unicode-input-toolconverter 0.2.0

package/browser_action/unicode/hangul.js

@@ -0,0 +1,253 @@
+/* eslint-disable unicorn/prefer-string-slice -- Easier */
+// Function can also be used standalone
+/**
+* @namespace This contains methods for translating Korean Hangul/Jamo,
+*   since these are obtained programmatically and not through the Unicode (or
+*   Unihan) database
+*/
+
+// Private static
+const JAMO_L_TABLE = [
+    'G', 'GG', 'N', 'D', 'DD', 'R', 'M', 'B', 'BB',
+    'S', 'SS', '', 'J', 'JJ', 'C', 'K', 'T', 'P', 'H'
+  ],
+  JAMO_V_TABLE = [
+    'A', 'AE', 'YA', 'YAE', 'EO', 'E', 'YEO', 'YE', 'O',
+    'WA', 'WAE', 'OE', 'YO', 'U', 'WEO', 'WE', 'WI',
+    'YU', 'EU', 'YI', 'I'
+  ],
+  JAMO_T_TABLE = [
+    '', 'G', 'GG', 'GS', 'N', 'NJ', 'NH', 'D', 'L', 'LG', 'LM',
+    'LB', 'LS', 'LT', 'LP', 'LH', 'M', 'B', 'BS',
+    'S', 'SS', 'NG', 'J', 'C', 'K', 'T', 'P', 'H'
+  ];
+const sBase = 0xAC00,
+  lBase = 0x1100,
+  vBase = 0x1161,
+  tBase = 0x11A7,
+  sCount = 11172,
+  lCount = 19, // Not in use for decomposition
+  vCount = 21,
+  tCount = 28,
+  nCount = vCount * tCount;
+
+/**
+ * Break up a Hangul syllable into its Jamo components.
+ * Currently unused.
+ * @param {Integer} syllableCode Decimal code point for Hangul syllable
+ *   to decompose
+ * @returns {Integer[]|string} An array of the numeric value of each
+ *   component or string if unchanged
+ */
+function decomposeHangul (syllableCode) {
+  const sIndex = syllableCode - sBase;
+  if (sIndex < 0 || sIndex >= sCount) {
+    // Return as single-item array instead or change "result" to String?
+    return String.fromCodePoint(syllableCode);
+  }
+  const result = [];
+  const l = lBase + Math.floor(sIndex / nCount);
+  const v = vBase + Math.floor((sIndex % nCount) / tCount);
+  const t = tBase + (sIndex % tCount);
+  result.push(String.fromCodePoint(l), String.fromCodePoint(v));
+  if (t !== tBase) {
+    result.push(String.fromCodePoint(t));
+  }
+  return result;
+}
+/**
+ *
+ * @param {string[]} source
+ * @returns {string[]}
+ */
+function composeHangul (source) {
+  const len = source.length;
+  if (len === 0) {
+    return '';
+  }
+  const result = [];
+  const chars = [...source];
+
+  let last = chars[0];
+
+  // copy first char
+  result.push(last);
+
+  chars.slice(1).forEach((ch) => {
+    // 1. check to see if two current characters are L and V
+    const lIndex = last.codePointAt() - lBase;
+    if (lIndex > 0 && lIndex < lCount) {
+      const vIndex = ch.codePointAt() - vBase;
+      if (vIndex > 0 && vIndex < vCount) {
+        // make syllable of form LV
+        last = String.fromCodePoint(
+          sBase + (((lIndex * vCount) + vIndex) * tCount)
+        );
+        result[result.length - 1] = last; // reset last
+        return; // discard ch
+      }
+    }
+
+    // 2. check to see if two current characters are LV and T
+    const sIndex = last.codePointAt() - sBase;
+    if (sIndex > 0 && sIndex < sCount && (sIndex % tCount) === 0) {
+      const tIndex = ch.codePointAt() - tBase;
+      if (tIndex >= 0 && tIndex < tCount) {
+        // make syllable of form LVT
+        last = String.fromCodePoint(last.codePointAt() + tIndex);
+        result[result.length - 1] = last; // reset last
+        return; // discard ch
+      }
+    }
+    // if neither case was true, just add the character
+    last = ch;
+    result.push(ch);
+  });
+  return result;
+}
+
+/**
+ * Gets a Unicode character for the passed-in Hangul syllable name.
+ * @param {string} name The name of the syllable to find
+ * @author Brett Zamir (others adapted directly from Unicode)
+ * @returns {string|boolean} False if invalid, or otherwise the Hangul
+ *   character represented by the supplied name
+ */
+function getHangulFromName (name) {
+  // Turn indices into individual Jamo characters
+  let t, lIndex, vIndex, tIndex;
+  let ptr = 1;
+
+  // L (can be 1-2 in name length)
+  if (name.charAt(0) === name.charAt(1)) { // All two-letter names are doubles
+    lIndex = JAMO_L_TABLE.indexOf(name.slice(0, 2));
+    ptr++;
+  } else {
+    lIndex = JAMO_L_TABLE.indexOf(name.slice(0, 1));
+  }
+
+  // V (can be 1-3 in name length)
+  vIndex = JAMO_V_TABLE.indexOf(name.substr(ptr, 3));
+  if (vIndex !== -1) {
+    ptr += 3;
+  } else {
+    vIndex = JAMO_V_TABLE.indexOf(name.substr(ptr, 2));
+    if (vIndex !== -1) {
+      ptr += 2;
+    } else {
+      vIndex = JAMO_V_TABLE.indexOf(name.substr(ptr, 1));
+      ptr++;
+    }
+  }
+
+  // T (can be 1-2 in name length)
+  tIndex = JAMO_T_TABLE.indexOf(name.substr(ptr, 2).padStart(2, '0'));
+  if (tIndex !== -1) {
+    ptr += 2;
+  } else {
+    tIndex = JAMO_T_TABLE.indexOf(name.substr(ptr, 1));
+    ptr++;
+  }
+  if (
+    lIndex === -1 || vIndex === -1 ||
+    (tIndex && ptr < name.length)
+  ) { // If an invalid Hangul syllable name was passed in
+    return false;
+  }
+
+  const l = getJamoForIndex(lIndex, 'l');
+  const v = getJamoForIndex(vIndex, 'v');
+
+  // May only be LV
+  t = '';
+  if (tIndex) {
+    t = getJamoForIndex(tIndex, 't');
+  }
+
+  // Join Jamo characters together
+  const jamo = l + v + t;
+  // Convert Jamo into composite Hangul syllable
+  return composeHangul(jamo).join('');
+}
+
+/**
+ * Utility (could be adapted to accept the letter(s)).
+ * @param {string} index
+ * @param {'l'|'v'|'t'} type
+ * @throws {TypeError}
+ * @returns {string}
+ */
+function getJamoForIndex (index, type) {
+  switch (type) {
+  case 'l':
+    return String.fromCodePoint(lBase + index);
+  case 'v':
+    return String.fromCodePoint(vBase + index);
+  case 't':
+    return String.fromCodePoint(tBase + index);
+  default:
+    throw new TypeError('Unexpected type passed to getJamoCodePointForName');
+  }
+}
+
+/**
+ * @param {PositiveInteger} syllableCode
+ * @throws {Error}
+ * @returns {string}
+ */
+function getHangulName (syllableCode) {
+  // Adapted from Hangul Character Names:
+  //  https://unicode.org/reports/tr15/#Hangul
+
+  // Following numbered items, with minor changes are from
+  //  https://unicode.org/versions/Unicode5.0.0/ch03.pdf
+  //  now:
+  //  https://unicode.org/versions/Unicode13.0.0/ch03.pdf
+  // 1. Compute the index of the syllable:
+  // SIndex = S - SBase
+  const sIndex = syllableCode - sBase;
+  // 2. If SIndex is in the range (0 ? SIndex < SCount), then compute the
+  //     components as follows:
+  // The operators /” and  “%” are as defined in Table A-3 in Appendix A,
+  //    Notational Conventions.
+  if (sIndex < 0 || sIndex >= sCount) {
+    throw new Error('Not a hangul syllable ' + syllableCode);
+  }
+  /*
+  const l = lBase + Math.floor(sIndex / nCount);
+  const v = vBase + Math.floor((sIndex % nCount) / tCount);
+  const t = tBase + sIndex % tCount;
+  */
+  const l = Math.floor(sIndex / nCount);
+  const v = Math.floor((sIndex % nCount) / tCount);
+  const t = sIndex % tCount;
+  return JAMO_L_TABLE[l] + JAMO_V_TABLE[v] + JAMO_T_TABLE[t];
+
+  // 3. If T = TBase, then there is no trailing character, so replace S by the
+  //     sequence L V. Otherwise, there is a trailing character, so replace S
+  //     by the sequence L V T.
+  // Example. Compute the components:
+  // L = LBase + 17
+  // V = VBase + 16
+  // T = TBase + 15
+  // and replace the syllable by the sequence of components:
+  // 0xD4DB => 0x1111, 0x1171, 0x11B6
+  /*
+  const arr = [l, v];
+  if (t !== tBase) {
+    arr.push(t);
+  }
+  // The character names for Hangul syllables are derived from the
+  //   decomposition by starting with the string hangul syllable, and
+  //   appending the short name of each decomposition component in order.
+  for (let c = 0; c < arr.length; c++) {
+    const jamoComponent = getJamo(arr[c]);
+    cjkText += jamoComponent;
+  }
+  */
+}
+
+export {
+  decomposeHangul, composeHangul, getHangulFromName,
+  getJamoForIndex, getHangulName
+};

package/browser_action/unicode/lastScriptNames.json

@@ -0,0 +1,5 @@
+
+{
+  "$comment": "Do not edit this file; this is an auto-generated file used to track script names, some of which may end up needing to be deleted from locale files if no longer in use",
+  "lastScriptNames": ["European_Scripts","Armenian","Armenian_Ligatures","Carian","Caucasian_Albanian","Cypriot_Syllabary","Cypro_Minoan","Cyrillic","Cyrillic_Supplement","Cyrillic_Extended_A","Cyrillic_Extended_B","Cyrillic_Extended_C","Cyrillic_Extended_D","Elbasan","Georgian","Georgian_Extended","Georgian_Supplement","Glagolitic","Glagolitic_Supplement","Gothic","Greek","Greek_Extended","Ancient_Greek_Numbers","Latin","Basic_Latin","Latin_1_Supplement","Latin_Extended_A","Latin_Extended_B","Latin_Extended_C","Latin_Extended_D","Latin_Extended_E","Latin_Extended_F","Latin_Extended_G","Latin_Extended_Additional","Latin_Ligatures","Fullwidth_Latin_Letters","IPA_Extensions","Phonetic_Extensions","Phonetic_Extensions_Supplement","Linear_A","Linear_B","Linear_B_Syllabary","Linear_B_Ideograms","Aegean_Numbers","Lycian","Lydian","Ogham","Old_Hungarian","Old_Italic","Old_Permic","Phaistos_Disc","Runic","Shavian","Vithkuqi","Modifier_Letters","Modifier_Tone_Letters","Spacing_Modifier_Letters","Superscripts_and_Subscripts","Combining_Marks","Combining_Diacritical_Marks","Combining_Diacritical_Marks_Extended","Combining_Diacritical_Marks_Supplement","Combining_Diacritical_Marks_for_Symbols","Combining_Half_Marks","Miscellaneous","Alphabetic_Presentation_Forms","ASCII_Characters","Halfwidth_and_Fullwidth_Forms","African_Scripts","Adlam","Bamum","Bamum_Supplement","Bassa_Vah","Coptic","Coptic_in_Greek_block","Coptic_Epact_Numbers","Egyptian_Hieroglyphs","Egyptian_Hieroglyph_Format_Controls","Ethiopic","Ethiopic_Supplement","Ethiopic_Extended","Ethiopic_Extended_A","Ethiopic_Extended_B","Medefaidrin","Mende_Kikakui","Meroitic","Meroitic_Cursive","Meroitic_Hieroglyphs","N_Ko","Osmanya","Tifinagh","Vai","Middle_Eastern_Scripts","Anatolian_Hieroglyphs","Arabic","Arabic_Supplement","Arabic_Extended_A","Arabic_Extended_B","Arabic_Extended_C","Arabic_Presentation_Forms_A","Arabic_Presentation_Forms_B","Aramaic__Imperial","Avestan","Chorasmian","Cuneiform","Cuneiform_Numbers_and_Punctuation","Early_Dynastic_Cuneiform","Old_Persian","Ugaritic","Elymaic","Hatran","Hebrew","Hebrew_Presentation_Forms","Mandaic","Nabataean","Old_North_Arabian","Old_South_Arabian","Pahlavi__Inscriptional","Pahlavi__Psalter","Palmyrene","Parthian__Inscriptional","Phoenician","Samaritan","Syriac","Syriac_Supplement","Yezidi","Central_Asian_Scripts","Manichaean","Marchen","Mongolian","Mongolian_Supplement","Old_Sogdian","Old_Turkic","Old_Uyghur","Phags_Pa","Sogdian","Soyombo","Tibetan","Zanabazar_Square","South_Asian_Scripts","Ahom","Bengali_and_Assamese","Bhaiksuki","Brahmi","Chakma","Devanagari","Devanagari_Extended","Devanagari_Extended_A","Dives_Akuru","Dogra","Grantha","Gujarati","Gunjala_Gondi","Gurmukhi","Kaithi","Kannada","Kharoshthi","Khojki","Khudawadi","Lepcha","Limbu","Mahajani","Malayalam","Masaram_Gondi","Meetei_Mayek","Meetei_Mayek_Extensions","Modi","Mro","Multani","Nag_Mundari","Nandinagari","Newa","Ol_Chiki","Oriya","Saurashtra","Sharada","Siddham","Sinhala","Sinhala_Archaic_Numbers","Sora_Sompeng","Syloti_Nagri","Takri","Tamil","Tamil_Supplement","Telugu","Thaana","Tirhuta","Toto","Vedic_Extensions","Wancho","Warang_Citi","Southeast_Asian_Scripts","Cham","Hanifi_Rohingya","Kayah_Li","Khmer","Khmer_Symbols","Lao","Myanmar","Myanmar_Extended_A","Myanmar_Extended_B","New_Tai_Lue","Nyiakeng_Puachue_Hmong","Pahawh_Hmong","Pau_Cin_Hau","Tai_Le","Tai_Tham","Tai_Viet","Tangsa","Thai","Indonesian___Philippine_Scripts","Balinese","Batak","Buginese","Buhid","Hanunoo","Javanese","Kawi","Makasar","Rejang","Sundanese","Sundanese_Supplement","Tagalog","Tagbanwa","East_Asian_Scripts","Bopomofo","Bopomofo_Extended","CJK_Unified_Ideographs__Han_","CJK_Extension_A","CJK_Extension_B","CJK_Extension_C","CJK_Extension_D","CJK_Extension_E","CJK_Extension_F","CJK_Extension_G","CJK_Extension_H","CJK_Extension_I","_see_also_Unihan_Database_","CJK_Compatibility_Ideographs","CJK_Compatibility_Ideographs_Supplement","CJK_Radicals___Kangxi_Radicals","CJK_Radicals_Supplement","CJK_Strokes","Ideographic_Description_Characters","Hangul_Jamo","Hangul_Jamo_Extended_A","Hangul_Jamo_Extended_B","Hangul_Compatibility_Jamo","Halfwidth_Jamo","Hangul_Syllables","Hiragana","Kana_Extended_A","Kana_Extended_B","Kana_Supplement","Small_Kana_Extension","Kanbun","Katakana","Katakana_Phonetic_Extensions","Halfwidth_Katakana","Khitan_Small_Script","Lisu","Lisu_Supplement","Miao","Nushu","Tangut","Tangut_Components","Tangut_Supplement","Yi","Yi_Syllables","Yi_Radicals","American_Scripts","Cherokee","Cherokee_Supplement","Deseret","Osage","Unified_Canadian_Aboriginal_Syllabics","UCAS_Extended","UCAS_Extended_A","Notational_Systems","Braille_Patterns","Musical_Symbols","Ancient_Greek_Musical_Notation","Byzantine_Musical_Symbols","Znamenny_Musical_Notation","Duployan","Shorthand_Format_Controls","Sutton_SignWriting","Punctuation","General_Punctuation","ASCII_Punctuation","Latin_1_Punctuation","Supplemental_Punctuation","CJK_Symbols_and_Punctuation","Ideographic_Symbols_and_Punctuation","CJK_Compatibility_Forms","Halfwidth_and_Fullwidth_Forms","Small_Form_Variants","Vertical_Forms","Alphanumeric_Symbols","Letterlike_Symbols","Roman_Symbols","Mathematical_Alphanumeric_Symbols","Arabic_Mathematical_Alphabetic_Symbols","Enclosed_Alphanumerics","Enclosed_Alphanumeric_Supplement","Enclosed_CJK_Letters_and_Months","Enclosed_Ideographic_Supplement","CJK_Compatibility","Additional_Squared_Symbols","Technical_Symbols","APL_symbols","Control_Pictures","Miscellaneous_Technical","Optical_Character_Recognition__OCR_","Numbers___Digits","_see_also_specific_scripts_","ASCII_Digits","Fullwidth_ASCII_Digits","Common_Indic_Number_Forms","Coptic_Epact_Numbers","Counting_Rod_Numerals","Cuneiform_Numbers_and_Punctuation","Indic_Siyaq_Numbers","Kaktovik_Numerals","Mayan_Numerals","Number_Forms","Ottoman_Siyaq_Numbers","Rumi_Numeral_Symbols","Sinhala_Archaic_Numbers","Super_and_Subscripts","Mathematical_Symbols","Arrows","Supplemental_Arrows_A","Supplemental_Arrows_B","Supplemental_Arrows_C","Additional_Arrows","Miscellaneous_Symbols_and_Arrows","Mathematical_Alphanumeric_Symbols","Arabic_Mathematical_Alphabetic_Symbols","Letterlike_Symbols","Mathematical_Operators","Basic_operators__Plus__Factorial__Division__Multiplication","Supplemental_Mathematical_Operators","Miscellaneous_Mathematical_Symbols_A","Miscellaneous_Mathematical_Symbols_B","Floors_and_Ceilings","Invisible_Operators","Geometric_Shapes","Additional_Shapes","Box_Drawing","Block_Elements","Geometric_Shapes_Extended","Emoji___Pictographs","Dingbats","Ornamental_Dingbats","Emoticons","Miscellaneous_Symbols","Miscellaneous_Symbols_And_Pictographs","Supplemental_Symbols_and_Pictographs","Symbols_and_Pictographs_Extended_A","Transport_and_Map_Symbols","Other_Symbols","Alchemical_Symbols","Ancient_Symbols","Currency_Symbols","_see_also_specific_scripts_","Dollar_Sign__Euro_Sign","Yen__Pound_and_Cent","Fullwidth_Currency_Symbols","Rial_Sign","Game_Symbols","Chess__Checkers_Draughts","Chess_Symbols","Domino_Tiles","Japanese_Chess","Mahjong_Tiles","Playing_Cards","Card_suits","Miscellaneous_Symbols_and_Arrows","Symbols_for_Legacy_Computing","Yijing_Symbols","Yijing_Mono___Di__and_Trigrams","Yijing_Hexagram_Symbols","Tai_Xuan_Jing_Symbols","Specials","Controls__tC0__tC1","Layout_Controls","Invisible_Operators","Specials","Tags","Variation_Selectors","Variation_Selectors_Supplement","Private_Use","Private_Use_Area","Supplementary_Private_Use_Area_A","Supplementary_Private_Use_Area_B","Surrogates","High_Surrogates","Low_Surrogates","Noncharacters_in_Charts","Noncharacters_in_blocks","Range_in_Arabic_Presentation_Forms_A","Range_in_Specials","Noncharacters_at_end_of____","BMP__Plane_1__Plane_2__Plane_3__Plane_4__Plane_5__Plane_6__Plane_7__Plane_8__Plane_9__Plane_10__Plane_11__Plane_12__Plane_13__Plane_14__Plane_15__Plane_16"]
+}

package/browser_action/unicode/parseUnihanFromTextFileStrings.js

@@ -0,0 +1,56 @@
+// Todo: We might consider auto-building these fields in another file and/or
+//   merging with `unicodeFieldInfo.js`.
+/* eslint-disable @stylistic/max-len -- Long */
+const fields = ['code_pt', 'kAccountingNumeric', 'kAlternateTotalStrokes', 'kBigFive', 'kCCCII', 'kCNS1986', 'kCNS1992', 'kCangjie', 'kCantonese',
+  'kCheungBauer', 'kCheungBauerIndex', 'kCihaiT', 'kCompatibilityVariant', 'kCowles', 'kDaeJaweon',
+  'kDefinition', 'kEACC', 'kFenn', 'kFennIndex', 'kFourCornerCode', 'kFrequency', 'kGB0', 'kGB1', 'kGB3',
+  'kGB5', 'kGB7', 'kGB8', 'kGSR', 'kGradeLevel', 'kHDZRadBreak', 'kHKGlyph', 'kHKSCS', 'kHanYu', 'kHangul',
+  'kHanyuPinlu', 'kHanyuPinyin', 'kIBMJapan', 'kIICore', 'kIRGDaeJaweon', 'kIRGDaiKanwaZiten',
+  'kIRGHanyuDaZidian', 'kIRGKangXi', 'kIRG_GSource', 'kIRG_HSource', 'kIRG_JSource', 'kIRG_KPSource',
+  'kIRG_KSource', 'kIRG_MSource', 'kIRG_TSource', 'kIRG_USource', 'kIRG_VSource', 'kJIS0213', 'kJapaneseKun',
+  'kJapaneseOn', 'kJis0', 'kJis1', 'kKPS0', 'kKPS1', 'kKSC0', 'kKSC1', 'kKangXi', 'kKarlgren', 'kKorean', 'kLau',
+  'kMainlandTelegraph', 'kMandarin', 'kMatthews', 'kMeyerWempe', 'kMorohashi', 'kNelson', 'kOtherNumeric',
+  'kPhonetic', 'kPrimaryNumeric', 'kPseudoGB1', 'kRSAdobe_Japan1_6', 'kRSJapanese', 'kRSKanWa', 'kRSKangXi',
+  'kRSKorean', 'kRSUnicode', 'kSBGY', 'kSemanticVariant', 'kSimplifiedVariant', 'kSpecializedSemanticVariant',
+  'kTaiwanTelegraph', 'kTang', 'kTotalStrokes', 'kTraditionalVariant', 'kVietnamese', 'kXHC1983', 'kXerox', 'kZVariant',
+  'kUnihanCore2020', 'kIRG_UKSource', 'kIRG_SSource', 'kTGH', 'kKoreanName', 'kJa', 'kJoyoKanji', 'kKoreanEducationHanja',
+  'kJinmeiyoKanji', 'kTGHZ2013', 'kSpoofingVariant', 'kStrange'];
+/* eslint-enable @stylistic/max-len -- Long */
+
+/**
+* @param {string[]} scriptFileAsStrings
+* @returns {Object<string,string[]>}
+*/
+function parseUnihanFromTextFileStrings (scriptFileAsStrings) {
+  const scriptFileAsStr = scriptFileAsStrings.join('');
+  const notPresent = {};
+  let line;
+  const obj = {};
+  const lineRegex = /^U\+(?<cdpt>[\da-fA-F]{4,6})\t(?<col>\w+?)\t(?<value>.*)$/gum;
+  while ((line = (lineRegex).exec(scriptFileAsStr)) !== null) {
+    const {cdpt, col, value} = line.groups;
+    if (!obj[cdpt]) {
+      obj[cdpt] = [];
+      fields.forEach(function (val, idx) {
+        obj[cdpt][idx] = '';
+      });
+      obj[cdpt][0] = cdpt;
+    }
+    const pos = fields.indexOf(col);
+    if (pos === -1) {
+      // Todo: Even if not inserting, should auto-add locales as in
+      //   parseUnicodeCharts.js
+      if (!notPresent[col]) {
+        // eslint-disable-next-line no-console -- CLI
+        console.error(`Not present: ${col}\n`);
+        notPresent[col] = 1;
+      }
+      continue;
+    }
+    obj[cdpt][pos] = value;
+  }
+
+  return Object.values(obj);
+}
+
+export default parseUnihanFromTextFileStrings;

package/browser_action/unicode/unicodeFieldInfo.js

@@ -0,0 +1,120 @@
+export const unihanFieldInfo = [
+  ['kCangjie', 6],
+  ['kCantonese', 7],
+  // ['kDefinition', 3],
+  ['kHanYu', 31],
+  ['kHanyuPinyin', 34],
+  ['kIRGHanyuDaZidian', 39],
+  ['kIRGKangXi', 40],
+  ['kIRG_GSource', 41],
+  ['kIRG_HSource', 42],
+  ['kIRG_JSource', 43],
+  ['kIRG_KSource', 45],
+  ['kIRG_MSource', 46],
+  ['kIRG_TSource', 47],
+  ['kIRG_USource', 48],
+  ['kMandarin', 64],
+  ['kRSUnicode', 78],
+  ['kAccountingNumeric', 1],
+  ['kCompatibilityVariant', 11],
+  ['kSemanticVariant', 80],
+  ['kTotalStrokes', 85],
+  ['kCihaiT', 10],
+  ['kSBGY', 79],
+  ['kJIS0213', 50],
+  ['kNelson', 68],
+  ['kRSAdobe_Japan1_6', 73],
+  ['kCowles', 12],
+  ['kMatthews', 65],
+  ['kOtherNumeric', 69],
+  ['kPhonetic', 70],
+  ['kGSR', 26],
+  ['kIRG_KPSource', 44],
+  ['kIRG_VSource', 49],
+  ['kKPS1', 56],
+  ['kFenn', 16],
+  ['kFennIndex', 17],
+  ['kKarlgren', 60],
+  ['kHKSCS', 30],
+  ['kXHC1983', 88],
+  ['kMeyerWempe', 66],
+  ['kTraditionalVariant', 86],
+  ['kVietnamese', 87],
+  ['kSpecializedSemanticVariant', 82],
+  ['kLau', 62],
+  ['kCheungBauer', 8],
+  ['kCheungBauerIndex', 9],
+  ['kIICore', 36],
+  ['kTang', 84],
+  ['kZVariant', 90],
+  ['kRSKangXi', 76],
+  ['kJapaneseKun', 51],
+  ['kJapaneseOn', 52],
+  ['kSimplifiedVariant', 81],
+  ['kKangXi', 59],
+  ['kKPS0', 55],
+  ['kBigFive', 2],
+  ['kCCCII', 3],
+  ['kCNS1986', 4],
+  ['kCNS1992', 5],
+  ['kDaeJaweon', 13],
+  ['kEACC', 15],
+  ['kFourCornerCode', 18],
+  ['kFrequency', 19],
+  ['kGB0', 20],
+  ['kGB1', 21],
+  ['kGradeLevel', 27],
+  ['kHDZRadBreak', 28],
+  ['kHKGlyph', 29],
+  ['kHangul', 32],
+  ['kHanyuPinlu', 33],
+  ['kIRGDaeJaweon', 37],
+  ['kIRGDaiKanwaZiten', 38],
+  ['kJis0', 53],
+  ['kKSC0', 57],
+  ['kKorean', 61],
+  ['kMainlandTelegraph', 63],
+  ['kMorohashi', 67],
+  ['kPrimaryNumeric', 71],
+  ['kTaiwanTelegraph', 83],
+  ['kXerox', 89],
+  ['kGB5', 23],
+  ['kJis1', 54],
+  ['kPseudoGB1', 72],
+  ['kGB3', 22],
+  ['kGB7', 24],
+  ['kGB8', 25],
+  ['kKSC1', 58],
+  ['kIBMJapan', 35],
+  ['kRSKanWa', 75],
+  ['kRSKorean', 77],
+  ['kRSJapanese', 74],
+  ['kStrange', 91]
+];
+
+export const unicodeFieldInfo = [
+  'General_Category',
+  'Canonical_Combining_Class',
+  'Bidi_Class',
+
+  // We broke it up into two parts for easier viewing
+  // 'Decomposition_Type_and_Mapping',
+  'decompositionMapping',
+  'decompositionType',
+
+  // We broke this up for more convenient querying/display
+  /*
+  'Decimal',
+  'Digit',
+  'Numeric',
+   */
+  'numericType',
+  'numericValue',
+
+  'Bidi_Mirrored',
+  'Unicode_1_Name',
+  'ISO_Comment',
+  'Simple_Uppercase_Mapping',
+  'Simple_Lowercase_Mapping',
+  'Simple_Titlecase_Mapping'
+];