opencc-wasm 0.8.2 → 0.10.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (75) hide show
  1. package/README.md +50 -5
  2. package/README.zh.md +51 -6
  3. package/dist/cjs/index.cjs +9 -3
  4. package/dist/cjs/opencc-wasm.cjs +1 -1
  5. package/dist/cjs/opencc-wasm.wasm +0 -0
  6. package/dist/data/config/hk2s.json +30 -26
  7. package/dist/data/config/hk2sp.json +38 -0
  8. package/dist/data/config/hk2sp_jieba.json +61 -0
  9. package/dist/data/config/hk2t.json +14 -18
  10. package/dist/data/config/jp2t.json +15 -22
  11. package/dist/data/config/opencc_config.schema.json +45 -94
  12. package/dist/data/config/s2hk.json +37 -18
  13. package/dist/data/config/s2hk_jieba.json +51 -16
  14. package/dist/data/config/s2hkp.json +47 -0
  15. package/dist/data/config/s2hkp_jieba.json +66 -0
  16. package/dist/data/config/s2t.json +22 -19
  17. package/dist/data/config/s2t_cngov.json +16 -18
  18. package/dist/data/config/s2t_jieba.json +35 -11
  19. package/dist/data/config/s2tw.json +38 -19
  20. package/dist/data/config/s2tw_jieba.json +51 -16
  21. package/dist/data/config/s2twp.json +39 -24
  22. package/dist/data/config/s2twp_jieba.json +55 -21
  23. package/dist/data/config/t2cngov.json +16 -18
  24. package/dist/data/config/t2cngov_keep_simp.json +16 -18
  25. package/dist/data/config/t2hk.json +15 -13
  26. package/dist/data/config/t2jp.json +7 -14
  27. package/dist/data/config/t2s.json +20 -19
  28. package/dist/data/config/t2s_cngov.json +16 -18
  29. package/dist/data/config/t2tw.json +15 -13
  30. package/dist/data/config/tw2s.json +31 -27
  31. package/dist/data/config/tw2sp.json +32 -30
  32. package/dist/data/config/tw2sp_jieba.json +50 -25
  33. package/dist/data/config/tw2t.json +14 -18
  34. package/dist/data/dict/CJK_Compatibility_Ideographs.ocd2 +0 -0
  35. package/dist/data/dict/HKPhrases.ocd2 +0 -0
  36. package/dist/data/dict/HKPhrasesRev.ocd2 +0 -0
  37. package/dist/data/dict/HKVariants.ocd2 +0 -0
  38. package/dist/data/dict/HKVariantsPhrases.ocd2 +0 -0
  39. package/dist/data/dict/HKVariantsRev.ocd2 +0 -0
  40. package/dist/data/dict/HKVariantsRevPhrases.ocd2 +0 -0
  41. package/dist/data/dict/JPShinjitaiCharacters.ocd2 +0 -0
  42. package/dist/data/dict/JPShinjitaiCharactersRev.ocd2 +0 -0
  43. package/dist/data/dict/JPShinjitaiPhrases.ocd2 +0 -0
  44. package/dist/data/dict/STCharacters.ocd2 +0 -0
  45. package/dist/data/dict/STPhrases.ocd2 +0 -0
  46. package/dist/data/dict/STPhrases_GeneratedFromRegionalPhrases.ocd2 +0 -0
  47. package/dist/data/dict/TSCharacters.ocd2 +0 -0
  48. package/dist/data/dict/TSCharactersExt.ocd2 +0 -0
  49. package/dist/data/dict/TSPhrases.ocd2 +0 -0
  50. package/dist/data/dict/TWPhrases.ocd2 +0 -0
  51. package/dist/data/dict/TWPhrasesRev.ocd2 +0 -0
  52. package/dist/data/dict/TWVariants.ocd2 +0 -0
  53. package/dist/data/dict/TWVariantsPhrases.ocd2 +0 -0
  54. package/dist/data/dict/TWVariantsRev.ocd2 +0 -0
  55. package/dist/data/dict/TWVariantsRevPhrases.ocd2 +0 -0
  56. package/dist/data/dict/cngov/STCharacters.ocd2 +0 -0
  57. package/dist/data/dict/cngov/STPhrases.ocd2 +0 -0
  58. package/dist/data/dict/cngov/TGCharacters.ocd2 +0 -0
  59. package/dist/data/dict/cngov/TGCharacters_keep_simp.ocd2 +0 -0
  60. package/dist/data/dict/cngov/TGPhrases.ocd2 +0 -0
  61. package/dist/data/dict/cngov/TSCharacters.ocd2 +0 -0
  62. package/dist/data/dict/cngov/TSPhrases.ocd2 +0 -0
  63. package/dist/data/jieba_dict/jieba.dict.utf8 +1 -1
  64. package/dist/data/jieba_dict/jieba_merged.ocd2 +0 -0
  65. package/dist/data/jieba_dict/user.dict.utf8 +2 -1
  66. package/dist/esm/index.js +8 -0
  67. package/dist/esm/opencc-wasm.js +1 -1
  68. package/dist/esm/opencc-wasm.wasm +0 -0
  69. package/dist/opencc-wasm.wasm +0 -0
  70. package/index.d.ts +1 -0
  71. package/package.json +1 -1
  72. package/dist/data/dict/JPVariants.ocd2 +0 -0
  73. package/dist/data/dict/JPVariantsRev.ocd2 +0 -0
  74. package/dist/data/dict/cngov/GovVariants.ocd2 +0 -0
  75. package/dist/data/dict/cngov/GovVariants_keep_simp.ocd2 +0 -0
package/dist/data/config/s2tw_jieba.json CHANGED
@@ -1,5 +1,13 @@
1
1
  {
2
2
  "name": "Simplified Chinese to Traditional Chinese (Taiwan standard, Jieba Segmentation - Experimental)",
3
+ "normalization": [
4
+ {
5
+ "dict": {
6
+ "type": "ocd2",
7
+ "file": "CJK_Compatibility_Ideographs.ocd2"
8
+ }
9
+ }
10
+ ],
3
11
  "segmentation": {
4
12
  "type": "jieba",
5
13
  "resources": {
@@ -7,21 +15,48 @@
7
15
  "model_path": "jieba_dict/hmm_model.utf8"
8
16
  }
9
17
  },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "group",
13
- "dicts": [{
14
- "type": "ocd2",
15
- "file": "STPhrases.ocd2"
16
- }, {
17
- "type": "ocd2",
18
- "file": "STCharacters.ocd2"
19
- }]
20
- }
21
- }, {
22
- "dict": {
23
- "type": "ocd2",
24
- "file": "TWVariants.ocd2"
18
+ "conversion_chain": [
19
+ {
20
+ "dict": {
21
+ "type": "group",
22
+ "match_policy": "short_circuit",
23
+ "dicts": [
24
+ {
25
+ "type": "group",
26
+ "match_policy": "union",
27
+ "dicts": [
28
+ {
29
+ "type": "ocd2",
30
+ "file": "STPhrases.ocd2"
31
+ },
32
+ {
33
+ "type": "ocd2",
34
+ "file": "STPhrases_GeneratedFromRegionalPhrases.ocd2"
35
+ }
36
+ ]
37
+ },
38
+ {
39
+ "type": "ocd2",
40
+ "file": "STCharacters.ocd2"
41
+ }
42
+ ]
43
+ }
44
+ },
45
+ {
46
+ "dict": {
47
+ "type": "group",
48
+ "match_policy": "short_circuit",
49
+ "dicts": [
50
+ {
51
+ "type": "ocd2",
52
+ "file": "TWVariantsPhrases.ocd2"
53
+ },
54
+ {
55
+ "type": "ocd2",
56
+ "file": "TWVariants.ocd2"
57
+ }
58
+ ]
59
+ }
25
60
  }
26
- }]
61
+ ]
27
62
  }
package/dist/data/config/s2twp.json CHANGED
@@ -1,32 +1,47 @@
1
1
  {
2
- "name": "Simplified Chinese to Traditional Chinese (Taiwan standard, with phrases)",
2
+ "name": "Simplified Chinese to Traditional Chinese (Taiwan Standard, with Taiwan Phrases)",
3
+ "normalization": [
4
+ { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
5
+ ],
3
6
  "segmentation": {
4
7
  "type": "mmseg",
5
- "dict": {
6
- "type": "ocd2",
7
- "file": "STPhrases.ocd2"
8
- }
9
- },
10
- "conversion_chain": [{
11
8
  "dict": {
12
9
  "type": "group",
13
- "dicts": [{
14
- "type": "ocd2",
15
- "file": "STPhrases.ocd2"
16
- }, {
17
- "type": "ocd2",
18
- "file": "STCharacters.ocd2"
19
- }]
10
+ "match_policy": "union",
11
+ "dicts": [
12
+ { "type": "ocd2", "file": "STPhrases.ocd2" },
13
+ { "type": "ocd2", "file": "STPhrases_GeneratedFromRegionalPhrases.ocd2" }
14
+ ]
20
15
  }
21
- }, {
22
- "dict": {
23
- "type": "ocd2",
24
- "file": "TWPhrases.ocd2"
25
- }
26
- }, {
27
- "dict": {
28
- "type": "ocd2",
29
- "file": "TWVariants.ocd2"
16
+ },
17
+ "conversion_chain": [
18
+ {
19
+ "dict": {
20
+ "type": "group",
21
+ "match_policy": "short_circuit",
22
+ "dicts": [
23
+ {
24
+ "type": "group",
25
+ "match_policy": "union",
26
+ "dicts": [
27
+ { "type": "ocd2", "file": "STPhrases.ocd2" },
28
+ { "type": "ocd2", "file": "STPhrases_GeneratedFromRegionalPhrases.ocd2" }
29
+ ]
30
+ },
31
+ { "type": "ocd2", "file": "STCharacters.ocd2" }
32
+ ]
33
+ }
34
+ },
35
+ {
36
+ "dict": {
37
+ "type": "group",
38
+ "match_policy": "short_circuit",
39
+ "dicts": [
40
+ { "type": "ocd2", "file": "TWPhrases.ocd2" },
41
+ { "type": "ocd2", "file": "TWVariantsPhrases.ocd2" },
42
+ { "type": "ocd2", "file": "TWVariants.ocd2" }
43
+ ]
44
+ }
30
45
  }
31
- }]
46
+ ]
32
47
  }
package/dist/data/config/s2twp_jieba.json CHANGED
@@ -1,5 +1,13 @@
1
1
  {
2
2
  "name": "Simplified Chinese to Traditional Chinese (Taiwan standard, with phrases, Jieba Segmentation - Experimental)",
3
+ "normalization": [
4
+ {
5
+ "dict": {
6
+ "type": "ocd2",
7
+ "file": "CJK_Compatibility_Ideographs.ocd2"
8
+ }
9
+ }
10
+ ],
3
11
  "segmentation": {
4
12
  "type": "jieba",
5
13
  "resources": {
@@ -7,26 +15,52 @@
7
15
  "model_path": "jieba_dict/hmm_model.utf8"
8
16
  }
9
17
  },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "group",
13
- "dicts": [{
14
- "type": "ocd2",
15
- "file": "STPhrases.ocd2"
16
- }, {
17
- "type": "ocd2",
18
- "file": "STCharacters.ocd2"
19
- }]
20
- }
21
- }, {
22
- "dict": {
23
- "type": "ocd2",
24
- "file": "TWPhrases.ocd2"
25
- }
26
- }, {
27
- "dict": {
28
- "type": "ocd2",
29
- "file": "TWVariants.ocd2"
18
+ "conversion_chain": [
19
+ {
20
+ "dict": {
21
+ "type": "group",
22
+ "match_policy": "short_circuit",
23
+ "dicts": [
24
+ {
25
+ "type": "group",
26
+ "match_policy": "union",
27
+ "dicts": [
28
+ {
29
+ "type": "ocd2",
30
+ "file": "STPhrases.ocd2"
31
+ },
32
+ {
33
+ "type": "ocd2",
34
+ "file": "STPhrases_GeneratedFromRegionalPhrases.ocd2"
35
+ }
36
+ ]
37
+ },
38
+ {
39
+ "type": "ocd2",
40
+ "file": "STCharacters.ocd2"
41
+ }
42
+ ]
43
+ }
44
+ },
45
+ {
46
+ "dict": {
47
+ "type": "group",
48
+ "match_policy": "short_circuit",
49
+ "dicts": [
50
+ {
51
+ "type": "ocd2",
52
+ "file": "TWPhrases.ocd2"
53
+ },
54
+ {
55
+ "type": "ocd2",
56
+ "file": "TWVariantsPhrases.ocd2"
57
+ },
58
+ {
59
+ "type": "ocd2",
60
+ "file": "TWVariants.ocd2"
61
+ }
62
+ ]
63
+ }
30
64
  }
31
- }]
65
+ ]
32
66
  }
package/dist/data/config/t2cngov.json CHANGED
@@ -1,12 +1,5 @@
1
1
  {
2
2
  "name": "Traditional Chinese to Traditional Chinese (Chinese Government standard)",
3
- "author": "TerryTian-tech",
4
- "license": "Apache License 2.0",
5
- "source": "https://github.com/TerryTian-tech/OpenCC-Traditional-Chinese-characters-according-to-Chinese-government-standards",
6
- "contributors": ["TerryTian-tech", "Yi Jianpeng", "Hu Xinmei", "Duan Yatong"],
7
- "reference": "《通用规范汉字表》(2013)",
8
- "description": "Converts traditional Chinese (from various standards) to China's government standard traditional characters. Includes simplified-to-standard conversion for mixed documents.",
9
-
10
3
  "segmentation": {
11
4
  "type": "mmseg",
12
5
  "dict": {
@@ -14,16 +7,21 @@
14
7
  "file": "cngov/TGPhrases.ocd2"
15
8
  }
16
9
  },
17
- "conversion_chain": [{
18
- "dict": {
19
- "type": "group",
20
- "dicts": [{
21
- "type": "ocd2",
22
- "file": "cngov/TGPhrases.ocd2"
23
- }, {
24
- "type": "ocd2",
25
- "file": "cngov/TGCharacters.ocd2"
26
- }]
10
+ "conversion_chain": [
11
+ {
12
+ "dict": {
13
+ "type": "group",
14
+ "dicts": [
15
+ {
16
+ "type": "ocd2",
17
+ "file": "cngov/TGPhrases.ocd2"
18
+ },
19
+ {
20
+ "type": "ocd2",
21
+ "file": "cngov/TGCharacters.ocd2"
22
+ }
23
+ ]
24
+ }
27
25
  }
28
- }]
26
+ ]
29
27
  }
package/dist/data/config/t2cngov_keep_simp.json CHANGED
@@ -1,12 +1,5 @@
1
1
  {
2
2
  "name": "Traditional Chinese to Traditional Chinese (Chinese Government standard) with Simplified Chinese remaining unchanged",
3
- "author": "TerryTian-tech",
4
- "license": "Apache License 2.0",
5
- "source": "https://github.com/TerryTian-tech/OpenCC-Traditional-Chinese-characters-according-to-Chinese-government-standards",
6
- "contributors": ["TerryTian-tech", "Yi Jianpeng", "Hu Xinmei", "Duan Yatong"],
7
- "reference": "《通用规范汉字表》(2013)",
8
- "description": "Conservative conversion that preserves intentional simplified characters in mixed documents while standardizing traditional characters only.",
9
-
10
3
  "segmentation": {
11
4
  "type": "mmseg",
12
5
  "dict": {
@@ -14,16 +7,21 @@
14
7
  "file": "cngov/TGPhrases.ocd2"
15
8
  }
16
9
  },
17
- "conversion_chain": [{
18
- "dict": {
19
- "type": "group",
20
- "dicts": [{
21
- "type": "ocd2",
22
- "file": "cngov/TGPhrases.ocd2"
23
- }, {
24
- "type": "ocd2",
25
- "file": "cngov/TGCharacters_keep_simp.ocd2"
26
- }]
10
+ "conversion_chain": [
11
+ {
12
+ "dict": {
13
+ "type": "group",
14
+ "dicts": [
15
+ {
16
+ "type": "ocd2",
17
+ "file": "cngov/TGPhrases.ocd2"
18
+ },
19
+ {
20
+ "type": "ocd2",
21
+ "file": "cngov/TGCharacters_keep_simp.ocd2"
22
+ }
23
+ ]
24
+ }
27
25
  }
28
- }]
26
+ ]
29
27
  }
package/dist/data/config/t2hk.json CHANGED
@@ -1,16 +1,18 @@
1
1
  {
2
- "name": "Traditional Chinese to Traditional Chinese (Hong Kong variant)",
3
- "segmentation": {
4
- "type": "mmseg",
5
- "dict": {
6
- "type": "ocd2",
7
- "file": "HKVariants.ocd2"
2
+ "name": "Traditional Chinese (OpenCC Standard) to Traditional Chinese (Hong Kong variant)",
3
+ "normalization": [
4
+ { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
5
+ ],
6
+ "conversion_chain": [
7
+ {
8
+ "dict": {
9
+ "type": "group",
10
+ "match_policy": "short_circuit",
11
+ "dicts": [
12
+ { "type": "ocd2", "file": "HKVariantsPhrases.ocd2" },
13
+ { "type": "ocd2", "file": "HKVariants.ocd2" }
14
+ ]
15
+ }
8
16
  }
9
- },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "ocd2",
13
- "file": "HKVariants.ocd2"
14
- }
15
- }]
17
+ ]
16
18
  }
package/dist/data/config/t2jp.json CHANGED
@@ -1,16 +1,9 @@
1
1
  {
2
- "name": "Traditional Chinese Characters (Kyūjitai) to New Japanese Kanji (Shinjitai)",
3
- "segmentation": {
4
- "type": "mmseg",
5
- "dict": {
6
- "type": "ocd2",
7
- "file": "JPVariants.ocd2"
8
- }
9
- },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "ocd2",
13
- "file": "JPVariants.ocd2"
14
- }
15
- }]
2
+ "name": "Old Japanese Kanji (Kyūjitai) to New Japanese Kanji (Shinjitai)",
3
+ "normalization": [
4
+ { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
5
+ ],
6
+ "conversion_chain": [
7
+ { "dict": { "type": "ocd2", "file": "JPShinjitaiCharactersRev.ocd2" } }
8
+ ]
16
9
  }
package/dist/data/config/t2s.json CHANGED
@@ -1,22 +1,23 @@
1
1
  {
2
- "name": "Traditional Chinese to Simplified Chinese",
3
- "segmentation": {
4
- "type": "mmseg",
5
- "dict": {
6
- "type": "ocd2",
7
- "file": "TSPhrases.ocd2"
2
+ "name": "Traditional Chinese (OpenCC Standard) to Simplified Chinese",
3
+ "normalization": [
4
+ { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
5
+ ],
6
+ "conversion_chain": [
7
+ {
8
+ "dict": {
9
+ "type": "group",
10
+ "match_policy": "short_circuit",
11
+ "dicts": [
12
+ { "type": "ocd2", "file": "TSPhrases.ocd2" },
13
+ {
14
+ "type": "ocd2",
15
+ "file": "TSCharactersExt.ocd2",
16
+ "may_output_tofu": true
17
+ },
18
+ { "type": "ocd2", "file": "TSCharacters.ocd2" }
19
+ ]
20
+ }
8
21
  }
9
- },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "group",
13
- "dicts": [{
14
- "type": "ocd2",
15
- "file": "TSPhrases.ocd2"
16
- }, {
17
- "type": "ocd2",
18
- "file": "TSCharacters.ocd2"
19
- }]
20
- }
21
- }]
22
+ ]
22
23
  }
package/dist/data/config/t2s_cngov.json CHANGED
@@ -1,12 +1,5 @@
1
1
  {
2
2
  "name": "Traditional Chinese to Simplified Chinese",
3
- "author": "TerryTian-tech",
4
- "license": "Apache License 2.0",
5
- "source": "https://github.com/TerryTian-tech/OpenCC-Traditional-Chinese-characters-according-to-Chinese-government-standards",
6
- "contributors": ["TerryTian-tech", "Yi Jianpeng", "Hu Xinmei", "Duan Yatong"],
7
- "reference": "《通用规范汉字表》(2013)",
8
- "description": "Conservative conversion that preserves intentional simplified characters in mixed documents while standardizing traditional characters only.",
9
-
10
3
  "segmentation": {
11
4
  "type": "mmseg",
12
5
  "dict": {
@@ -14,16 +7,21 @@
14
7
  "file": "cngov/TSPhrases.ocd2"
15
8
  }
16
9
  },
17
- "conversion_chain": [{
18
- "dict": {
19
- "type": "group",
20
- "dicts": [{
21
- "type": "ocd2",
22
- "file": "cngov/TSPhrases.ocd2"
23
- }, {
24
- "type": "ocd2",
25
- "file": "cngov/TSCharacters.ocd2"
26
- }]
10
+ "conversion_chain": [
11
+ {
12
+ "dict": {
13
+ "type": "group",
14
+ "dicts": [
15
+ {
16
+ "type": "ocd2",
17
+ "file": "cngov/TSPhrases.ocd2"
18
+ },
19
+ {
20
+ "type": "ocd2",
21
+ "file": "cngov/TSCharacters.ocd2"
22
+ }
23
+ ]
24
+ }
27
25
  }
28
- }]
26
+ ]
29
27
  }
package/dist/data/config/t2tw.json CHANGED
@@ -1,16 +1,18 @@
1
1
  {
2
- "name": "Traditional Chinese to Traditional Chinese (Taiwan standard)",
3
- "segmentation": {
4
- "type": "mmseg",
5
- "dict": {
6
- "type": "ocd2",
7
- "file": "TWVariants.ocd2"
2
+ "name": "Traditional Chinese (OpenCC Standard) to Traditional Chinese (Taiwan Standard)",
3
+ "normalization": [
4
+ { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
5
+ ],
6
+ "conversion_chain": [
7
+ {
8
+ "dict": {
9
+ "type": "group",
10
+ "match_policy": "short_circuit",
11
+ "dicts": [
12
+ { "type": "ocd2", "file": "TWVariantsPhrases.ocd2" },
13
+ { "type": "ocd2", "file": "TWVariants.ocd2" }
14
+ ]
15
+ }
8
16
  }
9
- },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "ocd2",
13
- "file": "TWVariants.ocd2"
14
- }
15
- }]
17
+ ]
16
18
  }
package/dist/data/config/tw2s.json CHANGED
@@ -1,33 +1,37 @@
1
1
  {
2
- "name": "Traditional Chinese (Taiwan standard) to Simplified Chinese",
2
+ "name": "Traditional Chinese (Taiwan Standard) to Simplified Chinese",
3
+ "normalization": [
4
+ { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
5
+ ],
3
6
  "segmentation": {
4
7
  "type": "mmseg",
5
- "dict": {
6
- "type": "ocd2",
7
- "file": "TSPhrases.ocd2"
8
- }
8
+ "dict": { "type": "ocd2", "file": "TSPhrases.ocd2" }
9
9
  },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "group",
13
- "dicts": [{
14
- "type": "ocd2",
15
- "file": "TWVariantsRevPhrases.ocd2"
16
- }, {
17
- "type": "ocd2",
18
- "file": "TWVariantsRev.ocd2"
19
- }]
20
- }
21
- }, {
22
- "dict": {
23
- "type": "group",
24
- "dicts": [{
25
- "type": "ocd2",
26
- "file": "TSPhrases.ocd2"
27
- }, {
28
- "type": "ocd2",
29
- "file": "TSCharacters.ocd2"
30
- }]
10
+ "conversion_chain": [
11
+ {
12
+ "dict": {
13
+ "type": "group",
14
+ "match_policy": "short_circuit",
15
+ "dicts": [
16
+ { "type": "ocd2", "file": "TWVariantsRevPhrases.ocd2" },
17
+ { "type": "ocd2", "file": "TWVariantsRev.ocd2" }
18
+ ]
19
+ }
20
+ },
21
+ {
22
+ "dict": {
23
+ "type": "group",
24
+ "match_policy": "short_circuit",
25
+ "dicts": [
26
+ { "type": "ocd2", "file": "TSPhrases.ocd2" },
27
+ {
28
+ "type": "ocd2",
29
+ "file": "TSCharactersExt.ocd2",
30
+ "may_output_tofu": true
31
+ },
32
+ { "type": "ocd2", "file": "TSCharacters.ocd2" }
33
+ ]
34
+ }
31
35
  }
32
- }]
36
+ ]
33
37
  }
package/dist/data/config/tw2sp.json CHANGED
@@ -1,36 +1,38 @@
1
1
  {
2
- "name": "Traditional Chinese (Taiwan standard) to Simplified Chinese (with phrases)",
2
+ "name": "Traditional Chinese (Taiwan Standard) to Simplified Chinese (Mainland China Phrases)",
3
+ "normalization": [
4
+ { "dict": { "type": "ocd2", "file": "CJK_Compatibility_Ideographs.ocd2" } }
5
+ ],
3
6
  "segmentation": {
4
7
  "type": "mmseg",
5
- "dict": {
6
- "type": "ocd2",
7
- "file": "TSPhrases.ocd2"
8
- }
8
+ "dict": { "type": "ocd2", "file": "TSPhrases.ocd2" }
9
9
  },
10
- "conversion_chain": [{
11
- "dict": {
12
- "type": "group",
13
- "dicts": [{
14
- "type": "ocd2",
15
- "file": "TWPhrasesRev.ocd2"
16
- }, {
17
- "type": "ocd2",
18
- "file": "TWVariantsRevPhrases.ocd2"
19
- }, {
20
- "type": "ocd2",
21
- "file": "TWVariantsRev.ocd2"
22
- }]
23
- }
24
- }, {
25
- "dict": {
26
- "type": "group",
27
- "dicts": [{
28
- "type": "ocd2",
29
- "file": "TSPhrases.ocd2"
30
- }, {
31
- "type": "ocd2",
32
- "file": "TSCharacters.ocd2"
33
- }]
10
+ "conversion_chain": [
11
+ {
12
+ "dict": {
13
+ "type": "group",
14
+ "match_policy": "short_circuit",
15
+ "dicts": [
16
+ { "type": "ocd2", "file": "TWPhrasesRev.ocd2" },
17
+ { "type": "ocd2", "file": "TWVariantsRevPhrases.ocd2" },
18
+ { "type": "ocd2", "file": "TWVariantsRev.ocd2" }
19
+ ]
20
+ }
21
+ },
22
+ {
23
+ "dict": {
24
+ "type": "group",
25
+ "match_policy": "short_circuit",
26
+ "dicts": [
27
+ { "type": "ocd2", "file": "TSPhrases.ocd2" },
28
+ {
29
+ "type": "ocd2",
30
+ "file": "TSCharactersExt.ocd2",
31
+ "may_output_tofu": true
32
+ },
33
+ { "type": "ocd2", "file": "TSCharacters.ocd2" }
34
+ ]
35
+ }
34
36
  }
35
- }]
37
+ ]
36
38
  }