diff options
Diffstat (limited to 'scripts2/fullpinyintable.py')
-rw-r--r-- | scripts2/fullpinyintable.py | 100 |
1 files changed, 1 insertions, 99 deletions
diff --git a/scripts2/fullpinyintable.py b/scripts2/fullpinyintable.py index 6ad05be..b8cb1a6 100644 --- a/scripts2/fullpinyintable.py +++ b/scripts2/fullpinyintable.py @@ -25,7 +25,7 @@ import itertools import chewing from pyzymap import ZHUYIN_PINYIN_MAP, ZHUYIN_LUOMA_PINYIN_MAP, ZHUYIN_SECONDARY_ZHUYIN_MAP from pyzymap import PINYIN_ZHUYIN_MAP, ZHUYIN_SPECIAL_INITIAL_SET_IN_PINYIN_FORM -from fullpinyin import PINYIN_LIST, SHENGMU_LIST, YUNMU_LIST +from fullpinyin import PINYIN_LIST, SHENGMU_LIST from options import * from utils import shuffle_all @@ -403,94 +403,6 @@ def gen_table_index_for_chewing_key(content_table): return ",\n".join(entries) -#special table -pinyin_list = sorted(PINYIN_LIST) -shengmu_list = sorted(SHENGMU_LIST) -yunmu_list = sorted(YUNMU_LIST) - -phrase_dict = {} - - -def load_phrase(filename): - phrasefile = open(filename, "r") - for line in phrasefile.readlines(): - line = line.rstrip(os.linesep) - (pinyin_str, freq) = line.split(None, 1) - freq = int(freq) - if 0 == freq: - #print(pinyin_str) - continue - - # no duplicate here - if "'" in pinyin_str: - (first_key, second_key) = pinyin_str.split("'") - phrase_dict[(first_key, second_key)] = freq - else: - phrase_dict[pinyin_str] = freq - phrasefile.close() - - -def gen_all_divided(): - for pinyin_key in pinyin_list: - for first_key in pinyin_list: - if len(pinyin_key) <= len(first_key): - continue - if not pinyin_key.startswith(first_key): - continue - second_key = pinyin_key[len(first_key):] - if second_key in pinyin_list: - yield pinyin_key, first_key, second_key - - -def filter_divided(): - for (pinyin_key, first_key, second_key) in gen_all_divided(): - if not (first_key, second_key) in phrase_dict: - continue - orig_freq = 0 - if pinyin_key in phrase_dict: - orig_freq = phrase_dict[pinyin_key] - new_freq = phrase_dict[(first_key, second_key)] - yield pinyin_key, orig_freq, first_key, second_key, new_freq - - -def gen_all_resplit(): - for pinyin_key in pinyin_list: - if pinyin_key[-1] in ["n", "g", "r"]: - for yun in yunmu_list: - if yun not in pinyin_list: - continue - #check first new pinyin key - if not pinyin_key[:-1] in pinyin_list: - continue - #check second new pinyin key - new_pinyin_key = pinyin_key[-1] + yun - if new_pinyin_key in pinyin_list: - yield pinyin_key, yun, pinyin_key[:-1], new_pinyin_key -''' - elif pinyin_key[-1] in ["e"]: - #check first new pinyin key - if pinyin_key[:-1] in pinyin_list: - yield pinyin_key, "r", pinyin_key[:-1], "er" -''' - - -def filter_resplit(): - for (orig_first_key, orig_second_key, new_first_key, new_second_key) \ - in gen_all_resplit(): - #do the reverse here, as libpinyin pinyin parser is different with - #ibus-pinyin's parser. - (orig_first_key, orig_second_key, new_first_key, new_second_key) = \ - (new_first_key, new_second_key, orig_first_key, orig_second_key) - if (new_first_key, new_second_key) not in phrase_dict: - continue - orig_freq = 0 - new_freq = phrase_dict[(new_first_key, new_second_key)] - if (orig_first_key, orig_second_key) in phrase_dict: - orig_freq = phrase_dict[(orig_first_key, orig_second_key)] - yield orig_first_key, orig_second_key, orig_freq, \ - new_first_key, new_second_key, new_freq - - #init full pinyin table code filter_pinyin_list() check_rules(hsu_correct, hsu_correct_special) @@ -498,10 +410,6 @@ check_rules(eten26_correct, eten26_correct_special) populate_more_zhuyin_index() sort_all() -#init resplit/divided table code -load_phrase("pinyins.txt") -#load_phrase("specials.txt") - ### main function ### if __name__ == "__main__": @@ -517,9 +425,3 @@ if __name__ == "__main__": s = gen_hsu_zhuyin_index() + gen_eten26_zhuyin_index() s = gen_table_index_for_chewing_key(content_table) print(s) - - #dump - for p in filter_divided(): - print (p) - for p in filter_resplit(): - print (p) |