hebrew-transliteration 2.1.2 → 2.2.1
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/README.md +17 -0
- package/dist/hebCharsTrans.d.ts +6 -0
- package/dist/hebCharsTrans.js +56 -0
- package/dist/index.d.ts +6 -659
- package/dist/index.js +12 -434
- package/dist/mapChars.d.ts +10 -0
- package/dist/mapChars.js +14 -0
- package/dist/remove.d.ts +65 -0
- package/dist/remove.js +45 -0
- package/dist/rules.d.ts +5 -0
- package/dist/rules.js +242 -0
- package/dist/schema.d.ts +476 -0
- package/dist/schema.js +161 -0
- package/dist/schemas/brillAcademic.d.ts +2 -0
- package/dist/schemas/brillAcademic.js +74 -0
- package/dist/schemas/brillSimple.d.ts +2 -0
- package/dist/schemas/brillSimple.js +73 -0
- package/dist/schemas/index.d.ts +5 -0
- package/dist/schemas/index.js +11 -0
- package/dist/schemas/michiganClaremont.d.ts +2 -0
- package/dist/schemas/michiganClaremont.js +67 -0
- package/dist/schemas/sblAcademicSpirantization.d.ts +2 -0
- package/dist/schemas/sblAcademicSpirantization.js +73 -0
- package/dist/schemas/sblSimple.d.ts +2 -0
- package/dist/schemas/sblSimple.js +70 -0
- package/dist/sequence.d.ts +18 -0
- package/dist/sequence.js +25 -0
- package/dist/transliterate.d.ts +45 -0
- package/dist/transliterate.js +88 -0
- package/package.json +21 -3
- package/dist/index.esm.js +0 -406
package/dist/index.js
CHANGED
|
@@ -1,435 +1,13 @@
|
|
|
1
1
|
"use strict";
|
|
2
|
-
|
|
3
|
-
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
};
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
__defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
|
|
15
|
-
}
|
|
16
|
-
return to;
|
|
17
|
-
};
|
|
18
|
-
var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
|
|
19
|
-
|
|
20
|
-
// src/index.ts
|
|
21
|
-
var src_exports = {};
|
|
22
|
-
__export(src_exports, {
|
|
23
|
-
Schema: () => Schema,
|
|
24
|
-
Text: () => import_havarotjs3.Text,
|
|
25
|
-
remove: () => remove,
|
|
26
|
-
sequence: () => sequence,
|
|
27
|
-
transliterate: () => transliterate
|
|
28
|
-
});
|
|
29
|
-
module.exports = __toCommonJS(src_exports);
|
|
30
|
-
var import_havarotjs3 = require("havarotjs");
|
|
31
|
-
|
|
32
|
-
// src/rules.ts
|
|
33
|
-
var import_cluster = require("havarotjs/dist/cluster");
|
|
34
|
-
|
|
35
|
-
// src/hebCharsTrans.ts
|
|
36
|
-
var transliterateMap = {
|
|
37
|
-
"\u05B0": "VOCAL_SHEVA",
|
|
38
|
-
"\u05B1": "HATAF_SEGOL",
|
|
39
|
-
"\u05B2": "HATAF_PATAH",
|
|
40
|
-
"\u05B3": "HATAF_QAMATS",
|
|
41
|
-
"\u05B4": "HIRIQ",
|
|
42
|
-
"\u05B5": "TSERE",
|
|
43
|
-
"\u05B6": "SEGOL",
|
|
44
|
-
"\u05B7": "PATAH",
|
|
45
|
-
"\u05B8": "QAMATS",
|
|
46
|
-
"\u05B9": "HOLAM",
|
|
47
|
-
"\u05BA": "HOLAM",
|
|
48
|
-
"\u05BB": "QUBUTS",
|
|
49
|
-
"\u05BC": "DAGESH",
|
|
50
|
-
"\u05BE": "MAQAF",
|
|
51
|
-
"\u05C0": "PASEQ",
|
|
52
|
-
"\u05C3": "SOF_PASUQ",
|
|
53
|
-
"\u05C7": "QAMATS_QATAN",
|
|
54
|
-
\u05D0: "ALEF",
|
|
55
|
-
\u05D1: "BET",
|
|
56
|
-
\u05D2: "GIMEL",
|
|
57
|
-
\u05D3: "DALET",
|
|
58
|
-
\u05D4: "HE",
|
|
59
|
-
\u05D5: "VAV",
|
|
60
|
-
\u05D6: "ZAYIN",
|
|
61
|
-
\u05D7: "HET",
|
|
62
|
-
\u05D8: "TET",
|
|
63
|
-
\u05D9: "YOD",
|
|
64
|
-
\u05DA: "FINAL_KAF",
|
|
65
|
-
\u05DB: "KAF",
|
|
66
|
-
\u05DC: "LAMED",
|
|
67
|
-
\u05DD: "FINAL_MEM",
|
|
68
|
-
\u05DE: "MEM",
|
|
69
|
-
\u05DF: "FINAL_NUN",
|
|
70
|
-
\u05E0: "NUN",
|
|
71
|
-
\u05E1: "SAMEKH",
|
|
72
|
-
\u05E2: "AYIN",
|
|
73
|
-
\u05E3: "FINAL_PE",
|
|
74
|
-
\u05E4: "PE",
|
|
75
|
-
\u05E5: "FINAL_TSADI",
|
|
76
|
-
\u05E6: "TSADI",
|
|
77
|
-
\u05E7: "QOF",
|
|
78
|
-
\u05E8: "RESH",
|
|
79
|
-
\u05E9: "SHIN",
|
|
80
|
-
\u05EA: "TAV"
|
|
81
|
-
};
|
|
82
|
-
|
|
83
|
-
// src/mapChars.ts
|
|
84
|
-
var mapChars = (text, schema) => [...text].map((char) => char in transliterateMap ? schema[transliterateMap[char]] : char).join("");
|
|
85
|
-
|
|
86
|
-
// src/rules.ts
|
|
87
|
-
var taamim = /[\u{0590}-\u{05AF}\u{05BD}\u{05BF}]/u;
|
|
88
|
-
var changeElementSplit = (input, split, join) => input.split(split).join(join);
|
|
89
|
-
var consonantFeatures = (clusterText, syl, cluster, schema) => {
|
|
90
|
-
var _a;
|
|
91
|
-
if ((_a = schema.ADDITIONAL_FEATURES) == null ? void 0 : _a.length) {
|
|
92
|
-
const clusterSeqs = schema.ADDITIONAL_FEATURES.filter((s) => s.FEATURE === "cluster");
|
|
93
|
-
for (const seq of clusterSeqs) {
|
|
94
|
-
const heb = new RegExp(seq.HEBREW, "u");
|
|
95
|
-
if (heb.test(clusterText)) {
|
|
96
|
-
const sylSeq = changeElementSplit(clusterText, heb, seq.TRANSLITERATION);
|
|
97
|
-
return [...sylSeq].map((char) => mapChars(char, schema)).join("");
|
|
98
|
-
}
|
|
99
|
-
}
|
|
100
|
-
}
|
|
101
|
-
clusterText = cluster.hasShewa && syl.isClosed ? clusterText.replace(/\u{05B0}/u, "") : clusterText;
|
|
102
|
-
if (/ה\u{05BC}$/mu.test(clusterText)) {
|
|
103
|
-
return changeElementSplit(clusterText, /ה\u{05BC}/u, schema.HE);
|
|
104
|
-
}
|
|
105
|
-
if (syl.isFinal && !syl.isClosed) {
|
|
106
|
-
const furtiveChet = /\u{05D7}\u{05B7}$/mu;
|
|
107
|
-
if (furtiveChet.test(clusterText)) {
|
|
108
|
-
return changeElementSplit(clusterText, furtiveChet, "\u05B7\u05D7");
|
|
109
|
-
}
|
|
110
|
-
const furtiveAyin = /\u{05E2}\u{05B7}$/mu;
|
|
111
|
-
if (furtiveAyin.test(clusterText)) {
|
|
112
|
-
return changeElementSplit(clusterText, furtiveAyin, "\u05B7\u05E2");
|
|
113
|
-
}
|
|
114
|
-
const furtiveHe = /\u{05D4}\u{05BC}\u{05B7}$/mu;
|
|
115
|
-
if (furtiveHe.test(clusterText)) {
|
|
116
|
-
return changeElementSplit(clusterText, furtiveHe, "\u05B7\u05D4\u05BC");
|
|
117
|
-
}
|
|
118
|
-
}
|
|
119
|
-
const prevHasVowel = cluster.prev instanceof import_cluster.Cluster ? cluster.prev.hasVowel : false;
|
|
120
|
-
const isDoubled = schema.DAGESH_CHAZAQ && prevHasVowel && /\u{05BC}/u.test(clusterText);
|
|
121
|
-
if (schema.BET_DAGESH && /ב\u{05BC}/u.test(clusterText)) {
|
|
122
|
-
return changeElementSplit(clusterText, /ב\u{05BC}/u, schema.BET_DAGESH.repeat(isDoubled ? 2 : 1));
|
|
123
|
-
}
|
|
124
|
-
if (schema.GIMEL_DAGESH && /ג\u{05BC}/u.test(clusterText)) {
|
|
125
|
-
return changeElementSplit(clusterText, /ג\u{05BC}/u, schema.GIMEL_DAGESH.repeat(isDoubled ? 2 : 1));
|
|
126
|
-
}
|
|
127
|
-
if (schema.DALET_DAGESH && /ד\u{05BC}/u.test(clusterText)) {
|
|
128
|
-
return changeElementSplit(clusterText, /ד\u{05BC}/u, schema.DALET_DAGESH.repeat(isDoubled ? 2 : 1));
|
|
129
|
-
}
|
|
130
|
-
if (schema.KAF_DAGESH && /כ\u{05BC}/u.test(clusterText)) {
|
|
131
|
-
return changeElementSplit(clusterText, /כ\u{05BC}/u, schema.KAF_DAGESH.repeat(isDoubled ? 2 : 1));
|
|
132
|
-
}
|
|
133
|
-
if (schema.KAF_DAGESH && /ך\u{05BC}/u.test(clusterText)) {
|
|
134
|
-
return changeElementSplit(clusterText, /ך\u{05BC}/u, schema.KAF_DAGESH.repeat(isDoubled ? 2 : 1));
|
|
135
|
-
}
|
|
136
|
-
if (schema.PE_DAGESH && /פ\u{05BC}/u.test(clusterText)) {
|
|
137
|
-
return changeElementSplit(clusterText, /פ\u{05BC}/u, schema.PE_DAGESH.repeat(isDoubled ? 2 : 1));
|
|
138
|
-
}
|
|
139
|
-
if (schema.TAV_DAGESH && /ת\u{05BC}/u.test(clusterText)) {
|
|
140
|
-
return changeElementSplit(clusterText, /ת\u{05BC}/u, schema.TAV_DAGESH.repeat(isDoubled ? 2 : 1));
|
|
141
|
-
}
|
|
142
|
-
if (/ש\u{05C1}/u.test(clusterText)) {
|
|
143
|
-
return changeElementSplit(clusterText, /ש\u{05C1}/u, schema.SHIN.repeat(isDoubled ? 2 : 1));
|
|
144
|
-
}
|
|
145
|
-
if (/ש\u{05C2}/u.test(clusterText)) {
|
|
146
|
-
return changeElementSplit(clusterText, /ש\u{05C2}/u, schema.SIN.repeat(isDoubled ? 2 : 1));
|
|
147
|
-
}
|
|
148
|
-
if (isDoubled) {
|
|
149
|
-
const consonant = cluster.chars[0].text;
|
|
150
|
-
const consonantDagesh = new RegExp(consonant + "\u05BC", "u");
|
|
151
|
-
return changeElementSplit(clusterText, consonantDagesh, `${consonant + consonant}`);
|
|
152
|
-
}
|
|
153
|
-
if (cluster.isShureq) {
|
|
154
|
-
return schema.SHUREQ;
|
|
155
|
-
}
|
|
156
|
-
return clusterText;
|
|
157
|
-
};
|
|
158
|
-
var materFeatures = (syl, schema) => {
|
|
159
|
-
const mater = syl.clusters.filter((c) => c.isMater)[0];
|
|
160
|
-
const prev = mater.prev instanceof import_cluster.Cluster ? mater.prev : null;
|
|
161
|
-
const materText = mater.text;
|
|
162
|
-
const prevText = ((prev == null ? void 0 : prev.text) || "").replace(taamim, "");
|
|
163
|
-
let noMaterText = syl.clusters.filter((c) => !c.isMater).map((c) => consonantFeatures(c.text.replace(taamim, ""), syl, c, schema)).join("");
|
|
164
|
-
const hasMaqaf = mater.text.includes("\u05BE");
|
|
165
|
-
noMaterText = hasMaqaf ? noMaterText.concat("\u05BE") : noMaterText;
|
|
166
|
-
if (/י/.test(materText)) {
|
|
167
|
-
if (/\u{05B4}/u.test(prevText)) {
|
|
168
|
-
return changeElementSplit(noMaterText, /\u{05B4}/u, schema.HIRIQ_YOD);
|
|
169
|
-
}
|
|
170
|
-
if (/\u{05B5}/u.test(prevText)) {
|
|
171
|
-
return changeElementSplit(noMaterText, /\u{05B5}/u, schema.TSERE_YOD);
|
|
172
|
-
}
|
|
173
|
-
if (/\u{05B6}/u.test(prevText)) {
|
|
174
|
-
return changeElementSplit(noMaterText, /\u{05B6}/u, schema.SEGOL_YOD);
|
|
175
|
-
}
|
|
176
|
-
}
|
|
177
|
-
if (/ו/u.test(materText)) {
|
|
178
|
-
if (/\u{05B9}/u.test(prevText)) {
|
|
179
|
-
return changeElementSplit(noMaterText, /\u{05B9}/u, schema.HOLAM_VAV);
|
|
180
|
-
}
|
|
181
|
-
}
|
|
182
|
-
if (/ה/.test(materText)) {
|
|
183
|
-
if (/\u{05B8}/u.test(prevText)) {
|
|
184
|
-
return changeElementSplit(noMaterText, /\u{05B8}/u, schema.QAMATS_HE);
|
|
185
|
-
}
|
|
186
|
-
if (/\u{05B6}/u.test(prevText)) {
|
|
187
|
-
return changeElementSplit(noMaterText, /\u{05B6}/u, schema.SEGOL_HE);
|
|
188
|
-
}
|
|
189
|
-
if (/\u{05B5}/u.test(prevText)) {
|
|
190
|
-
return changeElementSplit(noMaterText, /\u{05B5}/u, schema.SEGOL_HE);
|
|
191
|
-
}
|
|
192
|
-
}
|
|
193
|
-
return materText;
|
|
194
|
-
};
|
|
195
|
-
var joinChars = (isAccented, sylChars, schema) => {
|
|
196
|
-
if (!isAccented) {
|
|
197
|
-
return sylChars.map((char) => mapChars(char, schema)).join("");
|
|
198
|
-
}
|
|
199
|
-
if (schema.STRESS_MARKER) {
|
|
200
|
-
const location = schema.STRESS_MARKER.location;
|
|
201
|
-
const mark = schema.STRESS_MARKER.mark;
|
|
202
|
-
if (location === "before-syllable") {
|
|
203
|
-
return `${mark}${sylChars.map((char) => mapChars(char, schema)).join("")}`;
|
|
204
|
-
}
|
|
205
|
-
if (location === "after-syllable") {
|
|
206
|
-
return `${sylChars.map((char) => mapChars(char, schema)).join("")}${mark}`;
|
|
207
|
-
}
|
|
208
|
-
const vowels3 = [
|
|
209
|
-
schema.PATAH,
|
|
210
|
-
schema.HATAF_PATAH,
|
|
211
|
-
schema.QAMATS,
|
|
212
|
-
schema.HATAF_QAMATS,
|
|
213
|
-
schema.SEGOL,
|
|
214
|
-
schema.HATAF_SEGOL,
|
|
215
|
-
schema.TSERE,
|
|
216
|
-
schema.HIRIQ,
|
|
217
|
-
schema.HOLAM,
|
|
218
|
-
schema.QAMATS_QATAN,
|
|
219
|
-
schema.QUBUTS,
|
|
220
|
-
schema.QAMATS_HE,
|
|
221
|
-
schema.SEGOL_HE,
|
|
222
|
-
schema.TSERE_HE,
|
|
223
|
-
schema.HIRIQ_YOD,
|
|
224
|
-
schema.TSERE_YOD,
|
|
225
|
-
schema.SEGOL_YOD,
|
|
226
|
-
schema.HOLAM_VAV,
|
|
227
|
-
schema.SHUREQ
|
|
228
|
-
].sort((a, b) => b.length - a.length);
|
|
229
|
-
const vowelRgx = new RegExp(`${vowels3.join("|")}`);
|
|
230
|
-
const str = sylChars.map((char) => mapChars(char, schema)).join("");
|
|
231
|
-
const match = str.match(vowelRgx);
|
|
232
|
-
if (location === "before-vowel") {
|
|
233
|
-
return (match == null ? void 0 : match.length) ? str.replace(match[0], `${mark}${match[0]}`) : str;
|
|
234
|
-
}
|
|
235
|
-
return (match == null ? void 0 : match.length) ? str.replace(match[0], `${match[0]}${mark}`) : str;
|
|
236
|
-
}
|
|
237
|
-
return sylChars.map((char) => mapChars(char, schema)).join("");
|
|
238
|
-
};
|
|
239
|
-
var sylRules = (syl, schema) => {
|
|
240
|
-
var _a;
|
|
241
|
-
const sylTxt = syl.text.replace(taamim, "");
|
|
242
|
-
if ((_a = schema.ADDITIONAL_FEATURES) == null ? void 0 : _a.length) {
|
|
243
|
-
const sylSeqs = schema.ADDITIONAL_FEATURES.filter((s) => s.FEATURE === "syllable");
|
|
244
|
-
for (const seq of sylSeqs) {
|
|
245
|
-
const heb = new RegExp(seq.HEBREW, "u");
|
|
246
|
-
if (heb.test(sylTxt)) {
|
|
247
|
-
const wordSeq = changeElementSplit(sylTxt, heb, seq.TRANSLITERATION);
|
|
248
|
-
return joinChars(syl.isAccented, [...wordSeq], schema);
|
|
249
|
-
}
|
|
250
|
-
}
|
|
251
|
-
}
|
|
252
|
-
const mSSuffix = /\u{05B8}\u{05D9}\u{05D5}/u;
|
|
253
|
-
if (syl.isFinal && mSSuffix.test(sylTxt)) {
|
|
254
|
-
const sufxSyl = changeElementSplit(sylTxt, mSSuffix, schema.MS_SUFX);
|
|
255
|
-
return joinChars(syl.isAccented, [...sufxSyl], schema);
|
|
256
|
-
}
|
|
257
|
-
const hasMater = syl.clusters.map((c) => c.isMater).includes(true);
|
|
258
|
-
if (hasMater) {
|
|
259
|
-
const materSyl = materFeatures(syl, schema);
|
|
260
|
-
return joinChars(syl.isAccented, [...materSyl], schema);
|
|
261
|
-
}
|
|
262
|
-
const returnTxt = syl.clusters.map((cluster) => {
|
|
263
|
-
const clusterText = cluster.text.replace(taamim, "");
|
|
264
|
-
return consonantFeatures(clusterText, syl, cluster, schema);
|
|
265
|
-
});
|
|
266
|
-
return joinChars(syl.isAccented, returnTxt, schema);
|
|
267
|
-
};
|
|
268
|
-
var wordRules = (word, schema) => {
|
|
269
|
-
var _a;
|
|
270
|
-
if (word.isDivineName)
|
|
271
|
-
return schema.DIVINE_NAME;
|
|
272
|
-
if (word.hasDivineName)
|
|
273
|
-
return `${sylRules(word.syllables[0], schema)}-${schema.DIVINE_NAME}`;
|
|
274
|
-
if (word.isNotHebrew)
|
|
275
|
-
return word.text;
|
|
276
|
-
if ((_a = schema.ADDITIONAL_FEATURES) == null ? void 0 : _a.length) {
|
|
277
|
-
const wordSeqs = schema.ADDITIONAL_FEATURES.filter((s) => s.FEATURE === "word");
|
|
278
|
-
for (const seq of wordSeqs) {
|
|
279
|
-
const heb = new RegExp(seq.HEBREW, "u");
|
|
280
|
-
const wordText = word.text.replace(taamim, "");
|
|
281
|
-
if (heb.test(wordText)) {
|
|
282
|
-
const wordSeq = changeElementSplit(wordText, heb, seq.TRANSLITERATION);
|
|
283
|
-
return [...wordSeq].map((char) => mapChars(char, schema)).join("");
|
|
284
|
-
}
|
|
285
|
-
}
|
|
286
|
-
}
|
|
287
|
-
return word;
|
|
288
|
-
};
|
|
289
|
-
|
|
290
|
-
// src/schema.ts
|
|
291
|
-
var Schema = class {
|
|
292
|
-
constructor(schema) {
|
|
293
|
-
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;
|
|
294
|
-
this.allowNoNiqqud = schema.allowNoNiqqud;
|
|
295
|
-
}
|
|
296
|
-
};
|
|
297
|
-
var SBL = class extends Schema {
|
|
298
|
-
constructor(schema) {
|
|
299
|
-
var _a, _b, _c, _d, _e, _f, _g;
|
|
300
|
-
super({
|
|
301
|
-
VOCAL_SHEVA: schema.VOCAL_SHEVA || "\u01DD",
|
|
302
|
-
HATAF_SEGOL: schema.HATAF_SEGOL || "\u0115",
|
|
303
|
-
HATAF_PATAH: schema.HATAF_PATAH || "\u0103",
|
|
304
|
-
HATAF_QAMATS: schema.HATAF_QAMATS || "\u014F",
|
|
305
|
-
HIRIQ: schema.HIRIQ || "i",
|
|
306
|
-
TSERE: schema.TSERE || "\u0113",
|
|
307
|
-
SEGOL: schema.SEGOL || "e",
|
|
308
|
-
PATAH: schema.PATAH || "a",
|
|
309
|
-
QAMATS: schema.QAMATS || "\u0101",
|
|
310
|
-
HOLAM: schema.HOLAM || "\u014D",
|
|
311
|
-
QUBUTS: schema.QUBUTS || "\u016B",
|
|
312
|
-
DAGESH: schema.DAGESH || "",
|
|
313
|
-
DAGESH_CHAZAQ: (_a = schema.DAGESH_CHAZAQ) != null ? _a : true,
|
|
314
|
-
MAQAF: schema.MAQAF || "-",
|
|
315
|
-
PASEQ: schema.PASEQ || "",
|
|
316
|
-
SOF_PASUQ: schema.SOF_PASUQ || "",
|
|
317
|
-
QAMATS_QATAN: schema.QAMATS_QATAN || "o",
|
|
318
|
-
FURTIVE_PATAH: schema.FURTIVE_PATAH || "a",
|
|
319
|
-
HIRIQ_YOD: schema.HIRIQ_YOD || "\xEE",
|
|
320
|
-
TSERE_YOD: schema.TSERE_YOD || "\xEA",
|
|
321
|
-
SEGOL_YOD: schema.SEGOL_YOD || "\xEA",
|
|
322
|
-
SHUREQ: schema.SHUREQ || "\xFB",
|
|
323
|
-
HOLAM_VAV: schema.HOLAM_VAV || "\xF4",
|
|
324
|
-
QAMATS_HE: schema.QAMATS_HE || "\xE2",
|
|
325
|
-
SEGOL_HE: schema.SEGOL_HE || "\xEA",
|
|
326
|
-
TSERE_HE: schema.TSERE_HE || "\xEA",
|
|
327
|
-
MS_SUFX: schema.MS_SUFX || "\u0101yw",
|
|
328
|
-
ALEF: schema.ALEF || "\u02BE",
|
|
329
|
-
BET: schema.BET || "b",
|
|
330
|
-
BET_DAGESH: schema.BET_DAGESH || void 0,
|
|
331
|
-
GIMEL: schema.GIMEL || "g",
|
|
332
|
-
GIMEL_DAGESH: schema.GIMEL_DAGESH || void 0,
|
|
333
|
-
DALET: schema.DALET || "d",
|
|
334
|
-
DALET_DAGESH: schema.DALET_DAGESH || void 0,
|
|
335
|
-
HE: schema.HE || "h",
|
|
336
|
-
VAV: schema.VAV || "w",
|
|
337
|
-
ZAYIN: schema.ZAYIN || "z",
|
|
338
|
-
HET: schema.HET || "\u1E25",
|
|
339
|
-
TET: schema.TET || "\u1E6D",
|
|
340
|
-
YOD: schema.YOD || "y",
|
|
341
|
-
FINAL_KAF: schema.FINAL_KAF || "k",
|
|
342
|
-
KAF: schema.KAF || "k",
|
|
343
|
-
KAF_DAGESH: schema.KAF_DAGESH || void 0,
|
|
344
|
-
LAMED: schema.LAMED || "l",
|
|
345
|
-
FINAL_MEM: schema.FINAL_MEM || "m",
|
|
346
|
-
MEM: schema.MEM || "m",
|
|
347
|
-
FINAL_NUN: schema.FINAL_NUN || "n",
|
|
348
|
-
NUN: schema.NUN || "n",
|
|
349
|
-
SAMEKH: schema.SAMEKH || "s",
|
|
350
|
-
AYIN: schema.AYIN || "\u02BF",
|
|
351
|
-
FINAL_PE: schema.FINAL_PE || "p",
|
|
352
|
-
PE: schema.PE || "p",
|
|
353
|
-
PE_DAGESH: schema.PE_DAGESH || void 0,
|
|
354
|
-
FINAL_TSADI: schema.FINAL_TSADI || "\u1E63",
|
|
355
|
-
TSADI: schema.TSADI || "\u1E63",
|
|
356
|
-
QOF: schema.QOF || "q",
|
|
357
|
-
RESH: schema.RESH || "r",
|
|
358
|
-
SHIN: schema.SHIN || "\u0161",
|
|
359
|
-
SIN: schema.SIN || "\u015B",
|
|
360
|
-
TAV: schema.TAV || "t",
|
|
361
|
-
TAV_DAGESH: schema.TAV_DAGESH || void 0,
|
|
362
|
-
DIVINE_NAME: schema.DIVINE_NAME || "yhwh",
|
|
363
|
-
SYLLABLE_SEPARATOR: schema.SYLLABLE_SEPARATOR || void 0,
|
|
364
|
-
ADDITIONAL_FEATURES: schema.ADDITIONAL_FEATURES || void 0,
|
|
365
|
-
STRESS_MARKER: schema.STRESS_MARKER || void 0,
|
|
366
|
-
longVowels: (_b = schema.longVowels) != null ? _b : true,
|
|
367
|
-
qametsQatan: (_c = schema.qametsQatan) != null ? _c : true,
|
|
368
|
-
sqnmlvy: (_d = schema.sqnmlvy) != null ? _d : true,
|
|
369
|
-
wawShureq: (_e = schema.wawShureq) != null ? _e : true,
|
|
370
|
-
article: (_f = schema.article) != null ? _f : true,
|
|
371
|
-
allowNoNiqqud: (_g = schema.allowNoNiqqud) != null ? _g : true
|
|
372
|
-
});
|
|
373
|
-
}
|
|
374
|
-
};
|
|
375
|
-
|
|
376
|
-
// src/transliterate.ts
|
|
377
|
-
var import_havarotjs = require("havarotjs");
|
|
378
|
-
var import_word = require("havarotjs/dist/word");
|
|
379
|
-
var getSylOpts = (schema) => {
|
|
380
|
-
const options = {};
|
|
381
|
-
if ("longVowels" in schema)
|
|
382
|
-
options.longVowels = schema.longVowels;
|
|
383
|
-
if ("qametsQatan" in schema)
|
|
384
|
-
options.qametsQatan = schema.qametsQatan;
|
|
385
|
-
if ("sqnmlvy" in schema)
|
|
386
|
-
options.sqnmlvy = schema.sqnmlvy;
|
|
387
|
-
if ("wawShureq" in schema)
|
|
388
|
-
options.wawShureq = schema.wawShureq;
|
|
389
|
-
if ("article" in schema)
|
|
390
|
-
options.article = schema.article;
|
|
391
|
-
if ("allowNoNiqqud" in schema)
|
|
392
|
-
options.allowNoNiqqud = schema.allowNoNiqqud;
|
|
393
|
-
return options;
|
|
394
|
-
};
|
|
395
|
-
var transliterate = (text, schema) => {
|
|
396
|
-
const transSchema = schema instanceof Schema ? schema : new SBL(schema != null ? schema : {});
|
|
397
|
-
const newText = text instanceof import_havarotjs.Text ? text : new import_havarotjs.Text(text, getSylOpts(transSchema != null ? transSchema : {}));
|
|
398
|
-
return newText.words.map((word) => {
|
|
399
|
-
var _a, _b;
|
|
400
|
-
let transliteration = wordRules(word, transSchema);
|
|
401
|
-
if (transliteration instanceof import_word.Word) {
|
|
402
|
-
transliteration = word.syllables.map((s) => sylRules(s, transSchema)).join((_a = transSchema.SYLLABLE_SEPARATOR) != null ? _a : "");
|
|
403
|
-
}
|
|
404
|
-
return `${transliteration}${(_b = word.whiteSpaceAfter) != null ? _b : ""}`;
|
|
405
|
-
}).join("");
|
|
406
|
-
};
|
|
407
|
-
|
|
408
|
-
// src/sequence.ts
|
|
409
|
-
var import_havarotjs2 = require("havarotjs");
|
|
410
|
-
var vowels = /[\u{05B0}-\u{05BC}\u{05C7}]/u;
|
|
411
|
-
var sequence = (text, qametsQatan = false) => {
|
|
412
|
-
return vowels.test(text) ? new import_havarotjs2.Text(text, { qametsQatan }).text : text;
|
|
413
|
-
};
|
|
414
|
-
|
|
415
|
-
// src/remove.ts
|
|
416
|
-
var cantillation = /[\u{0591}-\u{05AF}\u{05BF}\u{05C0}\u{05C3}-\u{05C6}\u{05F3}\u{05F4}]/gu;
|
|
417
|
-
var vowels2 = /[\u{05B0}-\u{05BD}\u{05BF}\u{05C7}]/gu;
|
|
418
|
-
var shinDot = /\u{05C1}/gu;
|
|
419
|
-
var sinDot = /\u{05C2}/gu;
|
|
420
|
-
var removeItem = (text, item) => text.replace(item, "");
|
|
421
|
-
var remove = (text, { removeVowels = false, removeShinDot = false, removeSinDot = false } = {}) => {
|
|
422
|
-
const sequenced = sequence(text);
|
|
423
|
-
const remCantillation = removeItem(sequenced, cantillation);
|
|
424
|
-
const remVowels = removeVowels ? removeItem(remCantillation, vowels2) : remCantillation;
|
|
425
|
-
const remShin = removeShinDot ? removeItem(remVowels, shinDot) : remVowels;
|
|
426
|
-
return removeSinDot ? removeItem(remShin, sinDot) : remShin;
|
|
427
|
-
};
|
|
428
|
-
// Annotate the CommonJS export names for ESM import in node:
|
|
429
|
-
0 && (module.exports = {
|
|
430
|
-
Schema,
|
|
431
|
-
Text,
|
|
432
|
-
remove,
|
|
433
|
-
sequence,
|
|
434
|
-
transliterate
|
|
435
|
-
});
|
|
2
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
3
|
+
exports.transliterate = exports.Text = exports.sequence = exports.Schema = exports.remove = void 0;
|
|
4
|
+
const havarotjs_1 = require("havarotjs");
|
|
5
|
+
Object.defineProperty(exports, "Text", { enumerable: true, get: function () { return havarotjs_1.Text; } });
|
|
6
|
+
const transliterate_1 = require("./transliterate");
|
|
7
|
+
Object.defineProperty(exports, "transliterate", { enumerable: true, get: function () { return transliterate_1.transliterate; } });
|
|
8
|
+
const sequence_1 = require("./sequence");
|
|
9
|
+
Object.defineProperty(exports, "sequence", { enumerable: true, get: function () { return sequence_1.sequence; } });
|
|
10
|
+
const remove_1 = require("./remove");
|
|
11
|
+
Object.defineProperty(exports, "remove", { enumerable: true, get: function () { return remove_1.remove; } });
|
|
12
|
+
const schema_1 = require("./schema");
|
|
13
|
+
Object.defineProperty(exports, "Schema", { enumerable: true, get: function () { return schema_1.Schema; } });
|
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
import { Schema } from "./schema";
|
|
2
|
+
/**
|
|
3
|
+
* maps single Hebrew characters to transliteration characters according to the schema
|
|
4
|
+
*
|
|
5
|
+
* @param text - a single character
|
|
6
|
+
* @param schema - a {@link Schema} for transliterating the text
|
|
7
|
+
* @returns transliteration of single characters according to the schema
|
|
8
|
+
*
|
|
9
|
+
*/
|
|
10
|
+
export declare const mapChars: (text: string, schema: Schema) => string;
|
package/dist/mapChars.js
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
3
|
+
exports.mapChars = void 0;
|
|
4
|
+
const hebCharsTrans_1 = require("./hebCharsTrans");
|
|
5
|
+
/**
|
|
6
|
+
* maps single Hebrew characters to transliteration characters according to the schema
|
|
7
|
+
*
|
|
8
|
+
* @param text - a single character
|
|
9
|
+
* @param schema - a {@link Schema} for transliterating the text
|
|
10
|
+
* @returns transliteration of single characters according to the schema
|
|
11
|
+
*
|
|
12
|
+
*/
|
|
13
|
+
const mapChars = (text, schema) => [...text].map((char) => (char in hebCharsTrans_1.transliterateMap ? schema[hebCharsTrans_1.transliterateMap[char]] : char)).join("");
|
|
14
|
+
exports.mapChars = mapChars;
|
package/dist/remove.d.ts
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Options for the `remove()` function
|
|
3
|
+
*/
|
|
4
|
+
interface RemoveOptions {
|
|
5
|
+
/**
|
|
6
|
+
* an option to remove vowels
|
|
7
|
+
*
|
|
8
|
+
* @example
|
|
9
|
+
* ```ts
|
|
10
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔", { removeVowels: true });
|
|
11
|
+
* // "שׂרי אשׁתך";
|
|
12
|
+
* ```
|
|
13
|
+
*/
|
|
14
|
+
removeVowels?: boolean;
|
|
15
|
+
/**
|
|
16
|
+
* an option to remove the shin dot (U+05C1)
|
|
17
|
+
*
|
|
18
|
+
* @example
|
|
19
|
+
* ```ts
|
|
20
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔", { removeVowels: true, removeShinDot: true, removeSinDot: true });
|
|
21
|
+
* // "שרי אשתך";
|
|
22
|
+
* ```
|
|
23
|
+
*/
|
|
24
|
+
removeShinDot?: boolean;
|
|
25
|
+
/**
|
|
26
|
+
* an option to remove the sin dot (U+05C2)
|
|
27
|
+
*
|
|
28
|
+
* @example
|
|
29
|
+
* ```ts
|
|
30
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔", { removeVowels: true, removeShinDot: true, removeSinDot: true });
|
|
31
|
+
* // "שרי אשתך";
|
|
32
|
+
* ```
|
|
33
|
+
*/
|
|
34
|
+
removeSinDot?: boolean;
|
|
35
|
+
}
|
|
36
|
+
/**
|
|
37
|
+
* removes taamim and optionally removes certain niqqudim
|
|
38
|
+
*
|
|
39
|
+
* @param text - a string of Hebrew characters
|
|
40
|
+
* @param RemoveOptions - {@link RemoveOptions}
|
|
41
|
+
* @returns Hebrew characters with taamim and niqqud optionally removed
|
|
42
|
+
*
|
|
43
|
+
* @example Default
|
|
44
|
+
*
|
|
45
|
+
* ```ts
|
|
46
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔");
|
|
47
|
+
* // "שָׂרַי אִשְׁתְּךָ";
|
|
48
|
+
* ```
|
|
49
|
+
*
|
|
50
|
+
* @example Remove vowels
|
|
51
|
+
*
|
|
52
|
+
* ```ts
|
|
53
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔", { removeVowels: true });
|
|
54
|
+
* // "שׂרי אשׁתך";
|
|
55
|
+
* ```
|
|
56
|
+
*
|
|
57
|
+
* @example Remove all
|
|
58
|
+
*
|
|
59
|
+
* ```ts
|
|
60
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔", { removeVowels: true, removeShinDot: true, removeSinDot: true });
|
|
61
|
+
* // "שרי אשתך";
|
|
62
|
+
* ```
|
|
63
|
+
*/
|
|
64
|
+
export declare const remove: (text: string, { removeVowels, removeShinDot, removeSinDot }?: RemoveOptions) => string;
|
|
65
|
+
export {};
|
package/dist/remove.js
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
3
|
+
exports.remove = void 0;
|
|
4
|
+
const sequence_1 = require("./sequence");
|
|
5
|
+
const cantillation = /[\u{0591}-\u{05AF}\u{05BF}\u{05C0}\u{05C3}-\u{05C6}\u{05F3}\u{05F4}]/gu;
|
|
6
|
+
const vowels = /[\u{05B0}-\u{05BD}\u{05BF}\u{05C7}]/gu;
|
|
7
|
+
const shinDot = /\u{05C1}/gu;
|
|
8
|
+
const sinDot = /\u{05C2}/gu;
|
|
9
|
+
const removeItem = (text, item) => text.replace(item, "");
|
|
10
|
+
/**
|
|
11
|
+
* removes taamim and optionally removes certain niqqudim
|
|
12
|
+
*
|
|
13
|
+
* @param text - a string of Hebrew characters
|
|
14
|
+
* @param RemoveOptions - {@link RemoveOptions}
|
|
15
|
+
* @returns Hebrew characters with taamim and niqqud optionally removed
|
|
16
|
+
*
|
|
17
|
+
* @example Default
|
|
18
|
+
*
|
|
19
|
+
* ```ts
|
|
20
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔");
|
|
21
|
+
* // "שָׂרַי אִשְׁתְּךָ";
|
|
22
|
+
* ```
|
|
23
|
+
*
|
|
24
|
+
* @example Remove vowels
|
|
25
|
+
*
|
|
26
|
+
* ```ts
|
|
27
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔", { removeVowels: true });
|
|
28
|
+
* // "שׂרי אשׁתך";
|
|
29
|
+
* ```
|
|
30
|
+
*
|
|
31
|
+
* @example Remove all
|
|
32
|
+
*
|
|
33
|
+
* ```ts
|
|
34
|
+
* heb.remove("שָׂרַ֣י אִשְׁתְּךָ֔", { removeVowels: true, removeShinDot: true, removeSinDot: true });
|
|
35
|
+
* // "שרי אשתך";
|
|
36
|
+
* ```
|
|
37
|
+
*/
|
|
38
|
+
const remove = (text, { removeVowels = false, removeShinDot = false, removeSinDot = false } = {}) => {
|
|
39
|
+
const sequenced = (0, sequence_1.sequence)(text);
|
|
40
|
+
const remCantillation = removeItem(sequenced, cantillation);
|
|
41
|
+
const remVowels = removeVowels ? removeItem(remCantillation, vowels) : remCantillation;
|
|
42
|
+
const remShin = removeShinDot ? removeItem(remVowels, shinDot) : remVowels;
|
|
43
|
+
return removeSinDot ? removeItem(remShin, sinDot) : remShin;
|
|
44
|
+
};
|
|
45
|
+
exports.remove = remove;
|
package/dist/rules.d.ts
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
1
|
+
import { Syllable } from "havarotjs/dist/syllable";
|
|
2
|
+
import { Word } from "havarotjs/dist/word";
|
|
3
|
+
import { Schema } from "./schema";
|
|
4
|
+
export declare const sylRules: (syl: Syllable, schema: Schema) => string;
|
|
5
|
+
export declare const wordRules: (word: Word, schema: Schema) => string | Word;
|