UEA-Prodem
This commit is contained in:
+21
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2026 Natural Intelligence
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
+142
@@ -0,0 +1,142 @@
|
||||
# anynum
|
||||
|
||||
Normalize Unicode decimal digits and minus signs to ASCII.
|
||||
|
||||
Converts digits from any script — Devanagari, Arabic-Indic, Thai, Bengali, Fullwidth, and [50+ others](#supported-scripts) — to their ASCII equivalents (`0`–`9`). Also normalizes Unicode minus variants (`−`, `－`, `﹣`) to ASCII `-`.
|
||||
|
||||
Pairs naturally with [`strnum`](https://github.com/nicolo-ribaudo/strnum) — use `anynum` to normalize first, then `strnum` to detect the numeric type.
|
||||
|
||||
```js
|
||||
import anynum from 'anynum';
|
||||
|
||||
anynum('१२.३४') // → '12.34' (Devanagari)
|
||||
anynum('٣٫١٤') // → '3.14' (Arabic-Indic)
|
||||
anynum('−४२') // → '-42' (Unicode minus + Devanagari)
|
||||
anynum('－９９.５') // → '-99.5' (Fullwidth minus + Fullwidth digits)
|
||||
anynum('hello') // → 'hello' (no digits — zero allocation)
|
||||
anynum('100') // → '100' (already ASCII — zero allocation)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Install
|
||||
|
||||
```bash
|
||||
npm install anynum
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
```js
|
||||
// ESM
|
||||
import anynum from 'anynum';
|
||||
import { anynum } from 'anynum';
|
||||
|
||||
```
|
||||
|
||||
### API
|
||||
|
||||
```ts
|
||||
anynum(str: string): string
|
||||
```
|
||||
|
||||
- Accepts a `string`, returns a `string`.
|
||||
- Non-string values are returned as-is (no throw).
|
||||
- Non-digit characters pass through unchanged.
|
||||
- If no conversion is needed, the **original string is returned** (zero allocation).
|
||||
|
||||
---
|
||||
|
||||
## What gets converted
|
||||
|
||||
### Decimal digits
|
||||
|
||||
Any Unicode character in category `Nd` (decimal digit) is mapped to its ASCII equivalent. This covers all positional decimal digit scripts — every script whose digits represent `0`–`9` by position.
|
||||
|
||||
```js
|
||||
anynum('๑๒๓') // Thai → '123'
|
||||
anynum('੧੨੩') // Gurmukhi → '123'
|
||||
anynum('᠑᠒᠓') // Mongolian → '123'
|
||||
anynum('𝟏𝟐𝟑') // Math Bold → '123'
|
||||
```
|
||||
|
||||
### Unicode minus variants
|
||||
|
||||
Three Unicode characters are normalized to ASCII `-` (`U+002D`):
|
||||
|
||||
| Code point | Character | Name |
|
||||
|---|---|---|
|
||||
| `U+2212` | `−` | MINUS SIGN (mathematical) |
|
||||
| `U+FF0D` | `－` | FULLWIDTH HYPHEN-MINUS |
|
||||
| `U+FE63` | `﹣` | SMALL HYPHEN-MINUS |
|
||||
|
||||
Dashes used for punctuation — EN DASH (`–`), EM DASH (`—`), HYPHEN (`‐`) — are intentionally **not** converted.
|
||||
|
||||
```js
|
||||
anynum('−42') // U+2212 MINUS SIGN → '-42'
|
||||
anynum('－42') // U+FF0D FULLWIDTH → '-42'
|
||||
anynum('–42') // U+2013 EN DASH → '–42' (unchanged)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Use with strnum
|
||||
|
||||
`anynum` and `strnum` compose cleanly:
|
||||
|
||||
```js
|
||||
import anynum from 'anynum';
|
||||
import strnum from 'strnum';
|
||||
|
||||
strnum(anynum('१२.३४')) // → 12.34 (number, float)
|
||||
strnum(anynum('−४२')) // → '-42' (string; strnum handles sign detection)
|
||||
strnum(anynum('hello')) // → 'hello'
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
|
||||
## Supported scripts
|
||||
|
||||
50+ decimal digit scripts from Unicode `Nd` category, including:
|
||||
|
||||
| Script | Zero | Sample |
|
||||
|---|---|---|
|
||||
| Devanagari (Hindi/Marathi/Nepali) | `U+0966` | `०१२३४५६७८९` |
|
||||
| Arabic-Indic | `U+0660` | `٠١٢٣٤٥٦٧٨٩` |
|
||||
| Extended Arabic-Indic (Urdu/Persian) | `U+06F0` | `۰۱۲۳۴۵۶۷۸۹` |
|
||||
| Bengali | `U+09E6` | `০১২৩৪৫৬৭৮৯` |
|
||||
| Gurmukhi | `U+0A66` | `੦੧੨੩੪੫੬੭੮੯` |
|
||||
| Gujarati | `U+0AE6` | `૦૧૨૩૪૫૬૭૮૯` |
|
||||
| Odia | `U+0B66` | `୦୧୨୩୪୫୬୭୮୯` |
|
||||
| Tamil | `U+0BE6` | `௦௧௨௩௪௫௬௭௮௯` |
|
||||
| Telugu | `U+0C66` | `౦౧౨౩౪౫౬౭౮౯` |
|
||||
| Kannada | `U+0CE6` | `೦೧೨೩೪೫೬೭೮೯` |
|
||||
| Malayalam | `U+0D66` | `൦൧൨൩൪൫൬൭൮൯` |
|
||||
| Thai | `U+0E50` | `๐๑๒๓๔๕๖๗๘๙` |
|
||||
| Lao | `U+0ED0` | `໐໑໒໓໔໕໖໗໘໙` |
|
||||
| Tibetan | `U+0F20` | `༠༡༢༣༤༥༦༧༨༩` |
|
||||
| Myanmar | `U+1040` | `၀၁၂၃၄၅၆၇၈၉` |
|
||||
| Khmer | `U+17E0` | `០១២៣៤៥៦៧៨៩` |
|
||||
| Mongolian | `U+1810` | `᠐᠑᠒᠓᠔᠕᠖᠗᠘᠙` |
|
||||
| Fullwidth (CJK context) | `U+FF10` | `０１２３４５６７８９` |
|
||||
| Mathematical Bold | `U+1D7CE` | `𝟎𝟏𝟐𝟑𝟒𝟓𝟔𝟕𝟖𝟗` |
|
||||
| Adlam | `U+1E950` | `𞥐𞥑𞥒𞥓𞥔𞥕𞥖𞥗𞥘𞥙` |
|
||||
| … and 30+ more | | |
|
||||
|
||||
---
|
||||
|
||||
## What it does NOT convert
|
||||
|
||||
- **Kanji/Chinese numeral words** (`三`, `百`, `万`) — these are ideographic numerals, not decimal digits. Each language has its own positional system requiring separate parsing logic.
|
||||
- **Roman numerals** (`Ⅳ`, `Ⅻ`) — not decimal digits.
|
||||
- **Punctuation dashes** (`–` EN, `—` EM, `‐` HYPHEN) — not numeric signs.
|
||||
- **Decimal separators** — commas, periods, Arabic decimal comma (`٫`) are passed through as-is. Separator normalization is the caller's responsibility.
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
MIT
|
||||
+135
@@ -0,0 +1,135 @@
|
||||
'use strict';
|
||||
|
||||
import { TABLE, TABLE_OFFSET, HIGH_MAP, NOT_DIGIT } from './digitTable.js';
|
||||
|
||||
const CHAR_0 = 48; // '0'.charCodeAt(0)
|
||||
const CHAR_9 = 57; // '9'.charCodeAt(0)
|
||||
const CHAR_MINUS = 45; // '-'.charCodeAt(0)
|
||||
|
||||
// Unicode minus/hyphen variants worth normalizing to ASCII '-' in numeric context:
|
||||
// U+2212 MINUS SIGN − (mathematically correct minus)
|
||||
// U+FF0D FULLWIDTH HYPHEN-MINUS － (Japanese fullwidth context)
|
||||
// U+FE63 SMALL HYPHEN-MINUS ﹣ (small form variant)
|
||||
//
|
||||
// NOT normalized (deliberate):
|
||||
// U+2013 EN DASH – (punctuation, not a numeric sign)
|
||||
// U+2014 EM DASH — (punctuation)
|
||||
// U+2010 HYPHEN ‐ (typographic hyphen)
|
||||
//
|
||||
// Rationale: only characters a human or locale formatter would plausibly use
|
||||
// as a numeric minus sign are normalized. Dashes used for punctuation are left
|
||||
// alone to avoid mangling non-numeric strings.
|
||||
const MINUS_SET = new Set([0x2212, 0xFF0D, 0xFE63]);
|
||||
|
||||
/**
|
||||
* Normalize all Unicode decimal digit characters in a string to ASCII (0-9),
|
||||
* and normalize Unicode minus variants to ASCII '-' (U+002D).
|
||||
*
|
||||
* Non-digit, non-minus characters are passed through unchanged.
|
||||
*
|
||||
* Performance design:
|
||||
* - Fast path: if the string has no convertible characters, return it unchanged
|
||||
* (zero allocation).
|
||||
* - BMP digits (0x0660..0xFFFF excl. surrogates): flat Uint8Array lookup (O(1)).
|
||||
* - Supplementary plane digits (> 0xFFFF, encoded as surrogate pairs): Map lookup.
|
||||
* - Minus variants: checked inline with a small fixed Set.
|
||||
*
|
||||
* @param {string} str
|
||||
* @returns {string}
|
||||
*/
|
||||
function anynum(str) {
|
||||
if (typeof str !== 'string') return str;
|
||||
|
||||
const len = str.length;
|
||||
if (len === 0) return str;
|
||||
|
||||
// Scan for first character needing conversion.
|
||||
// If none found, return original string (zero allocation).
|
||||
let firstHit = -1;
|
||||
|
||||
for (let i = 0; i < len; i++) {
|
||||
const cc = str.charCodeAt(i);
|
||||
|
||||
// ASCII digit or ASCII minus — already normalized, skip fast
|
||||
if ((cc >= CHAR_0 && cc <= CHAR_9) || cc === CHAR_MINUS) continue;
|
||||
|
||||
// Below first unicode digit script — check minus variants only
|
||||
if (cc < TABLE_OFFSET) {
|
||||
if (MINUS_SET.has(cc)) { firstHit = i; break; }
|
||||
continue;
|
||||
}
|
||||
|
||||
// Surrogate pairs live in BMP range 0xD800-0xDFFF — check before TABLE
|
||||
if (cc >= 0xD800 && cc <= 0xDBFF) {
|
||||
if (i + 1 < len) {
|
||||
const low = str.charCodeAt(i + 1);
|
||||
if (low >= 0xDC00 && low <= 0xDFFF) {
|
||||
const cp = 0x10000 + ((cc - 0xD800) << 10) + (low - 0xDC00);
|
||||
if (HIGH_MAP.has(cp)) { firstHit = i; break; }
|
||||
}
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
// BMP non-surrogate: flat table lookup; also check minus variants in this range
|
||||
if (TABLE[cc - TABLE_OFFSET] !== NOT_DIGIT || MINUS_SET.has(cc)) {
|
||||
firstHit = i;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Nothing to replace — return original, zero allocation
|
||||
if (firstHit === -1) return str;
|
||||
|
||||
// Build result: copy unchanged prefix, then convert from firstHit onward
|
||||
const chars = [];
|
||||
|
||||
if (firstHit > 0) chars.push(str.slice(0, firstHit));
|
||||
|
||||
for (let i = firstHit; i < len; i++) {
|
||||
const cc = str.charCodeAt(i);
|
||||
|
||||
// ASCII digit or ASCII minus — pass through
|
||||
if ((cc >= CHAR_0 && cc <= CHAR_9) || cc === CHAR_MINUS) {
|
||||
chars.push(str[i]);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Below TABLE_OFFSET — check minus variants, else pass through
|
||||
if (cc < TABLE_OFFSET) {
|
||||
chars.push(MINUS_SET.has(cc) ? '-' : str[i]);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Surrogate pairs
|
||||
if (cc >= 0xD800 && cc <= 0xDBFF) {
|
||||
if (i + 1 < len) {
|
||||
const low = str.charCodeAt(i + 1);
|
||||
if (low >= 0xDC00 && low <= 0xDFFF) {
|
||||
const cp = 0x10000 + ((cc - 0xD800) << 10) + (low - 0xDC00);
|
||||
const d = HIGH_MAP.get(cp);
|
||||
if (d !== undefined) {
|
||||
chars.push(String.fromCharCode(d + 48));
|
||||
i++; // consume low surrogate
|
||||
continue;
|
||||
}
|
||||
}
|
||||
}
|
||||
chars.push(str[i]);
|
||||
continue;
|
||||
}
|
||||
|
||||
// BMP non-surrogate: flat table lookup + minus variants
|
||||
if (MINUS_SET.has(cc)) {
|
||||
chars.push('-');
|
||||
continue;
|
||||
}
|
||||
const d = TABLE[cc - TABLE_OFFSET];
|
||||
chars.push(d !== NOT_DIGIT ? String.fromCharCode(d + 48) : str[i]);
|
||||
}
|
||||
|
||||
return chars.join('');
|
||||
}
|
||||
|
||||
export { anynum };
|
||||
export default anynum;
|
||||
+116
@@ -0,0 +1,116 @@
|
||||
/**
|
||||
* Flat lookup table: maps Unicode code point → ASCII digit (0-9).
|
||||
* Only decimal digit characters (Unicode category Nd) are included.
|
||||
*
|
||||
* Strategy: Int32Array of size (maxCodePoint - minCodePoint + 1).
|
||||
* Value 0xFF means "not a digit". Value 0-9 is the ASCII digit value.
|
||||
* This gives O(1) lookup with no branching, no bisect, no loop.
|
||||
*
|
||||
* Memory: range is 0x0660 to 0x1FBF0 → ~129,936 entries × 1 byte = ~127 KB.
|
||||
* Acceptable for a one-time init; lookup is a single array index.
|
||||
*/
|
||||
|
||||
// All known Unicode Nd (decimal digit) script zero code points.
|
||||
// Each script has exactly 10 consecutive digits: zero+0 .. zero+9.
|
||||
const SCRIPT_ZEROS = [
|
||||
// Basic Latin (ASCII) — included for completeness / pass-through
|
||||
0x0030, // 0-9
|
||||
|
||||
// Arabic scripts
|
||||
0x0660, // Arabic-Indic ٠١٢٣٤٥٦٧٨٩
|
||||
0x06F0, // Extended Arabic-Indic (Urdu/Persian/Sindhi) ۰۱۲۳
|
||||
|
||||
// Indic scripts
|
||||
0x0966, // Devanagari ०१२३४५६७८९
|
||||
0x09E6, // Bengali ০১২৩৪৫৬৭৮৯
|
||||
0x0A66, // Gurmukhi ੦੧੨੩੪੫੬੭੮੯
|
||||
0x0AE6, // Gujarati ૦૧૨૩૪૫૬૭૮૯
|
||||
0x0B66, // Odia ୦୧୨୩୪୫୬୭୮୯
|
||||
0x0BE6, // Tamil ௦௧௨௩௪௫௬௭௮௯
|
||||
0x0C66, // Telugu ౦౧౨౩౪౫౬౭౮౯
|
||||
0x0CE6, // Kannada ೦೧೨೩೪೫೬೭೮೯
|
||||
0x0D66, // Malayalam ൦൧൨൩൪൫൬൭൮൯
|
||||
0x0DE6, // Sinhala Archaic ෦෧෨෩෪෫෬෭෮෯
|
||||
|
||||
// Southeast Asian scripts
|
||||
0x0E50, // Thai ๐๑๒๓๔๕๖๗๘๙
|
||||
0x0ED0, // Lao ໐໑໒໓໔໕໖໗໘໙
|
||||
0x0F20, // Tibetan ༠༡༢༣༤༥༦༧༨༩
|
||||
0x1040, // Myanmar ၀၁၂၃၄၅၆၇၈၉
|
||||
0x1090, // Myanmar Shan ႐႑႒႓႔႕႖႗႘႙
|
||||
0x17E0, // Khmer ០១២៣៤៥៦៧៨៩
|
||||
0x1810, // Mongolian ᠐᠑᠒᠓᠔᠕᠖᠗᠘᠙
|
||||
0x1946, // Limbu ᥆᥇᥈᥉᥊᥋᥌᥍᥎᥏
|
||||
0x19D0, // New Tai Lue ᧐᧑᧒᧓᧔᧕᧖᧗᧘᧙
|
||||
0x1A80, // Tai Tham Hora ᪀᪁᪂᪃᪄᪅᪆᪇᪈᪉
|
||||
0x1A90, // Tai Tham Tham ᪐᪑᪒᪓᪔᪕᪖᪗᪘᪙
|
||||
0x1B50, // Balinese ᭐᭑᭒᭓᭔᭕᭖᭗᭘᭙
|
||||
0x1BB0, // Sundanese ᮰᮱᮲᮳᮴᮵᮶᮷᮸᮹
|
||||
0x1C40, // Lepcha ᱀᱁᱂᱃᱄᱅᱆᱇᱈᱉
|
||||
0x1C50, // Ol Chiki ᱐᱑᱒᱓᱔᱕᱖᱗᱘᱙
|
||||
|
||||
// Fullwidth (CJK context)
|
||||
0xFF10, // Fullwidth ０１２３４５６７８９
|
||||
|
||||
// Mathematical digit variants (Unicode math block)
|
||||
0x1D7CE, // Mathematical Bold
|
||||
0x1D7D8, // Mathematical Double-Struck
|
||||
0x1D7E2, // Mathematical Sans-Serif
|
||||
0x1D7EC, // Mathematical Sans-Serif Bold
|
||||
0x1D7F6, // Mathematical Monospace
|
||||
|
||||
// Other scripts
|
||||
0x104A0, // Osmanya 𐒠𐒡𐒢𐒣𐒤𐒥𐒦𐒧𐒨𐒩
|
||||
0x10D30, // Hanifi Rohingya 𐴰𐴱𐴲𐴳𐴴𐴵𐴶𐴷𐴸𐴹
|
||||
0x11066, // Brahmi 𑁦𑁧𑁨𑁩𑁪𑁫𑁬𑁭𑁮𑁯
|
||||
0x110F0, // Sora Sompeng 𑃰𑃱𑃲𑃳𑃴𑃵𑃶𑃷𑃸𑃹
|
||||
0x11136, // Chakma 𑄶𑄷𑄸𑄹𑄺𑄻𑄼𑄽𑄾𑄿
|
||||
0x111D0, // Sharada 𑇐𑇑𑇒𑇓𑇔𑇕𑇖𑇗𑇘𑇙
|
||||
0x112F0, // Khudawadi 𑋰𑋱𑋲𑋳𑋴𑋵𑋶𑋷𑋸𑋹
|
||||
0x11450, // Newa 𑑐𑑑𑑒𑑓𑑔𑑕𑑖𑑗𑑘𑑙
|
||||
0x114D0, // Tirhuta 𑓐𑓑𑓒𑓓𑓔𑓕𑓖𑓗𑓘𑓙
|
||||
0x11650, // Modi 𑙐𑙑𑙒𑙓𑙔𑙕𑙖𑙗𑙘𑙙
|
||||
0x116C0, // Takri 𑛀𑛁𑛂𑛃𑛄𑛅𑛆𑛇𑛈𑛉
|
||||
0x11730, // Ahom 𑜰𑜱𑜲𑜳𑜴𑜵𑜶𑜷𑜸𑜹
|
||||
0x118E0, // Warang Citi 𑣠𑣡𑣢𑣣𑣤𑣥𑣦𑣧𑣨𑣩
|
||||
0x11950, // Dives Akuru 𑥐𑥑𑥒𑥓𑥔𑥕𑥖𑥗𑥘𑥙
|
||||
0x11BF0, // Khitan Small Script
|
||||
0x11C50, // Bhaiksuki 𑱐𑱑𑱒𑱓𑱔𑱕𑱖𑱗𑱘𑱙
|
||||
0x11D50, // Masaram Gondi 𑵐𑵑𑵒𑵓𑵔𑵕𑵖𑵗𑵘𑵙
|
||||
0x11DA0, // Gunjala Gondi 𑶠𑶡𑶢𑶣𑶤𑶥𑶦𑶧𑶨𑶩
|
||||
0x11F50, // Kawi 𑽐𑽑𑽒𑽓𑽔𑽕𑽖𑽗𑽘𑽙
|
||||
0x16A60, // Mro 𖩠𖩡𖩢𖩣𖩤𖩥𖩦𖩧𖩨𖩩
|
||||
0x16AC0, // Tangsa 𖫀𖫁𖫂𖫃𖫄𖫅𖫆𖫇𖫈𖫉
|
||||
0x16B50, // Pahawh Hmong 𖭐𖭑𖭒𖭓𖭔𖭕𖭖𖭗𖭘𖭙
|
||||
0x1E140, // Nyiakeng Puachue Hmong 𞅀𞅁𞅂𞅃𞅄𞅅𞅆𞅇𞅈𞅉
|
||||
0x1E2F0, // Wancho 𞋰𞋱𞋲𞋳𞋴𞋵𞋶𞋷𞋸𞋹
|
||||
0x1E4F0, // Nag Mundari 𞓰𞓱𞓲𞓳𞓴𞓵𞓶𞓷𞓸𞓹
|
||||
0x1E950, // Adlam 𞥐𞥑𞥒𞥓𞥔𞥕𞥖𞥗𞥘𞥙
|
||||
0x1FBF0, // Segmented digit symbols 🯰🯱🯲🯳🯴🯵🯶🯷🯸🯹
|
||||
];
|
||||
|
||||
// Build a sparse Map for scripts above 0xFFFF (surrogate-pair range).
|
||||
// These can't go into a flat Uint8Array indexed by code point efficiently.
|
||||
const NOT_DIGIT = 0xFF;
|
||||
const HIGH_MAP = new Map(); // codePoint → digit value (0-9)
|
||||
|
||||
const LOW_MAX = 0xFFFF;
|
||||
const LOW_MIN = 0x0660; // first non-ASCII digit script
|
||||
|
||||
// Flat Uint8Array covering 0x0660 .. 0xFFFF
|
||||
const TABLE_OFFSET = LOW_MIN;
|
||||
const TABLE_SIZE = LOW_MAX - LOW_MIN + 1;
|
||||
const TABLE = new Uint8Array(TABLE_SIZE).fill(NOT_DIGIT);
|
||||
|
||||
for (const zero of SCRIPT_ZEROS) {
|
||||
for (let d = 0; d < 10; d++) {
|
||||
const cp = zero + d;
|
||||
if (cp <= LOW_MAX) {
|
||||
TABLE[cp - TABLE_OFFSET] = d;
|
||||
} else {
|
||||
HIGH_MAP.set(cp, d);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
export { TABLE, TABLE_OFFSET, HIGH_MAP, NOT_DIGIT };
|
||||
+42
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"name": "anynum",
|
||||
"version": "1.0.0",
|
||||
"description": "Normalize all Unicode decimal digits (Devanagari, Arabic, Thai, etc.) to ASCII numerals. Zero dependencies, performance-first.",
|
||||
"type": "module",
|
||||
"main": "./anynum.js",
|
||||
"files": [
|
||||
"anynum.js",
|
||||
"digitTable.js",
|
||||
"README.md"
|
||||
],
|
||||
"scripts": {
|
||||
"test": "jasmine tests/anynum.test.js",
|
||||
"bench": "node test/bench.js"
|
||||
},
|
||||
"keywords": [
|
||||
"unicode",
|
||||
"digits",
|
||||
"normalize",
|
||||
"devanagari",
|
||||
"arabic",
|
||||
"hindi",
|
||||
"japanese",
|
||||
"indic",
|
||||
"asian",
|
||||
"math",
|
||||
"numerals",
|
||||
"strnum"
|
||||
],
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "https://github.com/NaturalIntelligence/anynum"
|
||||
},
|
||||
"author": "Amit Gupta (https://solothought.work/)",
|
||||
"license": "MIT",
|
||||
"funding": [
|
||||
{
|
||||
"type": "github",
|
||||
"url": "https://github.com/sponsors/NaturalIntelligence"
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user