unicode-input-toolconverter 0.2.0 → 0.2.3

package/browser_action/unicode/charrefunicodeDb.js

@@ -1,34 +1,49 @@
 // Todo: Review `fromCharCode`, `charCodeAt`, and `charAt` on whether
 //   need modern substitutions
 
+/**
+ * @typedef {number} PositiveInteger
+ */
+
+/* eslint-disable jsdoc/reject-any-type -- Arbitrary */
+/**
+ * @typedef {any} AnyValue
+ */
+/* eslint-enable jsdoc/reject-any-type -- Arbitrary */
+
 /**
  *
  */
 class UnicodeDB {
   /**
-   * @param {PlainObject} cfg
-   * @param {string} cfg.name
+   * @param {object} cfg
+   * @param {string} [cfg.name]
    * @param {PositiveInteger} [cfg.version]
    */
   constructor ({name = 'unicode', version = 1} = {}) {
-    Object.assign(this, {name, version});
+    this.name = name;
+    this.version = version;
     this.db = null;
   }
 
   /**
-  * @returns {void}
-  */
+   * @returns {void}
+   */
   close () {
-    this.db.close();
+    this.db?.close();
   }
 
   /**
    * @param {string} storeName
-   * @param {string} key
-   * @returns {Promise<object>}
+   * @param {string} [key]
+   * @returns {Promise<{
+   *   codePoint: string, columns?: string[], [key: string]: unknown
+   * }[]>}
    */
   getAll (storeName, key) {
-    const tx = this.db.transaction(storeName, 'readonly');
+    const tx = /** @type {IDBDatabase} */ (
+      this.db
+    ).transaction(storeName, 'readonly');
     const store = tx.objectStore(storeName);
 
     const req = store.getAll(key);
@@ -47,17 +62,21 @@ class UnicodeDB {
   /* eslint-disable class-methods-use-this -- Abstract */
   /**
    * @abstract
+   * @param {AnyValue} cfg
    */
-  upgradeneeded () {
+  upgradeneeded (
+    // eslint-disable-next-line no-unused-vars -- Needed as base method
+    cfg
+  ) {
     throw new Error('`UnicodeDB.upgradeneeded` is an abstract method');
   }
   /* eslint-enable class-methods-use-this -- Abstract */
 
   /**
    * @param {object} [cfg]
-   * @param {JSON} [cfg.updateUnicodeData]
-   * @param {GenericFunction} [cfg.versionchange]
-   * @returns {Promise<void>}
+   * @param {AnyValue} [cfg.updateUnicodeData]
+   * @param {(e: Event) => void} [cfg.versionchange]
+   * @returns {Promise<IDBDatabase>}
    */
   connect ({updateUnicodeData, versionchange} = {}) {
     /* eslint-disable promise/avoid-new -- No Promise API */
@@ -67,13 +86,18 @@ class UnicodeDB {
       );
       if (updateUnicodeData) {
         req.addEventListener('upgradeneeded', (e) => {
-          const {result: db} = e.target;
+          const db = /** @type {EventTarget & {result: IDBDatabase}} */ (
+            e.target
+          )?.result;
           this.db = db;
           this.upgradeneeded({updateUnicodeData});
         });
       }
-      req.addEventListener('success', ({target}) => {
-        this.db = target.result;
+      req.addEventListener('success', (e) => {
+        const db = /** @type {EventTarget & {result: IDBDatabase}} */ (
+          e.target
+        )?.result;
+        this.db = db;
         if (versionchange) {
           this.db.addEventListener('versionchange', (ev) => {
             versionchange(ev);
@@ -97,20 +121,22 @@ class UnicodeDB {
  */
 export class UnihanDatabase extends UnicodeDB {
   /**
-   * @param {PlainObject} cfg
-   * @param {PositiveInteger} cfg.version
+   * @param {object} [cfg]
+   * @param {PositiveInteger} [cfg.version]
    */
   constructor ({version} = {}) {
     // We create a separate database so updates do not clobber both databases
     super({name: 'unicode-input-toolconverter-Unihan', version});
   }
   /**
-  * @param {string} codePoint
-  * @throws {Error}
-  * @returns {Promise<string[]>}
-  */
+   * @param {string} codePoint
+   * @throws {Error}
+   * @returns {Promise<string[]>}
+   */
   getUnicodeFields (codePoint) {
-    const tx = this.db.transaction(['Unihan'], 'readonly');
+    const tx = /** @type {IDBDatabase} */ (
+      this.db
+    ).transaction(['Unihan'], 'readonly');
     const store = tx.objectStore('Unihan');
 
     const request = store.get(codePoint);
@@ -126,19 +152,30 @@ export class UnihanDatabase extends UnicodeDB {
   }
 
   /**
-   * @param {string} key
-   * @returns {Promise<object>}
+   * @param {string} [key]
+   * @returns {Promise<{
+   *   codePoint: string, columns?: string[], [key: string]: unknown
+   * }[]>}
    */
   getAll (key) {
     return super.getAll('Unihan', key);
   }
 
   /**
-   * @param {JSON} updateUnicodeData
+   * @param {AnyValue} cfg
    * @returns {void}
    */
-  upgradeneeded ({updateUnicodeData}) {
-    const store = this.db.createObjectStore('Unihan', {
+  upgradeneeded (cfg) {
+    // eslint-disable-next-line prefer-destructuring -- TS
+    const updateUnicodeData =
+      /**
+       * @type {{
+       *   updateUnicodeData: [codePoint: string, ...info: string[]][]
+       * }}
+       */ (cfg).updateUnicodeData;
+    const store = /** @type {IDBDatabase} */ (
+      this.db
+    ).createObjectStore('Unihan', {
       keyPath: 'codePoint'
     });
     store.createIndex('code-point', 'codePoint', {
@@ -161,48 +198,59 @@ export class UnihanDatabase extends UnicodeDB {
  */
 export class UnicodeDatabase extends UnicodeDB {
   /**
-   * @param {PlainObject} cfg
-   * @param {PositiveInteger} cfg.version
+   * @param {object} [cfg]
+   * @param {PositiveInteger} [cfg.version]
    */
   constructor ({version} = {}) {
     super({name: 'unicode-input-toolconverter', version});
   }
 
   /**
-   * @param {string} key
-   * @returns {Promise<object>}
+   * @param {string} [key]
+   * @returns {Promise<{
+   *   codePoint: string, columns?: string[], [key: string]: unknown
+   * }[]>}
    */
   getAll (key) {
     return super.getAll('UnicodeData', key);
   }
 
   /**
-   * @param {JSON} updateUnicodeData
+   * @param {AnyValue} cfg
    * @returns {void}
    */
-  upgradeneeded ({updateUnicodeData}) {
-    const store = this.db.createObjectStore('UnicodeData', {
+  upgradeneeded (cfg) {
+    // eslint-disable-next-line prefer-destructuring -- TS
+    const updateUnicodeData =
+      /**
+       * @type {{
+       *   updateUnicodeData: [codePoint: string, ...info: string[]][]
+       * }}
+       */ (cfg).updateUnicodeData;
+    const store = /** @type {IDBDatabase} */ (
+      this.db
+    ).createObjectStore('UnicodeData', {
       keyPath: 'codePoint'
     });
     store.createIndex('code-point', 'codePoint', {
       unique: true
     });
     updateUnicodeData.forEach((codePointInfoRow) => {
-      // http://www.unicode.org/reports/tr44/#UnicodeData.txt
+      // https://www.unicode.org/reports/tr44/#UnicodeData.txt
       const [
         codePoint, name, generalCategory, canonicalCombiningClass, bidiClass,
         decomposition, numeric6, numeric7, numeric8,
         bidiMirrored, unicode1Name, isoComment,
         simpleUppercaseMapping, simpleLowercaseMapping, simpleTitlecaseMapping
       ] = codePointInfoRow;
-      const {groups: {
-        decompositionType,
-        decompositionMapping
-      }} = (
-        /<(?<decompositionType>[^>]*)>\s+(?<decompositionMapping>.*)/u
+      const groups = (
+        /<(?<decompositionType>[^>]*)>\s+(?<decompositionMapping>.*)/v
       ).exec(
         decomposition
-      ) ?? {groups: {}};
+      )?.groups ?? {};
+
+      const {decompositionType, decompositionMapping} = groups;
+
       let numericType = 'None';
       if (numeric6) {
         numericType = 'Decimal';
@@ -211,7 +259,7 @@ export class UnicodeDatabase extends UnicodeDB {
       } else if (numeric8) {
         numericType = 'Numeric';
       }
-      const numericValue = numericType ? numeric8 : Number.NaN;
+      const numericValue = numericType ? numeric8 : NaN;
 
       store.put({
         codePoint, name, generalCategory, canonicalCombiningClass, bidiClass,
@@ -223,15 +271,19 @@ export class UnicodeDatabase extends UnicodeDB {
   }
 
   /**
-  * @param {string} codePoint
-  * @returns {Promise<string[]>}
-  */
+   * @param {string} codePoint
+   * @returns {Promise<{
+   *   name: string, unicode1Name: string, [key: string]: string
+   * }>}
+   */
   getUnicodeFields (codePoint) {
     // const entityInParentheses = '(' + entity + ') ';
     // Todo: Should this not be padded to 6??
     // const currentStartCharCodeUpperCaseHexPadded =
     //   currentStartCharCode.toString(16).toUpperCase().padStart(4, '0');
-    const tx = this.db.transaction(['UnicodeData'], 'readonly');
+    const tx = /** @type {IDBDatabase} */ (
+      this.db
+    ).transaction(['UnicodeData'], 'readonly');
     const store = tx.objectStore('UnicodeData');
     const request = store.get(codePoint);
     // eslint-disable-next-line promise/avoid-new -- No Promise API
@@ -251,8 +303,6 @@ export class UnicodeDatabase extends UnicodeDB {
 }
 
 const charrefunicodeDb = new UnicodeDatabase();
-/*
-const unihanDb = new UnihanDatabase();
-*/
+/* const unihanDb = new UnihanDatabase(); */
 
 export default charrefunicodeDb;

package/browser_action/unicode/getScriptInfoForCodePoint.js

@@ -1,17 +1,26 @@
 // Todo: Auto-generate this function
 
+/**
+ * @typedef {number} PositiveInteger
+ */
+
 /**
  * @param {PositiveInteger} num
- * @param {IntlDom} _
+ * @param {import('intl-dom').I18NCallback<string>} _
  * @returns {{
  * codePointStart: string, script: string, plane: PositiveInteger,
- * privateuse: boolean, surrogate: boolean|string
+ * privateuse: boolean, surrogate: false|string
  * }}
  */
 export default function getScriptInfoForCodePoint (num, _) {
-  let privateuse = false, surrogate = false;
+  let privateuse = false;
+  /** @type {false|string} */
+  let surrogate = false;
   let plane = num >= 0x10000 && num <= 0x1FFFF ? 1 : 0;
-  let script = '', codePointStart = '';
+  // eslint-disable-next-line no-useless-assignment -- Ok
+  let script = '';
+  // eslint-disable-next-line no-useless-assignment -- Ok
+  let codePointStart = '';
   if (num < 0x0080) {
     codePointStart = '0000';
     script = _('Basic_Latin'); // + _ ('comma') + ' ' +

package/browser_action/unicode/hangul.js

@@ -1,10 +1,14 @@
 /* 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
-*/
+ * @namespace This contains methods for translating Korean Hangul/Jamo,
+ *   since these are obtained programmatically and not through the Unicode (or
+ *   Unihan) database
+ */
+
+/**
+ * @typedef {number} Integer
+ */
 
 // Private static
 const JAMO_L_TABLE = [
@@ -36,7 +40,7 @@ const sBase = 0xAC00,
  * Currently unused.
  * @param {Integer} syllableCode Decimal code point for Hangul syllable
  *   to decompose
- * @returns {Integer[]|string} An array of the numeric value of each
+ * @returns {string[]|string} An array of the numeric value of each
  *   component or string if unchanged
  */
 function decomposeHangul (syllableCode) {
@@ -57,8 +61,8 @@ function decomposeHangul (syllableCode) {
 }
 /**
  *
- * @param {string[]} source
- * @returns {string[]}
+ * @param {string} source
+ * @returns {string|string[]}
  */
 function composeHangul (source) {
   const len = source.length;
@@ -75,9 +79,9 @@ function composeHangul (source) {
 
   chars.slice(1).forEach((ch) => {
     // 1. check to see if two current characters are L and V
-    const lIndex = last.codePointAt() - lBase;
+    const lIndex = /** @type {number} */ (last.codePointAt(0)) - lBase;
     if (lIndex > 0 && lIndex < lCount) {
-      const vIndex = ch.codePointAt() - vBase;
+      const vIndex = /** @type {number} */ (ch.codePointAt(0)) - vBase;
       if (vIndex > 0 && vIndex < vCount) {
         // make syllable of form LV
         last = String.fromCodePoint(
@@ -89,12 +93,14 @@ function composeHangul (source) {
     }
 
     // 2. check to see if two current characters are LV and T
-    const sIndex = last.codePointAt() - sBase;
+    const sIndex = /** @type {number} */ (last.codePointAt(0)) - sBase;
     if (sIndex > 0 && sIndex < sCount && (sIndex % tCount) === 0) {
-      const tIndex = ch.codePointAt() - tBase;
+      const tIndex = /** @type {number} */ (ch.codePointAt(0)) - tBase;
       if (tIndex >= 0 && tIndex < tCount) {
         // make syllable of form LVT
-        last = String.fromCodePoint(last.codePointAt() + tIndex);
+        last = String.fromCodePoint(
+          /** @type {number} */ (last.codePointAt(0)) + tIndex
+        );
         result[result.length - 1] = last; // reset last
         return; // discard ch
       }
@@ -110,12 +116,12 @@ function composeHangul (source) {
  * 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
+ * @returns {string|false} 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 lIndex, vIndex, tIndex;
   let ptr = 1;
 
   // L (can be 1-2 in name length)
@@ -159,20 +165,17 @@ function getHangulFromName (name) {
   const v = getJamoForIndex(vIndex, 'v');
 
   // May only be LV
-  t = '';
-  if (tIndex) {
-    t = getJamoForIndex(tIndex, 't');
-  }
+  const t = tIndex ? getJamoForIndex(tIndex, 't') : '';
 
   // Join Jamo characters together
   const jamo = l + v + t;
   // Convert Jamo into composite Hangul syllable
-  return composeHangul(jamo).join('');
+  return /** @type {string[]} */ (composeHangul(jamo)).join('');
 }
 
 /**
  * Utility (could be adapted to accept the letter(s)).
- * @param {string} index
+ * @param {number} index
  * @param {'l'|'v'|'t'} type
  * @throws {TypeError}
  * @returns {string}
@@ -190,6 +193,10 @@ function getJamoForIndex (index, type) {
   }
 }
 
+/**
+ * @typedef {number} PositiveInteger
+ */
+
 /**
  * @param {PositiveInteger} syllableCode
  * @throws {Error}

package/browser_action/unicode/lastScriptNames.json

@@ -1,5 +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"]
+  "lastScriptNames": ["European_Scripts","Armenian","Armenian_Ligatures","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","Ogham","Old_Hungarian","Old_Italic","Old_Permic","Phaistos_Disc","Runic","Shavian","Todhri","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","Beria_Erfe","Coptic","Coptic_in_Greek_block","Coptic_Epact_Numbers","Egyptian_Hieroglyphs","Egyptian_Hieroglyph_Format_Controls","Egyptian_Hieroglyphs_Extended_A","Ethiopic","Ethiopic_Supplement","Ethiopic_Extended","Ethiopic_Extended_A","Ethiopic_Extended_B","Garay","Medefaidrin","Mende_Kikakui","Meroitic","Meroitic_Cursive","Meroitic_Hieroglyphs","N_Ko","Osmanya","Tifinagh","Vai","West_Asian_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","Carian","Chorasmian","Cuneiform","Cuneiform_Numbers_and_Punctuation","Archaic_Cuneiform_Numbers","Early_Dynastic_Cuneiform","Old_Persian","Ugaritic","Elymaic","Hatran","Hebrew","Hebrew_Presentation_Forms","Lycian","Lydian","Mandaic","Nabataean","Old_North_Arabian","Old_South_Arabian","Pahlavi__Inscriptional","Pahlavi__Psalter","Palmyrene","Parthian__Inscriptional","Phoenician","Samaritan","Sidetic","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","Bengali_Supplement","Bhaiksuki","Brahmi","Chakma","Devanagari","Devanagari_Extended","Devanagari_Extended_A","Dives_Akuru","Dogra","Grantha","Gujarati","Gunjala_Gondi","Gurmukhi","Gurung_Khema","Kaithi","Kannada","Kharoshthi","Khojki","Kirat_Rai","Khudawadi","Lepcha","Limbu","Mahajani","Malayalam","Masaram_Gondi","Meetei_Mayek","Meetei_Mayek_Extensions","Modi","Mro","Multani","Nag_Mundari","Nandinagari","Newa","Ol_Chiki","Ol_Onal","Oriya","Saurashtra","Sharada","Sharada_Supplement","Siddham","Sinhala","Sinhala_Archaic_Numbers","Sora_Sompeng","Sunuwar","Syloti_Nagri","Takri","Tamil","Tamil_Supplement","Telugu","Thaana","Tirhuta","Tolong_Siki","Toto","Tulu_Tigalari","Vedic_Extensions","Wancho","Warang_Citi","Southeast_Asian_Scripts","Cham","Hanifi_Rohingya","Kayah_Li","Khmer","Khmer_Symbols","Lao","Myanmar","Myanmar_Extended_A","Myanmar_Extended_B","Myanmar_Extended_C","New_Tai_Lue","Nyiakeng_Puachue_Hmong","Pahawh_Hmong","Pau_Cin_Hau","Tai_Le","Tai_Tham","Tai_Viet","Tai_Yo","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","CJK_Extension_J","Full_Radical_Stroke_Index__PDF__35MB_","Full_Radical_Stroke_Index__txt_","_see_also_Unihan_Database_Lookup_","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","Jurchen","Jurchen_Radicals","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","Small_Seal","Tangut","Tangut_Components","Tangut_Supplement","Tangut_Components_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","Musical_Symbols_Supplement","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","Archaic_Cuneiform_Numbers","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","Miscellaneous_Symbols_and_Arrows_Extended","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","Miscellaneous_Symbols_Supplement","Miscellaneous_Symbols_and_Arrows_Extended","Symbols_for_Legacy_Computing","Symbols_for_Legacy_Computing_Supplement","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

@@ -1,7 +1,13 @@
-// Todo: We might consider auto-building these fields in another file and/or
-//   merging with `unicodeFieldInfo.js`.
+// The known, stable column order historically used to build
+//   `download/unihan/unihan.json`. `parseUnihanFromTextFileStrings` below
+//   auto-appends any newly encountered field (e.g., from a Unihan standard
+//   update) after this base order, keeping existing field positions stable
+//   across re-downloads while never silently dropping new data. The
+//   resulting order is returned so callers (see `tools/unihan-import.js`)
+//   can persist it for `browser_action/unicodecharref.js`'s display code,
+//   which must stay in sync since it reads values by position.
 /* eslint-disable @stylistic/max-len -- Long */
-const fields = ['code_pt', 'kAccountingNumeric', 'kAlternateTotalStrokes', 'kBigFive', 'kCCCII', 'kCNS1986', 'kCNS1992', 'kCangjie', 'kCantonese',
+const baseFields = ['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',
@@ -14,43 +20,56 @@ const fields = ['code_pt', 'kAccountingNumeric', 'kAlternateTotalStrokes', 'kBig
   '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'];
+  'kJinmeiyoKanji', 'kTGHZ2013', 'kSpoofingVariant', 'kStrange',
+  'kSMSZD2003Index', 'kMojiJoho', 'kVietnameseNumeric', 'kZhuangNumeric', 'kTayNumeric',
+  'kJapanese', 'kFanqie', 'kSMSZD2003Readings', 'kZhuang', 'kJapaneseOldVariant', 'kJapaneseNewVariant'];
 /* eslint-enable @stylistic/max-len -- Long */
 
 /**
-* @param {string[]} scriptFileAsStrings
-* @returns {Object<string,string[]>}
-*/
+ * @param {string[]} scriptFileAsStrings
+ * @returns {{rows: string[][], fields: string[]}} `fields` includes the
+ *   leading `code_pt` entry; each `rows[n][0]` is the code point.
+ */
 function parseUnihanFromTextFileStrings (scriptFileAsStrings) {
   const scriptFileAsStr = scriptFileAsStrings.join('');
-  const notPresent = {};
+  const lineRegex = /^U\+(?<cdpt>[\da-fA-F]{4,6})\t(?<col>\w+?)\t(?<value>.*)$/gvm;
+
+  // Pass 1: discover the full field set before populating any rows, so
+  //   every row ends up uniformly sized regardless of when a given field
+  //   is first encountered.
+  const knownFields = new Set(baseFields);
+  const fields = [...baseFields];
   let line;
+  while ((line = lineRegex.exec(scriptFileAsStr)) !== null) {
+    const {col} = /** @type {{col: string}} */ (line.groups);
+    if (!knownFields.has(col)) {
+      knownFields.add(col);
+      fields.push(col);
+    }
+  }
+  const fieldPositions = new Map(fields.map((field, idx) => [field, idx]));
+
+  // Pass 2: populate rows now that `fields` (and thus each row's length)
+  //   is final.
+  /** @type {Record<string, string[]>} */
   const obj = {};
-  const lineRegex = /^U\+(?<cdpt>[\da-fA-F]{4,6})\t(?<col>\w+?)\t(?<value>.*)$/gum;
-  while ((line = (lineRegex).exec(scriptFileAsStr)) !== null) {
-    const {cdpt, col, value} = line.groups;
-    if (!obj[cdpt]) {
+  lineRegex.lastIndex = 0;
+  while ((line = lineRegex.exec(scriptFileAsStr)) !== null) {
+    // eslint-disable-next-line @stylistic/max-len -- Long
+    const {cdpt, col, value} = /** @type {{cdpt: string, col: string, value: string}} */ (
+      line.groups
+    );
+    if (!Object.hasOwn(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;
+    obj[cdpt][/** @type {number} */ (fieldPositions.get(col))] = value;
   }
 
-  return Object.values(obj);
+  return {rows: Object.values(obj), fields};
 }
 
 export default parseUnihanFromTextFileStrings;