@visulima/string 1.2.3 → 1.3.0

package/dist/case/split-by-case.mjs

@@ -1,637 +1 @@
-import { stripVTControlCharacters } from 'node:util';
-import { j as RE_EMOJI, s as stripEmoji, k as RE_SEPARATORS, R as RE_FAST_ANSI, l as RE_CYRILLIC, m as RE_LATIN, n as RE_GREEK, o as RE_GREEK_LATIN_SPLIT, p as RE_KANJI, q as RE_HEBREW, r as RE_ARABIC, t as RE_HANGUL, u as RE_UZBEK_LATIN_MODIFIER, v as RE_KATAKANA, w as RE_HIRAGANA, x as RE_DEVANAGARI, y as RE_BENGALI, z as RE_GUJARATI, A as RE_GURMUKHI, B as RE_KANNADA, C as RE_TAMIL, D as RE_TELUGU, E as RE_MALAYALAM, F as RE_SINHALA, G as RE_THAI, H as RE_LAO, I as RE_TIBETAN, J as RE_MYANMAR, K as RE_ETHIOPIC, L as RE_KHMER, M as RE_ORIYA } from '../packem_shared/constants-CKdlkHVU.mjs';
-import LRUCache from '../packem_shared/LRUCache-udNErhWw.mjs';
-
-var __defProp$2 = Object.defineProperty;
-var __name$2 = (target, value) => __defProp$2(target, "name", { value, configurable: true });
-const regexCache = new LRUCache(1e3);
-const getSeparatorsRegex = /* @__PURE__ */ __name$2((separators) => {
-  const key = separators.join("");
-  if (regexCache.has(key)) {
-    return regexCache.get(key);
-  }
-  const pattern = separators.map((s) => s.replaceAll(/[.*+?^${}()|[\]\\]/g, "\\$&")).join("|");
-  const regex = new RegExp(pattern, "g");
-  regexCache.set(key, regex);
-  return regex;
-}, "getSeparatorsRegex");
-
-var __defProp$1 = Object.defineProperty;
-var __name$1 = (target, value) => __defProp$1(target, "name", { value, configurable: true });
-const splitByEmoji = /* @__PURE__ */ __name$1((text) => {
-  const segments = [];
-  let lastIndex = 0;
-  let match;
-  RE_EMOJI.lastIndex = 0;
-  while ((match = RE_EMOJI.exec(text)) !== null) {
-    if (match.index > lastIndex) {
-      segments.push(text.slice(lastIndex, match.index));
-    }
-    segments.push(match[0]);
-    lastIndex = RE_EMOJI.lastIndex;
-  }
-  if (lastIndex < text.length) {
-    segments.push(text.slice(lastIndex));
-  }
-  return segments.filter(Boolean);
-}, "splitByEmoji");
-
-var __defProp = Object.defineProperty;
-var __name = (target, value) => __defProp(target, "name", { value, configurable: true });
-const isUpperCode = new Uint8Array(128);
-const isLowerCode = new Uint8Array(128);
-const isDigitCode = new Uint8Array(128);
-for (let index = 0; index < 128; index++) {
-  isUpperCode[index] = index >= 65 && index <= 90 ? 1 : 0;
-  isLowerCode[index] = index >= 97 && index <= 122 ? 1 : 0;
-  isDigitCode[index] = index >= 48 && index <= 57 ? 1 : 0;
-}
-const isUpper = /* @__PURE__ */ __name((code) => isUpperCode[code], "isUpper");
-const isLower = /* @__PURE__ */ __name((code) => isLowerCode[code], "isLower");
-const isDigit = /* @__PURE__ */ __name((code) => isDigitCode[code], "isDigit");
-const handleScriptTransitions = /* @__PURE__ */ __name((s, scriptDetectors, caseSensitive, locale, customSplitLogic) => {
-  if (s.length === 0) {
-    return [];
-  }
-  let hasDetectedScript = false;
-  for (const detector of Object.values(scriptDetectors)) {
-    if (detector(s[0])) {
-      hasDetectedScript = true;
-      break;
-    }
-  }
-  if (!hasDetectedScript && !caseSensitive) {
-    return [s];
-  }
-  const chars = [...s];
-  const result = [];
-  let currentSegment = chars[0];
-  let previousType = "other";
-  for (const [type, detector] of Object.entries(scriptDetectors)) {
-    if (detector(chars[0])) {
-      previousType = type;
-      break;
-    }
-  }
-  let previousIsUpper = caseSensitive && locale ? chars[0] === chars[0].toLocaleUpperCase(locale) : false;
-  for (let index = 1; index < chars.length; index++) {
-    const char = chars[index];
-    let currentType = "other";
-    for (const [type, detector] of Object.entries(scriptDetectors)) {
-      if (detector(char)) {
-        currentType = type;
-        break;
-      }
-    }
-    const isUpperCaseChar = caseSensitive && locale ? char === char.toLocaleUpperCase(locale) : false;
-    let shouldSplit = false;
-    if (customSplitLogic) {
-      shouldSplit = customSplitLogic(previousType, currentType, previousIsUpper, isUpperCaseChar, char, index, chars);
-    } else {
-      if (previousType !== currentType && previousType !== "other" && currentType !== "other") {
-        shouldSplit = true;
-      }
-      if (caseSensitive && currentType !== "other" && !previousIsUpper && isUpperCaseChar) {
-        shouldSplit = true;
-      }
-    }
-    if (shouldSplit) {
-      result.push(currentSegment);
-      currentSegment = char;
-    } else {
-      currentSegment += char;
-    }
-    previousType = currentType;
-    if (caseSensitive) {
-      previousIsUpper = isUpperCaseChar;
-    }
-  }
-  if (currentSegment && currentSegment.length > 0) {
-    result.push(currentSegment);
-  }
-  return result.length > 0 ? result : [s];
-}, "handleScriptTransitions");
-const splitCamelCaseFast = /* @__PURE__ */ __name((s, knownAcronyms = /* @__PURE__ */ new Set()) => {
-  if (s.length === 0) {
-    return [];
-  }
-  if (s.toUpperCase() === s) {
-    return [s];
-  }
-  let start = 0;
-  const tokens = [];
-  const width = s.length;
-  for (let index = 1; index < width; index++) {
-    const previousCode = s.codePointAt(index - 1);
-    const currentCode = s.codePointAt(index);
-    if (knownAcronyms.size > 0) {
-      for (const acronym of knownAcronyms) {
-        if (s.startsWith(acronym, start)) {
-          tokens.push(acronym);
-          start += acronym.length;
-          index = start - 1;
-          break;
-        }
-      }
-      if (index < start) {
-        continue;
-      }
-    }
-    const previousIsUpper = previousCode && previousCode < 128 && isUpper(previousCode);
-    const currentIsUpper = currentCode && currentCode < 128 && isUpper(currentCode);
-    const previousIsLower = previousCode && previousCode < 128 && isLower(previousCode);
-    const previousIsDigit = previousCode && previousCode < 128 && isDigit(previousCode);
-    const currentIsDigit = currentCode && currentCode < 128 && isDigit(currentCode);
-    if (previousIsLower && currentIsUpper) {
-      tokens.push(s.slice(start, index));
-      start = index;
-      continue;
-    }
-    if (previousIsDigit && !currentIsDigit || !previousIsDigit && currentIsDigit) {
-      tokens.push(s.slice(start, index));
-      start = index;
-      continue;
-    }
-    if (currentIsDigit && !previousIsDigit) {
-      let isNextUpper = false;
-      let isNextDigit = false;
-      if (index + 1 < width) {
-        const nextCode = s.codePointAt(index + 1);
-        isNextUpper = nextCode && nextCode < 128 && isUpper(nextCode);
-        isNextDigit = nextCode && nextCode < 128 && isDigit(nextCode);
-      }
-      if (!isNextDigit && isNextUpper) {
-        tokens.push(s.slice(start, index), s.slice(index, index + 1));
-        start = index + 1;
-        continue;
-      }
-    }
-    if (index + 1 < width) {
-      const nextCode = s.codePointAt(index + 1);
-      const nextIsLower = nextCode && nextCode < 128 && isLower(nextCode);
-      if (previousIsUpper && currentIsUpper && nextIsLower) {
-        const candidate = s.slice(start, index + 1);
-        if (!knownAcronyms.has(candidate)) {
-          tokens.push(s.slice(start, index));
-          start = index;
-        }
-      }
-    }
-  }
-  if (start < width) {
-    tokens.push(s.slice(start));
-  }
-  return tokens.filter((token) => token !== "");
-}, "splitCamelCaseFast");
-const splitCamelCaseLocale = /* @__PURE__ */ __name((s, locale, knownAcronyms) => {
-  if (s.length === 0) {
-    return [];
-  }
-  const isUpperCase = s === s.toLocaleUpperCase(locale);
-  if (locale.startsWith("de")) {
-    if (!isUpperCase && s.replaceAll("ß", "SS") === s.toLocaleUpperCase(locale)) {
-      return [s];
-    }
-    const chars2 = [...s];
-    const width_2 = chars2.length;
-    const result2 = [];
-    let currentSegment2 = chars2[0];
-    let previousIsUpper2 = chars2[0] === chars2[0].toLocaleUpperCase(locale);
-    let isInUpperSequence = previousIsUpper2;
-    let upperSequenceStart = previousIsUpper2 ? 0 : -1;
-    for (let index = 1; index < width_2; index++) {
-      const char = chars2[index];
-      const isUpperCaseChar = char === char.toLocaleUpperCase(locale);
-      if (isUpperCaseChar === previousIsUpper2) {
-        currentSegment2 += char;
-      } else if (isUpperCaseChar) {
-        if (currentSegment2 && currentSegment2.length > 0) {
-          result2.push(currentSegment2);
-          currentSegment2 = char;
-        }
-        isInUpperSequence = true;
-        upperSequenceStart = index;
-      } else {
-        if (isInUpperSequence && index - upperSequenceStart > 1) {
-          const lastUpperChar = chars2[index - 1];
-          const withoutLastUpper = currentSegment2.slice(0, -1);
-          if (withoutLastUpper && withoutLastUpper.length > 0) {
-            result2.push(withoutLastUpper);
-          }
-          currentSegment2 = lastUpperChar + char;
-        } else {
-          currentSegment2 += char;
-        }
-        isInUpperSequence = false;
-        upperSequenceStart = -1;
-      }
-      previousIsUpper2 = isUpperCaseChar;
-    }
-    if (currentSegment2 && currentSegment2.length > 0) {
-      result2.push(currentSegment2);
-    }
-    return result2;
-  }
-  if (locale.startsWith("uk") || locale.startsWith("ru") || locale.startsWith("bg") || locale.startsWith("sr") || locale.startsWith("mk") || locale.startsWith("be")) {
-    if (!RE_CYRILLIC.test(s) && !RE_LATIN.test(s)) {
-      return [s];
-    }
-    const chars2 = [...s];
-    const width_2 = chars2.length;
-    const result2 = [];
-    let currentSegment2 = chars2[0];
-    let previousType = RE_CYRILLIC.test(chars2[0]) ? 1 : RE_LATIN.test(chars2[0]) ? 2 : 0;
-    let previousIsUpper2 = chars2[0] === chars2[0].toLocaleUpperCase(locale);
-    for (let index = 1; index < width_2; index++) {
-      const char = chars2[index];
-      const currentType = RE_CYRILLIC.test(char) ? 1 : RE_LATIN.test(char) ? 2 : 0;
-      const isUpperCaseChar = char === char.toLocaleUpperCase(locale);
-      if (previousType !== currentType && (previousType === 1 || previousType === 2) && (currentType === 1 || currentType === 2) || currentType === previousType && !previousIsUpper2 && isUpperCaseChar) {
-        result2.push(currentSegment2);
-        currentSegment2 = char;
-      } else {
-        currentSegment2 += char;
-      }
-      previousType = currentType;
-      previousIsUpper2 = isUpperCaseChar;
-    }
-    if (currentSegment2 && currentSegment2.length > 0) {
-      result2.push(currentSegment2);
-    }
-    const finalResult = [];
-    for (let index = 0; index < result2.length; index++) {
-      if (index < result2.length - 1 && // eslint-disable-next-line security/detect-object-injection
-      result2[index].length === 1 && // eslint-disable-next-line security/detect-object-injection
-      RE_LATIN.test(result2[index]) && RE_CYRILLIC.test(result2[index + 1][0])) {
-        finalResult.push(result2[index] + result2[index + 1]);
-        index++;
-      } else {
-        finalResult.push(result2[index]);
-      }
-    }
-    return finalResult;
-  }
-  if (locale.startsWith("el")) {
-    if (!RE_GREEK.test(s) && !RE_LATIN.test(s)) {
-      return [s];
-    }
-    const parts = s.match(RE_GREEK_LATIN_SPLIT) ?? [s];
-    const result2 = [];
-    const width = parts.length;
-    if (width === 1) {
-      const part = parts[0];
-      if (!part || !RE_GREEK.test(part[0]) || part.length === 1) {
-        return [part || s];
-      }
-    }
-    for (const part of parts) {
-      if (!part) {
-        continue;
-      }
-      if (!RE_GREEK.test(part[0]) || part.length === 1) {
-        result2.push(part);
-        continue;
-      }
-      const partLength = part.length;
-      let word = part[0];
-      let previousIsUpper2 = part[0] === part[0].toLocaleUpperCase(locale);
-      for (let index = 1; index < partLength; index++) {
-        const char = part[index];
-        const isUpperCaseChar = char === char.toLocaleUpperCase(locale);
-        if (!previousIsUpper2 && isUpperCaseChar) {
-          result2.push(word);
-          word = char;
-        } else {
-          word += char;
-        }
-        previousIsUpper2 = isUpperCaseChar;
-      }
-      if (word) {
-        result2.push(word);
-      }
-    }
-    return result2;
-  }
-  if (locale.startsWith("ja") || locale.startsWith("ko")) {
-    const isJapanese = locale.startsWith("ja");
-    const scriptDetectors = isJapanese ? {
-      hiragana: /* @__PURE__ */ __name((char) => RE_HIRAGANA.test(char), "hiragana"),
-      kanji: /* @__PURE__ */ __name((char) => RE_KANJI.test(char), "kanji"),
-      katakana: /* @__PURE__ */ __name((char) => RE_KATAKANA.test(char), "katakana"),
-      latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin")
-    } : {
-      hangul: /* @__PURE__ */ __name((char) => RE_HANGUL.test(char), "hangul"),
-      latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin")
-    };
-    const particles = /* @__PURE__ */ new Set(["と", "に", "へ", "を", "は", "が", "の", "で", "や", "も"]);
-    if (isJapanese) {
-      const baseSegments = handleScriptTransitions(
-        s,
-        scriptDetectors,
-        false,
-        locale,
-        (previousType, currentType) => previousType === "hiragana" && currentType === "katakana" || // hiragana -> katakana
-        previousType === "katakana" && currentType === "hiragana" || // katakana -> hiragana
-        previousType === "hiragana" && currentType === "latin" || // hiragana -> latin
-        previousType === "katakana" && currentType === "latin" || // katakana -> latin
-        previousType === "kanji" && currentType === "latin" || // kanji -> latin
-        previousType === "latin" && (currentType === "hiragana" || currentType === "katakana" || currentType === "kanji")
-        // latin -> japanese
-      );
-      const result2 = [];
-      for (const segment of baseSegments) {
-        if (segment.length === 1 && particles.has(segment) && result2.length > 0) {
-          result2[result2.length - 1] += segment;
-        } else {
-          result2.push(segment);
-        }
-      }
-      return result2.length > 0 ? result2 : [s];
-    }
-    return handleScriptTransitions(
-      s,
-      scriptDetectors,
-      false,
-      locale,
-      (previousType, currentType) => previousType === "hangul" && currentType === "latin" || // hangul -> latin
-      previousType === "latin" && currentType === "hangul"
-      // latin -> hangul
-    );
-  }
-  if (locale.startsWith("sl")) {
-    const chars2 = [...s];
-    const width_2 = chars2.length;
-    const result2 = [];
-    let currentSegment2 = chars2[0];
-    let previousIsUpper2 = chars2[0] === chars2[0].toLocaleUpperCase(locale);
-    for (let index = 1; index < width_2; index++) {
-      const char = chars2[index];
-      const isUpperCaseChar = char === char.toLocaleUpperCase(locale);
-      const isSpecialChar = /[ČŠŽĐ]/i.test(char);
-      const nextIsUpper = index < width_2 - 1 && chars2[index + 1] === chars2[index + 1].toLocaleUpperCase(locale);
-      if (!previousIsUpper2 && isUpperCaseChar || isSpecialChar && nextIsUpper) {
-        result2.push(currentSegment2);
-        currentSegment2 = char;
-        if (isSpecialChar && nextIsUpper) {
-          result2.push(currentSegment2);
-          currentSegment2 = "";
-        }
-      } else {
-        currentSegment2 += char;
-      }
-      previousIsUpper2 = isUpperCaseChar;
-    }
-    if (currentSegment2 && currentSegment2.length > 0) {
-      result2.push(currentSegment2);
-    }
-    return result2;
-  }
-  if (locale.startsWith("zh")) {
-    return handleScriptTransitions(
-      s,
-      {
-        han: /* @__PURE__ */ __name((char) => RE_KANJI.test(char), "han"),
-        latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin")
-      },
-      false,
-      locale
-    );
-  }
-  if (["ar", "fa", "he", "ur"].includes(locale.split("-")[0])) {
-    const isRtlChar = /* @__PURE__ */ __name((ch) => RE_HEBREW.test(ch) || RE_ARABIC.test(ch), "isRtlChar");
-    return handleScriptTransitions(
-      s,
-      {
-        latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin"),
-        rtl: /* @__PURE__ */ __name((char) => isRtlChar(char), "rtl")
-      },
-      false,
-      locale
-    );
-  }
-  if ([
-    "am",
-    // Amharic
-    "bn",
-    // Bengali
-    "gu",
-    // Gujarati
-    "hi",
-    // Hindi
-    "km",
-    // Khmer
-    "kn",
-    // Kannada
-    "lo",
-    // Lao
-    "ml",
-    // Malayalam
-    "mr",
-    // Marathi
-    "ne",
-    // Nepali
-    "or",
-    // Oriya
-    "pa",
-    // Punjabi
-    "si",
-    // Sinhala
-    "ta",
-    // Tamil
-    "te",
-    // Telugu
-    "th"
-    // Thai
-  ].includes(locale.split("-")[0])) {
-    const isIndicChar = /* @__PURE__ */ __name((ch) => RE_DEVANAGARI.test(ch) || RE_BENGALI.test(ch) || RE_GUJARATI.test(ch) || RE_GURMUKHI.test(ch) || RE_KANNADA.test(ch) || RE_TAMIL.test(ch) || RE_TELUGU.test(ch) || RE_MALAYALAM.test(ch) || RE_SINHALA.test(ch) || RE_THAI.test(ch) || RE_LAO.test(ch) || RE_TIBETAN.test(ch) || RE_MYANMAR.test(ch) || RE_ETHIOPIC.test(ch) || RE_KHMER.test(ch) || RE_ORIYA.test(ch), "isIndicChar");
-    return handleScriptTransitions(
-      s,
-      {
-        indic: /* @__PURE__ */ __name((char) => isIndicChar(char), "indic"),
-        latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin")
-      },
-      false,
-      locale
-    );
-  }
-  if (["be", "bg", "ru", "sr", "uk"].includes(locale)) {
-    return handleScriptTransitions(
-      s,
-      {
-        cyrillic: /* @__PURE__ */ __name((char) => RE_CYRILLIC.test(char), "cyrillic"),
-        latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin")
-      },
-      true,
-      // Enable case-sensitive splitting
-      locale
-    );
-  }
-  if (["ar", "fa", "he"].includes(locale)) {
-    return handleScriptTransitions(
-      s,
-      {
-        latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin"),
-        rtl: /* @__PURE__ */ __name((char) => RE_HEBREW.test(char) || RE_ARABIC.test(char), "rtl")
-      },
-      false,
-      locale
-    );
-  }
-  if (locale.startsWith("ko")) {
-    return handleScriptTransitions(
-      s,
-      {
-        hangul: /* @__PURE__ */ __name((char) => RE_HANGUL.test(char), "hangul"),
-        latin: /* @__PURE__ */ __name((char) => RE_LATIN.test(char), "latin")
-      },
-      false,
-      locale
-    );
-  }
-  if (locale.startsWith("uz")) {
-    if (!RE_CYRILLIC.test(s) && !RE_LATIN.test(s)) {
-      return [s];
-    }
-    const chars2 = [...s];
-    const width_2 = chars2.length;
-    const result2 = [];
-    let currentSegment2 = chars2[0];
-    let previousIsUpper2 = chars2[0] === chars2[0].toLocaleUpperCase(locale);
-    for (let index = 1; index < width_2; index++) {
-      const char = chars2[index];
-      const isUpperCaseChar = char === char.toLocaleUpperCase(locale);
-      if (RE_UZBEK_LATIN_MODIFIER.test(char) || RE_UZBEK_LATIN_MODIFIER.test(chars2[index - 1])) {
-        currentSegment2 += char;
-        continue;
-      }
-      if (!previousIsUpper2 && isUpperCaseChar) {
-        result2.push(currentSegment2);
-        currentSegment2 = char;
-      } else {
-        currentSegment2 += char;
-      }
-      previousIsUpper2 = isUpperCaseChar;
-    }
-    if (currentSegment2 && currentSegment2.length > 0) {
-      result2.push(currentSegment2);
-    }
-    return result2;
-  }
-  const chars = [...s];
-  const width_ = chars.length;
-  const result = [];
-  let currentSegment = chars[0];
-  let previousIsUpper = chars[0] === chars[0].toLocaleUpperCase(locale);
-  for (const acronym of knownAcronyms) {
-    if (s.startsWith(acronym)) {
-      result.push(acronym);
-      currentSegment = chars[acronym.length];
-      previousIsUpper = currentSegment === currentSegment.toLocaleUpperCase(locale);
-      break;
-    }
-  }
-  for (let index = 1; index < width_; index++) {
-    const char = chars[index];
-    const isUpperCaseChar = char === char.toLocaleUpperCase(locale);
-    let isAcronym = false;
-    for (const acronym of knownAcronyms) {
-      if (s.startsWith(acronym, index)) {
-        result.push(currentSegment, acronym);
-        index += acronym.length - 1;
-        currentSegment = "";
-        isAcronym = true;
-        break;
-      }
-    }
-    if (isAcronym) {
-      continue;
-    }
-    if (!previousIsUpper && isUpperCaseChar) {
-      result.push(currentSegment);
-      currentSegment = char;
-    } else {
-      currentSegment += char;
-    }
-    previousIsUpper = isUpperCaseChar;
-  }
-  if (currentSegment) {
-    result.push(currentSegment);
-  }
-  return result;
-}, "splitCamelCaseLocale");
-const processTextWithAnsiEmoji = /* @__PURE__ */ __name((text, locale, knownAcronyms) => {
-  const result = [];
-  const segments = RE_FAST_ANSI.test(text) ? text.split(RE_FAST_ANSI).filter(Boolean) : [text];
-  for (const seg of segments) {
-    if (RE_FAST_ANSI.test(seg)) {
-      result.push(seg);
-    } else {
-      const subs = RE_EMOJI.test(seg) ? splitByEmoji(seg).filter(Boolean) : [seg];
-      for (const sub of subs) {
-        if (RE_EMOJI.test(sub)) {
-          result.push(sub);
-        } else {
-          if (locale) {
-            const normalizedLocale = locale.toLowerCase().split("-")[0];
-            result.push(...splitCamelCaseLocale(sub, normalizedLocale, knownAcronyms));
-          } else {
-            result.push(...splitCamelCaseFast(sub, knownAcronyms));
-          }
-        }
-      }
-    }
-  }
-  return result;
-}, "processTextWithAnsiEmoji");
-const splitByCase = /* @__PURE__ */ __name((input, options = {}) => {
-  if (!input || typeof input !== "string") {
-    return [];
-  }
-  const {
-    handleAnsi = false,
-    handleEmoji = false,
-    knownAcronyms = [],
-    locale,
-    normalize = false,
-    separators,
-    stripAnsi: stripAnsiOption = false,
-    stripEmoji: stripEmojiOption = false
-  } = options;
-  const acronymSet = new Set([...knownAcronyms].sort((a, b) => b.length - a.length));
-  let cleanedInput = input;
-  if (stripAnsiOption) {
-    cleanedInput = stripVTControlCharacters(cleanedInput);
-  }
-  if (stripEmojiOption) {
-    cleanedInput = stripEmoji(cleanedInput);
-  }
-  const separatorRegex = Array.isArray(separators) ? getSeparatorsRegex(separators) : separators instanceof RegExp ? separators : RE_SEPARATORS;
-  const parts = cleanedInput.split(separatorRegex).filter(Boolean);
-  let tokens = [];
-  for (const part of parts) {
-    if (handleAnsi || handleEmoji) {
-      tokens.push(...processTextWithAnsiEmoji(part, locale, acronymSet));
-    } else if (locale) {
-      tokens.push(...splitCamelCaseLocale(part, locale, acronymSet));
-    } else {
-      tokens.push(...splitCamelCaseFast(part, acronymSet));
-    }
-  }
-  if (normalize) {
-    tokens = tokens.map((token) => {
-      if (acronymSet.has(token)) {
-        return token;
-      }
-      if (locale && token === token.toLocaleUpperCase(locale)) {
-        return token[0] + token.slice(1).toLocaleLowerCase(locale);
-      }
-      if (token.toUpperCase() === token && !acronymSet.has(token)) {
-        return token.slice(0, 1) + token.slice(1).toLowerCase();
-      }
-      return token;
-    });
-  }
-  return tokens;
-}, "splitByCase");
-
-export { splitByCase };
+var D=Object.defineProperty;var m=(t,s)=>D(t,"name",{value:s,configurable:!0});import{stripVTControlCharacters as z}from"node:util";import{j as I,s as F,k as J,R as j,l as k,m as C,n as W,o as Y,p as $,q as N,r as V,t as B,u as O,v as S,w as q,x as Z,y as Q,z as X,A as tt,B as et,C as st,D as at,E as nt,F as rt,G as lt,H as ot,I as it,J as ct,K as pt,L as ft,M as x}from"../packem_shared/constants-Cd17VNEv.mjs";import ht from"../packem_shared/LRUCache-Bjo6gsbC.mjs";var ut=Object.defineProperty,gt=m((t,s)=>ut(t,"name",{value:s,configurable:!0}),"g");const T=new ht(1e3),At=gt(t=>{const s=t.join("");if(T.has(s))return T.get(s);const p=t.map(R=>R.replaceAll(/[.*+?^${}()|[\]\\]/g,"\\$&")).join("|"),u=new RegExp(p,"g");return T.set(s,u),u},"getSeparatorsRegex");var Et=Object.defineProperty,Rt=m((t,s)=>Et(t,"name",{value:s,configurable:!0}),"t");const Lt=Rt(t=>{const s=[];let p=0,u;for(I.lastIndex=0;(u=I.exec(t))!==null;)u.index>p&&s.push(t.slice(p,u.index)),s.push(u[0]),p=I.lastIndex;return p<t.length&&s.push(t.slice(p)),s.filter(Boolean)},"splitByEmoji");var Ct=Object.defineProperty,g=m((t,s)=>Ct(t,"name",{value:s,configurable:!0}),"u");const G=new Uint8Array(128),K=new Uint8Array(128),M=new Uint8Array(128);for(let t=0;t<128;t++)G[t]=t>=65&&t<=90?1:0,K[t]=t>=97&&t<=122?1:0,M[t]=t>=48&&t<=57?1:0;const y=g(t=>G[t],"isUpper"),v=g(t=>K[t],"isLower"),w=g(t=>M[t],"isDigit"),_=g((t,s,p,u,R)=>{if(t.length===0)return[];let c=!1;for(const r of Object.values(s))if(r(t[0])){c=!0;break}if(!c&&!p)return[t];const A=[...t],h=[];let L=A[0],e="other";for(const[r,a]of Object.entries(s))if(a(A[0])){e=r;break}let l=p&&u?A[0]===A[0].toLocaleUpperCase(u):!1;for(let r=1;r<A.length;r++){const a=A[r];let o="other";for(const[f,E]of Object.entries(s))if(E(a)){o=f;break}const i=p&&u?a===a.toLocaleUpperCase(u):!1;let n=!1;R?n=R(e,o,l,i,a,r,A):(e!==o&&e!=="other"&&o!=="other"&&(n=!0),p&&o!=="other"&&!l&&i&&(n=!0)),n?(h.push(L),L=a):L+=a,e=o,p&&(l=i)}return L&&L.length>0&&h.push(L),h.length>0?h:[t]},"handleScriptTransitions"),H=g((t,s=new Set)=>{if(t.length===0)return[];if(t.toUpperCase()===t)return[t];let p=0;const u=[],R=t.length;for(let c=1;c<R;c++){const A=t.codePointAt(c-1),h=t.codePointAt(c);if(s.size>0){for(const o of s)if(t.startsWith(o,p)){u.push(o),p+=o.length,c=p-1;break}if(c<p)continue}const L=A&&A<128&&y(A),e=h&&h<128&&y(h),l=A&&A<128&&v(A),r=A&&A<128&&w(A),a=h&&h<128&&w(h);if(l&&e){u.push(t.slice(p,c)),p=c;continue}if(r&&!a||!r&&a){u.push(t.slice(p,c)),p=c;continue}if(a&&!r){let o=!1,i=!1;if(c+1<R){const n=t.codePointAt(c+1);o=n&&n<128&&y(n),i=n&&n<128&&w(n)}if(!i&&o){u.push(t.slice(p,c),t.slice(c,c+1)),p=c+1;continue}}if(c+1<R){const o=t.codePointAt(c+1),i=o&&o<128&&v(o);if(L&&e&&i){const n=t.slice(p,c+1);s.has(n)||(u.push(t.slice(p,c)),p=c)}}}return p<R&&u.push(t.slice(p)),u.filter(c=>c!=="")},"splitCamelCaseFast"),P=g((t,s,p)=>{if(t.length===0)return[];const u=t===t.toLocaleUpperCase(s);if(s.startsWith("de")){if(!u&&t.replaceAll("ß","SS")===t.toLocaleUpperCase(s))return[t];const e=[...t],l=e.length,r=[];let a=e[0],o=e[0]===e[0].toLocaleUpperCase(s),i=o,n=o?0:-1;for(let f=1;f<l;f++){const E=e[f],U=E===E.toLocaleUpperCase(s);if(U===o)a+=E;else if(U)a&&a.length>0&&(r.push(a),a=E),i=!0,n=f;else{if(i&&f-n>1){const d=e[f-1],b=a.slice(0,-1);b&&b.length>0&&r.push(b),a=d+E}else a+=E;i=!1,n=-1}o=U}return a&&a.length>0&&r.push(a),r}if(s.startsWith("uk")||s.startsWith("ru")||s.startsWith("bg")||s.startsWith("sr")||s.startsWith("mk")||s.startsWith("be")){if(!k.test(t)&&!C.test(t))return[t];const e=[...t],l=e.length,r=[];let a=e[0],o=k.test(e[0])?1:C.test(e[0])?2:0,i=e[0]===e[0].toLocaleUpperCase(s);for(let f=1;f<l;f++){const E=e[f],U=k.test(E)?1:C.test(E)?2:0,d=E===E.toLocaleUpperCase(s);o!==U&&(o===1||o===2)&&(U===1||U===2)||U===o&&!i&&d?(r.push(a),a=E):a+=E,o=U,i=d}a&&a.length>0&&r.push(a);const n=[];for(let f=0;f<r.length;f++)f<r.length-1&&r[f].length===1&&C.test(r[f])&&k.test(r[f+1][0])?(n.push(r[f]+r[f+1]),f++):n.push(r[f]);return n}if(s.startsWith("el")){if(!W.test(t)&&!C.test(t))return[t];const e=t.match(Y)??[t],l=[];if(e.length===1){const r=e[0];if(!r||!W.test(r[0])||r.length===1)return[r||t]}for(const r of e){if(!r)continue;if(!W.test(r[0])||r.length===1){l.push(r);continue}const a=r.length;let o=r[0],i=r[0]===r[0].toLocaleUpperCase(s);for(let n=1;n<a;n++){const f=r[n],E=f===f.toLocaleUpperCase(s);!i&&E?(l.push(o),o=f):o+=f,i=E}o&&l.push(o)}return l}if(s.startsWith("ja")||s.startsWith("ko")){const e=s.startsWith("ja"),l=e?{hiragana:g(a=>V.test(a),"hiragana"),kanji:g(a=>N.test(a),"kanji"),katakana:g(a=>$.test(a),"katakana"),latin:g(a=>C.test(a),"latin")}:{hangul:g(a=>B.test(a),"hangul"),latin:g(a=>C.test(a),"latin")},r=new Set(["と","に","へ","を","は","が","の","で","や","も"]);if(e){const a=_(t,l,!1,s,(i,n)=>i==="hiragana"&&n==="katakana"||i==="katakana"&&n==="hiragana"||i==="hiragana"&&n==="latin"||i==="katakana"&&n==="latin"||i==="kanji"&&n==="latin"||i==="latin"&&(n==="hiragana"||n==="katakana"||n==="kanji")),o=[];for(const i of a)i.length===1&&r.has(i)&&o.length>0?o[o.length-1]+=i:o.push(i);return o.length>0?o:[t]}return _(t,l,!1,s,(a,o)=>a==="hangul"&&o==="latin"||a==="latin"&&o==="hangul")}if(s.startsWith("sl")){const e=[...t],l=e.length,r=[];let a=e[0],o=e[0]===e[0].toLocaleUpperCase(s);for(let i=1;i<l;i++){const n=e[i],f=n===n.toLocaleUpperCase(s),E=/[ČŠŽĐ]/i.test(n),U=i<l-1&&e[i+1]===e[i+1].toLocaleUpperCase(s);!o&&f||E&&U?(r.push(a),a=n,E&&U&&(r.push(a),a="")):a+=n,o=f}return a&&a.length>0&&r.push(a),r}if(s.startsWith("zh"))return _(t,{han:g(e=>N.test(e),"han"),latin:g(e=>C.test(e),"latin")},!1,s);if(["ar","fa","he","ur"].includes(s.split("-")[0])){const e=g(l=>O.test(l)||S.test(l),"isRtlChar");return _(t,{latin:g(l=>C.test(l),"latin"),rtl:g(l=>e(l),"rtl")},!1,s)}if(["am","bn","gu","hi","km","kn","lo","ml","mr","ne","or","pa","si","ta","te","th"].includes(s.split("-")[0])){const e=g(l=>q.test(l)||Z.test(l)||Q.test(l)||X.test(l)||tt.test(l)||et.test(l)||st.test(l)||at.test(l)||nt.test(l)||rt.test(l)||lt.test(l)||ot.test(l)||it.test(l)||ct.test(l)||pt.test(l)||ft.test(l),"isIndicChar");return _(t,{indic:g(l=>e(l),"indic"),latin:g(l=>C.test(l),"latin")},!1,s)}if(["be","bg","ru","sr","uk"].includes(s))return _(t,{cyrillic:g(e=>k.test(e),"cyrillic"),latin:g(e=>C.test(e),"latin")},!0,s);if(["ar","fa","he"].includes(s))return _(t,{latin:g(e=>C.test(e),"latin"),rtl:g(e=>O.test(e)||S.test(e),"rtl")},!1,s);if(s.startsWith("ko"))return _(t,{hangul:g(e=>B.test(e),"hangul"),latin:g(e=>C.test(e),"latin")},!1,s);if(s.startsWith("uz")){if(!k.test(t)&&!C.test(t))return[t];const e=[...t],l=e.length,r=[];let a=e[0],o=e[0]===e[0].toLocaleUpperCase(s);for(let i=1;i<l;i++){const n=e[i],f=n===n.toLocaleUpperCase(s);if(x.test(n)||x.test(e[i-1])){a+=n;continue}!o&&f?(r.push(a),a=n):a+=n,o=f}return a&&a.length>0&&r.push(a),r}const R=[...t],c=R.length,A=[];let h=R[0],L=R[0]===R[0].toLocaleUpperCase(s);for(const e of p)if(t.startsWith(e)){A.push(e),h=R[e.length],L=h===h.toLocaleUpperCase(s);break}for(let e=1;e<c;e++){const l=R[e],r=l===l.toLocaleUpperCase(s);let a=!1;for(const o of p)if(t.startsWith(o,e)){A.push(h,o),e+=o.length-1,h="",a=!0;break}a||(!L&&r?(A.push(h),h=l):h+=l,L=r)}return h&&A.push(h),A},"splitCamelCaseLocale"),Ut=g((t,s,p)=>{const u=[],R=j.test(t)?t.split(j).filter(Boolean):[t];for(const c of R)if(j.test(c))u.push(c);else{const A=I.test(c)?Lt(c).filter(Boolean):[c];for(const h of A)if(I.test(h))u.push(h);else if(s){const L=s.toLowerCase().split("-")[0];u.push(...P(h,L,p))}else u.push(...H(h,p))}return u},"processTextWithAnsiEmoji"),mt=g((t,s={})=>{if(!t||typeof t!="string")return[];const{handleAnsi:p=!1,handleEmoji:u=!1,knownAcronyms:R=[],locale:c,normalize:A=!1,separators:h,stripAnsi:L=!1,stripEmoji:e=!1}=s,l=new Set([...R].sort((n,f)=>f.length-n.length));let r=t;L&&(r=z(r)),e&&(r=F(r));const a=Array.isArray(h)?At(h):h instanceof RegExp?h:J,o=r.split(a).filter(Boolean);let i=[];for(const n of o)p||u?i.push(...Ut(n,c,l)):c?i.push(...P(n,c,l)):i.push(...H(n,l));return A&&(i=i.map(n=>l.has(n)?n:c&&n===n.toLocaleUpperCase(c)?n[0]+n.slice(1).toLocaleLowerCase(c):n.toUpperCase()===n&&!l.has(n)?n.slice(0,1)+n.slice(1).toLowerCase():n)),i},"splitByCase");export{mt as splitByCase};