Move normalizeRadicalCharacters to CJK-util

yomidevs · Nov 3, 2024 · b1b97ba · b1b97ba
1 parent 1a234b1
commit b1b97ba
Show file tree

Hide file tree

Showing 4 changed files with 12 additions and 20 deletions.
diff --git a/ext/js/language/CJK-util.js b/ext/js/language/CJK-util.js
@@ -15,6 +15,8 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
+import {basicTextProcessorOptions} from './text-processors.js';
+
 /** @type {import('CJK-util').CodepointRange} */
 const CJK_UNIFIED_IDEOGRAPHS_RANGE = [0x4e00, 0x9fff];
 /** @type {import('CJK-util').CodepointRange} */
@@ -123,3 +125,11 @@ export function normalizeRadicals(text) {
     }
     return result;
 }
+
+/** @type {import('language').TextProcessor<boolean>} */
+export const normalizeRadicalCharacters = {
+    name: 'Normalize radical characters',
+    description: '⼀ → 一 (U+2F00 → U+4E00)',
+    options: basicTextProcessorOptions,
+    process: (str, setting) => (setting ? normalizeRadicals(str) : str),
+};
diff --git a/ext/js/language/ja/japanese-text-preprocessors.js b/ext/js/language/ja/japanese-text-preprocessors.js
@@ -15,7 +15,6 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import {normalizeRadicals} from '../CJK-util.js';
 import {basicTextProcessorOptions} from '../text-processors.js';
 import {convertAlphabeticToKana} from './japanese-wanakana.js';
 import {
@@ -100,11 +99,3 @@ export const normalizeCombiningCharacters = {
     options: basicTextProcessorOptions,
     process: (str, setting) => (setting ? normalizeCombiningCharactersFunction(str) : str),
 };
-
-/** @type {import('language').TextProcessor<boolean>} */
-export const normalizeRadicalCharacters = {
-    name: 'Normalize radical characters',
-    description: '⼀ → 一 (U+2F00 → U+4E00)',
-    options: basicTextProcessorOptions,
-    process: (str, setting) => (setting ? normalizeRadicals(str) : str),
-};
diff --git a/ext/js/language/language-descriptors.js b/ext/js/language/language-descriptors.js
@@ -16,6 +16,7 @@
  */
 
 import {removeArabicScriptDiacritics} from './ar/arabic-text-preprocessors.js';
+import {normalizeRadicalCharacters} from './CJK-util.js';
 import {eszettPreprocessor} from './de/german-text-preprocessors.js';
 import {germanTransforms} from './de/german-transforms.js';
 import {englishTransforms} from './en/english-transforms.js';
@@ -27,7 +28,6 @@ import {
     convertHalfWidthCharacters,
     convertHiraganaToKatakana,
     normalizeCombiningCharacters,
-    normalizeRadicalCharacters,
 } from './ja/japanese-text-preprocessors.js';
 import {japaneseTransforms} from './ja/japanese-transforms.js';
 import {isStringPartiallyJapanese} from './ja/japanese.js';

diff --git a/ext/js/language/zh/chinese.js b/ext/js/language/zh/chinese.js
@@ -15,8 +15,7 @@
  * along with this program.  If not, see <https://www.gnu.org/licenses/>.
  */
 
-import {CJK_IDEOGRAPH_RANGES, CJK_PUNCTUATION_RANGE, FULLWIDTH_CHARACTER_RANGES, isCodePointInRanges, normalizeRadicals} from '../CJK-util.js';
-import {basicTextProcessorOptions} from '../text-processors.js';
+import {CJK_IDEOGRAPH_RANGES, CJK_PUNCTUATION_RANGE, FULLWIDTH_CHARACTER_RANGES, isCodePointInRanges} from '../CJK-util.js';
 
 /** @type {import('CJK-util').CodepointRange} */
 const BOPOMOFO_RANGE = [0x3100, 0x312f];
@@ -74,11 +73,3 @@ export function isCodePointChinese(codePoint) {
 export function normalizePinyin(str) {
     return str.normalize('NFC').toLowerCase().replace(/[\s・:'’-]|\/\//g, '');
 }
-
-/** @type {import('language').TextProcessor<boolean>} */
-export const normalizeRadicalCharacters = {
-    name: 'Normalize radical characters',
-    description: '⼀ → 一 (U+2F00 → U+4E00)',
-    options: basicTextProcessorOptions,
-    process: (str, setting) => (setting ? normalizeRadicals(str) : str),
-};