hebrew-transliteration 1.3.1 → 2.0.2

package/dist/index.esm.js

@@ -0,0 +1,404 @@
+// src/index.ts
+import { Text as Text3 } from "havarotjs";
+
+// src/sequence.ts
+import { Text } from "havarotjs";
+var vowels = /[\u{05B0}-\u{05BD}\u{05BF}\u{05C7}]/u;
+var sequence = (text, qametsQatan = false) => {
+  return vowels.test(text) ? new Text(text, { qametsQatan }).text : text;
+};
+
+// src/rules.ts
+import { Cluster } from "havarotjs/dist/cluster";
+
+// src/hebCharsTrans.ts
+var transliterateMap = {
+  "\u05B0": "VOCAL_SHEVA",
+  "\u05B1": "HATAF_SEGOL",
+  "\u05B2": "HATAF_PATAH",
+  "\u05B3": "HATAF_QAMATS",
+  "\u05B4": "HIRIQ",
+  "\u05B5": "TSERE",
+  "\u05B6": "SEGOL",
+  "\u05B7": "PATAH",
+  "\u05B8": "QAMATS",
+  "\u05B9": "HOLAM",
+  "\u05BA": "HOLAM",
+  "\u05BB": "QUBUTS",
+  "\u05BC": "DAGESH",
+  "\u05BE": "MAQAF",
+  "\u05C0": "PASEQ",
+  "\u05C3": "SOF_PASUQ",
+  "\u05C7": "QAMATS_QATAN",
+  \u05D0: "ALEF",
+  \u05D1: "BET",
+  \u05D2: "GIMEL",
+  \u05D3: "DALET",
+  \u05D4: "HE",
+  \u05D5: "VAV",
+  \u05D6: "ZAYIN",
+  \u05D7: "HET",
+  \u05D8: "TET",
+  \u05D9: "YOD",
+  \u05DA: "FINAL_KAF",
+  \u05DB: "KAF",
+  \u05DC: "LAMED",
+  \u05DD: "FINAL_MEM",
+  \u05DE: "MEM",
+  \u05DF: "FINAL_NUN",
+  \u05E0: "NUN",
+  \u05E1: "SAMEKH",
+  \u05E2: "AYIN",
+  \u05E3: "FINAL_PE",
+  \u05E4: "PE",
+  \u05E5: "FINAL_TSADI",
+  \u05E6: "TSADI",
+  \u05E7: "QOF",
+  \u05E8: "RESH",
+  \u05E9: "SHIN",
+  \u05EA: "TAV"
+};
+
+// src/mapChars.ts
+var mapChars = (text, schema) => [...text].map((char) => char in transliterateMap ? schema[transliterateMap[char]] : char).join("");
+
+// src/rules.ts
+var taamim = /[\u{0590}-\u{05AF}\u{05BD}\u{05BF}]/u;
+var changeElementSplit = (input, split, join) => input.split(split).join(join);
+var consonantFeatures = (clusterText, syl, cluster, schema) => {
+  var _a;
+  if ((_a = schema.ADDITIONAL_FEATURES) == null ? void 0 : _a.length) {
+    const clusterSeqs = schema.ADDITIONAL_FEATURES.filter((s) => s.FEATURE === "cluster");
+    for (const seq of clusterSeqs) {
+      const heb = new RegExp(seq.HEBREW, "u");
+      if (heb.test(clusterText)) {
+        const sylSeq = changeElementSplit(clusterText, heb, seq.TRANSLITERATION);
+        return [...sylSeq].map((char) => mapChars(char, schema)).join("");
+      }
+    }
+  }
+  clusterText = cluster.hasShewa && syl.isClosed ? clusterText.replace(/\u{05B0}/u, "") : clusterText;
+  if (/ה\u{05BC}$/mu.test(clusterText)) {
+    return changeElementSplit(clusterText, /ה\u{05BC}/u, schema.HE);
+  }
+  if (syl.isFinal && !syl.isClosed) {
+    const furtiveChet = /\u{05D7}\u{05B7}$/mu;
+    if (furtiveChet.test(clusterText)) {
+      return changeElementSplit(clusterText, furtiveChet, "\u05B7\u05D7");
+    }
+    const furtiveAyin = /\u{05E2}\u{05B7}$/mu;
+    if (furtiveAyin.test(clusterText)) {
+      return changeElementSplit(clusterText, furtiveAyin, "\u05B7\u05E2");
+    }
+    const furtiveHe = /\u{05D4}\u{05BC}\u{05B7}$/mu;
+    if (furtiveHe.test(clusterText)) {
+      return changeElementSplit(clusterText, furtiveHe, "\u05B7\u05D4\u05BC");
+    }
+  }
+  const prevHasVowel = cluster.prev instanceof Cluster ? cluster.prev.hasVowel : false;
+  const isDoubled = schema.DAGESH_CHAZAQ && prevHasVowel && /\u{05BC}/u.test(clusterText);
+  if (schema.BET_DAGESH && /ב\u{05BC}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /ב\u{05BC}/u, schema.BET_DAGESH.repeat(isDoubled ? 2 : 1));
+  }
+  if (schema.GIMEL_DAGESH && /ג\u{05BC}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /ג\u{05BC}/u, schema.GIMEL_DAGESH.repeat(isDoubled ? 2 : 1));
+  }
+  if (schema.DALET_DAGESH && /ד\u{05BC}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /ד\u{05BC}/u, schema.DALET_DAGESH.repeat(isDoubled ? 2 : 1));
+  }
+  if (schema.KAF_DAGESH && /כ\u{05BC}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /כ\u{05BC}/u, schema.KAF_DAGESH.repeat(isDoubled ? 2 : 1));
+  }
+  if (schema.KAF_DAGESH && /ך\u{05BC}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /ך\u{05BC}/u, schema.KAF_DAGESH.repeat(isDoubled ? 2 : 1));
+  }
+  if (schema.PE_DAGESH && /פ\u{05BC}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /פ\u{05BC}/u, schema.PE_DAGESH.repeat(isDoubled ? 2 : 1));
+  }
+  if (schema.TAV_DAGESH && /ת\u{05BC}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /ת\u{05BC}/u, schema.TAV_DAGESH.repeat(isDoubled ? 2 : 1));
+  }
+  if (/ש\u{05C1}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /ש\u{05C1}/u, schema.SHIN.repeat(isDoubled ? 2 : 1));
+  }
+  if (/ש\u{05C2}/u.test(clusterText)) {
+    return changeElementSplit(clusterText, /ש\u{05C2}/u, schema.SIN.repeat(isDoubled ? 2 : 1));
+  }
+  if (isDoubled) {
+    const consonant = cluster.chars[0].text;
+    const consonantDagesh = new RegExp(consonant + "\u05BC", "u");
+    return changeElementSplit(clusterText, consonantDagesh, `${consonant + consonant}`);
+  }
+  if (cluster.isShureq) {
+    return schema.SHUREQ;
+  }
+  return clusterText;
+};
+var materFeatures = (syl, schema) => {
+  const mater = syl.clusters.filter((c) => c.isMater)[0];
+  const prev = mater.prev instanceof Cluster ? mater.prev : null;
+  const materText = mater.text;
+  const prevText = ((prev == null ? void 0 : prev.text) || "").replace(taamim, "");
+  let noMaterText = syl.clusters.filter((c) => !c.isMater).map((c) => consonantFeatures(c.text.replace(taamim, ""), syl, c, schema)).join("");
+  const hasMaqaf = mater.text.includes("\u05BE");
+  noMaterText = hasMaqaf ? noMaterText.concat("\u05BE") : noMaterText;
+  if (/י/.test(materText)) {
+    if (/\u{05B4}/u.test(prevText)) {
+      return changeElementSplit(noMaterText, /\u{05B4}/u, schema.HIRIQ_YOD);
+    }
+    if (/\u{05B5}/u.test(prevText)) {
+      return changeElementSplit(noMaterText, /\u{05B5}/u, schema.TSERE_YOD);
+    }
+    if (/\u{05B6}/u.test(prevText)) {
+      return changeElementSplit(noMaterText, /\u{05B6}/u, schema.SEGOL_YOD);
+    }
+  }
+  if (/ו/u.test(materText)) {
+    if (/\u{05B9}/u.test(prevText)) {
+      return changeElementSplit(noMaterText, /\u{05B9}/u, schema.HOLAM_VAV);
+    }
+  }
+  if (/ה/.test(materText)) {
+    if (/\u{05B8}/u.test(prevText)) {
+      return changeElementSplit(noMaterText, /\u{05B8}/u, schema.QAMATS_HE);
+    }
+    if (/\u{05B6}/u.test(prevText)) {
+      return changeElementSplit(noMaterText, /\u{05B6}/u, schema.SEGOL_HE);
+    }
+    if (/\u{05B5}/u.test(prevText)) {
+      return changeElementSplit(noMaterText, /\u{05B5}/u, schema.SEGOL_HE);
+    }
+  }
+  return materText;
+};
+var joinChars = (isAccented, sylChars, schema) => {
+  if (!isAccented) {
+    return sylChars.map((char) => mapChars(char, schema)).join("");
+  }
+  if (schema.STRESS_MARKER) {
+    const location = schema.STRESS_MARKER.location;
+    const mark = schema.STRESS_MARKER.mark;
+    if (location === "before-syllable") {
+      return `${mark}${sylChars.map((char) => mapChars(char, schema)).join("")}`;
+    }
+    if (location === "after-syllable") {
+      return `${sylChars.map((char) => mapChars(char, schema)).join("")}${mark}`;
+    }
+    const vowels3 = [
+      schema.PATAH,
+      schema.HATAF_PATAH,
+      schema.QAMATS,
+      schema.HATAF_QAMATS,
+      schema.SEGOL,
+      schema.HATAF_SEGOL,
+      schema.TSERE,
+      schema.HIRIQ,
+      schema.HOLAM,
+      schema.QAMATS_QATAN,
+      schema.QUBUTS,
+      schema.QAMATS_HE,
+      schema.SEGOL_HE,
+      schema.TSERE_HE,
+      schema.HIRIQ_YOD,
+      schema.TSERE_YOD,
+      schema.SEGOL_YOD,
+      schema.HOLAM_VAV,
+      schema.SHUREQ
+    ].sort((a, b) => b.length - a.length);
+    const vowelRgx = new RegExp(`${vowels3.join("|")}`);
+    const str = sylChars.map((char) => mapChars(char, schema)).join("");
+    const match = str.match(vowelRgx);
+    if (location === "before-vowel") {
+      return (match == null ? void 0 : match.length) ? str.replace(match[0], `${mark}${match[0]}`) : str;
+    }
+    return (match == null ? void 0 : match.length) ? str.replace(match[0], `${match[0]}${mark}`) : str;
+  }
+  return sylChars.map((char) => mapChars(char, schema)).join("");
+};
+var sylRules = (syl, schema) => {
+  var _a;
+  const sylTxt = syl.text.replace(taamim, "");
+  if ((_a = schema.ADDITIONAL_FEATURES) == null ? void 0 : _a.length) {
+    const sylSeqs = schema.ADDITIONAL_FEATURES.filter((s) => s.FEATURE === "syllable");
+    for (const seq of sylSeqs) {
+      const heb = new RegExp(seq.HEBREW, "u");
+      if (heb.test(sylTxt)) {
+        const wordSeq = changeElementSplit(sylTxt, heb, seq.TRANSLITERATION);
+        return joinChars(syl.isAccented, [...wordSeq], schema);
+      }
+    }
+  }
+  const mSSuffix = /\u{05B8}\u{05D9}\u{05D5}/u;
+  if (syl.isFinal && mSSuffix.test(sylTxt)) {
+    const sufxSyl = changeElementSplit(sylTxt, mSSuffix, schema.MS_SUFX);
+    return joinChars(syl.isAccented, [...sufxSyl], schema);
+  }
+  const hasMater = syl.clusters.map((c) => c.isMater).includes(true);
+  if (hasMater) {
+    const materSyl = materFeatures(syl, schema);
+    return joinChars(syl.isAccented, [...materSyl], schema);
+  }
+  const returnTxt = syl.clusters.map((cluster) => {
+    const clusterText = cluster.text.replace(taamim, "");
+    return consonantFeatures(clusterText, syl, cluster, schema);
+  });
+  return joinChars(syl.isAccented, returnTxt, schema);
+};
+var wordRules = (word, schema) => {
+  var _a;
+  if (word.isDivineName)
+    return schema.DIVINE_NAME;
+  if (word.hasDivineName)
+    return `${sylRules(word.syllables[0], schema)}-${schema.DIVINE_NAME}`;
+  if ((_a = schema.ADDITIONAL_FEATURES) == null ? void 0 : _a.length) {
+    const wordSeqs = schema.ADDITIONAL_FEATURES.filter((s) => s.FEATURE === "word");
+    for (const seq of wordSeqs) {
+      const heb = new RegExp(seq.HEBREW, "u");
+      const wordText = word.text.replace(taamim, "");
+      if (heb.test(wordText)) {
+        const wordSeq = changeElementSplit(wordText, heb, seq.TRANSLITERATION);
+        return [...wordSeq].map((char) => mapChars(char, schema)).join("");
+      }
+    }
+  }
+  return word;
+};
+
+// src/schema.ts
+var Schema = class {
+  constructor(schema) {
+    this.VOCAL_SHEVA = schema.VOCAL_SHEVA, this.HATAF_SEGOL = schema.HATAF_SEGOL, this.HATAF_PATAH = schema.HATAF_PATAH, this.HATAF_QAMATS = schema.HATAF_QAMATS, this.HIRIQ = schema.HIRIQ, this.TSERE = schema.TSERE, this.SEGOL = schema.SEGOL, this.PATAH = schema.PATAH, this.QAMATS = schema.QAMATS, this.HOLAM = schema.HOLAM, this.QUBUTS = schema.QUBUTS, this.DAGESH = schema.DAGESH, this.DAGESH_CHAZAQ = schema.DAGESH_CHAZAQ, this.MAQAF = schema.MAQAF, this.PASEQ = schema.PASEQ, this.SOF_PASUQ = schema.SOF_PASUQ, this.QAMATS_QATAN = schema.QAMATS_QATAN, this.FURTIVE_PATAH = schema.FURTIVE_PATAH, this.HIRIQ_YOD = schema.HIRIQ_YOD, this.TSERE_YOD = schema.TSERE_YOD, this.SEGOL_YOD = schema.SEGOL_YOD, this.SHUREQ = schema.SHUREQ, this.HOLAM_VAV = schema.HOLAM_VAV, this.QAMATS_HE = schema.QAMATS_HE, this.SEGOL_HE = schema.SEGOL_HE, this.TSERE_HE = schema.TSERE_HE, this.MS_SUFX = schema.MS_SUFX, this.ALEF = schema.ALEF, this.BET_DAGESH = schema.BET_DAGESH, this.BET = schema.BET, this.GIMEL = schema.GIMEL, this.GIMEL_DAGESH = schema.GIMEL_DAGESH, this.DALET = schema.DALET, this.DALET_DAGESH = schema.DALET_DAGESH, this.HE = schema.HE, this.VAV = schema.VAV, this.ZAYIN = schema.ZAYIN, this.HET = schema.HET, this.TET = schema.TET, this.YOD = schema.YOD, this.FINAL_KAF = schema.FINAL_KAF, this.KAF = schema.KAF, this.KAF_DAGESH = schema.KAF_DAGESH, this.LAMED = schema.LAMED, this.FINAL_MEM = schema.FINAL_MEM, this.MEM = schema.MEM, this.FINAL_NUN = schema.FINAL_NUN, this.NUN = schema.NUN, this.SAMEKH = schema.SAMEKH, this.AYIN = schema.AYIN, this.FINAL_PE = schema.FINAL_PE, this.PE = schema.PE, this.PE_DAGESH = schema.PE_DAGESH, this.FINAL_TSADI = schema.FINAL_TSADI, this.TSADI = schema.TSADI, this.QOF = schema.QOF, this.RESH = schema.RESH, this.SHIN = schema.SHIN, this.SIN = schema.SIN, this.TAV = schema.TAV, this.TAV_DAGESH = schema.TAV_DAGESH, this.DIVINE_NAME = schema.DIVINE_NAME, this.SYLLABLE_SEPARATOR = schema.SYLLABLE_SEPARATOR, this.ADDITIONAL_FEATURES = schema.ADDITIONAL_FEATURES, this.STRESS_MARKER = schema.STRESS_MARKER, this.longVowels = schema.longVowels, this.qametsQatan = schema.qametsQatan, this.sqnmlvy = schema.sqnmlvy, this.wawShureq = schema.wawShureq, this.article = schema.article;
+  }
+};
+var SBL = class extends Schema {
+  constructor(schema) {
+    super({
+      VOCAL_SHEVA: schema.VOCAL_SHEVA || "\u01DD",
+      HATAF_SEGOL: schema.HATAF_SEGOL || "\u0115",
+      HATAF_PATAH: schema.HATAF_PATAH || "\u0103",
+      HATAF_QAMATS: schema.HATAF_QAMATS || "\u014F",
+      HIRIQ: schema.HIRIQ || "i",
+      TSERE: schema.TSERE || "\u0113",
+      SEGOL: schema.SEGOL || "e",
+      PATAH: schema.PATAH || "a",
+      QAMATS: schema.QAMATS || "\u0101",
+      HOLAM: schema.HOLAM || "\u014D",
+      QUBUTS: schema.QUBUTS || "\u016B",
+      DAGESH: schema.DAGESH || "",
+      DAGESH_CHAZAQ: (_a = schema.DAGESH_CHAZAQ) != null ? _a : true,
+      MAQAF: schema.MAQAF || "-",
+      PASEQ: schema.PASEQ || "",
+      SOF_PASUQ: schema.SOF_PASUQ || "",
+      QAMATS_QATAN: schema.QAMATS_QATAN || "o",
+      FURTIVE_PATAH: schema.FURTIVE_PATAH || "a",
+      HIRIQ_YOD: schema.HIRIQ_YOD || "\xEE",
+      TSERE_YOD: schema.TSERE_YOD || "\xEA",
+      SEGOL_YOD: schema.SEGOL_YOD || "\xEA",
+      SHUREQ: schema.SHUREQ || "\xFB",
+      HOLAM_VAV: schema.HOLAM_VAV || "\xF4",
+      QAMATS_HE: schema.QAMATS_HE || "\xE2",
+      SEGOL_HE: schema.SEGOL_HE || "\xEA",
+      TSERE_HE: schema.TSERE_HE || "\xEA",
+      MS_SUFX: schema.MS_SUFX || "\u0101yw",
+      ALEF: schema.ALEF || "\u02BE",
+      BET: schema.BET || "b",
+      BET_DAGESH: schema.BET_DAGESH || void 0,
+      GIMEL: schema.GIMEL || "g",
+      GIMEL_DAGESH: schema.GIMEL_DAGESH || void 0,
+      DALET: schema.DALET || "d",
+      DALET_DAGESH: schema.DALET_DAGESH || void 0,
+      HE: schema.HE || "h",
+      VAV: schema.VAV || "w",
+      ZAYIN: schema.ZAYIN || "z",
+      HET: schema.HET || "\u1E25",
+      TET: schema.TET || "\u1E6D",
+      YOD: schema.YOD || "y",
+      FINAL_KAF: schema.FINAL_KAF || "k",
+      KAF: schema.KAF || "k",
+      KAF_DAGESH: schema.KAF_DAGESH || void 0,
+      LAMED: schema.LAMED || "l",
+      FINAL_MEM: schema.FINAL_MEM || "m",
+      MEM: schema.MEM || "m",
+      FINAL_NUN: schema.FINAL_NUN || "n",
+      NUN: schema.NUN || "n",
+      SAMEKH: schema.SAMEKH || "s",
+      AYIN: schema.AYIN || "\u02BF",
+      FINAL_PE: schema.FINAL_PE || "p",
+      PE: schema.PE || "p",
+      PE_DAGESH: schema.PE_DAGESH || void 0,
+      FINAL_TSADI: schema.FINAL_TSADI || "\u1E63",
+      TSADI: schema.TSADI || "\u1E63",
+      QOF: schema.QOF || "q",
+      RESH: schema.RESH || "r",
+      SHIN: schema.SHIN || "\u0161",
+      SIN: schema.SIN || "\u015B",
+      TAV: schema.TAV || "t",
+      TAV_DAGESH: schema.TAV_DAGESH || void 0,
+      DIVINE_NAME: schema.DIVINE_NAME || "yhwh",
+      SYLLABLE_SEPARATOR: schema.SYLLABLE_SEPARATOR || void 0,
+      ADDITIONAL_FEATURES: schema.ADDITIONAL_FEATURES || void 0,
+      STRESS_MARKER: schema.STRESS_MARKER || void 0,
+      longVowels: (_b = schema.longVowels) != null ? _b : true,
+      qametsQatan: (_c = schema.qametsQatan) != null ? _c : true,
+      sqnmlvy: (_d = schema.sqnmlvy) != null ? _d : true,
+      wawShureq: (_e = schema.wawShureq) != null ? _e : true,
+      article: (_f = schema.article) != null ? _f : true
+    });
+    var _a, _b, _c, _d, _e, _f;
+  }
+};
+
+// src/transliterate.ts
+import { Text as Text2 } from "havarotjs";
+import { Word } from "havarotjs/dist/word";
+var getSylOpts = (schema) => {
+  const options = {};
+  if ("longVowels" in schema)
+    options.longVowels = schema.longVowels;
+  if ("qametsQatan" in schema)
+    options.qametsQatan = schema.qametsQatan;
+  if ("sqnmlvy" in schema)
+    options.sqnmlvy = schema.sqnmlvy;
+  if ("wawShureq" in schema)
+    options.wawShureq = schema.wawShureq;
+  if ("article" in schema)
+    options.article = schema.article;
+  return options;
+};
+var transliterate = (text, schema) => {
+  const transSchema = schema instanceof Schema ? schema : new SBL(schema != null ? schema : {});
+  const isText = text instanceof Text2;
+  if (!isText && !vowels.test(text))
+    return mapChars(text, transSchema);
+  const sylOptions = getSylOpts(transSchema != null ? transSchema : {});
+  const newText = isText ? text : new Text2(text, sylOptions);
+  return newText.words.map((word) => {
+    var _a, _b;
+    let transliteration = wordRules(word, transSchema);
+    if (transliteration instanceof Word) {
+      transliteration = word.syllables.map((s) => sylRules(s, transSchema)).join((_a = transSchema.SYLLABLE_SEPARATOR) != null ? _a : "");
+    }
+    return `${transliteration}${(_b = word.whiteSpaceAfter) != null ? _b : ""}`;
+  }).join("");
+};
+
+// src/remove.ts
+var cantillation = /[\u{0591}-\u{05AF}\u{05BF}\u{05C0}\u{05C3}-\u{05C6}\u{05F3}\u{05F4}]/gu;
+var vowels2 = /[\u{05B0}-\u{05BD}\u{05BF}\u{05C7}]/gu;
+var shinDot = /\u{05C1}/gu;
+var sinDot = /\u{05C2}/gu;
+var removeItem = (text, item) => text.replace(item, "");
+var remove = (text, { removeVowels = false, removeShinDot = false, removeSinDot = false } = {}) => {
+  const sequenced = sequence(text);
+  const remCantillation = removeItem(sequenced, cantillation);
+  const remVowels = removeVowels ? removeItem(remCantillation, vowels2) : remCantillation;
+  const remShin = removeShinDot ? removeItem(remVowels, shinDot) : remVowels;
+  return removeSinDot ? removeItem(remShin, sinDot) : remShin;
+};
+export {
+  Schema,
+  Text3 as Text,
+  remove,
+  sequence,
+  transliterate
+};