@kensio/pinyinjs 1.7.10 → 1.7.11
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/README.md +2 -0
- package/data/full.entries +118 -118
- package/data/full.freq +0 -0
- package/data/manifest.json +4 -4
- package/data/standard.entries +111 -111
- package/dist/decode/de-rule.d.ts +4 -4
- package/dist/decode/de-rule.d.ts.map +1 -1
- package/dist/decode/de-rule.js +6 -16
- package/dist/decode/de-rule.js.map +1 -1
- package/dist/decode/edge-context.d.ts +14 -6
- package/dist/decode/edge-context.d.ts.map +1 -1
- package/dist/decode/edge-context.js +25 -0
- package/dist/decode/edge-context.js.map +1 -1
- package/dist/decode/reading-rules.d.ts +1 -0
- package/dist/decode/reading-rules.d.ts.map +1 -1
- package/dist/decode/reading-rules.js +3 -0
- 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/taxi-rule.d.ts +45 -0
- package/dist/decode/taxi-rule.d.ts.map +1 -0
- package/dist/decode/taxi-rule.js +117 -0
- package/dist/decode/taxi-rule.js.map +1 -0
- package/dist/dictionary/dictionary.d.ts +14 -0
- package/dist/dictionary/dictionary.d.ts.map +1 -1
- package/dist/dictionary/dictionary.js +17 -0
- package/dist/dictionary/dictionary.js.map +1 -1
- package/dist/dictionary/entry-invariants.d.ts.map +1 -1
- package/dist/dictionary/entry-invariants.js +28 -0
- package/dist/dictionary/entry-invariants.js.map +1 -1
- package/dist/dictionary/proper-noun.d.ts.map +1 -1
- package/dist/dictionary/proper-noun.js +27 -3
- package/dist/dictionary/proper-noun.js.map +1 -1
- package/dist/dictionary/variant-counts.d.ts +4 -0
- package/dist/dictionary/variant-counts.d.ts.map +1 -1
- package/dist/dictionary/variant-counts.js +4 -0
- package/dist/dictionary/variant-counts.js.map +1 -1
- package/dist/index.d.ts +3 -2
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +3 -2
- package/dist/index.js.map +1 -1
- package/dist/search/candidate-query.d.ts +14 -0
- package/dist/search/candidate-query.d.ts.map +1 -1
- package/dist/search/candidate-query.js +23 -2
- package/dist/search/candidate-query.js.map +1 -1
- package/dist/search/reverse-index-format.d.ts +8 -0
- package/dist/search/reverse-index-format.d.ts.map +1 -1
- package/dist/search/reverse-index-format.js +8 -0
- package/dist/search/reverse-index-format.js.map +1 -1
- package/dist/sources/cedict.d.ts +15 -0
- package/dist/sources/cedict.d.ts.map +1 -1
- package/dist/sources/cedict.js +21 -0
- package/dist/sources/cedict.js.map +1 -1
- package/package.json +1 -1
package/dist/decode/de-rule.d.ts
CHANGED
|
@@ -60,10 +60,10 @@ export declare const POTENTIAL_DE: EdgeRule;
|
|
|
60
60
|
* Only a key **no source has tagged** is forbidden, which is the same line
|
|
61
61
|
* {@link TEACHING_JIAO} draws for a word ending in 教. 的确, 的士 and 的哥 are
|
|
62
62
|
* words jieba counted and tagged, and every one of them can genuinely begin
|
|
63
|
-
* where this fires: 我的确知道, 我要一辆的士, 那个的哥.
|
|
64
|
-
*
|
|
65
|
-
*
|
|
66
|
-
*
|
|
63
|
+
* where this fires: 我的确知道, 我要一辆的士, 那个的哥. What it does reach is
|
|
64
|
+
* the untagged tail — a reading somebody asserted rather than a word anybody
|
|
65
|
+
* counted — where the 的 is the particle every time. The tagged taxi keys are
|
|
66
|
+
* {@link import("./taxi-rule.js").TAXI_DI}'s, which is what settles 我的哥哥们.
|
|
67
67
|
*
|
|
68
68
|
* Measured over the 88,866 lines of Tatoeba and zh.wikipedia it forbids edges
|
|
69
69
|
* in 40 runs: 的筆 13, 的這 11, 的真 6, 的對 4, 的卡 4 and 的歷 once. Every one
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"de-rule.d.ts","sourceRoot":"","sources":["../../src/decode/de-rule.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"de-rule.d.ts","sourceRoot":"","sources":["../../src/decode/de-rule.ts"],"names":[],"mappings":"AASA,OAAO,EAEL,KAAK,QAAQ,EAKd,MAAM,YAAY,CAAC;AAgCpB;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AACH,eAAO,MAAM,QAAQ,EAAE,QActB,CAAC;AA8CF;;;;;;;;;;;;;;;;;;GAkBG;AACH,eAAO,MAAM,YAAY,EAAE,QAoB1B,CAAC;AAWF;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH,eAAO,MAAM,WAAW,EAAE,QAczB,CAAC"}
|
package/dist/decode/de-rule.js
CHANGED
|
@@ -1,13 +1,4 @@
|
|
|
1
|
-
|
|
2
|
-
* The two rules about 得 and 的, which are one character each and three jobs.
|
|
3
|
-
*
|
|
4
|
-
* 得 is stored as the structural particle with `dé` and `děi` as alternates,
|
|
5
|
-
* and 的 is stored as the particle full stop. Both are among the commonest
|
|
6
|
-
* characters in the language, so the words they begin and end are numerous and
|
|
7
|
-
* mostly wrong.
|
|
8
|
-
*/
|
|
9
|
-
import { toCharacters } from "../script/characters.js";
|
|
10
|
-
import { tagOf, wordEndingAt, wordStartingAt, wordsStartingAt, } from "./rules.js";
|
|
1
|
+
import { startsLongerWord, tagOf, wordEndingAt, wordStartingAt, } from "./rules.js";
|
|
11
2
|
/**
|
|
12
3
|
* Whether a syllable is `děi`, the modal reading of 得.
|
|
13
4
|
*
|
|
@@ -112,8 +103,7 @@ function isDe(syllable) {
|
|
|
112
103
|
* own and a test that counted those would answer yes everywhere.
|
|
113
104
|
*/
|
|
114
105
|
function isSwallowed(context, at) {
|
|
115
|
-
|
|
116
|
-
return longer(at) && !longer(at + 1);
|
|
106
|
+
return startsLongerWord(context, at) && !startsLongerWord(context, at + 1);
|
|
117
107
|
}
|
|
118
108
|
/**
|
|
119
109
|
* A verb and a 得 in front of a complement is not a word reading `dé`.
|
|
@@ -173,10 +163,10 @@ const MODIFIED_TAGS = /^(?:r|n|a|v|b|z)/u;
|
|
|
173
163
|
* Only a key **no source has tagged** is forbidden, which is the same line
|
|
174
164
|
* {@link TEACHING_JIAO} draws for a word ending in 教. 的确, 的士 and 的哥 are
|
|
175
165
|
* words jieba counted and tagged, and every one of them can genuinely begin
|
|
176
|
-
* where this fires: 我的确知道, 我要一辆的士, 那个的哥.
|
|
177
|
-
*
|
|
178
|
-
*
|
|
179
|
-
*
|
|
166
|
+
* where this fires: 我的确知道, 我要一辆的士, 那个的哥. What it does reach is
|
|
167
|
+
* the untagged tail — a reading somebody asserted rather than a word anybody
|
|
168
|
+
* counted — where the 的 is the particle every time. The tagged taxi keys are
|
|
169
|
+
* {@link import("./taxi-rule.js").TAXI_DI}'s, which is what settles 我的哥哥们.
|
|
180
170
|
*
|
|
181
171
|
* Measured over the 88,866 lines of Tatoeba and zh.wikipedia it forbids edges
|
|
182
172
|
* in 40 runs: 的筆 13, 的這 11, 的真 6, 的對 4, 的卡 4 and 的歷 once. Every one
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"de-rule.js","sourceRoot":"","sources":["../../src/decode/de-rule.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"de-rule.js","sourceRoot":"","sources":["../../src/decode/de-rule.ts"],"names":[],"mappings":"AASA,OAAO,EAGL,gBAAgB,EAChB,KAAK,EACL,YAAY,EACZ,cAAc,GACf,MAAM,YAAY,CAAC;AAEpB;;;;;GAKG;AACH,SAAS,KAAK,CAAC,QAA8B;IAC3C,OAAO,CACL,QAAQ,EAAE,OAAO,KAAK,GAAG,IAAI,QAAQ,CAAC,KAAK,KAAK,IAAI,IAAI,QAAQ,CAAC,IAAI,KAAK,CAAC,CAC5E,CAAC;AACJ,CAAC;AAED;;;;;;GAMG;AACH,MAAM,YAAY,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC;AAE9C;;;;;;GAMG;AACH,MAAM,aAAa,GAAG,eAAe,CAAC;AAEtC;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AACH,MAAM,CAAC,MAAM,QAAQ,GAAa;IAChC,IAAI,EAAE,UAAU;IAChB,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACzB,IAAI,IAAI,CAAC,IAAI,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YACjD,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,MAAM,MAAM,GAAG,YAAY,CAAC,OAAO,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAChD,MAAM,KAAK,GAAG,cAAc,CAAC,OAAO,EAAE,IAAI,CAAC,EAAE,CAAC,CAAC;QAC/C,OAAO,YAAY,CAAC,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC;YAC7C,aAAa,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,KAAK,CAAC,CAAC;YACzC,CAAC,CAAC,OAAO;YACT,CAAC,CAAC,MAAM,CAAC;IACb,CAAC;CACF,CAAC;AAEF;;;;;;;;;;;;GAYG;AACH,MAAM,WAAW,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC;AAElD;;GAEG;AACH,MAAM,QAAQ,GAAG,GAAG,CAAC;AAErB;;GAEG;AACH,SAAS,IAAI,CAAC,QAA8B;IAC1C,OAAO,CACL,QAAQ,EAAE,OAAO,KAAK,GAAG,IAAI,QAAQ,CAAC,KAAK,KAAK,GAAG,IAAI,QAAQ,CAAC,IAAI,KAAK,CAAC,CAC3E,CAAC;AACJ,CAAC;AAED;;;;;;;;;;GAUG;AACH,SAAS,WAAW,CAAC,OAAoB,EAAE,EAAU;IACnD,OAAO,gBAAgB,CAAC,OAAO,EAAE,EAAE,CAAC,IAAI,CAAC,gBAAgB,CAAC,OAAO,EAAE,EAAE,GAAG,CAAC,CAAC,CAAC;AAC7E,CAAC;AAED;;;;;;;;;;;;;;;;;;GAkBG;AACH,MAAM,CAAC,MAAM,YAAY,GAAa;IACpC,IAAI,EAAE,cAAc;IACpB,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,UAAU,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACrC,IACE,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,IAAI,KAAK,CAAC;YACzB,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,KAAK,GAAG;YACxB,IAAI,CAAC,OAAO,CAAC,MAAM,KAAK,CAAC;YACzB,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,EACtB,CAAC;YACD,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,UAAU,CAAC,QAAQ,CAAC,EAAE,CAAC;YAChE,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,OAAO,WAAW,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC;YAC/C,CAAC,WAAW,CAAC,OAAO,EAAE,IAAI,CAAC,EAAE,CAAC;YAC9B,CAAC,CAAC,QAAQ;YACV,CAAC,CAAC,MAAM,CAAC;IACb,CAAC;CACF,CAAC;AAEF;;;;;;GAMG;AACH,MAAM,aAAa,GAAG,mBAAmB,CAAC;AAE1C;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH,MAAM,CAAC,MAAM,WAAW,GAAa;IACnC,IAAI,EAAE,aAAa;IACnB,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACzB,IACE,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,IAAI,GAAG,CAAC;YACvB,IAAI,CAAC,YAAY,KAAK,EAAE;YACxB,CAAC,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAC1B,CAAC;YACD,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,MAAM,MAAM,GAAG,YAAY,CAAC,OAAO,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAChD,OAAO,aAAa,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC;IACxE,CAAC;CACF,CAAC"}
|
|
@@ -1,9 +1,3 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* What a rule can ask about the words around an edge.
|
|
3
|
-
*
|
|
4
|
-
* The lookups every edge rule shares: which word ends here, which starts here,
|
|
5
|
-
* and what part of speech the dictionary gives it.
|
|
6
|
-
*/
|
|
7
1
|
import type { EdgeContext } from "./rules.js";
|
|
8
2
|
/**
|
|
9
3
|
* The word ending at a position, longest first, or undefined.
|
|
@@ -41,6 +35,20 @@ export declare function wordsStartingAt(context: EdgeContext, at: number, longes
|
|
|
41
35
|
* The part of speech the dictionary gives a word, or the empty string.
|
|
42
36
|
*/
|
|
43
37
|
export declare function tagOf(context: EdgeContext, word: string | undefined): string;
|
|
38
|
+
/**
|
|
39
|
+
* Whether a word of more than one character starts at a position.
|
|
40
|
+
*
|
|
41
|
+
* Every character is a word of its own, so a test that counted those would
|
|
42
|
+
* answer yes everywhere. What a rule asking this wants to know is whether some
|
|
43
|
+
* longer word has a claim on the character.
|
|
44
|
+
*/
|
|
45
|
+
export declare function startsLongerWord(context: EdgeContext, at: number): boolean;
|
|
46
|
+
/**
|
|
47
|
+
* Whether a word of more than one character ends at a position.
|
|
48
|
+
*
|
|
49
|
+
* The mirror of {@link startsLongerWord}, and asked for the same reason.
|
|
50
|
+
*/
|
|
51
|
+
export declare function endsLongerWord(context: EdgeContext, at: number): boolean;
|
|
44
52
|
/**
|
|
45
53
|
* What follows a 教 that is teaching where no object does: aspect and the
|
|
46
54
|
* complement marker, which only a verb takes.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"edge-context.d.ts","sourceRoot":"","sources":["../../src/decode/edge-context.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"edge-context.d.ts","sourceRoot":"","sources":["../../src/decode/edge-context.ts"],"names":[],"mappings":"AAOA,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,YAAY,CAAC;AAE9C;;;;;;;GAOG;AACH,wBAAgB,YAAY,CAC1B,OAAO,EAAE,WAAW,EACpB,EAAE,EAAE,MAAM,EACV,OAAO,SAAI,GACV,MAAM,GAAG,SAAS,CAYpB;AAED;;;;;;;;;GASG;AACH,wBAAgB,aAAa,CAC3B,OAAO,EAAE,WAAW,EACpB,EAAE,EAAE,MAAM,EACV,OAAO,SAAI,GACV,SAAS,MAAM,EAAE,CAanB;AAED;;GAEG;AACH,wBAAgB,cAAc,CAC5B,OAAO,EAAE,WAAW,EACpB,EAAE,EAAE,MAAM,EACV,OAAO,SAAI,GACV,MAAM,GAAG,SAAS,CAUpB;AAED;;;;;;GAMG;AACH,wBAAgB,eAAe,CAC7B,OAAO,EAAE,WAAW,EACpB,EAAE,EAAE,MAAM,EACV,OAAO,SAAI,GACV,SAAS,MAAM,EAAE,CASnB;AAED;;GAEG;AACH,wBAAgB,KAAK,CAAC,OAAO,EAAE,WAAW,EAAE,IAAI,EAAE,MAAM,GAAG,SAAS,GAAG,MAAM,CAI5E;AAED;;;;;;GAMG;AACH,wBAAgB,gBAAgB,CAAC,OAAO,EAAE,WAAW,EAAE,EAAE,EAAE,MAAM,GAAG,OAAO,CAI1E;AAED;;;;GAIG;AACH,wBAAgB,cAAc,CAAC,OAAO,EAAE,WAAW,EAAE,EAAE,EAAE,MAAM,GAAG,OAAO,CAIxE;AAED;;;;;;;GAOG;AACH,eAAO,MAAM,MAAM,aAA0C,CAAC;AAE9D;;GAEG;AACH,eAAO,MAAM,YAAY,MAAM,CAAC"}
|
|
@@ -1,3 +1,10 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* What a rule can ask about the words around an edge.
|
|
3
|
+
*
|
|
4
|
+
* The lookups every edge rule shares: which word ends here, which starts here,
|
|
5
|
+
* and what part of speech the dictionary gives it.
|
|
6
|
+
*/
|
|
7
|
+
import { toCharacters } from "../script/characters.js";
|
|
1
8
|
/**
|
|
2
9
|
* The word ending at a position, longest first, or undefined.
|
|
3
10
|
*
|
|
@@ -82,6 +89,24 @@ export function tagOf(context, word) {
|
|
|
82
89
|
? ""
|
|
83
90
|
: (context.dictionary.lookup(word)?.partOfSpeech ?? "");
|
|
84
91
|
}
|
|
92
|
+
/**
|
|
93
|
+
* Whether a word of more than one character starts at a position.
|
|
94
|
+
*
|
|
95
|
+
* Every character is a word of its own, so a test that counted those would
|
|
96
|
+
* answer yes everywhere. What a rule asking this wants to know is whether some
|
|
97
|
+
* longer word has a claim on the character.
|
|
98
|
+
*/
|
|
99
|
+
export function startsLongerWord(context, at) {
|
|
100
|
+
return wordsStartingAt(context, at).some((word) => toCharacters(word).length > 1);
|
|
101
|
+
}
|
|
102
|
+
/**
|
|
103
|
+
* Whether a word of more than one character ends at a position.
|
|
104
|
+
*
|
|
105
|
+
* The mirror of {@link startsLongerWord}, and asked for the same reason.
|
|
106
|
+
*/
|
|
107
|
+
export function endsLongerWord(context, at) {
|
|
108
|
+
return wordsEndingAt(context, at).some((word) => toCharacters(word).length > 1);
|
|
109
|
+
}
|
|
85
110
|
/**
|
|
86
111
|
* What follows a 教 that is teaching where no object does: aspect and the
|
|
87
112
|
* complement marker, which only a verb takes.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"edge-context.js","sourceRoot":"","sources":["../../src/decode/edge-context.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"edge-context.js","sourceRoot":"","sources":["../../src/decode/edge-context.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AACH,OAAO,EAAE,YAAY,EAAE,MAAM,yBAAyB,CAAC;AAGvD;;;;;;;GAOG;AACH,MAAM,UAAU,YAAY,CAC1B,OAAoB,EACpB,EAAU,EACV,OAAO,GAAG,CAAC;IAEX,KAAK,IAAI,MAAM,GAAG,OAAO,EAAE,MAAM,GAAG,CAAC,EAAE,MAAM,EAAE,EAAE,CAAC;QAChD,MAAM,IAAI,GAAG,EAAE,GAAG,MAAM,CAAC;QACzB,IAAI,IAAI,GAAG,CAAC,EAAE,CAAC;YACb,SAAS;QACX,CAAC;QACD,MAAM,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACzD,IAAI,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,SAAS,EAAE,CAAC;YAClD,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,SAAS,CAAC;AACnB,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,UAAU,aAAa,CAC3B,OAAoB,EACpB,EAAU,EACV,OAAO,GAAG,CAAC;IAEX,MAAM,IAAI,GAAa,EAAE,CAAC;IAC1B,KAAK,IAAI,MAAM,GAAG,OAAO,EAAE,MAAM,GAAG,CAAC,EAAE,MAAM,EAAE,EAAE,CAAC;QAChD,MAAM,IAAI,GAAG,EAAE,GAAG,MAAM,CAAC;QACzB,IAAI,IAAI,GAAG,CAAC,EAAE,CAAC;YACb,SAAS;QACX,CAAC;QACD,MAAM,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACzD,IAAI,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,SAAS,EAAE,CAAC;YAClD,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAClB,CAAC;IACH,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,cAAc,CAC5B,OAAoB,EACpB,EAAU,EACV,OAAO,GAAG,CAAC;IAEX,KAAK,IAAI,MAAM,GAAG,OAAO,EAAE,MAAM,GAAG,CAAC,EAAE,MAAM,EAAE,EAAE,CAAC;QAChD,mEAAmE;QACnE,sBAAsB;QACtB,MAAM,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,GAAG,MAAM,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAChE,IAAI,IAAI,KAAK,EAAE,IAAI,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,SAAS,EAAE,CAAC;YACjE,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,SAAS,CAAC;AACnB,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,eAAe,CAC7B,OAAoB,EACpB,EAAU,EACV,OAAO,GAAG,CAAC;IAEX,MAAM,IAAI,GAAa,EAAE,CAAC;IAC1B,KAAK,IAAI,MAAM,GAAG,OAAO,EAAE,MAAM,GAAG,CAAC,EAAE,MAAM,EAAE,EAAE,CAAC;QAChD,MAAM,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,EAAE,EAAE,GAAG,MAAM,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QAChE,IAAI,IAAI,KAAK,EAAE,IAAI,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,SAAS,EAAE,CAAC;YACjE,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAClB,CAAC;IACH,CAAC;IACD,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,KAAK,CAAC,OAAoB,EAAE,IAAwB;IAClE,OAAO,IAAI,KAAK,SAAS;QACvB,CAAC,CAAC,EAAE;QACJ,CAAC,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,YAAY,IAAI,EAAE,CAAC,CAAC;AAC5D,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,gBAAgB,CAAC,OAAoB,EAAE,EAAU;IAC/D,OAAO,eAAe,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,IAAI,CACtC,CAAC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,CACxC,CAAC;AACJ,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,cAAc,CAAC,OAAoB,EAAE,EAAU;IAC7D,OAAO,aAAa,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,IAAI,CACpC,CAAC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,CACxC,CAAC;AACJ,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,CAAC,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC;AAE9D;;GAEG;AACH,MAAM,CAAC,MAAM,YAAY,GAAG,GAAG,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"reading-rules.d.ts","sourceRoot":"","sources":["../../src/decode/reading-rules.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"reading-rules.d.ts","sourceRoot":"","sources":["../../src/decode/reading-rules.ts"],"names":[],"mappings":"AAMA,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AACnE,OAAO,EAAE,OAAO,EAAE,MAAM,gBAAgB,CAAC;AACzC,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAE/C,OAAO,EAEL,KAAK,QAAQ,EAGd,MAAM,YAAY,CAAC;AAEpB;;;;;;;;;;;;;;;;;;;GAmBG;AACH,eAAO,MAAM,cAAc,EAAE,QAY5B,CAAC;AAsCF;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AACH,eAAO,MAAM,eAAe,EAAE,QAuB7B,CAAC;AAIF,OAAO,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAErE;;GAEG;AACH,eAAO,MAAM,aAAa,EAAE,SAAS,QAAQ,EAW5C,CAAC"}
|
|
@@ -1,8 +1,10 @@
|
|
|
1
1
|
import { QUANTITY_CHARACTERS } from "../numerals/characters.js";
|
|
2
2
|
import { MODAL_DE, PARTICLE_DE, POTENTIAL_DE } from "./de-rule.js";
|
|
3
|
+
import { TAXI_DI } from "./taxi-rule.js";
|
|
3
4
|
import { EXPERIENTIAL_GUO } from "./guo-rule.js";
|
|
4
5
|
import { TEACHING_JIAO } from "./jiao-rule.js";
|
|
5
6
|
export { MODAL_DE, PARTICLE_DE, POTENTIAL_DE } from "./de-rule.js";
|
|
7
|
+
export { TAXI_DI } from "./taxi-rule.js";
|
|
6
8
|
export { EXPERIENTIAL_GUO } from "./guo-rule.js";
|
|
7
9
|
export { TEACHING_JIAO } from "./jiao-rule.js";
|
|
8
10
|
import { toCharacters } from "../script/characters.js";
|
|
@@ -132,6 +134,7 @@ export const READING_RULES = [
|
|
|
132
134
|
MODAL_DE,
|
|
133
135
|
PARTICLE_DE,
|
|
134
136
|
POTENTIAL_DE,
|
|
137
|
+
TAXI_DI,
|
|
135
138
|
TEACHING_JIAO,
|
|
136
139
|
ATTESTED_ERHUA,
|
|
137
140
|
COUNTED_MEASURE,
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"reading-rules.js","sourceRoot":"","sources":["../../src/decode/reading-rules.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,mBAAmB,EAAE,MAAM,2BAA2B,CAAC;AAChE,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AACnE,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAE/C,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AACnE,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAC/C,OAAO,EAAE,YAAY,EAAE,MAAM,yBAAyB,CAAC;AACvD,OAAO,EAGL,KAAK,EACL,YAAY,GACb,MAAM,YAAY,CAAC;AAEpB;;;;;;;;;;;;;;;;;;;GAmBG;AACH,MAAM,CAAC,MAAM,cAAc,GAAa;IACtC,IAAI,EAAE,gBAAgB;IACtB,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,UAAU,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACrC,IAAI,IAAI,CAAC,IAAI,KAAK,GAAG,IAAI,IAAI,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;YACzC,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,wEAAwE;QACxE,MAAM,QAAQ,GAAG,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,GAAG,CAAC;QACvD,MAAM,OAAO,GAAG,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,QAAQ,CAAC,EAAE,OAAO,CAAC;QAC7D,OAAO,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC;IAC/D,CAAC;CACF,CAAC;AAEF;;GAEG;AACH,MAAM,OAAO,GAAG,GAAG,CAAC;AAEpB;;;;;GAKG;AACH,MAAM,OAAO,GAAG,GAAG,CAAC;AAEpB;;;;;;;;GAQG;AACH,SAAS,WAAW,CAAC,OAAoB,EAAE,EAAU;IACnD,MAAM,EAAE,UAAU,EAAE,GAAG,OAAO,CAAC;IAC/B,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,OAAO,IAAI,GAAG,CAAC,IAAI,mBAAmB,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC;QACvE,IAAI,EAAE,CAAC;IACT,CAAC;IACD,IAAI,IAAI,KAAK,EAAE,IAAI,UAAU,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,OAAO,EAAE,CAAC;QACpD,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,MAAM,MAAM,GAAG,YAAY,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;IACzC,MAAM,IAAI,GAAG,MAAM,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC;IAC1E,OAAO,IAAI,GAAG,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC;AACxC,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AACH,MAAM,CAAC,MAAM,eAAe,GAAa;IACvC,IAAI,EAAE,iBAAiB;IACvB,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,UAAU,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACrC,yEAAyE;QACzE,yEAAyE;QACzE,yEAAyE;QACzE,WAAW;QACX,IACE,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,IAAI,GAAG,CAAC;YACvB,IAAI,CAAC,OAAO,CAAC,MAAM,KAAK,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,IAAI,EAC3C,CAAC;YACD,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,MAAM,OAAO,GAAG,WAAW,CAAC,OAAO,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAChD,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;YAC1B,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,OAAO,KAAK,CAAC,OAAO,EAAE,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,OAAO;YACtD,IAAI,CAAC,YAAY,KAAK,OAAO;YAC7B,CAAC,CAAC,QAAQ;YACV,CAAC,CAAC,MAAM,CAAC;IACb,CAAC;CACF,CAAC;AAEF,OAAO,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAErE,OAAO,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAErE;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAwB;IAChD,QAAQ;IACR,WAAW;IACX,YAAY;IACZ,aAAa;IACb,cAAc;IACd,eAAe;IACf,gBAAgB;IAChB,WAAW;IACX,gBAAgB;CACjB,CAAC"}
|
|
1
|
+
{"version":3,"file":"reading-rules.js","sourceRoot":"","sources":["../../src/decode/reading-rules.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,mBAAmB,EAAE,MAAM,2BAA2B,CAAC;AAChE,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AACnE,OAAO,EAAE,OAAO,EAAE,MAAM,gBAAgB,CAAC;AACzC,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAE/C,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,YAAY,EAAE,MAAM,cAAc,CAAC;AACnE,OAAO,EAAE,OAAO,EAAE,MAAM,gBAAgB,CAAC;AACzC,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAC/C,OAAO,EAAE,YAAY,EAAE,MAAM,yBAAyB,CAAC;AACvD,OAAO,EAGL,KAAK,EACL,YAAY,GACb,MAAM,YAAY,CAAC;AAEpB;;;;;;;;;;;;;;;;;;;GAmBG;AACH,MAAM,CAAC,MAAM,cAAc,GAAa;IACtC,IAAI,EAAE,gBAAgB;IACtB,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,UAAU,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACrC,IAAI,IAAI,CAAC,IAAI,KAAK,GAAG,IAAI,IAAI,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;YACzC,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,wEAAwE;QACxE,MAAM,QAAQ,GAAG,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,GAAG,CAAC;QACvD,MAAM,OAAO,GAAG,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC,QAAQ,CAAC,EAAE,OAAO,CAAC;QAC7D,OAAO,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,EAAE,KAAK,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC;IAC/D,CAAC;CACF,CAAC;AAEF;;GAEG;AACH,MAAM,OAAO,GAAG,GAAG,CAAC;AAEpB;;;;;GAKG;AACH,MAAM,OAAO,GAAG,GAAG,CAAC;AAEpB;;;;;;;;GAQG;AACH,SAAS,WAAW,CAAC,OAAoB,EAAE,EAAU;IACnD,MAAM,EAAE,UAAU,EAAE,GAAG,OAAO,CAAC;IAC/B,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,OAAO,IAAI,GAAG,CAAC,IAAI,mBAAmB,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC;QACvE,IAAI,EAAE,CAAC;IACT,CAAC;IACD,IAAI,IAAI,KAAK,EAAE,IAAI,UAAU,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,OAAO,EAAE,CAAC;QACpD,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,MAAM,MAAM,GAAG,YAAY,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;IACzC,MAAM,IAAI,GAAG,MAAM,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC;IAC1E,OAAO,IAAI,GAAG,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC;AACxC,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AACH,MAAM,CAAC,MAAM,eAAe,GAAa;IACvC,IAAI,EAAE,iBAAiB;IACvB,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,UAAU,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACrC,yEAAyE;QACzE,yEAAyE;QACzE,yEAAyE;QACzE,WAAW;QACX,IACE,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,IAAI,GAAG,CAAC;YACvB,IAAI,CAAC,OAAO,CAAC,MAAM,KAAK,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,IAAI,EAC3C,CAAC;YACD,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,MAAM,OAAO,GAAG,WAAW,CAAC,OAAO,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC;QAChD,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;YAC1B,OAAO,MAAM,CAAC;QAChB,CAAC;QACD,OAAO,KAAK,CAAC,OAAO,EAAE,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,OAAO;YACtD,IAAI,CAAC,YAAY,KAAK,OAAO;YAC7B,CAAC,CAAC,QAAQ;YACV,CAAC,CAAC,MAAM,CAAC;IACb,CAAC;CACF,CAAC;AAEF,OAAO,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAErE,OAAO,EAAE,gBAAgB,EAAE,WAAW,EAAE,MAAM,sBAAsB,CAAC;AAErE;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAwB;IAChD,QAAQ;IACR,WAAW;IACX,YAAY;IACZ,OAAO;IACP,aAAa;IACb,cAAc;IACd,eAAe;IACf,gBAAgB;IAChB,WAAW;IACX,gBAAgB;CACjB,CAAC"}
|
package/dist/decode/rules.d.ts
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import type { Dictionary } from "../dictionary/dictionary.js";
|
|
2
2
|
import type { Lattice, LatticeEdge } from "./lattice.js";
|
|
3
|
-
export { ASPECT, PARTICLE_TAG, tagOf, wordEndingAt, wordsEndingAt, wordStartingAt, wordsStartingAt, } from "./edge-context.js";
|
|
3
|
+
export { ASPECT, endsLongerWord, PARTICLE_TAG, startsLongerWord, tagOf, wordEndingAt, wordsEndingAt, wordStartingAt, wordsStartingAt, } from "./edge-context.js";
|
|
4
4
|
/**
|
|
5
5
|
* What a rule can say about one edge.
|
|
6
6
|
*
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"rules.d.ts","sourceRoot":"","sources":["../../src/decode/rules.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,6BAA6B,CAAC;AAC9D,OAAO,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,MAAM,cAAc,CAAC;AAEzD,OAAO,EACL,MAAM,EACN,YAAY,EACZ,KAAK,EACL,YAAY,EACZ,aAAa,EACb,cAAc,EACd,eAAe,GAChB,MAAM,mBAAmB,CAAC;AAE3B;;;;;;;GAOG;AACH,MAAM,MAAM,WAAW,GAAG,MAAM,GAAG,QAAQ,GAAG,OAAO,CAAC;AAEtD;;;;;;GAMG;AACH,MAAM,WAAW,WAAW;IAC1B,QAAQ,CAAC,UAAU,EAAE,UAAU,CAAC;IAChC,QAAQ,CAAC,UAAU,EAAE,SAAS,MAAM,EAAE,CAAC;IACvC,QAAQ,CAAC,IAAI,EAAE,WAAW,CAAC;CAC5B;AAED;;;;;;;GAOG;AACH,MAAM,WAAW,QAAQ;IACvB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,UAAU,EAAE,CAAC,OAAO,EAAE,WAAW,KAAK,WAAW,CAAC;CAC5D;AA+DD;;;;;;;;;;;GAWG;AACH,wBAAgB,cAAc,CAC5B,OAAO,EAAE,OAAO,EAChB,UAAU,EAAE,UAAU,EACtB,KAAK,EAAE,SAAS,QAAQ,EAAE,GACzB,OAAO,CAsCT"}
|
|
1
|
+
{"version":3,"file":"rules.d.ts","sourceRoot":"","sources":["../../src/decode/rules.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,6BAA6B,CAAC;AAC9D,OAAO,KAAK,EAAE,OAAO,EAAE,WAAW,EAAE,MAAM,cAAc,CAAC;AAEzD,OAAO,EACL,MAAM,EACN,cAAc,EACd,YAAY,EACZ,gBAAgB,EAChB,KAAK,EACL,YAAY,EACZ,aAAa,EACb,cAAc,EACd,eAAe,GAChB,MAAM,mBAAmB,CAAC;AAE3B;;;;;;;GAOG;AACH,MAAM,MAAM,WAAW,GAAG,MAAM,GAAG,QAAQ,GAAG,OAAO,CAAC;AAEtD;;;;;;GAMG;AACH,MAAM,WAAW,WAAW;IAC1B,QAAQ,CAAC,UAAU,EAAE,UAAU,CAAC;IAChC,QAAQ,CAAC,UAAU,EAAE,SAAS,MAAM,EAAE,CAAC;IACvC,QAAQ,CAAC,IAAI,EAAE,WAAW,CAAC;CAC5B;AAED;;;;;;;GAOG;AACH,MAAM,WAAW,QAAQ;IACvB,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,UAAU,EAAE,CAAC,OAAO,EAAE,WAAW,KAAK,WAAW,CAAC;CAC5D;AA+DD;;;;;;;;;;;GAWG;AACH,wBAAgB,cAAc,CAC5B,OAAO,EAAE,OAAO,EAChB,UAAU,EAAE,UAAU,EACtB,KAAK,EAAE,SAAS,QAAQ,EAAE,GACzB,OAAO,CAsCT"}
|
package/dist/decode/rules.js
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
export { ASPECT, PARTICLE_TAG, tagOf, wordEndingAt, wordsEndingAt, wordStartingAt, wordsStartingAt, } from "./edge-context.js";
|
|
1
|
+
export { ASPECT, endsLongerWord, PARTICLE_TAG, startsLongerWord, tagOf, wordEndingAt, wordsEndingAt, wordStartingAt, wordsStartingAt, } from "./edge-context.js";
|
|
2
2
|
/**
|
|
3
3
|
* Whether every position can still be left, and the end still reached.
|
|
4
4
|
*
|
package/dist/decode/rules.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"rules.js","sourceRoot":"","sources":["../../src/decode/rules.ts"],"names":[],"mappings":"AAGA,OAAO,EACL,MAAM,EACN,YAAY,EACZ,KAAK,EACL,YAAY,EACZ,aAAa,EACb,cAAc,EACd,eAAe,GAChB,MAAM,mBAAmB,CAAC;AAsC3B;;;;;;;GAOG;AACH,SAAS,aAAa,CAAC,OAAgB;IACrC,MAAM,MAAM,GAAG,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC;IACzC,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,MAAM,GAAG,CAAC,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC;IAChE,OAAO,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC;IACvB,KAAK,IAAI,EAAE,GAAG,MAAM,GAAG,CAAC,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC;QACxC,0EAA0E;QAC1E,OAAO,CAAC,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,CAC1C,CAAC,IAAI,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,KAAK,CACpC,CAAC;IACJ,CAAC;IACD,qDAAqD;IACrD,OAAO,OAAO,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC;AAC7B,CAAC;AAED;;GAEG;AACH,SAAS,UAAU,CACjB,KAA0B,EAC1B,OAAoB;IAEpB,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,MAAM,OAAO,GAAG,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,CAAC;QACzC,IAAI,OAAO,KAAK,MAAM,EAAE,CAAC;YACvB,OAAO,OAAO,CAAC;QACjB,CAAC;IACH,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED;;;;;;;GAOG;AACH,SAAS,YAAY,CACnB,KAA6B,EAC7B,MAAgC,EAChC,SAA2B;IAE3B,MAAM,OAAO,GAAG,IAAI,GAAG,CACrB,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAChE,CAAC;IACF,KAAK,MAAM,KAAK,IAAI,KAAK,EAAE,CAAC;QAC1B,IAAI,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC;YAChD,SAAS,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;QACvB,CAAC;IACH,CAAC;AACH,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,cAAc,CAC5B,OAAgB,EAChB,UAAsB,EACtB,KAA0B;IAE1B,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,MAAM,SAAS,GAAG,IAAI,GAAG,EAAe,CAAC;IACzC,MAAM,MAAM,GAAG,IAAI,GAAG,EAAe,CAAC;IAEtC,KAAK,MAAM,KAAK,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;QAClC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,MAAM,OAAO,GAAG,UAAU,CAAC,KAAK,EAAE;gBAChC,UAAU;gBACV,UAAU,EAAE,OAAO,CAAC,UAAU;gBAC9B,IAAI;aACL,CAAC,CAAC;YACH,IAAI,OAAO,KAAK,QAAQ,EAAE,CAAC;gBACzB,SAAS,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YACtB,CAAC;iBAAM,IAAI,OAAO,KAAK,OAAO,EAAE,CAAC;gBAC/B,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YACnB,CAAC;QACH,CAAC;IACH,CAAC;IAED,4EAA4E;IAC5E,kEAAkE;IAClE,KAAK,MAAM,KAAK,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;QAClC,YAAY,CAAC,KAAK,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;IACzC,CAAC;IAED,IAAI,SAAS,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;QACzB,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,MAAM,KAAK,GAAY;QACrB,UAAU,EAAE,OAAO,CAAC,UAAU;QAC9B,KAAK,EAAE,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CACjC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,SAAS,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAC7C;KACF,CAAC;IACF,OAAO,aAAa,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,OAAO,CAAC;AAChD,CAAC"}
|
|
1
|
+
{"version":3,"file":"rules.js","sourceRoot":"","sources":["../../src/decode/rules.ts"],"names":[],"mappings":"AAGA,OAAO,EACL,MAAM,EACN,cAAc,EACd,YAAY,EACZ,gBAAgB,EAChB,KAAK,EACL,YAAY,EACZ,aAAa,EACb,cAAc,EACd,eAAe,GAChB,MAAM,mBAAmB,CAAC;AAsC3B;;;;;;;GAOG;AACH,SAAS,aAAa,CAAC,OAAgB;IACrC,MAAM,MAAM,GAAG,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC;IACzC,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,MAAM,GAAG,CAAC,EAAE,EAAE,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC;IAChE,OAAO,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC;IACvB,KAAK,IAAI,EAAE,GAAG,MAAM,GAAG,CAAC,EAAE,EAAE,IAAI,CAAC,EAAE,EAAE,EAAE,EAAE,CAAC;QACxC,0EAA0E;QAC1E,OAAO,CAAC,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,CAC1C,CAAC,IAAI,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,KAAK,CACpC,CAAC;IACJ,CAAC;IACD,qDAAqD;IACrD,OAAO,OAAO,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC;AAC7B,CAAC;AAED;;GAEG;AACH,SAAS,UAAU,CACjB,KAA0B,EAC1B,OAAoB;IAEpB,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,MAAM,OAAO,GAAG,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,CAAC;QACzC,IAAI,OAAO,KAAK,MAAM,EAAE,CAAC;YACvB,OAAO,OAAO,CAAC;QACjB,CAAC;IACH,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED;;;;;;;GAOG;AACH,SAAS,YAAY,CACnB,KAA6B,EAC7B,MAAgC,EAChC,SAA2B;IAE3B,MAAM,OAAO,GAAG,IAAI,GAAG,CACrB,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAChE,CAAC;IACF,KAAK,MAAM,KAAK,IAAI,KAAK,EAAE,CAAC;QAC1B,IAAI,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC;YAChD,SAAS,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC;QACvB,CAAC;IACH,CAAC;AACH,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,cAAc,CAC5B,OAAgB,EAChB,UAAsB,EACtB,KAA0B;IAE1B,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,MAAM,SAAS,GAAG,IAAI,GAAG,EAAe,CAAC;IACzC,MAAM,MAAM,GAAG,IAAI,GAAG,EAAe,CAAC;IAEtC,KAAK,MAAM,KAAK,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;QAClC,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,MAAM,OAAO,GAAG,UAAU,CAAC,KAAK,EAAE;gBAChC,UAAU;gBACV,UAAU,EAAE,OAAO,CAAC,UAAU;gBAC9B,IAAI;aACL,CAAC,CAAC;YACH,IAAI,OAAO,KAAK,QAAQ,EAAE,CAAC;gBACzB,SAAS,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YACtB,CAAC;iBAAM,IAAI,OAAO,KAAK,OAAO,EAAE,CAAC;gBAC/B,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YACnB,CAAC;QACH,CAAC;IACH,CAAC;IAED,4EAA4E;IAC5E,kEAAkE;IAClE,KAAK,MAAM,KAAK,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;QAClC,YAAY,CAAC,KAAK,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;IACzC,CAAC;IAED,IAAI,SAAS,CAAC,IAAI,KAAK,CAAC,EAAE,CAAC;QACzB,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,MAAM,KAAK,GAAY;QACrB,UAAU,EAAE,OAAO,CAAC,UAAU;QAC9B,KAAK,EAAE,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CACjC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,SAAS,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAC7C;KACF,CAAC;IACF,OAAO,aAAa,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,OAAO,CAAC;AAChD,CAAC"}
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
import { type EdgeRule } from "./rules.js";
|
|
2
|
+
/**
|
|
3
|
+
* 的 read `dī` where the taxi word holding it stands, and written whole there.
|
|
4
|
+
*
|
|
5
|
+
* The taxi vocabulary is six keys (的士, 的哥, 的姐, 打的, 面的 and 摩的). The
|
|
6
|
+
* `dī` in them is the only `dī` the dictionary holds, and that reading names
|
|
7
|
+
* the set. All six also spell a modifier, a particle 的 and a head, much the
|
|
8
|
+
* commoner reading of the same characters, and the decode had it both ways at
|
|
9
|
+
* once. 我的哥哥们 came out `wǒ dī gēgē men` on the strength of 的哥, while
|
|
10
|
+
* 的士 came out `dī shì` on the strength of nothing at all.
|
|
11
|
+
*
|
|
12
|
+
* What decides it is what follows the 的, and where the key sits around the 的
|
|
13
|
+
* decides which question that is.
|
|
14
|
+
*
|
|
15
|
+
* A key **beginning** with the 的 offers its own second character as the head.
|
|
16
|
+
* A longer word starting there is the better claim on it. 哥哥 takes the 哥 of
|
|
17
|
+
* 我的哥哥们, 姐姐 the 姐 of 我的姐姐 and 士兵 the 士 of 我的士兵. Nothing
|
|
18
|
+
* starts at the 哥 of 那个的哥 or the 士 of 我要一辆的士, and both keys stand.
|
|
19
|
+
*
|
|
20
|
+
* A key **ending** with the 的 puts the head outside itself, and
|
|
21
|
+
* {@link AFTER_PARTICLE} is what one looks like. The other side is asked as
|
|
22
|
+
* well. A longer word ending at the 的 owns the character in front of it, and
|
|
23
|
+
* that is what 上面的, 方面的 and 表面的 are. Without that test 26 more runs of
|
|
24
|
+
* the corpus change and every one of them is wrong.
|
|
25
|
+
*
|
|
26
|
+
* Where the word does stand the bare 的 is taken out from under it. That is the
|
|
27
|
+
* spacing half of the same claim. 的 sits in the cheapest band the dictionary
|
|
28
|
+
* holds, at 5.62 against a 4.62 floor. A two-character key spanning one is
|
|
29
|
+
* therefore weighed against a split starting several buckets ahead of an
|
|
30
|
+
* ordinary word's, and 的士 came apart at 16.62 against 16.24 for the split
|
|
31
|
+
* where 的哥 at 14.62 held. Forbidding the split is what reaches spacing at
|
|
32
|
+
* all, since forcing an edge only settles the rivals covering the same
|
|
33
|
+
* characters.
|
|
34
|
+
*
|
|
35
|
+
* Measured over the 88,866 lines of Tatoeba and zh.wikipedia, 21 的 read `dī`
|
|
36
|
+
* and 9 of them were the particle. This changes 17 runs. Six are readings it
|
|
37
|
+
* corrects (所打的仗, 谁打的电话, 打的不是很好, 我的哥哥们, 我打的这辆出租车,
|
|
38
|
+
* 见过面的那个人), ten are taxi words that were split and now hold together,
|
|
39
|
+
* and the last is 用一元硬币来打的, which joins up while staying wrong. That
|
|
40
|
+
* one closes a 是⋯的 whose 是 sits in the clause before it, and no local
|
|
41
|
+
* evidence says so. The two others left are the 的哥里 of a transliterated
|
|
42
|
+
* Gori. The gold corpus holds at 3 misses and CPP at 91.49%.
|
|
43
|
+
*/
|
|
44
|
+
export declare const TAXI_DI: EdgeRule;
|
|
45
|
+
//# sourceMappingURL=taxi-rule.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"taxi-rule.d.ts","sourceRoot":"","sources":["../../src/decode/taxi-rule.ts"],"names":[],"mappings":"AAQA,OAAO,EAEL,KAAK,QAAQ,EAKd,MAAM,YAAY,CAAC;AA2EpB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAyCG;AACH,eAAO,MAAM,OAAO,EAAE,QAYrB,CAAC"}
|
|
@@ -0,0 +1,117 @@
|
|
|
1
|
+
import { endsLongerWord, startsLongerWord, tagOf, wordsStartingAt, } from "./rules.js";
|
|
2
|
+
/**
|
|
3
|
+
* Whether a syllable is `dī`, the reading 的 takes in the taxi vocabulary.
|
|
4
|
+
*/
|
|
5
|
+
function isDi(syllable) {
|
|
6
|
+
return (syllable?.initial === "d" && syllable.final === "i" && syllable.tone === 1);
|
|
7
|
+
}
|
|
8
|
+
/**
|
|
9
|
+
* What can follow a 的 that is the structural particle.
|
|
10
|
+
*
|
|
11
|
+
* A noun or a pronoun is the head the particle marks (打的电话, 所打的仗,
|
|
12
|
+
* 见过面的那个人). An adjective or an adverb is the complement, where the 的
|
|
13
|
+
* stands for a 得 (打的不是很好, 打的很好). None of the four can follow a taxi
|
|
14
|
+
* word, which is a verb and its object already.
|
|
15
|
+
*/
|
|
16
|
+
const AFTER_PARTICLE = /^(?:n|r|a|d)/u;
|
|
17
|
+
/**
|
|
18
|
+
* Where the taxi 的 sits in an edge, or undefined for every other edge.
|
|
19
|
+
*/
|
|
20
|
+
function taxiIn(edge) {
|
|
21
|
+
if (edge.to - edge.from !== 2 || edge.reading.length !== 2) {
|
|
22
|
+
return undefined;
|
|
23
|
+
}
|
|
24
|
+
if (edge.text.startsWith("的") && isDi(edge.reading[0])) {
|
|
25
|
+
return edge.from;
|
|
26
|
+
}
|
|
27
|
+
return edge.text.endsWith("的") && isDi(edge.reading[1])
|
|
28
|
+
? edge.from + 1
|
|
29
|
+
: undefined;
|
|
30
|
+
}
|
|
31
|
+
/**
|
|
32
|
+
* Whether the taxi key running from a position holds the 的 inside it.
|
|
33
|
+
*
|
|
34
|
+
* See {@link TAXI_DI} for what the two branches are asking.
|
|
35
|
+
*/
|
|
36
|
+
function holdsTaxi(context, from, di) {
|
|
37
|
+
if (di === from) {
|
|
38
|
+
return !startsLongerWord(context, di + 1);
|
|
39
|
+
}
|
|
40
|
+
return (!endsLongerWord(context, di) &&
|
|
41
|
+
!wordsStartingAt(context, di + 1).some((word) => AFTER_PARTICLE.test(tagOf(context, word))));
|
|
42
|
+
}
|
|
43
|
+
/**
|
|
44
|
+
* Whether a standing taxi key covers the 的 at a position.
|
|
45
|
+
*
|
|
46
|
+
* Both keys are asked about, since the 的 can be either character of one: the
|
|
47
|
+
* 的 of 打的士 opens 的士 and closes 打的.
|
|
48
|
+
*/
|
|
49
|
+
function isUnderTaxi(context, at) {
|
|
50
|
+
const { characters, dictionary } = context;
|
|
51
|
+
for (const from of [at - 1, at]) {
|
|
52
|
+
const key = from < 0 ? "" : characters.slice(from, from + 2).join("");
|
|
53
|
+
const reading = dictionary.lookup(key)?.reading;
|
|
54
|
+
if (reading?.length === 2 &&
|
|
55
|
+
isDi(reading[at - from]) &&
|
|
56
|
+
holdsTaxi(context, from, at)) {
|
|
57
|
+
return true;
|
|
58
|
+
}
|
|
59
|
+
}
|
|
60
|
+
return false;
|
|
61
|
+
}
|
|
62
|
+
/**
|
|
63
|
+
* 的 read `dī` where the taxi word holding it stands, and written whole there.
|
|
64
|
+
*
|
|
65
|
+
* The taxi vocabulary is six keys (的士, 的哥, 的姐, 打的, 面的 and 摩的). The
|
|
66
|
+
* `dī` in them is the only `dī` the dictionary holds, and that reading names
|
|
67
|
+
* the set. All six also spell a modifier, a particle 的 and a head, much the
|
|
68
|
+
* commoner reading of the same characters, and the decode had it both ways at
|
|
69
|
+
* once. 我的哥哥们 came out `wǒ dī gēgē men` on the strength of 的哥, while
|
|
70
|
+
* 的士 came out `dī shì` on the strength of nothing at all.
|
|
71
|
+
*
|
|
72
|
+
* What decides it is what follows the 的, and where the key sits around the 的
|
|
73
|
+
* decides which question that is.
|
|
74
|
+
*
|
|
75
|
+
* A key **beginning** with the 的 offers its own second character as the head.
|
|
76
|
+
* A longer word starting there is the better claim on it. 哥哥 takes the 哥 of
|
|
77
|
+
* 我的哥哥们, 姐姐 the 姐 of 我的姐姐 and 士兵 the 士 of 我的士兵. Nothing
|
|
78
|
+
* starts at the 哥 of 那个的哥 or the 士 of 我要一辆的士, and both keys stand.
|
|
79
|
+
*
|
|
80
|
+
* A key **ending** with the 的 puts the head outside itself, and
|
|
81
|
+
* {@link AFTER_PARTICLE} is what one looks like. The other side is asked as
|
|
82
|
+
* well. A longer word ending at the 的 owns the character in front of it, and
|
|
83
|
+
* that is what 上面的, 方面的 and 表面的 are. Without that test 26 more runs of
|
|
84
|
+
* the corpus change and every one of them is wrong.
|
|
85
|
+
*
|
|
86
|
+
* Where the word does stand the bare 的 is taken out from under it. That is the
|
|
87
|
+
* spacing half of the same claim. 的 sits in the cheapest band the dictionary
|
|
88
|
+
* holds, at 5.62 against a 4.62 floor. A two-character key spanning one is
|
|
89
|
+
* therefore weighed against a split starting several buckets ahead of an
|
|
90
|
+
* ordinary word's, and 的士 came apart at 16.62 against 16.24 for the split
|
|
91
|
+
* where 的哥 at 14.62 held. Forbidding the split is what reaches spacing at
|
|
92
|
+
* all, since forcing an edge only settles the rivals covering the same
|
|
93
|
+
* characters.
|
|
94
|
+
*
|
|
95
|
+
* Measured over the 88,866 lines of Tatoeba and zh.wikipedia, 21 的 read `dī`
|
|
96
|
+
* and 9 of them were the particle. This changes 17 runs. Six are readings it
|
|
97
|
+
* corrects (所打的仗, 谁打的电话, 打的不是很好, 我的哥哥们, 我打的这辆出租车,
|
|
98
|
+
* 见过面的那个人), ten are taxi words that were split and now hold together,
|
|
99
|
+
* and the last is 用一元硬币来打的, which joins up while staying wrong. That
|
|
100
|
+
* one closes a 是⋯的 whose 是 sits in the clause before it, and no local
|
|
101
|
+
* evidence says so. The two others left are the 的哥里 of a transliterated
|
|
102
|
+
* Gori. The gold corpus holds at 3 misses and CPP at 91.49%.
|
|
103
|
+
*/
|
|
104
|
+
export const TAXI_DI = {
|
|
105
|
+
name: "taxi-di",
|
|
106
|
+
verdictFor: (context) => {
|
|
107
|
+
const { edge } = context;
|
|
108
|
+
if (edge.text === "的") {
|
|
109
|
+
return isUnderTaxi(context, edge.from) ? "forbid" : "keep";
|
|
110
|
+
}
|
|
111
|
+
const di = taxiIn(edge);
|
|
112
|
+
return di !== undefined && !holdsTaxi(context, edge.from, di)
|
|
113
|
+
? "forbid"
|
|
114
|
+
: "keep";
|
|
115
|
+
},
|
|
116
|
+
};
|
|
117
|
+
//# sourceMappingURL=taxi-rule.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"taxi-rule.js","sourceRoot":"","sources":["../../src/decode/taxi-rule.ts"],"names":[],"mappings":"AAQA,OAAO,EAGL,cAAc,EACd,gBAAgB,EAChB,KAAK,EACL,eAAe,GAChB,MAAM,YAAY,CAAC;AAEpB;;GAEG;AACH,SAAS,IAAI,CAAC,QAA8B;IAC1C,OAAO,CACL,QAAQ,EAAE,OAAO,KAAK,GAAG,IAAI,QAAQ,CAAC,KAAK,KAAK,GAAG,IAAI,QAAQ,CAAC,IAAI,KAAK,CAAC,CAC3E,CAAC;AACJ,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,cAAc,GAAG,eAAe,CAAC;AAEvC;;GAEG;AACH,SAAS,MAAM,CAAC,IAAyB;IACvC,IAAI,IAAI,CAAC,EAAE,GAAG,IAAI,CAAC,IAAI,KAAK,CAAC,IAAI,IAAI,CAAC,OAAO,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC3D,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,IAAI,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QACvD,OAAO,IAAI,CAAC,IAAI,CAAC;IACnB,CAAC;IACD,OAAO,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC;QACrD,CAAC,CAAC,IAAI,CAAC,IAAI,GAAG,CAAC;QACf,CAAC,CAAC,SAAS,CAAC;AAChB,CAAC;AAED;;;;GAIG;AACH,SAAS,SAAS,CAAC,OAAoB,EAAE,IAAY,EAAE,EAAU;IAC/D,IAAI,EAAE,KAAK,IAAI,EAAE,CAAC;QAChB,OAAO,CAAC,gBAAgB,CAAC,OAAO,EAAE,EAAE,GAAG,CAAC,CAAC,CAAC;IAC5C,CAAC;IACD,OAAO,CACL,CAAC,cAAc,CAAC,OAAO,EAAE,EAAE,CAAC;QAC5B,CAAC,eAAe,CAAC,OAAO,EAAE,EAAE,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAC9C,cAAc,CAAC,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,IAAI,CAAC,CAAC,CAC1C,CACF,CAAC;AACJ,CAAC;AAED;;;;;GAKG;AACH,SAAS,WAAW,CAAC,OAAoB,EAAE,EAAU;IACnD,MAAM,EAAE,UAAU,EAAE,UAAU,EAAE,GAAG,OAAO,CAAC;IAC3C,KAAK,MAAM,IAAI,IAAI,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC;QAChC,MAAM,GAAG,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,CAAC,KAAK,CAAC,IAAI,EAAE,IAAI,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACtE,MAAM,OAAO,GAAG,UAAU,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,OAAO,CAAC;QAChD,IACE,OAAO,EAAE,MAAM,KAAK,CAAC;YACrB,IAAI,CAAC,OAAO,CAAC,EAAE,GAAG,IAAI,CAAC,CAAC;YACxB,SAAS,CAAC,OAAO,EAAE,IAAI,EAAE,EAAE,CAAC,EAC5B,CAAC;YACD,OAAO,IAAI,CAAC;QACd,CAAC;IACH,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAyCG;AACH,MAAM,CAAC,MAAM,OAAO,GAAa;IAC/B,IAAI,EAAE,SAAS;IACf,UAAU,EAAE,CAAC,OAAoB,EAAE,EAAE;QACnC,MAAM,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC;QACzB,IAAI,IAAI,CAAC,IAAI,KAAK,GAAG,EAAE,CAAC;YACtB,OAAO,WAAW,CAAC,OAAO,EAAE,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC;QAC7D,CAAC;QACD,MAAM,EAAE,GAAG,MAAM,CAAC,IAAI,CAAC,CAAC;QACxB,OAAO,EAAE,KAAK,SAAS,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,CAAC,IAAI,EAAE,EAAE,CAAC;YAC3D,CAAC,CAAC,QAAQ;YACV,CAAC,CAAC,MAAM,CAAC;IACb,CAAC;CACF,CAAC"}
|
|
@@ -55,6 +55,20 @@ export declare class Dictionary {
|
|
|
55
55
|
* candidate to learn one number. See {@link FrequencyTable.bucketOf}.
|
|
56
56
|
*/
|
|
57
57
|
frequencyAt(at: number): number;
|
|
58
|
+
/**
|
|
59
|
+
* The frequency bucket of a word under either script, or undefined.
|
|
60
|
+
*
|
|
61
|
+
* What {@link Dictionary.frequencyAt} answers by position, answered by the
|
|
62
|
+
* word itself and off the same search {@link Dictionary.lookup} runs. Ranking
|
|
63
|
+
* a word list against itself is what asks for it, and reading a bucket
|
|
64
|
+
* decodes no entry.
|
|
65
|
+
*
|
|
66
|
+
* Regional 繁體 glyph forms are normalised the way `lookup` normalises them,
|
|
67
|
+
* so 裏面 and 裡面 report alike. A word the dictionary lacks reports
|
|
68
|
+
* undefined. Bucket 0 says something else. The word is a key the corpus
|
|
69
|
+
* never counted, which two thirds of the full tier's keys are.
|
|
70
|
+
*/
|
|
71
|
+
frequencyOf(word: string): number | undefined;
|
|
58
72
|
/**
|
|
59
73
|
* A cursor over every key's reading, in key order.
|
|
60
74
|
*/
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"dictionary.d.ts","sourceRoot":"","sources":["../../src/dictionary/dictionary.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AACxD,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,eAAe,CAAC;AACxD,OAAO,EAAe,KAAK,SAAS,EAAE,MAAM,uBAAuB,CAAC;AACpE,OAAO,EAEL,KAAK,kBAAkB,EAGxB,MAAM,0BAA0B,CAAC;AAKlC,YAAY,EAAE,SAAS,EAAE,MAAM,uBAAuB,CAAC;AACvD,YAAY,EAAE,kBAAkB,EAAE,MAAM,0BAA0B,CAAC;AAEnE;;;;;;;;;;;;;;;;;;GAkBG;AACH,qBAAa,UAAU;;IACrB;;OAEG;IACH,MAAM,CAAC,IAAI,CAAC,QAAQ,EAAE,kBAAkB,GAAG,UAAU,CAEpD;IAOD;;OAEG;IACH,OAAO,eAON;IAED;;OAEG;IACH,IAAI,IAAI,IAAI,MAAM,CAEjB;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,EAAE,EAAE,MAAM,GAAG,MAAM,CAEzB;IAED;;;;;;;OAOG;IACH,WAAW,CAAC,EAAE,EAAE,MAAM,GAAG,MAAM,CAE9B;IAED;;OAEG;IACH,eAAe,IAAI,kBAAkB,CAEpC;IAED;;;;;OAKG;IACH,SAAS,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAE/B;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,IAAI,EAAE,MAAM,GAAG,SAAS,GAAG,SAAS,CAkB1C;IAED;;;;;;;;OAQG;IACH,UAAU,CAAC,SAAS,EAAE,MAAM,GAAG,SAAS,CAAC,SAAS,QAAQ,EAAE,CAAC,EAAE,CAO9D;CACF"}
|
|
1
|
+
{"version":3,"file":"dictionary.d.ts","sourceRoot":"","sources":["../../src/dictionary/dictionary.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AACxD,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,eAAe,CAAC;AACxD,OAAO,EAAe,KAAK,SAAS,EAAE,MAAM,uBAAuB,CAAC;AACpE,OAAO,EAEL,KAAK,kBAAkB,EAGxB,MAAM,0BAA0B,CAAC;AAKlC,YAAY,EAAE,SAAS,EAAE,MAAM,uBAAuB,CAAC;AACvD,YAAY,EAAE,kBAAkB,EAAE,MAAM,0BAA0B,CAAC;AAEnE;;;;;;;;;;;;;;;;;;GAkBG;AACH,qBAAa,UAAU;;IACrB;;OAEG;IACH,MAAM,CAAC,IAAI,CAAC,QAAQ,EAAE,kBAAkB,GAAG,UAAU,CAEpD;IAOD;;OAEG;IACH,OAAO,eAON;IAED;;OAEG;IACH,IAAI,IAAI,IAAI,MAAM,CAEjB;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,EAAE,EAAE,MAAM,GAAG,MAAM,CAEzB;IAED;;;;;;;OAOG;IACH,WAAW,CAAC,EAAE,EAAE,MAAM,GAAG,MAAM,CAE9B;IAED;;;;;;;;;;;;OAYG;IACH,WAAW,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAG5C;IAED;;OAEG;IACH,eAAe,IAAI,kBAAkB,CAEpC;IAED;;;;;OAKG;IACH,SAAS,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAE/B;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,IAAI,EAAE,MAAM,GAAG,SAAS,GAAG,SAAS,CAkB1C;IAED;;;;;;;;OAQG;IACH,UAAU,CAAC,SAAS,EAAE,MAAM,GAAG,SAAS,CAAC,SAAS,QAAQ,EAAE,CAAC,EAAE,CAO9D;CACF"}
|
|
@@ -70,6 +70,23 @@ export class Dictionary {
|
|
|
70
70
|
frequencyAt(at) {
|
|
71
71
|
return this.#frequencies.bucketOf(at);
|
|
72
72
|
}
|
|
73
|
+
/**
|
|
74
|
+
* The frequency bucket of a word under either script, or undefined.
|
|
75
|
+
*
|
|
76
|
+
* What {@link Dictionary.frequencyAt} answers by position, answered by the
|
|
77
|
+
* word itself and off the same search {@link Dictionary.lookup} runs. Ranking
|
|
78
|
+
* a word list against itself is what asks for it, and reading a bucket
|
|
79
|
+
* decodes no entry.
|
|
80
|
+
*
|
|
81
|
+
* Regional 繁體 glyph forms are normalised the way `lookup` normalises them,
|
|
82
|
+
* so 裏面 and 裡面 report alike. A word the dictionary lacks reports
|
|
83
|
+
* undefined. Bucket 0 says something else. The word is a key the corpus
|
|
84
|
+
* never counted, which two thirds of the full tier's keys are.
|
|
85
|
+
*/
|
|
86
|
+
frequencyOf(word) {
|
|
87
|
+
const found = this.#index.lookup(toCanonicalGlyphs(word));
|
|
88
|
+
return found.isKey ? this.#frequencies.bucketOf(found.index) : undefined;
|
|
89
|
+
}
|
|
73
90
|
/**
|
|
74
91
|
* A cursor over every key's reading, in key order.
|
|
75
92
|
*/
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"dictionary.js","sourceRoot":"","sources":["../../src/dictionary/dictionary.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;AAGxD,OAAO,EAAE,WAAW,EAAkB,MAAM,uBAAuB,CAAC;AACpE,OAAO,EACL,iBAAiB,EAEjB,cAAc,EACd,eAAe,GAChB,MAAM,0BAA0B,CAAC;AAClC,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AACtD,OAAO,EAAE,QAAQ,EAAE,MAAM,gBAAgB,CAAC;AAK1C;;;;;;;;;;;;;;;;;;GAkBG;AACH,MAAM,OAAO,UAAU;IACrB;;OAEG;IACH,MAAM,CAAC,IAAI,CAAC,QAA4B;QACtC,OAAO,IAAI,UAAU,CAAC,QAAQ,CAAC,CAAC;IAClC,CAAC;IAEQ,MAAM,CAAW;IACjB,MAAM,CAAa;IACnB,YAAY,CAAiB;IAC7B,QAAQ,GAAG,IAAI,GAAG,EAAqB,CAAC;IAEjD;;OAEG;IACH,YAAoB,QAA4B;QAC9C,IAAI,CAAC,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QAC3C,IAAI,CAAC,MAAM,GAAG,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC;QAChD,IAAI,CAAC,YAAY,GAAG,cAAc,CAAC,IAAI,CACrC,QAAQ,CAAC,WAAW,EACpB,IAAI,CAAC,MAAM,CAAC,IAAI,CACjB,CAAC;IACJ,CAAC;IAED;;OAEG;IACH,IAAI,IAAI;QACN,OAAO,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC;IAC1B,CAAC;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,EAAU;QACf,OAAO,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAC/B,CAAC;IAED;;;;;;;OAOG;IACH,WAAW,CAAC,EAAU;QACpB,OAAO,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC;IACxC,CAAC;IAED;;OAEG;IACH,eAAe;QACb,OAAO,cAAc,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC;IAClD,CAAC;IAED;;;;;OAKG;IACH,SAAS,CAAC,IAAY;QACpB,OAAO,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,iBAAiB,CAAC,IAAI,CAAC,CAAC,CAAC;IACxD,CAAC;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,IAAY;QACjB,MAAM,SAAS,GAAG,iBAAiB,CAAC,IAAI,CAAC,CAAC;QAC1C,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;QAC5C,IAAI,CAAC,KAAK,CAAC,KAAK,EAAE,CAAC;YACjB,OAAO,SAAS,CAAC;QACnB,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;QAC5C,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACvB,OAAO,IAAI,CAAC;QACd,CAAC;QACD,MAAM,KAAK,GAAG,WAAW,CACvB,SAAS,EACT,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,EAClC,CAAC,SAAS,EAAE,EAAE,CAAC,eAAe,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS,CAAC,EACnE,IAAI,CAAC,YAAY,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,CACtC,CAAC;QACF,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACtC,OAAO,KAAK,CAAC;IACf,CAAC;IAED;;;;;;;;OAQG;IACH,UAAU,CAAC,SAAiB;QAC1B,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;QACrC,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,OAAO,EAAE,CAAC;QACZ,CAAC;QACD,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,iBAAiB,CAAC,SAAS,CAAC,CAAC,CAAC;QAC/D,OAAO,CAAC,KAAK,CAAC,OAAO,EAAE,GAAG,iBAAiB,CAAC,IAAI,CAAC,MAAM,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC;IACzE,CAAC;CACF"}
|
|
1
|
+
{"version":3,"file":"dictionary.js","sourceRoot":"","sources":["../../src/dictionary/dictionary.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;AAGxD,OAAO,EAAE,WAAW,EAAkB,MAAM,uBAAuB,CAAC;AACpE,OAAO,EACL,iBAAiB,EAEjB,cAAc,EACd,eAAe,GAChB,MAAM,0BAA0B,CAAC;AAClC,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AACtD,OAAO,EAAE,QAAQ,EAAE,MAAM,gBAAgB,CAAC;AAK1C;;;;;;;;;;;;;;;;;;GAkBG;AACH,MAAM,OAAO,UAAU;IACrB;;OAEG;IACH,MAAM,CAAC,IAAI,CAAC,QAA4B;QACtC,OAAO,IAAI,UAAU,CAAC,QAAQ,CAAC,CAAC;IAClC,CAAC;IAEQ,MAAM,CAAW;IACjB,MAAM,CAAa;IACnB,YAAY,CAAiB;IAC7B,QAAQ,GAAG,IAAI,GAAG,EAAqB,CAAC;IAEjD;;OAEG;IACH,YAAoB,QAA4B;QAC9C,IAAI,CAAC,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC;QAC3C,IAAI,CAAC,MAAM,GAAG,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC;QAChD,IAAI,CAAC,YAAY,GAAG,cAAc,CAAC,IAAI,CACrC,QAAQ,CAAC,WAAW,EACpB,IAAI,CAAC,MAAM,CAAC,IAAI,CACjB,CAAC;IACJ,CAAC;IAED;;OAEG;IACH,IAAI,IAAI;QACN,OAAO,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC;IAC1B,CAAC;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,EAAU;QACf,OAAO,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAC/B,CAAC;IAED;;;;;;;OAOG;IACH,WAAW,CAAC,EAAU;QACpB,OAAO,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAC;IACxC,CAAC;IAED;;;;;;;;;;;;OAYG;IACH,WAAW,CAAC,IAAY;QACtB,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,iBAAiB,CAAC,IAAI,CAAC,CAAC,CAAC;QAC1D,OAAO,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IAC3E,CAAC;IAED;;OAEG;IACH,eAAe;QACb,OAAO,cAAc,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC;IAClD,CAAC;IAED;;;;;OAKG;IACH,SAAS,CAAC,IAAY;QACpB,OAAO,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,iBAAiB,CAAC,IAAI,CAAC,CAAC,CAAC;IACxD,CAAC;IAED;;;;;;;OAOG;IACH,MAAM,CAAC,IAAY;QACjB,MAAM,SAAS,GAAG,iBAAiB,CAAC,IAAI,CAAC,CAAC;QAC1C,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;QAC5C,IAAI,CAAC,KAAK,CAAC,KAAK,EAAE,CAAC;YACjB,OAAO,SAAS,CAAC;QACnB,CAAC;QACD,MAAM,IAAI,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;QAC5C,IAAI,IAAI,KAAK,SAAS,EAAE,CAAC;YACvB,OAAO,IAAI,CAAC;QACd,CAAC;QACD,MAAM,KAAK,GAAG,WAAW,CACvB,SAAS,EACT,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,EAClC,CAAC,SAAS,EAAE,EAAE,CAAC,eAAe,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,SAAS,CAAC,EACnE,IAAI,CAAC,YAAY,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,CACtC,CAAC;QACF,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACtC,OAAO,KAAK,CAAC;IACf,CAAC;IAED;;;;;;;;OAQG;IACH,UAAU,CAAC,SAAiB;QAC1B,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC;QACrC,IAAI,KAAK,KAAK,SAAS,EAAE,CAAC;YACxB,OAAO,EAAE,CAAC;QACZ,CAAC;QACD,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,iBAAiB,CAAC,SAAS,CAAC,CAAC,CAAC;QAC/D,OAAO,CAAC,KAAK,CAAC,OAAO,EAAE,GAAG,iBAAiB,CAAC,IAAI,CAAC,MAAM,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC;IACzE,CAAC;CACF"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"entry-invariants.d.ts","sourceRoot":"","sources":["../../src/dictionary/entry-invariants.ts"],"names":[],"mappings":"AAOA,OAAO,KAAK,EAAE,cAAc,EAAmB,MAAM,uBAAuB,CAAC;AAE7E,eAAO,MAAM,gBAAgB,EAAE,SAAS,cAAc,
|
|
1
|
+
{"version":3,"file":"entry-invariants.d.ts","sourceRoot":"","sources":["../../src/dictionary/entry-invariants.ts"],"names":[],"mappings":"AAOA,OAAO,KAAK,EAAE,cAAc,EAAmB,MAAM,uBAAuB,CAAC;AAE7E,eAAO,MAAM,gBAAgB,EAAE,SAAS,cAAc,EAqGrD,CAAC"}
|
|
@@ -34,6 +34,34 @@ export const ENTRY_INVARIANTS = [
|
|
|
34
34
|
: `no longer proper nouns: ${wrong.join(", ")}`;
|
|
35
35
|
},
|
|
36
36
|
},
|
|
37
|
+
{
|
|
38
|
+
// A capitalised sense that only says `see 長壽區|长寿区` is the district's
|
|
39
|
+
// capital, not the word's. 保安 and 京都 are the control: both hold a
|
|
40
|
+
// lowercase sense too, and both state their proper noun rather than
|
|
41
|
+
// pointing at it.
|
|
42
|
+
description: "长寿, 友谊 and 温泉 are not proper nouns, 保安 and 京都 are",
|
|
43
|
+
check: (dictionary) => {
|
|
44
|
+
const wrong = ["长寿", "友谊", "温泉"].filter((word) => dictionary.get(word)?.isProperNoun === true);
|
|
45
|
+
const missing = ["保安", "京都"].filter((word) => dictionary.get(word)?.isProperNoun !== true);
|
|
46
|
+
if (wrong.length > 0) {
|
|
47
|
+
return `marked as proper nouns: ${wrong.join(", ")}`;
|
|
48
|
+
}
|
|
49
|
+
return missing.length === 0
|
|
50
|
+
? undefined
|
|
51
|
+
: `no longer proper nouns: ${missing.join(", ")}`;
|
|
52
|
+
},
|
|
53
|
+
},
|
|
54
|
+
{
|
|
55
|
+
// Nothing else is left to read where every sense refers on, so the
|
|
56
|
+
// cross-reference is taken at its word. 2,347 flagged keys sit here.
|
|
57
|
+
description: "三亚 and 上饶 stay proper nouns on a cross-reference alone",
|
|
58
|
+
check: (dictionary) => {
|
|
59
|
+
const wrong = ["三亚", "上饶", "三门峡"].filter((word) => dictionary.get(word)?.isProperNoun !== true);
|
|
60
|
+
return wrong.length === 0
|
|
61
|
+
? undefined
|
|
62
|
+
: `no longer proper nouns: ${wrong.join(", ")}`;
|
|
63
|
+
},
|
|
64
|
+
},
|
|
37
65
|
{
|
|
38
66
|
// The gap composeLocaleDeltas closes, and the two ways it must not close
|
|
39
67
|
// it. 運行狀況 contains the marked word 行狀 and cuts elsewhere; 一个个地
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"entry-invariants.js","sourceRoot":"","sources":["../../src/dictionary/entry-invariants.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AACH,OAAO,EAAE,aAAa,EAAE,MAAM,yBAAyB,CAAC;AAGxD,MAAM,CAAC,MAAM,gBAAgB,GAA8B;IACzD;QACE,WAAW,EAAE,iDAAiD;QAC9D,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE,CACzD,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI;YACzC,CAAC,CAAC,SAAS;YACX,CAAC,CAAC,mCAAmC;KAC1C;IACD;QACE,qEAAqE;QACrE,2EAA2E;QAC3E,WAAW,EAAE,wCAAwC;QACrD,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,KAAK,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC,MAAM,CAC3C,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI,CACtD,CAAC;YACF,OAAO,KAAK,CAAC,MAAM,KAAK,CAAC;gBACvB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,2BAA2B,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACpD,CAAC;KACF;IACD;QACE,kEAAkE;QAClE,6DAA6D;QAC7D,WAAW,EAAE,mCAAmC;QAChD,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,KAAK,GAAG,CAAC,KAAK,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC,MAAM,CACvC,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI,CACtD,CAAC;YACF,OAAO,KAAK,CAAC,MAAM,KAAK,CAAC;gBACvB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,2BAA2B,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACpD,CAAC;KACF;IACD;QACE,yEAAyE;QACzE,gEAAgE;QAChE,sEAAsE;QACtE,WAAW,EACT,sDAAsD;QACxD,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,MAAM,GAAG,CAAC,IAAY,EAAsB,EAAE,CAClD,UAAU;iBACP,GAAG,CAAC,IAAI,CAAC;gBACV,EAAE,QAAQ,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC;iBACxD,IAAI,CAAC,GAAG,CAAC,CAAC;YACf,MAAM,QAAQ,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC;YAChC,IAAI,QAAQ,KAAK,eAAe,EAAE,CAAC;gBACjC,OAAO,cAAc,QAAQ,IAAI,SAAS,mCAAmC,CAAC;YAChF,CAAC;YACD,MAAM,KAAK,GAAG,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC,MAAM,CAC3C,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,SAAS,CACrC,CAAC;YACF,OAAO,KAAK,CAAC,MAAM,KAAK,CAAC;gBACvB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,iCAAiC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QAC1D,CAAC;KACF;IACD;QACE,WAAW,EAAE,8BAA8B;QAC3C,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,IAAI,GAAG,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,IAAI,CAAC;YACxC,OAAO,IAAI,KAAK,IAAI;gBAClB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,cAAc,IAAI,IAAI,SAAS,eAAe,CAAC;QACrD,CAAC;KACF;CACF,CAAC"}
|
|
1
|
+
{"version":3,"file":"entry-invariants.js","sourceRoot":"","sources":["../../src/dictionary/entry-invariants.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AACH,OAAO,EAAE,aAAa,EAAE,MAAM,yBAAyB,CAAC;AAGxD,MAAM,CAAC,MAAM,gBAAgB,GAA8B;IACzD;QACE,WAAW,EAAE,iDAAiD;QAC9D,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE,CACzD,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI;YACzC,CAAC,CAAC,SAAS;YACX,CAAC,CAAC,mCAAmC;KAC1C;IACD;QACE,qEAAqE;QACrE,2EAA2E;QAC3E,WAAW,EAAE,wCAAwC;QACrD,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,KAAK,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC,MAAM,CAC3C,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI,CACtD,CAAC;YACF,OAAO,KAAK,CAAC,MAAM,KAAK,CAAC;gBACvB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,2BAA2B,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACpD,CAAC;KACF;IACD;QACE,kEAAkE;QAClE,6DAA6D;QAC7D,WAAW,EAAE,mCAAmC;QAChD,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,KAAK,GAAG,CAAC,KAAK,EAAE,KAAK,EAAE,IAAI,CAAC,CAAC,MAAM,CACvC,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI,CACtD,CAAC;YACF,OAAO,KAAK,CAAC,MAAM,KAAK,CAAC;gBACvB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,2BAA2B,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACpD,CAAC;KACF;IACD;QACE,qEAAqE;QACrE,kEAAkE;QAClE,oEAAoE;QACpE,kBAAkB;QAClB,WAAW,EAAE,mDAAmD;QAChE,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,KAAK,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC,CAAC,MAAM,CACrC,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI,CACtD,CAAC;YACF,MAAM,OAAO,GAAG,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,MAAM,CACjC,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI,CACtD,CAAC;YACF,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACrB,OAAO,2BAA2B,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YACvD,CAAC;YACD,OAAO,OAAO,CAAC,MAAM,KAAK,CAAC;gBACzB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,2BAA2B,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACtD,CAAC;KACF;IACD;QACE,mEAAmE;QACnE,qEAAqE;QACrE,WAAW,EAAE,wDAAwD;QACrE,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,KAAK,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,MAAM,CACtC,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,YAAY,KAAK,IAAI,CACtD,CAAC;YACF,OAAO,KAAK,CAAC,MAAM,KAAK,CAAC;gBACvB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,2BAA2B,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACpD,CAAC;KACF;IACD;QACE,yEAAyE;QACzE,gEAAgE;QAChE,sEAAsE;QACtE,WAAW,EACT,sDAAsD;QACxD,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,MAAM,GAAG,CAAC,IAAY,EAAsB,EAAE,CAClD,UAAU;iBACP,GAAG,CAAC,IAAI,CAAC;gBACV,EAAE,QAAQ,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC;iBACxD,IAAI,CAAC,GAAG,CAAC,CAAC;YACf,MAAM,QAAQ,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC;YAChC,IAAI,QAAQ,KAAK,eAAe,EAAE,CAAC;gBACjC,OAAO,cAAc,QAAQ,IAAI,SAAS,mCAAmC,CAAC;YAChF,CAAC;YACD,MAAM,KAAK,GAAG,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,CAAC,MAAM,CAC3C,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,SAAS,CACrC,CAAC;YACF,OAAO,KAAK,CAAC,MAAM,KAAK,CAAC;gBACvB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,iCAAiC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QAC1D,CAAC;KACF;IACD;QACE,WAAW,EAAE,8BAA8B;QAC3C,KAAK,EAAE,CAAC,UAA2B,EAAsB,EAAE;YACzD,MAAM,IAAI,GAAG,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,IAAI,CAAC;YACxC,OAAO,IAAI,KAAK,IAAI;gBAClB,CAAC,CAAC,SAAS;gBACX,CAAC,CAAC,cAAc,IAAI,IAAI,SAAS,eAAe,CAAC;QACrD,CAAC;KACF;CACF,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"proper-noun.d.ts","sourceRoot":"","sources":["../../src/dictionary/proper-noun.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"proper-noun.d.ts","sourceRoot":"","sources":["../../src/dictionary/proper-noun.ts"],"names":[],"mappings":"AAcA,OAAO,EACL,KAAK,WAAW,EAGjB,MAAM,sBAAsB,CAAC;AAC9B,OAAO,EAAmB,KAAK,UAAU,EAAE,MAAM,qBAAqB,CAAC;AACvE,OAAO,KAAK,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AACxD,OAAO,EAAc,KAAK,aAAa,EAAE,MAAM,gBAAgB,CAAC;AAEhE;;GAEG;AACH,MAAM,WAAW,UAAU;IACzB,QAAQ,CAAC,YAAY,EAAE,OAAO,CAAC;IAC/B,oEAAoE;IACpE,QAAQ,CAAC,UAAU,EAAE,SAAS,MAAM,EAAE,CAAC;IACvC,kEAAkE;IAClE,QAAQ,CAAC,QAAQ,EAAE,OAAO,CAAC;CAC5B;AAED;;;;;;;;;;;;;;;;;;GAkBG;AACH,wBAAgB,YAAY,CAC1B,IAAI,EAAE,MAAM,EACZ,UAAU,EAAE,UAAU,GAAG,SAAS,EAClC,aAAa,EAAE,SAAS,WAAW,EAAE,EACrC,MAAM,EAAE,SAAS,WAAW,EAAE,EAC9B,OAAO,EAAE,SAAS,QAAQ,EAAE,EAC5B,QAAQ,EAAE,aAAa,GACtB,UAAU,CAwBZ"}
|