def generate_rhythms():
while 1:
user_input = input('◼︎ 请输入一个你想押韵的词(按回车退出): ')
if user_input:
word = prune_word(user_input)
if word:
num_char = len(word)
cs = input(
'\t-是否押声母？例如对于"欢喜"，押"还席"不押"惯技"。\n\t 请输入要押声母的字的位置\n\t (0-不押；1-押"欢"；2-押"喜"；12-押"欢喜"): '
)
vs = input(
'\t-是否押全韵母？例如对于"欢喜"，押"端倪"不押"叹息"。\n\t 请输入要押全韵母的字的位置\n\t (0-不押；1-押"欢"；2-押"喜"；12-押"欢喜"): '
)
c_ids = check_positions(cs, num_char)
v_ids = check_positions(vs, num_char)
pinyins = word_parser(word)
candidates = get_candidates(word, pinyins, num_char, c_ids,
v_ids)
if candidates:
display_results(candidates)
else:
print(
'>>> 太可惜了，没有适合押韵的词！请尝试分解押韵，例如将"光明磊落"分为"光明"和"磊落"分别进行查询。'
)
else:
break
def single_rhyme(target_word, pinyins, candidates, c_ids, v_ids):
print('单押检索较慢，请稍等...')
target_vowel = pinyins[0][1][-1]
for k, v in phrase_dict.items():
if k[-1] == target_vowel:
for word in v:
word_pys = word_parser(word)
if word[-1] != target_word \
and match_cv(word_pys[-1:], pinyins, c_ids, v_ids) \
and word not in candidates[len(word)]:
candidates[len(word)].append(word)
return candidates
def single_rhyme(target_word, pinyins, candidates, c_ids, v_ids):
print('单押检索较慢，请稍等...')
target_vowel = pinyins[0][1][-1]
for k, v in phrase_dict.items():
if k[-1] == target_vowel:
for word in v:
word_pys = word_parser(word)
if word[-1] != target_word \
and match_cv(word_pys[-1:], pinyins, c_ids, v_ids) \
and word not in candidates[len(word)]:
candidates[len(word)].append(word)
return candidates
def multi_rhyme(target_word, pinyins, num_char, candidates, c_ids, v_ids):
hash_vowels = tuple([pinyin[1][-1] for pinyin in pinyins])
try:
basic_candidates = phrase_dict[hash_vowels]
except KeyError:
return candidates
parsed_candidates = [(word, word_parser(word)) for word in basic_candidates]
for word, word_pinyins in parsed_candidates:
if word[-num_char:] != target_word \
and match_cv(word_pinyins[-num_char:], pinyins, c_ids, v_ids):
candidates[len(word)].append(word)
return candidates
def multi_rhyme(target_word, pinyins, num_char, candidates, c_ids, v_ids):
hash_vowels = tuple([pinyin[1][-1] for pinyin in pinyins])
try:
basic_candidates = phrase_dict[hash_vowels]
except KeyError:
return candidates
parsed_candidates = [(word, word_parser(word))
for word in basic_candidates]
for word, word_pinyins in parsed_candidates:
if word[-num_char:] != target_word \
and match_cv(word_pinyins[-num_char:], pinyins, c_ids, v_ids):
candidates[len(word)].append(word)
return candidates
def generate_rhythms():
while 1:
user_input = input('◼︎ 请输入一个你想押韵的词(按回车退出): ')
if user_input:
word = prune_word(user_input)
if word:
num_char = len(word)
cs = input('\t-是否押声母？例如对于"欢喜"，押"还席"不押"惯技"。\n\t 请输入要押声母的字的位置\n\t (0-不押；1-押"欢"；2-押"喜"；12-押"欢喜"): ')
vs = input('\t-是否押全韵母？例如对于"欢喜"，押"端倪"不押"叹息"。\n\t 请输入要押全韵母的字的位置\n\t (0-不押；1-押"欢"；2-押"喜"；12-押"欢喜"): ')
c_ids = check_positions(cs, num_char)
v_ids = check_positions(vs, num_char)
pinyins = word_parser(word)
candidates = get_candidates(word, pinyins, num_char, c_ids, v_ids)
if candidates:
display_results(candidates)
else:
print('>>> 太可惜了，没有适合押韵的词！请尝试分解押韵，例如将"光明磊落"分为"光明"和"磊落"分别进行查询。')
else:
break
if len(word) > 1 and re.match(r'^[\u4E00-\u9FA5，]+$', word):
vocab.add(word)
print('+ 各大输入法词库 (无俗语，含英语)：', len(vocab))
for words in phrases_dict:
for word in words.split('，'):
vocab.add(word.strip())
print('+ 自带词库 (无俗语)：', len(vocab))
look_up = defaultdict(list)
for word in vocab:
pinyins = word_parser(word)
if len(word) > 1:
look_up[tuple([pinyin[1][-1] for pinyin in pinyins[-2:]])].append(word)
if len(word) > 2:
look_up[tuple([pinyin[1][-1] for pinyin in pinyins[-3:]])].append(word)
if len(word) > 3 and word[-4] != '，':
look_up[tuple([pinyin[1][-1] for pinyin in pinyins[-4:]])].append(word)
with open('phrase_dict.txt', 'w') as f:
for k, v in look_up.items():
f.write('{}\t{}\n'.format(' '.join(list(k)), ' '.join(sorted(v))))
print('done!')
# with open('phrase_dict.py', 'w') as f:
# f.write('phrase_dict = {\n')
for line in f:
word = line.strip().split()[0]
if len(word) > 1 and re.match(r'^[\u4E00-\u9FA5，]+$', word):
vocab.add(word)
print('+ 各大输入法词库 (无俗语，含英语)：', len(vocab))
for words in phrases_dict:
for word in words.split('，'):
vocab.add(word.strip())
print('+ 自带词库 (无俗语)：', len(vocab))
look_up = defaultdict(list)
for word in vocab:
pinyins = word_parser(word)
if len(word) > 1:
look_up[tuple([pinyin[1][-1] for pinyin in pinyins[-2:]])].append(word)
if len(word) > 2:
look_up[tuple([pinyin[1][-1] for pinyin in pinyins[-3:]])].append(word)
if len(word) > 3 and word[-4] != '，':
look_up[tuple([pinyin[1][-1] for pinyin in pinyins[-4:]])].append(word)
with open('phrase_dict.txt', 'w', encoding="utf-8") as f:
for k, v in look_up.items():
f.write('{}\t{}\n'.format(' '.join(list(k)), ' '.join(sorted(v))))
print('done!')
# with open('phrase_dict.py', 'w') as f:
# f.write('phrase_dict = {\n')
# for k, v in look_up.items():