def get_input_rules_from_giving_words(input_words):
'''输入汉字，输出相应的输入规则'''
try:
assert isinstance(input_words, unicode)
except:
input_words = input_words.decode('utf-8')
coding_map = {'a': '2', 'c': '2', 'b': '2', 'e': '3', 'd': '3', 'g': '4', 'f': '3', 'i': '4', 'h': '4', 'k': '5', 'j': '5', 'm': '6', 'l': '5', 'o': '6', 'n': '6', 'q': '7', 'p': '7', 's': '7', 'r': '7', 'u': '8', 't': '8', 'w': '9', 'v': '8', 'y': '9', 'x': '9', 'z': '9'}
ws = WordsSearch()
pinyin_str = ' '.join(ws.get_splited_pinyin(input_words)[0]).replace('*', '')
role_num = ''.join([coding_map[letter] for letter in pinyin_str if letter.isalpha()])
print '\t'.join((words.decode('utf-8'), pinyin_str, role_num))
def convert_pinyin_to_rules():
'''把基础词库中的拼音转换为输入规则（数字序列）'''
coding_map = {'a': '2', 'c': '2', 'b': '2', 'e': '3', 'd': '3', 'g': '4', 'f': '3', 'i': '4', 'h': '4', 'k': '5', 'j': '5', 'm': '6', 'l': '5', 'o': '6', 'n': '6', 'q': '7', 'p': '7', 's': '7', 'r': '7', 'u': '8', 't': '8', 'w': '9', 'v': '8', 'y': '9', 'x': '9', 'z': '9'}
ws = WordsSearch()
base_filename = os.path.join(src_file_path, 'combine_top60000_and_5041.txt')
base_file_with_pinyin = os.path.join(src_file_path, 'combine_top60000_and_5041_pinyin_role.txt')
with codecs.open(base_filename, encoding='utf-8') as f,\
codecs.open(base_file_with_pinyin, mode='wb', encoding='utf-8') as wf:
whole_word_list = (item.split('\t')[0] for item in f.readlines())
for word in whole_word_list:
pinyin_str = ' '.join(ws.get_splited_pinyin(word)[0]).replace('*', '')
role_num = ''.join([coding_map[letter] for letter in pinyin_str if letter.isalpha()])
com_str = '\t'.join((word, pinyin_str, role_num))
wf.write(com_str+'\n')
def convert_pinyin_to_rules():
'''把基础词库中的拼音转换为输入规则（数字序列）'''
coding_map = {
'a': '2',
'c': '2',
'b': '2',
'e': '3',
'd': '3',
'g': '4',
'f': '3',
'i': '4',
'h': '4',
'k': '5',
'j': '5',
'm': '6',
'l': '5',
'o': '6',
'n': '6',
'q': '7',
'p': '7',
's': '7',
'r': '7',
'u': '8',
't': '8',
'w': '9',
'v': '8',
'y': '9',
'x': '9',
'z': '9'
}
ws = WordsSearch()
base_filename = os.path.join(src_file_path,
'combine_top60000_and_5041.txt')
base_file_with_pinyin = os.path.join(
src_file_path, 'combine_top60000_and_5041_pinyin_role.txt')
with codecs.open(base_filename, encoding='utf-8') as f,\
codecs.open(base_file_with_pinyin, mode='wb', encoding='utf-8') as wf:
whole_word_list = (item.split('\t')[0] for item in f.readlines())
for word in whole_word_list:
pinyin_str = ' '.join(ws.get_splited_pinyin(word)[0]).replace(
'*', '')
role_num = ''.join([
coding_map[letter] for letter in pinyin_str
if letter.isalpha()
])
com_str = '\t'.join((word, pinyin_str, role_num))
wf.write(com_str + '\n')
def get_input_rules_from_giving_words(input_words):
'''输入汉字，输出相应的输入规则'''
try:
assert isinstance(input_words, unicode)
except:
input_words = input_words.decode('utf-8')
coding_map = {
'a': '2',
'c': '2',
'b': '2',
'e': '3',
'd': '3',
'g': '4',
'f': '3',
'i': '4',
'h': '4',
'k': '5',
'j': '5',
'm': '6',
'l': '5',
'o': '6',
'n': '6',
'q': '7',
'p': '7',
's': '7',
'r': '7',
'u': '8',
't': '8',
'w': '9',
'v': '8',
'y': '9',
'x': '9',
'z': '9'
}
ws = WordsSearch()
pinyin_str = ' '.join(ws.get_splited_pinyin(input_words)[0]).replace(
'*', '')
role_num = ''.join(
[coding_map[letter] for letter in pinyin_str if letter.isalpha()])
print '\t'.join((words.decode('utf-8'), pinyin_str, role_num))