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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
|
#
# Creating the file ZhConversion.php used for Simplified/Traditional
# Chinese conversion. It gets the basic conversion table from the Unihan
# database, and construct the phrase tables using phrase libraries in
# the SCIM packages and the libtabe package. There are also special
# tables used to for adjustment.
#
GREP = LANG=zh_CN.UTF8 grep
SED = LANG=zh_CN.UTF8 sed
DIFF = LANG=zh_CN.UTF8 diff
CC ?= gcc
SF_MIRROR = easynews
SCIM_TABLES_VER = 0.5.7
SCIM_PINYIN_VER = 0.5.91
LIBTABE_VER = 0.2.3
# Installation directory
INSTDIR = /usr/local/share/zhdaemons/
all: ZhConversion.php tradphrases.notsure simpphrases.notsure wordlist toHans.dict toHant.dict toCN.dict toTW.dict toHK.dict toSG.dict
Unihan.txt:
wget -nc ftp://ftp.unicode.org/Public/UNIDATA/Unihan.zip
unzip -q Unihan.zip
EZ.txt.in:
wget -nc http://$(SF_MIRROR).dl.sourceforge.net/sourceforge/scim/scim-tables-$(SCIM_TABLES_VER).tar.gz
tar -xzf scim-tables-$(SCIM_TABLES_VER).tar.gz -O scim-tables-$(SCIM_TABLES_VER)/tables/zh/EZ-Big.txt.in > EZ.txt.in
phrase_lib.txt:
wget -nc http://$(SF_MIRROR).dl.sourceforge.net/sourceforge/scim/scim-pinyin-$(SCIM_PINYIN_VER).tar.gz
tar -xzf scim-pinyin-$(SCIM_PINYIN_VER).tar.gz -O scim-pinyin-$(SCIM_PINYIN_VER)/data/phrase_lib.txt > phrase_lib.txt
tsi.src:
wget -nc http://$(SF_MIRROR).dl.sourceforge.net/sourceforge/libtabe/libtabe-$(LIBTABE_VER).tgz
tar -xzf libtabe-$(LIBTABE_VER).tgz -O libtabe/tsi-src/tsi.src > tsi.src
wordlist: phrase_lib.txt EZ.txt.in tsi.src
iconv -c -f big5 -t utf8 tsi.src | $(SED) 's/# //g' | $(SED) 's/[ ][0-9].*//' > wordlist
$(SED) 's/\(.*\)\t[0-9][0-9]*.*/\1/' phrase_lib.txt | $(SED) '1,5d' >> wordlist
$(SED) '1,/BEGIN_TABLE/d' EZ.txt.in | colrm 1 8 | $(SED) 's/\t.*//' | $(GREP) "^...*" >> wordlist
sort wordlist | uniq | $(SED) 's/ //g' > t
mv t wordlist
printutf8: printutf8.c
$(CC) -o printutf8 printutf8.c
unihan.t2s.t: Unihan.txt printutf8
$(GREP) kSimplifiedVariant Unihan.txt | $(SED) '/#/d' | $(SED) 's/kSimplifiedVariant//' | ./printutf8 > unihan.t2s.t
trad2simp.t: trad2simp.manual unihan.t2s.t
cp unihan.t2s.t tmp1
for I in `colrm 11 < trad2simp.manual` ; do $(SED) "/^$$I/d" tmp1 > tmp2; mv tmp2 tmp1; done
cat trad2simp.manual tmp1 > trad2simp.t
unihan.s2t.t: Unihan.txt printutf8
$(GREP) kTraditionalVariant Unihan.txt | $(SED) '/#/d' | $(SED) 's/kTraditionalVariant//' | ./printutf8 > unihan.s2t.t
simp2trad.t: unihan.s2t.t simp2trad.manual
cp unihan.s2t.t tmp1
for I in `colrm 11 < simp2trad.manual` ; do $(SED) "/^$$I/d" tmp1 > tmp2; mv tmp2 tmp1; done
cat simp2trad.manual tmp1 > simp2trad.t
t2s_1tomany.t: trad2simp.t
$(GREP) -s ".\{19,\}" trad2simp.t | $(SED) 's/U+...../"/' | $(SED) 's/|U+...../"=>"/' | $(SED) 's/|U+.....//g' | $(SED) 's/|/",/' > t2s_1tomany.t
t2s_1to1.t: trad2simp.t s2t_1tomany.t
$(SED) "/.*|.*|.*|.*/d" trad2simp.t | $(SED) 's/U+[0-9a-z][0-9a-z]*/"/' | $(SED) 's/|U+[0-9a-z][0-9a-z]*/"=>"/' | $(SED) 's/|/",/' > t2s_1to1.t
$(GREP) '"."=>"..",' s2t_1tomany.t | $(SED) 's/\("."\)=>".\(.\)",/"\2"=>\1,/' >> t2s_1to1.t
$(GREP) '"."=>"...",' s2t_1tomany.t | $(SED) 's/\("."\)=>".\(.\).",/"\2"=>\1,/' >> t2s_1to1.t
$(GREP) '"."=>"...",' s2t_1tomany.t | $(SED) 's/\("."\)=>"..\(.\)",/"\2"=>\1,/' >> t2s_1to1.t
$(GREP) '"."=>"....",' s2t_1tomany.t | $(SED) 's/\("."\)=>".\(.\)..",/"\2"=>\1,/' >> t2s_1to1.t
$(GREP) '"."=>"....",' s2t_1tomany.t | $(SED) 's/\("."\)=>"..\(.\).",/"\2"=>\1,/' >> t2s_1to1.t
$(GREP) '"."=>"....",' s2t_1tomany.t | $(SED) 's/\("."\)=>"...\(.\)",/"\2"=>\1,/' >> t2s_1to1.t
sort t2s_1to1.t | uniq > t
mv t t2s_1to1.t
s2t_1tomany.t: simp2trad.t
$(GREP) -s ".\{19,\}" simp2trad.t | $(SED) 's/U+...../"/' | $(SED) 's/|U+...../"=>"/' | $(SED) 's/|U+.....//g' | $(SED) 's/|/",/' > s2t_1tomany.t
s2t_1to1.t: simp2trad.t t2s_1tomany.t
$(SED) "/.*|.*|.*|.*/d" simp2trad.t | $(SED) 's/U+[0-9a-z][0-9a-z]*/"/' | $(SED) 's/|U+[0-9a-z][0-9a-z]*/"=>"/' | $(SED) 's/|/",/' > s2t_1to1.t
$(GREP) '"."=>"..",' t2s_1tomany.t | $(SED) 's/\("."\)=>".\(.\)",/"\2"=>\1,/' >> s2t_1to1.t
$(GREP) '"."=>"...",' t2s_1tomany.t | $(SED) 's/\("."\)=>".\(.\).",/"\2"=>\1,/' >> s2t_1to1.t
$(GREP) '"."=>"...",' t2s_1tomany.t | $(SED) 's/\("."\)=>"..\(.\)",/"\2"=>\1,/' >> s2t_1to1.t
$(GREP) '"."=>"....",' t2s_1tomany.t | $(SED) 's/\("."\)=>".\(.\)..",/"\2"=>\1,/' >> s2t_1to1.t
$(GREP) '"."=>"....",' t2s_1tomany.t | $(SED) 's/\("."\)=>"..\(.\).",/"\2"=>\1,/' >> s2t_1to1.t
$(GREP) '"."=>"....",' t2s_1tomany.t | $(SED) 's/\("."\)=>"...\(.\)",/"\2"=>\1,/' >> s2t_1to1.t
sort s2t_1to1.t | uniq > t
mv t s2t_1to1.t
tphrase.t: EZ.txt.in tsi.src
colrm 1 8 < EZ.txt.in | $(SED) 's/\t//g' | $(GREP) "^.\{2,4\}[0-9]" | $(SED) 's/[0-9]//g' > t
iconv -c -f big5 -t utf8 tsi.src | $(SED) 's/ [0-9].*//g' | $(SED) 's/[# ]//g'| $(GREP) "^.\{2,4\}" >> t
sort t | uniq > tphrase.t
alltradphrases.t: tphrase.t s2t_1tomany.t
for i in `cat s2t_1tomany.t | $(SED) 's/.*=>".//' | $(SED) 's/"//g' |$(SED) 's/,/\n/' | $(SED) 's/\(.\)/\1\n/g' |sort | uniq`; do $(GREP) -s $$i tphrase.t ; done > alltradphrases.t || true
tradphrases_2.t: alltradphrases.t
cat alltradphrases.t | $(GREP) "^..$$" | sort | uniq > tradphrases_2.t
tradphrases_3.t: alltradphrases.t
cat alltradphrases.t | $(GREP) "^...$$" | sort | uniq > tradphrases_3.t
for i in `cat tradphrases_2.t`; do $(GREP) $$i tradphrases_3.t ; done | sort | uniq > t3 || true
$(DIFF) t3 tradphrases_3.t | $(GREP) ">" | $(SED) 's/> //' > t
mv t tradphrases_3.t
tradphrases_4.t: alltradphrases.t
cat alltradphrases.t | $(GREP) "^....$$" | sort | uniq > tradphrases_4.t
for i in `cat tradphrases_2.t`; do $(GREP) $$i tradphrases_4.t ; done | sort | uniq > t3 || true
$(DIFF) t3 tradphrases_4.t | $(GREP) ">" | $(SED) 's/> //' > t
mv t tradphrases_4.t
for i in `cat tradphrases_3.t`; do $(GREP) $$i tradphrases_4.t ; done | sort | uniq > t3 || true
$(DIFF) t3 tradphrases_4.t | $(GREP) ">" | $(SED) 's/> //' > t
mv t tradphrases_4.t
tradphrases.t: tradphrases.manual tradphrases_2.t tradphrases_3.t tradphrases_4.t t2s_1tomany.t
cat tradphrases.manual tradphrases_2.t tradphrases_3.t tradphrases_4.t |sort | uniq > tradphrases.t
for i in `$(SED) 's/"\(.\).*/\1/' t2s_1tomany.t ` ; do $(GREP) $$i tradphrases.t ; done | $(DIFF) tradphrases.t - | $(GREP) '<' | $(SED) 's/< //' > t
mv t tradphrases.t
tradphrases.notsure: tradphrases_2.t tradphrases_3.t tradphrases_4.t t2s_1tomany.t
cat tradphrases_2.t tradphrases_3.t tradphrases_4.t |sort | uniq > t
for i in `$(SED) 's/"\(.\).*/\1/' t2s_1tomany.t ` ; do $(GREP) $$i t; done | $(DIFF) t - | $(GREP) '>' | $(SED) 's/> //' > tradphrases.notsure
ph.t: phrase_lib.txt
$(SED) 's/[\t0-9a-zA-Z]//g' phrase_lib.txt | $(GREP) "^.\{2,4\}$$" > ph.t
allsimpphrases.t: ph.t
rm -f allsimpphrases.t
for i in `cat t2s_1tomany.t | $(SED) 's/.*=>".//' | $(SED) 's/"//g' | $(SED) 's/,/\n/' | $(SED) 's/\(.\)/\1\n/g' | sort | uniq `; do $(GREP) $$i ph.t >> allsimpphrases.t; done
simpphrases_2.t: allsimpphrases.t
cat allsimpphrases.t | $(GREP) "^..$$" | sort | uniq > simpphrases_2.t
simpphrases_3.t: allsimpphrases.t
cat allsimpphrases.t | $(GREP) "^...$$" | sort | uniq > simpphrases_3.t
for i in `cat simpphrases_2.t`; do $(GREP) $$i simpphrases_3.t ; done | sort | uniq > t3 || true
$(DIFF) t3 simpphrases_3.t | $(GREP) ">" | $(SED) 's/> //' > t
mv t simpphrases_3.t
simpphrases_4.t: allsimpphrases.t
cat allsimpphrases.t | $(GREP) "^....$$" | sort | uniq > simpphrases_4.t
rm -f t
for i in `cat simpphrases_2.t`; do $(GREP) $$i simpphrases_4.t >> t; done || true
sort t | uniq > t3
$(DIFF) t3 simpphrases_4.t | $(GREP) ">" | $(SED) 's/> //' > t
mv t simpphrases_4.t
for i in `cat simpphrases_3.t`; do $(GREP) $$i simpphrases_4.t; done | sort | uniq > t3 || true
$(DIFF) t3 simpphrases_4.t | $(GREP) ">" | $(SED) 's/> //' > t
mv t simpphrases_4.t
simpphrases.t:simpphrases_2.t simpphrases_3.t simpphrases_4.t t2s_1tomany.t
cat simpphrases_2.t simpphrases_3.t simpphrases_4.t > simpphrases.t
for i in `$(SED) 's/"\(.\).*/\1/' t2s_1tomany.t ` ; do $(GREP) $$i simpphrases.t ; done | $(DIFF) simpphrases.t - | $(GREP) '<' | $(SED) 's/< //' > t
mv t simpphrases.t
simpphrases.notsure:simpphrases_2.t simpphrases_3.t simpphrases_4.t t2s_1tomany.t
cat simpphrases_2.t simpphrases_3.t simpphrases_4.t > t
for i in `$(SED) 's/"\(.\).*/\1/' t2s_1tomany.t ` ; do $(GREP) $$i t ; done | $(DIFF) t - | $(GREP) '>' | $(SED) 's/> //' > simpphrases.notsure
trad2simp1to1.t: t2s_1tomany.t t2s_1to1.t
$(SED) 's/\(.......\).*/\1",/' t2s_1tomany.t > trad2simp1to1.t
cat t2s_1to1.t >> trad2simp1to1.t
simp2trad1to1.t: s2t_1tomany.t s2t_1to1.t
$(SED) 's/\(.......\).*/\1",/' s2t_1tomany.t > simp2trad1to1.t
cat s2t_1to1.t >> simp2trad1to1.t
trad2simp.php: trad2simp1to1.t tradphrases.t
printf '<?php\n$$trad2simp=array(' > trad2simp.php
cat trad2simp1to1.t >> trad2simp.php
printf ');\n$$str=\n"' >> trad2simp.php
cat tradphrases.t >> trad2simp.php
printf '";\n$$t=strtr($$str, $$trad2simp);\necho $$t;\n?>' >> trad2simp.php
simp2trad.php: simp2trad1to1.t simpphrases.t
printf '<?php\n$$simp2trad=array(' > simp2trad.php
cat simp2trad1to1.t >> simp2trad.php
printf ');\n$$str=\n"' >> simp2trad.php
cat simpphrases.t >> simp2trad.php
printf '";\n$$t=strtr($$str, $$simp2trad);\necho $$t;\n?>' >> simp2trad.php
simp2trad.phrases.t: trad2simp.php tradphrases.t
php -f trad2simp.php | $(SED) 's/\(.*\)/"\1" => /' > tmp1
cat tradphrases.t | $(SED) 's/\(.*\)/"\1",/' > tmp2
paste tmp1 tmp2 > simp2trad.phrases.t
trad2simp.phrases.t: simp2trad.php simpphrases.t
php -f simp2trad.php | $(SED) 's/\(.*\)/"\1" => /' > tmp1
cat simpphrases.t | $(SED) 's/\(.*\)/"\1",/' > tmp2
paste tmp1 tmp2 > trad2simp.phrases.t
toHans.dict: trad2simp1to1.t trad2simp.phrases.t
cat trad2simp1to1.t | $(SED) 's/[, \t]//g' | $(SED) 's/=>/\t/' > toHans.dict
cat trad2simp.phrases.t | $(SED) 's/[, \t]//g' | $(SED) 's/=>/\t/' >> toHans.dict
toHant.dict: simp2trad1to1.t simp2trad.phrases.t
cat simp2trad1to1.t | $(SED) 's/[, \t]//g' | $(SED) 's/=>/\t/' > toHant.dict
cat simp2trad.phrases.t | $(SED) 's/[, \t]//g' | $(SED) 's/=>/\t/' >> toHant.dict
toTW.dict: toTW.manual
cat toTW.manual | $(SED) 's/ //g' | $(SED) 's/\(^.*\)\t\(.*\)/"\1"\t"\2"/' > toTW.dict
toHK.dict: toHK.manual
cat toHK.manual | $(SED) 's/ //g' | $(SED) 's/\(^.*\)\t\(.*\)/"\1"\t"\2"/' > toHK.dict
toCN.dict: toCN.manual
cat toCN.manual | $(SED) 's/ //g' | $(SED) 's/\(^.*\)\t\(.*\)/"\1"\t"\2"/' > toCN.dict
toSG.dict: toSG.manual
cat toSG.manual | $(SED) 's/ //g' | $(SED) 's/\(^.*\)\t\(.*\)/"\1"\t"\2"/' > toSG.dict
ZhConversion.php: simp2trad1to1.t simp2trad.phrases.t trad2simp1to1.t trad2simp.phrases.t toCN.manual toHK.manual toSG.manual toTW.manual
printf '<?php\n/**\n * Simplified / Traditional Chinese conversion tables\n' > ZhConversion.php
printf ' *\n * Automatically generated using code and data in includes/zhtable/\n' >> ZhConversion.php
printf ' * Do not modify directly!\n */\n\n' >> ZhConversion.php
printf '$$zh2Hant = array(\n' >> ZhConversion.php
cat simp2trad1to1.t >> ZhConversion.php
echo >> ZhConversion.php
cat simp2trad.phrases.t >> ZhConversion.php
echo ');' >> ZhConversion.php
echo >> ZhConversion.php
printf '$$zh2Hans = array(\n' >> ZhConversion.php
cat trad2simp1to1.t >> ZhConversion.php
echo >> ZhConversion.php
cat trad2simp.phrases.t >> ZhConversion.php
echo ');' >> ZhConversion.php
echo >> ZhConversion.php
printf '$$zh2TW = array(\n' >> ZhConversion.php
$(SED) 's/\(.*\)\t\(.*\)/"\1" => "\2",/' toTW.manual >> ZhConversion.php
echo ');' >> ZhConversion.php
echo >> ZhConversion.php
printf '$$zh2HK = array(\n' >> ZhConversion.php
$(SED) 's/\(.*\)\t\(.*\)/"\1" => "\2",/' toHK.manual >> ZhConversion.php
echo ');' >> ZhConversion.php
echo >> ZhConversion.php
printf '$$zh2CN = array(\n' >> ZhConversion.php
$(SED) 's/\(.*\)\t\(.*\)/"\1" => "\2",/' toCN.manual >> ZhConversion.php
echo ');' >> ZhConversion.php
echo >> ZhConversion.php
printf '$$zh2SG = array(\n' >> ZhConversion.php
$(SED) 's/\(.*\)\t\(.*\)/"\1" => "\2",/' toSG.manual >> ZhConversion.php
echo >> ZhConversion.php
printf ');' >> ZhConversion.php
clean: cleantmp cleandl
cleantmp:
# Stuff unpacked from the files fetched by wget
rm -f \
Unihan.txt \
EZ.txt.in \
phrase_lib.txt \
tsi.src
# Temporary files and other trash
rm -f ZhConversion.php tmp1 tmp2 tmp3 t3 *.t trad2simp.php simp2trad.php *.dict printutf8 *~ \
simpphrases.notsure tradphrases.notsure wordlist
cleandl:
rm -f \
Unihan.zip \
scim-tables-$(SCIM_TABLES_VER).tar.gz \
scim-pinyin-$(SCIM_PINYIN_VER).tar.gz \
libtabe-$(LIBTABE_VER).tgz
|
