@stll/anonymize 2.0.0-alpha.1 → 2.0.1

package/dist/person-stopwords.mjs

@@ -1,211 +0,0 @@
-//#region src/data/person-stopwords.json
-var _comment = "Words that are valid in other labels (address, org) but should never be classified as person. Checked only in person chain scoring.";
-var cs = ["cena"];
-var en = ["dodd-frank"];
-var words = [
-	"addendum",
-	"agent",
-	"agreement",
-	"alameda",
-	"amendment",
-	"annex",
-	"april",
-	"article",
-	"august",
-	"austria",
-	"austrian",
-	"avenida",
-	"basic",
-	"belgian",
-	"borrower",
-	"branch",
-	"british",
-	"bulgarian",
-	"buyer",
-	"california",
-	"center",
-	"consent",
-	"consultant",
-	"contract",
-	"contractor",
-	"croatian",
-	"customer",
-	"cypriot",
-	"czech",
-	"danish",
-	"december",
-	"default",
-	"delaware",
-	"delivery",
-	"department",
-	"division",
-	"dry",
-	"dutch",
-	"english",
-	"estonian",
-	"estrada",
-	"european",
-	"event",
-	"exhibit",
-	"february",
-	"finnish",
-	"french",
-	"german",
-	"germany",
-	"greek",
-	"guarantor",
-	"headquarters",
-	"hungarian",
-	"indiana",
-	"interest",
-	"irish",
-	"israel",
-	"italian",
-	"january",
-	"july",
-	"june",
-	"landlord",
-	"largo",
-	"latvian",
-	"lender",
-	"lessee",
-	"lessor",
-	"license",
-	"licensee",
-	"licensor",
-	"lithuanian",
-	"louisiana",
-	"luxembourgish",
-	"maltese",
-	"march",
-	"maryland",
-	"memorandum",
-	"missouri",
-	"nevada",
-	"notice",
-	"november",
-	"october",
-	"office",
-	"ohio",
-	"opportunity",
-	"owner",
-	"page",
-	"party",
-	"payment",
-	"polish",
-	"portuguese",
-	"praca",
-	"praça",
-	"price",
-	"principal",
-	"purchaser",
-	"rate",
-	"rodovia",
-	"romanian",
-	"rua",
-	"sale",
-	"schedule",
-	"section",
-	"seller",
-	"september",
-	"subsidiary",
-	"slovak",
-	"slovenian",
-	"spanish",
-	"swedish",
-	"tenant",
-	"term",
-	"termination",
-	"time",
-	"travessa",
-	"union",
-	"university",
-	"vendor",
-	"waiver",
-	"borgo",
-	"contrada",
-	"corso",
-	"indirizzo",
-	"lungarno",
-	"lungomare",
-	"lungotevere",
-	"piazza",
-	"piazzale",
-	"salita",
-	"sede",
-	"sezione",
-	"strada",
-	"stradone",
-	"traversa",
-	"via",
-	"viale",
-	"vico",
-	"vicolo",
-	"tato",
-	"tento",
-	"tito",
-	"tomto",
-	"tomuto",
-	"toto",
-	"touto",
-	"tuto",
-	"tyto",
-	"této",
-	"acheteur",
-	"acheteuse",
-	"acquéreur",
-	"acquéreuse",
-	"allée",
-	"annexe",
-	"avenue",
-	"bailleresse",
-	"bailleur",
-	"boulevard",
-	"cédant",
-	"cédante",
-	"cessionnaire",
-	"chapitre",
-	"chemin",
-	"domicilié",
-	"domiciliée",
-	"employé",
-	"employée",
-	"employeur",
-	"employeuse",
-	"fournisseur",
-	"fournisseuse",
-	"impasse",
-	"locataire",
-	"maître",
-	"mandant",
-	"mandante",
-	"mandataire",
-	"passage",
-	"préambule",
-	"preneur",
-	"preneuse",
-	"prestataire",
-	"prêteur",
-	"prêteuse",
-	"promesse",
-	"quai",
-	"résidence",
-	"ruelle",
-	"salarié",
-	"salariée",
-	"société",
-	"titre",
-	"vendeur",
-	"vendeuse",
-	"voie"
-];
-var person_stopwords_default = {
-	_comment,
-	cs,
-	en,
-	words
-};
-//#endregion
-export { _comment, cs, person_stopwords_default as default, en, words };
-
-//# sourceMappingURL=person-stopwords.mjs.map

package/dist/person-stopwords.mjs.map

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

package/dist/section-headings.mjs

@@ -1,64 +0,0 @@
-//#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*(?:Annexe|Préambule|Titre)\\s*\\d",
-		"flags": "iu"
-	},
-	{
-		"re": "^\\s*(?:Capitolo|Sezione|Articolo)\\s*\\d",
-		"flags": "iu"
-	},
-	{
-		"re": "^\\s*Sezione\\s+[IVX]+\\b",
-		"flags": "iu"
-	},
-	{
-		"re": "^\\s*(?:AMMINISTRAZIONE\\s+AGGIUDICATRICE|ALTRE\\s+INFORMAZIONI|OGGETTO|PROCEDURA)\\b",
-		"flags": "iu"
-	},
-	{
-		"re": "^\\s*(?:Artículo|Sección)\\s*\\d",
-		"flags": "iu"
-	},
-	{
-		"re": "^\\s*(?:Článok|Čl\\.|Oddiel|Odsek|Príloha)\\s*\\d",
-		"flags": "iu"
-	},
-	{
-		"re": "^\\s*(?:Rozdział|Artykuł|Paragraf|Załącznik)\\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

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

package/dist/sentence-verb-indicators.mjs

@@ -1,232 +0,0 @@
-//#region src/data/sentence-verb-indicators.json
-var _comment = "Verb-like tokens that signal sentence context inside a legal-form match span. When one of these appears between a role-head opening ('Vendor', 'Predávajúci') and the legal-form suffix ('Inc.', 's.r.o.'), the match is a swept sentence fragment and gets trimmed back to the real organisation name. Lowercased; matched case-insensitively. Organised per-language because verb morphology is language-specific; at runtime the legal-form detector unions every language's list into a single set because match spans don't carry a language tag.";
-var cs = [
-	"je",
-	"jsou",
-	"byl",
-	"byla",
-	"byly",
-	"bude",
-	"není",
-	"vlastní",
-	"vlastníkem",
-	"prodává",
-	"prodal",
-	"prodala",
-	"koupil",
-	"koupila",
-	"kupuje",
-	"platí",
-	"hradí",
-	"podepsal",
-	"podepsala",
-	"podepisuje",
-	"uzavírá",
-	"uzavřel",
-	"uzavřela",
-	"zavazuje",
-	"dluží"
-];
-var en = [
-	"is",
-	"are",
-	"was",
-	"were",
-	"owns",
-	"grants",
-	"sells",
-	"sold",
-	"buys",
-	"bought",
-	"has",
-	"holds",
-	"agrees",
-	"pays",
-	"paid",
-	"owes",
-	"signs",
-	"signed",
-	"leases",
-	"rents",
-	"entered",
-	"made",
-	"executed",
-	"retained",
-	"hired",
-	"engaged",
-	"appointed",
-	"named",
-	"sued"
-];
-var de = [
-	"ist",
-	"sind",
-	"war",
-	"waren",
-	"besitzt",
-	"gewährt",
-	"verkauft",
-	"kauft",
-	"hat",
-	"unterzeichnet",
-	"zahlt"
-];
-var fr = [
-	"est",
-	"sont",
-	"était",
-	"étaient",
-	"sera",
-	"seront",
-	"possède",
-	"possèdent",
-	"détient",
-	"détiennent",
-	"vend",
-	"vendent",
-	"achète",
-	"achètent",
-	"signe",
-	"signent",
-	"paie",
-	"paient",
-	"accorde",
-	"accordent",
-	"loue",
-	"louent",
-	"s'engage",
-	"s’engage",
-	"s'engagent",
-	"s’engagent",
-	"conclut",
-	"concluent",
-	"doit",
-	"doivent"
-];
-var sk = [
-	"je",
-	"sú",
-	"bol",
-	"bola",
-	"boli",
-	"bude",
-	"nie je",
-	"uzatvára",
-	"uzatvoril",
-	"uzatvorila",
-	"uzaviera",
-	"uzavrel",
-	"uzavrela",
-	"podpisuje",
-	"podpísal",
-	"podpísala",
-	"vlastní",
-	"vlastníkom",
-	"vlastníkmi",
-	"predáva",
-	"predal",
-	"predala",
-	"kupuje",
-	"kúpil",
-	"kúpila",
-	"platí",
-	"hradí",
-	"zaväzuje",
-	"dlží",
-	"prenajíma",
-	"najíma"
-];
-var es = [
-	"actúa",
-	"actúan",
-	"adquiere",
-	"adquirió",
-	"celebra",
-	"celebran",
-	"celebró",
-	"compra",
-	"compró",
-	"concede",
-	"contrata",
-	"contrató",
-	"debe",
-	"es",
-	"fue",
-	"fueron",
-	"firma",
-	"firman",
-	"firmó",
-	"ha",
-	"han",
-	"otorga",
-	"otorgan",
-	"otorgó",
-	"paga",
-	"pagó",
-	"posee",
-	"compromete",
-	"comprometen",
-	"comprometió",
-	"ser",
-	"son",
-	"suscribe",
-	"tiene",
-	"tienen",
-	"transfiere",
-	"vende",
-	"vendió"
-];
-var it = [
-	"è",
-	"sono",
-	"era",
-	"erano",
-	"possiede",
-	"concede",
-	"vende",
-	"compra",
-	"ha",
-	"firma",
-	"firmato",
-	"paga",
-	"deve",
-	"ratifica",
-	"stipula"
-];
-var pl = [
-	"jest",
-	"są",
-	"był",
-	"była",
-	"było",
-	"były",
-	"będzie",
-	"będą",
-	"nie jest",
-	"oświadcza",
-	"oświadczają",
-	"sprzedaje",
-	"sprzedają",
-	"kupuje",
-	"kupują",
-	"zawiera",
-	"zawierają",
-	"podpisuje",
-	"płaci",
-	"wynajmuje"
-];
-var sentence_verb_indicators_default = {
-	_comment,
-	cs,
-	en,
-	de,
-	fr,
-	sk,
-	es,
-	it,
-	pl
-};
-//#endregion
-export { _comment, cs, de, sentence_verb_indicators_default as default, en, es, fr, it, pl, sk };
-
-//# sourceMappingURL=sentence-verb-indicators.mjs.map

package/dist/sentence-verb-indicators.mjs.map

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

package/dist/signing-clauses.mjs

@@ -1,102 +0,0 @@
-//#region src/data/signing-clauses.json
-var _comment = "Signing clause patterns. Captures the place name from contract signing locations. Each entry: prefix/suffix build regexes; prefilterPhrases gate native regex scans; guardPrefixPhrases/guardSuffixPhrases suppress deny-list place hits in the same signing context.";
-var patterns = [
-	{
-		"lang": "cs",
-		"prefix": "(?:V|Ve)\\s+",
-		"suffix": "\\s*,?\\s*dne",
-		"prepositions": [
-			"nad",
-			"pod",
-			"u",
-			"ve",
-			"na"
-		],
-		"prefilterPhrases": ["dne"],
-		"guardPrefixPhrases": ["v", "ve"],
-		"guardSuffixPhrases": ["dne"]
-	},
-	{
-		"lang": "sk",
-		"prefix": "(?:V|Vo)\\s+",
-		"suffix": "\\s*,?\\s*dňa",
-		"prepositions": [
-			"nad",
-			"pod",
-			"pri"
-		],
-		"prefilterPhrases": ["dňa"],
-		"guardPrefixPhrases": ["v", "vo"],
-		"guardSuffixPhrases": ["dňa"]
-	},
-	{
-		"lang": "de",
-		"prefix": "",
-		"suffix": "\\s*,\\s*den",
-		"prepositions": [
-			"am",
-			"an",
-			"im"
-		],
-		"prefilterPhrases": ["den"],
-		"guardPrefixPhrases": [""],
-		"guardSuffixPhrases": ["den"]
-	},
-	{
-		"lang": "fr",
-		"prefix": "(?:Fait\\s+)?[Àà]\\s+",
-		"suffix": "\\s*,?\\s*le",
-		"prepositions": [],
-		"prefilterPhrases": ["À ", "à "],
-		"guardPrefixPhrases": ["à", "fait à"],
-		"guardSuffixPhrases": ["le"]
-	},
-	{
-		"lang": "en",
-		"prefix": "(?:Signed|Executed)\\s+in\\s+",
-		"suffix": "",
-		"prepositions": [],
-		"prefilterPhrases": ["Signed in", "Executed in"],
-		"guardPrefixPhrases": ["signed in", "executed in"],
-		"guardSuffixPhrases": [""]
-	},
-	{
-		"lang": "pl",
-		"prefix": "(?:W|We)\\s+",
-		"suffix": "\\s*,?\\s*dnia",
-		"prepositions": [
-			"nad",
-			"pod",
-			"przy"
-		],
-		"prefilterPhrases": ["dnia"],
-		"guardPrefixPhrases": ["w", "we"],
-		"guardSuffixPhrases": ["dnia"]
-	},
-	{
-		"lang": "it",
-		"prefix": "(?:Fatto\\s+)?[Aa]\\s+",
-		"suffix": "\\s*,?\\s*(?:il|lì)",
-		"prepositions": [],
-		"prefilterPhrases": ["A ", "a "],
-		"guardPrefixPhrases": ["a", "fatto a"],
-		"guardSuffixPhrases": ["il", "lì"]
-	},
-	{
-		"lang": "es",
-		"prefix": "(?:Firmado\\s+)?[Ee]n\\s+",
-		"suffix": "\\s*,?\\s*(?:a|el)",
-		"prepositions": ["de", "del"],
-		"prefilterPhrases": ["En ", "en "],
-		"guardPrefixPhrases": ["en", "firmado en"],
-		"guardSuffixPhrases": ["a", "el"]
-	}
-];
-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

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