summaryrefslogtreecommitdiffstats
path: root/scripts/specialtable.py
blob: c47f2b9fa3868b8a436470a17eabbdaea60244c3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
# -*- coding: utf-8 -*-
# vim:set et sts=4 sw=4:
#
# libpinyin - Library to deal with pinyin.
#
# Copyright (C) 2011 Peng Wu <alexepico@gmail.com>
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.


import os
import sys
import math
import pinyin

pinyin_list = sorted(pinyin.PINYIN_LIST)
shengmu_list = sorted(pinyin.SHENGMU_LIST)
yunmu_list = sorted(pinyin.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(' ', 1)
        freq = int(math.floor(float(freq)))
        if 0 == freq:
            #print(pinyin_str)
            continue

        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
        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
    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 code
load_phrase("pinyins.txt")
load_phrase("specials.txt")

if __name__ == "__main__":
    for p in filter_divided():
        print (p)
    for p in filter_resplit():
        print (p)