opencc-wasm 0.9.0 → 0.10.0

package/dist/data/config/t2jp.json

@@ -1,9 +1,8 @@
 {
   "name": "Old Japanese Kanji (Kyūjitai) to New Japanese Kanji (Shinjitai)",
-  "segmentation": {
-    "type": "mmseg",
-    "dict": { "type": "ocd2", "file": "JPShinjitaiCharactersRev.ocd2" }
-  },
+  "normalization": [
+    { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
+  ],
   "conversion_chain": [
     { "dict": { "type": "ocd2", "file": "JPShinjitaiCharactersRev.ocd2" } }
   ]

package/dist/data/config/t2s.json

@@ -1,13 +1,13 @@
 {
   "name": "Traditional Chinese (OpenCC Standard) to Simplified Chinese",
-  "segmentation": {
-    "type": "mmseg",
-    "dict": { "type": "ocd2", "file": "TSPhrases.ocd2" }
-  },
+  "normalization": [
+    { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
+  ],
   "conversion_chain": [
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
           { "type": "ocd2", "file": "TSPhrases.ocd2" },
           {

package/dist/data/config/t2s_cngov.json

@@ -7,16 +7,21 @@
       "file": "cngov/TSPhrases.ocd2"
     }
   },
-  "conversion_chain": [{
-    "dict": {
-      "type": "group",
-      "dicts": [{
-        "type": "ocd2",
-        "file": "cngov/TSPhrases.ocd2"
-      }, {
-        "type": "ocd2",
-        "file": "cngov/TSCharacters.ocd2"
-      }]
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "cngov/TSPhrases.ocd2"
+          },
+          {
+            "type": "ocd2",
+            "file": "cngov/TSCharacters.ocd2"
+          }
+        ]
+      }
     }
-  }]
+  ]
 }

package/dist/data/config/t2tw.json

@@ -1,19 +1,13 @@
 {
   "name": "Traditional Chinese (OpenCC Standard) to Traditional Chinese (Taiwan Standard)",
-  "segmentation": {
-    "type": "mmseg",
-    "dict": {
-      "type": "group",
-      "dicts": [
-        { "type": "ocd2", "file": "TWVariantsPhrases.ocd2" },
-        { "type": "ocd2", "file": "TWVariants.ocd2" }
-      ]
-    }
-  },
+  "normalization": [
+    { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
+  ],
   "conversion_chain": [
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
           { "type": "ocd2", "file": "TWVariantsPhrases.ocd2" },
           { "type": "ocd2", "file": "TWVariants.ocd2" }

package/dist/data/config/tw2s.json

@@ -1,5 +1,8 @@
 {
   "name": "Traditional Chinese (Taiwan Standard) to Simplified Chinese",
+  "normalization": [
+    { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
+  ],
   "segmentation": {
     "type": "mmseg",
     "dict": { "type": "ocd2", "file": "TSPhrases.ocd2" }
@@ -8,6 +11,7 @@
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
           { "type": "ocd2", "file": "TWVariantsRevPhrases.ocd2" },
           { "type": "ocd2", "file": "TWVariantsRev.ocd2" }
@@ -17,6 +21,7 @@
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
           { "type": "ocd2", "file": "TSPhrases.ocd2" },
           {

package/dist/data/config/tw2sp.json

@@ -1,5 +1,8 @@
 {
   "name": "Traditional Chinese (Taiwan Standard) to Simplified Chinese (Mainland China Phrases)",
+  "normalization": [
+    { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
+  ],
   "segmentation": {
     "type": "mmseg",
     "dict": { "type": "ocd2", "file": "TSPhrases.ocd2" }
@@ -8,6 +11,7 @@
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
           { "type": "ocd2", "file": "TWPhrasesRev.ocd2" },
           { "type": "ocd2", "file": "TWVariantsRevPhrases.ocd2" },
@@ -18,6 +22,7 @@
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
           { "type": "ocd2", "file": "TSPhrases.ocd2" },
           {

package/dist/data/config/tw2sp_jieba.json

@@ -1,5 +1,13 @@
 {
   "name": "Traditional Chinese (Taiwan standard) to Simplified Chinese (with phrases, Jieba Segmentation - Experimental)",
+  "normalization": [
+    {
+      "dict": {
+        "type": "ocd2",
+        "file": "CJK_Compatibility_Ideographs.ocd2"
+      }
+    }
+  ],
   "segmentation": {
     "type": "jieba",
     "resources": {
@@ -11,24 +19,41 @@
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
-          { "type": "ocd2", "file": "TWPhrasesRev.ocd2" },
-          { "type": "ocd2", "file": "TWVariantsRevPhrases.ocd2" },
-          { "type": "ocd2", "file": "TWVariantsRev.ocd2" }
+          {
+            "type": "ocd2",
+            "file": "TWPhrasesRev.ocd2"
+          },
+          {
+            "type": "ocd2",
+            "file": "TWVariantsRevPhrases.ocd2"
+          },
+          {
+            "type": "ocd2",
+            "file": "TWVariantsRev.ocd2"
+          }
         ]
       }
     },
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
-          { "type": "ocd2", "file": "TSPhrases.ocd2" },
+          {
+            "type": "ocd2",
+            "file": "TSPhrases.ocd2"
+          },
           {
             "type": "ocd2",
             "file": "TSCharactersExt.ocd2",
             "may_output_tofu": true
           },
-          { "type": "ocd2", "file": "TSCharacters.ocd2" }
+          {
+            "type": "ocd2",
+            "file": "TSCharacters.ocd2"
+          }
         ]
       }
     }

package/dist/data/config/tw2t.json

@@ -1,13 +1,13 @@
 {
   "name": "Traditional Chinese (Taiwan Standard) to Traditional Chinese (OpenCC Standard)",
-  "segmentation": {
-    "type": "mmseg",
-    "dict": { "type": "ocd2", "file": "TWVariantsRevPhrases.ocd2" }
-  },
+  "normalization": [
+    { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
+  ],
   "conversion_chain": [
     {
       "dict": {
         "type": "group",
+        "match_policy": "short_circuit",
         "dicts": [
           { "type": "ocd2", "file": "TWVariantsRevPhrases.ocd2" },
           { "type": "ocd2", "file": "TWVariantsRev.ocd2" }

package/dist/data/jieba_dict/jieba.dict.utf8

@@ -887,7 +887,6 @@ T恤 4 n
 一准儿 2 l
 一凉 3 a
 一几 10 m
-一出 964 m
 一出场 3 m
 一出头 3 m
 一出戏 3 i
@@ -18653,6 +18652,7 @@ T恤 4 n
 也门 234 d
 也门共和国 14 ns
 习 1216 v
+习总书记 4 nr
 习与性成 3 i
 习中学 3 n
 习举业 2 n

package/dist/data/jieba_dict/user.dict.utf8

@@ -1,5 +1,4 @@
 云计算
-韩玉鉴赏
 蓝翔 nz
 区块链 10 nz
 牛骥同一皁

package/dist/esm/index.js

@@ -165,6 +165,9 @@ async function ensureConfig(configName) {
 
   const dicts = new Set();
   const resources = new Set();
+  if (Array.isArray(cfgJson.normalization)) {
+    cfgJson.normalization.forEach((item) => collectOcd2Files(item?.dict, dicts));
+  }
   collectOcd2Files(cfgJson.segmentation?.dict, dicts);
   collectSegmentationResources(cfgJson.segmentation, resources);
   if (Array.isArray(cfgJson.conversion_chain)) {
@@ -198,6 +201,9 @@ async function ensureConfig(configName) {
       node.dicts.forEach(patchPaths);
     }
   };
+  if (Array.isArray(cfgJson.normalization)) {
+    cfgJson.normalization.forEach((item) => patchPaths(item?.dict));
+  }
   patchPaths(cfgJson.segmentation?.dict);
   if (Array.isArray(cfgJson.conversion_chain)) {
     cfgJson.conversion_chain.forEach((item) => patchPaths(item?.dict));