text-number-parser 0.1.0

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Michael Three
+
+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.

package/README.md

@@ -0,0 +1,155 @@
+# text-number-parser
+
+[![CI](https://github.com/michaelthreekiv/text-number-parser/actions/workflows/ci.yml/badge.svg)](https://github.com/michaelthreekiv/text-number-parser/actions/workflows/ci.yml)
+[![npm version](https://img.shields.io/npm/v/text-number-parser)](https://www.npmjs.com/package/text-number-parser)
+
+Parse localized Unicode number words into JavaScript `number` or `bigint` values.
+
+## Features
+
+- TypeScript source with generated declaration files.
+- Narrow public API with throwing and non-throwing parse functions.
+- Unicode-aware tokenization and normalization.
+- Parser modes for connector words and hyphenated input.
+- Extensible lexicons for custom scale words and localization.
+- Typed error objects for empty input, invalid tokens, and invalid number syntax.
+- Vitest coverage for the public API.
+- Tinybench suite for quick performance checks.
+
+## Installation
+
+```bash
+npm install text-number-parser
+```
+
+## Usage
+
+```ts
+import {
+  InvalidTokenError,
+  createParser,
+  parseTextNumber,
+  tryParseTextNumber,
+} from "text-number-parser";
+
+parseTextNumber("one hundred and twenty-one");
+// 121
+
+parseTextNumber("nine quadrillion nine trillion");
+// 9009000000000000n
+
+parseTextNumber("one hundred and one", { allowAnd: false });
+// throws InvalidSyntaxError
+
+const result = tryParseTextNumber("twenty hundred million cat");
+
+if (!result.ok) {
+  console.error(result.error.code, result.error.message);
+}
+
+try {
+  parseTextNumber("two cats");
+} catch (error) {
+  if (error instanceof InvalidTokenError) {
+    console.error(error.token, error.index);
+  }
+}
+
+const indianParser = createParser({
+  extendLexicon: [
+    { word: "dozen", type: "multiplier", value: 12 },
+    { word: "lakh", type: "multiplier", value: 100_000 },
+    { word: "crore", type: "multiplier", value: 10_000_000 },
+  ],
+});
+
+indianParser.parse("three crore five lakh");
+// 30500000
+
+const spanishParser = createParser({
+  lexicon: [{ word: "veintidós", type: "number", value: 22, cls: "teen" }],
+  locale: "es",
+  normalization: "NFC",
+});
+
+spanishParser.parse("VEINTIDO\u0301S");
+// 22
+```
+
+## Public API
+
+### parseTextNumber(input, modes?)
+
+Parses an English number phrase and returns either a `number` or a `bigint` when the value exceeds `Number.MAX_SAFE_INTEGER`.
+
+Supported modes:
+
+```ts
+type ParserModes = {
+  allowAnd?: boolean;
+  allowHyphen?: boolean;
+};
+```
+
+### tryParseTextNumber(input, modes?)
+
+Returns a discriminated union:
+
+```ts
+type ParseResult =
+  | { ok: true; value: number | bigint }
+  | { ok: false; error: TextNumberError };
+```
+
+### createParser(options)
+
+Builds an isolated parser instance with its own lexicon, default modes, locale-aware lowercasing, and Unicode normalization strategy.
+
+```ts
+type CreateParserOptions = {
+  lexicon?: Iterable<LexiconEntry>;
+  extendLexicon?: Iterable<LexiconEntry>;
+  locale?: string | string[];
+  normalization?: "NFC" | "NFD" | "NFKC" | "NFKD" | false;
+  modes?: ParserModes;
+};
+```
+
+### englishLexicon
+
+Readonly default English lexicon used by the top-level parser.
+
+### Error classes
+
+- `TextNumberError`
+- `EmptyInputError`
+- `InvalidTokenError`
+- `InvalidSyntaxError`
+
+Each error carries the original input. Token and syntax errors also expose the offending token and character index.
+
+## Supported language rules
+
+- Units: `zero` through `nine`
+- Teens: `ten` through `nineteen`
+- Tens: `twenty` through `ninety`
+- Multipliers: `hundred`, `thousand`, `million`, `billion`, `trillion`, `quadrillion`
+- Optional filler: `and`
+- Optional sign prefix: `minus`, `negative`
+- Hyphenated inputs are accepted by default and can be disabled with `allowHyphen: false`
+- Connector words can be disabled with `allowAnd: false`
+
+## Extensibility
+
+- Use `extendLexicon` to add new words such as `dozen`, `lakh`, and `crore`.
+- Use `lexicon` to replace the default dictionary entirely for localization.
+- Unicode words are normalized before lookup, so composed and decomposed forms can resolve to the same entry.
+
+## Development
+
+```bash
+npm install
+npm run build
+npm test
+npm run bench
+```

package/dist/index.cjs

@@ -0,0 +1,344 @@
+"use strict";
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+
+// src/index.ts
+var index_exports = {};
+__export(index_exports, {
+  EmptyInputError: () => EmptyInputError,
+  InvalidSyntaxError: () => InvalidSyntaxError,
+  InvalidTokenError: () => InvalidTokenError,
+  TextNumberError: () => TextNumberError,
+  createParser: () => createParser,
+  englishLexicon: () => englishLexicon,
+  isTextNumberError: () => isTextNumberError,
+  parseTextNumber: () => parseTextNumber,
+  tryParseTextNumber: () => tryParseTextNumber
+});
+module.exports = __toCommonJS(index_exports);
+
+// src/errors.ts
+var TextNumberError = class extends Error {
+  code;
+  input;
+  constructor(code, message, input) {
+    super(message);
+    this.name = "TextNumberError";
+    this.code = code;
+    this.input = input;
+  }
+};
+var EmptyInputError = class extends TextNumberError {
+  constructor(input) {
+    super("EMPTY_INPUT", "Input does not contain any number words.", input);
+    this.name = "EmptyInputError";
+  }
+};
+var InvalidTokenError = class extends TextNumberError {
+  token;
+  index;
+  constructor(input, token, index) {
+    super(
+      "INVALID_TOKEN",
+      `Unknown number word "${token}" at index ${index}.`,
+      input
+    );
+    this.name = "InvalidTokenError";
+    this.token = token;
+    this.index = index;
+  }
+};
+var InvalidSyntaxError = class extends TextNumberError {
+  token;
+  index;
+  reason;
+  constructor(input, token, index, reason) {
+    super(
+      "INVALID_SYNTAX",
+      `${reason} Problematic token "${token}" at index ${index}.`,
+      input
+    );
+    this.name = "InvalidSyntaxError";
+    this.token = token;
+    this.index = index;
+    this.reason = reason;
+  }
+};
+function isTextNumberError(error) {
+  return error instanceof TextNumberError;
+}
+
+// src/parser.ts
+var MAX_SAFE_BIGINT = BigInt(Number.MAX_SAFE_INTEGER);
+var DEFAULT_MODES = {
+  allowAnd: true,
+  allowHyphen: true
+};
+var WORD_PATTERN = /[\p{L}\p{M}]+/gu;
+var HYPHENATED_WORD_PATTERN = /[\p{L}\p{M}](?:[\p{Pd}\u2212])[\p{L}\p{M}]/u;
+var englishLexicon = [
+  { word: "zero", type: "number", value: 0, cls: "unit" },
+  { word: "one", type: "number", value: 1, cls: "unit" },
+  { word: "two", type: "number", value: 2, cls: "unit" },
+  { word: "three", type: "number", value: 3, cls: "unit" },
+  { word: "four", type: "number", value: 4, cls: "unit" },
+  { word: "five", type: "number", value: 5, cls: "unit" },
+  { word: "six", type: "number", value: 6, cls: "unit" },
+  { word: "seven", type: "number", value: 7, cls: "unit" },
+  { word: "eight", type: "number", value: 8, cls: "unit" },
+  { word: "nine", type: "number", value: 9, cls: "unit" },
+  { word: "ten", type: "number", value: 10, cls: "teen" },
+  { word: "eleven", type: "number", value: 11, cls: "teen" },
+  { word: "twelve", type: "number", value: 12, cls: "teen" },
+  { word: "thirteen", type: "number", value: 13, cls: "teen" },
+  { word: "fourteen", type: "number", value: 14, cls: "teen" },
+  { word: "fifteen", type: "number", value: 15, cls: "teen" },
+  { word: "sixteen", type: "number", value: 16, cls: "teen" },
+  { word: "seventeen", type: "number", value: 17, cls: "teen" },
+  { word: "eighteen", type: "number", value: 18, cls: "teen" },
+  { word: "nineteen", type: "number", value: 19, cls: "teen" },
+  { word: "twenty", type: "number", value: 20, cls: "tens" },
+  { word: "thirty", type: "number", value: 30, cls: "tens" },
+  { word: "forty", type: "number", value: 40, cls: "tens" },
+  { word: "fifty", type: "number", value: 50, cls: "tens" },
+  { word: "sixty", type: "number", value: 60, cls: "tens" },
+  { word: "seventy", type: "number", value: 70, cls: "tens" },
+  { word: "eighty", type: "number", value: 80, cls: "tens" },
+  { word: "ninety", type: "number", value: 90, cls: "tens" },
+  { word: "hundred", type: "hundred", value: 100 },
+  { word: "thousand", type: "multiplier", value: 1e3 },
+  { word: "million", type: "multiplier", value: 1e6 },
+  { word: "billion", type: "multiplier", value: 1e9 },
+  { word: "trillion", type: "multiplier", value: 1e12 },
+  { word: "quadrillion", type: "multiplier", value: 1e15 },
+  { word: "minus", type: "sign", value: -1 },
+  { word: "negative", type: "sign", value: -1 },
+  { word: "and", type: "none", requiresMode: "allowAnd" }
+];
+function normalizeWord(word, locale, normalization) {
+  const normalized = normalization ? word.normalize(normalization) : word;
+  return locale === void 0 ? normalized.toLowerCase() : normalized.toLocaleLowerCase(locale);
+}
+function resolveModes(baseModes, overrideModes) {
+  return {
+    allowAnd: overrideModes?.allowAnd ?? baseModes.allowAnd,
+    allowHyphen: overrideModes?.allowHyphen ?? baseModes.allowHyphen
+  };
+}
+function toResolvedEntry(entry, normalizer) {
+  return {
+    word: entry.word,
+    normalizedWord: normalizer(entry.word),
+    type: entry.type,
+    value: BigInt(entry.value ?? 0),
+    cls: entry.cls ?? "none",
+    requiresMode: entry.requiresMode
+  };
+}
+function createLexiconMap(entries, normalizer) {
+  const lexicon = /* @__PURE__ */ new Map();
+  for (const entry of entries) {
+    const resolvedEntry = toResolvedEntry(entry, normalizer);
+    lexicon.set(resolvedEntry.normalizedWord, resolvedEntry);
+  }
+  return lexicon;
+}
+function invalidSyntax(input, token, reason) {
+  throw new InvalidSyntaxError(input, token.word, token.index, reason);
+}
+function toOutput(value) {
+  if (value <= MAX_SAFE_BIGINT && value >= -MAX_SAFE_BIGINT) {
+    return Number(value);
+  }
+  return value;
+}
+function tokenize(input, modes, normalizer) {
+  if (!modes.allowHyphen) {
+    const hyphenatedWord = input.match(HYPHENATED_WORD_PATTERN);
+    if (hyphenatedWord) {
+      throw new InvalidSyntaxError(
+        input,
+        hyphenatedWord[0],
+        hyphenatedWord.index ?? 0,
+        "Hyphenated words are disabled in the current parser mode."
+      );
+    }
+  }
+  const tokens = [];
+  for (const match of input.matchAll(WORD_PATTERN)) {
+    tokens.push({
+      word: normalizer(match[0]),
+      index: match.index ?? 0
+    });
+  }
+  return tokens;
+}
+function parseWithLexicon(input, lexicon, modes, normalizer) {
+  const tokens = tokenize(input, modes, normalizer);
+  if (tokens.length === 0) {
+    throw new EmptyInputError(input);
+  }
+  let total = 0n;
+  let group = 0n;
+  let sign = 1n;
+  let signUsed = false;
+  let hasValue = false;
+  let usedHundred = false;
+  let lastClass = "none";
+  let lastMultiplier = null;
+  for (const token of tokens) {
+    const definition = lexicon.get(token.word);
+    if (!definition) {
+      throw new InvalidTokenError(input, token.word, token.index);
+    }
+    if (definition.requiresMode && !modes[definition.requiresMode]) {
+      invalidSyntax(
+        input,
+        token,
+        `Token "${token.word}" is disabled in the current parser mode.`
+      );
+    }
+    switch (definition.type) {
+      case "sign": {
+        if (signUsed || hasValue) {
+          invalidSyntax(input, token, "Sign words are only allowed before the number.");
+        }
+        signUsed = true;
+        sign = definition.value;
+        break;
+      }
+      case "none": {
+        break;
+      }
+      case "number": {
+        if (lastClass === "unit" && definition.cls === "unit") {
+          invalidSyntax(input, token, "Two unit words cannot appear next to each other.");
+        }
+        if ((lastClass === "teen" || definition.cls === "teen") && lastClass !== "none") {
+          invalidSyntax(input, token, "Teen words must stand on their own within a group.");
+        }
+        if (lastClass === "tens" && definition.cls !== "unit") {
+          invalidSyntax(input, token, "A tens word can only be followed by a unit word.");
+        }
+        if (definition.cls === "tens" && lastClass !== "none") {
+          invalidSyntax(input, token, "A tens word must start a new group fragment.");
+        }
+        group += definition.value;
+        hasValue = true;
+        lastClass = definition.cls;
+        break;
+      }
+      case "hundred": {
+        if (group === 0n || usedHundred) {
+          invalidSyntax(
+            input,
+            token,
+            "Hundred requires a leading number and may only be used once per group."
+          );
+        }
+        group *= definition.value;
+        hasValue = true;
+        usedHundred = true;
+        lastClass = "none";
+        break;
+      }
+      case "multiplier": {
+        if (group === 0n) {
+          invalidSyntax(input, token, "Large multipliers require a leading group value.");
+        }
+        if (lastMultiplier !== null && definition.value >= lastMultiplier) {
+          invalidSyntax(input, token, "Large multipliers must appear in descending order.");
+        }
+        total += group * definition.value;
+        group = 0n;
+        hasValue = true;
+        usedHundred = false;
+        lastClass = "none";
+        lastMultiplier = definition.value;
+        break;
+      }
+    }
+  }
+  if (!hasValue) {
+    const lastToken = tokens.at(-1);
+    invalidSyntax(input, lastToken, "Input did not contain a numeric value.");
+  }
+  return toOutput((total + group) * sign);
+}
+function createParser(options = {}) {
+  const normalization = options.normalization ?? "NFKC";
+  const locale = options.locale;
+  const normalizer = (word) => normalizeWord(word, locale, normalization);
+  const lexicon = createLexiconMap(options.lexicon ?? englishLexicon, normalizer);
+  for (const entry of options.extendLexicon ?? []) {
+    const resolvedEntry = toResolvedEntry(entry, normalizer);
+    lexicon.set(resolvedEntry.normalizedWord, resolvedEntry);
+  }
+  const defaultModes = resolveModes(DEFAULT_MODES, options.modes);
+  const parse = (input, modes) => {
+    if (typeof input !== "string") {
+      throw new TypeError("parseTextNumber expects a string input.");
+    }
+    return parseWithLexicon(input, lexicon, resolveModes(defaultModes, modes), normalizer);
+  };
+  const tryParse = (input, modes) => {
+    try {
+      return {
+        ok: true,
+        value: parse(input, modes)
+      };
+    } catch (error) {
+      if (isTextNumberError(error)) {
+        return {
+          ok: false,
+          error
+        };
+      }
+      throw error;
+    }
+  };
+  return {
+    parse,
+    tryParse,
+    lexicon,
+    locale,
+    normalization,
+    modes: defaultModes
+  };
+}
+
+// src/index.ts
+var defaultParser = createParser();
+function parseTextNumber(input, modes) {
+  return defaultParser.parse(input, modes);
+}
+function tryParseTextNumber(input, modes) {
+  return defaultParser.tryParse(input, modes);
+}
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  EmptyInputError,
+  InvalidSyntaxError,
+  InvalidTokenError,
+  TextNumberError,
+  createParser,
+  englishLexicon,
+  isTextNumberError,
+  parseTextNumber,
+  tryParseTextNumber
+});

package/dist/index.d.cts

@@ -0,0 +1,257 @@
+type TextNumberErrorCode = "EMPTY_INPUT" | "INVALID_TOKEN" | "INVALID_SYNTAX";
+declare class TextNumberError extends Error {
+    readonly code: TextNumberErrorCode;
+    readonly input: string;
+    constructor(code: TextNumberErrorCode, message: string, input: string);
+}
+declare class EmptyInputError extends TextNumberError {
+    constructor(input: string);
+}
+declare class InvalidTokenError extends TextNumberError {
+    readonly token: string;
+    readonly index: number;
+    constructor(input: string, token: string, index: number);
+}
+declare class InvalidSyntaxError extends TextNumberError {
+    readonly token: string;
+    readonly index: number;
+    readonly reason: string;
+    constructor(input: string, token: string, index: number, reason: string);
+}
+declare function isTextNumberError(error: unknown): error is TextNumberError;
+
+type ParsedNumber = bigint | number;
+type LexiconTokenType = "none" | "sign" | "number" | "hundred" | "multiplier";
+type LexiconTokenClass = "none" | "unit" | "teen" | "tens";
+type TextNormalizationForm = "NFC" | "NFD" | "NFKC" | "NFKD";
+type ParserModeName = "allowAnd" | "allowHyphen";
+interface ParserModes {
+    allowAnd?: boolean;
+    allowHyphen?: boolean;
+}
+interface LexiconEntry {
+    word: string;
+    type: LexiconTokenType;
+    value?: number | bigint;
+    cls?: LexiconTokenClass;
+    requiresMode?: Extract<ParserModeName, "allowAnd">;
+}
+interface CreateParserOptions {
+    lexicon?: Iterable<LexiconEntry>;
+    extendLexicon?: Iterable<LexiconEntry>;
+    locale?: Intl.LocalesArgument;
+    normalization?: TextNormalizationForm | false;
+    modes?: ParserModes;
+}
+type ParseSuccess = {
+    ok: true;
+    value: ParsedNumber;
+};
+type ParseFailure = {
+    ok: false;
+    error: TextNumberError;
+};
+type ParseResult = ParseSuccess | ParseFailure;
+interface TextNumberParser {
+    parse(input: string, modes?: ParserModes): ParsedNumber;
+    tryParse(input: string, modes?: ParserModes): ParseResult;
+    readonly lexicon: ReadonlyMap<string, Readonly<ResolvedLexiconEntry>>;
+    readonly locale?: Intl.LocalesArgument;
+    readonly normalization: TextNormalizationForm | false;
+    readonly modes: Readonly<ResolvedParserModes>;
+}
+interface ResolvedLexiconEntry {
+    word: string;
+    normalizedWord: string;
+    type: LexiconTokenType;
+    value: bigint;
+    cls: LexiconTokenClass;
+    requiresMode?: Extract<ParserModeName, "allowAnd">;
+}
+interface ResolvedParserModes {
+    allowAnd: boolean;
+    allowHyphen: boolean;
+}
+declare const englishLexicon: readonly [{
+    readonly word: "zero";
+    readonly type: "number";
+    readonly value: 0;
+    readonly cls: "unit";
+}, {
+    readonly word: "one";
+    readonly type: "number";
+    readonly value: 1;
+    readonly cls: "unit";
+}, {
+    readonly word: "two";
+    readonly type: "number";
+    readonly value: 2;
+    readonly cls: "unit";
+}, {
+    readonly word: "three";
+    readonly type: "number";
+    readonly value: 3;
+    readonly cls: "unit";
+}, {
+    readonly word: "four";
+    readonly type: "number";
+    readonly value: 4;
+    readonly cls: "unit";
+}, {
+    readonly word: "five";
+    readonly type: "number";
+    readonly value: 5;
+    readonly cls: "unit";
+}, {
+    readonly word: "six";
+    readonly type: "number";
+    readonly value: 6;
+    readonly cls: "unit";
+}, {
+    readonly word: "seven";
+    readonly type: "number";
+    readonly value: 7;
+    readonly cls: "unit";
+}, {
+    readonly word: "eight";
+    readonly type: "number";
+    readonly value: 8;
+    readonly cls: "unit";
+}, {
+    readonly word: "nine";
+    readonly type: "number";
+    readonly value: 9;
+    readonly cls: "unit";
+}, {
+    readonly word: "ten";
+    readonly type: "number";
+    readonly value: 10;
+    readonly cls: "teen";
+}, {
+    readonly word: "eleven";
+    readonly type: "number";
+    readonly value: 11;
+    readonly cls: "teen";
+}, {
+    readonly word: "twelve";
+    readonly type: "number";
+    readonly value: 12;
+    readonly cls: "teen";
+}, {
+    readonly word: "thirteen";
+    readonly type: "number";
+    readonly value: 13;
+    readonly cls: "teen";
+}, {
+    readonly word: "fourteen";
+    readonly type: "number";
+    readonly value: 14;
+    readonly cls: "teen";
+}, {
+    readonly word: "fifteen";
+    readonly type: "number";
+    readonly value: 15;
+    readonly cls: "teen";
+}, {
+    readonly word: "sixteen";
+    readonly type: "number";
+    readonly value: 16;
+    readonly cls: "teen";
+}, {
+    readonly word: "seventeen";
+    readonly type: "number";
+    readonly value: 17;
+    readonly cls: "teen";
+}, {
+    readonly word: "eighteen";
+    readonly type: "number";
+    readonly value: 18;
+    readonly cls: "teen";
+}, {
+    readonly word: "nineteen";
+    readonly type: "number";
+    readonly value: 19;
+    readonly cls: "teen";
+}, {
+    readonly word: "twenty";
+    readonly type: "number";
+    readonly value: 20;
+    readonly cls: "tens";
+}, {
+    readonly word: "thirty";
+    readonly type: "number";
+    readonly value: 30;
+    readonly cls: "tens";
+}, {
+    readonly word: "forty";
+    readonly type: "number";
+    readonly value: 40;
+    readonly cls: "tens";
+}, {
+    readonly word: "fifty";
+    readonly type: "number";
+    readonly value: 50;
+    readonly cls: "tens";
+}, {
+    readonly word: "sixty";
+    readonly type: "number";
+    readonly value: 60;
+    readonly cls: "tens";
+}, {
+    readonly word: "seventy";
+    readonly type: "number";
+    readonly value: 70;
+    readonly cls: "tens";
+}, {
+    readonly word: "eighty";
+    readonly type: "number";
+    readonly value: 80;
+    readonly cls: "tens";
+}, {
+    readonly word: "ninety";
+    readonly type: "number";
+    readonly value: 90;
+    readonly cls: "tens";
+}, {
+    readonly word: "hundred";
+    readonly type: "hundred";
+    readonly value: 100;
+}, {
+    readonly word: "thousand";
+    readonly type: "multiplier";
+    readonly value: 1000;
+}, {
+    readonly word: "million";
+    readonly type: "multiplier";
+    readonly value: 1000000;
+}, {
+    readonly word: "billion";
+    readonly type: "multiplier";
+    readonly value: 1000000000;
+}, {
+    readonly word: "trillion";
+    readonly type: "multiplier";
+    readonly value: 1000000000000;
+}, {
+    readonly word: "quadrillion";
+    readonly type: "multiplier";
+    readonly value: 1000000000000000;
+}, {
+    readonly word: "minus";
+    readonly type: "sign";
+    readonly value: -1;
+}, {
+    readonly word: "negative";
+    readonly type: "sign";
+    readonly value: -1;
+}, {
+    readonly word: "and";
+    readonly type: "none";
+    readonly requiresMode: "allowAnd";
+}];
+declare function createParser(options?: CreateParserOptions): TextNumberParser;
+
+declare function parseTextNumber(input: string, modes?: ParserModes): ParsedNumber;
+declare function tryParseTextNumber(input: string, modes?: ParserModes): ParseResult;
+
+export { type CreateParserOptions, EmptyInputError, InvalidSyntaxError, InvalidTokenError, type LexiconEntry, type LexiconTokenClass, type LexiconTokenType, type ParseFailure, type ParseResult, type ParseSuccess, type ParsedNumber, type ParserModeName, type ParserModes, type TextNormalizationForm, TextNumberError, type TextNumberParser, createParser, englishLexicon, isTextNumberError, parseTextNumber, tryParseTextNumber };

package/dist/index.d.ts

@@ -0,0 +1,257 @@
+type TextNumberErrorCode = "EMPTY_INPUT" | "INVALID_TOKEN" | "INVALID_SYNTAX";
+declare class TextNumberError extends Error {
+    readonly code: TextNumberErrorCode;
+    readonly input: string;
+    constructor(code: TextNumberErrorCode, message: string, input: string);
+}
+declare class EmptyInputError extends TextNumberError {
+    constructor(input: string);
+}
+declare class InvalidTokenError extends TextNumberError {
+    readonly token: string;
+    readonly index: number;
+    constructor(input: string, token: string, index: number);
+}
+declare class InvalidSyntaxError extends TextNumberError {
+    readonly token: string;
+    readonly index: number;
+    readonly reason: string;
+    constructor(input: string, token: string, index: number, reason: string);
+}
+declare function isTextNumberError(error: unknown): error is TextNumberError;
+
+type ParsedNumber = bigint | number;
+type LexiconTokenType = "none" | "sign" | "number" | "hundred" | "multiplier";
+type LexiconTokenClass = "none" | "unit" | "teen" | "tens";
+type TextNormalizationForm = "NFC" | "NFD" | "NFKC" | "NFKD";
+type ParserModeName = "allowAnd" | "allowHyphen";
+interface ParserModes {
+    allowAnd?: boolean;
+    allowHyphen?: boolean;
+}
+interface LexiconEntry {
+    word: string;
+    type: LexiconTokenType;
+    value?: number | bigint;
+    cls?: LexiconTokenClass;
+    requiresMode?: Extract<ParserModeName, "allowAnd">;
+}
+interface CreateParserOptions {
+    lexicon?: Iterable<LexiconEntry>;
+    extendLexicon?: Iterable<LexiconEntry>;
+    locale?: Intl.LocalesArgument;
+    normalization?: TextNormalizationForm | false;
+    modes?: ParserModes;
+}
+type ParseSuccess = {
+    ok: true;
+    value: ParsedNumber;
+};
+type ParseFailure = {
+    ok: false;
+    error: TextNumberError;
+};
+type ParseResult = ParseSuccess | ParseFailure;
+interface TextNumberParser {
+    parse(input: string, modes?: ParserModes): ParsedNumber;
+    tryParse(input: string, modes?: ParserModes): ParseResult;
+    readonly lexicon: ReadonlyMap<string, Readonly<ResolvedLexiconEntry>>;
+    readonly locale?: Intl.LocalesArgument;
+    readonly normalization: TextNormalizationForm | false;
+    readonly modes: Readonly<ResolvedParserModes>;
+}
+interface ResolvedLexiconEntry {
+    word: string;
+    normalizedWord: string;
+    type: LexiconTokenType;
+    value: bigint;
+    cls: LexiconTokenClass;
+    requiresMode?: Extract<ParserModeName, "allowAnd">;
+}
+interface ResolvedParserModes {
+    allowAnd: boolean;
+    allowHyphen: boolean;
+}
+declare const englishLexicon: readonly [{
+    readonly word: "zero";
+    readonly type: "number";
+    readonly value: 0;
+    readonly cls: "unit";
+}, {
+    readonly word: "one";
+    readonly type: "number";
+    readonly value: 1;
+    readonly cls: "unit";
+}, {
+    readonly word: "two";
+    readonly type: "number";
+    readonly value: 2;
+    readonly cls: "unit";
+}, {
+    readonly word: "three";
+    readonly type: "number";
+    readonly value: 3;
+    readonly cls: "unit";
+}, {
+    readonly word: "four";
+    readonly type: "number";
+    readonly value: 4;
+    readonly cls: "unit";
+}, {
+    readonly word: "five";
+    readonly type: "number";
+    readonly value: 5;
+    readonly cls: "unit";
+}, {
+    readonly word: "six";
+    readonly type: "number";
+    readonly value: 6;
+    readonly cls: "unit";
+}, {
+    readonly word: "seven";
+    readonly type: "number";
+    readonly value: 7;
+    readonly cls: "unit";
+}, {
+    readonly word: "eight";
+    readonly type: "number";
+    readonly value: 8;
+    readonly cls: "unit";
+}, {
+    readonly word: "nine";
+    readonly type: "number";
+    readonly value: 9;
+    readonly cls: "unit";
+}, {
+    readonly word: "ten";
+    readonly type: "number";
+    readonly value: 10;
+    readonly cls: "teen";
+}, {
+    readonly word: "eleven";
+    readonly type: "number";
+    readonly value: 11;
+    readonly cls: "teen";
+}, {
+    readonly word: "twelve";
+    readonly type: "number";
+    readonly value: 12;
+    readonly cls: "teen";
+}, {
+    readonly word: "thirteen";
+    readonly type: "number";
+    readonly value: 13;
+    readonly cls: "teen";
+}, {
+    readonly word: "fourteen";
+    readonly type: "number";
+    readonly value: 14;
+    readonly cls: "teen";
+}, {
+    readonly word: "fifteen";
+    readonly type: "number";
+    readonly value: 15;
+    readonly cls: "teen";
+}, {
+    readonly word: "sixteen";
+    readonly type: "number";
+    readonly value: 16;
+    readonly cls: "teen";
+}, {
+    readonly word: "seventeen";
+    readonly type: "number";
+    readonly value: 17;
+    readonly cls: "teen";
+}, {
+    readonly word: "eighteen";
+    readonly type: "number";
+    readonly value: 18;
+    readonly cls: "teen";
+}, {
+    readonly word: "nineteen";
+    readonly type: "number";
+    readonly value: 19;
+    readonly cls: "teen";
+}, {
+    readonly word: "twenty";
+    readonly type: "number";
+    readonly value: 20;
+    readonly cls: "tens";
+}, {
+    readonly word: "thirty";
+    readonly type: "number";
+    readonly value: 30;
+    readonly cls: "tens";
+}, {
+    readonly word: "forty";
+    readonly type: "number";
+    readonly value: 40;
+    readonly cls: "tens";
+}, {
+    readonly word: "fifty";
+    readonly type: "number";
+    readonly value: 50;
+    readonly cls: "tens";
+}, {
+    readonly word: "sixty";
+    readonly type: "number";
+    readonly value: 60;
+    readonly cls: "tens";
+}, {
+    readonly word: "seventy";
+    readonly type: "number";
+    readonly value: 70;
+    readonly cls: "tens";
+}, {
+    readonly word: "eighty";
+    readonly type: "number";
+    readonly value: 80;
+    readonly cls: "tens";
+}, {
+    readonly word: "ninety";
+    readonly type: "number";
+    readonly value: 90;
+    readonly cls: "tens";
+}, {
+    readonly word: "hundred";
+    readonly type: "hundred";
+    readonly value: 100;
+}, {
+    readonly word: "thousand";
+    readonly type: "multiplier";
+    readonly value: 1000;
+}, {
+    readonly word: "million";
+    readonly type: "multiplier";
+    readonly value: 1000000;
+}, {
+    readonly word: "billion";
+    readonly type: "multiplier";
+    readonly value: 1000000000;
+}, {
+    readonly word: "trillion";
+    readonly type: "multiplier";
+    readonly value: 1000000000000;
+}, {
+    readonly word: "quadrillion";
+    readonly type: "multiplier";
+    readonly value: 1000000000000000;
+}, {
+    readonly word: "minus";
+    readonly type: "sign";
+    readonly value: -1;
+}, {
+    readonly word: "negative";
+    readonly type: "sign";
+    readonly value: -1;
+}, {
+    readonly word: "and";
+    readonly type: "none";
+    readonly requiresMode: "allowAnd";
+}];
+declare function createParser(options?: CreateParserOptions): TextNumberParser;
+
+declare function parseTextNumber(input: string, modes?: ParserModes): ParsedNumber;
+declare function tryParseTextNumber(input: string, modes?: ParserModes): ParseResult;
+
+export { type CreateParserOptions, EmptyInputError, InvalidSyntaxError, InvalidTokenError, type LexiconEntry, type LexiconTokenClass, type LexiconTokenType, type ParseFailure, type ParseResult, type ParseSuccess, type ParsedNumber, type ParserModeName, type ParserModes, type TextNormalizationForm, TextNumberError, type TextNumberParser, createParser, englishLexicon, isTextNumberError, parseTextNumber, tryParseTextNumber };

package/dist/index.js

@@ -0,0 +1,309 @@
+// src/errors.ts
+var TextNumberError = class extends Error {
+  code;
+  input;
+  constructor(code, message, input) {
+    super(message);
+    this.name = "TextNumberError";
+    this.code = code;
+    this.input = input;
+  }
+};
+var EmptyInputError = class extends TextNumberError {
+  constructor(input) {
+    super("EMPTY_INPUT", "Input does not contain any number words.", input);
+    this.name = "EmptyInputError";
+  }
+};
+var InvalidTokenError = class extends TextNumberError {
+  token;
+  index;
+  constructor(input, token, index) {
+    super(
+      "INVALID_TOKEN",
+      `Unknown number word "${token}" at index ${index}.`,
+      input
+    );
+    this.name = "InvalidTokenError";
+    this.token = token;
+    this.index = index;
+  }
+};
+var InvalidSyntaxError = class extends TextNumberError {
+  token;
+  index;
+  reason;
+  constructor(input, token, index, reason) {
+    super(
+      "INVALID_SYNTAX",
+      `${reason} Problematic token "${token}" at index ${index}.`,
+      input
+    );
+    this.name = "InvalidSyntaxError";
+    this.token = token;
+    this.index = index;
+    this.reason = reason;
+  }
+};
+function isTextNumberError(error) {
+  return error instanceof TextNumberError;
+}
+
+// src/parser.ts
+var MAX_SAFE_BIGINT = BigInt(Number.MAX_SAFE_INTEGER);
+var DEFAULT_MODES = {
+  allowAnd: true,
+  allowHyphen: true
+};
+var WORD_PATTERN = /[\p{L}\p{M}]+/gu;
+var HYPHENATED_WORD_PATTERN = /[\p{L}\p{M}](?:[\p{Pd}\u2212])[\p{L}\p{M}]/u;
+var englishLexicon = [
+  { word: "zero", type: "number", value: 0, cls: "unit" },
+  { word: "one", type: "number", value: 1, cls: "unit" },
+  { word: "two", type: "number", value: 2, cls: "unit" },
+  { word: "three", type: "number", value: 3, cls: "unit" },
+  { word: "four", type: "number", value: 4, cls: "unit" },
+  { word: "five", type: "number", value: 5, cls: "unit" },
+  { word: "six", type: "number", value: 6, cls: "unit" },
+  { word: "seven", type: "number", value: 7, cls: "unit" },
+  { word: "eight", type: "number", value: 8, cls: "unit" },
+  { word: "nine", type: "number", value: 9, cls: "unit" },
+  { word: "ten", type: "number", value: 10, cls: "teen" },
+  { word: "eleven", type: "number", value: 11, cls: "teen" },
+  { word: "twelve", type: "number", value: 12, cls: "teen" },
+  { word: "thirteen", type: "number", value: 13, cls: "teen" },
+  { word: "fourteen", type: "number", value: 14, cls: "teen" },
+  { word: "fifteen", type: "number", value: 15, cls: "teen" },
+  { word: "sixteen", type: "number", value: 16, cls: "teen" },
+  { word: "seventeen", type: "number", value: 17, cls: "teen" },
+  { word: "eighteen", type: "number", value: 18, cls: "teen" },
+  { word: "nineteen", type: "number", value: 19, cls: "teen" },
+  { word: "twenty", type: "number", value: 20, cls: "tens" },
+  { word: "thirty", type: "number", value: 30, cls: "tens" },
+  { word: "forty", type: "number", value: 40, cls: "tens" },
+  { word: "fifty", type: "number", value: 50, cls: "tens" },
+  { word: "sixty", type: "number", value: 60, cls: "tens" },
+  { word: "seventy", type: "number", value: 70, cls: "tens" },
+  { word: "eighty", type: "number", value: 80, cls: "tens" },
+  { word: "ninety", type: "number", value: 90, cls: "tens" },
+  { word: "hundred", type: "hundred", value: 100 },
+  { word: "thousand", type: "multiplier", value: 1e3 },
+  { word: "million", type: "multiplier", value: 1e6 },
+  { word: "billion", type: "multiplier", value: 1e9 },
+  { word: "trillion", type: "multiplier", value: 1e12 },
+  { word: "quadrillion", type: "multiplier", value: 1e15 },
+  { word: "minus", type: "sign", value: -1 },
+  { word: "negative", type: "sign", value: -1 },
+  { word: "and", type: "none", requiresMode: "allowAnd" }
+];
+function normalizeWord(word, locale, normalization) {
+  const normalized = normalization ? word.normalize(normalization) : word;
+  return locale === void 0 ? normalized.toLowerCase() : normalized.toLocaleLowerCase(locale);
+}
+function resolveModes(baseModes, overrideModes) {
+  return {
+    allowAnd: overrideModes?.allowAnd ?? baseModes.allowAnd,
+    allowHyphen: overrideModes?.allowHyphen ?? baseModes.allowHyphen
+  };
+}
+function toResolvedEntry(entry, normalizer) {
+  return {
+    word: entry.word,
+    normalizedWord: normalizer(entry.word),
+    type: entry.type,
+    value: BigInt(entry.value ?? 0),
+    cls: entry.cls ?? "none",
+    requiresMode: entry.requiresMode
+  };
+}
+function createLexiconMap(entries, normalizer) {
+  const lexicon = /* @__PURE__ */ new Map();
+  for (const entry of entries) {
+    const resolvedEntry = toResolvedEntry(entry, normalizer);
+    lexicon.set(resolvedEntry.normalizedWord, resolvedEntry);
+  }
+  return lexicon;
+}
+function invalidSyntax(input, token, reason) {
+  throw new InvalidSyntaxError(input, token.word, token.index, reason);
+}
+function toOutput(value) {
+  if (value <= MAX_SAFE_BIGINT && value >= -MAX_SAFE_BIGINT) {
+    return Number(value);
+  }
+  return value;
+}
+function tokenize(input, modes, normalizer) {
+  if (!modes.allowHyphen) {
+    const hyphenatedWord = input.match(HYPHENATED_WORD_PATTERN);
+    if (hyphenatedWord) {
+      throw new InvalidSyntaxError(
+        input,
+        hyphenatedWord[0],
+        hyphenatedWord.index ?? 0,
+        "Hyphenated words are disabled in the current parser mode."
+      );
+    }
+  }
+  const tokens = [];
+  for (const match of input.matchAll(WORD_PATTERN)) {
+    tokens.push({
+      word: normalizer(match[0]),
+      index: match.index ?? 0
+    });
+  }
+  return tokens;
+}
+function parseWithLexicon(input, lexicon, modes, normalizer) {
+  const tokens = tokenize(input, modes, normalizer);
+  if (tokens.length === 0) {
+    throw new EmptyInputError(input);
+  }
+  let total = 0n;
+  let group = 0n;
+  let sign = 1n;
+  let signUsed = false;
+  let hasValue = false;
+  let usedHundred = false;
+  let lastClass = "none";
+  let lastMultiplier = null;
+  for (const token of tokens) {
+    const definition = lexicon.get(token.word);
+    if (!definition) {
+      throw new InvalidTokenError(input, token.word, token.index);
+    }
+    if (definition.requiresMode && !modes[definition.requiresMode]) {
+      invalidSyntax(
+        input,
+        token,
+        `Token "${token.word}" is disabled in the current parser mode.`
+      );
+    }
+    switch (definition.type) {
+      case "sign": {
+        if (signUsed || hasValue) {
+          invalidSyntax(input, token, "Sign words are only allowed before the number.");
+        }
+        signUsed = true;
+        sign = definition.value;
+        break;
+      }
+      case "none": {
+        break;
+      }
+      case "number": {
+        if (lastClass === "unit" && definition.cls === "unit") {
+          invalidSyntax(input, token, "Two unit words cannot appear next to each other.");
+        }
+        if ((lastClass === "teen" || definition.cls === "teen") && lastClass !== "none") {
+          invalidSyntax(input, token, "Teen words must stand on their own within a group.");
+        }
+        if (lastClass === "tens" && definition.cls !== "unit") {
+          invalidSyntax(input, token, "A tens word can only be followed by a unit word.");
+        }
+        if (definition.cls === "tens" && lastClass !== "none") {
+          invalidSyntax(input, token, "A tens word must start a new group fragment.");
+        }
+        group += definition.value;
+        hasValue = true;
+        lastClass = definition.cls;
+        break;
+      }
+      case "hundred": {
+        if (group === 0n || usedHundred) {
+          invalidSyntax(
+            input,
+            token,
+            "Hundred requires a leading number and may only be used once per group."
+          );
+        }
+        group *= definition.value;
+        hasValue = true;
+        usedHundred = true;
+        lastClass = "none";
+        break;
+      }
+      case "multiplier": {
+        if (group === 0n) {
+          invalidSyntax(input, token, "Large multipliers require a leading group value.");
+        }
+        if (lastMultiplier !== null && definition.value >= lastMultiplier) {
+          invalidSyntax(input, token, "Large multipliers must appear in descending order.");
+        }
+        total += group * definition.value;
+        group = 0n;
+        hasValue = true;
+        usedHundred = false;
+        lastClass = "none";
+        lastMultiplier = definition.value;
+        break;
+      }
+    }
+  }
+  if (!hasValue) {
+    const lastToken = tokens.at(-1);
+    invalidSyntax(input, lastToken, "Input did not contain a numeric value.");
+  }
+  return toOutput((total + group) * sign);
+}
+function createParser(options = {}) {
+  const normalization = options.normalization ?? "NFKC";
+  const locale = options.locale;
+  const normalizer = (word) => normalizeWord(word, locale, normalization);
+  const lexicon = createLexiconMap(options.lexicon ?? englishLexicon, normalizer);
+  for (const entry of options.extendLexicon ?? []) {
+    const resolvedEntry = toResolvedEntry(entry, normalizer);
+    lexicon.set(resolvedEntry.normalizedWord, resolvedEntry);
+  }
+  const defaultModes = resolveModes(DEFAULT_MODES, options.modes);
+  const parse = (input, modes) => {
+    if (typeof input !== "string") {
+      throw new TypeError("parseTextNumber expects a string input.");
+    }
+    return parseWithLexicon(input, lexicon, resolveModes(defaultModes, modes), normalizer);
+  };
+  const tryParse = (input, modes) => {
+    try {
+      return {
+        ok: true,
+        value: parse(input, modes)
+      };
+    } catch (error) {
+      if (isTextNumberError(error)) {
+        return {
+          ok: false,
+          error
+        };
+      }
+      throw error;
+    }
+  };
+  return {
+    parse,
+    tryParse,
+    lexicon,
+    locale,
+    normalization,
+    modes: defaultModes
+  };
+}
+
+// src/index.ts
+var defaultParser = createParser();
+function parseTextNumber(input, modes) {
+  return defaultParser.parse(input, modes);
+}
+function tryParseTextNumber(input, modes) {
+  return defaultParser.tryParse(input, modes);
+}
+export {
+  EmptyInputError,
+  InvalidSyntaxError,
+  InvalidTokenError,
+  TextNumberError,
+  createParser,
+  englishLexicon,
+  isTextNumberError,
+  parseTextNumber,
+  tryParseTextNumber
+};

package/package.json

@@ -0,0 +1,61 @@
+{
+  "name": "text-number-parser",
+  "version": "0.1.0",
+  "description": "Parse localized Unicode number words into JavaScript number and bigint values.",
+  "author": "Michael Three <michael.three@kiv.dev>",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/michaelthreekiv/text-number-parser.git"
+  },
+  "homepage": "https://github.com/michaelthreekiv/text-number-parser#readme",
+  "bugs": {
+    "url": "https://github.com/michaelthreekiv/text-number-parser/issues"
+  },
+  "type": "module",
+  "main": "./dist/index.cjs",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "publishConfig": {
+    "access": "public"
+  },
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js",
+      "require": "./dist/index.cjs"
+    }
+  },
+  "files": [
+    "dist",
+    "README.md"
+  ],
+  "engines": {
+    "node": ">=18"
+  },
+  "scripts": {
+    "build": "tsup src/index.ts --format esm,cjs --dts --clean",
+    "test": "vitest run",
+    "bench": "tsx benchmark/parse.bench.ts",
+    "check": "npm run build && npm run test",
+    "prepublishOnly": "npm run check"
+  },
+  "keywords": [
+    "parser",
+    "number",
+    "words-to-number",
+    "text-number",
+    "unicode",
+    "localization",
+    "i18n",
+    "bigint",
+    "nlp"
+  ],
+  "license": "MIT",
+  "devDependencies": {
+    "tinybench": "^2.9.0",
+    "tsup": "^8.3.5",
+    "tsx": "^4.20.3",
+    "typescript": "^5.8.3",
+    "vitest": "^3.2.4"
+  }
+}