@kensio/pinyinjs 1.7.6 → 1.7.7
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.
- package/data/full.entries +46 -46
- package/data/manifest.json +8 -8
- package/data/script.map +102 -0
- package/data/standard.entries +8 -8
- package/dist/decode/chang-complement.d.ts +19 -0
- package/dist/decode/chang-complement.d.ts.map +1 -0
- package/dist/decode/chang-complement.js +113 -0
- package/dist/decode/chang-complement.js.map +1 -0
- package/dist/decode/chang-context.d.ts +9 -7
- package/dist/decode/chang-context.d.ts.map +1 -1
- package/dist/decode/chang-context.js +36 -3
- package/dist/decode/chang-context.js.map +1 -1
- package/dist/decode/chang-rule.d.ts +25 -15
- package/dist/decode/chang-rule.d.ts.map +1 -1
- package/dist/decode/chang-rule.js +38 -19
- package/dist/decode/chang-rule.js.map +1 -1
- package/dist/decode/convert-pipeline.d.ts.map +1 -1
- package/dist/decode/convert-pipeline.js +3 -3
- package/dist/decode/convert-pipeline.js.map +1 -1
- package/dist/decode/de-rule.d.ts +20 -0
- package/dist/decode/de-rule.d.ts.map +1 -1
- package/dist/decode/de-rule.js +87 -1
- package/dist/decode/de-rule.js.map +1 -1
- package/dist/decode/decode.d.ts +12 -25
- package/dist/decode/decode.d.ts.map +1 -1
- package/dist/decode/decode.js +10 -47
- package/dist/decode/decode.js.map +1 -1
- package/dist/decode/decoders.d.ts +9 -4
- package/dist/decode/decoders.d.ts.map +1 -1
- package/dist/decode/decoders.js +7 -7
- package/dist/decode/decoders.js.map +1 -1
- package/dist/decode/edge-context.d.ts +19 -0
- package/dist/decode/edge-context.d.ts.map +1 -1
- package/dist/decode/edge-context.js +41 -0
- package/dist/decode/edge-context.js.map +1 -1
- package/dist/decode/lattice-decode.d.ts +28 -0
- package/dist/decode/lattice-decode.d.ts.map +1 -0
- package/dist/decode/lattice-decode.js +48 -0
- package/dist/decode/lattice-decode.js.map +1 -0
- package/dist/decode/lattice-slice.d.ts +22 -6
- package/dist/decode/lattice-slice.d.ts.map +1 -1
- package/dist/decode/lattice-slice.js +24 -18
- package/dist/decode/lattice-slice.js.map +1 -1
- package/dist/decode/numbers.d.ts +0 -8
- package/dist/decode/numbers.d.ts.map +1 -1
- package/dist/decode/numbers.js +0 -10
- package/dist/decode/numbers.js.map +1 -1
- package/dist/decode/reading-rules.d.ts +1 -1
- package/dist/decode/reading-rules.d.ts.map +1 -1
- package/dist/decode/reading-rules.js +3 -2
- package/dist/decode/reading-rules.js.map +1 -1
- package/dist/decode/rules.d.ts +1 -1
- package/dist/decode/rules.d.ts.map +1 -1
- package/dist/decode/rules.js +1 -1
- package/dist/decode/rules.js.map +1 -1
- package/dist/decode/run-context.d.ts +33 -0
- package/dist/decode/run-context.d.ts.map +1 -0
- package/dist/decode/run-context.js +47 -0
- package/dist/decode/run-context.js.map +1 -0
- package/dist/decode/run-lattice.d.ts +13 -10
- package/dist/decode/run-lattice.d.ts.map +1 -1
- package/dist/decode/run-lattice.js +15 -12
- package/dist/decode/run-lattice.js.map +1 -1
- package/dist/decode/script-region.d.ts +15 -0
- package/dist/decode/script-region.d.ts.map +1 -0
- package/dist/decode/script-region.js +61 -0
- package/dist/decode/script-region.js.map +1 -0
- package/dist/decode/script-types.d.ts +11 -2
- package/dist/decode/script-types.d.ts.map +1 -1
- package/dist/decode/script-types.js +2 -1
- package/dist/decode/script-types.js.map +1 -1
- package/dist/decode/script-words.d.ts +7 -5
- package/dist/decode/script-words.d.ts.map +1 -1
- package/dist/decode/script-words.js +18 -25
- package/dist/decode/script-words.js.map +1 -1
- package/dist/decode/script.d.ts.map +1 -1
- package/dist/decode/script.js +2 -1
- package/dist/decode/script.js.map +1 -1
- package/dist/dictionary/measure-tone.d.ts +36 -0
- package/dist/dictionary/measure-tone.d.ts.map +1 -0
- package/dist/dictionary/measure-tone.js +139 -0
- package/dist/dictionary/measure-tone.js.map +1 -0
- package/dist/dictionary/merge-types.d.ts +8 -3
- package/dist/dictionary/merge-types.d.ts.map +1 -1
- package/dist/dictionary/merge-types.js.map +1 -1
- package/dist/dictionary/merge.d.ts.map +1 -1
- package/dist/dictionary/merge.js +7 -1
- package/dist/dictionary/merge.js.map +1 -1
- package/dist/dictionary/overrides.d.ts +5 -0
- package/dist/dictionary/overrides.d.ts.map +1 -1
- package/dist/dictionary/overrides.js +5 -5
- package/dist/dictionary/overrides.js.map +1 -1
- package/dist/dictionary/script-tables.js +91 -13
- package/dist/dictionary/script-tables.js.map +1 -1
- package/dist/dictionary/word-readings.d.ts.map +1 -1
- package/dist/dictionary/word-readings.js +3 -0
- package/dist/dictionary/word-readings.js.map +1 -1
- package/dist/index.d.ts +1 -1
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +1 -1
- package/dist/index.js.map +1 -1
- package/dist/script/glyphs.d.ts +9 -8
- package/dist/script/glyphs.d.ts.map +1 -1
- package/dist/script/glyphs.js +21 -48
- package/dist/script/glyphs.js.map +1 -1
- package/dist/script/reading-splits.d.ts +41 -0
- package/dist/script/reading-splits.d.ts.map +1 -0
- package/dist/script/reading-splits.js +98 -0
- package/dist/script/reading-splits.js.map +1 -0
- package/package.json +1 -1
|
@@ -0,0 +1,139 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Settling the tone of 个, which no source settles for itself.
|
|
3
|
+
*
|
|
4
|
+
* Every source writes 个 both ways, and where one writes the 轻声 it is a
|
|
5
|
+
* choice made an entry at a time. CC-CEDICT has 一个 `ge5` beside 一个人 `ge4`,
|
|
6
|
+
* 那个 `ge5` beside 那个人 `ge4`, 上个 `ge5` beside 上个月 `ge4`, and 每个 `ge4`
|
|
7
|
+
* beside 每个人 `ge5`. large_pinyin wanders the same way over 半个 and 半个人,
|
|
8
|
+
* and over 这个 and 这些个. No reading of sense separates them, because there is
|
|
9
|
+
* no difference of sense to read: 那个人 is 那个 followed by 人.
|
|
10
|
+
*
|
|
11
|
+
* The sources do agree on the proportion. The full tone is the large majority in
|
|
12
|
+
* all three. 现代汉语频率词典 counts 个 as `gè` 11,693 times against `ge` 1,891
|
|
13
|
+
* (Unihan's `kHanyuPinlu`), large_pinyin writes 243 against 36, and CC-CEDICT
|
|
14
|
+
* 102 against 45. So the package writes the tone and names the exception.
|
|
15
|
+
*
|
|
16
|
+
* **A numeral in front of it means the 量词 is counting**, and a counting 个 is
|
|
17
|
+
* written `gè`: 一个, 两个, 十二个, 一百个, and 一个人 and 上一个 with them.
|
|
18
|
+
* This is what the gold corpus already asserts for every 个 it holds, and what
|
|
19
|
+
* the 一个 override used to state on its own.
|
|
20
|
+
*
|
|
21
|
+
* **The exception is the determiners.** 这个, 那个 and 哪个 are headwords in
|
|
22
|
+
* 现代汉语词典 read `zhège`, `nàge` and `nǎge`, and both sources write them 轻声
|
|
23
|
+
* wherever the pair stands on its own. 每个, 上个 and 下个 are the same
|
|
24
|
+
* determiner shape and the sources split on them by length: CC-CEDICT has 上个
|
|
25
|
+
* `ge5` beside 上个月 `ge4`, and 每个 `ge4` beside 每个人 `ge5`. The 轻声 is taken
|
|
26
|
+
* for all six, which is what 那个人, 每个人 and 上个月 are said with.
|
|
27
|
+
*
|
|
28
|
+
* Everything else keeps the reading its source gave it. 几个, 半个, 多个 and
|
|
29
|
+
* 单个 have neither a numeral nor a listed determiner in front of them, so their
|
|
30
|
+
* 轻声 stands. So does the colloquial 个 of 我勒个去 and 一口吃个胖子, which
|
|
31
|
+
* counts nothing, and the 北京话 今儿个, 明儿个 and 昨儿个, whose 儿 folds into
|
|
32
|
+
* the syllable before it and leaves the reading shorter than the key.
|
|
33
|
+
*
|
|
34
|
+
* Measured over the committed dictionary it retones 25 entries of the 279 that
|
|
35
|
+
* hold a 个. Over the 88,866 lines of Tatoeba and zh.wikipedia the reading
|
|
36
|
+
* rules were sized against it moves 339 conversions, and every one is a 个:
|
|
37
|
+
* 每个 106, 那个 63, 下个月 and 下个星期 62, 上个月 and 上个星期 60, and 35
|
|
38
|
+
* where 一个 gains its tone and the 一 sandhi that follows from it. Before the
|
|
39
|
+
* pass, 2,467 of the corpus's 5,397 个 sat after a character the package read
|
|
40
|
+
* both ways; after it, 204 do, and all of those are positions no key covers,
|
|
41
|
+
* where the decode falls back to the character's own `gè`.
|
|
42
|
+
*/
|
|
43
|
+
import { QUANTITY_CHARACTERS } from "../numerals/characters.js";
|
|
44
|
+
import { toCharacters } from "../script/characters.js";
|
|
45
|
+
import { NEUTRAL_TONE } from "../tone/tone.js";
|
|
46
|
+
/**
|
|
47
|
+
* The 量词 this settles, in both scripts.
|
|
48
|
+
*/
|
|
49
|
+
const MEASURE_CHARACTERS = new Set(["个", "個"]);
|
|
50
|
+
/**
|
|
51
|
+
* The tone a counting 个 carries.
|
|
52
|
+
*/
|
|
53
|
+
const COUNTING_TONE = 4;
|
|
54
|
+
/**
|
|
55
|
+
* The determiners that take 个 into a word of their own, where it is 轻声.
|
|
56
|
+
*
|
|
57
|
+
* Six characters and not a part of speech, because the tag cannot draw the
|
|
58
|
+
* line. jieba tags 这个, 那个 and 每个 `r` and tags 各个, 某个 and 整个 `r` as
|
|
59
|
+
* well, and those three are `gègè`, `mǒugè` and `zhěnggè` in both sources with
|
|
60
|
+
* nothing disagreeing. So this is a list of judgements, in the way
|
|
61
|
+
* {@link import("./neutral-senses.js").NEUTRAL_SENSE_WORDS} is, and the words
|
|
62
|
+
* it decides are the ones where a source writes the 轻声 on the determiner and
|
|
63
|
+
* the pair together.
|
|
64
|
+
*/
|
|
65
|
+
export const NEUTRAL_MEASURE_DETERMINERS = new Set([
|
|
66
|
+
"这",
|
|
67
|
+
"這",
|
|
68
|
+
"那",
|
|
69
|
+
"哪",
|
|
70
|
+
"每",
|
|
71
|
+
"上",
|
|
72
|
+
"下",
|
|
73
|
+
]);
|
|
74
|
+
/**
|
|
75
|
+
* Whether a syllable is the 量词 rather than 个's other reading.
|
|
76
|
+
*
|
|
77
|
+
* 独自个 is `dú zì gě`, and a `gě` retoned to `gè` would be a different word.
|
|
78
|
+
* Testing the syllable keeps it out without a list of the words it appears in.
|
|
79
|
+
*/
|
|
80
|
+
function isCountingSyllable(syllable) {
|
|
81
|
+
return (syllable.initial === "g" &&
|
|
82
|
+
syllable.final === "e" &&
|
|
83
|
+
(syllable.tone === COUNTING_TONE || syllable.tone === NEUTRAL_TONE));
|
|
84
|
+
}
|
|
85
|
+
/**
|
|
86
|
+
* The tone the 个 at a position takes, or undefined where nothing settles it.
|
|
87
|
+
*/
|
|
88
|
+
export function countingToneAt(characters, at) {
|
|
89
|
+
// Nothing stands in front of a 个 that starts the word, and nothing settles
|
|
90
|
+
// it there: 个人 is `gèrén` on its own account.
|
|
91
|
+
const before = characters[at - 1] ?? "";
|
|
92
|
+
if (NEUTRAL_MEASURE_DETERMINERS.has(before)) {
|
|
93
|
+
return NEUTRAL_TONE;
|
|
94
|
+
}
|
|
95
|
+
return QUANTITY_CHARACTERS.has(before) ? COUNTING_TONE : undefined;
|
|
96
|
+
}
|
|
97
|
+
/**
|
|
98
|
+
* Give every 个 the tone its position calls for.
|
|
99
|
+
*
|
|
100
|
+
* Runs over the finished entries, before the constituent repair, so that a
|
|
101
|
+
* phrase held to the words inside it is held to a settled reading. Only the
|
|
102
|
+
* 普通话 reading is touched. A zh-TW delta is a claim about how 國語 differs
|
|
103
|
+
* from what stands beside it, and none of the 279 entries holding a 个 has one.
|
|
104
|
+
*/
|
|
105
|
+
export function settleMeasureTones(entries) {
|
|
106
|
+
let settled = 0;
|
|
107
|
+
const settle = (entry) => {
|
|
108
|
+
const characters = toCharacters(entry.hans);
|
|
109
|
+
const reading = entry.readings.cn;
|
|
110
|
+
// 儿化 folds two characters into one syllable, so a reading shorter than
|
|
111
|
+
// the word says nothing about which character each syllable reads.
|
|
112
|
+
if (reading.length !== characters.length) {
|
|
113
|
+
return entry;
|
|
114
|
+
}
|
|
115
|
+
const corrected = [...reading];
|
|
116
|
+
let isMoved = false;
|
|
117
|
+
for (const [at, syllable] of reading.entries()) {
|
|
118
|
+
if (
|
|
119
|
+
/* c8 ignore next -- the reading and the characters are the same length */
|
|
120
|
+
!MEASURE_CHARACTERS.has(characters[at] ?? "") ||
|
|
121
|
+
!isCountingSyllable(syllable)) {
|
|
122
|
+
continue;
|
|
123
|
+
}
|
|
124
|
+
const tone = countingToneAt(characters, at);
|
|
125
|
+
if (tone === undefined || syllable.tone === tone) {
|
|
126
|
+
continue;
|
|
127
|
+
}
|
|
128
|
+
corrected[at] = { ...syllable, tone };
|
|
129
|
+
isMoved = true;
|
|
130
|
+
}
|
|
131
|
+
if (!isMoved) {
|
|
132
|
+
return entry;
|
|
133
|
+
}
|
|
134
|
+
settled++;
|
|
135
|
+
return { ...entry, readings: { ...entry.readings, cn: corrected } };
|
|
136
|
+
};
|
|
137
|
+
return { entries: entries.map((entry) => settle(entry)), settled };
|
|
138
|
+
}
|
|
139
|
+
//# sourceMappingURL=measure-tone.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"measure-tone.js","sourceRoot":"","sources":["../../src/dictionary/measure-tone.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAyCG;AACH,OAAO,EAAE,mBAAmB,EAAE,MAAM,2BAA2B,CAAC;AAChE,OAAO,EAAE,YAAY,EAAE,MAAM,yBAAyB,CAAC;AAEvD,OAAO,EAAE,YAAY,EAAa,MAAM,iBAAiB,CAAC;AAG1D;;GAEG;AACH,MAAM,kBAAkB,GAAwB,IAAI,GAAG,CAAC,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC;AAEpE;;GAEG;AACH,MAAM,aAAa,GAAG,CAAgB,CAAC;AAEvC;;;;;;;;;;GAUG;AACH,MAAM,CAAC,MAAM,2BAA2B,GAAwB,IAAI,GAAG,CAAC;IACtE,GAAG;IACH,GAAG;IACH,GAAG;IACH,GAAG;IACH,GAAG;IACH,GAAG;IACH,GAAG;CACJ,CAAC,CAAC;AAEH;;;;;GAKG;AACH,SAAS,kBAAkB,CAAC,QAAkB;IAC5C,OAAO,CACL,QAAQ,CAAC,OAAO,KAAK,GAAG;QACxB,QAAQ,CAAC,KAAK,KAAK,GAAG;QACtB,CAAC,QAAQ,CAAC,IAAI,KAAK,aAAa,IAAI,QAAQ,CAAC,IAAI,KAAK,YAAY,CAAC,CACpE,CAAC;AACJ,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,cAAc,CAC5B,UAA6B,EAC7B,EAAU;IAEV,2EAA2E;IAC3E,8CAA8C;IAC9C,MAAM,MAAM,GAAG,UAAU,CAAC,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;IACxC,IAAI,2BAA2B,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;QAC5C,OAAO,YAAY,CAAC;IACtB,CAAC;IACD,OAAO,mBAAmB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,SAAS,CAAC;AACrE,CAAC;AAWD;;;;;;;GAOG;AACH,MAAM,UAAU,kBAAkB,CAChC,OAAmC;IAEnC,IAAI,OAAO,GAAG,CAAC,CAAC;IAEhB,MAAM,MAAM,GAAG,CAAC,KAAsB,EAAmB,EAAE;QACzD,MAAM,UAAU,GAAG,YAAY,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAC5C,MAAM,OAAO,GAAG,KAAK,CAAC,QAAQ,CAAC,EAAE,CAAC;QAClC,uEAAuE;QACvE,mEAAmE;QACnE,IAAI,OAAO,CAAC,MAAM,KAAK,UAAU,CAAC,MAAM,EAAE,CAAC;YACzC,OAAO,KAAK,CAAC;QACf,CAAC;QAED,MAAM,SAAS,GAAG,CAAC,GAAG,OAAO,CAAC,CAAC;QAC/B,IAAI,OAAO,GAAG,KAAK,CAAC;QACpB,KAAK,MAAM,CAAC,EAAE,EAAE,QAAQ,CAAC,IAAI,OAAO,CAAC,OAAO,EAAE,EAAE,CAAC;YAC/C;YACE,0EAA0E;YAC1E,CAAC,kBAAkB,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC;gBAC7C,CAAC,kBAAkB,CAAC,QAAQ,CAAC,EAC7B,CAAC;gBACD,SAAS;YACX,CAAC;YACD,MAAM,IAAI,GAAG,cAAc,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;YAC5C,IAAI,IAAI,KAAK,SAAS,IAAI,QAAQ,CAAC,IAAI,KAAK,IAAI,EAAE,CAAC;gBACjD,SAAS;YACX,CAAC;YACD,SAAS,CAAC,EAAE,CAAC,GAAG,EAAE,GAAG,QAAQ,EAAE,IAAI,EAAE,CAAC;YACtC,OAAO,GAAG,IAAI,CAAC;QACjB,CAAC;QAED,IAAI,CAAC,OAAO,EAAE,CAAC;YACb,OAAO,KAAK,CAAC;QACf,CAAC;QACD,OAAO,EAAE,CAAC;QACV,OAAO,EAAE,GAAG,KAAK,EAAE,QAAQ,EAAE,EAAE,GAAG,KAAK,CAAC,QAAQ,EAAE,EAAE,EAAE,SAAS,EAAE,EAAE,CAAC;IACtE,CAAC,CAAC;IAEF,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,OAAO,EAAE,CAAC;AACrE,CAAC"}
|
|
@@ -36,6 +36,11 @@ export interface MergeStats {
|
|
|
36
36
|
readonly reducedNeutrals: number;
|
|
37
37
|
/** Words whose trailing 儿 was folded into the syllable before it. */
|
|
38
38
|
readonly erhuaRepairs: number;
|
|
39
|
+
/**
|
|
40
|
+
* Entries whose 个 was retoned by its position — see
|
|
41
|
+
* {@link import("./measure-tone.js").settleMeasureTones}.
|
|
42
|
+
*/
|
|
43
|
+
readonly settledMeasureTones: number;
|
|
39
44
|
/** Words whose 繁體 form was derived rather than taken from CC-CEDICT. */
|
|
40
45
|
readonly derivedTraditional: number;
|
|
41
46
|
/** Entries with a 繁體 form differing from their 简体 one. */
|
|
@@ -90,9 +95,9 @@ export interface WordSources {
|
|
|
90
95
|
* What one word contributed to the build's counts.
|
|
91
96
|
*
|
|
92
97
|
* The per-word view of {@link MergeStats}, minus the counts no single word can
|
|
93
|
-
* move: `reducedNeutrals`, `repairedConstituents` and
|
|
94
|
-
* are settled by passes over the whole dictionary, and
|
|
95
|
-
* the caller.
|
|
98
|
+
* move: `reducedNeutrals`, `settledMeasureTones`, `repairedConstituents` and
|
|
99
|
+
* `composedTaiwanReadings` are settled by passes over the whole dictionary, and
|
|
100
|
+
* `rejected` is counted by the caller.
|
|
96
101
|
*/
|
|
97
102
|
export interface WordTally {
|
|
98
103
|
readonly neutralToneCorrections: number;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"merge-types.d.ts","sourceRoot":"","sources":["../../src/dictionary/merge-types.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AACH,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AACxD,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,qBAAqB,CAAC;AACtD,OAAO,KAAK,EAAE,cAAc,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AAC3E,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AACxD,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,YAAY,CAAC;AAClD,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AAE/D;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,QAAQ,CAAC,cAAc,EAAE,WAAW,CAAC,MAAM,EAAE,cAAc,CAAC,CAAC;IAC7D,QAAQ,CAAC,cAAc,EAAE,cAAc,CAAC;IACxC,QAAQ,CAAC,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,QAAQ,CAAC,MAAM,EAAE,SAAS,WAAW,EAAE,CAAC;IACxC,QAAQ,CAAC,KAAK,EAAE,WAAW,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;CACjD;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC;IAC5B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,iEAAiE;IACjE,QAAQ,CAAC,sBAAsB,EAAE,MAAM,CAAC;IACxC;;;OAGG;IACH,QAAQ,CAAC,eAAe,EAAE,MAAM,CAAC;IACjC,qEAAqE;IACrE,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAC;IAC9B,wEAAwE;IACxE,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,0DAA0D;IAC1D,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,4DAA4D;IAC5D,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC;;;OAGG;IACH,QAAQ,CAAC,oBAAoB,EAAE,MAAM,CAAC;IACtC,8DAA8D;IAC9D,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,sEAAsE;IACtE,QAAQ,CAAC,sBAAsB,EAAE,MAAM,CAAC;IACxC;;OAEG;IACH,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC,8DAA8D;IAC9D,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,6DAA6D;IAC7D,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;CAC3B;AAED;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,yCAAyC;IACzC,QAAQ,CAAC,OAAO,EAAE,SAAS,eAAe,EAAE,CAAC;IAC7C,mEAAmE;IACnE,QAAQ,CAAC,QAAQ,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IAC1D,QAAQ,CAAC,KAAK,EAAE,UAAU,CAAC;CAC5B;AAED;;;;;;GAMG;AACH,MAAM,WAAW,WAAW;IAC1B,QAAQ,CAAC,YAAY,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,WAAW,EAAE,CAAC,CAAC;IACnE,QAAQ,CAAC,YAAY,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,WAAW,EAAE,CAAC,CAAC;IACnE,QAAQ,CAAC,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,QAAQ,CAAC,KAAK,EAAE,WAAW,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;IAChD,QAAQ,CAAC,cAAc,EAAE,WAAW,CAAC,MAAM,EAAE,cAAc,CAAC,CAAC;IAC7D,QAAQ,CAAC,WAAW,EAAE,gBAAgB,CAAC;IACvC,QAAQ,CAAC,QAAQ,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,QAAQ,EAAE,CAAC,CAAC;CAC7D;AAED;;;;;;;GAOG;AACH,MAAM,WAAW,SAAS;IACxB,QAAQ,CAAC,sBAAsB,EAAE,MAAM,CAAC;IACxC,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAC;IAC9B,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC;IAC5B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;CAC9B;AAED;;GAEG;AACH,eAAO,MAAM,QAAQ,EAAE,SAYtB,CAAC;AAEF;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,QAAQ,CAAC,KAAK,EAAE,eAAe,GAAG,SAAS,CAAC;IAC5C,8EAA8E;IAC9E,QAAQ,CAAC,QAAQ,EAAE,SAAS,MAAM,EAAE,GAAG,SAAS,CAAC;IACjD,QAAQ,CAAC,KAAK,EAAE,SAAS,CAAC;CAC3B;AAED;;GAEG;AACH,wBAAgB,QAAQ,CAAC,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,SAAS,GAAG,SAAS,CAetE"}
|
|
1
|
+
{"version":3,"file":"merge-types.d.ts","sourceRoot":"","sources":["../../src/dictionary/merge-types.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AACH,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AACxD,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,qBAAqB,CAAC;AACtD,OAAO,KAAK,EAAE,cAAc,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AAC3E,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AACxD,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,YAAY,CAAC;AAClD,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AAE/D;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,QAAQ,CAAC,cAAc,EAAE,WAAW,CAAC,MAAM,EAAE,cAAc,CAAC,CAAC;IAC7D,QAAQ,CAAC,cAAc,EAAE,cAAc,CAAC;IACxC,QAAQ,CAAC,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,QAAQ,CAAC,MAAM,EAAE,SAAS,WAAW,EAAE,CAAC;IACxC,QAAQ,CAAC,KAAK,EAAE,WAAW,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;CACjD;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC;IAC5B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,iEAAiE;IACjE,QAAQ,CAAC,sBAAsB,EAAE,MAAM,CAAC;IACxC;;;OAGG;IACH,QAAQ,CAAC,eAAe,EAAE,MAAM,CAAC;IACjC,qEAAqE;IACrE,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAC;IAC9B;;;OAGG;IACH,QAAQ,CAAC,mBAAmB,EAAE,MAAM,CAAC;IACrC,wEAAwE;IACxE,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,0DAA0D;IAC1D,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,4DAA4D;IAC5D,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC;;;OAGG;IACH,QAAQ,CAAC,oBAAoB,EAAE,MAAM,CAAC;IACtC,8DAA8D;IAC9D,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,sEAAsE;IACtE,QAAQ,CAAC,sBAAsB,EAAE,MAAM,CAAC;IACxC;;OAEG;IACH,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC,8DAA8D;IAC9D,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,6DAA6D;IAC7D,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;CAC3B;AAED;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,yCAAyC;IACzC,QAAQ,CAAC,OAAO,EAAE,SAAS,eAAe,EAAE,CAAC;IAC7C,mEAAmE;IACnE,QAAQ,CAAC,QAAQ,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IAC1D,QAAQ,CAAC,KAAK,EAAE,UAAU,CAAC;CAC5B;AAED;;;;;;GAMG;AACH,MAAM,WAAW,WAAW;IAC1B,QAAQ,CAAC,YAAY,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,WAAW,EAAE,CAAC,CAAC;IACnE,QAAQ,CAAC,YAAY,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,WAAW,EAAE,CAAC,CAAC;IACnE,QAAQ,CAAC,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC;IACxD,QAAQ,CAAC,KAAK,EAAE,WAAW,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;IAChD,QAAQ,CAAC,cAAc,EAAE,WAAW,CAAC,MAAM,EAAE,cAAc,CAAC,CAAC;IAC7D,QAAQ,CAAC,WAAW,EAAE,gBAAgB,CAAC;IACvC,QAAQ,CAAC,QAAQ,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,QAAQ,EAAE,CAAC,CAAC;CAC7D;AAED;;;;;;;GAOG;AACH,MAAM,WAAW,SAAS;IACxB,QAAQ,CAAC,sBAAsB,EAAE,MAAM,CAAC;IACxC,QAAQ,CAAC,YAAY,EAAE,MAAM,CAAC;IAC9B,QAAQ,CAAC,kBAAkB,EAAE,MAAM,CAAC;IACpC,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAC;IAChC,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC;IAC5B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;CAC9B;AAED;;GAEG;AACH,eAAO,MAAM,QAAQ,EAAE,SAYtB,CAAC;AAEF;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,QAAQ,CAAC,KAAK,EAAE,eAAe,GAAG,SAAS,CAAC;IAC5C,8EAA8E;IAC9E,QAAQ,CAAC,QAAQ,EAAE,SAAS,MAAM,EAAE,GAAG,SAAS,CAAC;IACjD,QAAQ,CAAC,KAAK,EAAE,SAAS,CAAC;CAC3B;AAED;;GAEG;AACH,wBAAgB,QAAQ,CAAC,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,SAAS,GAAG,SAAS,CAetE"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"merge-types.js","sourceRoot":"","sources":["../../src/dictionary/merge-types.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"merge-types.js","sourceRoot":"","sources":["../../src/dictionary/merge-types.ts"],"names":[],"mappings":"AAwHA;;GAEG;AACH,MAAM,CAAC,MAAM,QAAQ,GAAc;IACjC,sBAAsB,EAAE,CAAC;IACzB,YAAY,EAAE,CAAC;IACf,kBAAkB,EAAE,CAAC;IACrB,WAAW,EAAE,CAAC;IACd,gBAAgB,EAAE,CAAC;IACnB,cAAc,EAAE,CAAC;IACjB,gBAAgB,EAAE,CAAC;IACnB,cAAc,EAAE,CAAC;IACjB,UAAU,EAAE,CAAC;IACb,WAAW,EAAE,CAAC;IACd,WAAW,EAAE,CAAC;CACf,CAAC;AAYF;;GAEG;AACH,MAAM,UAAU,QAAQ,CAAC,KAAgB,EAAE,KAAgB;IACzD,OAAO;QACL,sBAAsB,EACpB,KAAK,CAAC,sBAAsB,GAAG,KAAK,CAAC,sBAAsB;QAC7D,YAAY,EAAE,KAAK,CAAC,YAAY,GAAG,KAAK,CAAC,YAAY;QACrD,kBAAkB,EAAE,KAAK,CAAC,kBAAkB,GAAG,KAAK,CAAC,kBAAkB;QACvE,WAAW,EAAE,KAAK,CAAC,WAAW,GAAG,KAAK,CAAC,WAAW;QAClD,gBAAgB,EAAE,KAAK,CAAC,gBAAgB,GAAG,KAAK,CAAC,gBAAgB;QACjE,cAAc,EAAE,KAAK,CAAC,cAAc,GAAG,KAAK,CAAC,cAAc;QAC3D,gBAAgB,EAAE,KAAK,CAAC,gBAAgB,GAAG,KAAK,CAAC,gBAAgB;QACjE,cAAc,EAAE,KAAK,CAAC,cAAc,GAAG,KAAK,CAAC,cAAc;QAC3D,UAAU,EAAE,KAAK,CAAC,UAAU,GAAG,KAAK,CAAC,UAAU;QAC/C,WAAW,EAAE,KAAK,CAAC,WAAW,GAAG,KAAK,CAAC,WAAW;QAClD,WAAW,EAAE,KAAK,CAAC,WAAW,GAAG,KAAK,CAAC,WAAW;KACnD,CAAC;AACJ,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"merge.d.ts","sourceRoot":"","sources":["../../src/dictionary/merge.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"merge.d.ts","sourceRoot":"","sources":["../../src/dictionary/merge.ts"],"names":[],"mappings":"AAaA,OAAO,KAAK,EAAE,WAAW,EAAE,YAAY,EAAe,MAAM,kBAAkB,CAAC;AAE/E,YAAY,EAAE,WAAW,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAE9E;;;;;;;;GAQG;AACH,wBAAgB,YAAY,CAAC,OAAO,EAAE,YAAY,GAAG,WAAW,CA6D/D"}
|
package/dist/dictionary/merge.js
CHANGED
|
@@ -9,6 +9,7 @@ import { composeLocaleDeltas } from "./locale.js";
|
|
|
9
9
|
import { indexCedict, senseLookup } from "./cedict-senses.js";
|
|
10
10
|
import { buildCharacterDefaults } from "./character-defaults.js";
|
|
11
11
|
import { repairConstituentReadings } from "./constituent-repair.js";
|
|
12
|
+
import { settleMeasureTones } from "./measure-tone.js";
|
|
12
13
|
import { mergeWords, wordList } from "./merge-walk.js";
|
|
13
14
|
/**
|
|
14
15
|
* Build the merged dictionary from the four parsed sources.
|
|
@@ -38,11 +39,15 @@ export function mergeSources(sources) {
|
|
|
38
39
|
defaults,
|
|
39
40
|
};
|
|
40
41
|
const { entries, rejected, counts } = mergeWords(wordList(phrase, defaults, cedictByWord, cedictByHant), wordSources);
|
|
42
|
+
// ── 个 given one tone per position ─────────────────────────
|
|
43
|
+
// Before the repair below, which reads a phrase's constituents off these same
|
|
44
|
+
// entries: settling first is what lets 那个人 be held to a settled 那个.
|
|
45
|
+
const measured = settleMeasureTones(entries);
|
|
41
46
|
// ── Phrase entries held to the words inside them ───────────
|
|
42
47
|
// Before the locale pass, which asks whether a compound reads a constituent
|
|
43
48
|
// the way that constituent's own entry reads it. A phrase entry repaired here
|
|
44
49
|
// answers yes where it used to answer no.
|
|
45
|
-
const held = repairConstituentReadings(entries, senseLookup(cedictByWord, cedictByHant));
|
|
50
|
+
const held = repairConstituentReadings(measured.entries, senseLookup(cedictByWord, cedictByHant));
|
|
46
51
|
// ── zh-TW deltas the sources marked only on a constituent ──
|
|
47
52
|
// Last, because it segments each compound against the finished entries: the
|
|
48
53
|
// readings, both scripts' keys and the frequencies all have to be settled
|
|
@@ -54,6 +59,7 @@ export function mergeSources(sources) {
|
|
|
54
59
|
stats: {
|
|
55
60
|
...counts,
|
|
56
61
|
reducedNeutrals,
|
|
62
|
+
settledMeasureTones: measured.settled,
|
|
57
63
|
repairedConstituents: held.repaired,
|
|
58
64
|
composedTaiwanReadings: localised.composed,
|
|
59
65
|
rejected: rejected.size,
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"merge.js","sourceRoot":"","sources":["../../src/dictionary/merge.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AACH,OAAO,EAAE,mBAAmB,EAAE,MAAM,aAAa,CAAC;AAClD,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAC9D,OAAO,EAAE,sBAAsB,EAAE,MAAM,yBAAyB,CAAC;AACjE,OAAO,EAAE,yBAAyB,EAAE,MAAM,yBAAyB,CAAC;AACpE,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,iBAAiB,CAAC;AAKvD;;;;;;;;GAQG;AACH,MAAM,UAAU,YAAY,CAAC,OAAqB;IAChD,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC;IACnC,MAAM,YAAY,GAAG,WAAW,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;IACtE,6EAA6E;IAC7E,2EAA2E;IAC3E,0EAA0E;IAC1E,kCAAkC;IAClC,MAAM,YAAY,GAAG,WAAW,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;IAEvE,MAAM,EAAE,WAAW,EAAE,QAAQ,EAAE,eAAe,EAAE,GAAG,sBAAsB,CACvE,OAAO,EACP,YAAY,EACZ,YAAY,CACb,CAAC;IAEF,MAAM,WAAW,GAAgB;QAC/B,YAAY;QACZ,YAAY;QACZ,MAAM;QACN,KAAK,EAAE,OAAO,CAAC,KAAK;QACpB,cAAc,EAAE,OAAO,CAAC,cAAc;QACtC,WAAW;QACX,QAAQ;KACT,CAAC;IACF,MAAM,EAAE,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,GAAG,UAAU,CAC9C,QAAQ,CAAC,MAAM,EAAE,QAAQ,EAAE,YAAY,EAAE,YAAY,CAAC,EACtD,WAAW,CACZ,CAAC;IAEF,8DAA8D;IAC9D,4EAA4E;IAC5E,8EAA8E;IAC9E,0CAA0C;IAC1C,MAAM,IAAI,GAAG,yBAAyB,CACpC,OAAO,
|
|
1
|
+
{"version":3,"file":"merge.js","sourceRoot":"","sources":["../../src/dictionary/merge.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AACH,OAAO,EAAE,mBAAmB,EAAE,MAAM,aAAa,CAAC;AAClD,OAAO,EAAE,WAAW,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAC9D,OAAO,EAAE,sBAAsB,EAAE,MAAM,yBAAyB,CAAC;AACjE,OAAO,EAAE,yBAAyB,EAAE,MAAM,yBAAyB,CAAC;AACpE,OAAO,EAAE,kBAAkB,EAAE,MAAM,mBAAmB,CAAC;AACvD,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,iBAAiB,CAAC;AAKvD;;;;;;;;GAQG;AACH,MAAM,UAAU,YAAY,CAAC,OAAqB;IAChD,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC;IACnC,MAAM,YAAY,GAAG,WAAW,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC;IACtE,6EAA6E;IAC7E,2EAA2E;IAC3E,0EAA0E;IAC1E,kCAAkC;IAClC,MAAM,YAAY,GAAG,WAAW,CAAC,MAAM,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;IAEvE,MAAM,EAAE,WAAW,EAAE,QAAQ,EAAE,eAAe,EAAE,GAAG,sBAAsB,CACvE,OAAO,EACP,YAAY,EACZ,YAAY,CACb,CAAC;IAEF,MAAM,WAAW,GAAgB;QAC/B,YAAY;QACZ,YAAY;QACZ,MAAM;QACN,KAAK,EAAE,OAAO,CAAC,KAAK;QACpB,cAAc,EAAE,OAAO,CAAC,cAAc;QACtC,WAAW;QACX,QAAQ;KACT,CAAC;IACF,MAAM,EAAE,OAAO,EAAE,QAAQ,EAAE,MAAM,EAAE,GAAG,UAAU,CAC9C,QAAQ,CAAC,MAAM,EAAE,QAAQ,EAAE,YAAY,EAAE,YAAY,CAAC,EACtD,WAAW,CACZ,CAAC;IAEF,6DAA6D;IAC7D,8EAA8E;IAC9E,oEAAoE;IACpE,MAAM,QAAQ,GAAG,kBAAkB,CAAC,OAAO,CAAC,CAAC;IAE7C,8DAA8D;IAC9D,4EAA4E;IAC5E,8EAA8E;IAC9E,0CAA0C;IAC1C,MAAM,IAAI,GAAG,yBAAyB,CACpC,QAAQ,CAAC,OAAO,EAChB,WAAW,CAAC,YAAY,EAAE,YAAY,CAAC,CACxC,CAAC;IAEF,8DAA8D;IAC9D,4EAA4E;IAC5E,0EAA0E;IAC1E,qDAAqD;IACrD,MAAM,SAAS,GAAG,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IAEpD,OAAO;QACL,OAAO,EAAE,SAAS,CAAC,OAAO;QAC1B,QAAQ;QACR,KAAK,EAAE;YACL,GAAG,MAAM;YACT,eAAe;YACf,mBAAmB,EAAE,QAAQ,CAAC,OAAO;YACrC,oBAAoB,EAAE,IAAI,CAAC,QAAQ;YACnC,sBAAsB,EAAE,SAAS,CAAC,QAAQ;YAC1C,QAAQ,EAAE,QAAQ,CAAC,IAAI;SACxB;KACF,CAAC;AACJ,CAAC"}
|
|
@@ -29,6 +29,11 @@ export interface ReadingOverride {
|
|
|
29
29
|
* {@link import("./neutral-senses.js").NEUTRAL_SENSE_WORDS} instead — that
|
|
30
30
|
* table names the word and lets CC-CEDICT supply the reading, so nothing is
|
|
31
31
|
* typed by hand that a source already holds.
|
|
32
|
+
*
|
|
33
|
+
* 一个 was listed here for `yī gè` until the whole of 个 was settled by
|
|
34
|
+
* position. One word taken out of a disagreement the sources have about 262 of
|
|
35
|
+
* them is a rule missing rather than an override earned, and the rule is
|
|
36
|
+
* {@link import("./measure-tone.js").settleMeasureTones}.
|
|
32
37
|
*/
|
|
33
38
|
export declare const READING_OVERRIDES: readonly ReadingOverride[];
|
|
34
39
|
/**
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"overrides.d.ts","sourceRoot":"","sources":["../../src/dictionary/overrides.ts"],"names":[],"mappings":"AAAA,OAAO,EAAgB,KAAK,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AAGtE;;GAEG;AACH,MAAM,WAAW,eAAe;IAC9B,uBAAuB;IACvB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,4CAA4C;IAC5C,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,0CAA0C;IAC1C,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;CACzB;AAED
|
|
1
|
+
{"version":3,"file":"overrides.d.ts","sourceRoot":"","sources":["../../src/dictionary/overrides.ts"],"names":[],"mappings":"AAAA,OAAO,EAAgB,KAAK,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AAGtE;;GAEG;AACH,MAAM,WAAW,eAAe;IAC9B,uBAAuB;IACvB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,4CAA4C;IAC5C,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,0CAA0C;IAC1C,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC;CACzB;AAED;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AACH,eAAO,MAAM,iBAAiB,EAAE,SAAS,eAAe,EAOvD,CAAC;AAEF;;;;;;;GAOG;AACH,wBAAgB,mBAAmB,CACjC,QAAQ,EAAE,eAAe,GACxB,SAAS,QAAQ,EAAE,CAqBrB;AAED;;GAEG;AACH,eAAO,MAAM,iBAAiB,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,QAAQ,EAAE,CAMpE,CAAC"}
|
|
@@ -19,6 +19,11 @@ import { NEUTRAL_TONE } from "../tone/tone.js";
|
|
|
19
19
|
* {@link import("./neutral-senses.js").NEUTRAL_SENSE_WORDS} instead — that
|
|
20
20
|
* table names the word and lets CC-CEDICT supply the reading, so nothing is
|
|
21
21
|
* typed by hand that a source already holds.
|
|
22
|
+
*
|
|
23
|
+
* 一个 was listed here for `yī gè` until the whole of 个 was settled by
|
|
24
|
+
* position. One word taken out of a disagreement the sources have about 262 of
|
|
25
|
+
* them is a rule missing rather than an override earned, and the rule is
|
|
26
|
+
* {@link import("./measure-tone.js").settleMeasureTones}.
|
|
22
27
|
*/
|
|
23
28
|
export const READING_OVERRIDES = [
|
|
24
29
|
{
|
|
@@ -26,11 +31,6 @@ export const READING_OVERRIDES = [
|
|
|
26
31
|
reading: "dài fu",
|
|
27
32
|
reason: "Both sources give dà fū, the ancient court title. The everyday sense, doctor, is dàifu and is overwhelmingly the more common.",
|
|
28
33
|
},
|
|
29
|
-
{
|
|
30
|
-
word: "一个",
|
|
31
|
-
reading: "yī gè",
|
|
32
|
-
reason: "Not a source defect but a real disagreement: CC-CEDICT has yi1 ge5 and large_pinyin has yí gè, and both are attested speech. Step 7 prefers CC-CEDICT on neutral tones, which is right for the other 771 words it settles and wrong here — 个 counting is written with its tone. Stored underlyingly, so the runtime sandhi pass writes yí gè.",
|
|
33
|
-
},
|
|
34
34
|
];
|
|
35
35
|
/**
|
|
36
36
|
* Read an override's reading into syllables, throwing if it is malformed.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"overrides.js","sourceRoot":"","sources":["../../src/dictionary/overrides.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAiB,MAAM,yBAAyB,CAAC;AACtE,OAAO,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AAc/C
|
|
1
|
+
{"version":3,"file":"overrides.js","sourceRoot":"","sources":["../../src/dictionary/overrides.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAiB,MAAM,yBAAyB,CAAC;AACtE,OAAO,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AAc/C;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAA+B;IAC3D;QACE,IAAI,EAAE,IAAI;QACV,OAAO,EAAE,QAAQ;QACjB,MAAM,EACJ,+HAA+H;KAClI;CACF,CAAC;AAEF;;;;;;;GAOG;AACH,MAAM,UAAU,mBAAmB,CACjC,QAAyB;IAEzB,MAAM,SAAS,GAAG,QAAQ,CAAC,OAAO;SAC/B,KAAK,CAAC,MAAM,CAAC;SACb,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,KAAK,EAAE,CAAC;SAC/B,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC;IACvC,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC3B,MAAM,IAAI,KAAK,CAAC,gBAAgB,QAAQ,CAAC,IAAI,iBAAiB,CAAC,CAAC;IAClE,CAAC;IAED,MAAM,IAAI,GAAe,EAAE,CAAC;IAC5B,KAAK,MAAM,QAAQ,IAAI,SAAS,EAAE,CAAC;QACjC,IAAI,QAAQ,KAAK,SAAS,EAAE,CAAC;YAC3B,MAAM,IAAI,KAAK,CACb,gBAAgB,QAAQ,CAAC,IAAI,sBAAsB,QAAQ,CAAC,OAAO,EAAE,CACtE,CAAC;QACJ,CAAC;QACD,2EAA2E;QAC3E,oEAAoE;QACpE,IAAI,CAAC,IAAI,CAAC,EAAE,GAAG,QAAQ,EAAE,IAAI,EAAE,QAAQ,CAAC,IAAI,IAAI,YAAY,EAAE,CAAC,CAAC;IAClE,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAC5B,IAAI,GAAG,CACL,iBAAiB,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC;IAClC,QAAQ,CAAC,IAAI;IACb,mBAAmB,CAAC,QAAQ,CAAC;CAC9B,CAAC,CACH,CAAC"}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { toCharacters } from "../script/characters.js";
|
|
2
|
-
import { toCanonicalGlyphs } from "../script/glyphs.js";
|
|
2
|
+
import { CANONICAL_FORMS, toCanonicalGlyphs } from "../script/glyphs.js";
|
|
3
3
|
import { convertCharacters } from "../script/conversion.js";
|
|
4
4
|
import { alignedReadings, pairingsOf, tableOf, tally, } from "./script-pairings.js";
|
|
5
5
|
/**
|
|
@@ -80,10 +80,78 @@ export function buildScriptTables(entries) {
|
|
|
80
80
|
* 鹫峯寺 — and taking those at face value put 衞 and 峯 in the 简体-only set. A
|
|
81
81
|
* text written 衞生 was then detected as 简体 and left alone when it was asked
|
|
82
82
|
* for 简体, which is the opposite of what it needed.
|
|
83
|
+
*
|
|
84
|
+
* Occurrence alone is too strict, and that is what {@link writesCharacter}
|
|
85
|
+
* settles. A word list assembled from four sources holds a few headwords that
|
|
86
|
+
* failed to simplify — 见幾而作 and 极深研幾 are 简体 keys written with 幾 — and
|
|
87
|
+
* one of those was enough to take 幾 out of the 繁體-only set against the 297
|
|
88
|
+
* words that put it in. 衛 was out on the strength of a single 简体 headword
|
|
89
|
+
* against 394. So a script counts as writing a character when it writes it
|
|
90
|
+
* often enough to mean something, on the two-condition shape
|
|
91
|
+
* `deriveGlyphTables` already uses for the same kind of question.
|
|
92
|
+
*
|
|
93
|
+
* The variant forms are added afterwards, because normalising folds them away
|
|
94
|
+
* before anything is counted: every 裏 becomes 裡 on the way in, so 裏 occurs
|
|
95
|
+
* nowhere and settled nothing. Every key of `CANONICAL_FORMS` is 繁體 by
|
|
96
|
+
* construction — the variants 简体 writes were excluded from it, measured
|
|
97
|
+
* against CC-CEDICT's 简体 column — so the domain of that table is 繁體-only and
|
|
98
|
+
* joins the set wholesale.
|
|
99
|
+
*
|
|
100
|
+
* Measured against the dictionary's own paired headwords, which is 190,000
|
|
101
|
+
* labelled texts in two scripts: the multi-character pairs settle 99.13% of the
|
|
102
|
+
* time against 97.84% before, and 4 settle the wrong way. Checked against
|
|
103
|
+
* OpenCC's character tables, which no part of this is derived from, the 33
|
|
104
|
+
* characters that join the 简体 side all agree and 56 of the 60 judgeable ones
|
|
105
|
+
* joining the 繁體 side do. The four it disagrees about are 捝, 棁, 涚 and 蒀,
|
|
106
|
+
* which OpenCC lists in both its 简→繁 and 繁→简 tables and no corpus writes at
|
|
107
|
+
* all.
|
|
108
|
+
*
|
|
109
|
+
* 著 stays out of both, which is the honest answer rather than a miss: 简体
|
|
110
|
+
* writes it in its `zhù` sense — 专著, 显著, 著名 — and 繁體 writes it for that
|
|
111
|
+
* and for the aspect particle. 干, 台 and 里 are out for the same reason.
|
|
112
|
+
*/
|
|
113
|
+
/**
|
|
114
|
+
* How many words a script must write a character in before it counts.
|
|
115
|
+
*
|
|
116
|
+
* The absolute floor, paired with {@link WRITTEN_SHARE} below. Both come from
|
|
117
|
+
* `deriveGlyphTables`, which asks the same question about a variant spelling
|
|
118
|
+
* and answers it with the same two conditions and the same numbers.
|
|
119
|
+
*/
|
|
120
|
+
const WRITTEN_WORDS = 10;
|
|
121
|
+
/**
|
|
122
|
+
* The share of the other script's evidence that makes a handful count anyway.
|
|
123
|
+
*
|
|
124
|
+
* Without this a rare character would belong to neither script. 齶 is written
|
|
125
|
+
* in two 繁體 words and no 简体 one, which is 繁體-only however small the number,
|
|
126
|
+
* and a bare floor would throw it away along with 幾's two stray headwords.
|
|
127
|
+
*/
|
|
128
|
+
const WRITTEN_SHARE = 0.05;
|
|
129
|
+
/**
|
|
130
|
+
* Whether a script writes a character often enough for it to mean anything.
|
|
131
|
+
*
|
|
132
|
+
* Two conditions, asking different questions. The floor asks whether the
|
|
133
|
+
* character is written at all in that script, and the share asks whether it is
|
|
134
|
+
* written *relative to the other script* — which is what separates 幾, at two
|
|
135
|
+
* 简体 headwords against 297 繁體 ones, from 著 at 36 against 733.
|
|
83
136
|
*/
|
|
137
|
+
/**
|
|
138
|
+
* Count each character of a word once, into a running tally.
|
|
139
|
+
*/
|
|
140
|
+
function countCharacters(into, word) {
|
|
141
|
+
for (const character of toCharacters(word)) {
|
|
142
|
+
into.set(character, (into.get(character) ?? 0) + 1);
|
|
143
|
+
}
|
|
144
|
+
}
|
|
145
|
+
function writesCharacter(counts, other, character) {
|
|
146
|
+
const held = counts.get(character) ?? 0;
|
|
147
|
+
if (held === 0) {
|
|
148
|
+
return false;
|
|
149
|
+
}
|
|
150
|
+
return (held >= WRITTEN_WORDS || held > (other.get(character) ?? 0) * WRITTEN_SHARE);
|
|
151
|
+
}
|
|
84
152
|
function scriptOnlyCharacters(entries) {
|
|
85
|
-
const inHans = new
|
|
86
|
-
const inHant = new
|
|
153
|
+
const inHans = new Map();
|
|
154
|
+
const inHant = new Map();
|
|
87
155
|
for (const entry of entries) {
|
|
88
156
|
// A 繁體 form that differs from the 简体 one only by glyph normalisation is
|
|
89
157
|
// not evidence about script — 衞生 and 衛生 are two 繁體 spellings of one
|
|
@@ -95,18 +163,28 @@ function scriptOnlyCharacters(entries) {
|
|
|
95
163
|
if (forms.length === 0) {
|
|
96
164
|
continue;
|
|
97
165
|
}
|
|
98
|
-
|
|
99
|
-
for (const
|
|
100
|
-
|
|
166
|
+
countCharacters(inHans, canonicalHans);
|
|
167
|
+
for (const form of forms) {
|
|
168
|
+
countCharacters(inHant, toCanonicalGlyphs(form));
|
|
101
169
|
}
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
170
|
+
}
|
|
171
|
+
const hansOnly = new Set();
|
|
172
|
+
const hantOnly = new Set();
|
|
173
|
+
for (const character of new Set([...inHans.keys(), ...inHant.keys()])) {
|
|
174
|
+
const hans = writesCharacter(inHans, inHant, character);
|
|
175
|
+
const hant = writesCharacter(inHant, inHans, character);
|
|
176
|
+
if (hans && !hant) {
|
|
177
|
+
hansOnly.add(character);
|
|
178
|
+
}
|
|
179
|
+
else if (hant && !hans) {
|
|
180
|
+
hantOnly.add(character);
|
|
105
181
|
}
|
|
106
182
|
}
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
183
|
+
for (const variant of CANONICAL_FORMS.keys()) {
|
|
184
|
+
if (!hansOnly.has(variant)) {
|
|
185
|
+
hantOnly.add(variant);
|
|
186
|
+
}
|
|
187
|
+
}
|
|
188
|
+
return { hansOnly, hantOnly };
|
|
111
189
|
}
|
|
112
190
|
//# sourceMappingURL=script-tables.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"script-tables.js","sourceRoot":"","sources":["../../src/dictionary/script-tables.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,yBAAyB,CAAC;AACvD,OAAO,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;
|
|
1
|
+
{"version":3,"file":"script-tables.js","sourceRoot":"","sources":["../../src/dictionary/script-tables.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,yBAAyB,CAAC;AACvD,OAAO,EAAE,eAAe,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;AACzE,OAAO,EAAE,iBAAiB,EAAqB,MAAM,yBAAyB,CAAC;AAE/E,OAAO,EACL,eAAe,EAEf,UAAU,EACV,OAAO,EACP,KAAK,GACN,MAAM,sBAAsB,CAAC;AAC9B;;;;;;;;;;;;GAYG;AACH,MAAM,UAAU,iBAAiB,CAC/B,OAAmC;IAEnC,MAAM,mBAAmB,GAAG,IAAI,GAAG,EAAqB,CAAC;IACzD,MAAM,kBAAkB,GAAG,IAAI,GAAG,EAAqB,CAAC;IAExD,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,KAAK,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YACpD,KAAK,CAAC,mBAAmB,EAAE,IAAI,EAAE,IAAI,EAAE,GAAG,EAAE,CAAC,CAAC,CAAC;YAC/C,KAAK,CAAC,kBAAkB,EAAE,IAAI,EAAE,IAAI,EAAE,GAAG,EAAE,CAAC,CAAC,CAAC;QAChD,CAAC;IACH,CAAC;IAED,MAAM,aAAa,GAAG,OAAO,CAAC,mBAAmB,CAAC,CAAC;IACnD,MAAM,YAAY,GAAG,OAAO,CAAC,kBAAkB,CAAC,CAAC;IAEjD,4EAA4E;IAC5E,+CAA+C;IAC/C,EAAE;IACF,4EAA4E;IAC5E,4EAA4E;IAC5E,8EAA8E;IAC9E,2EAA2E;IAC3E,6EAA6E;IAC7E,oEAAoE;IACpE,MAAM,gBAAgB,GAAG,IAAI,GAAG,EAAkB,CAAC;IACnD,MAAM,eAAe,GAAG,IAAI,GAAG,EAAkB,CAAC;IAClD,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,IAAI,YAAY,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACxC,SAAS;QACX,CAAC;QACD,MAAM,QAAQ,GAAG,eAAe,CAAC,KAAK,CAAC,CAAC;QACxC,IAAI,iBAAiB,CAAC,aAAa,EAAE,KAAK,CAAC,IAAI,EAAE,QAAQ,CAAC,KAAK,KAAK,CAAC,IAAI,EAAE,CAAC;YAC1E,gBAAgB,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;QAC/C,CAAC;QACD,IAAI,iBAAiB,CAAC,YAAY,EAAE,KAAK,CAAC,IAAI,EAAE,QAAQ,CAAC,KAAK,KAAK,CAAC,IAAI,EAAE,CAAC;YACzE,eAAe,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC;QAC9C,CAAC;IACH,CAAC;IAED,OAAO;QACL,aAAa;QACb,YAAY;QACZ,gBAAgB;QAChB,eAAe;QACf,GAAG,oBAAoB,CAAC,OAAO,CAAC;KACjC,CAAC;AACJ,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoDG;AACH;;;;;;GAMG;AACH,MAAM,aAAa,GAAG,EAAE,CAAC;AAEzB;;;;;;GAMG;AACH,MAAM,aAAa,GAAG,IAAI,CAAC;AAE3B;;;;;;;GAOG;AACH;;GAEG;AACH,SAAS,eAAe,CAAC,IAAyB,EAAE,IAAY;IAC9D,KAAK,MAAM,SAAS,IAAI,YAAY,CAAC,IAAI,CAAC,EAAE,CAAC;QAC3C,IAAI,CAAC,GAAG,CAAC,SAAS,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC;IACtD,CAAC;AACH,CAAC;AAED,SAAS,eAAe,CACtB,MAAmC,EACnC,KAAkC,EAClC,SAAiB;IAEjB,MAAM,IAAI,GAAG,MAAM,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;IACxC,IAAI,IAAI,KAAK,CAAC,EAAE,CAAC;QACf,OAAO,KAAK,CAAC;IACf,CAAC;IACD,OAAO,CACL,IAAI,IAAI,aAAa,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,GAAG,aAAa,CAC5E,CAAC;AACJ,CAAC;AAED,SAAS,oBAAoB,CAAC,OAAmC;IAI/D,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;IACzC,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;IAEzC,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,wEAAwE;QACxE,oEAAoE;QACpE,0EAA0E;QAC1E,uEAAuE;QACvE,2BAA2B;QAC3B,MAAM,aAAa,GAAG,iBAAiB,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACpD,MAAM,KAAK,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,GAAG,CAAC,KAAK,CAAC,YAAY,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAC9D,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,KAAK,KAAK,CAAC,IAAI,IAAI,IAAI,KAAK,aAAa,CACxD,CAAC;QACF,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,SAAS;QACX,CAAC;QACD,eAAe,CAAC,MAAM,EAAE,aAAa,CAAC,CAAC;QACvC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,eAAe,CAAC,MAAM,EAAE,iBAAiB,CAAC,IAAI,CAAC,CAAC,CAAC;QACnD,CAAC;IACH,CAAC;IAED,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAU,CAAC;IACnC,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAU,CAAC;IACnC,KAAK,MAAM,SAAS,IAAI,IAAI,GAAG,CAAC,CAAC,GAAG,MAAM,CAAC,IAAI,EAAE,EAAE,GAAG,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,EAAE,CAAC;QACtE,MAAM,IAAI,GAAG,eAAe,CAAC,MAAM,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;QACxD,MAAM,IAAI,GAAG,eAAe,CAAC,MAAM,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;QACxD,IAAI,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC;YAClB,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;QAC1B,CAAC;aAAM,IAAI,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC;YACzB,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;QAC1B,CAAC;IACH,CAAC;IAED,KAAK,MAAM,OAAO,IAAI,eAAe,CAAC,IAAI,EAAE,EAAE,CAAC;QAC7C,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC;YAC3B,QAAQ,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC;QACxB,CAAC;IACH,CAAC;IAED,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,CAAC;AAChC,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"word-readings.d.ts","sourceRoot":"","sources":["../../src/dictionary/word-readings.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AACH,OAAO,KAAK,EAAE,cAAc,EAAmB,MAAM,uBAAuB,CAAC;AAE7E;;GAEG;AACH,wBAAgB,KAAK,CACnB,IAAI,EAAE,MAAM,EACZ,QAAQ,EAAE,MAAM,EAChB,GAAG,EAAE,MAAM,GACV,cAAc,CAahB;AAED,eAAO,MAAM,aAAa,EAAE,SAAS,cAAc,
|
|
1
|
+
{"version":3,"file":"word-readings.d.ts","sourceRoot":"","sources":["../../src/dictionary/word-readings.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AACH,OAAO,KAAK,EAAE,cAAc,EAAmB,MAAM,uBAAuB,CAAC;AAE7E;;GAEG;AACH,wBAAgB,KAAK,CACnB,IAAI,EAAE,MAAM,EACZ,QAAQ,EAAE,MAAM,EAChB,GAAG,EAAE,MAAM,GACV,cAAc,CAahB;AAED,eAAO,MAAM,aAAa,EAAE,SAAS,cAAc,EAyBlD,CAAC"}
|
|
@@ -34,6 +34,9 @@ export const WORD_READINGS = [
|
|
|
34
34
|
reads("重複", "chóng fù", "one of two 繁體 spellings, both keyed"),
|
|
35
35
|
reads("重覆", "chóng fù", "the other, on the same entry"),
|
|
36
36
|
reads("下麵", "xià miàn", "both spellings of a word CC-CEDICT writes twice"),
|
|
37
|
+
reads("一个", "yī gè", "个 counting is written with its tone"),
|
|
38
|
+
reads("那个人", "nà ge rén", "and 那个's 轻声 holds inside a longer key"),
|
|
39
|
+
reads("独自个", "dú zì gě", "while 个's other reading is not the 量词"),
|
|
37
40
|
reads("做什么", "zuò shén me", "an uncorroborated key held to 什么"),
|
|
38
41
|
reads("什么意思", "shén me yì si", "and to 意思, on the neutral tone"),
|
|
39
42
|
reads("分子结构", "fēn zǐ jié gòu", "but not to a sense 分子 also carries"),
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"word-readings.js","sourceRoot":"","sources":["../../src/dictionary/word-readings.ts"],"names":[],"mappings":"AAUA;;GAEG;AACH,MAAM,UAAU,KAAK,CACnB,IAAY,EACZ,QAAgB,EAChB,GAAW;IAEX,OAAO;QACL,WAAW,EAAE,GAAG,IAAI,MAAM,QAAQ,KAAK,GAAG,GAAG;QAC7C,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,MAAM,GAAG,UAAU,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACxC,IAAI,MAAM,KAAK,SAAS,EAAE,CAAC;gBACzB,OAAO,GAAG,IAAI,iCAAiC,CAAC;YAClD,CAAC;YACD,OAAO,MAAM,KAAK,QAAQ;gBACxB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,GAAG,IAAI,UAAU,MAAM,cAAc,QAAQ,EAAE,CAAC;QACtD,CAAC;KACF,CAAC;AACJ,CAAC;AAED,MAAM,CAAC,MAAM,aAAa,GAA8B;IACtD,KAAK,CAAC,IAAI,EAAE,MAAM,EAAE,iCAAiC,CAAC;IACtD,KAAK,CAAC,IAAI,EAAE,OAAO,EAAE,+BAA+B,CAAC;IACrD,KAAK,CAAC,IAAI,EAAE,MAAM,EAAE,8CAA8C,CAAC;IACnE,KAAK,CAAC,IAAI,EAAE,OAAO,EAAE,6BAA6B,CAAC;IACnD,KAAK,CAAC,MAAM,EAAE,gBAAgB,EAAE,yBAAyB,CAAC;IAC1D,KAAK,CAAC,MAAM,EAAE,gBAAgB,EAAE,+BAA+B,CAAC;IAChE,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,oCAAoC,CAAC;IAC3D,KAAK,CAAC,IAAI,EAAE,SAAS,EAAE,uCAAuC,CAAC;IAC/D,KAAK,CAAC,KAAK,EAAE,cAAc,EAAE,2CAA2C,CAAC;IACzE,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,2CAA2C,CAAC;IAClE,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,oBAAoB,CAAC;IAC7C,KAAK,CAAC,IAAI,EAAE,YAAY,EAAE,oBAAoB,CAAC;IAC/C,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,oCAAoC,CAAC;IAC3D,KAAK,CAAC,IAAI,EAAE,SAAS,EAAE,oCAAoC,CAAC;IAC5D,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,kDAAkD,CAAC;IACzE,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,qCAAqC,CAAC;IAC9D,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,8BAA8B,CAAC;IACvD,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,iDAAiD,CAAC;IAC1E,KAAK,CAAC,KAAK,EAAE,aAAa,EAAE,kCAAkC,CAAC;IAC/D,KAAK,CAAC,MAAM,EAAE,eAAe,EAAE,gCAAgC,CAAC;IAChE,KAAK,CAAC,MAAM,EAAE,gBAAgB,EAAE,oCAAoC,CAAC;CACtE,CAAC"}
|
|
1
|
+
{"version":3,"file":"word-readings.js","sourceRoot":"","sources":["../../src/dictionary/word-readings.ts"],"names":[],"mappings":"AAUA;;GAEG;AACH,MAAM,UAAU,KAAK,CACnB,IAAY,EACZ,QAAgB,EAChB,GAAW;IAEX,OAAO;QACL,WAAW,EAAE,GAAG,IAAI,MAAM,QAAQ,KAAK,GAAG,GAAG;QAC7C,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,MAAM,GAAG,UAAU,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;YACxC,IAAI,MAAM,KAAK,SAAS,EAAE,CAAC;gBACzB,OAAO,GAAG,IAAI,iCAAiC,CAAC;YAClD,CAAC;YACD,OAAO,MAAM,KAAK,QAAQ;gBACxB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,GAAG,IAAI,UAAU,MAAM,cAAc,QAAQ,EAAE,CAAC;QACtD,CAAC;KACF,CAAC;AACJ,CAAC;AAED,MAAM,CAAC,MAAM,aAAa,GAA8B;IACtD,KAAK,CAAC,IAAI,EAAE,MAAM,EAAE,iCAAiC,CAAC;IACtD,KAAK,CAAC,IAAI,EAAE,OAAO,EAAE,+BAA+B,CAAC;IACrD,KAAK,CAAC,IAAI,EAAE,MAAM,EAAE,8CAA8C,CAAC;IACnE,KAAK,CAAC,IAAI,EAAE,OAAO,EAAE,6BAA6B,CAAC;IACnD,KAAK,CAAC,MAAM,EAAE,gBAAgB,EAAE,yBAAyB,CAAC;IAC1D,KAAK,CAAC,MAAM,EAAE,gBAAgB,EAAE,+BAA+B,CAAC;IAChE,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,oCAAoC,CAAC;IAC3D,KAAK,CAAC,IAAI,EAAE,SAAS,EAAE,uCAAuC,CAAC;IAC/D,KAAK,CAAC,KAAK,EAAE,cAAc,EAAE,2CAA2C,CAAC;IACzE,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,2CAA2C,CAAC;IAClE,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,oBAAoB,CAAC;IAC7C,KAAK,CAAC,IAAI,EAAE,YAAY,EAAE,oBAAoB,CAAC;IAC/C,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,oCAAoC,CAAC;IAC3D,KAAK,CAAC,IAAI,EAAE,SAAS,EAAE,oCAAoC,CAAC;IAC5D,KAAK,CAAC,IAAI,EAAE,QAAQ,EAAE,kDAAkD,CAAC;IACzE,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,qCAAqC,CAAC;IAC9D,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,8BAA8B,CAAC;IACvD,KAAK,CAAC,IAAI,EAAE,UAAU,EAAE,iDAAiD,CAAC;IAC1E,KAAK,CAAC,IAAI,EAAE,OAAO,EAAE,qCAAqC,CAAC;IAC3D,KAAK,CAAC,KAAK,EAAE,WAAW,EAAE,uCAAuC,CAAC;IAClE,KAAK,CAAC,KAAK,EAAE,UAAU,EAAE,uCAAuC,CAAC;IACjE,KAAK,CAAC,KAAK,EAAE,aAAa,EAAE,kCAAkC,CAAC;IAC/D,KAAK,CAAC,MAAM,EAAE,eAAe,EAAE,gCAAgC,CAAC;IAChE,KAAK,CAAC,MAAM,EAAE,gBAAgB,EAAE,oCAAoC,CAAC;CACtE,CAAC"}
|
package/dist/index.d.ts
CHANGED
|
@@ -50,7 +50,7 @@ export type { ReadingProjection, ReadingUnit } from "./decode/locking.js";
|
|
|
50
50
|
export { applyEdgeRules, tagOf, wordEndingAt, wordStartingAt, } from "./decode/rules.js";
|
|
51
51
|
export type { EdgeContext, EdgeRule, EdgeVerdict } from "./decode/rules.js";
|
|
52
52
|
export type { PositionalReading, ReadingHint, ReadingHints, WordReading, } from "./decode/hints.js";
|
|
53
|
-
export { ADJECTIVAL_CHANG, ATTESTED_ERHUA, COUNTED_MEASURE, MODAL_DE, PARTICLE_DE, PLAYING_TAN, READING_RULES, TEACHING_JIAO, } from "./decode/reading-rules.js";
|
|
53
|
+
export { ADJECTIVAL_CHANG, ATTESTED_ERHUA, COUNTED_MEASURE, MODAL_DE, PARTICLE_DE, PLAYING_TAN, POTENTIAL_DE, READING_RULES, TEACHING_JIAO, } from "./decode/reading-rules.js";
|
|
54
54
|
export { readingCost, shortestPath, spacingCost } from "./decode/viterbi.js";
|
|
55
55
|
export type { CostOf } from "./decode/viterbi.js";
|
|
56
56
|
export type { DecodedWord, ScoredWord, WordSeparator } from "./decode/word.js";
|
package/dist/index.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EACL,aAAa,EACb,aAAa,EACb,aAAa,EACb,oBAAoB,EACpB,YAAY,GACb,MAAM,0BAA0B,CAAC;AAClC,YAAY,EAAE,kBAAkB,EAAE,MAAM,0BAA0B,CAAC;AAEnE,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,UAAU,GACX,MAAM,4BAA4B,CAAC;AACpC,YAAY,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAEjE,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AACtE,YAAY,EAAE,eAAe,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAC;AAE5E,OAAO,EACL,WAAW,EACX,SAAS,EACT,kBAAkB,EAClB,SAAS,GACV,MAAM,uBAAuB,CAAC;AAE/B,OAAO,EACL,iBAAiB,EACjB,cAAc,GACf,MAAM,iCAAiC,CAAC;AAEzC,OAAO,EAAE,QAAQ,EAAE,MAAM,2BAA2B,CAAC;AACrD,YAAY,EAAE,SAAS,EAAE,MAAM,2BAA2B,CAAC;AAE3D,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AACrD,YAAY,EACV,WAAW,EACX,YAAY,EACZ,UAAU,GACX,MAAM,uBAAuB,CAAC;AAE/B,OAAO,EACL,iBAAiB,EACjB,iBAAiB,EACjB,mBAAmB,GACpB,MAAM,2BAA2B,CAAC;AACnC,YAAY,EAAE,eAAe,EAAE,MAAM,2BAA2B,CAAC;AAEjE,OAAO,EACL,kBAAkB,EAClB,qBAAqB,GACtB,MAAM,yBAAyB,CAAC;AACjC,YAAY,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAC;AAE9D,OAAO,EAAE,WAAW,EAAE,gBAAgB,EAAE,MAAM,6BAA6B,CAAC;AAC5E,YAAY,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAC;AAEjE,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAC;AACxD,YAAY,EAAE,kBAAkB,EAAE,SAAS,EAAE,MAAM,4BAA4B,CAAC;AAEhF,OAAO,EACL,WAAW,EACX,YAAY,EACZ,cAAc,EACd,gBAAgB,EAChB,WAAW,EACX,SAAS,GACV,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AAE/D,OAAO,EACL,OAAO,EACP,eAAe,EACf,aAAa,EACb,UAAU,GACX,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,cAAc,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAC;AAE1E,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,wBAAwB,CAAC;AACpE,YAAY,EACV,kBAAkB,EAClB,iBAAiB,EACjB,UAAU,GACX,MAAM,wBAAwB,CAAC;AAEhC,OAAO,EACL,cAAc,EACd,SAAS,EACT,eAAe,EACf,aAAa,GACd,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,sBAAsB,EACtB,aAAa,EACb,eAAe,EACf,MAAM,GACP,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EACL,kBAAkB,EAClB,eAAe,EACf,KAAK,oBAAoB,EACzB,KAAK,SAAS,GACf,MAAM,2BAA2B,CAAC;AACnC,YAAY,EAAE,WAAW,EAAE,MAAM,kBAAkB,CAAC;AAEpD,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AACxC,YAAY,EACV,WAAW,EACX,aAAa,EACb,SAAS,EACT,UAAU,GACX,MAAM,kBAAkB,CAAC;AAE1B,OAAO,EAAE,cAAc,EAAE,MAAM,oBAAoB,CAAC;AAEpD,OAAO,EACL,iBAAiB,EACjB,eAAe,EACf,cAAc,EACd,QAAQ,EACR,cAAc,GACf,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EACV,YAAY,EACZ,gBAAgB,EAChB,cAAc,EACd,aAAa,EACb,YAAY,GACb,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,iBAAiB,EACjB,OAAO,EACP,oBAAoB,EACpB,iBAAiB,EACjB,gBAAgB,EAChB,iBAAiB,GAClB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,mBAAmB,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAEhF,OAAO,EAAE,iBAAiB,EAAE,MAAM,+BAA+B,CAAC;AAElE,OAAO,EACL,QAAQ,EACR,YAAY,EACZ,SAAS,EACT,cAAc,GACf,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,OAAO,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAEhE,OAAO,EACL,SAAS,EACT,eAAe,EACf,YAAY,EACZ,OAAO,GACR,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,iBAAiB,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAE1E,OAAO,EACL,cAAc,EACd,KAAK,EACL,YAAY,EACZ,cAAc,GACf,MAAM,mBAAmB,CAAC;AAC3B,YAAY,EAAE,WAAW,EAAE,QAAQ,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAE5E,YAAY,EACV,iBAAiB,EACjB,WAAW,EACX,YAAY,EACZ,WAAW,GACZ,MAAM,mBAAmB,CAAC;AAE3B,OAAO,EACL,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,QAAQ,EACR,WAAW,EACX,WAAW,EACX,aAAa,EACb,aAAa,GACd,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAC7E,YAAY,EAAE,MAAM,EAAE,MAAM,qBAAqB,CAAC;AAElD,YAAY,EAAE,WAAW,EAAE,UAAU,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AAE/E,OAAO,EAAE,aAAa,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AACzE,YAAY,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAC;AAE9D,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,mBAAmB,EACnB,WAAW,EACX,WAAW,GACZ,MAAM,0BAA0B,CAAC;AAElC,OAAO,EACL,aAAa,EACb,YAAY,EACZ,YAAY,EACZ,WAAW,EACX,gBAAgB,GACjB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,cAAc,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAE3E,OAAO,EACL,UAAU,EACV,YAAY,EACZ,aAAa,EACb,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AACrC,YAAY,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAC;AAEnE,OAAO,EACL,aAAa,EACb,oBAAoB,EACpB,cAAc,EACd,sBAAsB,EACtB,kBAAkB,GACnB,MAAM,+BAA+B,CAAC;AACvC,YAAY,EAAE,gBAAgB,EAAE,MAAM,+BAA+B,CAAC;AAEtE,OAAO,EACL,QAAQ,EACR,SAAS,EACT,iBAAiB,EACjB,aAAa,GACd,MAAM,yBAAyB,CAAC;AACjC,YAAY,EAAE,WAAW,EAAE,MAAM,yBAAyB,CAAC;AAE3D,OAAO,EACL,UAAU,EACV,WAAW,EACX,eAAe,GAChB,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,OAAO,EACP,QAAQ,EACR,eAAe,EACf,YAAY,GACb,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,UAAU,EAAE,MAAM,wBAAwB,CAAC;AAEzD,OAAO,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAC9C,YAAY,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAEnD,OAAO,EAAE,KAAK,EAAE,MAAM,mBAAmB,CAAC;AAC1C,YAAY,EAAE,UAAU,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAEjE,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAClE,YAAY,EACV,gBAAgB,EAChB,gBAAgB,GACjB,MAAM,wBAAwB,CAAC;AAEhC,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAC;AACzD,YAAY,EACV,iBAAiB,EACjB,gBAAgB,GACjB,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EAAE,KAAK,EAAE,MAAM,kBAAkB,CAAC;AACzC,YAAY,EACV,eAAe,EACf,YAAY,EACZ,gBAAgB,EAChB,WAAW,EACX,aAAa,EACb,cAAc,GACf,MAAM,kBAAkB,CAAC;AAE1B,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,YAAY,EAAE,OAAO,EAAE,MAAM,kBAAkB,CAAC;AAEhD,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AACjD,YAAY,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,oBAAoB,CAAC;AAExE,OAAO,EACL,YAAY,EACZ,UAAU,EACV,mBAAmB,EACnB,KAAK,GACN,MAAM,uBAAuB,CAAC;AAC/B,YAAY,EAAE,IAAI,EAAE,MAAM,uBAAuB,CAAC;AAElD,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,6BAA6B,CAAC;AACjE,YAAY,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAC;AAEnE,OAAO,EACL,uBAAuB,EACvB,mBAAmB,EACnB,cAAc,EACd,UAAU,GACX,MAAM,2BAA2B,CAAC;AACnC,YAAY,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAC;AAE9D,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,cAAc,EACd,UAAU,EACV,cAAc,EACd,gBAAgB,EAChB,QAAQ,GACT,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,kBAAkB,EAClB,kBAAkB,GACnB,MAAM,gCAAgC,CAAC;AAExC,OAAO,EAAE,aAAa,EAAE,MAAM,yBAAyB,CAAC;AAExD,OAAO,EACL,sBAAsB,EACtB,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AAErC,YAAY,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAE1D,OAAO,EACL,mBAAmB,EACnB,iBAAiB,EACjB,YAAY,GACb,MAAM,4BAA4B,CAAC;AACpC,YAAY,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAC;AAE7D,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AACtD,YAAY,EAAE,iBAAiB,EAAE,MAAM,wBAAwB,CAAC;AAEhE,OAAO,EACL,kBAAkB,EAClB,uBAAuB,GACxB,MAAM,8BAA8B,CAAC;AACtC,YAAY,EAAE,gBAAgB,EAAE,MAAM,8BAA8B,CAAC;AAErE,OAAO,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,0BAA0B,CAAC;AAE9E,OAAO,EACL,YAAY,EACZ,cAAc,EACd,QAAQ,EACR,QAAQ,EACR,OAAO,EACP,OAAO,GACR,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,oBAAoB,CAAC;AAEzD,OAAO,EACL,cAAc,EACd,kBAAkB,EAClB,OAAO,EACP,gBAAgB,EAChB,iBAAiB,EACjB,eAAe,EACf,gBAAgB,GACjB,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EAAE,MAAM,EAAE,MAAM,oBAAoB,CAAC;AAEjD,OAAO,EACL,kBAAkB,EAClB,oBAAoB,EACpB,cAAc,EACd,cAAc,EACd,cAAc,GACf,MAAM,yBAAyB,CAAC;AAEjC,OAAO,EACL,MAAM,EACN,QAAQ,EACR,OAAO,EACP,SAAS,EACT,gBAAgB,GACjB,MAAM,yBAAyB,CAAC;AACjC,YAAY,EAAE,KAAK,EAAE,OAAO,EAAE,MAAM,yBAAyB,CAAC;AAE9D,OAAO,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAC;AAE/D,OAAO,EACL,UAAU,EACV,eAAe,EACf,YAAY,EACZ,aAAa,EACb,qBAAqB,GACtB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,QAAQ,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAErE,OAAO,EACL,aAAa,EACb,cAAc,EACd,aAAa,GACd,MAAM,qBAAqB,CAAC;AAE7B,OAAO,EAAE,MAAM,EAAE,YAAY,EAAE,gBAAgB,EAAE,KAAK,EAAE,MAAM,gBAAgB,CAAC;AAC/E,YAAY,EAAE,IAAI,EAAE,MAAM,gBAAgB,CAAC"}
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EACL,aAAa,EACb,aAAa,EACb,aAAa,EACb,oBAAoB,EACpB,YAAY,GACb,MAAM,0BAA0B,CAAC;AAClC,YAAY,EAAE,kBAAkB,EAAE,MAAM,0BAA0B,CAAC;AAEnE,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,UAAU,GACX,MAAM,4BAA4B,CAAC;AACpC,YAAY,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAEjE,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AACtE,YAAY,EAAE,eAAe,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAC;AAE5E,OAAO,EACL,WAAW,EACX,SAAS,EACT,kBAAkB,EAClB,SAAS,GACV,MAAM,uBAAuB,CAAC;AAE/B,OAAO,EACL,iBAAiB,EACjB,cAAc,GACf,MAAM,iCAAiC,CAAC;AAEzC,OAAO,EAAE,QAAQ,EAAE,MAAM,2BAA2B,CAAC;AACrD,YAAY,EAAE,SAAS,EAAE,MAAM,2BAA2B,CAAC;AAE3D,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AACrD,YAAY,EACV,WAAW,EACX,YAAY,EACZ,UAAU,GACX,MAAM,uBAAuB,CAAC;AAE/B,OAAO,EACL,iBAAiB,EACjB,iBAAiB,EACjB,mBAAmB,GACpB,MAAM,2BAA2B,CAAC;AACnC,YAAY,EAAE,eAAe,EAAE,MAAM,2BAA2B,CAAC;AAEjE,OAAO,EACL,kBAAkB,EAClB,qBAAqB,GACtB,MAAM,yBAAyB,CAAC;AACjC,YAAY,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAC;AAE9D,OAAO,EAAE,WAAW,EAAE,gBAAgB,EAAE,MAAM,6BAA6B,CAAC;AAC5E,YAAY,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAC;AAEjE,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAC;AACxD,YAAY,EAAE,kBAAkB,EAAE,SAAS,EAAE,MAAM,4BAA4B,CAAC;AAEhF,OAAO,EACL,WAAW,EACX,YAAY,EACZ,cAAc,EACd,gBAAgB,EAChB,WAAW,EACX,SAAS,GACV,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AAE/D,OAAO,EACL,OAAO,EACP,eAAe,EACf,aAAa,EACb,UAAU,GACX,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,cAAc,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAC;AAE1E,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,wBAAwB,CAAC;AACpE,YAAY,EACV,kBAAkB,EAClB,iBAAiB,EACjB,UAAU,GACX,MAAM,wBAAwB,CAAC;AAEhC,OAAO,EACL,cAAc,EACd,SAAS,EACT,eAAe,EACf,aAAa,GACd,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,sBAAsB,EACtB,aAAa,EACb,eAAe,EACf,MAAM,GACP,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EACL,kBAAkB,EAClB,eAAe,EACf,KAAK,oBAAoB,EACzB,KAAK,SAAS,GACf,MAAM,2BAA2B,CAAC;AACnC,YAAY,EAAE,WAAW,EAAE,MAAM,kBAAkB,CAAC;AAEpD,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AACxC,YAAY,EACV,WAAW,EACX,aAAa,EACb,SAAS,EACT,UAAU,GACX,MAAM,kBAAkB,CAAC;AAE1B,OAAO,EAAE,cAAc,EAAE,MAAM,oBAAoB,CAAC;AAEpD,OAAO,EACL,iBAAiB,EACjB,eAAe,EACf,cAAc,EACd,QAAQ,EACR,cAAc,GACf,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EACV,YAAY,EACZ,gBAAgB,EAChB,cAAc,EACd,aAAa,EACb,YAAY,GACb,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,iBAAiB,EACjB,OAAO,EACP,oBAAoB,EACpB,iBAAiB,EACjB,gBAAgB,EAChB,iBAAiB,GAClB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,mBAAmB,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAEhF,OAAO,EAAE,iBAAiB,EAAE,MAAM,+BAA+B,CAAC;AAElE,OAAO,EACL,QAAQ,EACR,YAAY,EACZ,SAAS,EACT,cAAc,GACf,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,OAAO,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAEhE,OAAO,EACL,SAAS,EACT,eAAe,EACf,YAAY,EACZ,OAAO,GACR,MAAM,qBAAqB,CAAC;AAC7B,YAAY,EAAE,iBAAiB,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAE1E,OAAO,EACL,cAAc,EACd,KAAK,EACL,YAAY,EACZ,cAAc,GACf,MAAM,mBAAmB,CAAC;AAC3B,YAAY,EAAE,WAAW,EAAE,QAAQ,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAE5E,YAAY,EACV,iBAAiB,EACjB,WAAW,EACX,YAAY,EACZ,WAAW,GACZ,MAAM,mBAAmB,CAAC;AAE3B,OAAO,EACL,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,QAAQ,EACR,WAAW,EACX,WAAW,EACX,YAAY,EACZ,aAAa,EACb,aAAa,GACd,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAC7E,YAAY,EAAE,MAAM,EAAE,MAAM,qBAAqB,CAAC;AAElD,YAAY,EAAE,WAAW,EAAE,UAAU,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AAE/E,OAAO,EAAE,aAAa,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AACzE,YAAY,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAC;AAE9D,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,mBAAmB,EACnB,WAAW,EACX,WAAW,GACZ,MAAM,0BAA0B,CAAC;AAElC,OAAO,EACL,aAAa,EACb,YAAY,EACZ,YAAY,EACZ,WAAW,EACX,gBAAgB,GACjB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,cAAc,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAE3E,OAAO,EACL,UAAU,EACV,YAAY,EACZ,aAAa,EACb,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AACrC,YAAY,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAC;AAEnE,OAAO,EACL,aAAa,EACb,oBAAoB,EACpB,cAAc,EACd,sBAAsB,EACtB,kBAAkB,GACnB,MAAM,+BAA+B,CAAC;AACvC,YAAY,EAAE,gBAAgB,EAAE,MAAM,+BAA+B,CAAC;AAEtE,OAAO,EACL,QAAQ,EACR,SAAS,EACT,iBAAiB,EACjB,aAAa,GACd,MAAM,yBAAyB,CAAC;AACjC,YAAY,EAAE,WAAW,EAAE,MAAM,yBAAyB,CAAC;AAE3D,OAAO,EACL,UAAU,EACV,WAAW,EACX,eAAe,GAChB,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,OAAO,EACP,QAAQ,EACR,eAAe,EACf,YAAY,GACb,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,UAAU,EAAE,MAAM,wBAAwB,CAAC;AAEzD,OAAO,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAC9C,YAAY,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAEnD,OAAO,EAAE,KAAK,EAAE,MAAM,mBAAmB,CAAC;AAC1C,YAAY,EAAE,UAAU,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAEjE,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAClE,YAAY,EACV,gBAAgB,EAChB,gBAAgB,GACjB,MAAM,wBAAwB,CAAC;AAEhC,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAC;AACzD,YAAY,EACV,iBAAiB,EACjB,gBAAgB,GACjB,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EAAE,KAAK,EAAE,MAAM,kBAAkB,CAAC;AACzC,YAAY,EACV,eAAe,EACf,YAAY,EACZ,gBAAgB,EAChB,WAAW,EACX,aAAa,EACb,cAAc,GACf,MAAM,kBAAkB,CAAC;AAE1B,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAC7C,YAAY,EAAE,OAAO,EAAE,MAAM,kBAAkB,CAAC;AAEhD,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AACjD,YAAY,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,oBAAoB,CAAC;AAExE,OAAO,EACL,YAAY,EACZ,UAAU,EACV,mBAAmB,EACnB,KAAK,GACN,MAAM,uBAAuB,CAAC;AAC/B,YAAY,EAAE,IAAI,EAAE,MAAM,uBAAuB,CAAC;AAElD,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,6BAA6B,CAAC;AACjE,YAAY,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAC;AAEnE,OAAO,EACL,uBAAuB,EACvB,mBAAmB,EACnB,cAAc,EACd,UAAU,GACX,MAAM,2BAA2B,CAAC;AACnC,YAAY,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAC;AAE9D,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,cAAc,EACd,UAAU,EACV,cAAc,EACd,gBAAgB,EAChB,QAAQ,GACT,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,kBAAkB,EAClB,kBAAkB,GACnB,MAAM,gCAAgC,CAAC;AAExC,OAAO,EAAE,aAAa,EAAE,MAAM,yBAAyB,CAAC;AAExD,OAAO,EACL,sBAAsB,EACtB,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AAErC,YAAY,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAE1D,OAAO,EACL,mBAAmB,EACnB,iBAAiB,EACjB,YAAY,GACb,MAAM,4BAA4B,CAAC;AACpC,YAAY,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAC;AAE7D,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AACtD,YAAY,EAAE,iBAAiB,EAAE,MAAM,wBAAwB,CAAC;AAEhE,OAAO,EACL,kBAAkB,EAClB,uBAAuB,GACxB,MAAM,8BAA8B,CAAC;AACtC,YAAY,EAAE,gBAAgB,EAAE,MAAM,8BAA8B,CAAC;AAErE,OAAO,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,0BAA0B,CAAC;AAE9E,OAAO,EACL,YAAY,EACZ,cAAc,EACd,QAAQ,EACR,QAAQ,EACR,OAAO,EACP,OAAO,GACR,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,oBAAoB,CAAC;AAEzD,OAAO,EACL,cAAc,EACd,kBAAkB,EAClB,OAAO,EACP,gBAAgB,EAChB,iBAAiB,EACjB,eAAe,EACf,gBAAgB,GACjB,MAAM,oBAAoB,CAAC;AAC5B,YAAY,EAAE,MAAM,EAAE,MAAM,oBAAoB,CAAC;AAEjD,OAAO,EACL,kBAAkB,EAClB,oBAAoB,EACpB,cAAc,EACd,cAAc,EACd,cAAc,GACf,MAAM,yBAAyB,CAAC;AAEjC,OAAO,EACL,MAAM,EACN,QAAQ,EACR,OAAO,EACP,SAAS,EACT,gBAAgB,GACjB,MAAM,yBAAyB,CAAC;AACjC,YAAY,EAAE,KAAK,EAAE,OAAO,EAAE,MAAM,yBAAyB,CAAC;AAE9D,OAAO,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAC;AAE/D,OAAO,EACL,UAAU,EACV,eAAe,EACf,YAAY,EACZ,aAAa,EACb,qBAAqB,GACtB,MAAM,wBAAwB,CAAC;AAChC,YAAY,EAAE,QAAQ,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAErE,OAAO,EACL,aAAa,EACb,cAAc,EACd,aAAa,GACd,MAAM,qBAAqB,CAAC;AAE7B,OAAO,EAAE,MAAM,EAAE,YAAY,EAAE,gBAAgB,EAAE,KAAK,EAAE,MAAM,gBAAgB,CAAC;AAC/E,YAAY,EAAE,IAAI,EAAE,MAAM,gBAAgB,CAAC"}
|
package/dist/index.js
CHANGED
|
@@ -30,7 +30,7 @@ export { buildScriptTables } from "./dictionary/script-tables.js";
|
|
|
30
30
|
export { allEdges, buildLattice, cutPoints, READING_CHARGE, } from "./decode/lattice.js";
|
|
31
31
|
export { isSettled, projectReadings, settledUnits, unitsOf, } from "./decode/locking.js";
|
|
32
32
|
export { applyEdgeRules, tagOf, wordEndingAt, wordStartingAt, } from "./decode/rules.js";
|
|
33
|
-
export { ADJECTIVAL_CHANG, ATTESTED_ERHUA, COUNTED_MEASURE, MODAL_DE, PARTICLE_DE, PLAYING_TAN, READING_RULES, TEACHING_JIAO, } from "./decode/reading-rules.js";
|
|
33
|
+
export { ADJECTIVAL_CHANG, ATTESTED_ERHUA, COUNTED_MEASURE, MODAL_DE, PARTICLE_DE, PLAYING_TAN, POTENTIAL_DE, READING_RULES, TEACHING_JIAO, } from "./decode/reading-rules.js";
|
|
34
34
|
export { readingCost, shortestPath, spacingCost } from "./decode/viterbi.js";
|
|
35
35
|
export { cardinalHanzi, LARGEST_CARDINAL } from "./numerals/cardinal.js";
|
|
36
36
|
export { DIGIT_CHARACTERS, numeralSyllable, QUANTITY_CHARACTERS, UNIT_VALUES, yaoSyllable, } from "./numerals/characters.js";
|
package/dist/index.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EACL,aAAa,EACb,aAAa,EACb,aAAa,EACb,oBAAoB,EACpB,YAAY,GACb,MAAM,0BAA0B,CAAC;AAGlC,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,UAAU,GACX,MAAM,4BAA4B,CAAC;AAGpC,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AAGtE,OAAO,EACL,WAAW,EACX,SAAS,EACT,kBAAkB,EAClB,SAAS,GACV,MAAM,uBAAuB,CAAC;AAE/B,OAAO,EACL,iBAAiB,EACjB,cAAc,GACf,MAAM,iCAAiC,CAAC;AAEzC,OAAO,EAAE,QAAQ,EAAE,MAAM,2BAA2B,CAAC;AAGrD,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAOrD,OAAO,EACL,iBAAiB,EACjB,iBAAiB,EACjB,mBAAmB,GACpB,MAAM,2BAA2B,CAAC;AAGnC,OAAO,EACL,kBAAkB,EAClB,qBAAqB,GACtB,MAAM,yBAAyB,CAAC;AAGjC,OAAO,EAAE,WAAW,EAAE,gBAAgB,EAAE,MAAM,6BAA6B,CAAC;AAG5E,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAC;AAGxD,OAAO,EACL,WAAW,EACX,YAAY,EACZ,cAAc,EACd,gBAAgB,EAChB,WAAW,EACX,SAAS,GACV,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EACL,OAAO,EACP,eAAe,EACf,aAAa,EACb,UAAU,GACX,MAAM,qBAAqB,CAAC;AAG7B,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,wBAAwB,CAAC;AAOpE,OAAO,EACL,cAAc,EACd,SAAS,EACT,eAAe,EACf,aAAa,GACd,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,sBAAsB,EACtB,aAAa,EACb,eAAe,EACf,MAAM,GACP,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EACL,kBAAkB,EAClB,eAAe,GAGhB,MAAM,2BAA2B,CAAC;AAGnC,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AAQxC,OAAO,EAAE,cAAc,EAAE,MAAM,oBAAoB,CAAC;AAEpD,OAAO,EACL,iBAAiB,EACjB,eAAe,EACf,cAAc,EACd,QAAQ,EACR,cAAc,GACf,MAAM,oBAAoB,CAAC;AAS5B,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,iBAAiB,EACjB,OAAO,EACP,oBAAoB,EACpB,iBAAiB,EACjB,gBAAgB,EAChB,iBAAiB,GAClB,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EAAE,iBAAiB,EAAE,MAAM,+BAA+B,CAAC;AAElE,OAAO,EACL,QAAQ,EACR,YAAY,EACZ,SAAS,EACT,cAAc,GACf,MAAM,qBAAqB,CAAC;AAG7B,OAAO,EACL,SAAS,EACT,eAAe,EACf,YAAY,EACZ,OAAO,GACR,MAAM,qBAAqB,CAAC;AAG7B,OAAO,EACL,cAAc,EACd,KAAK,EACL,YAAY,EACZ,cAAc,GACf,MAAM,mBAAmB,CAAC;AAU3B,OAAO,EACL,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,QAAQ,EACR,WAAW,EACX,WAAW,EACX,aAAa,EACb,aAAa,GACd,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAK7E,OAAO,EAAE,aAAa,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AAGzE,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,mBAAmB,EACnB,WAAW,EACX,WAAW,GACZ,MAAM,0BAA0B,CAAC;AAElC,OAAO,EACL,aAAa,EACb,YAAY,EACZ,YAAY,EACZ,WAAW,EACX,gBAAgB,GACjB,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EACL,UAAU,EACV,YAAY,EACZ,aAAa,EACb,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AAGrC,OAAO,EACL,aAAa,EACb,oBAAoB,EACpB,cAAc,EACd,sBAAsB,EACtB,kBAAkB,GACnB,MAAM,+BAA+B,CAAC;AAGvC,OAAO,EACL,QAAQ,EACR,SAAS,EACT,iBAAiB,EACjB,aAAa,GACd,MAAM,yBAAyB,CAAC;AAGjC,OAAO,EACL,UAAU,EACV,WAAW,EACX,eAAe,GAChB,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,OAAO,EACP,QAAQ,EACR,eAAe,EACf,YAAY,GACb,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAG9C,OAAO,EAAE,KAAK,EAAE,MAAM,mBAAmB,CAAC;AAG1C,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAMlE,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAC;AAMzD,OAAO,EAAE,KAAK,EAAE,MAAM,kBAAkB,CAAC;AAUzC,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAG7C,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAGjD,OAAO,EACL,YAAY,EACZ,UAAU,EACV,mBAAmB,EACnB,KAAK,GACN,MAAM,uBAAuB,CAAC;AAG/B,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,6BAA6B,CAAC;AAGjE,OAAO,EACL,uBAAuB,EACvB,mBAAmB,EACnB,cAAc,EACd,UAAU,GACX,MAAM,2BAA2B,CAAC;AAGnC,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,cAAc,EACd,UAAU,EACV,cAAc,EACd,gBAAgB,EAChB,QAAQ,GACT,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,kBAAkB,EAClB,kBAAkB,GACnB,MAAM,gCAAgC,CAAC;AAExC,OAAO,EAAE,aAAa,EAAE,MAAM,yBAAyB,CAAC;AAExD,OAAO,EACL,sBAAsB,EACtB,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AAIrC,OAAO,EACL,mBAAmB,EACnB,iBAAiB,EACjB,YAAY,GACb,MAAM,4BAA4B,CAAC;AAGpC,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAGtD,OAAO,EACL,kBAAkB,EAClB,uBAAuB,GACxB,MAAM,8BAA8B,CAAC;AAGtC,OAAO,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,0BAA0B,CAAC;AAE9E,OAAO,EACL,YAAY,EACZ,cAAc,EACd,QAAQ,EACR,QAAQ,EACR,OAAO,EACP,OAAO,GACR,MAAM,oBAAoB,CAAC;AAG5B,OAAO,EACL,cAAc,EACd,kBAAkB,EAClB,OAAO,EACP,gBAAgB,EAChB,iBAAiB,EACjB,eAAe,EACf,gBAAgB,GACjB,MAAM,oBAAoB,CAAC;AAG5B,OAAO,EACL,kBAAkB,EAClB,oBAAoB,EACpB,cAAc,EACd,cAAc,EACd,cAAc,GACf,MAAM,yBAAyB,CAAC;AAEjC,OAAO,EACL,MAAM,EACN,QAAQ,EACR,OAAO,EACP,SAAS,EACT,gBAAgB,GACjB,MAAM,yBAAyB,CAAC;AAGjC,OAAO,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAC;AAE/D,OAAO,EACL,UAAU,EACV,eAAe,EACf,YAAY,EACZ,aAAa,EACb,qBAAqB,GACtB,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EACL,aAAa,EACb,cAAc,EACd,aAAa,GACd,MAAM,qBAAqB,CAAC;AAE7B,OAAO,EAAE,MAAM,EAAE,YAAY,EAAE,gBAAgB,EAAE,KAAK,EAAE,MAAM,gBAAgB,CAAC"}
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EACL,aAAa,EACb,aAAa,EACb,aAAa,EACb,oBAAoB,EACpB,YAAY,GACb,MAAM,0BAA0B,CAAC;AAGlC,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,UAAU,GACX,MAAM,4BAA4B,CAAC;AAGpC,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,MAAM,uBAAuB,CAAC;AAGtE,OAAO,EACL,WAAW,EACX,SAAS,EACT,kBAAkB,EAClB,SAAS,GACV,MAAM,uBAAuB,CAAC;AAE/B,OAAO,EACL,iBAAiB,EACjB,cAAc,GACf,MAAM,iCAAiC,CAAC;AAEzC,OAAO,EAAE,QAAQ,EAAE,MAAM,2BAA2B,CAAC;AAGrD,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAC;AAOrD,OAAO,EACL,iBAAiB,EACjB,iBAAiB,EACjB,mBAAmB,GACpB,MAAM,2BAA2B,CAAC;AAGnC,OAAO,EACL,kBAAkB,EAClB,qBAAqB,GACtB,MAAM,yBAAyB,CAAC;AAGjC,OAAO,EAAE,WAAW,EAAE,gBAAgB,EAAE,MAAM,6BAA6B,CAAC;AAG5E,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAC;AAGxD,OAAO,EACL,WAAW,EACX,YAAY,EACZ,cAAc,EACd,gBAAgB,EAChB,WAAW,EACX,SAAS,GACV,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EACL,OAAO,EACP,eAAe,EACf,aAAa,EACb,UAAU,GACX,MAAM,qBAAqB,CAAC;AAG7B,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,wBAAwB,CAAC;AAOpE,OAAO,EACL,cAAc,EACd,SAAS,EACT,eAAe,EACf,aAAa,GACd,MAAM,oBAAoB,CAAC;AAE5B,OAAO,EACL,sBAAsB,EACtB,aAAa,EACb,eAAe,EACf,MAAM,GACP,MAAM,kBAAkB,CAAC;AAC1B,OAAO,EACL,kBAAkB,EAClB,eAAe,GAGhB,MAAM,2BAA2B,CAAC;AAGnC,OAAO,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAC;AAQxC,OAAO,EAAE,cAAc,EAAE,MAAM,oBAAoB,CAAC;AAEpD,OAAO,EACL,iBAAiB,EACjB,eAAe,EACf,cAAc,EACd,QAAQ,EACR,cAAc,GACf,MAAM,oBAAoB,CAAC;AAS5B,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,iBAAiB,EACjB,OAAO,EACP,oBAAoB,EACpB,iBAAiB,EACjB,gBAAgB,EAChB,iBAAiB,GAClB,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EAAE,iBAAiB,EAAE,MAAM,+BAA+B,CAAC;AAElE,OAAO,EACL,QAAQ,EACR,YAAY,EACZ,SAAS,EACT,cAAc,GACf,MAAM,qBAAqB,CAAC;AAG7B,OAAO,EACL,SAAS,EACT,eAAe,EACf,YAAY,EACZ,OAAO,GACR,MAAM,qBAAqB,CAAC;AAG7B,OAAO,EACL,cAAc,EACd,KAAK,EACL,YAAY,EACZ,cAAc,GACf,MAAM,mBAAmB,CAAC;AAU3B,OAAO,EACL,gBAAgB,EAChB,cAAc,EACd,eAAe,EACf,QAAQ,EACR,WAAW,EACX,WAAW,EACX,YAAY,EACZ,aAAa,EACb,aAAa,GACd,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAK7E,OAAO,EAAE,aAAa,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAC;AAGzE,OAAO,EACL,gBAAgB,EAChB,eAAe,EACf,mBAAmB,EACnB,WAAW,EACX,WAAW,GACZ,MAAM,0BAA0B,CAAC;AAElC,OAAO,EACL,aAAa,EACb,YAAY,EACZ,YAAY,EACZ,WAAW,EACX,gBAAgB,GACjB,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EACL,UAAU,EACV,YAAY,EACZ,aAAa,EACb,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AAGrC,OAAO,EACL,aAAa,EACb,oBAAoB,EACpB,cAAc,EACd,sBAAsB,EACtB,kBAAkB,GACnB,MAAM,+BAA+B,CAAC;AAGvC,OAAO,EACL,QAAQ,EACR,SAAS,EACT,iBAAiB,EACjB,aAAa,GACd,MAAM,yBAAyB,CAAC;AAGjC,OAAO,EACL,UAAU,EACV,WAAW,EACX,eAAe,GAChB,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,OAAO,EACP,QAAQ,EACR,eAAe,EACf,YAAY,GACb,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAC;AAG9C,OAAO,EAAE,KAAK,EAAE,MAAM,mBAAmB,CAAC;AAG1C,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAMlE,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAC;AAMzD,OAAO,EAAE,KAAK,EAAE,MAAM,kBAAkB,CAAC;AAUzC,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AAG7C,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAGjD,OAAO,EACL,YAAY,EACZ,UAAU,EACV,mBAAmB,EACnB,KAAK,GACN,MAAM,uBAAuB,CAAC;AAG/B,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,6BAA6B,CAAC;AAGjE,OAAO,EACL,uBAAuB,EACvB,mBAAmB,EACnB,cAAc,EACd,UAAU,GACX,MAAM,2BAA2B,CAAC;AAGnC,OAAO,EACL,aAAa,EACb,gBAAgB,EAChB,cAAc,EACd,UAAU,EACV,cAAc,EACd,gBAAgB,EAChB,QAAQ,GACT,MAAM,2BAA2B,CAAC;AAEnC,OAAO,EACL,kBAAkB,EAClB,kBAAkB,GACnB,MAAM,gCAAgC,CAAC;AAExC,OAAO,EAAE,aAAa,EAAE,MAAM,yBAAyB,CAAC;AAExD,OAAO,EACL,sBAAsB,EACtB,iBAAiB,GAClB,MAAM,6BAA6B,CAAC;AAIrC,OAAO,EACL,mBAAmB,EACnB,iBAAiB,EACjB,YAAY,GACb,MAAM,4BAA4B,CAAC;AAGpC,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AAGtD,OAAO,EACL,kBAAkB,EAClB,uBAAuB,GACxB,MAAM,8BAA8B,CAAC;AAGtC,OAAO,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,MAAM,0BAA0B,CAAC;AAE9E,OAAO,EACL,YAAY,EACZ,cAAc,EACd,QAAQ,EACR,QAAQ,EACR,OAAO,EACP,OAAO,GACR,MAAM,oBAAoB,CAAC;AAG5B,OAAO,EACL,cAAc,EACd,kBAAkB,EAClB,OAAO,EACP,gBAAgB,EAChB,iBAAiB,EACjB,eAAe,EACf,gBAAgB,GACjB,MAAM,oBAAoB,CAAC;AAG5B,OAAO,EACL,kBAAkB,EAClB,oBAAoB,EACpB,cAAc,EACd,cAAc,EACd,cAAc,GACf,MAAM,yBAAyB,CAAC;AAEjC,OAAO,EACL,MAAM,EACN,QAAQ,EACR,OAAO,EACP,SAAS,EACT,gBAAgB,GACjB,MAAM,yBAAyB,CAAC;AAGjC,OAAO,EAAE,QAAQ,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAC;AAE/D,OAAO,EACL,UAAU,EACV,eAAe,EACf,YAAY,EACZ,aAAa,EACb,qBAAqB,GACtB,MAAM,wBAAwB,CAAC;AAGhC,OAAO,EACL,aAAa,EACb,cAAc,EACd,aAAa,GACd,MAAM,qBAAqB,CAAC;AAE7B,OAAO,EAAE,MAAM,EAAE,YAAY,EAAE,gBAAgB,EAAE,KAAK,EAAE,MAAM,gBAAgB,CAAC"}
|
package/dist/script/glyphs.d.ts
CHANGED
|
@@ -1,4 +1,5 @@
|
|
|
1
1
|
import type { Syllable } from "../syllable/syllable.js";
|
|
2
|
+
export { isReadingScoped, isReadingSensitive } from "./reading-splits.js";
|
|
2
3
|
/**
|
|
3
4
|
* The regional 繁體 orthographies this package writes.
|
|
4
5
|
*
|
|
@@ -40,14 +41,6 @@ export declare const CANONICAL_FORMS: ReadonlyMap<string, string>;
|
|
|
40
41
|
* {@link CANONICAL_FORMS}.
|
|
41
42
|
*/
|
|
42
43
|
export declare const HONG_KONG_FORMS: ReadonlyMap<string, string>;
|
|
43
|
-
/**
|
|
44
|
-
* Whether a character's regional form depends on how it is read.
|
|
45
|
-
*
|
|
46
|
-
* Exposed so that a conversion can report the choice as uncertain when it had
|
|
47
|
-
* no reading to go on, rather than presenting a default as though it were
|
|
48
|
-
* settled.
|
|
49
|
-
*/
|
|
50
|
-
export declare function isReadingSensitive(character: string): boolean;
|
|
51
44
|
/**
|
|
52
45
|
* Normalise one 繁體 character to the canonical form the dictionary stores.
|
|
53
46
|
*
|
|
@@ -83,6 +76,14 @@ export declare function toCanonicalGlyphs(text: string): string;
|
|
|
83
76
|
* changes how a character is read.
|
|
84
77
|
*/
|
|
85
78
|
export declare function toRegionalGlyph(character: string, region: Region, syllable?: Syllable): string;
|
|
79
|
+
/**
|
|
80
|
+
* Every form a character can take in a region, likeliest first.
|
|
81
|
+
*
|
|
82
|
+
* The region's own answer followed by whatever a reading would have kept, which
|
|
83
|
+
* is what a conversion made without a reading needs in order to say what it was
|
|
84
|
+
* choosing between.
|
|
85
|
+
*/
|
|
86
|
+
export declare function regionalGlyphsOf(character: string, region: Region): readonly string[];
|
|
86
87
|
/**
|
|
87
88
|
* Write a whole canonical text in a region's orthography.
|
|
88
89
|
*
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"glyphs.d.ts","sourceRoot":"","sources":["../../src/script/glyphs.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;
|
|
1
|
+
{"version":3,"file":"glyphs.d.ts","sourceRoot":"","sources":["../../src/script/glyphs.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AAIxD,OAAO,EAAE,eAAe,EAAE,kBAAkB,EAAE,MAAM,qBAAqB,CAAC;AAE1E;;;;;;GAMG;AACH,eAAO,MAAM,OAAO,YAAI,IAAI,EAAE,IAAI,CAAU,CAAC;AAE7C;;;;;GAKG;AACH,MAAM,MAAM,MAAM,GAAG,CAAC,OAAO,OAAO,CAAC,CAAC,MAAM,CAAC,CAAC;AAE9C;;;;;;;;;;;GAWG;AACH,eAAO,MAAM,cAAc,OAAwB,CAAC;AAiFpD;;;;;;GAMG;AACH,eAAO,MAAM,eAAe,6BAA6B,CAAC;AAE1D;;;GAGG;AACH,eAAO,MAAM,eAAe,6BAA6B,CAAC;AAE1D;;;;;;GAMG;AACH,wBAAgB,gBAAgB,CAAC,SAAS,EAAE,MAAM,GAAG,MAAM,CAE1D;AAcD;;;;;;;;;;;;;;;;;GAiBG;AACH,wBAAgB,iBAAiB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAStD;AAED;;;;;;GAMG;AACH,wBAAgB,eAAe,CAC7B,SAAS,EAAE,MAAM,EACjB,MAAM,EAAE,MAAM,EACd,QAAQ,CAAC,EAAE,QAAQ,GAClB,MAAM,CASR;AAED;;;;;;GAMG;AACH,wBAAgB,gBAAgB,CAC9B,SAAS,EAAE,MAAM,EACjB,MAAM,EAAE,MAAM,GACb,SAAS,MAAM,EAAE,CAOnB;AAED;;;;;;;GAOG;AACH,wBAAgB,gBAAgB,CAC9B,IAAI,EAAE,MAAM,EACZ,MAAM,EAAE,MAAM,EACd,QAAQ,GAAE,SAAS,CAAC,QAAQ,GAAG,SAAS,CAAC,EAAO,GAC/C,MAAM,CASR"}
|