diff options
Diffstat (limited to 'scripts')
| -rw-r--r-- | scripts/Makefile.data | 4 | ||||
| -rw-r--r-- | scripts/specialtable.py | 19 |
2 files changed, 5 insertions, 18 deletions
diff --git a/scripts/Makefile.data b/scripts/Makefile.data index 1457407..7929e97 100644 --- a/scripts/Makefile.data +++ b/scripts/Makefile.data @@ -2,9 +2,7 @@ all: pinyins.txt pinyins.txt: - awk -f genpinyins.awk -vlen=1 ../data/gb_char.table \ - ../data/gbk_char.table > $@ - awk -f genpinyins.awk -vlen=2 ../data/gb_char.table >> $@ + python3 genpinyins.py update-header: diff --git a/scripts/specialtable.py b/scripts/specialtable.py index 5d1d599..b6fb680 100644 --- a/scripts/specialtable.py +++ b/scripts/specialtable.py @@ -37,28 +37,17 @@ def load_phrase(filename): for line in phrasefile.readlines(): line = line.rstrip(os.linesep) (pinyin_str, freq) = line.split(None, 1) - freq = int(math.floor(float(freq))) + freq = int(freq) if 0 == freq: #print(pinyin_str) continue + # no duplicate here if "'" in pinyin_str: (first_key, second_key) = pinyin_str.split("'") - if first_key[-1].isdigit(): - first_key = first_key[:-1] - if second_key[-1].isdigit(): - second_key = second_key[:-1] - if (first_key, second_key) in phrase_dict: - phrase_dict[(first_key, second_key)] += freq - else: - phrase_dict[(first_key, second_key)] = freq + phrase_dict[(first_key, second_key)] = freq else: - if pinyin_str[-1].isdigit(): - pinyin_str = pinyin_str[:-1] - if pinyin_str in phrase_dict: - phrase_dict[pinyin_str] += freq - else: - phrase_dict[pinyin_str] = freq + phrase_dict[pinyin_str] = freq phrasefile.close() |