@stll/anonymize-wasm 1.4.0 → 1.4.1
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/dist/address-street-types.mjs +20 -1
- package/dist/allow-list.mjs +12 -0
- package/dist/amount-words.mjs +472 -36
- package/dist/generic-roles.mjs +1 -0
- package/dist/rolldown-runtime.mjs +13 -0
- package/dist/structural-single-cap-prefixes.mjs +99 -0
- package/dist/structural-single-cap-prefixes.mjs.map +1 -0
- package/dist/triggers.en.mjs +16 -1
- package/dist/wasm.d.mts +11 -1
- package/dist/wasm.mjs +712 -102
- package/dist/wasm.mjs.map +1 -1
- package/package.json +1 -1
|
@@ -0,0 +1,99 @@
|
|
|
1
|
+
//#region src/data/structural-single-cap-prefixes.json
|
|
2
|
+
var _comment = "Structural document-unit words that can precede a single-letter or letter-number marker before a legal form word, e.g. 'Schedule A LLC Members' or 'Exhibit A-1 LLC Agreement'. Lowercased; matched case-insensitively. Organised per-language; runtime unions all languages because match spans do not carry a language tag.";
|
|
3
|
+
var en = [
|
|
4
|
+
"annex",
|
|
5
|
+
"appendix",
|
|
6
|
+
"article",
|
|
7
|
+
"attachment",
|
|
8
|
+
"clause",
|
|
9
|
+
"exhibit",
|
|
10
|
+
"paragraph",
|
|
11
|
+
"part",
|
|
12
|
+
"schedule",
|
|
13
|
+
"section"
|
|
14
|
+
];
|
|
15
|
+
var cs = [
|
|
16
|
+
"bod",
|
|
17
|
+
"paragraf",
|
|
18
|
+
"podbod",
|
|
19
|
+
"ustanovení",
|
|
20
|
+
"článek"
|
|
21
|
+
];
|
|
22
|
+
var sk = [
|
|
23
|
+
"bod",
|
|
24
|
+
"hlava",
|
|
25
|
+
"oddiel",
|
|
26
|
+
"odsek",
|
|
27
|
+
"pododdiel",
|
|
28
|
+
"sekcia",
|
|
29
|
+
"časť",
|
|
30
|
+
"článok"
|
|
31
|
+
];
|
|
32
|
+
var de = [
|
|
33
|
+
"absatz",
|
|
34
|
+
"abschnitt",
|
|
35
|
+
"abteilung",
|
|
36
|
+
"anlage",
|
|
37
|
+
"anhang",
|
|
38
|
+
"artikel",
|
|
39
|
+
"kapitel",
|
|
40
|
+
"klausel",
|
|
41
|
+
"punkt",
|
|
42
|
+
"sektion",
|
|
43
|
+
"unterabschnitt",
|
|
44
|
+
"unterpunkt"
|
|
45
|
+
];
|
|
46
|
+
var es = [
|
|
47
|
+
"anexo",
|
|
48
|
+
"apartado",
|
|
49
|
+
"artículo",
|
|
50
|
+
"cláusula",
|
|
51
|
+
"sección"
|
|
52
|
+
];
|
|
53
|
+
var fr = [
|
|
54
|
+
"annexe",
|
|
55
|
+
"article",
|
|
56
|
+
"clause",
|
|
57
|
+
"paragraphe",
|
|
58
|
+
"partie",
|
|
59
|
+
"section"
|
|
60
|
+
];
|
|
61
|
+
var it = [
|
|
62
|
+
"allegato",
|
|
63
|
+
"appendice",
|
|
64
|
+
"articolo",
|
|
65
|
+
"clausola",
|
|
66
|
+
"paragrafo",
|
|
67
|
+
"sezione"
|
|
68
|
+
];
|
|
69
|
+
var pl = [
|
|
70
|
+
"aneksem",
|
|
71
|
+
"artykuł",
|
|
72
|
+
"paragraf",
|
|
73
|
+
"punkt",
|
|
74
|
+
"sekcja",
|
|
75
|
+
"załącznik"
|
|
76
|
+
];
|
|
77
|
+
var pt_br = [
|
|
78
|
+
"anexo",
|
|
79
|
+
"artigo",
|
|
80
|
+
"cláusula",
|
|
81
|
+
"parágrafo",
|
|
82
|
+
"seção"
|
|
83
|
+
];
|
|
84
|
+
var structural_single_cap_prefixes_default = {
|
|
85
|
+
_comment,
|
|
86
|
+
en,
|
|
87
|
+
cs,
|
|
88
|
+
sk,
|
|
89
|
+
de,
|
|
90
|
+
es,
|
|
91
|
+
fr,
|
|
92
|
+
it,
|
|
93
|
+
pl,
|
|
94
|
+
"pt-br": pt_br
|
|
95
|
+
};
|
|
96
|
+
//#endregion
|
|
97
|
+
export { _comment, cs, de, structural_single_cap_prefixes_default as default, en, es, fr, it, pl, pt_br as "pt-br", sk };
|
|
98
|
+
|
|
99
|
+
//# sourceMappingURL=structural-single-cap-prefixes.mjs.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"structural-single-cap-prefixes.mjs","names":[],"sources":["../../src/data/structural-single-cap-prefixes.json"],"sourcesContent":[""],"mappings":""}
|
package/dist/triggers.en.mjs
CHANGED
|
@@ -33,7 +33,22 @@ var triggers_en_default = [
|
|
|
33
33
|
{
|
|
34
34
|
"id": "en-jurisdiction",
|
|
35
35
|
"label": "address",
|
|
36
|
-
"strategy": {
|
|
36
|
+
"strategy": {
|
|
37
|
+
"type": "to-next-comma",
|
|
38
|
+
"maxLength": 30,
|
|
39
|
+
"stopWords": [
|
|
40
|
+
"or",
|
|
41
|
+
"and",
|
|
42
|
+
"in",
|
|
43
|
+
"sitting",
|
|
44
|
+
"shall",
|
|
45
|
+
"that",
|
|
46
|
+
"which",
|
|
47
|
+
"without",
|
|
48
|
+
"for",
|
|
49
|
+
"to"
|
|
50
|
+
]
|
|
51
|
+
},
|
|
37
52
|
"triggers": [
|
|
38
53
|
"State of",
|
|
39
54
|
"Commonwealth of",
|
package/dist/wasm.d.mts
CHANGED
|
@@ -15,7 +15,7 @@ type Entity = {
|
|
|
15
15
|
text: string;
|
|
16
16
|
score: number;
|
|
17
17
|
source: DetectionSource;
|
|
18
|
-
sourceDetail?: "custom-deny-list" | "custom-regex";
|
|
18
|
+
sourceDetail?: "custom-deny-list" | "custom-regex" | "gazetteer-extension";
|
|
19
19
|
};
|
|
20
20
|
/**
|
|
21
21
|
* Entity after human review. Extends the base Entity
|
|
@@ -52,6 +52,16 @@ type TriggerStrategy = {
|
|
|
52
52
|
* word-boundary, case-insensitive.
|
|
53
53
|
*/
|
|
54
54
|
stopWords?: string[];
|
|
55
|
+
/**
|
|
56
|
+
* Hard cap on the captured span length, in characters,
|
|
57
|
+
* regardless of where the next comma / stop char sits.
|
|
58
|
+
* Use for triggers that label short formulaic phrases
|
|
59
|
+
* ("State of Delaware") and must not absorb the rest
|
|
60
|
+
* of a long forum-selection clause when the comma is
|
|
61
|
+
* sentences away. Falls back to the default 100-char
|
|
62
|
+
* fallback when omitted.
|
|
63
|
+
*/
|
|
64
|
+
maxLength?: number;
|
|
55
65
|
} | {
|
|
56
66
|
type: "to-end-of-line";
|
|
57
67
|
} | {
|