From 07258ecc35c1a05aa1581a54c9f47a40ce3d76c9 Mon Sep 17 00:00:00 2001 From: StefanVukovic99 Date: Sun, 21 Apr 2024 17:15:08 +0200 Subject: rework text processors (#793) * rework text processors * rename text-preprocessors file * Fix search header left margins on small screens (#839) * Refocuses search input on backspace (#840) Fixes #775. Note that this behavior gets overridden if backspace is set as a shortcut action. * Change hotkey triggering condition to account for IME usage (#837) _isKeyCharacterInput only worked when not using an IME, as inside of an IME when a keydown event is fired, the key is reported as "Process", which does not have a key.length equal to 1. This resulted in hotkeys being triggered while typing, which this commit fixes. --------- Co-authored-by: James Maa Co-authored-by: Kuuuube <61125188+Kuuuube@users.noreply.github.com> Co-authored-by: Andrew Thomas Sartor --- ext/js/language/ja/japanese-text-preprocessors.js | 24 +++++------ ext/js/language/ja/japanese-wanakana.js | 52 +++-------------------- ext/js/language/ja/japanese.js | 15 +------ 3 files changed, 19 insertions(+), 72 deletions(-) (limited to 'ext/js/language/ja') 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 . */ -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} */ +/** @type {import('language').TextProcessor} */ 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} */ +/** @type {import('language').TextProcessor} */ 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} */ +/** @type {import('language').TextProcessor} */ 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; -- cgit v1.2.3