urdu-text-utils 0.2.2 → 0.3.0

package/dist/index.d.cts

@@ -114,6 +114,8 @@ interface SplitSentenceOptions {
     /** If true, the sentence-ending punctuation (۔ ؟ ! . etc.) is preserved with each sentence. Default `false`. */
     preserveTerminators?: boolean;
 }
+/** Common Urdu abbreviations and honorifics that should not cause false sentence splits. */
+declare const SENTENCE_ABBREVIATIONS: string[];
 /**
  * Sentences count, split on Urdu and standard terminators (۔ ؟ ! . …).
  * Protects common titles, abbreviations, and numeric decimals from false splits.
@@ -406,6 +408,11 @@ declare const URDU_PREFIXES: readonly ["غیر", "خود", "اہل", "بے", "ن
  * Canonical Urdu suffixes (لاحقے) ordered by descending length.
  */
 declare const URDU_SUFFIXES: readonly ["یںگے", "ینگے", "ےگا", "ےگی", "ینگی", "داری", "گاری", "کاری", "سازی", "بازی", "مندی", "ترین", "ستان", "خانہ", "نامہ", "جات", "گان", "دار", "گار", "کار", "ساز", "باز", "مند", "ناک", "وار", "دان", "زار", "یت", "پن", "ائی", "تر", "یاں", "ئیں", "ؤں", "یوں", "وں", "یں", "ات", "ہا", "ین", "تیں", "تا", "تی", "تے", "نا"];
+/**
+ * Irreducible base words that must not have prefixes or suffixes stripped falsely.
+ * Exported so the PHP port can consume the identical list via tables.json.
+ */
+declare const PROTECTED_WORDS: Set<string>;
 interface StemmerOptions {
     /**
      * Whether to strip canonical Urdu prefixes (e.g. بے-, نا-, غیر-, لا-).
@@ -454,8 +461,11 @@ interface AffixBreakdown {
  * getAffixes("کتابیں")
  * // { stem: "کتاب", suffix: "یں" }
  *
+ * getAffixes("غیرملکیوں")
+ * // { prefix: "غیر", stem: "ملکی", suffix: "یوں" }
+ *
  * getAffixes("نااہلی")
- * // { prefix: "نا", stem: "اہل", suffix: "ی" }
+ * // { prefix: "نا", stem: "اہلی" }
  */
 declare function getAffixes(input: string, options?: StemmerOptions): AffixBreakdown;
 /**
@@ -483,6 +493,20 @@ declare function stemUrdu(word: string, options?: StemmerOptions): string;
  */
 declare function stemUrduText(text: string, options?: StemmerOptions): string;
 
+/** Common Urdu first names mapped to their standard English spellings. */
+declare const URDU_FIRST_NAMES: Record<string, string>;
+/** Common Urdu family/last names mapped to their standard English spellings. */
+declare const URDU_FAMILY_NAMES: Record<string, string>;
+/** Honorific titles used in Urdu names. */
+declare const HONORIFICS: Record<string, string>;
+/** Name prefixes that are kept in both languages. */
+declare const NAME_PREFIXES: Record<string, string>;
+/**
+ * Alternate English spellings of names already in the forward tables
+ * (e.g. `Omar` for عمر, canonically spelled `Umar` in English).
+ * Exported so the PHP port can consume the identical list via tables.json.
+ */
+declare const ENGLISH_NAME_ALIASES: Record<string, string>;
 interface NameTransliterationOptions {
     /** Preserve the original case of the English name. Default: true (capitalized). */
     preserveCase?: boolean;
@@ -519,4 +543,4 @@ declare function extractNameParts(fullName: string): {
     suffix?: string;
 };
 
-export { type AffixBreakdown, type DigitStyle, type FormatUrduDateOptions, type IsUrduOptions, type NameTransliterationOptions, type NormalizeOptions, type SearchOptions, type SearchResult, type SlugOptions, type SortOptions, type SplitSentenceOptions, type StemmerOptions, type TimeAgoOptions, URDU_MONTHS_GREGORIAN, URDU_MONTHS_HIJRI, URDU_PREFIXES, URDU_STOP_WORDS, URDU_SUFFIXES, URDU_WEEKDAYS, type UrduStats, analyzeUrdu, compareUrdu, convertNumbers, countSentences, countWords, editDistance, extractNameParts, filterStopWords, foldUrdu, formatUrduDate, getAffixes, getUrduMonthName, getUrduWeekdayName, hasUrduSpecificLetters, highlightUrdu, isStopWord, isUrdu, normalizeUrdu, numberToUrduWords, parseUrduNumber, removeDiacritics, removeStopWords, romanToUrdu, romanize, searchUrdu, searchUrduRanked, sortUrdu, splitSentences, splitWords, stemUrdu, stemUrduText, timeAgoUrdu, toArabicIndicDigits, toEnglishDigits, toUrduDigits, transliterateNameToEnglish, transliterateNameToUrdu, urduRatio, urduSlug };
+export { type AffixBreakdown, type DigitStyle, ENGLISH_NAME_ALIASES, type FormatUrduDateOptions, HONORIFICS, type IsUrduOptions, NAME_PREFIXES, type NameTransliterationOptions, type NormalizeOptions, PROTECTED_WORDS, SENTENCE_ABBREVIATIONS, type SearchOptions, type SearchResult, type SlugOptions, type SortOptions, type SplitSentenceOptions, type StemmerOptions, type TimeAgoOptions, URDU_FAMILY_NAMES, URDU_FIRST_NAMES, URDU_MONTHS_GREGORIAN, URDU_MONTHS_HIJRI, URDU_PREFIXES, URDU_STOP_WORDS, URDU_SUFFIXES, URDU_WEEKDAYS, type UrduStats, analyzeUrdu, compareUrdu, convertNumbers, countSentences, countWords, editDistance, extractNameParts, filterStopWords, foldUrdu, formatUrduDate, getAffixes, getUrduMonthName, getUrduWeekdayName, hasUrduSpecificLetters, highlightUrdu, isStopWord, isUrdu, normalizeUrdu, numberToUrduWords, parseUrduNumber, removeDiacritics, removeStopWords, romanToUrdu, romanize, searchUrdu, searchUrduRanked, sortUrdu, splitSentences, splitWords, stemUrdu, stemUrduText, timeAgoUrdu, toArabicIndicDigits, toEnglishDigits, toUrduDigits, transliterateNameToEnglish, transliterateNameToUrdu, urduRatio, urduSlug };

package/dist/index.d.ts

@@ -114,6 +114,8 @@ interface SplitSentenceOptions {
     /** If true, the sentence-ending punctuation (۔ ؟ ! . etc.) is preserved with each sentence. Default `false`. */
     preserveTerminators?: boolean;
 }
+/** Common Urdu abbreviations and honorifics that should not cause false sentence splits. */
+declare const SENTENCE_ABBREVIATIONS: string[];
 /**
  * Sentences count, split on Urdu and standard terminators (۔ ؟ ! . …).
  * Protects common titles, abbreviations, and numeric decimals from false splits.
@@ -406,6 +408,11 @@ declare const URDU_PREFIXES: readonly ["غیر", "خود", "اہل", "بے", "ن
  * Canonical Urdu suffixes (لاحقے) ordered by descending length.
  */
 declare const URDU_SUFFIXES: readonly ["یںگے", "ینگے", "ےگا", "ےگی", "ینگی", "داری", "گاری", "کاری", "سازی", "بازی", "مندی", "ترین", "ستان", "خانہ", "نامہ", "جات", "گان", "دار", "گار", "کار", "ساز", "باز", "مند", "ناک", "وار", "دان", "زار", "یت", "پن", "ائی", "تر", "یاں", "ئیں", "ؤں", "یوں", "وں", "یں", "ات", "ہا", "ین", "تیں", "تا", "تی", "تے", "نا"];
+/**
+ * Irreducible base words that must not have prefixes or suffixes stripped falsely.
+ * Exported so the PHP port can consume the identical list via tables.json.
+ */
+declare const PROTECTED_WORDS: Set<string>;
 interface StemmerOptions {
     /**
      * Whether to strip canonical Urdu prefixes (e.g. بے-, نا-, غیر-, لا-).
@@ -454,8 +461,11 @@ interface AffixBreakdown {
  * getAffixes("کتابیں")
  * // { stem: "کتاب", suffix: "یں" }
  *
+ * getAffixes("غیرملکیوں")
+ * // { prefix: "غیر", stem: "ملکی", suffix: "یوں" }
+ *
  * getAffixes("نااہلی")
- * // { prefix: "نا", stem: "اہل", suffix: "ی" }
+ * // { prefix: "نا", stem: "اہلی" }
  */
 declare function getAffixes(input: string, options?: StemmerOptions): AffixBreakdown;
 /**
@@ -483,6 +493,20 @@ declare function stemUrdu(word: string, options?: StemmerOptions): string;
  */
 declare function stemUrduText(text: string, options?: StemmerOptions): string;
 
+/** Common Urdu first names mapped to their standard English spellings. */
+declare const URDU_FIRST_NAMES: Record<string, string>;
+/** Common Urdu family/last names mapped to their standard English spellings. */
+declare const URDU_FAMILY_NAMES: Record<string, string>;
+/** Honorific titles used in Urdu names. */
+declare const HONORIFICS: Record<string, string>;
+/** Name prefixes that are kept in both languages. */
+declare const NAME_PREFIXES: Record<string, string>;
+/**
+ * Alternate English spellings of names already in the forward tables
+ * (e.g. `Omar` for عمر, canonically spelled `Umar` in English).
+ * Exported so the PHP port can consume the identical list via tables.json.
+ */
+declare const ENGLISH_NAME_ALIASES: Record<string, string>;
 interface NameTransliterationOptions {
     /** Preserve the original case of the English name. Default: true (capitalized). */
     preserveCase?: boolean;
@@ -519,4 +543,4 @@ declare function extractNameParts(fullName: string): {
     suffix?: string;
 };
 
-export { type AffixBreakdown, type DigitStyle, type FormatUrduDateOptions, type IsUrduOptions, type NameTransliterationOptions, type NormalizeOptions, type SearchOptions, type SearchResult, type SlugOptions, type SortOptions, type SplitSentenceOptions, type StemmerOptions, type TimeAgoOptions, URDU_MONTHS_GREGORIAN, URDU_MONTHS_HIJRI, URDU_PREFIXES, URDU_STOP_WORDS, URDU_SUFFIXES, URDU_WEEKDAYS, type UrduStats, analyzeUrdu, compareUrdu, convertNumbers, countSentences, countWords, editDistance, extractNameParts, filterStopWords, foldUrdu, formatUrduDate, getAffixes, getUrduMonthName, getUrduWeekdayName, hasUrduSpecificLetters, highlightUrdu, isStopWord, isUrdu, normalizeUrdu, numberToUrduWords, parseUrduNumber, removeDiacritics, removeStopWords, romanToUrdu, romanize, searchUrdu, searchUrduRanked, sortUrdu, splitSentences, splitWords, stemUrdu, stemUrduText, timeAgoUrdu, toArabicIndicDigits, toEnglishDigits, toUrduDigits, transliterateNameToEnglish, transliterateNameToUrdu, urduRatio, urduSlug };
+export { type AffixBreakdown, type DigitStyle, ENGLISH_NAME_ALIASES, type FormatUrduDateOptions, HONORIFICS, type IsUrduOptions, NAME_PREFIXES, type NameTransliterationOptions, type NormalizeOptions, PROTECTED_WORDS, SENTENCE_ABBREVIATIONS, type SearchOptions, type SearchResult, type SlugOptions, type SortOptions, type SplitSentenceOptions, type StemmerOptions, type TimeAgoOptions, URDU_FAMILY_NAMES, URDU_FIRST_NAMES, URDU_MONTHS_GREGORIAN, URDU_MONTHS_HIJRI, URDU_PREFIXES, URDU_STOP_WORDS, URDU_SUFFIXES, URDU_WEEKDAYS, type UrduStats, analyzeUrdu, compareUrdu, convertNumbers, countSentences, countWords, editDistance, extractNameParts, filterStopWords, foldUrdu, formatUrduDate, getAffixes, getUrduMonthName, getUrduWeekdayName, hasUrduSpecificLetters, highlightUrdu, isStopWord, isUrdu, normalizeUrdu, numberToUrduWords, parseUrduNumber, removeDiacritics, removeStopWords, romanToUrdu, romanize, searchUrdu, searchUrduRanked, sortUrdu, splitSentences, splitWords, stemUrdu, stemUrduText, timeAgoUrdu, toArabicIndicDigits, toEnglishDigits, toUrduDigits, transliterateNameToEnglish, transliterateNameToUrdu, urduRatio, urduSlug };