@kensio/pinyinjs 1.7.10 → 1.7.12

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 (60) hide show
  1. package/README.md +2 -0
  2. package/data/full.entries +118 -118
  3. package/data/full.freq +0 -0
  4. package/data/manifest.json +4 -4
  5. package/data/standard.entries +111 -111
  6. package/dist/decode/de-rule.d.ts +4 -4
  7. package/dist/decode/de-rule.d.ts.map +1 -1
  8. package/dist/decode/de-rule.js +6 -16
  9. package/dist/decode/de-rule.js.map +1 -1
  10. package/dist/decode/edge-context.d.ts +14 -6
  11. package/dist/decode/edge-context.d.ts.map +1 -1
  12. package/dist/decode/edge-context.js +25 -0
  13. package/dist/decode/edge-context.js.map +1 -1
  14. package/dist/decode/reading-rules.d.ts +2 -0
  15. package/dist/decode/reading-rules.d.ts.map +1 -1
  16. package/dist/decode/reading-rules.js +6 -0
  17. package/dist/decode/reading-rules.js.map +1 -1
  18. package/dist/decode/rules.d.ts +1 -1
  19. package/dist/decode/rules.d.ts.map +1 -1
  20. package/dist/decode/rules.js +1 -1
  21. package/dist/decode/rules.js.map +1 -1
  22. package/dist/decode/split-rule.d.ts +43 -0
  23. package/dist/decode/split-rule.d.ts.map +1 -0
  24. package/dist/decode/split-rule.js +174 -0
  25. package/dist/decode/split-rule.js.map +1 -0
  26. package/dist/decode/taxi-rule.d.ts +45 -0
  27. package/dist/decode/taxi-rule.d.ts.map +1 -0
  28. package/dist/decode/taxi-rule.js +117 -0
  29. package/dist/decode/taxi-rule.js.map +1 -0
  30. package/dist/dictionary/dictionary.d.ts +14 -0
  31. package/dist/dictionary/dictionary.d.ts.map +1 -1
  32. package/dist/dictionary/dictionary.js +17 -0
  33. package/dist/dictionary/dictionary.js.map +1 -1
  34. package/dist/dictionary/entry-invariants.d.ts.map +1 -1
  35. package/dist/dictionary/entry-invariants.js +28 -0
  36. package/dist/dictionary/entry-invariants.js.map +1 -1
  37. package/dist/dictionary/proper-noun.d.ts.map +1 -1
  38. package/dist/dictionary/proper-noun.js +27 -3
  39. package/dist/dictionary/proper-noun.js.map +1 -1
  40. package/dist/dictionary/variant-counts.d.ts +4 -0
  41. package/dist/dictionary/variant-counts.d.ts.map +1 -1
  42. package/dist/dictionary/variant-counts.js +4 -0
  43. package/dist/dictionary/variant-counts.js.map +1 -1
  44. package/dist/index.d.ts +3 -2
  45. package/dist/index.d.ts.map +1 -1
  46. package/dist/index.js +3 -2
  47. package/dist/index.js.map +1 -1
  48. package/dist/search/candidate-query.d.ts +14 -0
  49. package/dist/search/candidate-query.d.ts.map +1 -1
  50. package/dist/search/candidate-query.js +23 -2
  51. package/dist/search/candidate-query.js.map +1 -1
  52. package/dist/search/reverse-index-format.d.ts +8 -0
  53. package/dist/search/reverse-index-format.d.ts.map +1 -1
  54. package/dist/search/reverse-index-format.js +8 -0
  55. package/dist/search/reverse-index-format.js.map +1 -1
  56. package/dist/sources/cedict.d.ts +15 -0
  57. package/dist/sources/cedict.d.ts.map +1 -1
  58. package/dist/sources/cedict.js +21 -0
  59. package/dist/sources/cedict.js.map +1 -1
  60. package/package.json +1 -1
@@ -89,6 +89,27 @@ function isCapitalised(reading) {
89
89
  const first = reading.slice(0, 1);
90
90
  return first !== first.toLowerCase();
91
91
  }
92
+ /**
93
+ * A definition that only points at another headword.
94
+ */
95
+ const CROSS_REFERENCE = /^see(\s+also)?\s/u;
96
+ /**
97
+ * Whether an entry states a meaning of its own, or only points elsewhere.
98
+ *
99
+ * CC-CEDICT gives a district, county or city its own headword and cross-refers
100
+ * the bare name to it. 长寿 is `[Chang2 shou4] /see 長壽區|长寿区/` beside
101
+ * `[chang2 shou4] /longevity/`, and 长寿区 carries the place. The capital on
102
+ * the cross-reference belongs to the entry it points at, so a sense written
103
+ * this way says nothing about how the bare word is usually read. 4,088 entries
104
+ * are written entirely this way and 3,019 of those are capitalised.
105
+ *
106
+ * A sense with any definition of its own is stated, however many
107
+ * cross-references sit beside it. 青龙 glosses the Azure Dragon and then refers
108
+ * on to 青龙满族自治县, and the dragon is a proper noun whatever follows it.
109
+ */
110
+ export function isStated(entry) {
111
+ return entry.definitions.some((definition) => !CROSS_REFERENCE.test(definition));
112
+ }
92
113
  /**
93
114
  * Where CC-CEDICT's own capitalisation divides a proper noun into its parts.
94
115
  *
@@ -1 +1 @@
1
- {"version":3,"file":"cedict.js","sourceRoot":"","sources":["../../src/sources/cedict.ts"],"names":[],"mappings":"AAgEA;;GAEG;AACH,MAAM,UAAU,GAAG,+CAA+C,CAAC;AAEnE;;GAEG;AACH,MAAM,cAAc,GAAG,2BAA2B,CAAC;AAEnD;;;;;;;;;;GAUG;AACH,MAAM,eAAe,GAAG,mBAAmB,CAAC;AAE5C;;GAEG;AACH,SAAS,aAAa,CACpB,WAA8B;IAE9B,MAAM,MAAM,GAAG,WAAW,CAAC,MAAM,CAAC,CAAC,UAAU,EAAE,EAAE,CAC/C,cAAc,CAAC,IAAI,CAAC,UAAU,CAAC,CAChC,CAAC;IACF,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACxB,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,CAAC,CAAC,UAAU,EAAE,EAAE,CAAC,eAAe,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,EAAE,CAAC;QAClE,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,OAAO,WAAW,CAAC,SAAS,CAAC,CAAC,UAAU,EAAE,EAAE,CAC1C,cAAc,CAAC,IAAI,CAAC,UAAU,CAAC,CAChC,KAAK,CAAC;QACL,CAAC,CAAC,SAAS;QACX,CAAC,CAAC,OAAO,CAAC;AACd,CAAC;AAED;;GAEG;AACH,MAAM,eAAe,GAAG,UAAU,CAAC;AAEnC;;;;;;;;;GASG;AACH,MAAM,UAAU,WAAW,CAAC,IAAY;IACtC,MAAM,OAAO,GAAkB,EAAE,CAAC;IAElC,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QACpC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YACzB,SAAS;QACX,CAAC;QACD,MAAM,KAAK,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACpC,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;YACnB,SAAS;QACX,CAAC;QAED,MAAM,CAAC,EAAE,WAAW,GAAG,EAAE,EAAE,UAAU,GAAG,EAAE,EAAE,MAAM,GAAG,EAAE,EAAE,IAAI,GAAG,EAAE,CAAC,GAAG,KAAK,CAAC;QAC5E,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,KAAK,EAAE,CAAC,CAAC;QAC1E,IACE,QAAQ,CAAC,MAAM,KAAK,CAAC;YACrB,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAC7C,CAAC;YACD,SAAS;QACX,CAAC;QAED,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,KAAK,EAAE,CAAC,CAAC;QACxE,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACzC,MAAM,cAAc,GAAG,MAAM,EAAE,CAAC,CAAC,CAAC;YAChC,EAAE,KAAK,CAAC,MAAM,CAAC;aACd,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,KAAK,EAAE,CAAC,CAAC;QACvC,MAAM,WAAW,GAAG,aAAa,CAAC,WAAW,CAAC,CAAC;QAE/C,OAAO,CAAC,IAAI,CAAC;YACX,WAAW,EAAE,WAAW,CAAC,SAAS,CAAC,KAAK,CAAC;YACzC,UAAU,EAAE,UAAU,CAAC,SAAS,CAAC,KAAK,CAAC;YACvC,QAAQ;YACR,YAAY,EAAE,aAAa,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;YAC9C,GAAG,CAAC,cAAc,KAAK,SAAS;gBAC9B,cAAc,CAAC,MAAM,GAAG,CAAC;gBACzB,WAAW,KAAK,SAAS,IAAI,EAAE,cAAc,EAAE,WAAW,EAAE,CAAC;YAC/D,WAAW;SACZ,CAAC,CAAC;IACL,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;GAEG;AACH,SAAS,aAAa,CAAC,OAAe;IACpC,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;IAClC,OAAO,KAAK,KAAK,KAAK,CAAC,WAAW,EAAE,CAAC;AACvC,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH,MAAM,UAAU,gBAAgB,CAC9B,QAA2B;IAE3B,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,IAAI,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC;QAC7D,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,OAAO,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,KAAK,EAAE,EAAE,CACzC,KAAK,GAAG,CAAC,IAAI,aAAa,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CACnD,CAAC;AACJ,CAAC"}
1
+ {"version":3,"file":"cedict.js","sourceRoot":"","sources":["../../src/sources/cedict.ts"],"names":[],"mappings":"AAgEA;;GAEG;AACH,MAAM,UAAU,GAAG,+CAA+C,CAAC;AAEnE;;GAEG;AACH,MAAM,cAAc,GAAG,2BAA2B,CAAC;AAEnD;;;;;;;;;;GAUG;AACH,MAAM,eAAe,GAAG,mBAAmB,CAAC;AAE5C;;GAEG;AACH,SAAS,aAAa,CACpB,WAA8B;IAE9B,MAAM,MAAM,GAAG,WAAW,CAAC,MAAM,CAAC,CAAC,UAAU,EAAE,EAAE,CAC/C,cAAc,CAAC,IAAI,CAAC,UAAU,CAAC,CAChC,CAAC;IACF,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACxB,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,IAAI,MAAM,CAAC,IAAI,CAAC,CAAC,UAAU,EAAE,EAAE,CAAC,eAAe,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,EAAE,CAAC;QAClE,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,OAAO,WAAW,CAAC,SAAS,CAAC,CAAC,UAAU,EAAE,EAAE,CAC1C,cAAc,CAAC,IAAI,CAAC,UAAU,CAAC,CAChC,KAAK,CAAC;QACL,CAAC,CAAC,SAAS;QACX,CAAC,CAAC,OAAO,CAAC;AACd,CAAC;AAED;;GAEG;AACH,MAAM,eAAe,GAAG,UAAU,CAAC;AAEnC;;;;;;;;;GASG;AACH,MAAM,UAAU,WAAW,CAAC,IAAY;IACtC,MAAM,OAAO,GAAkB,EAAE,CAAC;IAElC,KAAK,MAAM,IAAI,IAAI,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QACpC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YACzB,SAAS;QACX,CAAC;QACD,MAAM,KAAK,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACpC,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;YACnB,SAAS;QACX,CAAC;QAED,MAAM,CAAC,EAAE,WAAW,GAAG,EAAE,EAAE,UAAU,GAAG,EAAE,EAAE,MAAM,GAAG,EAAE,EAAE,IAAI,GAAG,EAAE,CAAC,GAAG,KAAK,CAAC;QAC5E,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,KAAK,EAAE,CAAC,CAAC;QAC1E,IACE,QAAQ,CAAC,MAAM,KAAK,CAAC;YACrB,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,EAC7C,CAAC;YACD,SAAS;QACX,CAAC;QAED,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,KAAK,EAAE,CAAC,CAAC;QACxE,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QACzC,MAAM,cAAc,GAAG,MAAM,EAAE,CAAC,CAAC,CAAC;YAChC,EAAE,KAAK,CAAC,MAAM,CAAC;aACd,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,KAAK,EAAE,CAAC,CAAC;QACvC,MAAM,WAAW,GAAG,aAAa,CAAC,WAAW,CAAC,CAAC;QAE/C,OAAO,CAAC,IAAI,CAAC;YACX,WAAW,EAAE,WAAW,CAAC,SAAS,CAAC,KAAK,CAAC;YACzC,UAAU,EAAE,UAAU,CAAC,SAAS,CAAC,KAAK,CAAC;YACvC,QAAQ;YACR,YAAY,EAAE,aAAa,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;YAC9C,GAAG,CAAC,cAAc,KAAK,SAAS;gBAC9B,cAAc,CAAC,MAAM,GAAG,CAAC;gBACzB,WAAW,KAAK,SAAS,IAAI,EAAE,cAAc,EAAE,WAAW,EAAE,CAAC;YAC/D,WAAW;SACZ,CAAC,CAAC;IACL,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED;;GAEG;AACH,SAAS,aAAa,CAAC,OAAe;IACpC,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;IAClC,OAAO,KAAK,KAAK,KAAK,CAAC,WAAW,EAAE,CAAC;AACvC,CAAC;AAED;;GAEG;AACH,MAAM,eAAe,GAAG,mBAAmB,CAAC;AAE5C;;;;;;;;;;;;;GAaG;AACH,MAAM,UAAU,QAAQ,CAAC,KAAkB;IACzC,OAAO,KAAK,CAAC,WAAW,CAAC,IAAI,CAC3B,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC,eAAe,CAAC,IAAI,CAAC,UAAU,CAAC,CAClD,CAAC;AACJ,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH,MAAM,UAAU,gBAAgB,CAC9B,QAA2B;IAE3B,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,IAAI,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC;QAC7D,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,OAAO,QAAQ,CAAC,OAAO,CAAC,CAAC,OAAO,EAAE,KAAK,EAAE,EAAE,CACzC,KAAK,GAAG,CAAC,IAAI,aAAa,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CACnD,CAAC;AACJ,CAAC"}
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@kensio/pinyinjs",
3
- "version": "1.7.10",
3
+ "version": "1.7.12",
4
4
  "description": "Chinese hanzi to pinyin conversion",
5
5
  "repository": "https://github.com/KensioSoftware/pinyinjs",
6
6
  "homepage": "https://pinyinjs.dev",