diff options
-rw-r--r-- | ext/js/background/backend.js | 12 | ||||
-rw-r--r-- | ext/js/data/anki-note-data-creator.js | 6 | ||||
-rw-r--r-- | ext/js/display/display-generator.js | 6 | ||||
-rw-r--r-- | ext/js/language/japanese-util.js | 10 | ||||
-rw-r--r-- | ext/js/templates/template-renderer.js | 16 | ||||
-rw-r--r-- | test/test-japanese.js | 324 |
6 files changed, 189 insertions, 185 deletions
diff --git a/ext/js/background/backend.js b/ext/js/background/backend.js index 21b18e99..84ff2c0d 100644 --- a/ext/js/background/backend.js +++ b/ext/js/background/backend.js @@ -1066,9 +1066,9 @@ class Backend { const {headwords: [{term, reading}]} = dictionaryEntries[0]; const source = text.substring(i, i + originalTextLength); const textSegments = []; - for (const {text: text2, furigana} of jp.distributeFuriganaInflected(term, reading, source)) { - const reading2 = jp.convertReading(text2, furigana, readingMode); - textSegments.push({text: text2, reading: reading2}); + for (const {text: text2, reading: reading2} of jp.distributeFuriganaInflected(term, reading, source)) { + const reading3 = jp.convertReading(text2, reading2, readingMode); + textSegments.push({text: text2, reading: reading3}); } results.push(textSegments); i += originalTextLength; @@ -1102,13 +1102,13 @@ class Backend { for (const line of lines) { for (const {term, reading, source} of line) { const termParts = []; - for (const {text: text2, furigana} of jp.distributeFuriganaInflected( + for (const {text: text2, reading: reading2} of jp.distributeFuriganaInflected( term.length > 0 ? term : source, jp.convertKatakanaToHiragana(reading), source )) { - const reading2 = jp.convertReading(text2, furigana, readingMode); - termParts.push({text: text2, reading: reading2}); + const reading3 = jp.convertReading(text2, reading2, readingMode); + termParts.push({text: text2, reading: reading3}); } result.push(termParts); } diff --git a/ext/js/data/anki-note-data-creator.js b/ext/js/data/anki-note-data-creator.js index 1c32c4b4..e3ff2ca0 100644 --- a/ext/js/data/anki-note-data-creator.js +++ b/ext/js/data/anki-note-data-creator.js @@ -596,6 +596,10 @@ class AnkiNoteDataCreator { } _getTermHeadwordFuriganaSegments(term, reading) { - return this._japaneseUtil.distributeFurigana(term, reading); + const result = []; + for (const {text, reading: reading2} of this._japaneseUtil.distributeFurigana(term, reading)) { + result.push({text, furigana: reading2}); + } + return result; } } diff --git a/ext/js/display/display-generator.js b/ext/js/display/display-generator.js index 61c93b4a..9a90502e 100644 --- a/ext/js/display/display-generator.js +++ b/ext/js/display/display-generator.js @@ -715,13 +715,13 @@ class DisplayGenerator { _appendFurigana(container, term, reading, addText) { container.lang = 'ja'; const segments = this._japaneseUtil.distributeFurigana(term, reading); - for (const {text, furigana} of segments) { - if (furigana) { + for (const {text, reading: reading2} of segments) { + if (reading2) { const ruby = document.createElement('ruby'); const rt = document.createElement('rt'); addText(ruby, text); ruby.appendChild(rt); - rt.appendChild(document.createTextNode(furigana)); + rt.appendChild(document.createTextNode(reading2)); container.appendChild(ruby); } else { addText(container, text); diff --git a/ext/js/language/japanese-util.js b/ext/js/language/japanese-util.js index 4d5e8092..8780c24c 100644 --- a/ext/js/language/japanese-util.js +++ b/ext/js/language/japanese-util.js @@ -507,7 +507,7 @@ const JapaneseUtil = (() => { if (stemLength < source.length) { const remainder = source.substring(stemLength); const segmentCount = segments.length; - if (segmentCount > 0 && segments[segmentCount - 1].furigana.length === 0) { + if (segmentCount > 0 && segments[segmentCount - 1].reading.length === 0) { // Append to the last segment if it has an empty reading segments[segmentCount - 1].text += remainder; } else { @@ -554,8 +554,8 @@ const JapaneseUtil = (() => { // Private - _createFuriganaSegment(text, furigana) { - return {text, furigana}; + _createFuriganaSegment(text, reading) { + return {text, reading}; } _segmentizeFurigana(reading, readingNormalized, groups, groupsStart) { @@ -600,8 +600,8 @@ const JapaneseUtil = (() => { // More than one way to segmentize the tail; mark as ambiguous return null; } - const furigana = reading.substring(0, i); - segments.unshift(this._createFuriganaSegment(text, furigana)); + const segmentReading = reading.substring(0, i); + segments.unshift(this._createFuriganaSegment(text, segmentReading)); result = segments; } // There is only one way to segmentize the last non-kana group diff --git a/ext/js/templates/template-renderer.js b/ext/js/templates/template-renderer.js index ed9cc41c..9bb7a414 100644 --- a/ext/js/templates/template-renderer.js +++ b/ext/js/templates/template-renderer.js @@ -177,11 +177,11 @@ class TemplateRenderer { const segs = this._japaneseUtil.distributeFurigana(expression, reading); let result = ''; - for (const seg of segs) { - if (seg.furigana.length > 0) { - result += `<ruby>${seg.text}<rt>${seg.furigana}</rt></ruby>`; + for (const {text, reading: reading2} of segs) { + if (reading2.length > 0) { + result += `<ruby>${text}<rt>${reading2}</rt></ruby>`; } else { - result += seg.text; + result += text; } } @@ -193,12 +193,12 @@ class TemplateRenderer { const segs = this._japaneseUtil.distributeFurigana(expression, reading); let result = ''; - for (const seg of segs) { - if (seg.furigana.length > 0) { + for (const {text, reading: reading2} of segs) { + if (reading2.length > 0) { if (result.length > 0) { result += ' '; } - result += `${seg.text}[${seg.furigana}]`; + result += `${text}[${reading2}]`; } else { - result += seg.text; + result += text; } } diff --git a/test/test-japanese.js b/test/test-japanese.js index 2772e984..9452a1d1 100644 --- a/test/test-japanese.js +++ b/test/test-japanese.js @@ -278,441 +278,441 @@ function testDistributeFurigana() { [ ['有り難う', 'ありがとう'], [ - {text: '有', furigana: 'あ'}, - {text: 'り', furigana: ''}, - {text: '難', furigana: 'がと'}, - {text: 'う', furigana: ''} + {text: '有', reading: 'あ'}, + {text: 'り', reading: ''}, + {text: '難', reading: 'がと'}, + {text: 'う', reading: ''} ] ], [ ['方々', 'かたがた'], [ - {text: '方々', furigana: 'かたがた'} + {text: '方々', reading: 'かたがた'} ] ], [ ['お祝い', 'おいわい'], [ - {text: 'お', furigana: ''}, - {text: '祝', furigana: 'いわ'}, - {text: 'い', furigana: ''} + {text: 'お', reading: ''}, + {text: '祝', reading: 'いわ'}, + {text: 'い', reading: ''} ] ], [ ['美味しい', 'おいしい'], [ - {text: '美味', furigana: 'おい'}, - {text: 'しい', furigana: ''} + {text: '美味', reading: 'おい'}, + {text: 'しい', reading: ''} ] ], [ ['食べ物', 'たべもの'], [ - {text: '食', furigana: 'た'}, - {text: 'べ', furigana: ''}, - {text: '物', furigana: 'もの'} + {text: '食', reading: 'た'}, + {text: 'べ', reading: ''}, + {text: '物', reading: 'もの'} ] ], [ ['試し切り', 'ためしぎり'], [ - {text: '試', furigana: 'ため'}, - {text: 'し', furigana: ''}, - {text: '切', furigana: 'ぎ'}, - {text: 'り', furigana: ''} + {text: '試', reading: 'ため'}, + {text: 'し', reading: ''}, + {text: '切', reading: 'ぎ'}, + {text: 'り', reading: ''} ] ], // Ambiguous [ ['飼い犬', 'かいいぬ'], [ - {text: '飼い犬', furigana: 'かいいぬ'} + {text: '飼い犬', reading: 'かいいぬ'} ] ], [ ['長い間', 'ながいあいだ'], [ - {text: '長い間', furigana: 'ながいあいだ'} + {text: '長い間', reading: 'ながいあいだ'} ] ], // Same/empty reading [ ['飼い犬', ''], [ - {text: '飼い犬', furigana: ''} + {text: '飼い犬', reading: ''} ] ], [ ['かいいぬ', 'かいいぬ'], [ - {text: 'かいいぬ', furigana: ''} + {text: 'かいいぬ', reading: ''} ] ], [ ['かいぬ', 'かいぬ'], [ - {text: 'かいぬ', furigana: ''} + {text: 'かいぬ', reading: ''} ] ], // Misc [ ['月', 'か'], [ - {text: '月', furigana: 'か'} + {text: '月', reading: 'か'} ] ], [ ['月', 'カ'], [ - {text: '月', furigana: 'カ'} + {text: '月', reading: 'カ'} ] ], // Mismatched kana readings [ ['有り難う', 'アリガトウ'], [ - {text: '有', furigana: 'ア'}, - {text: 'り', furigana: 'リ'}, - {text: '難', furigana: 'ガト'}, - {text: 'う', furigana: 'ウ'} + {text: '有', reading: 'ア'}, + {text: 'り', reading: 'リ'}, + {text: '難', reading: 'ガト'}, + {text: 'う', reading: 'ウ'} ] ], [ ['ありがとう', 'アリガトウ'], [ - {text: 'ありがとう', furigana: 'アリガトウ'} + {text: 'ありがとう', reading: 'アリガトウ'} ] ], // Mismatched kana readings (real examples) [ ['カ月', 'かげつ'], [ - {text: 'カ', furigana: 'か'}, - {text: '月', furigana: 'げつ'} + {text: 'カ', reading: 'か'}, + {text: '月', reading: 'げつ'} ] ], [ ['序ノ口', 'じょのくち'], [ - {text: '序', furigana: 'じょ'}, - {text: 'ノ', furigana: 'の'}, - {text: '口', furigana: 'くち'} + {text: '序', reading: 'じょ'}, + {text: 'ノ', reading: 'の'}, + {text: '口', reading: 'くち'} ] ], [ ['スズメの涙', 'すずめのなみだ'], [ - {text: 'スズメ', furigana: 'すずめ'}, - {text: 'の', furigana: ''}, - {text: '涙', furigana: 'なみだ'} + {text: 'スズメ', reading: 'すずめ'}, + {text: 'の', reading: ''}, + {text: '涙', reading: 'なみだ'} ] ], [ ['二カ所', 'にかしょ'], [ - {text: '二', furigana: 'に'}, - {text: 'カ', furigana: 'か'}, - {text: '所', furigana: 'しょ'} + {text: '二', reading: 'に'}, + {text: 'カ', reading: 'か'}, + {text: '所', reading: 'しょ'} ] ], [ ['八ツ橋', 'やつはし'], [ - {text: '八', furigana: 'や'}, - {text: 'ツ', furigana: 'つ'}, - {text: '橋', furigana: 'はし'} + {text: '八', reading: 'や'}, + {text: 'ツ', reading: 'つ'}, + {text: '橋', reading: 'はし'} ] ], [ ['八ツ橋', 'やつはし'], [ - {text: '八', furigana: 'や'}, - {text: 'ツ', furigana: 'つ'}, - {text: '橋', furigana: 'はし'} + {text: '八', reading: 'や'}, + {text: 'ツ', reading: 'つ'}, + {text: '橋', reading: 'はし'} ] ], [ ['一カ月', 'いっかげつ'], [ - {text: '一', furigana: 'いっ'}, - {text: 'カ', furigana: 'か'}, - {text: '月', furigana: 'げつ'} + {text: '一', reading: 'いっ'}, + {text: 'カ', reading: 'か'}, + {text: '月', reading: 'げつ'} ] ], [ ['一カ所', 'いっかしょ'], [ - {text: '一', furigana: 'いっ'}, - {text: 'カ', furigana: 'か'}, - {text: '所', furigana: 'しょ'} + {text: '一', reading: 'いっ'}, + {text: 'カ', reading: 'か'}, + {text: '所', reading: 'しょ'} ] ], [ ['カ所', 'かしょ'], [ - {text: 'カ', furigana: 'か'}, - {text: '所', furigana: 'しょ'} + {text: 'カ', reading: 'か'}, + {text: '所', reading: 'しょ'} ] ], [ ['数カ月', 'すうかげつ'], [ - {text: '数', furigana: 'すう'}, - {text: 'カ', furigana: 'か'}, - {text: '月', furigana: 'げつ'} + {text: '数', reading: 'すう'}, + {text: 'カ', reading: 'か'}, + {text: '月', reading: 'げつ'} ] ], [ ['くノ一', 'くのいち'], [ - {text: 'く', furigana: ''}, - {text: 'ノ', furigana: 'の'}, - {text: '一', furigana: 'いち'} + {text: 'く', reading: ''}, + {text: 'ノ', reading: 'の'}, + {text: '一', reading: 'いち'} ] ], [ ['くノ一', 'くのいち'], [ - {text: 'く', furigana: ''}, - {text: 'ノ', furigana: 'の'}, - {text: '一', furigana: 'いち'} + {text: 'く', reading: ''}, + {text: 'ノ', reading: 'の'}, + {text: '一', reading: 'いち'} ] ], [ ['数カ国', 'すうかこく'], [ - {text: '数', furigana: 'すう'}, - {text: 'カ', furigana: 'か'}, - {text: '国', furigana: 'こく'} + {text: '数', reading: 'すう'}, + {text: 'カ', reading: 'か'}, + {text: '国', reading: 'こく'} ] ], [ ['数カ所', 'すうかしょ'], [ - {text: '数', furigana: 'すう'}, - {text: 'カ', furigana: 'か'}, - {text: '所', furigana: 'しょ'} + {text: '数', reading: 'すう'}, + {text: 'カ', reading: 'か'}, + {text: '所', reading: 'しょ'} ] ], [ ['壇ノ浦の戦い', 'だんのうらのたたかい'], [ - {text: '壇', furigana: 'だん'}, - {text: 'ノ', furigana: 'の'}, - {text: '浦', furigana: 'うら'}, - {text: 'の', furigana: ''}, - {text: '戦', furigana: 'たたか'}, - {text: 'い', furigana: ''} + {text: '壇', reading: 'だん'}, + {text: 'ノ', reading: 'の'}, + {text: '浦', reading: 'うら'}, + {text: 'の', reading: ''}, + {text: '戦', reading: 'たたか'}, + {text: 'い', reading: ''} ] ], [ ['壇ノ浦の戦', 'だんのうらのたたかい'], [ - {text: '壇', furigana: 'だん'}, - {text: 'ノ', furigana: 'の'}, - {text: '浦', furigana: 'うら'}, - {text: 'の', furigana: ''}, - {text: '戦', furigana: 'たたかい'} + {text: '壇', reading: 'だん'}, + {text: 'ノ', reading: 'の'}, + {text: '浦', reading: 'うら'}, + {text: 'の', reading: ''}, + {text: '戦', reading: 'たたかい'} ] ], [ ['序ノ口格', 'じょのくちかく'], [ - {text: '序', furigana: 'じょ'}, - {text: 'ノ', furigana: 'の'}, - {text: '口格', furigana: 'くちかく'} + {text: '序', reading: 'じょ'}, + {text: 'ノ', reading: 'の'}, + {text: '口格', reading: 'くちかく'} ] ], [ ['二カ国語', 'にかこくご'], [ - {text: '二', furigana: 'に'}, - {text: 'カ', furigana: 'か'}, - {text: '国語', furigana: 'こくご'} + {text: '二', reading: 'に'}, + {text: 'カ', reading: 'か'}, + {text: '国語', reading: 'こくご'} ] ], [ ['カ国', 'かこく'], [ - {text: 'カ', furigana: 'か'}, - {text: '国', furigana: 'こく'} + {text: 'カ', reading: 'か'}, + {text: '国', reading: 'こく'} ] ], [ ['カ国語', 'かこくご'], [ - {text: 'カ', furigana: 'か'}, - {text: '国語', furigana: 'こくご'} + {text: 'カ', reading: 'か'}, + {text: '国語', reading: 'こくご'} ] ], [ ['壇ノ浦の合戦', 'だんのうらのかっせん'], [ - {text: '壇', furigana: 'だん'}, - {text: 'ノ', furigana: 'の'}, - {text: '浦', furigana: 'うら'}, - {text: 'の', furigana: ''}, - {text: '合戦', furigana: 'かっせん'} + {text: '壇', reading: 'だん'}, + {text: 'ノ', reading: 'の'}, + {text: '浦', reading: 'うら'}, + {text: 'の', reading: ''}, + {text: '合戦', reading: 'かっせん'} ] ], [ ['一タ偏', 'いちたへん'], [ - {text: '一', furigana: 'いち'}, - {text: 'タ', furigana: 'た'}, - {text: '偏', furigana: 'へん'} + {text: '一', reading: 'いち'}, + {text: 'タ', reading: 'た'}, + {text: '偏', reading: 'へん'} ] ], [ ['ル又', 'るまた'], [ - {text: 'ル', furigana: 'る'}, - {text: '又', furigana: 'また'} + {text: 'ル', reading: 'る'}, + {text: '又', reading: 'また'} ] ], [ ['ノ木偏', 'のぎへん'], [ - {text: 'ノ', furigana: 'の'}, - {text: '木偏', furigana: 'ぎへん'} + {text: 'ノ', reading: 'の'}, + {text: '木偏', reading: 'ぎへん'} ] ], [ ['一ノ貝', 'いちのかい'], [ - {text: '一', furigana: 'いち'}, - {text: 'ノ', furigana: 'の'}, - {text: '貝', furigana: 'かい'} + {text: '一', reading: 'いち'}, + {text: 'ノ', reading: 'の'}, + {text: '貝', reading: 'かい'} ] ], [ ['虎ノ門事件', 'とらのもんじけん'], [ - {text: '虎', furigana: 'とら'}, - {text: 'ノ', furigana: 'の'}, - {text: '門事件', furigana: 'もんじけん'} + {text: '虎', reading: 'とら'}, + {text: 'ノ', reading: 'の'}, + {text: '門事件', reading: 'もんじけん'} ] ], [ ['教育ニ関スル勅語', 'きょういくにかんするちょくご'], [ - {text: '教育', furigana: 'きょういく'}, - {text: 'ニ', furigana: 'に'}, - {text: '関', furigana: 'かん'}, - {text: 'スル', furigana: 'する'}, - {text: '勅語', furigana: 'ちょくご'} + {text: '教育', reading: 'きょういく'}, + {text: 'ニ', reading: 'に'}, + {text: '関', reading: 'かん'}, + {text: 'スル', reading: 'する'}, + {text: '勅語', reading: 'ちょくご'} ] ], [ ['二カ年', 'にかねん'], [ - {text: '二', furigana: 'に'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '二', reading: 'に'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['三カ年', 'さんかねん'], [ - {text: '三', furigana: 'さん'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '三', reading: 'さん'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['四カ年', 'よんかねん'], [ - {text: '四', furigana: 'よん'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '四', reading: 'よん'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['五カ年', 'ごかねん'], [ - {text: '五', furigana: 'ご'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '五', reading: 'ご'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['六カ年', 'ろっかねん'], [ - {text: '六', furigana: 'ろっ'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '六', reading: 'ろっ'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['七カ年', 'ななかねん'], [ - {text: '七', furigana: 'なな'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '七', reading: 'なな'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['八カ年', 'はちかねん'], [ - {text: '八', furigana: 'はち'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '八', reading: 'はち'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['九カ年', 'きゅうかねん'], [ - {text: '九', furigana: 'きゅう'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '九', reading: 'きゅう'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['十カ年', 'じゅうかねん'], [ - {text: '十', furigana: 'じゅう'}, - {text: 'カ', furigana: 'か'}, - {text: '年', furigana: 'ねん'} + {text: '十', reading: 'じゅう'}, + {text: 'カ', reading: 'か'}, + {text: '年', reading: 'ねん'} ] ], [ ['鏡ノ間', 'かがみのま'], [ - {text: '鏡', furigana: 'かがみ'}, - {text: 'ノ', furigana: 'の'}, - {text: '間', furigana: 'ま'} + {text: '鏡', reading: 'かがみ'}, + {text: 'ノ', reading: 'の'}, + {text: '間', reading: 'ま'} ] ], [ ['鏡ノ間', 'かがみのま'], [ - {text: '鏡', furigana: 'かがみ'}, - {text: 'ノ', furigana: 'の'}, - {text: '間', furigana: 'ま'} + {text: '鏡', reading: 'かがみ'}, + {text: 'ノ', reading: 'の'}, + {text: '間', reading: 'ま'} ] ], [ ['ページ違反', 'ぺーじいはん'], [ - {text: 'ペ', furigana: 'ぺ'}, - {text: 'ー', furigana: ''}, - {text: 'ジ', furigana: 'じ'}, - {text: '違反', furigana: 'いはん'} + {text: 'ペ', reading: 'ぺ'}, + {text: 'ー', reading: ''}, + {text: 'ジ', reading: 'じ'}, + {text: '違反', reading: 'いはん'} ] ], // Mismatched kana [ ['サボる', 'サボル'], [ - {text: 'サボ', furigana: ''}, - {text: 'る', furigana: 'ル'} + {text: 'サボ', reading: ''}, + {text: 'る', reading: 'ル'} ] ], // Reading starts with term, but has remainder characters [ ['シック', 'シック・ビルしょうこうぐん'], [ - {text: 'シック', furigana: 'シック・ビルしょうこうぐん'} + {text: 'シック', reading: 'シック・ビルしょうこうぐん'} ] ] ]; @@ -728,40 +728,40 @@ function testDistributeFuriganaInflected() { [ ['美味しい', 'おいしい', '美味しかた'], [ - {text: '美味', furigana: 'おい'}, - {text: 'しかた', furigana: ''} + {text: '美味', reading: 'おい'}, + {text: 'しかた', reading: ''} ] ], [ ['食べる', 'たべる', '食べた'], [ - {text: '食', furigana: 'た'}, - {text: 'べた', furigana: ''} + {text: '食', reading: 'た'}, + {text: 'べた', reading: ''} ] ], [ ['迄に', 'までに', 'までに'], [ - {text: 'までに', furigana: ''} + {text: 'までに', reading: ''} ] ], [ ['行う', 'おこなう', 'おこなわなかった'], [ - {text: 'おこなわなかった', furigana: ''} + {text: 'おこなわなかった', reading: ''} ] ], [ ['いい', 'いい', 'イイ'], [ - {text: 'イイ', furigana: ''} + {text: 'イイ', reading: ''} ] ], [ ['否か', 'いなか', '否カ'], [ - {text: '否', furigana: 'いな'}, - {text: 'カ', furigana: 'か'} + {text: '否', reading: 'いな'}, + {text: 'カ', reading: 'か'} ] ] ]; |