Sync OpenCC dictionaries, configs, and upstream testcases to version 1.4.1

MANIFEST.in

@@ -1,3 +1,3 @@
 include LICENSE.txt
 include README.md
-recursive-include opencc *.txt *.py
+recursive-include opencc *.txt *.py *.json

README.md

@@ -74,17 +74,27 @@ See https://docs.python.org/3/library/codecs.html#standard-encodings for list of
 
 ### Conversions 轉換
 
-* `hk2s`: Traditional Chinese (Hong Kong standard) to Simplified Chinese
+* `hk2s`: Traditional Chinese (Hong Kong variant) to Simplified Chinese
 
-* `s2hk`: Simplified Chinese to Traditional Chinese (Hong Kong standard)
+* `hk2sp`: Traditional Chinese (Hong Kong variant) to Simplified Chinese (with phrases)
+
+* `hk2t`: Traditional Chinese (Hong Kong variant) to Traditional Chinese
+
+* `jp2t`: New Japanese Kanji (Shinjitai) to Traditional Chinese Characters (Kyūjitai)
+
+* `s2hk`: Simplified Chinese to Traditional Chinese (Hong Kong variant)
+
+* `s2hkp`: Simplified Chinese to Traditional Chinese (Hong Kong variant, with phrases)
 
 * `s2t`: Simplified Chinese to Traditional Chinese
 
 * `s2tw`: Simplified Chinese to Traditional Chinese (Taiwan standard)
 
 * `s2twp`: Simplified Chinese to Traditional Chinese (Taiwan standard, with phrases)
 
-* `t2hk`: Traditional Chinese to Traditional Chinese (Hong Kong standard)
+* `t2hk`: Traditional Chinese to Traditional Chinese (Hong Kong variant)
+
+* `t2jp`: Traditional Chinese Characters (Kyūjitai) to New Japanese Kanji (Shinjitai)
 
 * `t2s`: Traditional Chinese to Simplified Chinese
 
@@ -94,6 +104,8 @@ See https://docs.python.org/3/library/codecs.html#standard-encodings for list of
 
 * `tw2sp`: Traditional Chinese (Taiwan standard) to Simplified Chinese (with phrases)
 
+* `tw2t`: Traditional Chinese (Taiwan standard) to Traditional Chinese
+
 ## Issues 問題
 
 當轉換有兩個以上的字詞可能時，程式只會使用第一個。

helper/readme.txt

@@ -1,13 +1,3 @@
-merge.py
-    for merging dictionary files into a single file (requires Python3)
-
-    merge 'TWPhrasesIT.txt', 'TWPhrasesName.txt', and 'TWPhrasesOther.txt'
-    into a single file 'TWPhrases.txt'
-
-    Run:
-        python3 merge.py
-
-
 reverse.py
     for reversing dictionary keys and values (requires Python3)
 

helper/reverse.py

@@ -15,7 +15,8 @@
 REV_INPUTS = [
     'TWVariants',
     'TWPhrases',
-    'HKVariants'
+    'HKVariants',
+    'JPShinjitaiCharacters'
 ]
 
 
@@ -36,13 +37,18 @@ def reverse(rev_inputs=REV_INPUTS):
         with open(input_file, 'r', encoding='utf-8') as f:
             for line in f:
                 line = line.strip()
+                # Skip blank lines and upstream comment/header lines
+                if not line or line.startswith('#'):
+                    continue
                 split = line.split('\t')
                 if len(split) < 2:
                     continue
                 term1 = split[0]
                 term2 = split[1]
 
                 for char in term2.split(' '):
+                    if not char:
+                        continue
                     if char in reversed_dict:
                         reversed_dict[char].append(term1)
                     else:

opencc/config/hk2sp.json

@@ -0,0 +1,36 @@
+{
+  "name": "Traditional Chinese (Hong Kong variant) to Simplified Chinese (with phrases)",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "txt",
+      "file": "TSPhrases.txt"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "txt",
+        "file": "HKPhrasesRev.txt"
+      }, {
+        "type": "txt",
+        "file": "HKVariantsRevPhrases.txt"
+      }, {
+        "type": "txt",
+        "file": "HKVariantsRev.txt"
+      }]
+    }
+  }, {
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "txt",
+        "file": "TSPhrases.txt"
+      }, {
+        "type": "txt",
+        "file": "TSCharacters.txt"
+      }]
+    }
+  }]
+}

opencc/config/hk2t.json

@@ -1,5 +1,5 @@
 {
-  "name": "Traditional Chinese (Hong Kong variant) to Traditional Chinese",
+  "name": "Traditional Chinese (Hong Kong variant) to Traditional Chinese (OpenCC Standard)",
   "segmentation": {
     "type": "mmseg",
     "dict": {

opencc/config/jp2t.json

@@ -16,9 +16,6 @@
       }, {
         "type": "txt",
         "file": "JPShinjitaiCharacters.txt"
-      }, {
-        "type": "txt",
-        "file": "JPVariantsRev.txt"
       }]
     }
   }]

opencc/config/s2hkp.json

@@ -0,0 +1,36 @@
+{
+  "name": "Simplified Chinese to Traditional Chinese (Hong Kong variant, with phrases)",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "txt",
+      "file": "STPhrases.txt"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "txt",
+        "file": "STPhrases.txt"
+      }, {
+        "type": "txt",
+        "file": "STCharacters.txt"
+      }]
+    }
+  }, {
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "txt",
+        "file": "HKPhrases.txt"
+      }, {
+        "type": "txt",
+        "file": "HKVariantsPhrases.txt"
+      }, {
+        "type": "txt",
+        "file": "HKVariants.txt"
+      }]
+    }
+  }]
+}

opencc/config/t2jp.json

@@ -4,13 +4,13 @@
     "type": "mmseg",
     "dict": {
       "type": "txt",
-      "file": "JPVariants.txt"
+      "file": "JPShinjitaiCharactersRev.txt"
     }
   },
   "conversion_chain": [{
     "dict": {
       "type": "txt",
-      "file": "JPVariants.txt"
+      "file": "JPShinjitaiCharactersRev.txt"
     }
   }]
 }

opencc/config/tw2t.json

@@ -1,5 +1,5 @@
 {
-  "name": "Traditional Chinese (Taiwan standard) to Traditional Chinese",
+  "name": "Traditional Chinese (Taiwan Standard) to Traditional Chinese (OpenCC Standard)",
   "segmentation": {
     "type": "mmseg",
     "dict": {

opencc/dictionary/HKPhrases.txt

@@ -0,0 +1,46 @@
+# Open Chinese Convert (OpenCC) Dictionary
+# File: HKPhrases.txt
+# Format: key	value(s) (values separated by spaces)
+# License: Apache-2.0 (see LICENSE)
+# Source: https://github.com/ByVoid/OpenCC
+# Used in configs: s2hkp.json (via HKPhrases.ocd2)
+
+伊利諾伊	伊利諾
+伊利諾伊州	伊利諾州
+俄克拉何馬	奧克拉荷馬
+俄克拉何馬州	奧克拉荷馬州
+俄克拉荷馬	奧克拉荷馬
+俄克拉荷馬州	奧克拉荷馬州
+光標	游標
+北卡羅來納	北卡羅萊納
+北卡羅來納州	北卡羅萊納州
+南卡羅來納	南卡羅萊納
+南卡羅來納州	南卡羅萊納州
+密歇根	密芝根
+密歇根州	密芝根州
+寬帶	寬頻
+幾率	機率 概率
+弗吉尼亞	維珍尼亞
+弗吉尼亞州	維珍尼亞州
+得克薩斯	德薩斯
+得克薩斯州	德薩斯州
+德克薩斯	德薩斯
+德克薩斯州	德薩斯州
+搜索	搜尋
+操作系統	作業系統
+文件夾	資料夾
+服務器	伺服器
+概率	概率 機會率
+硬盤	硬碟
+編程語言	程式語言
+羅得島	羅德島
+羅得島州	羅德島州
+舒芙蕾	梳芙厘
+西弗吉尼亞	西維珍尼亞
+西弗吉尼亞州	西維珍尼亞州
+賓夕法尼亞	賓夕凡尼亞
+賓夕法尼亞州	賓夕凡尼亞州
+隱私權	私隱權
+馬里蘭	馬利蘭
+馬里蘭州	馬利蘭州
+鼠標	滑鼠

opencc/dictionary/HKPhrasesRev.txt

@@ -0,0 +1,43 @@
+# Open Chinese Convert (OpenCC) Dictionary
+# File: HKPhrasesRev.txt
+# Format: key	value(s) (values separated by spaces)
+# License: Apache-2.0 (see LICENSE)
+# Source: https://github.com/ByVoid/OpenCC
+# Used in configs: hk2sp.json (via HKPhrasesRev.ocd2)
+
+伊利諾	伊利諾伊
+伊利諾州	伊利諾伊州
+伺服器	服務器
+作業系統	操作系統
+北卡羅萊納	北卡羅來納
+北卡羅萊納州	北卡羅來納州
+南卡羅萊納	南卡羅來納
+南卡羅萊納州	南卡羅來納州
+奧克拉荷馬	俄克拉何馬 俄克拉荷馬
+奧克拉荷馬州	俄克拉何馬州 俄克拉荷馬州
+密芝根	密歇根
+密芝根州	密歇根州
+寬頻	寬帶
+德薩斯	得克薩斯 德克薩斯
+德薩斯州	得克薩斯州 德克薩斯州
+搜尋	搜索
+梳芙厘	舒芙蕾
+概率	概率 幾率
+機會率	概率
+機率	幾率
+游標	光標
+滑鼠	鼠標
+硬碟	硬盤
+私隱權	隱私權
+程式語言	編程語言
+維珍尼亞	弗吉尼亞
+維珍尼亞州	弗吉尼亞州
+羅德島	羅得島
+羅德島州	羅得島州
+西維珍尼亞	西弗吉尼亞
+西維珍尼亞州	西弗吉尼亞州
+資料夾	文件夾
+賓夕凡尼亞	賓夕法尼亞
+賓夕凡尼亞州	賓夕法尼亞州
+馬利蘭	馬里蘭
+馬利蘭州	馬里蘭州