加入符号词汇

build

@@ -123,20 +123,23 @@ extract 360万中文词库+词性+词频.zip || exit
 ln -sf rime-essay/essay.txt essay.txt || exit
 ln -sf rime-pinyin-simp/pinyin_simp.dict.yaml pinyin_simp.dict.yaml || exit
 
-# 开始生成词典
-../src/clover-dict-gen --minfreq=$minfreq || exit
-for i in THUOCL/data/THUOCL_*; do
-	echo "转换 $i"
-	../src/thuocl2rime $i || exit
-done
-
 # 生成符号列表
 cd rime-symbols || exit
 mkdir -p opencc || exit
 cd opencc || exit
 ../rime-symbols-gen || exit
 cd ../.. || exit
 
+# 生成符号词汇
+cat */opencc/*.txt | opencc -c t2s.json | uniq > symbols.txt
+
+# 开始生成词典
+../src/clover-dict-gen --minfreq=$minfreq || exit
+for i in THUOCL/data/THUOCL_*; do
+	echo "转换 $i"
+	../src/thuocl2rime $i || exit
+done
+
 # 生成 data 目录
 mkdir -p ../data || exit
 cp ../src/*.yaml ../data || exit

src/clover-dict-gen

@@ -265,6 +265,16 @@ def main(args):
         100000, PrintProcess('正在合并袖珍简化字拼音的词库 (%s/%s)').process)
     print('成功合并袖珍简化字拼音 %s 个汉字， %s 个词组。' % r)
 
+    # 合并转换符号词汇
+    r = generator.mergeDict(
+        open('symbols.txt',
+            'r',
+            encoding = 'utf-8').read(),
+        10000,
+        0,
+        100000, PrintProcess('正在合并符号词汇 (%s/%s)').process)
+    print('成功合并符号词汇 %s 个汉字， %s 个词组。' % r)
+
     word_dict_name = 'clover.base'
     parse_dict_name = 'clover.phrase'