@mailwoman/query-shape 4.16.1 → 5.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/out/character-class.d.ts +4 -4
- package/out/character-class.d.ts.map +1 -1
- package/out/character-class.js +6 -6
- package/out/character-class.js.map +1 -1
- package/out/compute.d.ts +3 -2
- package/out/compute.d.ts.map +1 -1
- package/out/compute.js +3 -2
- package/out/compute.js.map +1 -1
- package/out/known-formats.d.ts +2 -2
- package/out/known-formats.d.ts.map +1 -1
- package/out/known-formats.js +2 -2
- package/out/known-formats.js.map +1 -1
- package/out/region-abbreviations.d.ts +2 -2
- package/out/region-abbreviations.d.ts.map +1 -1
- package/out/region-abbreviations.js +2 -2
- package/out/region-abbreviations.js.map +1 -1
- package/out/segmentation.d.ts +2 -2
- package/out/segmentation.d.ts.map +1 -1
- package/out/segmentation.js +2 -2
- package/out/segmentation.js.map +1 -1
- package/out/types.d.ts +12 -13
- package/out/types.d.ts.map +1 -1
- package/package.json +6 -6
package/out/character-class.d.ts
CHANGED
|
@@ -9,15 +9,15 @@ export type CodepointClass = TokenCharacterClass | "whitespace" | "connector" |
|
|
|
9
9
|
/** Classify a single Unicode codepoint. */
|
|
10
10
|
export declare function classifyCodepoint(cp: number): CodepointClass;
|
|
11
11
|
/**
|
|
12
|
-
* Classify a token by walking its codepoints and folding to the dominant class. Mixed alphanumeric
|
|
13
|
-
*
|
|
12
|
+
* Classify a token by walking its codepoints and folding to the dominant class. Mixed alphanumeric (e.g. `"221B"`,
|
|
13
|
+
* `"10118-1234"`) returns `"mixed"`. Pure-punct tokens return `"punct"`.
|
|
14
14
|
*/
|
|
15
15
|
export declare function classifyToken(text: string): TokenCharacterClass;
|
|
16
16
|
/** Fold per-token classes into the whole-input character class. */
|
|
17
17
|
export declare function foldInputClass(tokens: ReadonlyArray<TokenClass>): CharacterClass;
|
|
18
18
|
/**
|
|
19
|
-
* Walk a string and emit token spans (whitespace-and-punctuation-separated). Internal helper —
|
|
20
|
-
*
|
|
19
|
+
* Walk a string and emit token spans (whitespace-and-punctuation-separated). Internal helper — callers receive
|
|
20
|
+
* `TokenClass[]` from `computeQueryShape`.
|
|
21
21
|
*/
|
|
22
22
|
export declare function tokenizeForClass(text: string): SpanRange[];
|
|
23
23
|
//# sourceMappingURL=character-class.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"character-class.d.ts","sourceRoot":"","sources":["../character-class.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAE,cAAc,EAAE,SAAS,EAAE,mBAAmB,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;AAE5F,uCAAuC;AACvC,MAAM,MAAM,cAAc,GAAG,mBAAmB,GAAG,YAAY,GAAG,WAAW,GAAG,OAAO,CAAA;
|
|
1
|
+
{"version":3,"file":"character-class.d.ts","sourceRoot":"","sources":["../character-class.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAE,cAAc,EAAE,SAAS,EAAE,mBAAmB,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;AAE5F,uCAAuC;AACvC,MAAM,MAAM,cAAc,GAAG,mBAAmB,GAAG,YAAY,GAAG,WAAW,GAAG,OAAO,CAAA;AAwFvF,2CAA2C;AAC3C,wBAAgB,iBAAiB,CAAC,EAAE,EAAE,MAAM,GAAG,cAAc,CAqB5D;AAED;;;GAGG;AACH,wBAAgB,aAAa,CAAC,IAAI,EAAE,MAAM,GAAG,mBAAmB,CAsD/D;AAED,mEAAmE;AACnE,wBAAgB,cAAc,CAAC,MAAM,EAAE,aAAa,CAAC,UAAU,CAAC,GAAG,cAAc,CAgDhF;AAED;;;GAGG;AACH,wBAAgB,gBAAgB,CAAC,IAAI,EAAE,MAAM,GAAG,SAAS,EAAE,CAwD1D"}
|
package/out/character-class.js
CHANGED
|
@@ -73,8 +73,8 @@ const PUNCT_CODEPOINTS = new Set([
|
|
|
73
73
|
0x3002, // 。 (CJK period)
|
|
74
74
|
]);
|
|
75
75
|
/**
|
|
76
|
-
* "Connector" codepoints join adjacent tokens instead of separating them. Hyphen, apostrophe,
|
|
77
|
-
*
|
|
76
|
+
* "Connector" codepoints join adjacent tokens instead of separating them. Hyphen, apostrophe, underscore — surface in
|
|
77
|
+
* "10118-1234", "O'Brien", "Saint-Denis", and similar.
|
|
78
78
|
*/
|
|
79
79
|
const CONNECTOR_CODEPOINTS = new Set([
|
|
80
80
|
0x2d, // -
|
|
@@ -107,8 +107,8 @@ export function classifyCodepoint(cp) {
|
|
|
107
107
|
return "other";
|
|
108
108
|
}
|
|
109
109
|
/**
|
|
110
|
-
* Classify a token by walking its codepoints and folding to the dominant class. Mixed alphanumeric
|
|
111
|
-
*
|
|
110
|
+
* Classify a token by walking its codepoints and folding to the dominant class. Mixed alphanumeric (e.g. `"221B"`,
|
|
111
|
+
* `"10118-1234"`) returns `"mixed"`. Pure-punct tokens return `"punct"`.
|
|
112
112
|
*/
|
|
113
113
|
export function classifyToken(text) {
|
|
114
114
|
let hasDigit = false;
|
|
@@ -211,8 +211,8 @@ export function foldInputClass(tokens) {
|
|
|
211
211
|
return "mixed";
|
|
212
212
|
}
|
|
213
213
|
/**
|
|
214
|
-
* Walk a string and emit token spans (whitespace-and-punctuation-separated). Internal helper —
|
|
215
|
-
*
|
|
214
|
+
* Walk a string and emit token spans (whitespace-and-punctuation-separated). Internal helper — callers receive
|
|
215
|
+
* `TokenClass[]` from `computeQueryShape`.
|
|
216
216
|
*/
|
|
217
217
|
export function tokenizeForClass(text) {
|
|
218
218
|
const tokens = [];
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"character-class.js","sourceRoot":"","sources":["../character-class.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAOH,MAAM,UAAU,GAAoC;IACnD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;IACxC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,+BAA+B;IACjD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,qCAAqC;IACvD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,yBAAyB;IAC3C,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,KAAK;IACvB,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,mBAAmB;IACrC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,+BAA+B;IACjD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,8BAA8B;IAChD,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,qCAAqC;CACzD,CAAA;AAED,MAAM,eAAe,GAAoC;IACxD,CAAC,MAAM,EAAE,MAAM,CAAC;IAChB,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;IACxC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;IACxC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;CACxC,CAAA;AAED,MAAM,aAAa,GAAoC;IACtD,CAAC,MAAM,EAAE,MAAM,CAAC;IAChB,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,oBAAoB;IACtC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,oBAAoB;IACtC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,8BAA8B;IAChD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,8BAA8B;CAChD,CAAA;AAED,SAAS,OAAO,CAAC,EAAU,EAAE,MAAuC;IACnE,KAAK,MAAM,CAAC,EAAE,EAAE,EAAE,CAAC,IAAI,MAAM,EAAE,CAAC;QAC/B,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE;YAAE,OAAO,IAAI,CAAA;IACtC,CAAC;
|
|
1
|
+
{"version":3,"file":"character-class.js","sourceRoot":"","sources":["../character-class.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAOH,MAAM,UAAU,GAAoC;IACnD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;IACxC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,+BAA+B;IACjD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,qCAAqC;IACvD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,yBAAyB;IAC3C,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,KAAK;IACvB,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,mBAAmB;IACrC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,+BAA+B;IACjD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,8BAA8B;IAChD,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,qCAAqC;CACzD,CAAA;AAED,MAAM,eAAe,GAAoC;IACxD,CAAC,MAAM,EAAE,MAAM,CAAC;IAChB,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;IACxC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;IACxC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,sBAAsB;CACxC,CAAA;AAED,MAAM,aAAa,GAAoC;IACtD,CAAC,MAAM,EAAE,MAAM,CAAC;IAChB,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,oBAAoB;IACtC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,oBAAoB;IACtC,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,8BAA8B;IAChD,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE,8BAA8B;CAChD,CAAA;AAED,SAAS,OAAO,CAAC,EAAU,EAAE,MAAuC;IACnE,KAAK,MAAM,CAAC,EAAE,EAAE,EAAE,CAAC,IAAI,MAAM,EAAE,CAAC;QAC/B,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE;YAAE,OAAO,IAAI,CAAA;IACtC,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAS;IACxC,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,MAAM,EAAE,IAAI;IACZ,MAAM,EAAE,IAAI;IACZ,MAAM,EAAE,IAAI;IACZ,MAAM,EAAE,IAAI;IACZ,MAAM,EAAE,IAAI;IACZ,MAAM,EAAE,IAAI;IACZ,MAAM,EAAE,gBAAgB;IACxB,MAAM,EAAE,iBAAiB;CACzB,CAAC,CAAA;AAEF;;;GAGG;AACH,MAAM,oBAAoB,GAAG,IAAI,GAAG,CAAS;IAC5C,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,IAAI,EAAE,IAAI;IACV,MAAM,EAAE,IAAI;IACZ,MAAM,EAAE,IAAI;CACZ,CAAC,CAAA;AAEF,2CAA2C;AAC3C,MAAM,UAAU,iBAAiB,CAAC,EAAU;IAC3C,IAAI,EAAE,IAAI,IAAI,IAAI,EAAE,IAAI,IAAI;QAAE,OAAO,OAAO,CAAA;IAE5C,IAAI,CAAC,EAAE,IAAI,IAAI,IAAI,EAAE,IAAI,IAAI,CAAC,IAAI,CAAC,EAAE,IAAI,IAAI,IAAI,EAAE,IAAI,IAAI,CAAC;QAAE,OAAO,OAAO,CAAA;IAE5E,uDAAuD;IACvD,IAAI,CAAC,EAAE,IAAI,MAAM,IAAI,EAAE,IAAI,MAAM,CAAC,IAAI,CAAC,EAAE,IAAI,MAAM,IAAI,EAAE,IAAI,MAAM,CAAC;QAAE,OAAO,OAAO,CAAA;IAEpF,IAAI,EAAE,KAAK,IAAI,IAAI,EAAE,KAAK,IAAI,IAAI,EAAE,KAAK,IAAI,IAAI,EAAE,KAAK,IAAI,IAAI,EAAE,KAAK,IAAI;QAAE,OAAO,YAAY,CAAA;IAEhG,IAAI,oBAAoB,CAAC,GAAG,CAAC,EAAE,CAAC;QAAE,OAAO,WAAW,CAAA;IAEpD,IAAI,gBAAgB,CAAC,GAAG,CAAC,EAAE,CAAC;QAAE,OAAO,OAAO,CAAA;IAE5C,IAAI,OAAO,CAAC,EAAE,EAAE,UAAU,CAAC;QAAE,OAAO,KAAK,CAAA;IAEzC,IAAI,OAAO,CAAC,EAAE,EAAE,eAAe,CAAC;QAAE,OAAO,UAAU,CAAA;IAEnD,IAAI,OAAO,CAAC,EAAE,EAAE,aAAa,CAAC;QAAE,OAAO,QAAQ,CAAA;IAE/C,OAAO,OAAO,CAAA;AACf,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,aAAa,CAAC,IAAY;IACzC,IAAI,QAAQ,GAAG,KAAK,CAAA;IACpB,IAAI,QAAQ,GAAG,KAAK,CAAA;IACpB,IAAI,MAAM,GAAG,KAAK,CAAA;IAClB,IAAI,WAAW,GAAG,KAAK,CAAA;IACvB,IAAI,SAAS,GAAG,KAAK,CAAA;IACrB,IAAI,QAAQ,GAAG,KAAK,CAAA;IAEpB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,GAAI,CAAC;QACnC,MAAM,EAAE,GAAG,IAAI,CAAC,WAAW,CAAC,CAAC,CAAE,CAAA;QAC/B,CAAC,IAAI,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;QACxB,MAAM,GAAG,GAAG,iBAAiB,CAAC,EAAE,CAAC,CAAA;QAEjC,QAAQ,GAAG,EAAE,CAAC;YACb,KAAK,OAAO;gBACX,QAAQ,GAAG,IAAI,CAAA;gBACf,MAAK;YACN,KAAK,OAAO;gBACX,QAAQ,GAAG,IAAI,CAAA;gBACf,MAAK;YACN,KAAK,KAAK;gBACT,MAAM,GAAG,IAAI,CAAA;gBACb,MAAK;YACN,KAAK,UAAU;gBACd,WAAW,GAAG,IAAI,CAAA;gBAClB,MAAK;YACN,KAAK,QAAQ;gBACZ,SAAS,GAAG,IAAI,CAAA;gBAChB,MAAK;YACN,KAAK,OAAO;gBACX,QAAQ,GAAG,IAAI,CAAA;gBACf,MAAK;YACN,KAAK,WAAW,CAAC;YACjB,KAAK,YAAY,CAAC;YAClB,KAAK,OAAO;gBACX,MAAK;QACP,CAAC;IACF,CAAC;IAED,IAAI,MAAM;QAAE,OAAO,KAAK,CAAA;IAExB,IAAI,WAAW;QAAE,OAAO,UAAU,CAAA;IAElC,IAAI,SAAS;QAAE,OAAO,QAAQ,CAAA;IAE9B,IAAI,QAAQ,IAAI,QAAQ;QAAE,OAAO,OAAO,CAAA;IAExC,IAAI,QAAQ;QAAE,OAAO,OAAO,CAAA;IAE5B,IAAI,QAAQ;QAAE,OAAO,OAAO,CAAA;IAE5B,IAAI,QAAQ;QAAE,OAAO,OAAO,CAAA;IAE5B,OAAO,OAAO,CAAA;AACf,CAAC;AAED,mEAAmE;AACnE,MAAM,UAAU,cAAc,CAAC,MAAiC;IAC/D,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,OAAO,CAAA;IAEvC,IAAI,QAAQ,GAAG,KAAK,CAAA;IACpB,IAAI,QAAQ,GAAG,KAAK,CAAA;IACpB,IAAI,MAAM,GAAG,KAAK,CAAA;IAClB,IAAI,WAAW,GAAG,KAAK,CAAA;IACvB,IAAI,SAAS,GAAG,KAAK,CAAA;IACrB,IAAI,QAAQ,GAAG,KAAK,CAAA;IAEpB,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;QACxB,QAAQ,CAAC,CAAC,KAAK,EAAE,CAAC;YACjB,KAAK,KAAK;gBACT,MAAM,GAAG,IAAI,CAAA;gBACb,MAAK;YACN,KAAK,UAAU;gBACd,WAAW,GAAG,IAAI,CAAA;gBAClB,MAAK;YACN,KAAK,QAAQ;gBACZ,SAAS,GAAG,IAAI,CAAA;gBAChB,MAAK;YACN,KAAK,OAAO;gBACX,QAAQ,GAAG,IAAI,CAAA;gBACf,MAAK;YACN,KAAK,OAAO;gBACX,QAAQ,GAAG,IAAI,CAAA;gBACf,MAAK;YACN,KAAK,OAAO;gBACX,QAAQ,GAAG,IAAI,CAAA;gBACf,MAAK;QACP,CAAC;IACF,CAAC;IAED,IAAI,MAAM,IAAI,CAAC,QAAQ,IAAI,CAAC,WAAW,IAAI,CAAC,SAAS;QAAE,OAAO,KAAK,CAAA;IAEnE,IAAI,WAAW,IAAI,CAAC,QAAQ,IAAI,CAAC,MAAM,IAAI,CAAC,SAAS;QAAE,OAAO,UAAU,CAAA;IAExE,IAAI,SAAS,IAAI,CAAC,QAAQ,IAAI,CAAC,MAAM,IAAI,CAAC,WAAW;QAAE,OAAO,QAAQ,CAAA;IAEtE,IAAI,MAAM,IAAI,WAAW,IAAI,SAAS;QAAE,OAAO,OAAO,CAAA;IAEtD,IAAI,QAAQ,IAAI,CAAC,QAAQ,IAAI,QAAQ,CAAC;QAAE,OAAO,cAAc,CAAA;IAE7D,IAAI,QAAQ,IAAI,CAAC,QAAQ;QAAE,OAAO,SAAS,CAAA;IAE3C,IAAI,QAAQ,IAAI,CAAC,QAAQ;QAAE,OAAO,OAAO,CAAA;IAEzC,OAAO,OAAO,CAAA;AACf,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,gBAAgB,CAAC,IAAY;IAC5C,MAAM,MAAM,GAAgB,EAAE,CAAA;IAC9B,IAAI,CAAC,GAAG,CAAC,CAAA;IACT,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,CAAA;IAErB,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC;QACd,MAAM,EAAE,GAAG,IAAI,CAAC,WAAW,CAAC,CAAC,CAAE,CAAA;QAC/B,MAAM,GAAG,GAAG,iBAAiB,CAAC,EAAE,CAAC,CAAA;QAEjC,IAAI,GAAG,KAAK,YAAY,IAAI,GAAG,KAAK,OAAO,EAAE,CAAC;YAC7C,CAAC,IAAI,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;YACxB,SAAQ;QACT,CAAC;QAED,+FAA+F;QAC/F,IAAI,GAAG,KAAK,WAAW,EAAE,CAAC;YACzB,CAAC,IAAI,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;YACxB,SAAQ;QACT,CAAC;QAED,iFAAiF;QACjF,iEAAiE;QACjE,MAAM,KAAK,GAAG,CAAC,CAAA;QACf,MAAM,QAAQ,GAAG,GAAG,CAAA;QACpB,IAAI,GAAG,GAAG,CAAC,CAAA;QAEX,OAAO,GAAG,GAAG,CAAC,EAAE,CAAC;YAChB,MAAM,GAAG,GAAG,IAAI,CAAC,WAAW,CAAC,GAAG,CAAE,CAAA;YAClC,MAAM,KAAK,GAAG,GAAG,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;YAClC,MAAM,IAAI,GAAG,iBAAiB,CAAC,GAAG,CAAC,CAAA;YAEnC,IAAI,IAAI,KAAK,YAAY,IAAI,IAAI,KAAK,OAAO;gBAAE,MAAK;YAEpD,IAAI,IAAI,KAAK,WAAW,EAAE,CAAC;gBAC1B,GAAG,IAAI,KAAK,CAAA;gBACZ,SAAQ;YACT,CAAC;YACD,yFAAyF;YACzF,MAAM,WAAW,GAAG,CAAC,CAAiB,EAAE,CAAiB,EAAE,EAAE,CAC5D,CAAC,CAAC,KAAK,OAAO,IAAI,CAAC,KAAK,OAAO,CAAC,IAAI,CAAC,CAAC,KAAK,OAAO,IAAI,CAAC,KAAK,OAAO,CAAC,CAAA;YAErE,IACC,IAAI,KAAK,QAAQ;gBACjB,CAAC,WAAW,CAAC,QAAQ,EAAE,IAAI,CAAC;gBAC5B,CAAC,CAAC,QAAQ,KAAK,OAAO,IAAI,CAAC,IAAI,KAAK,OAAO,IAAI,IAAI,KAAK,OAAO,CAAC,CAAC,EAChE,CAAC;gBACF,MAAK;YACN,CAAC;YACD,GAAG,IAAI,KAAK,CAAA;QACb,CAAC;QAED,MAAM,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,GAAG,EAAE,GAAG,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,CAAC,CAAA;QAC9D,CAAC,GAAG,GAAG,CAAA;IACR,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC"}
|
package/out/compute.d.ts
CHANGED
|
@@ -7,8 +7,9 @@ import type { ComputeQueryShapeOpts, NormalizedInputLite, QueryShape } from "./t
|
|
|
7
7
|
/**
|
|
8
8
|
* Compute a `QueryShape` from a string or normalized input. Microseconds-cheap, pure-function.
|
|
9
9
|
*
|
|
10
|
-
* @example
|
|
11
|
-
* shape
|
|
10
|
+
* @example
|
|
11
|
+
* Const shape = computeQueryShape("350 5th Ave, New York, NY 10118") //
|
|
12
|
+
* shape.knownFormats.find((f) => f.format === "us_zip") → defined // shape.segments.length === 4
|
|
12
13
|
*/
|
|
13
14
|
export declare function computeQueryShape(input: string | NormalizedInputLite, opts?: ComputeQueryShapeOpts): QueryShape;
|
|
14
15
|
//# sourceMappingURL=compute.d.ts.map
|
package/out/compute.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"compute.d.ts","sourceRoot":"","sources":["../compute.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAMH,OAAO,KAAK,EAAE,qBAAqB,EAAE,mBAAmB,EAAE,UAAU,EAAiC,MAAM,YAAY,CAAA;
|
|
1
|
+
{"version":3,"file":"compute.d.ts","sourceRoot":"","sources":["../compute.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAMH,OAAO,KAAK,EAAE,qBAAqB,EAAE,mBAAmB,EAAE,UAAU,EAAiC,MAAM,YAAY,CAAA;AAiCvH;;;;;;GAMG;AACH,wBAAgB,iBAAiB,CAAC,KAAK,EAAE,MAAM,GAAG,mBAAmB,EAAE,IAAI,CAAC,EAAE,qBAAqB,GAAG,UAAU,CA0B/G"}
|
package/out/compute.js
CHANGED
|
@@ -40,8 +40,9 @@ function detectWhitespacePattern(text) {
|
|
|
40
40
|
/**
|
|
41
41
|
* Compute a `QueryShape` from a string or normalized input. Microseconds-cheap, pure-function.
|
|
42
42
|
*
|
|
43
|
-
* @example
|
|
44
|
-
* shape
|
|
43
|
+
* @example
|
|
44
|
+
* Const shape = computeQueryShape("350 5th Ave, New York, NY 10118") //
|
|
45
|
+
* shape.knownFormats.find((f) => f.format === "us_zip") → defined // shape.segments.length === 4
|
|
45
46
|
*/
|
|
46
47
|
export function computeQueryShape(input, opts) {
|
|
47
48
|
const text = typeof input === "string" ? input : input.normalized;
|
package/out/compute.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"compute.js","sourceRoot":"","sources":["../compute.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,gBAAgB,EAAE,MAAM,sBAAsB,CAAA;AACtF,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAA;AACvD,OAAO,EAAE,yBAAyB,EAAE,MAAM,2BAA2B,CAAA;AACrE,OAAO,EAAE,OAAO,EAAE,MAAM,mBAAmB,CAAA;AAG3C,SAAS,uBAAuB,CAAC,IAAY;IAC5C,IAAI,MAAM,GAAG,KAAK,CAAA;IAClB,IAAI,SAAS,GAAG,KAAK,CAAA;IACrB,IAAI,SAAS,GAAG,KAAK,CAAA;IACrB,IAAI,SAAS,GAAG,KAAK,CAAA;
|
|
1
|
+
{"version":3,"file":"compute.js","sourceRoot":"","sources":["../compute.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,gBAAgB,EAAE,MAAM,sBAAsB,CAAA;AACtF,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAA;AACvD,OAAO,EAAE,yBAAyB,EAAE,MAAM,2BAA2B,CAAA;AACrE,OAAO,EAAE,OAAO,EAAE,MAAM,mBAAmB,CAAA;AAG3C,SAAS,uBAAuB,CAAC,IAAY;IAC5C,IAAI,MAAM,GAAG,KAAK,CAAA;IAClB,IAAI,SAAS,GAAG,KAAK,CAAA;IACrB,IAAI,SAAS,GAAG,KAAK,CAAA;IACrB,IAAI,SAAS,GAAG,KAAK,CAAA;IAErB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACtC,MAAM,EAAE,GAAG,IAAI,CAAC,CAAC,CAAC,CAAA;QAElB,IAAI,EAAE,KAAK,IAAI,EAAE,CAAC;YACjB,MAAM,GAAG,IAAI,CAAA;QACd,CAAC;aAAM,IAAI,EAAE,KAAK,GAAG,EAAE,CAAC;YACvB,IAAI,SAAS;gBAAE,SAAS,GAAG,IAAI,CAAA;;gBAC1B,SAAS,GAAG,IAAI,CAAA;YACrB,SAAS,GAAG,IAAI,CAAA;YAChB,SAAQ;QACT,CAAC;QACD,SAAS,GAAG,KAAK,CAAA;IAClB,CAAC;IAED,IAAI,MAAM,IAAI,CAAC,SAAS,IAAI,SAAS,CAAC;QAAE,OAAO,OAAO,CAAA;IAEtD,IAAI,MAAM;QAAE,OAAO,KAAK,CAAA;IAExB,IAAI,SAAS;QAAE,OAAO,QAAQ,CAAA;IAE9B,IAAI,SAAS;QAAE,OAAO,QAAQ,CAAA;IAE9B,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,iBAAiB,CAAC,KAAmC,EAAE,IAA4B;IAClG,MAAM,IAAI,GAAG,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,UAAU,CAAA;IACjE,MAAM,MAAM,GAAG,IAAI,EAAE,MAAM,IAAI,CAAC,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,KAAK,CAAC,aAAa,CAAC,CAAA;IAE5F,MAAM,UAAU,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAA;IACzC,MAAM,YAAY,GAAiB,UAAU,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC;QAC5D,IAAI;QACJ,KAAK,EAAE,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC;QAC/B,MAAM,EAAE,IAAI,CAAC,GAAG,GAAG,IAAI,CAAC,KAAK;KAC7B,CAAC,CAAC,CAAA;IAEH,MAAM,QAAQ,GAAG,OAAO,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;IACtC,MAAM,YAAY,GAAG,kBAAkB,CAAC,IAAI,EAAE,YAAY,CAAC,CAAA;IAC3D,MAAM,mBAAmB,GAAG,yBAAyB,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAC7E,MAAM,cAAc,GAAG,cAAc,CAAC,YAAY,CAAC,CAAA;IACnD,MAAM,iBAAiB,GAAG,uBAAuB,CAAC,IAAI,CAAC,CAAA;IAEvD,OAAO,MAAM,CAAC,MAAM,CAAC;QACpB,cAAc;QACd,YAAY,EAAE,MAAM,CAAC,MAAM,CAAC,YAAY,CAAiB;QACzD,QAAQ,EAAE,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAoB;QACpD,YAAY,EAAE,MAAM,CAAC,MAAM,CAAC,YAAY,CAAwB;QAChE,mBAAmB,EAAE,MAAM,CAAC,MAAM,CAAC,mBAAmB,CAA+B;QACrF,WAAW,EAAE,IAAI,CAAC,MAAM;QACxB,iBAAiB;KACjB,CAAsB,CAAA;AACxB,CAAC"}
|
package/out/known-formats.d.ts
CHANGED
|
@@ -7,8 +7,8 @@ import type { KnownFormatHit, TokenClass } from "./types.js";
|
|
|
7
7
|
/**
|
|
8
8
|
* Detect known-format hits among the tokenized input.
|
|
9
9
|
*
|
|
10
|
-
* Strategy: for each token (or adjacent pair), try every pattern. Multiple format hits on the same
|
|
11
|
-
*
|
|
10
|
+
* Strategy: for each token (or adjacent pair), try every pattern. Multiple format hits on the same span are allowed
|
|
11
|
+
* (US/FR/DE 5-digit ambiguity surfaces all three).
|
|
12
12
|
*/
|
|
13
13
|
export declare function detectKnownFormats(text: string, tokens: ReadonlyArray<TokenClass>): KnownFormatHit[];
|
|
14
14
|
//# sourceMappingURL=known-formats.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"known-formats.d.ts","sourceRoot":"","sources":["../known-formats.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAe,cAAc,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;
|
|
1
|
+
{"version":3,"file":"known-formats.d.ts","sourceRoot":"","sources":["../known-formats.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAe,cAAc,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;AAqCzE;;;;;GAKG;AACH,wBAAgB,kBAAkB,CAAC,IAAI,EAAE,MAAM,EAAE,MAAM,EAAE,aAAa,CAAC,UAAU,CAAC,GAAG,cAAc,EAAE,CA0CpG"}
|
package/out/known-formats.js
CHANGED
|
@@ -23,8 +23,8 @@ const PO_BOX_LEADERS = new Set(["po", "p.o.", "p.o", "box", "bp", "b.p.", "b.p",
|
|
|
23
23
|
/**
|
|
24
24
|
* Detect known-format hits among the tokenized input.
|
|
25
25
|
*
|
|
26
|
-
* Strategy: for each token (or adjacent pair), try every pattern. Multiple format hits on the same
|
|
27
|
-
*
|
|
26
|
+
* Strategy: for each token (or adjacent pair), try every pattern. Multiple format hits on the same span are allowed
|
|
27
|
+
* (US/FR/DE 5-digit ambiguity surfaces all three).
|
|
28
28
|
*/
|
|
29
29
|
export function detectKnownFormats(text, tokens) {
|
|
30
30
|
const hits = [];
|
package/out/known-formats.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"known-formats.js","sourceRoot":"","sources":["../known-formats.ts"],"names":[],"mappings":"AAAA;;;;GAIG;
|
|
1
|
+
{"version":3,"file":"known-formats.js","sourceRoot":"","sources":["../known-formats.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAoBH,MAAM,QAAQ,GAAiC;IAC9C,2CAA2C;IAC3C,EAAE,MAAM,EAAE,SAAS,EAAE,OAAO,EAAE,eAAe,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,IAAI,EAAE;IAC/E,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,0BAA0B,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,IAAI,EAAE;IAC9F,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,eAAe,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,IAAI,EAAE;IACnF,oFAAoF;IACpF,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,mCAAmC,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,GAAG,EAAE;IACtG,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,oCAAoC,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,GAAG,EAAE;IACvG,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,2BAA2B,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,GAAG,EAAE;IAC9F,+FAA+F;IAC/F,oEAAoE;IACpE,EAAE,MAAM,EAAE,QAAQ,EAAE,OAAO,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,GAAG,EAAE;IACvE,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,GAAG,EAAE;IAC5E,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,GAAG,EAAE;IAC5E,yFAAyF;CACzF,CAAA;AAED,MAAM,cAAc,GAAG,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,SAAS,EAAE,UAAU,CAAC,CAAC,CAAA;AAExG;;;;;GAKG;AACH,MAAM,UAAU,kBAAkB,CAAC,IAAY,EAAE,MAAiC;IACjF,MAAM,IAAI,GAAqB,EAAE,CAAA;IAEjC,yBAAyB;IACzB,KAAK,MAAM,GAAG,IAAI,MAAM,EAAE,CAAC;QAC1B,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;YAC1B,IAAI,CAAC,CAAC,SAAS,KAAK,CAAC;gBAAE,SAAQ;YAE/B,IAAI,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;gBACnC,IAAI,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,EAAE,UAAU,EAAE,CAAC,CAAC,UAAU,EAAE,CAAC,CAAA;YAC1E,CAAC;QACF,CAAC;IACF,CAAC;IAED,iDAAiD;IACjD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QAC5C,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;QACnB,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;QAEvB,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC;YAAE,SAAQ;QACtB,MAAM,MAAM,GAAG,GAAG,CAAC,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,CAAC,IAAI,CAAC,IAAI,EAAE,CAAA;QAE9C,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;YAC1B,IAAI,CAAC,CAAC,SAAS,KAAK,CAAC;gBAAE,SAAQ;YAE/B,IAAI,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;gBAC5B,IAAI,CAAC,IAAI,CAAC;oBACT,MAAM,EAAE,CAAC,CAAC,MAAM;oBAChB,IAAI,EAAE,EAAE,KAAK,EAAE,CAAC,CAAC,IAAI,CAAC,KAAK,EAAE,GAAG,EAAE,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE;oBAC1F,UAAU,EAAE,CAAC,CAAC,UAAU;iBACxB,CAAC,CAAA;YACH,CAAC;QACF,CAAC;IACF,CAAC;IAED,4FAA4F;IAC5F,uBAAuB;IACvB,MAAM,KAAK,GAAG,WAAW,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;IAEvC,IAAI,KAAK;QAAE,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IAE3B,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,SAAS,WAAW,CAAC,IAAY,EAAE,MAAiC;IACnE,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,IAAI,CAAA;IAEpC,+DAA+D;IAC/D,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACxC,MAAM,OAAO,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;QAEzB,IAAI,CAAC,OAAO;YAAE,SAAQ;QACtB,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,CAAA;QAE5C,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC;YAAE,SAAQ;QAEvC,0DAA0D;QAC1D,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,WAAW,GAAG,KAAK,CAAA;QAEvB,KAAK,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,EAAE,MAAM,CAAC,MAAM,GAAG,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;YAClE,MAAM,EAAE,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;YAEpB,IAAI,CAAC,EAAE;gBAAE,MAAK;YACd,MAAM,MAAM,GAAG,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,CAAA;YAEzC,IAAI,cAAc,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;gBAChC,IAAI,GAAG,CAAC,CAAA;gBACR,SAAQ;YACT,CAAC;YAED,kDAAkD;YAClD,IAAI,EAAE,CAAC,KAAK,KAAK,OAAO,IAAI,EAAE,CAAC,KAAK,KAAK,OAAO,EAAE,CAAC;gBAClD,IAAI,GAAG,CAAC,CAAA;gBACR,WAAW,GAAG,IAAI,CAAA;gBAClB,MAAK;YACN,CAAC;YACD,MAAK;QACN,CAAC;QAED,IAAI,WAAW,EAAE,CAAC;YACjB,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;YAC1B,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,CAAA;YAE3B,IAAI,CAAC,QAAQ,IAAI,CAAC,MAAM;gBAAE,OAAO,IAAI,CAAA;YACrC,MAAM,KAAK,GAAG,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAA;YACjC,MAAM,GAAG,GAAG,MAAM,CAAC,IAAI,CAAC,GAAG,CAAA;YAE3B,OAAO;gBACN,MAAM,EAAE,QAAQ;gBAChB,IAAI,EAAE,EAAE,KAAK,EAAE,GAAG,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE;gBAClD,UAAU,EAAE,IAAI;aAChB,CAAA;QACF,CAAC;IACF,CAAC;IAED,OAAO,IAAI,CAAA;AACZ,CAAC"}
|
|
@@ -8,8 +8,8 @@
|
|
|
8
8
|
*/
|
|
9
9
|
import type { RegionAbbreviationHit, Segment, TokenClass } from "./types.js";
|
|
10
10
|
/**
|
|
11
|
-
* Find region abbreviation hits. A hit is a 2-letter all-uppercase token that appears after a
|
|
12
|
-
*
|
|
11
|
+
* Find region abbreviation hits. A hit is a 2-letter all-uppercase token that appears after a comma-separated segment
|
|
12
|
+
* boundary — the canonical "City, ST" or "City, ST ZIP" tail pattern.
|
|
13
13
|
*
|
|
14
14
|
* Returns empty array for non-Western locales or inputs without comma segmentation.
|
|
15
15
|
*/
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"region-abbreviations.d.ts","sourceRoot":"","sources":["../region-abbreviations.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,OAAO,KAAK,EAAE,qBAAqB,EAAE,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;AAI5E;;;;;GAKG;AACH,wBAAgB,yBAAyB,CACxC,MAAM,EAAE,aAAa,CAAC,UAAU,CAAC,EACjC,QAAQ,EAAE,aAAa,CAAC,OAAO,CAAC,GAC9B,qBAAqB,EAAE,
|
|
1
|
+
{"version":3,"file":"region-abbreviations.d.ts","sourceRoot":"","sources":["../region-abbreviations.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,OAAO,KAAK,EAAE,qBAAqB,EAAE,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;AAI5E;;;;;GAKG;AACH,wBAAgB,yBAAyB,CACxC,MAAM,EAAE,aAAa,CAAC,UAAU,CAAC,EACjC,QAAQ,EAAE,aAAa,CAAC,OAAO,CAAC,GAC9B,qBAAqB,EAAE,CAoBzB"}
|
|
@@ -8,8 +8,8 @@
|
|
|
8
8
|
*/
|
|
9
9
|
const REGION_ABBREV_RE = /^[A-Z]{2}$/;
|
|
10
10
|
/**
|
|
11
|
-
* Find region abbreviation hits. A hit is a 2-letter all-uppercase token that appears after a
|
|
12
|
-
*
|
|
11
|
+
* Find region abbreviation hits. A hit is a 2-letter all-uppercase token that appears after a comma-separated segment
|
|
12
|
+
* boundary — the canonical "City, ST" or "City, ST ZIP" tail pattern.
|
|
13
13
|
*
|
|
14
14
|
* Returns empty array for non-Western locales or inputs without comma segmentation.
|
|
15
15
|
*/
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"region-abbreviations.js","sourceRoot":"","sources":["../region-abbreviations.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAIH,MAAM,gBAAgB,GAAG,YAAY,CAAA;AAErC;;;;;GAKG;AACH,MAAM,UAAU,yBAAyB,CACxC,MAAiC,EACjC,QAAgC;IAEhC,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,EAAE,CAAA;IAElC,MAAM,IAAI,GAA4B,EAAE,CAAA;IAExC,KAAK,MAAM,GAAG,IAAI,QAAQ,EAAE,CAAC;QAC5B,IAAI,GAAG,CAAC,SAAS,KAAK,OAAO;YAAE,SAAQ;QAEvC,KAAK,MAAM,GAAG,IAAI,MAAM,EAAE,CAAC;YAC1B,IAAI,GAAG,CAAC,IAAI,CAAC,KAAK,GAAG,GAAG,CAAC,IAAI,CAAC,KAAK,IAAI,GAAG,CAAC,IAAI,CAAC,GAAG,GAAG,GAAG,CAAC,IAAI,CAAC,GAAG;gBAAE,SAAQ;
|
|
1
|
+
{"version":3,"file":"region-abbreviations.js","sourceRoot":"","sources":["../region-abbreviations.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAIH,MAAM,gBAAgB,GAAG,YAAY,CAAA;AAErC;;;;;GAKG;AACH,MAAM,UAAU,yBAAyB,CACxC,MAAiC,EACjC,QAAgC;IAEhC,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC;QAAE,OAAO,EAAE,CAAA;IAElC,MAAM,IAAI,GAA4B,EAAE,CAAA;IAExC,KAAK,MAAM,GAAG,IAAI,QAAQ,EAAE,CAAC;QAC5B,IAAI,GAAG,CAAC,SAAS,KAAK,OAAO;YAAE,SAAQ;QAEvC,KAAK,MAAM,GAAG,IAAI,MAAM,EAAE,CAAC;YAC1B,IAAI,GAAG,CAAC,IAAI,CAAC,KAAK,GAAG,GAAG,CAAC,IAAI,CAAC,KAAK,IAAI,GAAG,CAAC,IAAI,CAAC,GAAG,GAAG,GAAG,CAAC,IAAI,CAAC,GAAG;gBAAE,SAAQ;YAE5E,IAAI,GAAG,CAAC,KAAK,KAAK,OAAO;gBAAE,SAAQ;YAEnC,IAAI,CAAC,gBAAgB,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC;gBAAE,SAAQ;YAEnD,IAAI,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,GAAG,CAAC,IAAI,CAAC,KAAK,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAA;QAC1D,CAAC;IACF,CAAC;IAED,OAAO,IAAI,CAAA;AACZ,CAAC"}
|
package/out/segmentation.d.ts
CHANGED
|
@@ -5,8 +5,8 @@
|
|
|
5
5
|
*/
|
|
6
6
|
import type { Segment } from "./types.js";
|
|
7
7
|
/**
|
|
8
|
-
* Comma / newline / tab separate segments. Locale-aware grammar reserved for future (JP whitespace,
|
|
9
|
-
*
|
|
8
|
+
* Comma / newline / tab separate segments. Locale-aware grammar reserved for future (JP whitespace, KR honorifics).
|
|
9
|
+
* Default rules apply when no locale-specific override exists.
|
|
10
10
|
*/
|
|
11
11
|
export declare function segment(text: string, _locale?: string): Segment[];
|
|
12
12
|
//# sourceMappingURL=segmentation.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"segmentation.d.ts","sourceRoot":"","sources":["../segmentation.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAE,OAAO,EAAoB,MAAM,YAAY,CAAA;AAE3D;;;GAGG;AACH,wBAAgB,OAAO,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,MAAM,GAAG,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"segmentation.d.ts","sourceRoot":"","sources":["../segmentation.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAE,OAAO,EAAoB,MAAM,YAAY,CAAA;AAE3D;;;GAGG;AACH,wBAAgB,OAAO,CAAC,IAAI,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,MAAM,GAAG,OAAO,EAAE,CAiDjE"}
|
package/out/segmentation.js
CHANGED
|
@@ -4,8 +4,8 @@
|
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*/
|
|
6
6
|
/**
|
|
7
|
-
* Comma / newline / tab separate segments. Locale-aware grammar reserved for future (JP whitespace,
|
|
8
|
-
*
|
|
7
|
+
* Comma / newline / tab separate segments. Locale-aware grammar reserved for future (JP whitespace, KR honorifics).
|
|
8
|
+
* Default rules apply when no locale-specific override exists.
|
|
9
9
|
*/
|
|
10
10
|
export function segment(text, _locale) {
|
|
11
11
|
const segments = [];
|
package/out/segmentation.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"segmentation.js","sourceRoot":"","sources":["../segmentation.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAIH;;;GAGG;AACH,MAAM,UAAU,OAAO,CAAC,IAAY,EAAE,OAAgB;IACrD,MAAM,QAAQ,GAAc,EAAE,CAAA;
|
|
1
|
+
{"version":3,"file":"segmentation.js","sourceRoot":"","sources":["../segmentation.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAIH;;;GAGG;AACH,MAAM,UAAU,OAAO,CAAC,IAAY,EAAE,OAAgB;IACrD,MAAM,QAAQ,GAAc,EAAE,CAAA;IAE9B,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,QAAQ,CAAA;IAEtC,IAAI,KAAK,GAAG,CAAC,CAAA;IACb,IAAI,aAAa,GAAqB,IAAI,CAAA;IAC1C,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,MAAM,KAAK,GAAG,CAAC,GAAW,EAAE,SAA2B,EAAE,EAAE;QAC1D,qFAAqF;QACrF,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,KAAK,EAAE,GAAG,CAAC,CAAA;QAClC,MAAM,OAAO,GAAG,GAAG,CAAC,KAAK,CAAC,MAAM,CAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;QAC5C,MAAM,QAAQ,GAAG,GAAG,CAAC,KAAK,CAAC,MAAM,CAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;QAC7C,MAAM,UAAU,GAAG,KAAK,GAAG,OAAO,CAAA;QAClC,MAAM,QAAQ,GAAG,GAAG,GAAG,QAAQ,CAAA;QAE/B,IAAI,QAAQ,GAAG,UAAU,EAAE,CAAC;YAC3B,QAAQ,CAAC,IAAI,CAAC;gBACb,IAAI,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,GAAG,EAAE,QAAQ,EAAE,IAAI,EAAE,IAAI,CAAC,KAAK,CAAC,UAAU,EAAE,QAAQ,CAAC,EAAE;gBAClF,IAAI,EAAE,IAAI,CAAC,KAAK,CAAC,UAAU,EAAE,QAAQ,CAAC;gBACtC,KAAK;gBACL,SAAS,EAAE,aAAa;aACxB,CAAC,CAAA;YACF,KAAK,IAAI,CAAC,CAAA;QACX,CAAC;QACD,aAAa,GAAG,SAAS,CAAA;IAC1B,CAAC,CAAA;IAED,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACtC,MAAM,EAAE,GAAG,IAAI,CAAC,CAAC,CAAC,CAAA;QAElB,IAAI,EAAE,KAAK,GAAG,EAAE,CAAC;YAChB,KAAK,CAAC,CAAC,EAAE,OAAO,CAAC,CAAA;YACjB,KAAK,GAAG,CAAC,GAAG,CAAC,CAAA;QACd,CAAC;aAAM,IAAI,EAAE,KAAK,IAAI,EAAE,CAAC;YACxB,KAAK,CAAC,CAAC,EAAE,SAAS,CAAC,CAAA;YACnB,KAAK,GAAG,CAAC,GAAG,CAAC,CAAA;QACd,CAAC;aAAM,IAAI,EAAE,KAAK,IAAI,EAAE,CAAC;YACxB,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAA;YACf,KAAK,GAAG,CAAC,GAAG,CAAC,CAAA;QACd,CAAC;aAAM,IAAI,EAAE,KAAK,GAAG,EAAE,CAAC;YACvB,KAAK,CAAC,CAAC,EAAE,OAAO,CAAC,CAAA,CAAC,wCAAwC;YAC1D,KAAK,GAAG,CAAC,GAAG,CAAC,CAAA;QACd,CAAC;IACF,CAAC;IACD,KAAK,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,CAAA;IAExB,OAAO,QAAQ,CAAA;AAChB,CAAC"}
|
package/out/types.d.ts
CHANGED
|
@@ -4,8 +4,8 @@
|
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*/
|
|
6
6
|
/**
|
|
7
|
-
* Minimal character-range descriptor used internally. Compatible with `@mailwoman/core`'s `Span`
|
|
8
|
-
*
|
|
7
|
+
* Minimal character-range descriptor used internally. Compatible with `@mailwoman/core`'s `Span` class by shape —
|
|
8
|
+
* consumers holding a `Span` can pass it where `SpanRange` is expected.
|
|
9
9
|
*/
|
|
10
10
|
export interface SpanRange {
|
|
11
11
|
start: number;
|
|
@@ -42,8 +42,8 @@ export interface KnownFormatHit {
|
|
|
42
42
|
confidence: number;
|
|
43
43
|
}
|
|
44
44
|
/**
|
|
45
|
-
* A detected region abbreviation (e.g., "DC", "NY", "CA"). Used by the locality soft prior to bias
|
|
46
|
-
*
|
|
45
|
+
* A detected region abbreviation (e.g., "DC", "NY", "CA"). Used by the locality soft prior to bias preceding place-name
|
|
46
|
+
* tokens toward `B-locality`.
|
|
47
47
|
*/
|
|
48
48
|
export interface RegionAbbreviationHit {
|
|
49
49
|
/** Character offset into the normalized input. */
|
|
@@ -52,12 +52,11 @@ export interface RegionAbbreviationHit {
|
|
|
52
52
|
span: string;
|
|
53
53
|
}
|
|
54
54
|
/**
|
|
55
|
-
* Structural snapshot of an input string, computed once at the boundary between Stage 1 and Stage 2
|
|
56
|
-
*
|
|
57
|
-
* additional context.
|
|
55
|
+
* Structural snapshot of an input string, computed once at the boundary between Stage 1 and Stage 2 of the runtime
|
|
56
|
+
* pipeline. Microseconds-cheap. Consumed by stages 2, 2.5, 3 (optional), and 6 as additional context.
|
|
58
57
|
*
|
|
59
|
-
* Bitter-lesson-safe: recognizes universal structural patterns (character class, punctuation,
|
|
60
|
-
*
|
|
58
|
+
* Bitter-lesson-safe: recognizes universal structural patterns (character class, punctuation, postcode shape) rather
|
|
59
|
+
* than place-specific knowledge.
|
|
61
60
|
*/
|
|
62
61
|
export interface QueryShape {
|
|
63
62
|
characterClass: CharacterClass;
|
|
@@ -65,16 +64,16 @@ export interface QueryShape {
|
|
|
65
64
|
segments: Segment[];
|
|
66
65
|
knownFormats: KnownFormatHit[];
|
|
67
66
|
/**
|
|
68
|
-
* Region abbreviation hits detected in the input. The locality soft prior uses these to bias
|
|
69
|
-
*
|
|
67
|
+
* Region abbreviation hits detected in the input. The locality soft prior uses these to bias preceding place-name
|
|
68
|
+
* tokens toward `B-locality` / `I-locality` during Viterbi decoding.
|
|
70
69
|
*/
|
|
71
70
|
regionAbbreviations: RegionAbbreviationHit[];
|
|
72
71
|
totalLength: number;
|
|
73
72
|
whitespacePattern: WhitespacePattern;
|
|
74
73
|
}
|
|
75
74
|
/**
|
|
76
|
-
* Minimal shape that satisfies `computeQueryShape`'s input contract. The full `NormalizedInput`
|
|
77
|
-
*
|
|
75
|
+
* Minimal shape that satisfies `computeQueryShape`'s input contract. The full `NormalizedInput` from
|
|
76
|
+
* `@mailwoman/normalize` is structurally compatible — no import required.
|
|
78
77
|
*/
|
|
79
78
|
export interface NormalizedInputLite {
|
|
80
79
|
normalized: string;
|
package/out/types.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../types.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH;;;GAGG;AACH,MAAM,WAAW,SAAS;IACzB,KAAK,EAAE,MAAM,CAAA;IACb,GAAG,EAAE,MAAM,CAAA;IACX,IAAI,EAAE,MAAM,CAAA;CACZ;AAED,0CAA0C;AAC1C,MAAM,MAAM,mBAAmB,GAAG,OAAO,GAAG,OAAO,GAAG,OAAO,GAAG,OAAO,GAAG,KAAK,GAAG,UAAU,GAAG,QAAQ,CAAA;AAEvG,uEAAuE;AACvE,MAAM,MAAM,cAAc,GAAG,SAAS,GAAG,OAAO,GAAG,cAAc,GAAG,KAAK,GAAG,UAAU,GAAG,QAAQ,GAAG,OAAO,CAAA;AAE3G,2EAA2E;AAC3E,MAAM,MAAM,WAAW,GACpB,QAAQ,GACR,SAAS,GACT,aAAa,GACb,aAAa,GACb,aAAa,GACb,aAAa,GACb,aAAa,GACb,QAAQ,CAAA;AAEX,kEAAkE;AAClE,MAAM,MAAM,gBAAgB,GAAG,OAAO,GAAG,SAAS,GAAG,KAAK,GAAG,YAAY,GAAG,gBAAgB,GAAG,IAAI,CAAA;AAEnG,6CAA6C;AAC7C,MAAM,MAAM,iBAAiB,GAAG,QAAQ,GAAG,QAAQ,GAAG,KAAK,GAAG,OAAO,GAAG,MAAM,CAAA;AAE9E,MAAM,WAAW,UAAU;IAC1B,IAAI,EAAE,SAAS,CAAA;IACf,KAAK,EAAE,mBAAmB,CAAA;IAC1B,MAAM,EAAE,MAAM,CAAA;CACd;AAED,MAAM,WAAW,OAAO;IACvB,IAAI,EAAE,SAAS,CAAA;IACf,IAAI,EAAE,MAAM,CAAA;IACZ,+CAA+C;IAC/C,KAAK,EAAE,MAAM,CAAA;IACb,iFAAiF;IACjF,SAAS,EAAE,gBAAgB,CAAA;CAC3B;AAED,MAAM,WAAW,cAAc;IAC9B,MAAM,EAAE,WAAW,CAAA;IACnB,IAAI,EAAE,SAAS,CAAA;IACf,gGAAgG;IAChG,UAAU,EAAE,MAAM,CAAA;CAClB;AAED;;;GAGG;AACH,MAAM,WAAW,qBAAqB;IACrC,kDAAkD;IAClD,KAAK,EAAE,MAAM,CAAA;IACb,gDAAgD;IAChD,IAAI,EAAE,MAAM,CAAA;CACZ;AAED
|
|
1
|
+
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../types.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH;;;GAGG;AACH,MAAM,WAAW,SAAS;IACzB,KAAK,EAAE,MAAM,CAAA;IACb,GAAG,EAAE,MAAM,CAAA;IACX,IAAI,EAAE,MAAM,CAAA;CACZ;AAED,0CAA0C;AAC1C,MAAM,MAAM,mBAAmB,GAAG,OAAO,GAAG,OAAO,GAAG,OAAO,GAAG,OAAO,GAAG,KAAK,GAAG,UAAU,GAAG,QAAQ,CAAA;AAEvG,uEAAuE;AACvE,MAAM,MAAM,cAAc,GAAG,SAAS,GAAG,OAAO,GAAG,cAAc,GAAG,KAAK,GAAG,UAAU,GAAG,QAAQ,GAAG,OAAO,CAAA;AAE3G,2EAA2E;AAC3E,MAAM,MAAM,WAAW,GACpB,QAAQ,GACR,SAAS,GACT,aAAa,GACb,aAAa,GACb,aAAa,GACb,aAAa,GACb,aAAa,GACb,QAAQ,CAAA;AAEX,kEAAkE;AAClE,MAAM,MAAM,gBAAgB,GAAG,OAAO,GAAG,SAAS,GAAG,KAAK,GAAG,YAAY,GAAG,gBAAgB,GAAG,IAAI,CAAA;AAEnG,6CAA6C;AAC7C,MAAM,MAAM,iBAAiB,GAAG,QAAQ,GAAG,QAAQ,GAAG,KAAK,GAAG,OAAO,GAAG,MAAM,CAAA;AAE9E,MAAM,WAAW,UAAU;IAC1B,IAAI,EAAE,SAAS,CAAA;IACf,KAAK,EAAE,mBAAmB,CAAA;IAC1B,MAAM,EAAE,MAAM,CAAA;CACd;AAED,MAAM,WAAW,OAAO;IACvB,IAAI,EAAE,SAAS,CAAA;IACf,IAAI,EAAE,MAAM,CAAA;IACZ,+CAA+C;IAC/C,KAAK,EAAE,MAAM,CAAA;IACb,iFAAiF;IACjF,SAAS,EAAE,gBAAgB,CAAA;CAC3B;AAED,MAAM,WAAW,cAAc;IAC9B,MAAM,EAAE,WAAW,CAAA;IACnB,IAAI,EAAE,SAAS,CAAA;IACf,gGAAgG;IAChG,UAAU,EAAE,MAAM,CAAA;CAClB;AAED;;;GAGG;AACH,MAAM,WAAW,qBAAqB;IACrC,kDAAkD;IAClD,KAAK,EAAE,MAAM,CAAA;IACb,gDAAgD;IAChD,IAAI,EAAE,MAAM,CAAA;CACZ;AAED;;;;;;GAMG;AACH,MAAM,WAAW,UAAU;IAC1B,cAAc,EAAE,cAAc,CAAA;IAC9B,YAAY,EAAE,UAAU,EAAE,CAAA;IAC1B,QAAQ,EAAE,OAAO,EAAE,CAAA;IACnB,YAAY,EAAE,cAAc,EAAE,CAAA;IAC9B;;;OAGG;IACH,mBAAmB,EAAE,qBAAqB,EAAE,CAAA;IAC5C,WAAW,EAAE,MAAM,CAAA;IACnB,iBAAiB,EAAE,iBAAiB,CAAA;CACpC;AAED;;;GAGG;AACH,MAAM,WAAW,mBAAmB;IACnC,UAAU,EAAE,MAAM,CAAA;IAClB,aAAa,CAAC,EAAE,MAAM,CAAA;CACtB;AAED,MAAM,WAAW,qBAAqB;IACrC,2EAA2E;IAC3E,MAAM,CAAC,EAAE,MAAM,CAAA;CACf"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@mailwoman/query-shape",
|
|
3
|
-
"version": "
|
|
3
|
+
"version": "5.0.0",
|
|
4
4
|
"description": "Cheap structural priors for the runtime pipeline: character class, segmentation, known-format detection. Pure functions, no ML.",
|
|
5
5
|
"license": "AGPL-3.0-only",
|
|
6
6
|
"repository": {
|
|
@@ -8,17 +8,17 @@
|
|
|
8
8
|
"url": "https://github.com/sister-software/mailwoman.git",
|
|
9
9
|
"directory": "query-shape"
|
|
10
10
|
},
|
|
11
|
-
"type": "module",
|
|
12
|
-
"exports": {
|
|
13
|
-
"./package.json": "./package.json",
|
|
14
|
-
".": "./out/index.js"
|
|
15
|
-
},
|
|
16
11
|
"files": [
|
|
17
12
|
"out/**/*.js",
|
|
18
13
|
"out/**/*.js.map",
|
|
19
14
|
"out/**/*.d.ts",
|
|
20
15
|
"out/**/*.d.ts.map"
|
|
21
16
|
],
|
|
17
|
+
"type": "module",
|
|
18
|
+
"exports": {
|
|
19
|
+
"./package.json": "./package.json",
|
|
20
|
+
".": "./out/index.js"
|
|
21
|
+
},
|
|
22
22
|
"publishConfig": {
|
|
23
23
|
"access": "public"
|
|
24
24
|
}
|