@chr33s/pdf-codepoints 5.0.0

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.
@@ -0,0 +1,5 @@
1
+ import parser from "./parser.js";
2
+ declare const codePoints: import("./parser.js").CodePointTable;
3
+ export default codePoints;
4
+ export * from "./parser.js";
5
+ export { parser };
package/dist/index.js ADDED
@@ -0,0 +1,6 @@
1
+ import parser from "./parser.js";
2
+ const codePoints = parser();
3
+ export default codePoints;
4
+ export * from "./parser.js";
5
+ export { parser };
6
+ //# sourceMappingURL=index.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,MAAM,MAAM,aAAa,CAAC;AAEjC,MAAM,UAAU,GAAG,MAAM,EAAE,CAAC;AAE5B,eAAe,UAAU,CAAC;AAC1B,cAAc,aAAa,CAAC;AAC5B,OAAO,EAAE,MAAM,EAAE,CAAC"}
@@ -0,0 +1,35 @@
1
+ export type CodePointRange = [number, number];
2
+ export interface CodePoint {
3
+ code: number;
4
+ name: string;
5
+ unicode1Name: string | null;
6
+ isoComment: string | null;
7
+ category: string;
8
+ block: string | null;
9
+ script: string | null;
10
+ eastAsianWidth: string | null;
11
+ combiningClass: number;
12
+ combiningClassName: string | null;
13
+ bidiClass: string;
14
+ bidiMirrored: boolean;
15
+ numeric: string | null;
16
+ uppercase: number[] | null;
17
+ lowercase: number[] | null;
18
+ titlecase: number[] | null;
19
+ folded: number[] | null;
20
+ caseConditions: string[] | null;
21
+ decomposition: number[];
22
+ compositions: Record<number, number>;
23
+ isCompat: boolean;
24
+ isExcluded: boolean;
25
+ joiningType: string | null;
26
+ joiningGroup: string | null;
27
+ indicSyllabicCategory: string | null;
28
+ indicPositionalCategory: string | null;
29
+ NFD_QC: number;
30
+ NFKD_QC: number;
31
+ NFC_QC: number;
32
+ NFKC_QC: number;
33
+ }
34
+ export type CodePointTable = Array<CodePoint | undefined>;
35
+ export default function loadCodePoints(ucdPath?: string): CodePointTable;
package/dist/parser.js ADDED
@@ -0,0 +1,308 @@
1
+ import { readFileSync } from "node:fs";
2
+ import { dirname, join, resolve } from "node:path";
3
+ import { fileURLToPath } from "node:url";
4
+ const moduleDir = dirname(fileURLToPath(import.meta.url));
5
+ const defaultUcdPath = resolve(moduleDir, "..", "data");
6
+ const COMMENT_PATTERN = /\s*#.*$/;
7
+ const RANGE_PATTERN = /([a-f0-9]+)\.\.([a-f0-9]+)/i;
8
+ function parseCodes(code) {
9
+ if (!code) {
10
+ return null;
11
+ }
12
+ return code
13
+ .split(" ")
14
+ .filter((segment) => segment.length > 0)
15
+ .map((segment) => parseInt(segment, 16));
16
+ }
17
+ function createCodePoint(parts) {
18
+ const [codeHex, name, category, combiningClassValue, bidiClass, decompositionRaw, decimal, digit, numeric, bidiMirroredFlag, unicode1Name, isoComment, uppercaseHex, lowercaseHex, titlecaseHex,] = parts;
19
+ const decomposition = parseCodes(decompositionRaw) ?? [];
20
+ const codePoint = {
21
+ code: parseInt(codeHex, 16),
22
+ name,
23
+ unicode1Name: unicode1Name || null,
24
+ isoComment: isoComment || null,
25
+ category,
26
+ block: null,
27
+ script: null,
28
+ eastAsianWidth: null,
29
+ combiningClass: parseInt(combiningClassValue, 10) || 0,
30
+ combiningClassName: null,
31
+ bidiClass,
32
+ bidiMirrored: bidiMirroredFlag === "Y",
33
+ numeric: numeric || null,
34
+ uppercase: uppercaseHex ? [parseInt(uppercaseHex, 16)] : null,
35
+ lowercase: lowercaseHex ? [parseInt(lowercaseHex, 16)] : null,
36
+ titlecase: titlecaseHex ? [parseInt(titlecaseHex, 16)] : null,
37
+ folded: null,
38
+ caseConditions: null,
39
+ decomposition,
40
+ compositions: {},
41
+ isCompat: false,
42
+ isExcluded: false,
43
+ joiningType: null,
44
+ joiningGroup: null,
45
+ indicSyllabicCategory: null,
46
+ indicPositionalCategory: null,
47
+ NFD_QC: 0,
48
+ NFKD_QC: 0,
49
+ NFC_QC: 0,
50
+ NFKC_QC: 0,
51
+ };
52
+ if (codePoint.decomposition.length && Number.isNaN(codePoint.decomposition[0])) {
53
+ codePoint.isCompat = true;
54
+ codePoint.decomposition.shift();
55
+ }
56
+ if ((decimal && decimal !== codePoint.numeric) || (digit && digit !== codePoint.numeric)) {
57
+ throw new Error("Decimal or digit does not match numeric value");
58
+ }
59
+ return codePoint;
60
+ }
61
+ function cloneCodePoint(source, code) {
62
+ return { ...source, code };
63
+ }
64
+ function readRangeFile(ucdPath, filename, handler) {
65
+ const data = readFileSync(join(ucdPath, filename), "ascii");
66
+ for (const rawLine of data.split("\n")) {
67
+ let line = rawLine.trim();
68
+ if (!line || line.startsWith("#")) {
69
+ continue;
70
+ }
71
+ line = line.replace(COMMENT_PATTERN, "");
72
+ if (!line) {
73
+ continue;
74
+ }
75
+ const parts = line.split(/\s*;\s*/);
76
+ const match = parts[0].match(RANGE_PATTERN);
77
+ let range = null;
78
+ if (match) {
79
+ range = [parseInt(match[1], 16), parseInt(match[2], 16)];
80
+ }
81
+ else {
82
+ const value = parseInt(parts[0], 16);
83
+ if (!Number.isNaN(value)) {
84
+ range = [value, value];
85
+ }
86
+ }
87
+ if (!range) {
88
+ continue;
89
+ }
90
+ const rest = parts.slice(1);
91
+ handler([range, ...rest]);
92
+ }
93
+ }
94
+ function readRawFile(ucdPath, filename, handler) {
95
+ const data = readFileSync(join(ucdPath, filename), "ascii");
96
+ for (const rawLine of data.split("\n")) {
97
+ let line = rawLine.trim();
98
+ if (!line || line.startsWith("#")) {
99
+ continue;
100
+ }
101
+ line = line.replace(COMMENT_PATTERN, "");
102
+ if (!line) {
103
+ continue;
104
+ }
105
+ handler(line.split(/\s*;\s*/));
106
+ }
107
+ }
108
+ export default function loadCodePoints(ucdPath = defaultUcdPath) {
109
+ const codePoints = [];
110
+ const unicodeData = readFileSync(join(ucdPath, "UnicodeData.txt"), "ascii");
111
+ let rangeStart = -1;
112
+ for (const line of unicodeData.split("\n")) {
113
+ if (!line.length) {
114
+ continue;
115
+ }
116
+ const parts = line.split(";");
117
+ const name = parts[1];
118
+ const codePoint = createCodePoint(parts);
119
+ if (rangeStart >= 0) {
120
+ if (!/<.+, Last>/.test(name)) {
121
+ throw new Error("No range end found");
122
+ }
123
+ for (let code = rangeStart; code <= codePoint.code; code += 1) {
124
+ codePoints[code] = cloneCodePoint(codePoint, code);
125
+ }
126
+ rangeStart = -1;
127
+ continue;
128
+ }
129
+ if (/<.+, First>/.test(name)) {
130
+ rangeStart = codePoint.code;
131
+ }
132
+ else {
133
+ codePoints[codePoint.code] = codePoint;
134
+ }
135
+ }
136
+ readRangeFile(ucdPath, "extracted/DerivedNumericValues.txt", (parts) => {
137
+ const [start, end] = parts[0];
138
+ const value = parts[3];
139
+ for (let code = start; code <= end; code += 1) {
140
+ const codePoint = codePoints[code];
141
+ if (codePoint && !codePoint.numeric) {
142
+ codePoint.numeric = value;
143
+ }
144
+ }
145
+ });
146
+ const combiningClasses = {};
147
+ const joiningTypes = {};
148
+ readRawFile(ucdPath, "PropertyValueAliases.txt", (parts) => {
149
+ if (parts[0] === "ccc") {
150
+ const num = parseInt(parts[1], 10);
151
+ const name = parts[3];
152
+ combiningClasses[num] = name;
153
+ }
154
+ if (parts[0] === "jt") {
155
+ joiningTypes[parts[1]] = parts[2];
156
+ }
157
+ });
158
+ for (const codePoint of codePoints) {
159
+ if (codePoint) {
160
+ codePoint.combiningClassName = combiningClasses[codePoint.combiningClass] ?? null;
161
+ }
162
+ }
163
+ readRangeFile(ucdPath, "Blocks.txt", (parts) => {
164
+ const [start, end] = parts[0];
165
+ for (let code = start; code <= end; code += 1) {
166
+ const codePoint = codePoints[code];
167
+ if (codePoint) {
168
+ codePoint.block = parts[1];
169
+ }
170
+ }
171
+ });
172
+ readRangeFile(ucdPath, "Scripts.txt", (parts) => {
173
+ const [start, end] = parts[0];
174
+ for (let code = start; code <= end; code += 1) {
175
+ const codePoint = codePoints[code];
176
+ if (codePoint) {
177
+ codePoint.script = parts[1];
178
+ }
179
+ }
180
+ });
181
+ readRangeFile(ucdPath, "EastAsianWidth.txt", (parts) => {
182
+ const [start, end] = parts[0];
183
+ for (let code = start; code <= end; code += 1) {
184
+ const codePoint = codePoints[code];
185
+ if (codePoint) {
186
+ codePoint.eastAsianWidth = parts[1];
187
+ }
188
+ }
189
+ });
190
+ readRangeFile(ucdPath, "SpecialCasing.txt", (parts) => {
191
+ const [start] = parts[0];
192
+ const lower = parseCodes(parts[1]);
193
+ const title = parseCodes(parts[2]);
194
+ const upper = parseCodes(parts[3]);
195
+ const conditions = parts[4] ? parts[4].split(/\s+/) : null;
196
+ const codePoint = codePoints[start];
197
+ if (!codePoint) {
198
+ return;
199
+ }
200
+ if (!conditions) {
201
+ codePoint.uppercase = upper;
202
+ codePoint.lowercase = lower;
203
+ codePoint.titlecase = title;
204
+ }
205
+ else {
206
+ codePoint.caseConditions = conditions;
207
+ }
208
+ });
209
+ readRangeFile(ucdPath, "CaseFolding.txt", (parts) => {
210
+ const [start] = parts[0];
211
+ const type = parts[1];
212
+ const folded = parseCodes(parts[2]) ?? [];
213
+ if (["C", "F"].includes(type)) {
214
+ const codePoint = codePoints[start];
215
+ if (!codePoint) {
216
+ return;
217
+ }
218
+ const lowercase = codePoint.lowercase?.join("|") ?? "";
219
+ const foldedStr = folded.join("|");
220
+ if (lowercase !== foldedStr) {
221
+ codePoint.folded = folded;
222
+ }
223
+ }
224
+ });
225
+ readRangeFile(ucdPath, "CompositionExclusions.txt", (parts) => {
226
+ const [start] = parts[0];
227
+ const codePoint = codePoints[start];
228
+ if (codePoint) {
229
+ codePoint.isExcluded = true;
230
+ }
231
+ });
232
+ readRangeFile(ucdPath, "DerivedNormalizationProps.txt", (parts) => {
233
+ const [start, end] = parts[0];
234
+ const prop = parts[1];
235
+ const value = parts[2];
236
+ if (["NFD_QC", "NFKD_QC", "NFC_QC", "NFKC_QC"].includes(prop)) {
237
+ const quickCheckValue = value === "Y" ? 0 : value === "N" ? 1 : 2;
238
+ for (let code = start; code <= end; code += 1) {
239
+ const codePoint = codePoints[code];
240
+ if (!codePoint) {
241
+ continue;
242
+ }
243
+ switch (prop) {
244
+ case "NFD_QC":
245
+ codePoint.NFD_QC = quickCheckValue;
246
+ break;
247
+ case "NFKD_QC":
248
+ codePoint.NFKD_QC = quickCheckValue;
249
+ break;
250
+ case "NFC_QC":
251
+ codePoint.NFC_QC = quickCheckValue;
252
+ break;
253
+ case "NFKC_QC":
254
+ codePoint.NFKC_QC = quickCheckValue;
255
+ break;
256
+ default:
257
+ break;
258
+ }
259
+ }
260
+ }
261
+ });
262
+ readRangeFile(ucdPath, "ArabicShaping.txt", (parts) => {
263
+ const [start, end] = parts[0];
264
+ const joiningType = parts[2];
265
+ const joiningGroup = parts[3];
266
+ for (let code = start; code <= end; code += 1) {
267
+ const codePoint = codePoints[code];
268
+ if (!codePoint) {
269
+ continue;
270
+ }
271
+ codePoint.joiningType = joiningTypes[joiningType] ?? null;
272
+ codePoint.joiningGroup = joiningGroup || null;
273
+ }
274
+ });
275
+ readRangeFile(ucdPath, "IndicPositionalCategory.txt", (parts) => {
276
+ const [start, end] = parts[0];
277
+ const prop = parts[1];
278
+ for (let code = start; code <= end; code += 1) {
279
+ const codePoint = codePoints[code];
280
+ if (codePoint) {
281
+ codePoint.indicPositionalCategory = prop;
282
+ }
283
+ }
284
+ });
285
+ readRangeFile(ucdPath, "IndicSyllabicCategory.txt", (parts) => {
286
+ const [start, end] = parts[0];
287
+ const prop = parts[1];
288
+ for (let code = start; code <= end; code += 1) {
289
+ const codePoint = codePoints[code];
290
+ if (codePoint) {
291
+ codePoint.indicSyllabicCategory = prop;
292
+ }
293
+ }
294
+ });
295
+ for (const codePoint of codePoints) {
296
+ if (codePoint &&
297
+ codePoint.decomposition.length > 1 &&
298
+ !codePoint.isCompat &&
299
+ !codePoint.isExcluded) {
300
+ const base = codePoints[codePoint.decomposition[1]];
301
+ if (base) {
302
+ base.compositions[codePoint.decomposition[0]] = codePoint.code;
303
+ }
304
+ }
305
+ }
306
+ return codePoints;
307
+ }
308
+ //# sourceMappingURL=parser.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"parser.js","sourceRoot":"","sources":["../src/parser.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACvC,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACnD,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AAEzC,MAAM,SAAS,GAAG,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AAC1D,MAAM,cAAc,GAAG,OAAO,CAAC,SAAS,EAAE,IAAI,EAAE,MAAM,CAAC,CAAC;AAuCxD,MAAM,eAAe,GAAG,SAAS,CAAC;AAElC,MAAM,aAAa,GAAG,6BAA6B,CAAC;AAEpD,SAAS,UAAU,CAAC,IAAwB;IAC1C,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,OAAO,IAAI,CAAC;IACd,CAAC;IAED,OAAO,IAAI;SACR,KAAK,CAAC,GAAG,CAAC;SACV,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC;SACvC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,QAAQ,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,CAAC;AAC7C,CAAC;AAED,SAAS,eAAe,CAAC,KAAe;IACtC,MAAM,CACJ,OAAO,EACP,IAAI,EACJ,QAAQ,EACR,mBAAmB,EACnB,SAAS,EACT,gBAAgB,EAChB,OAAO,EACP,KAAK,EACL,OAAO,EACP,gBAAgB,EAChB,YAAY,EACZ,UAAU,EACV,YAAY,EACZ,YAAY,EACZ,YAAY,EACb,GAAG,KAAK,CAAC;IAEV,MAAM,aAAa,GAAG,UAAU,CAAC,gBAAgB,CAAC,IAAI,EAAE,CAAC;IAEzD,MAAM,SAAS,GAAc;QAC3B,IAAI,EAAE,QAAQ,CAAC,OAAO,EAAE,EAAE,CAAC;QAC3B,IAAI;QACJ,YAAY,EAAE,YAAY,IAAI,IAAI;QAClC,UAAU,EAAE,UAAU,IAAI,IAAI;QAC9B,QAAQ;QACR,KAAK,EAAE,IAAI;QACX,MAAM,EAAE,IAAI;QACZ,cAAc,EAAE,IAAI;QACpB,cAAc,EAAE,QAAQ,CAAC,mBAAmB,EAAE,EAAE,CAAC,IAAI,CAAC;QACtD,kBAAkB,EAAE,IAAI;QACxB,SAAS;QACT,YAAY,EAAE,gBAAgB,KAAK,GAAG;QACtC,OAAO,EAAE,OAAO,IAAI,IAAI;QACxB,SAAS,EAAE,YAAY,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,YAAY,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI;QAC7D,SAAS,EAAE,YAAY,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,YAAY,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI;QAC7D,SAAS,EAAE,YAAY,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,YAAY,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI;QAC7D,MAAM,EAAE,IAAI;QACZ,cAAc,EAAE,IAAI;QACpB,aAAa;QACb,YAAY,EAAE,EAAE;QAChB,QAAQ,EAAE,KAAK;QACf,UAAU,EAAE,KAAK;QACjB,WAAW,EAAE,IAAI;QACjB,YAAY,EAAE,IAAI;QAClB,qBAAqB,EAAE,IAAI;QAC3B,uBAAuB,EAAE,IAAI;QAC7B,MAAM,EAAE,CAAC;QACT,OAAO,EAAE,CAAC;QACV,MAAM,EAAE,CAAC;QACT,OAAO,EAAE,CAAC;KACX,CAAC;IAEF,IAAI,SAAS,CAAC,aAAa,CAAC,MAAM,IAAI,MAAM,CAAC,KAAK,CAAC,SAAS,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;QAC/E,SAAS,CAAC,QAAQ,GAAG,IAAI,CAAC;QAC1B,SAAS,CAAC,aAAa,CAAC,KAAK,EAAE,CAAC;IAClC,CAAC;IAED,IAAI,CAAC,OAAO,IAAI,OAAO,KAAK,SAAS,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,IAAI,KAAK,KAAK,SAAS,CAAC,OAAO,CAAC,EAAE,CAAC;QACzF,MAAM,IAAI,KAAK,CAAC,+CAA+C,CAAC,CAAC;IACnE,CAAC;IAED,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,SAAS,cAAc,CAAC,MAAiB,EAAE,IAAY;IACrD,OAAO,EAAE,GAAG,MAAM,EAAE,IAAI,EAAE,CAAC;AAC7B,CAAC;AAED,SAAS,aAAa,CACpB,OAAe,EACf,QAAgB,EAChB,OAAuD;IAEvD,MAAM,IAAI,GAAG,YAAY,CAAC,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,EAAE,OAAO,CAAC,CAAC;IAE5D,KAAK,MAAM,OAAO,IAAI,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QACvC,IAAI,IAAI,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;QAC1B,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YAClC,SAAS;QACX,CAAC;QAED,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,eAAe,EAAE,EAAE,CAAC,CAAC;QACzC,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,SAAS;QACX,CAAC;QAED,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC;QAEpC,MAAM,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC;QAC5C,IAAI,KAAK,GAA0B,IAAI,CAAC;QAExC,IAAI,KAAK,EAAE,CAAC;YACV,KAAK,GAAG,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC;QAC3D,CAAC;aAAM,CAAC;YACN,MAAM,KAAK,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC;YACrC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBACzB,KAAK,GAAG,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;YACzB,CAAC;QACH,CAAC;QAED,IAAI,CAAC,KAAK,EAAE,CAAC;YACX,SAAS;QACX,CAAC;QAED,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,CAAa,CAAC;QACxC,OAAO,CAAC,CAAC,KAAK,EAAE,GAAG,IAAI,CAAC,CAAC,CAAC;IAC5B,CAAC;AACH,CAAC;AAED,SAAS,WAAW,CAAC,OAAe,EAAE,QAAgB,EAAE,OAAkC;IACxF,MAAM,IAAI,GAAG,YAAY,CAAC,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,EAAE,OAAO,CAAC,CAAC;IAE5D,KAAK,MAAM,OAAO,IAAI,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QACvC,IAAI,IAAI,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;QAC1B,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;YAClC,SAAS;QACX,CAAC;QAED,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,eAAe,EAAE,EAAE,CAAC,CAAC;QACzC,IAAI,CAAC,IAAI,EAAE,CAAC;YACV,SAAS;QACX,CAAC;QAED,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,CAAC;IACjC,CAAC;AACH,CAAC;AAED,MAAM,CAAC,OAAO,UAAU,cAAc,CAAC,UAAkB,cAAc;IACrE,MAAM,UAAU,GAAmB,EAAE,CAAC;IAEtC,MAAM,WAAW,GAAG,YAAY,CAAC,IAAI,CAAC,OAAO,EAAE,iBAAiB,CAAC,EAAE,OAAO,CAAC,CAAC;IAE5E,IAAI,UAAU,GAAG,CAAC,CAAC,CAAC;IAEpB,KAAK,MAAM,IAAI,IAAI,WAAW,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QAC3C,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YACjB,SAAS;QACX,CAAC;QAED,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;QAC9B,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACtB,MAAM,SAAS,GAAG,eAAe,CAAC,KAAK,CAAC,CAAC;QAEzC,IAAI,UAAU,IAAI,CAAC,EAAE,CAAC;YACpB,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;gBAC7B,MAAM,IAAI,KAAK,CAAC,oBAAoB,CAAC,CAAC;YACxC,CAAC;YAED,KAAK,IAAI,IAAI,GAAG,UAAU,EAAE,IAAI,IAAI,SAAS,CAAC,IAAI,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;gBAC9D,UAAU,CAAC,IAAI,CAAC,GAAG,cAAc,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;YACrD,CAAC;YAED,UAAU,GAAG,CAAC,CAAC,CAAC;YAChB,SAAS;QACX,CAAC;QAED,IAAI,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YAC7B,UAAU,GAAG,SAAS,CAAC,IAAI,CAAC;QAC9B,CAAC;aAAM,CAAC;YACN,UAAU,CAAC,SAAS,CAAC,IAAI,CAAC,GAAG,SAAS,CAAC;QACzC,CAAC;IACH,CAAC;IAED,aAAa,CAAC,OAAO,EAAE,oCAAoC,EAAE,CAAC,KAAK,EAAE,EAAE;QACrE,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC9B,MAAM,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAEvB,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;YACnC,IAAI,SAAS,IAAI,CAAC,SAAS,CAAC,OAAO,EAAE,CAAC;gBACpC,SAAS,CAAC,OAAO,GAAG,KAAK,CAAC;YAC5B,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,MAAM,gBAAgB,GAA2B,EAAE,CAAC;IACpD,MAAM,YAAY,GAA2B,EAAE,CAAC;IAEhD,WAAW,CAAC,OAAO,EAAE,0BAA0B,EAAE,CAAC,KAAK,EAAE,EAAE;QACzD,IAAI,KAAK,CAAC,CAAC,CAAC,KAAK,KAAK,EAAE,CAAC;YACvB,MAAM,GAAG,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC;YACnC,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;YACtB,gBAAgB,CAAC,GAAG,CAAC,GAAG,IAAI,CAAC;QAC/B,CAAC;QAED,IAAI,KAAK,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;YACtB,YAAY,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACpC,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,KAAK,MAAM,SAAS,IAAI,UAAU,EAAE,CAAC;QACnC,IAAI,SAAS,EAAE,CAAC;YACd,SAAS,CAAC,kBAAkB,GAAG,gBAAgB,CAAC,SAAS,CAAC,cAAc,CAAC,IAAI,IAAI,CAAC;QACpF,CAAC;IACH,CAAC;IAED,aAAa,CAAC,OAAO,EAAE,YAAY,EAAE,CAAC,KAAK,EAAE,EAAE;QAC7C,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAE9B,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;YACnC,IAAI,SAAS,EAAE,CAAC;gBACd,SAAS,CAAC,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;YAC7B,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,aAAa,EAAE,CAAC,KAAK,EAAE,EAAE;QAC9C,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAE9B,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;YACnC,IAAI,SAAS,EAAE,CAAC;gBACd,SAAS,CAAC,MAAM,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;YAC9B,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,oBAAoB,EAAE,CAAC,KAAK,EAAE,EAAE;QACrD,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAE9B,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;YACnC,IAAI,SAAS,EAAE,CAAC;gBACd,SAAS,CAAC,cAAc,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;YACtC,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,mBAAmB,EAAE,CAAC,KAAK,EAAE,EAAE;QACpD,MAAM,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACzB,MAAM,KAAK,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;QACnC,MAAM,KAAK,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;QACnC,MAAM,KAAK,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC;QACnC,MAAM,UAAU,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC;QAE3D,MAAM,SAAS,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC;QACpC,IAAI,CAAC,SAAS,EAAE,CAAC;YACf,OAAO;QACT,CAAC;QAED,IAAI,CAAC,UAAU,EAAE,CAAC;YAChB,SAAS,CAAC,SAAS,GAAG,KAAK,CAAC;YAC5B,SAAS,CAAC,SAAS,GAAG,KAAK,CAAC;YAC5B,SAAS,CAAC,SAAS,GAAG,KAAK,CAAC;QAC9B,CAAC;aAAM,CAAC;YACN,SAAS,CAAC,cAAc,GAAG,UAAU,CAAC;QACxC,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,iBAAiB,EAAE,CAAC,KAAK,EAAE,EAAE;QAClD,MAAM,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACzB,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACtB,MAAM,MAAM,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QAE1C,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAC;YAC9B,MAAM,SAAS,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC;YACpC,IAAI,CAAC,SAAS,EAAE,CAAC;gBACf,OAAO;YACT,CAAC;YAED,MAAM,SAAS,GAAG,SAAS,CAAC,SAAS,EAAE,IAAI,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;YACvD,MAAM,SAAS,GAAG,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;YACnC,IAAI,SAAS,KAAK,SAAS,EAAE,CAAC;gBAC5B,SAAS,CAAC,MAAM,GAAG,MAAM,CAAC;YAC5B,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,2BAA2B,EAAE,CAAC,KAAK,EAAE,EAAE;QAC5D,MAAM,CAAC,KAAK,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACzB,MAAM,SAAS,GAAG,UAAU,CAAC,KAAK,CAAC,CAAC;QACpC,IAAI,SAAS,EAAE,CAAC;YACd,SAAS,CAAC,UAAU,GAAG,IAAI,CAAC;QAC9B,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,+BAA+B,EAAE,CAAC,KAAK,EAAE,EAAE;QAChE,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC9B,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QACtB,MAAM,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAEvB,IAAI,CAAC,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,CAAC,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAC;YAC9D,MAAM,eAAe,GAAG,KAAK,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,KAAK,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;YAElE,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;gBAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;gBACnC,IAAI,CAAC,SAAS,EAAE,CAAC;oBACf,SAAS;gBACX,CAAC;gBAED,QAAQ,IAAI,EAAE,CAAC;oBACb,KAAK,QAAQ;wBACX,SAAS,CAAC,MAAM,GAAG,eAAe,CAAC;wBACnC,MAAM;oBACR,KAAK,SAAS;wBACZ,SAAS,CAAC,OAAO,GAAG,eAAe,CAAC;wBACpC,MAAM;oBACR,KAAK,QAAQ;wBACX,SAAS,CAAC,MAAM,GAAG,eAAe,CAAC;wBACnC,MAAM;oBACR,KAAK,SAAS;wBACZ,SAAS,CAAC,OAAO,GAAG,eAAe,CAAC;wBACpC,MAAM;oBACR;wBACE,MAAM;gBACV,CAAC;YACH,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,mBAAmB,EAAE,CAAC,KAAK,EAAE,EAAE;QACpD,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC9B,MAAM,WAAW,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC7B,MAAM,YAAY,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAE9B,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;YACnC,IAAI,CAAC,SAAS,EAAE,CAAC;gBACf,SAAS;YACX,CAAC;YAED,SAAS,CAAC,WAAW,GAAG,YAAY,CAAC,WAAW,CAAC,IAAI,IAAI,CAAC;YAC1D,SAAS,CAAC,YAAY,GAAG,YAAY,IAAI,IAAI,CAAC;QAChD,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,6BAA6B,EAAE,CAAC,KAAK,EAAE,EAAE;QAC9D,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC9B,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAEtB,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;YACnC,IAAI,SAAS,EAAE,CAAC;gBACd,SAAS,CAAC,uBAAuB,GAAG,IAAI,CAAC;YAC3C,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,aAAa,CAAC,OAAO,EAAE,2BAA2B,EAAE,CAAC,KAAK,EAAE,EAAE;QAC5D,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC9B,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAEtB,KAAK,IAAI,IAAI,GAAG,KAAK,EAAE,IAAI,IAAI,GAAG,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAC9C,MAAM,SAAS,GAAG,UAAU,CAAC,IAAI,CAAC,CAAC;YACnC,IAAI,SAAS,EAAE,CAAC;gBACd,SAAS,CAAC,qBAAqB,GAAG,IAAI,CAAC;YACzC,CAAC;QACH,CAAC;IACH,CAAC,CAAC,CAAC;IAEH,KAAK,MAAM,SAAS,IAAI,UAAU,EAAE,CAAC;QACnC,IACE,SAAS;YACT,SAAS,CAAC,aAAa,CAAC,MAAM,GAAG,CAAC;YAClC,CAAC,SAAS,CAAC,QAAQ;YACnB,CAAC,SAAS,CAAC,UAAU,EACrB,CAAC;YACD,MAAM,IAAI,GAAG,UAAU,CAAC,SAAS,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,CAAC;YACpD,IAAI,IAAI,EAAE,CAAC;gBACT,IAAI,CAAC,YAAY,CAAC,SAAS,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,GAAG,SAAS,CAAC,IAAI,CAAC;YACjE,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,UAAU,CAAC;AACpB,CAAC"}
package/package.json ADDED
@@ -0,0 +1,40 @@
1
+ {
2
+ "name": "@chr33s/pdf-codepoints",
3
+ "version": "5.0.0",
4
+ "description": "A parser for files in the Unicode database",
5
+ "type": "module",
6
+ "sideEffects": false,
7
+ "exports": {
8
+ ".": {
9
+ "types": "./dist/index.d.ts",
10
+ "default": "./dist/index.js"
11
+ }
12
+ },
13
+ "scripts": {
14
+ "build": "tsc",
15
+ "clean": "rm -rf dist",
16
+ "update-data": "node scripts/update-data.ts",
17
+ "typecheck": "tsc --project tsconfig.typecheck.json",
18
+ "test": "vitest run"
19
+ },
20
+ "keywords": [
21
+ "unicode",
22
+ "ucd",
23
+ "codepoint"
24
+ ],
25
+ "author": "Devon Govett <devongovett@gmail.com>",
26
+ "repository": {
27
+ "type": "git",
28
+ "url": "https://github.com/chr33s/pdf.git"
29
+ },
30
+ "bugs": {
31
+ "url": "https://github.com/chr33s/pdf/issues"
32
+ },
33
+ "license": "MIT",
34
+ "homepage": "https://github.com/chr33s/pdf",
35
+ "devDependencies": {
36
+ "@types/node": "24.10.1",
37
+ "typescript": "5.9.3",
38
+ "vitest": "4.0.15"
39
+ }
40
+ }
@@ -0,0 +1,64 @@
1
+ import { Buffer } from "node:buffer";
2
+ import { mkdir, readdir, stat, writeFile } from "node:fs/promises";
3
+ import { dirname, join, relative, resolve } from "node:path";
4
+ import { fileURLToPath } from "node:url";
5
+
6
+ const unicodeVersion = process.env.UNICODE_VERSION ?? "12.0.0";
7
+ const packageRoot = resolve(dirname(fileURLToPath(import.meta.url)), "..");
8
+ const dataDir = join(packageRoot, "data");
9
+
10
+ async function* walk(dir: string): AsyncGenerator<string> {
11
+ const entries = await readdir(dir, { withFileTypes: true });
12
+ for (const entry of entries) {
13
+ const entryPath = join(dir, entry.name);
14
+ if (entry.isDirectory()) {
15
+ for await (const child of walk(entryPath)) {
16
+ yield child;
17
+ }
18
+ } else {
19
+ yield entryPath;
20
+ }
21
+ }
22
+ }
23
+
24
+ async function ensureDir(path: string): Promise<void> {
25
+ await mkdir(path, { recursive: true });
26
+ }
27
+
28
+ async function downloadFile(source: string, destination: string): Promise<void> {
29
+ const response = await fetch(source);
30
+ if (!response.ok) {
31
+ throw new Error(`Failed to download ${source}: ${response.status} ${response.statusText}`);
32
+ }
33
+
34
+ const arrayBuffer = await response.arrayBuffer();
35
+ await ensureDir(dirname(destination));
36
+ await writeFile(destination, Buffer.from(arrayBuffer));
37
+ }
38
+
39
+ async function main(): Promise<void> {
40
+ console.log(`Fetching Unicode data files (version ${unicodeVersion})...`);
41
+
42
+ for await (const absolutePath of walk(dataDir)) {
43
+ if (!absolutePath.endsWith(".txt")) continue;
44
+
45
+ const relativePath = relative(dataDir, absolutePath).split("\\").join("/");
46
+ const url = `https://www.unicode.org/Public/${unicodeVersion}/ucd/${relativePath}`;
47
+
48
+ const stats = await stat(absolutePath).catch(() => null);
49
+ const previousSize = stats?.size ?? 0;
50
+
51
+ await downloadFile(url, absolutePath);
52
+
53
+ const newStats = await stat(absolutePath);
54
+ const sizeChange = newStats.size - previousSize;
55
+ const changeLabel =
56
+ sizeChange === 0 ? "unchanged" : sizeChange > 0 ? `+${sizeChange}` : `${sizeChange}`;
57
+ console.log(`Downloaded ${relativePath} (${newStats.size} bytes, ${changeLabel})`);
58
+ }
59
+ }
60
+
61
+ main().catch((error) => {
62
+ console.error(error);
63
+ process.exitCode = 1;
64
+ });
package/src/index.ts ADDED
@@ -0,0 +1,7 @@
1
+ import parser from "./parser.js";
2
+
3
+ const codePoints = parser();
4
+
5
+ export default codePoints;
6
+ export * from "./parser.js";
7
+ export { parser };