summaryrefslogtreecommitdiff
path: root/ext/js/language/ja
diff options
context:
space:
mode:
Diffstat (limited to 'ext/js/language/ja')
-rw-r--r--ext/js/language/ja/japanese-text-preprocessors.js24
-rw-r--r--ext/js/language/ja/japanese-wanakana.js52
-rw-r--r--ext/js/language/ja/japanese.js15
3 files changed, 19 insertions, 72 deletions
diff --git a/ext/js/language/ja/japanese-text-preprocessors.js b/ext/js/language/ja/japanese-text-preprocessors.js
index 06f944c1..b3d50817 100644
--- a/ext/js/language/ja/japanese-text-preprocessors.js
+++ b/ext/js/language/ja/japanese-text-preprocessors.js
@@ -15,7 +15,7 @@
* along with this program. If not, see <https://www.gnu.org/licenses/>.
*/
-import {basicTextPreprocessorOptions} from '../text-preprocessors.js';
+import {basicTextProcessorOptions} from '../text-processors.js';
import {convertAlphabeticToKana} from './japanese-wanakana.js';
import {
collapseEmphaticSequences as collapseEmphaticSequencesFunction,
@@ -25,28 +25,28 @@ import {
convertNumericToFullWidth
} from './japanese.js';
-/** @type {import('language').TextPreprocessor<boolean>} */
+/** @type {import('language').TextProcessor<boolean>} */
export const convertHalfWidthCharacters = {
name: 'Convert half width characters to full width',
description: 'ヨミチャン → ヨミチャン',
- options: basicTextPreprocessorOptions,
- process: (str, setting, sourceMap) => (setting ? convertHalfWidthKanaToFullWidth(str, sourceMap) : str)
+ options: basicTextProcessorOptions,
+ process: (str, setting) => (setting ? convertHalfWidthKanaToFullWidth(str) : str)
};
-/** @type {import('language').TextPreprocessor<boolean>} */
+/** @type {import('language').TextProcessor<boolean>} */
export const convertNumericCharacters = {
name: 'Convert numeric characters to full width',
description: '1234 → 1234',
- options: basicTextPreprocessorOptions,
+ options: basicTextProcessorOptions,
process: (str, setting) => (setting ? convertNumericToFullWidth(str) : str)
};
-/** @type {import('language').TextPreprocessor<boolean>} */
+/** @type {import('language').TextProcessor<boolean>} */
export const convertAlphabeticCharacters = {
name: 'Convert alphabetic characters to hiragana',
description: 'yomichan → よみちゃん',
- options: basicTextPreprocessorOptions,
- process: (str, setting, sourceMap) => (setting ? convertAlphabeticToKana(str, sourceMap) : str)
+ options: basicTextProcessorOptions,
+ process: (str, setting) => (setting ? convertAlphabeticToKana(str) : str)
};
/** @type {import('language').BidirectionalConversionPreprocessor} */
@@ -66,15 +66,15 @@ export const convertHiraganaToKatakana = {
}
};
-/** @type {import('language').TextPreprocessor<[collapseEmphatic: boolean, collapseEmphaticFull: boolean]>} */
+/** @type {import('language').TextProcessor<[collapseEmphatic: boolean, collapseEmphaticFull: boolean]>} */
export const collapseEmphaticSequences = {
name: 'Collapse emphatic character sequences',
description: 'すっっごーーい → すっごーい / すごい',
options: [[false, false], [true, false], [true, true]],
- process: (str, setting, sourceMap) => {
+ process: (str, setting) => {
const [collapseEmphatic, collapseEmphaticFull] = setting;
if (collapseEmphatic) {
- str = collapseEmphaticSequencesFunction(str, collapseEmphaticFull, sourceMap);
+ str = collapseEmphaticSequencesFunction(str, collapseEmphaticFull);
}
return str;
}
diff --git a/ext/js/language/ja/japanese-wanakana.js b/ext/js/language/ja/japanese-wanakana.js
index 32260489..a87db6b7 100644
--- a/ext/js/language/ja/japanese-wanakana.js
+++ b/ext/js/language/ja/japanese-wanakana.js
@@ -19,51 +19,10 @@ import * as wanakana from '../../../lib/wanakana.js';
/**
* @param {string} text
- * @param {?import('../../general/text-source-map.js').TextSourceMap} sourceMap
- * @param {number} sourceMapStart
* @returns {string}
*/
-function convertAlphabeticPartToKana(text, sourceMap, sourceMapStart) {
- const result = wanakana.toHiragana(text);
-
- // Generate source mapping
- if (sourceMap !== null) {
- let i = 0;
- let resultPos = 0;
- const ii = text.length;
- while (i < ii) {
- // Find smallest matching substring
- let iNext = i + 1;
- let resultPosNext = result.length;
- while (iNext < ii) {
- const t = wanakana.toHiragana(text.substring(0, iNext));
- if (t === result.substring(0, t.length)) {
- resultPosNext = t.length;
- break;
- }
- ++iNext;
- }
-
- // Merge characters
- const removals = iNext - i - 1;
- if (removals > 0) {
- sourceMap.combine(sourceMapStart, removals);
- }
- ++sourceMapStart;
-
- // Empty elements
- const additions = resultPosNext - resultPos - 1;
- for (let j = 0; j < additions; ++j) {
- sourceMap.insert(sourceMapStart, 0);
- ++sourceMapStart;
- }
-
- i = iNext;
- resultPos = resultPosNext;
- }
- }
-
- return result;
+function convertAlphabeticPartToKana(text) {
+ return wanakana.toHiragana(text);
}
/**
@@ -84,10 +43,9 @@ export function convertToRomaji(text) {
/**
* @param {string} text
- * @param {?import('../../general/text-source-map.js').TextSourceMap} sourceMap
* @returns {string}
*/
-export function convertAlphabeticToKana(text, sourceMap = null) {
+export function convertAlphabeticToKana(text) {
let part = '';
let result = '';
@@ -106,7 +64,7 @@ export function convertAlphabeticToKana(text, sourceMap = null) {
c = 0x2d; // '-'
} else {
if (part.length > 0) {
- result += convertAlphabeticPartToKana(part, sourceMap, result.length);
+ result += convertAlphabeticPartToKana(part);
part = '';
}
result += char;
@@ -116,7 +74,7 @@ export function convertAlphabeticToKana(text, sourceMap = null) {
}
if (part.length > 0) {
- result += convertAlphabeticPartToKana(part, sourceMap, result.length);
+ result += convertAlphabeticPartToKana(part);
}
return result;
}
diff --git a/ext/js/language/ja/japanese.js b/ext/js/language/ja/japanese.js
index 2c9a1f7f..3507e5df 100644
--- a/ext/js/language/ja/japanese.js
+++ b/ext/js/language/ja/japanese.js
@@ -539,10 +539,9 @@ export function convertNumericToFullWidth(text) {
/**
* @param {string} text
- * @param {?import('../../general/text-source-map.js').TextSourceMap} [sourceMap]
* @returns {string}
*/
-export function convertHalfWidthKanaToFullWidth(text, sourceMap = null) {
+export function convertHalfWidthKanaToFullWidth(text) {
let result = '';
// This function is safe to use charCodeAt instead of codePointAt, since all
@@ -575,9 +574,6 @@ export function convertHalfWidthKanaToFullWidth(text, sourceMap = null) {
}
}
- if (sourceMap !== null && index > 0) {
- sourceMap.combine(result.length, 1);
- }
result += c2;
}
@@ -705,13 +701,11 @@ export function distributeFuriganaInflected(term, reading, source) {
/**
* @param {string} text
* @param {boolean} fullCollapse
- * @param {?import('../../general/text-source-map.js').TextSourceMap} [sourceMap]
* @returns {string}
*/
-export function collapseEmphaticSequences(text, fullCollapse, sourceMap = null) {
+export function collapseEmphaticSequences(text, fullCollapse) {
let result = '';
let collapseCodePoint = -1;
- const hasSourceMap = (sourceMap !== null);
for (const char of text) {
const c = char.codePointAt(0);
if (
@@ -729,11 +723,6 @@ export function collapseEmphaticSequences(text, fullCollapse, sourceMap = null)
} else {
collapseCodePoint = -1;
result += char;
- continue;
- }
-
- if (hasSourceMap) {
- sourceMap.combine(Math.max(0, result.length - 1), 1);
}
}
return result;