@stll/anonymize-wasm 1.0.8 → 1.1.0

package/dist/names-surnames.mjs

@@ -0,0 +1,113 @@
+//#region src/data/names-surnames.json
+var _comment = "Common surnames for person detection. Czech, Slovak, German, Austrian sources.";
+var names = [
+	"Bartoš",
+	"Bauer",
+	"Becker",
+	"Beneš",
+	"Berger",
+	"Blaha",
+	"Braun",
+	"Brunner",
+	"Čermák",
+	"Černá",
+	"Černý",
+	"Doležal",
+	"Duda",
+	"Dvořák",
+	"Dvořáková",
+	"Fiala",
+	"Fischer",
+	"Fuchs",
+	"Gruber",
+	"Hájek",
+	"Hartmann",
+	"Hermann",
+	"Hofer",
+	"Hoffmann",
+	"Holub",
+	"Horák",
+	"Horáková",
+	"Hruška",
+	"Huber",
+	"Jelínek",
+	"Kadlec",
+	"Kaiser",
+	"Koch",
+	"Köhler",
+	"Kolář",
+	"Koller",
+	"Konečný",
+	"Kopecký",
+	"Král",
+	"Kratochvíl",
+	"Krejčí",
+	"Kříž",
+	"Krüger",
+	"Kubík",
+	"Kučera",
+	"Kučerová",
+	"Lang",
+	"Lehmann",
+	"Maier",
+	"Malý",
+	"Mareš",
+	"Mašek",
+	"Mayer",
+	"Meyer",
+	"Moser",
+	"Müller",
+	"Musil",
+	"Navrátil",
+	"Němcová",
+	"Němec",
+	"Neumann",
+	"Nguyen",
+	"Novák",
+	"Nováková",
+	"Novotná",
+	"Novotný",
+	"Pavlík",
+	"Pichler",
+	"Pokorný",
+	"Polák",
+	"Pospíšil",
+	"Procházka",
+	"Procházková",
+	"Richter",
+	"Růžička",
+	"Schmid",
+	"Schmidt",
+	"Schmitt",
+	"Schneider",
+	"Schröder",
+	"Schulz",
+	"Schwarz",
+	"Sedláček",
+	"Šimek",
+	"Šťastný",
+	"Steiner",
+	"Svoboda",
+	"Svobodová",
+	"Tichý",
+	"Urban",
+	"Vaněk",
+	"Veselá",
+	"Veselý",
+	"Vlček",
+	"Wagner",
+	"Weber",
+	"Werner",
+	"Winkler",
+	"Wolf",
+	"Zeman",
+	"Zimmermann"
+];
+var names_surnames_default = {
+	_comment,
+	names
+};
+//#endregion
+export { _comment, names_surnames_default as default, names };
+
+//# sourceMappingURL=names-surnames.mjs.map

package/dist/names-surnames.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"names-surnames.mjs","names":[],"sources":["../../src/data/names-surnames.json"],"sourcesContent":[""],"mappings":""}

package/dist/names-title-tokens.mjs

@@ -0,0 +1,40 @@
+//#region src/data/names-title-tokens.json
+var _comment = "Lowercase title tokens that signal a person name follows. Used for token classification in the name chain detector.";
+var tokens = [
+	"bc",
+	"dame",
+	"doc",
+	"dr",
+	"frau",
+	"herr",
+	"ing",
+	"judge",
+	"judr",
+	"justice",
+	"lady",
+	"lord",
+	"maître",
+	"mgr",
+	"miss",
+	"mlle",
+	"mme",
+	"mr",
+	"mrs",
+	"ms",
+	"mudr",
+	"mvdr",
+	"paeddr",
+	"phdr",
+	"prof",
+	"rndr",
+	"sir",
+	"thdr"
+];
+var names_title_tokens_default = {
+	_comment,
+	tokens
+};
+//#endregion
+export { _comment, names_title_tokens_default as default, tokens };
+
+//# sourceMappingURL=names-title-tokens.mjs.map

package/dist/names-title-tokens.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"names-title-tokens.mjs","names":[],"sources":["../../src/data/names-title-tokens.json"],"sourcesContent":[""],"mappings":""}

package/dist/person-stopwords.mjs

@@ -0,0 +1,69 @@
+//#region src/data/person-stopwords.json
+var person_stopwords_default = {
+	_comment: "Words that are valid in other labels (address, org) but should never be classified as person. Checked only in person chain scoring.",
+	words: [
+		"april",
+		"august",
+		"austria",
+		"austrian",
+		"basic",
+		"belgian",
+		"british",
+		"bulgarian",
+		"california",
+		"center",
+		"croatian",
+		"cypriot",
+		"czech",
+		"danish",
+		"december",
+		"delaware",
+		"dry",
+		"dutch",
+		"english",
+		"estonian",
+		"european",
+		"february",
+		"finnish",
+		"french",
+		"german",
+		"germany",
+		"greek",
+		"hungarian",
+		"indiana",
+		"irish",
+		"israel",
+		"italian",
+		"january",
+		"july",
+		"june",
+		"latvian",
+		"lithuanian",
+		"louisiana",
+		"luxembourgish",
+		"maltese",
+		"march",
+		"maryland",
+		"missouri",
+		"nevada",
+		"november",
+		"october",
+		"ohio",
+		"opportunity",
+		"page",
+		"polish",
+		"portuguese",
+		"romanian",
+		"sale",
+		"september",
+		"slovak",
+		"slovenian",
+		"spanish",
+		"swedish",
+		"university"
+	]
+};
+//#endregion
+export { person_stopwords_default as default };
+
+//# sourceMappingURL=person-stopwords.mjs.map

package/dist/person-stopwords.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"person-stopwords.mjs","names":[],"sources":["../../src/data/person-stopwords.json"],"sourcesContent":[""],"mappings":""}

package/dist/section-headings.mjs

@@ -0,0 +1,52 @@
+//#region src/data/section-headings.json
+var _comment = "Section heading patterns that mark the end of the header zone. Multilingual: Czech, English, German, French, Italian, Spanish, Slovak, Polish. All patterns require a trailing numeral or roman numeral to avoid false-positives on body text. Each entry specifies its own regex flags; keyword-based patterns use 'iu' for case-insensitive Unicode matching, while the roman-numeral pattern stays case-sensitive to avoid matching lowercase list markers (i., ii.).";
+var patterns = [
+	{
+		"re": "^\\s*(?:I\\.|1\\.)\\s",
+		"flags": ""
+	},
+	{
+		"re": "^\\s*(?:Článek|Čl\\.)\\s*\\d",
+		"flags": "iu"
+	},
+	{
+		"re": "^\\s*(?:Article|Art\\.)\\s*\\d",
+		"flags": "iu"
+	},
+	{
+		"re": "^\\s*§\\s*\\d",
+		"flags": ""
+	},
+	{
+		"re": "^\\s*(?:Abschnitt|Kapitel)\\s*\\d",
+		"flags": "iu"
+	},
+	{
+		"re": "^\\s*(?:Chapitre|Section)\\s*\\d",
+		"flags": "iu"
+	},
+	{
+		"re": "^\\s*(?:Capitolo|Sezione)\\s*\\d",
+		"flags": "iu"
+	},
+	{
+		"re": "^\\s*(?:Artículo|Sección)\\s*\\d",
+		"flags": "iu"
+	},
+	{
+		"re": "^\\s*(?:Článok|Čl\\.)\\s*\\d",
+		"flags": "iu"
+	},
+	{
+		"re": "^\\s*(?:Rozdział|Artykuł)\\s*\\d",
+		"flags": "iu"
+	}
+];
+var section_headings_default = {
+	_comment,
+	patterns
+};
+//#endregion
+export { _comment, section_headings_default as default, patterns };
+
+//# sourceMappingURL=section-headings.mjs.map

package/dist/section-headings.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"section-headings.mjs","names":[],"sources":["../../src/data/section-headings.json"],"sourcesContent":[""],"mappings":""}

package/dist/signing-clauses.mjs

@@ -0,0 +1,78 @@
+//#region src/data/signing-clauses.json
+var _comment = "Signing clause patterns. Captures the place name from contract signing locations. Each entry: prefix (before place), suffix (after place), prepositions (allowed inside multi-word place names).";
+var patterns = [
+	{
+		"lang": "cs",
+		"prefix": "(?:V|Ve)\\s+",
+		"suffix": "\\s*,?\\s*dne",
+		"prepositions": [
+			"nad",
+			"pod",
+			"u",
+			"ve",
+			"na"
+		]
+	},
+	{
+		"lang": "sk",
+		"prefix": "(?:V|Vo)\\s+",
+		"suffix": "\\s*,?\\s*dňa",
+		"prepositions": [
+			"nad",
+			"pod",
+			"pri"
+		]
+	},
+	{
+		"lang": "de",
+		"prefix": "",
+		"suffix": "\\s*,\\s*den",
+		"prepositions": [
+			"am",
+			"an",
+			"im"
+		]
+	},
+	{
+		"lang": "fr",
+		"prefix": "(?:Fait\\s+)?[Àà]\\s+",
+		"suffix": "\\s*,?\\s*le",
+		"prepositions": []
+	},
+	{
+		"lang": "en",
+		"prefix": "(?:Signed|Executed)\\s+in\\s+",
+		"suffix": "",
+		"prepositions": []
+	},
+	{
+		"lang": "pl",
+		"prefix": "(?:W|We)\\s+",
+		"suffix": "\\s*,?\\s*dnia",
+		"prepositions": [
+			"nad",
+			"pod",
+			"przy"
+		]
+	},
+	{
+		"lang": "it",
+		"prefix": "(?:Fatto\\s+)?[Aa]\\s+",
+		"suffix": "\\s*,?\\s*(?:il|lì)",
+		"prepositions": []
+	},
+	{
+		"lang": "es",
+		"prefix": "(?:Firmado\\s+)?[Ee]n\\s+",
+		"suffix": "\\s*,?\\s*(?:a|el)",
+		"prepositions": ["de", "del"]
+	}
+];
+var signing_clauses_default = {
+	_comment,
+	patterns
+};
+//#endregion
+export { _comment, signing_clauses_default as default, patterns };
+
+//# sourceMappingURL=signing-clauses.mjs.map

package/dist/signing-clauses.mjs.map

@@ -0,0 +1 @@
+{"version":3,"file":"signing-clauses.mjs","names":[],"sources":["../../src/data/signing-clauses.json"],"sourcesContent":[""],"mappings":""}