Fix incorrect furigana distribution (#1514)

* Improve distributeFuriganaInflected implementation

* Update tests

ext/js/language/japanese-util.js

@@ -466,27 +466,55 @@ const JapaneseUtil = (() => {
         }
 
         distributeFuriganaInflected(expression, reading, source) {
-            let stemLength = 0;
+            const expressionNormalized = this.convertKatakanaToHiragana(expression);
-            const shortest = Math.min(source.length, expression.length);
+            const readingNormalized = this.convertKatakanaToHiragana(reading);
-            const sourceHiragana = this.convertKatakanaToHiragana(source);
+            const sourceNormalized = this.convertKatakanaToHiragana(source);
-            const expressionHiragana = this.convertKatakanaToHiragana(expression);
-            while (stemLength < shortest && sourceHiragana[stemLength] === expressionHiragana[stemLength]) {
-                ++stemLength;
-            }
-            const offset = source.length - stemLength;
 
-            const stemExpression = source.substring(0, source.length - offset);
+            let mainText = expression;
-            const stemReading = reading.substring(
+            let stemLength = this._getStemLength(expressionNormalized, sourceNormalized);
-                0,
-                offset === 0 ? reading.length : reading.length - expression.length + stemLength
-            );
-            const result = this.distributeFurigana(stemExpression, stemReading);
 
-            if (stemLength !== source.length) {
+            // Check if source is derived from the reading instead of the expression
-                result.push(this._createFuriganaSegment(source.substring(stemLength), ''));
+            const readingStemLength = this._getStemLength(readingNormalized, sourceNormalized);
+            if (readingStemLength > stemLength) {
+                mainText = reading;
+                stemLength = readingStemLength;
             }
 
-            return result;
+            const segments = [];
+            if (stemLength > 0) {
+                const segments2 = this.distributeFurigana(mainText, reading);
+                let consumed = 0;
+                for (const segment of segments2) {
+                    const {text} = segment;
+                    const start = consumed;
+                    consumed += text.length;
+                    if (consumed < stemLength) {
+                        segments.push(segment);
+                    } else if (consumed === stemLength) {
+                        segments.push(segment);
+                        break;
+                    } else {
+                        if (start < stemLength) {
+                            segments.push(this._createFuriganaSegment(mainText.substring(start, stemLength), ''));
+                        }
+                        break;
+                    }
+                }
+            }
+
+            if (stemLength < source.length) {
+                const remainder = source.substring(stemLength);
+                const segmentCount = segments.length;
+                if (segmentCount > 0 && segments[segmentCount - 1].furigana.length === 0) {
+                    // Append to the last segment if it has an empty reading
+                    segments[segmentCount - 1].text += remainder;
+                } else {
+                    // Otherwise, create a new segment
+                    segments.push(this._createFuriganaSegment(remainder, ''));
+                }
+            }
+
+            return segments;
         }
 
         // Miscellaneous
@@ -648,6 +676,27 @@ const JapaneseUtil = (() => {
 
             return result;
         }
+
+        _getStemLength(text1, text2) {
+            const minLength = Math.min(text1.length, text2.length);
+            if (minLength === 0) { return 0; }
+
+            let i = 0;
+            while (true) {
+                const char1 = text1.codePointAt(i);
+                const char2 = text2.codePointAt(i);
+                if (char1 !== char2) { break; }
+                const charLength = String.fromCodePoint(char1).length;
+                i += charLength;
+                if (i >= minLength) {
+                    if (i > minLength) {
+                        i -= charLength; // Don't consume partial UTF16 surrogate characters
+                    }
+                    break;
+                }
+            }
+            return i;
+        }
     }
 
 

test/test-japanese.js

@@ -729,16 +729,26 @@ function testDistributeFuriganaInflected() {
             ['美味しい', 'おいしい', '美味しかた'],
             [
                 {text: '美味', furigana: 'おい'},
-                {text: 'し', furigana: ''},
+                {text: 'しかた', furigana: ''}
-                {text: 'かた', furigana: ''}
             ]
         ],
         [
             ['食べる', 'たべる', '食べた'],
             [
                 {text: '食', furigana: 'た'},
-                {text: 'べ', furigana: ''},
+                {text: 'べた', furigana: ''}
-                {text: 'た', furigana: ''}
+            ]
+        ],
+        [
+            ['迄に', 'までに', 'までに'],
+            [
+                {text: 'までに', furigana: ''}
+            ]
+        ],
+        [
+            ['行う', 'おこなう', 'おこなわなかった'],
+            [
+                {text: 'おこなわなかった', furigana: ''}
             ]
         ]
     ];