()[0].base()
if key_base in map_verb_and_pattern_of_particle_and_morphs:
d = map_verb_and_pattern_of_particle_and_morphs[key_base]
d['particles'] += copy.deepcopy(particles)
d['morphs'] += copy.deepcopy(morphs)
else:
new_dict = dict(particles = copy.deepcopy(particles), morphs = copy.deepcopy(morphs))
map_verb_and_pattern_of_particle_and_morphs[key_base] = new_dict
write_verb_and_pattern_of_particle_and_morphs_result(i, map_verb_and_pattern_of_particle_and_morphs)
def write_verb_and_pattern_of_particle_and_morphs_result(i, map_verb_and_pattern_of_particle_and_morphs):
#print(i)
for key_base in map_verb_and_pattern_of_particle_and_morphs:
d = map_verb_and_pattern_of_particle_and_morphs[key_base]
particles = d['particles']
morphs = d['morphs']
chunk_strings = list(map(lambda x: NLP42.concat_morphs(x), morphs))
if len(particles) > 0:
print(key_base, ' '.join(map(lambda x: str(x), particles)), ' '.join(chunk_strings), sep = '\t')
if __name__ == '__main__':
lines = NLP40.read_kakariuke_analysis_result()
map_list = NLP41.parse_chunk_analysis_result(lines)
write_verb_and_pattern_of_particle_and_morphs(map_list)
def parse_morph_from(line):
elem_list = line.split('\t')
essence = elem_list[1]
elements = essence.split(',')
surface = elem_list[0]
base = elements[6]
pos = elements[0]
pos1 = elements[1]
return Morph(surface = surface, base = base, pos = pos, pos1 = pos1)
def parse_chunk_info(line):
m = re.match(r'\*\s+\d+\s+(\d+)D', line)
if m:
return int(m.group(1)) #dst
else:
return -1
def set_srcs_for_chunk_list(chunk_list):
for i, chunk in enumerate(chunk_list):
d = chunk.dst()
if d is None or d == -1:
continue
else:
d_chunk = chunk_list[d]
d_chunk.append_srcs(i)
if __name__ == '__main__':
lines = NLP40.read_kakariuke_analysis_result()
map_list = parse_chunk_analysis_result(lines)
NLP40.write_map_list(map_list, [8])
