aboutsummaryrefslogtreecommitdiff
path: root/ext/js/language/sandbox
diff options
context:
space:
mode:
Diffstat (limited to 'ext/js/language/sandbox')
-rw-r--r--ext/js/language/sandbox/dictionary-data-util.js161
-rw-r--r--ext/js/language/sandbox/japanese-util.js1371
2 files changed, 895 insertions, 637 deletions
diff --git a/ext/js/language/sandbox/dictionary-data-util.js b/ext/js/language/sandbox/dictionary-data-util.js
index 1b71346a..a54b043b 100644
--- a/ext/js/language/sandbox/dictionary-data-util.js
+++ b/ext/js/language/sandbox/dictionary-data-util.js
@@ -17,6 +17,10 @@
*/
export class DictionaryDataUtil {
+ /**
+ * @param {import('dictionary').TermDictionaryEntry} dictionaryEntry
+ * @returns {import('dictionary-data-util').TagGroup[]}
+ */
static groupTermTags(dictionaryEntry) {
const {headwords} = dictionaryEntry;
const headwordCount = headwords.length;
@@ -27,8 +31,8 @@ export class DictionaryDataUtil {
const {tags} = headwords[i];
for (const tag of tags) {
if (uniqueCheck) {
- const {name, category, notes, dictionary} = tag;
- const key = this._createMapKey([name, category, notes, dictionary]);
+ const {name, category, content, dictionaries} = tag;
+ const key = this._createMapKey([name, category, content, dictionaries]);
const index = resultsIndexMap.get(key);
if (typeof index !== 'undefined') {
const existingItem = results[index];
@@ -45,11 +49,16 @@ export class DictionaryDataUtil {
return results;
}
+ /**
+ * @param {import('dictionary').TermDictionaryEntry} dictionaryEntry
+ * @returns {import('dictionary-data-util').DictionaryFrequency<import('dictionary-data-util').TermFrequency>[]}
+ */
static groupTermFrequencies(dictionaryEntry) {
- const {headwords, frequencies} = dictionaryEntry;
+ const {headwords, frequencies: sourceFrequencies} = dictionaryEntry;
+ /** @type {import('dictionary-data-util').TermFrequenciesMap1} */
const map1 = new Map();
- for (const {headwordIndex, dictionary, hasReading, frequency, displayValue} of frequencies) {
+ for (const {headwordIndex, dictionary, hasReading, frequency, displayValue} of sourceFrequencies) {
const {term, reading} = headwords[headwordIndex];
let map2 = map1.get(dictionary);
@@ -68,12 +77,30 @@ export class DictionaryDataUtil {
frequencyData.values.set(this._createMapKey([frequency, displayValue]), {frequency, displayValue});
}
- return this._createFrequencyGroupsFromMap(map1);
+
+ const results = [];
+ for (const [dictionary, map2] of map1.entries()) {
+ const frequencies = [];
+ for (const {term, reading, values} of map2.values()) {
+ frequencies.push({
+ term,
+ reading,
+ values: [...values.values()]
+ });
+ }
+ results.push({dictionary, frequencies});
+ }
+ return results;
}
- static groupKanjiFrequencies(frequencies) {
+ /**
+ * @param {import('dictionary').KanjiFrequency[]} sourceFrequencies
+ * @returns {import('dictionary-data-util').DictionaryFrequency<import('dictionary-data-util').KanjiFrequency>[]}
+ */
+ static groupKanjiFrequencies(sourceFrequencies) {
+ /** @type {import('dictionary-data-util').KanjiFrequenciesMap1} */
const map1 = new Map();
- for (const {dictionary, character, frequency, displayValue} of frequencies) {
+ for (const {dictionary, character, frequency, displayValue} of sourceFrequencies) {
let map2 = map1.get(dictionary);
if (typeof map2 === 'undefined') {
map2 = new Map();
@@ -88,9 +115,25 @@ export class DictionaryDataUtil {
frequencyData.values.set(this._createMapKey([frequency, displayValue]), {frequency, displayValue});
}
- return this._createFrequencyGroupsFromMap(map1);
+
+ const results = [];
+ for (const [dictionary, map2] of map1.entries()) {
+ const frequencies = [];
+ for (const {character, values} of map2.values()) {
+ frequencies.push({
+ character,
+ values: [...values.values()]
+ });
+ }
+ results.push({dictionary, frequencies});
+ }
+ return results;
}
+ /**
+ * @param {import('dictionary').TermDictionaryEntry} dictionaryEntry
+ * @returns {import('dictionary-data-util').DictionaryGroupedPronunciations[]}
+ */
static getGroupedPronunciations(dictionaryEntry) {
const {headwords, pronunciations} = dictionaryEntry;
@@ -101,6 +144,7 @@ export class DictionaryDataUtil {
allReadings.add(reading);
}
+ /** @type {Map<string, import('dictionary-data-util').GroupedPronunciationInternal[]>} */
const groupedPronunciationsMap = new Map();
for (const {headwordIndex, dictionary, pitches} of pronunciations) {
const {term, reading} = headwords[headwordIndex];
@@ -118,9 +162,7 @@ export class DictionaryDataUtil {
position,
nasalPositions,
devoicePositions,
- tags,
- exclusiveTerms: [],
- exclusiveReadings: []
+ tags
};
dictionaryGroupedPronunciationList.push(groupedPronunciation);
}
@@ -128,27 +170,39 @@ export class DictionaryDataUtil {
}
}
+ /** @type {import('dictionary-data-util').DictionaryGroupedPronunciations[]} */
+ const results2 = [];
const multipleReadings = (allReadings.size > 1);
- for (const dictionaryGroupedPronunciationList of groupedPronunciationsMap.values()) {
+ for (const [dictionary, dictionaryGroupedPronunciationList] of groupedPronunciationsMap.entries()) {
+ /** @type {import('dictionary-data-util').GroupedPronunciation[]} */
+ const pronunciations2 = [];
for (const groupedPronunciation of dictionaryGroupedPronunciationList) {
- const {terms, reading, exclusiveTerms, exclusiveReadings} = groupedPronunciation;
- if (!this._areSetsEqual(terms, allTerms)) {
- exclusiveTerms.push(...this._getSetIntersection(terms, allTerms));
- }
+ const {terms, reading, position, nasalPositions, devoicePositions, tags} = groupedPronunciation;
+ const exclusiveTerms = !this._areSetsEqual(terms, allTerms) ? this._getSetIntersection(terms, allTerms) : [];
+ const exclusiveReadings = [];
if (multipleReadings) {
exclusiveReadings.push(reading);
}
- groupedPronunciation.terms = [...terms];
+ pronunciations2.push({
+ terms: [...terms],
+ reading,
+ position,
+ nasalPositions,
+ devoicePositions,
+ tags,
+ exclusiveTerms,
+ exclusiveReadings
+ });
}
- }
-
- const results2 = [];
- for (const [dictionary, pronunciations2] of groupedPronunciationsMap.entries()) {
results2.push({dictionary, pronunciations: pronunciations2});
}
return results2;
}
+ /**
+ * @param {import('dictionary').Tag[]|import('anki-templates').Tag[]} termTags
+ * @returns {import('dictionary-data-util').TermFrequencyType}
+ */
static getTermFrequency(termTags) {
let totalScore = 0;
for (const {score} of termTags) {
@@ -163,10 +217,19 @@ export class DictionaryDataUtil {
}
}
+ /**
+ * @param {import('dictionary').TermHeadword[]} headwords
+ * @param {number[]} headwordIndices
+ * @param {Set<string>} allTermsSet
+ * @param {Set<string>} allReadingsSet
+ * @returns {string[]}
+ */
static getDisambiguations(headwords, headwordIndices, allTermsSet, allReadingsSet) {
if (allTermsSet.size <= 1 && allReadingsSet.size <= 1) { return []; }
+ /** @type {Set<string>} */
const terms = new Set();
+ /** @type {Set<string>} */
const readings = new Set();
for (const headwordIndex of headwordIndices) {
const {term, reading} = headwords[headwordIndex];
@@ -174,6 +237,7 @@ export class DictionaryDataUtil {
readings.add(reading);
}
+ /** @type {string[]} */
const disambiguations = [];
const addTerms = !this._areSetsEqual(terms, allTermsSet);
const addReadings = !this._areSetsEqual(readings, allReadingsSet);
@@ -191,6 +255,10 @@ export class DictionaryDataUtil {
return disambiguations;
}
+ /**
+ * @param {string[]} wordClasses
+ * @returns {boolean}
+ */
static isNonNounVerbOrAdjective(wordClasses) {
let isVerbOrAdjective = false;
let isSuruVerb = false;
@@ -218,19 +286,15 @@ export class DictionaryDataUtil {
// Private
- static _createFrequencyGroupsFromMap(map) {
- const results = [];
- for (const [dictionary, map2] of map.entries()) {
- const frequencies = [];
- for (const frequencyData of map2.values()) {
- frequencyData.values = [...frequencyData.values.values()];
- frequencies.push(frequencyData);
- }
- results.push({dictionary, frequencies});
- }
- return results;
- }
-
+ /**
+ * @param {string} reading
+ * @param {number} position
+ * @param {number[]} nasalPositions
+ * @param {number[]} devoicePositions
+ * @param {import('dictionary').Tag[]} tags
+ * @param {import('dictionary-data-util').GroupedPronunciationInternal[]} groupedPronunciationList
+ * @returns {?import('dictionary-data-util').GroupedPronunciationInternal}
+ */
static _findExistingGroupedPronunciation(reading, position, nasalPositions, devoicePositions, tags, groupedPronunciationList) {
for (const pitchInfo of groupedPronunciationList) {
if (
@@ -246,6 +310,12 @@ export class DictionaryDataUtil {
return null;
}
+ /**
+ * @template [T=unknown]
+ * @param {T[]} array1
+ * @param {T[]} array2
+ * @returns {boolean}
+ */
static _areArraysEqual(array1, array2) {
const ii = array1.length;
if (ii !== array2.length) { return false; }
@@ -255,6 +325,11 @@ export class DictionaryDataUtil {
return true;
}
+ /**
+ * @param {import('dictionary').Tag[]} tagList1
+ * @param {import('dictionary').Tag[]} tagList2
+ * @returns {boolean}
+ */
static _areTagListsEqual(tagList1, tagList2) {
const ii = tagList1.length;
if (tagList2.length !== ii) { return false; }
@@ -262,7 +337,7 @@ export class DictionaryDataUtil {
for (let i = 0; i < ii; ++i) {
const tag1 = tagList1[i];
const tag2 = tagList2[i];
- if (tag1.name !== tag2.name || tag1.dictionary !== tag2.dictionary) {
+ if (tag1.name !== tag2.name || !this._areArraysEqual(tag1.dictionaries, tag2.dictionaries)) {
return false;
}
}
@@ -270,6 +345,12 @@ export class DictionaryDataUtil {
return true;
}
+ /**
+ * @template [T=unknown]
+ * @param {Set<T>} set1
+ * @param {Set<T>} set2
+ * @returns {boolean}
+ */
static _areSetsEqual(set1, set2) {
if (set1.size !== set2.size) {
return false;
@@ -284,6 +365,12 @@ export class DictionaryDataUtil {
return true;
}
+ /**
+ * @template [T=unknown]
+ * @param {Set<T>} set1
+ * @param {Set<T>} set2
+ * @returns {T[]}
+ */
static _getSetIntersection(set1, set2) {
const result = [];
for (const value of set1) {
@@ -294,6 +381,10 @@ export class DictionaryDataUtil {
return result;
}
+ /**
+ * @param {unknown[]} array
+ * @returns {string}
+ */
static _createMapKey(array) {
return JSON.stringify(array);
}
diff --git a/ext/js/language/sandbox/japanese-util.js b/ext/js/language/sandbox/japanese-util.js
index 316b1c2e..f7f20b3b 100644
--- a/ext/js/language/sandbox/japanese-util.js
+++ b/ext/js/language/sandbox/japanese-util.js
@@ -16,710 +16,877 @@
* along with this program. If not, see <https://www.gnu.org/licenses/>.
*/
-export const JapaneseUtil = (() => {
- const HIRAGANA_SMALL_TSU_CODE_POINT = 0x3063;
- const KATAKANA_SMALL_TSU_CODE_POINT = 0x30c3;
- const KATAKANA_SMALL_KA_CODE_POINT = 0x30f5;
- const KATAKANA_SMALL_KE_CODE_POINT = 0x30f6;
- const KANA_PROLONGED_SOUND_MARK_CODE_POINT = 0x30fc;
-
- const HIRAGANA_RANGE = [0x3040, 0x309f];
- const KATAKANA_RANGE = [0x30a0, 0x30ff];
-
- const HIRAGANA_CONVERSION_RANGE = [0x3041, 0x3096];
- const KATAKANA_CONVERSION_RANGE = [0x30a1, 0x30f6];
-
- const KANA_RANGES = [HIRAGANA_RANGE, KATAKANA_RANGE];
-
- const CJK_UNIFIED_IDEOGRAPHS_RANGE = [0x4e00, 0x9fff];
- const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A_RANGE = [0x3400, 0x4dbf];
- const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B_RANGE = [0x20000, 0x2a6df];
- const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C_RANGE = [0x2a700, 0x2b73f];
- const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D_RANGE = [0x2b740, 0x2b81f];
- const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E_RANGE = [0x2b820, 0x2ceaf];
- const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F_RANGE = [0x2ceb0, 0x2ebef];
- const CJK_COMPATIBILITY_IDEOGRAPHS_RANGE = [0xf900, 0xfaff];
- const CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT_RANGE = [0x2f800, 0x2fa1f];
- const CJK_IDEOGRAPH_RANGES = [
- CJK_UNIFIED_IDEOGRAPHS_RANGE,
- CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A_RANGE,
- CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B_RANGE,
- CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C_RANGE,
- CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D_RANGE,
- CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E_RANGE,
- CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F_RANGE,
- CJK_COMPATIBILITY_IDEOGRAPHS_RANGE,
- CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT_RANGE
- ];
-
- // Japanese character ranges, roughly ordered in order of expected frequency
- const JAPANESE_RANGES = [
- HIRAGANA_RANGE,
- KATAKANA_RANGE,
-
- ...CJK_IDEOGRAPH_RANGES,
-
- [0xff66, 0xff9f], // Halfwidth katakana
-
- [0x30fb, 0x30fc], // Katakana punctuation
- [0xff61, 0xff65], // Kana punctuation
- [0x3000, 0x303f], // CJK punctuation
-
- [0xff10, 0xff19], // Fullwidth numbers
- [0xff21, 0xff3a], // Fullwidth upper case Latin letters
- [0xff41, 0xff5a], // Fullwidth lower case Latin letters
-
- [0xff01, 0xff0f], // Fullwidth punctuation 1
- [0xff1a, 0xff1f], // Fullwidth punctuation 2
- [0xff3b, 0xff3f], // Fullwidth punctuation 3
- [0xff5b, 0xff60], // Fullwidth punctuation 4
- [0xffe0, 0xffee] // Currency markers
- ];
-
- const SMALL_KANA_SET = new Set(Array.from('ぁぃぅぇぉゃゅょゎァィゥェォャュョヮ'));
-
- const HALFWIDTH_KATAKANA_MAPPING = new Map([
- ['ヲ', 'ヲヺ-'],
- ['ァ', 'ァ--'],
- ['ィ', 'ィ--'],
- ['ゥ', 'ゥ--'],
- ['ェ', 'ェ--'],
- ['ォ', 'ォ--'],
- ['ャ', 'ャ--'],
- ['ュ', 'ュ--'],
- ['ョ', 'ョ--'],
- ['ッ', 'ッ--'],
- ['ー', 'ー--'],
- ['ア', 'ア--'],
- ['イ', 'イ--'],
- ['ウ', 'ウヴ-'],
- ['エ', 'エ--'],
- ['オ', 'オ--'],
- ['カ', 'カガ-'],
- ['キ', 'キギ-'],
- ['ク', 'クグ-'],
- ['ケ', 'ケゲ-'],
- ['コ', 'コゴ-'],
- ['サ', 'サザ-'],
- ['シ', 'シジ-'],
- ['ス', 'スズ-'],
- ['セ', 'セゼ-'],
- ['ソ', 'ソゾ-'],
- ['タ', 'タダ-'],
- ['チ', 'チヂ-'],
- ['ツ', 'ツヅ-'],
- ['テ', 'テデ-'],
- ['ト', 'トド-'],
- ['ナ', 'ナ--'],
- ['ニ', 'ニ--'],
- ['ヌ', 'ヌ--'],
- ['ネ', 'ネ--'],
- ['ノ', 'ノ--'],
- ['ハ', 'ハバパ'],
- ['ヒ', 'ヒビピ'],
- ['フ', 'フブプ'],
- ['ヘ', 'ヘベペ'],
- ['ホ', 'ホボポ'],
- ['マ', 'マ--'],
- ['ミ', 'ミ--'],
- ['ム', 'ム--'],
- ['メ', 'メ--'],
- ['モ', 'モ--'],
- ['ヤ', 'ヤ--'],
- ['ユ', 'ユ--'],
- ['ヨ', 'ヨ--'],
- ['ラ', 'ラ--'],
- ['リ', 'リ--'],
- ['ル', 'ル--'],
- ['レ', 'レ--'],
- ['ロ', 'ロ--'],
- ['ワ', 'ワ--'],
- ['ン', 'ン--']
- ]);
-
- const VOWEL_TO_KANA_MAPPING = new Map([
- ['a', 'ぁあかがさざただなはばぱまゃやらゎわヵァアカガサザタダナハバパマャヤラヮワヵヷ'],
- ['i', 'ぃいきぎしじちぢにひびぴみりゐィイキギシジチヂニヒビピミリヰヸ'],
- ['u', 'ぅうくぐすずっつづぬふぶぷむゅゆるゥウクグスズッツヅヌフブプムュユルヴ'],
- ['e', 'ぇえけげせぜてでねへべぺめれゑヶェエケゲセゼテデネヘベペメレヱヶヹ'],
- ['o', 'ぉおこごそぞとどのほぼぽもょよろをォオコゴソゾトドノホボポモョヨロヲヺ'],
- ['', 'のノ']
- ]);
-
- const KANA_TO_VOWEL_MAPPING = (() => {
- const map = new Map();
- for (const [vowel, characters] of VOWEL_TO_KANA_MAPPING) {
- for (const character of characters) {
- map.set(character, vowel);
- }
- }
- return map;
- })();
-
- const DIACRITIC_MAPPING = (() => {
- const kana = 'うゔ-かが-きぎ-くぐ-けげ-こご-さざ-しじ-すず-せぜ-そぞ-ただ-ちぢ-つづ-てで-とど-はばぱひびぴふぶぷへべぺほぼぽワヷ-ヰヸ-ウヴ-ヱヹ-ヲヺ-カガ-キギ-クグ-ケゲ-コゴ-サザ-シジ-スズ-セゼ-ソゾ-タダ-チヂ-ツヅ-テデ-トド-ハバパヒビピフブプヘベペホボポ';
- const map = new Map();
- for (let i = 0, ii = kana.length; i < ii; i += 3) {
- const character = kana[i];
- const dakuten = kana[i + 1];
- const handakuten = kana[i + 2];
- map.set(dakuten, {character, type: 'dakuten'});
- if (handakuten !== '-') {
- map.set(handakuten, {character, type: 'handakuten'});
- }
+const HIRAGANA_SMALL_TSU_CODE_POINT = 0x3063;
+const KATAKANA_SMALL_TSU_CODE_POINT = 0x30c3;
+const KATAKANA_SMALL_KA_CODE_POINT = 0x30f5;
+const KATAKANA_SMALL_KE_CODE_POINT = 0x30f6;
+const KANA_PROLONGED_SOUND_MARK_CODE_POINT = 0x30fc;
+
+/** @type {import('japanese-util').CodepointRange} */
+const HIRAGANA_RANGE = [0x3040, 0x309f];
+/** @type {import('japanese-util').CodepointRange} */
+const KATAKANA_RANGE = [0x30a0, 0x30ff];
+
+/** @type {import('japanese-util').CodepointRange} */
+const HIRAGANA_CONVERSION_RANGE = [0x3041, 0x3096];
+/** @type {import('japanese-util').CodepointRange} */
+const KATAKANA_CONVERSION_RANGE = [0x30a1, 0x30f6];
+
+/** @type {import('japanese-util').CodepointRange[]} */
+const KANA_RANGES = [HIRAGANA_RANGE, KATAKANA_RANGE];
+
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_UNIFIED_IDEOGRAPHS_RANGE = [0x4e00, 0x9fff];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A_RANGE = [0x3400, 0x4dbf];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B_RANGE = [0x20000, 0x2a6df];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C_RANGE = [0x2a700, 0x2b73f];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D_RANGE = [0x2b740, 0x2b81f];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E_RANGE = [0x2b820, 0x2ceaf];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F_RANGE = [0x2ceb0, 0x2ebef];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_COMPATIBILITY_IDEOGRAPHS_RANGE = [0xf900, 0xfaff];
+/** @type {import('japanese-util').CodepointRange} */
+const CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT_RANGE = [0x2f800, 0x2fa1f];
+/** @type {import('japanese-util').CodepointRange[]} */
+const CJK_IDEOGRAPH_RANGES = [
+ CJK_UNIFIED_IDEOGRAPHS_RANGE,
+ CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A_RANGE,
+ CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B_RANGE,
+ CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C_RANGE,
+ CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D_RANGE,
+ CJK_UNIFIED_IDEOGRAPHS_EXTENSION_E_RANGE,
+ CJK_UNIFIED_IDEOGRAPHS_EXTENSION_F_RANGE,
+ CJK_COMPATIBILITY_IDEOGRAPHS_RANGE,
+ CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT_RANGE
+];
+
+// Japanese character ranges, roughly ordered in order of expected frequency
+/** @type {import('japanese-util').CodepointRange[]} */
+const JAPANESE_RANGES = [
+ HIRAGANA_RANGE,
+ KATAKANA_RANGE,
+
+ ...CJK_IDEOGRAPH_RANGES,
+
+ [0xff66, 0xff9f], // Halfwidth katakana
+
+ [0x30fb, 0x30fc], // Katakana punctuation
+ [0xff61, 0xff65], // Kana punctuation
+ [0x3000, 0x303f], // CJK punctuation
+
+ [0xff10, 0xff19], // Fullwidth numbers
+ [0xff21, 0xff3a], // Fullwidth upper case Latin letters
+ [0xff41, 0xff5a], // Fullwidth lower case Latin letters
+
+ [0xff01, 0xff0f], // Fullwidth punctuation 1
+ [0xff1a, 0xff1f], // Fullwidth punctuation 2
+ [0xff3b, 0xff3f], // Fullwidth punctuation 3
+ [0xff5b, 0xff60], // Fullwidth punctuation 4
+ [0xffe0, 0xffee] // Currency markers
+];
+
+const SMALL_KANA_SET = new Set(Array.from('ぁぃぅぇぉゃゅょゎァィゥェォャュョヮ'));
+
+const HALFWIDTH_KATAKANA_MAPPING = new Map([
+ ['ヲ', 'ヲヺ-'],
+ ['ァ', 'ァ--'],
+ ['ィ', 'ィ--'],
+ ['ゥ', 'ゥ--'],
+ ['ェ', 'ェ--'],
+ ['ォ', 'ォ--'],
+ ['ャ', 'ャ--'],
+ ['ュ', 'ュ--'],
+ ['ョ', 'ョ--'],
+ ['ッ', 'ッ--'],
+ ['ー', 'ー--'],
+ ['ア', 'ア--'],
+ ['イ', 'イ--'],
+ ['ウ', 'ウヴ-'],
+ ['エ', 'エ--'],
+ ['オ', 'オ--'],
+ ['カ', 'カガ-'],
+ ['キ', 'キギ-'],
+ ['ク', 'クグ-'],
+ ['ケ', 'ケゲ-'],
+ ['コ', 'コゴ-'],
+ ['サ', 'サザ-'],
+ ['シ', 'シジ-'],
+ ['ス', 'スズ-'],
+ ['セ', 'セゼ-'],
+ ['ソ', 'ソゾ-'],
+ ['タ', 'タダ-'],
+ ['チ', 'チヂ-'],
+ ['ツ', 'ツヅ-'],
+ ['テ', 'テデ-'],
+ ['ト', 'トド-'],
+ ['ナ', 'ナ--'],
+ ['ニ', 'ニ--'],
+ ['ヌ', 'ヌ--'],
+ ['ネ', 'ネ--'],
+ ['ノ', 'ノ--'],
+ ['ハ', 'ハバパ'],
+ ['ヒ', 'ヒビピ'],
+ ['フ', 'フブプ'],
+ ['ヘ', 'ヘベペ'],
+ ['ホ', 'ホボポ'],
+ ['マ', 'マ--'],
+ ['ミ', 'ミ--'],
+ ['ム', 'ム--'],
+ ['メ', 'メ--'],
+ ['モ', 'モ--'],
+ ['ヤ', 'ヤ--'],
+ ['ユ', 'ユ--'],
+ ['ヨ', 'ヨ--'],
+ ['ラ', 'ラ--'],
+ ['リ', 'リ--'],
+ ['ル', 'ル--'],
+ ['レ', 'レ--'],
+ ['ロ', 'ロ--'],
+ ['ワ', 'ワ--'],
+ ['ン', 'ン--']
+]);
+
+const VOWEL_TO_KANA_MAPPING = new Map([
+ ['a', 'ぁあかがさざただなはばぱまゃやらゎわヵァアカガサザタダナハバパマャヤラヮワヵヷ'],
+ ['i', 'ぃいきぎしじちぢにひびぴみりゐィイキギシジチヂニヒビピミリヰヸ'],
+ ['u', 'ぅうくぐすずっつづぬふぶぷむゅゆるゥウクグスズッツヅヌフブプムュユルヴ'],
+ ['e', 'ぇえけげせぜてでねへべぺめれゑヶェエケゲセゼテデネヘベペメレヱヶヹ'],
+ ['o', 'ぉおこごそぞとどのほぼぽもょよろをォオコゴソゾトドノホボポモョヨロヲヺ'],
+ ['', 'のノ']
+]);
+
+const KANA_TO_VOWEL_MAPPING = (() => {
+ /** @type {Map<string, string>} */
+ const map = new Map();
+ for (const [vowel, characters] of VOWEL_TO_KANA_MAPPING) {
+ for (const character of characters) {
+ map.set(character, vowel);
}
- return map;
- })();
-
-
- function isCodePointInRange(codePoint, [min, max]) {
- return (codePoint >= min && codePoint <= max);
}
+ return map;
+})();
- function isCodePointInRanges(codePoint, ranges) {
- for (const [min, max] of ranges) {
- if (codePoint >= min && codePoint <= max) {
- return true;
- }
+const DIACRITIC_MAPPING = (() => {
+ const kana = 'うゔ-かが-きぎ-くぐ-けげ-こご-さざ-しじ-すず-せぜ-そぞ-ただ-ちぢ-つづ-てで-とど-はばぱひびぴふぶぷへべぺほぼぽワヷ-ヰヸ-ウヴ-ヱヹ-ヲヺ-カガ-キギ-クグ-ケゲ-コゴ-サザ-シジ-スズ-セゼ-ソゾ-タダ-チヂ-ツヅ-テデ-トド-ハバパヒビピフブプヘベペホボポ';
+ /** @type {Map<string, {character: string, type: import('japanese-util').DiacriticType}>} */
+ const map = new Map();
+ for (let i = 0, ii = kana.length; i < ii; i += 3) {
+ const character = kana[i];
+ const dakuten = kana[i + 1];
+ const handakuten = kana[i + 2];
+ map.set(dakuten, {character, type: 'dakuten'});
+ if (handakuten !== '-') {
+ map.set(handakuten, {character, type: 'handakuten'});
}
- return false;
}
+ return map;
+})();
+
- function getProlongedHiragana(previousCharacter) {
- switch (KANA_TO_VOWEL_MAPPING.get(previousCharacter)) {
- case 'a': return 'あ';
- case 'i': return 'い';
- case 'u': return 'う';
- case 'e': return 'え';
- case 'o': return 'う';
- default: return null;
+/**
+ * @param {number} codePoint
+ * @param {import('japanese-util').CodepointRange} range
+ * @returns {boolean}
+ */
+// eslint-disable-next-line no-implicit-globals
+function isCodePointInRange(codePoint, [min, max]) {
+ return (codePoint >= min && codePoint <= max);
+}
+
+/**
+ * @param {number} codePoint
+ * @param {import('japanese-util').CodepointRange[]} ranges
+ * @returns {boolean}
+ */
+// eslint-disable-next-line no-implicit-globals
+function isCodePointInRanges(codePoint, ranges) {
+ for (const [min, max] of ranges) {
+ if (codePoint >= min && codePoint <= max) {
+ return true;
}
}
+ return false;
+}
+/**
+ * @param {string} previousCharacter
+ * @returns {?string}
+ */
+// eslint-disable-next-line no-implicit-globals
+function getProlongedHiragana(previousCharacter) {
+ switch (KANA_TO_VOWEL_MAPPING.get(previousCharacter)) {
+ case 'a': return 'あ';
+ case 'i': return 'い';
+ case 'u': return 'う';
+ case 'e': return 'え';
+ case 'o': return 'う';
+ default: return null;
+ }
+}
- // eslint-disable-next-line no-shadow
- class JapaneseUtil {
- constructor(wanakana=null) {
- this._wanakana = wanakana;
- }
- // Character code testing functions
+export class JapaneseUtil {
+ /**
+ * @param {?import('wanakana')} wanakana
+ */
+ constructor(wanakana=null) {
+ /** @type {?import('wanakana')} */
+ this._wanakana = wanakana;
+ }
- isCodePointKanji(codePoint) {
- return isCodePointInRanges(codePoint, CJK_IDEOGRAPH_RANGES);
- }
+ // Character code testing functions
- isCodePointKana(codePoint) {
- return isCodePointInRanges(codePoint, KANA_RANGES);
- }
+ /**
+ * @param {number} codePoint
+ * @returns {boolean}
+ */
+ isCodePointKanji(codePoint) {
+ return isCodePointInRanges(codePoint, CJK_IDEOGRAPH_RANGES);
+ }
- isCodePointJapanese(codePoint) {
- return isCodePointInRanges(codePoint, JAPANESE_RANGES);
- }
+ /**
+ * @param {number} codePoint
+ * @returns {boolean}
+ */
+ isCodePointKana(codePoint) {
+ return isCodePointInRanges(codePoint, KANA_RANGES);
+ }
- // String testing functions
+ /**
+ * @param {number} codePoint
+ * @returns {boolean}
+ */
+ isCodePointJapanese(codePoint) {
+ return isCodePointInRanges(codePoint, JAPANESE_RANGES);
+ }
- isStringEntirelyKana(str) {
- if (str.length === 0) { return false; }
- for (const c of str) {
- if (!isCodePointInRanges(c.codePointAt(0), KANA_RANGES)) {
- return false;
- }
+ // String testing functions
+
+ /**
+ * @param {string} str
+ * @returns {boolean}
+ */
+ isStringEntirelyKana(str) {
+ if (str.length === 0) { return false; }
+ for (const c of str) {
+ if (!isCodePointInRanges(/** @type {number} */ (c.codePointAt(0)), KANA_RANGES)) {
+ return false;
}
- return true;
}
+ return true;
+ }
- isStringPartiallyJapanese(str) {
- if (str.length === 0) { return false; }
- for (const c of str) {
- if (isCodePointInRanges(c.codePointAt(0), JAPANESE_RANGES)) {
- return true;
- }
+ /**
+ * @param {string} str
+ * @returns {boolean}
+ */
+ isStringPartiallyJapanese(str) {
+ if (str.length === 0) { return false; }
+ for (const c of str) {
+ if (isCodePointInRanges(/** @type {number} */ (c.codePointAt(0)), JAPANESE_RANGES)) {
+ return true;
}
- return false;
}
+ return false;
+ }
- // Mora functions
+ // Mora functions
- isMoraPitchHigh(moraIndex, pitchAccentDownstepPosition) {
- switch (pitchAccentDownstepPosition) {
- case 0: return (moraIndex > 0);
- case 1: return (moraIndex < 1);
- default: return (moraIndex > 0 && moraIndex < pitchAccentDownstepPosition);
- }
+ /**
+ * @param {number} moraIndex
+ * @param {number} pitchAccentDownstepPosition
+ * @returns {boolean}
+ */
+ isMoraPitchHigh(moraIndex, pitchAccentDownstepPosition) {
+ switch (pitchAccentDownstepPosition) {
+ case 0: return (moraIndex > 0);
+ case 1: return (moraIndex < 1);
+ default: return (moraIndex > 0 && moraIndex < pitchAccentDownstepPosition);
}
+ }
- getPitchCategory(text, pitchAccentDownstepPosition, isVerbOrAdjective) {
- if (pitchAccentDownstepPosition === 0) {
- return 'heiban';
- }
- if (isVerbOrAdjective) {
- return pitchAccentDownstepPosition > 0 ? 'kifuku' : null;
- }
- if (pitchAccentDownstepPosition === 1) {
- return 'atamadaka';
- }
- if (pitchAccentDownstepPosition > 1) {
- return pitchAccentDownstepPosition >= this.getKanaMoraCount(text) ? 'odaka' : 'nakadaka';
- }
- return null;
+ /**
+ * @param {string} text
+ * @param {number} pitchAccentDownstepPosition
+ * @param {boolean} isVerbOrAdjective
+ * @returns {?import('japanese-util').PitchCategory}
+ */
+ getPitchCategory(text, pitchAccentDownstepPosition, isVerbOrAdjective) {
+ if (pitchAccentDownstepPosition === 0) {
+ return 'heiban';
+ }
+ if (isVerbOrAdjective) {
+ return pitchAccentDownstepPosition > 0 ? 'kifuku' : null;
+ }
+ if (pitchAccentDownstepPosition === 1) {
+ return 'atamadaka';
}
+ if (pitchAccentDownstepPosition > 1) {
+ return pitchAccentDownstepPosition >= this.getKanaMoraCount(text) ? 'odaka' : 'nakadaka';
+ }
+ return null;
+ }
- getKanaMorae(text) {
- const morae = [];
- let i;
- for (const c of text) {
- if (SMALL_KANA_SET.has(c) && (i = morae.length) > 0) {
- morae[i - 1] += c;
- } else {
- morae.push(c);
- }
+ /**
+ * @param {string} text
+ * @returns {string[]}
+ */
+ getKanaMorae(text) {
+ const morae = [];
+ let i;
+ for (const c of text) {
+ if (SMALL_KANA_SET.has(c) && (i = morae.length) > 0) {
+ morae[i - 1] += c;
+ } else {
+ morae.push(c);
}
- return morae;
}
+ return morae;
+ }
- getKanaMoraCount(text) {
- let moraCount = 0;
- for (const c of text) {
- if (!(SMALL_KANA_SET.has(c) && moraCount > 0)) {
- ++moraCount;
- }
+ /**
+ * @param {string} text
+ * @returns {number}
+ */
+ getKanaMoraCount(text) {
+ let moraCount = 0;
+ for (const c of text) {
+ if (!(SMALL_KANA_SET.has(c) && moraCount > 0)) {
+ ++moraCount;
}
- return moraCount;
}
+ return moraCount;
+ }
- // Conversion functions
+ // Conversion functions
- convertToKana(text) {
- return this._getWanakana().toKana(text);
- }
+ /**
+ * @param {string} text
+ * @returns {string}
+ */
+ convertToKana(text) {
+ return this._getWanakana().toKana(text);
+ }
- convertToKanaSupported() {
- return this._wanakana !== null;
- }
+ /**
+ * @returns {boolean}
+ */
+ convertToKanaSupported() {
+ return this._wanakana !== null;
+ }
- convertKatakanaToHiragana(text, keepProlongedSoundMarks=false) {
- let result = '';
- const offset = (HIRAGANA_CONVERSION_RANGE[0] - KATAKANA_CONVERSION_RANGE[0]);
- for (let char of text) {
- const codePoint = char.codePointAt(0);
- switch (codePoint) {
- case KATAKANA_SMALL_KA_CODE_POINT:
- case KATAKANA_SMALL_KE_CODE_POINT:
- // No change
- break;
- case KANA_PROLONGED_SOUND_MARK_CODE_POINT:
- if (!keepProlongedSoundMarks && result.length > 0) {
- const char2 = getProlongedHiragana(result[result.length - 1]);
- if (char2 !== null) { char = char2; }
- }
- break;
- default:
- if (isCodePointInRange(codePoint, KATAKANA_CONVERSION_RANGE)) {
- char = String.fromCodePoint(codePoint + offset);
- }
- break;
- }
- result += char;
+ /**
+ * @param {string} text
+ * @param {boolean} [keepProlongedSoundMarks]
+ * @returns {string}
+ */
+ convertKatakanaToHiragana(text, keepProlongedSoundMarks=false) {
+ let result = '';
+ const offset = (HIRAGANA_CONVERSION_RANGE[0] - KATAKANA_CONVERSION_RANGE[0]);
+ for (let char of text) {
+ const codePoint = /** @type {number} */ (char.codePointAt(0));
+ switch (codePoint) {
+ case KATAKANA_SMALL_KA_CODE_POINT:
+ case KATAKANA_SMALL_KE_CODE_POINT:
+ // No change
+ break;
+ case KANA_PROLONGED_SOUND_MARK_CODE_POINT:
+ if (!keepProlongedSoundMarks && result.length > 0) {
+ const char2 = getProlongedHiragana(result[result.length - 1]);
+ if (char2 !== null) { char = char2; }
+ }
+ break;
+ default:
+ if (isCodePointInRange(codePoint, KATAKANA_CONVERSION_RANGE)) {
+ char = String.fromCodePoint(codePoint + offset);
+ }
+ break;
}
- return result;
+ result += char;
}
+ return result;
+ }
- convertHiraganaToKatakana(text) {
- let result = '';
- const offset = (KATAKANA_CONVERSION_RANGE[0] - HIRAGANA_CONVERSION_RANGE[0]);
- for (let char of text) {
- const codePoint = char.codePointAt(0);
- if (isCodePointInRange(codePoint, HIRAGANA_CONVERSION_RANGE)) {
- char = String.fromCodePoint(codePoint + offset);
- }
- result += char;
+ /**
+ * @param {string} text
+ * @returns {string}
+ */
+ convertHiraganaToKatakana(text) {
+ let result = '';
+ const offset = (KATAKANA_CONVERSION_RANGE[0] - HIRAGANA_CONVERSION_RANGE[0]);
+ for (let char of text) {
+ const codePoint = /** @type {number} */ (char.codePointAt(0));
+ if (isCodePointInRange(codePoint, HIRAGANA_CONVERSION_RANGE)) {
+ char = String.fromCodePoint(codePoint + offset);
}
- return result;
+ result += char;
}
+ return result;
+ }
- convertToRomaji(text) {
- const wanakana = this._getWanakana();
- return wanakana.toRomaji(text);
- }
+ /**
+ * @param {string} text
+ * @returns {string}
+ */
+ convertToRomaji(text) {
+ const wanakana = this._getWanakana();
+ return wanakana.toRomaji(text);
+ }
- convertToRomajiSupported() {
- return this._wanakana !== null;
- }
+ /**
+ * @returns {boolean}
+ */
+ convertToRomajiSupported() {
+ return this._wanakana !== null;
+ }
- convertNumericToFullWidth(text) {
- let result = '';
- for (const char of text) {
- let c = char.codePointAt(0);
- if (c >= 0x30 && c <= 0x39) { // ['0', '9']
- c += 0xff10 - 0x30; // 0xff10 = '0' full width
- result += String.fromCodePoint(c);
- } else {
- result += char;
- }
+ /**
+ * @param {string} text
+ * @returns {string}
+ */
+ convertNumericToFullWidth(text) {
+ let result = '';
+ for (const char of text) {
+ let c = /** @type {number} */ (char.codePointAt(0));
+ if (c >= 0x30 && c <= 0x39) { // ['0', '9']
+ c += 0xff10 - 0x30; // 0xff10 = '0' full width
+ result += String.fromCodePoint(c);
+ } else {
+ result += char;
}
- return result;
}
+ return result;
+ }
- convertHalfWidthKanaToFullWidth(text, sourceMap=null) {
- let result = '';
-
- // This function is safe to use charCodeAt instead of codePointAt, since all
- // the relevant characters are represented with a single UTF-16 character code.
- for (let i = 0, ii = text.length; i < ii; ++i) {
- const c = text[i];
- const mapping = HALFWIDTH_KATAKANA_MAPPING.get(c);
- if (typeof mapping !== 'string') {
- result += c;
- continue;
- }
-
- let index = 0;
- switch (text.charCodeAt(i + 1)) {
- case 0xff9e: // dakuten
- index = 1;
- break;
- case 0xff9f: // handakuten
- index = 2;
- break;
- }
-
- let c2 = mapping[index];
- if (index > 0) {
- if (c2 === '-') { // invalid
- index = 0;
- c2 = mapping[0];
- } else {
- ++i;
- }
- }
-
- if (sourceMap !== null && index > 0) {
- sourceMap.combine(result.length, 1);
- }
- result += c2;
+ /**
+ * @param {string} text
+ * @param {?TextSourceMap} [sourceMap]
+ * @returns {string}
+ */
+ convertHalfWidthKanaToFullWidth(text, sourceMap=null) {
+ let result = '';
+
+ // This function is safe to use charCodeAt instead of codePointAt, since all
+ // the relevant characters are represented with a single UTF-16 character code.
+ for (let i = 0, ii = text.length; i < ii; ++i) {
+ const c = text[i];
+ const mapping = HALFWIDTH_KATAKANA_MAPPING.get(c);
+ if (typeof mapping !== 'string') {
+ result += c;
+ continue;
}
- return result;
- }
+ let index = 0;
+ switch (text.charCodeAt(i + 1)) {
+ case 0xff9e: // dakuten
+ index = 1;
+ break;
+ case 0xff9f: // handakuten
+ index = 2;
+ break;
+ }
- convertAlphabeticToKana(text, sourceMap=null) {
- let part = '';
- let result = '';
-
- for (const char of text) {
- // Note: 0x61 is the character code for 'a'
- let c = char.codePointAt(0);
- if (c >= 0x41 && c <= 0x5a) { // ['A', 'Z']
- c += (0x61 - 0x41);
- } else if (c >= 0x61 && c <= 0x7a) { // ['a', 'z']
- // NOP; c += (0x61 - 0x61);
- } else if (c >= 0xff21 && c <= 0xff3a) { // ['A', 'Z'] fullwidth
- c += (0x61 - 0xff21);
- } else if (c >= 0xff41 && c <= 0xff5a) { // ['a', 'z'] fullwidth
- c += (0x61 - 0xff41);
- } else if (c === 0x2d || c === 0xff0d) { // '-' or fullwidth dash
- c = 0x2d; // '-'
+ let c2 = mapping[index];
+ if (index > 0) {
+ if (c2 === '-') { // invalid
+ index = 0;
+ c2 = mapping[0];
} else {
- if (part.length > 0) {
- result += this._convertAlphabeticPartToKana(part, sourceMap, result.length);
- part = '';
- }
- result += char;
- continue;
+ ++i;
}
- part += String.fromCodePoint(c);
}
- if (part.length > 0) {
- result += this._convertAlphabeticPartToKana(part, sourceMap, result.length);
+ if (sourceMap !== null && index > 0) {
+ sourceMap.combine(result.length, 1);
}
- return result;
+ result += c2;
}
- convertAlphabeticToKanaSupported() {
- return this._wanakana !== null;
+ return result;
+ }
+
+ /**
+ * @param {string} text
+ * @param {?TextSourceMap} sourceMap
+ * @returns {string}
+ */
+ convertAlphabeticToKana(text, sourceMap=null) {
+ let part = '';
+ let result = '';
+
+ for (const char of text) {
+ // Note: 0x61 is the character code for 'a'
+ let c = /** @type {number} */ (char.codePointAt(0));
+ if (c >= 0x41 && c <= 0x5a) { // ['A', 'Z']
+ c += (0x61 - 0x41);
+ } else if (c >= 0x61 && c <= 0x7a) { // ['a', 'z']
+ // NOP; c += (0x61 - 0x61);
+ } else if (c >= 0xff21 && c <= 0xff3a) { // ['A', 'Z'] fullwidth
+ c += (0x61 - 0xff21);
+ } else if (c >= 0xff41 && c <= 0xff5a) { // ['a', 'z'] fullwidth
+ c += (0x61 - 0xff41);
+ } else if (c === 0x2d || c === 0xff0d) { // '-' or fullwidth dash
+ c = 0x2d; // '-'
+ } else {
+ if (part.length > 0) {
+ result += this._convertAlphabeticPartToKana(part, sourceMap, result.length);
+ part = '';
+ }
+ result += char;
+ continue;
+ }
+ part += String.fromCodePoint(c);
}
- getKanaDiacriticInfo(character) {
- const info = DIACRITIC_MAPPING.get(character);
- return typeof info !== 'undefined' ? {character: info.character, type: info.type} : null;
+ if (part.length > 0) {
+ result += this._convertAlphabeticPartToKana(part, sourceMap, result.length);
}
+ return result;
+ }
- // Furigana distribution
+ /**
+ * @returns {boolean}
+ */
+ convertAlphabeticToKanaSupported() {
+ return this._wanakana !== null;
+ }
- distributeFurigana(term, reading) {
- if (reading === term) {
- // Same
- return [this._createFuriganaSegment(term, '')];
- }
+ /**
+ * @param {string} character
+ * @returns {?{character: string, type: import('japanese-util').DiacriticType}}
+ */
+ getKanaDiacriticInfo(character) {
+ const info = DIACRITIC_MAPPING.get(character);
+ return typeof info !== 'undefined' ? {character: info.character, type: info.type} : null;
+ }
- const groups = [];
- let groupPre = null;
- let isKanaPre = null;
- for (const c of term) {
- const codePoint = c.codePointAt(0);
- const isKana = this.isCodePointKana(codePoint);
- if (isKana === isKanaPre) {
- groupPre.text += c;
- } else {
- groupPre = {isKana, text: c, textNormalized: null};
- groups.push(groupPre);
- isKanaPre = isKana;
- }
- }
- for (const group of groups) {
- if (group.isKana) {
- group.textNormalized = this.convertKatakanaToHiragana(group.text);
- }
+ // Furigana distribution
+
+ /**
+ * @param {string} term
+ * @param {string} reading
+ * @returns {import('japanese-util').FuriganaSegment[]}
+ */
+ distributeFurigana(term, reading) {
+ if (reading === term) {
+ // Same
+ return [this._createFuriganaSegment(term, '')];
+ }
+
+ /** @type {import('japanese-util').FuriganaGroup[]} */
+ const groups = [];
+ /** @type {?import('japanese-util').FuriganaGroup} */
+ let groupPre = null;
+ let isKanaPre = null;
+ for (const c of term) {
+ const codePoint = /** @type {number} */ (c.codePointAt(0));
+ const isKana = this.isCodePointKana(codePoint);
+ if (isKana === isKanaPre) {
+ /** @type {import('japanese-util').FuriganaGroup} */ (groupPre).text += c;
+ } else {
+ groupPre = {isKana, text: c, textNormalized: null};
+ groups.push(groupPre);
+ isKanaPre = isKana;
}
-
- const readingNormalized = this.convertKatakanaToHiragana(reading);
- const segments = this._segmentizeFurigana(reading, readingNormalized, groups, 0);
- if (segments !== null) {
- return segments;
+ }
+ for (const group of groups) {
+ if (group.isKana) {
+ group.textNormalized = this.convertKatakanaToHiragana(group.text);
}
-
- // Fallback
- return [this._createFuriganaSegment(term, reading)];
}
- distributeFuriganaInflected(term, reading, source) {
- const termNormalized = this.convertKatakanaToHiragana(term);
- const readingNormalized = this.convertKatakanaToHiragana(reading);
- const sourceNormalized = this.convertKatakanaToHiragana(source);
-
- let mainText = term;
- let stemLength = this._getStemLength(termNormalized, sourceNormalized);
+ const readingNormalized = this.convertKatakanaToHiragana(reading);
+ const segments = this._segmentizeFurigana(reading, readingNormalized, groups, 0);
+ if (segments !== null) {
+ return segments;
+ }
- // Check if source is derived from the reading instead of the term
- const readingStemLength = this._getStemLength(readingNormalized, sourceNormalized);
- if (readingStemLength > 0 && readingStemLength >= stemLength) {
- mainText = reading;
- stemLength = readingStemLength;
- reading = `${source.substring(0, stemLength)}${reading.substring(stemLength)}`;
- }
+ // Fallback
+ return [this._createFuriganaSegment(term, reading)];
+ }
- const segments = [];
- if (stemLength > 0) {
- mainText = `${source.substring(0, stemLength)}${mainText.substring(stemLength)}`;
- 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;
+ /**
+ * @param {string} term
+ * @param {string} reading
+ * @param {string} source
+ * @returns {import('japanese-util').FuriganaSegment[]}
+ */
+ distributeFuriganaInflected(term, reading, source) {
+ const termNormalized = this.convertKatakanaToHiragana(term);
+ const readingNormalized = this.convertKatakanaToHiragana(reading);
+ const sourceNormalized = this.convertKatakanaToHiragana(source);
+
+ let mainText = term;
+ let stemLength = this._getStemLength(termNormalized, sourceNormalized);
+
+ // Check if source is derived from the reading instead of the term
+ const readingStemLength = this._getStemLength(readingNormalized, sourceNormalized);
+ if (readingStemLength > 0 && readingStemLength >= stemLength) {
+ mainText = reading;
+ stemLength = readingStemLength;
+ reading = `${source.substring(0, stemLength)}${reading.substring(stemLength)}`;
+ }
+
+ const segments = [];
+ if (stemLength > 0) {
+ mainText = `${source.substring(0, stemLength)}${mainText.substring(stemLength)}`;
+ 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].reading.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, ''));
- }
+ if (stemLength < source.length) {
+ const remainder = source.substring(stemLength);
+ const segmentCount = segments.length;
+ 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 {
+ // Otherwise, create a new segment
+ segments.push(this._createFuriganaSegment(remainder, ''));
}
-
- return segments;
}
- // Miscellaneous
-
- collapseEmphaticSequences(text, fullCollapse, sourceMap=null) {
- let result = '';
- let collapseCodePoint = -1;
- const hasSourceMap = (sourceMap !== null);
- for (const char of text) {
- const c = char.codePointAt(0);
- if (
- c === HIRAGANA_SMALL_TSU_CODE_POINT ||
- c === KATAKANA_SMALL_TSU_CODE_POINT ||
- c === KANA_PROLONGED_SOUND_MARK_CODE_POINT
- ) {
- if (collapseCodePoint !== c) {
- collapseCodePoint = c;
- if (!fullCollapse) {
- result += char;
- continue;
- }
+ return segments;
+ }
+
+ // Miscellaneous
+
+ /**
+ * @param {string} text
+ * @param {boolean} fullCollapse
+ * @param {?TextSourceMap} [sourceMap]
+ * @returns {string}
+ */
+ collapseEmphaticSequences(text, fullCollapse, sourceMap=null) {
+ let result = '';
+ let collapseCodePoint = -1;
+ const hasSourceMap = (sourceMap !== null);
+ for (const char of text) {
+ const c = char.codePointAt(0);
+ if (
+ c === HIRAGANA_SMALL_TSU_CODE_POINT ||
+ c === KATAKANA_SMALL_TSU_CODE_POINT ||
+ c === KANA_PROLONGED_SOUND_MARK_CODE_POINT
+ ) {
+ if (collapseCodePoint !== c) {
+ collapseCodePoint = c;
+ if (!fullCollapse) {
+ result += char;
+ continue;
}
- } else {
- collapseCodePoint = -1;
- result += char;
- continue;
}
+ } else {
+ collapseCodePoint = -1;
+ result += char;
+ continue;
+ }
- if (hasSourceMap) {
- sourceMap.combine(Math.max(0, result.length - 1), 1);
- }
+ if (hasSourceMap) {
+ sourceMap.combine(Math.max(0, result.length - 1), 1);
}
- return result;
}
+ return result;
+ }
- // Private
-
- _createFuriganaSegment(text, reading) {
- return {text, reading};
- }
+ // Private
- _segmentizeFurigana(reading, readingNormalized, groups, groupsStart) {
- const groupCount = groups.length - groupsStart;
- if (groupCount <= 0) {
- return reading.length === 0 ? [] : null;
- }
+ /**
+ * @param {string} text
+ * @param {string} reading
+ * @returns {import('japanese-util').FuriganaSegment}
+ */
+ _createFuriganaSegment(text, reading) {
+ return {text, reading};
+ }
- const group = groups[groupsStart];
- const {isKana, text} = group;
- const textLength = text.length;
- if (isKana) {
- const {textNormalized} = group;
- if (readingNormalized.startsWith(textNormalized)) {
- const segments = this._segmentizeFurigana(
- reading.substring(textLength),
- readingNormalized.substring(textLength),
- groups,
- groupsStart + 1
- );
- if (segments !== null) {
- if (reading.startsWith(text)) {
- segments.unshift(this._createFuriganaSegment(text, ''));
- } else {
- segments.unshift(...this._getFuriganaKanaSegments(text, reading));
- }
- return segments;
+ /**
+ * @param {string} reading
+ * @param {string} readingNormalized
+ * @param {import('japanese-util').FuriganaGroup[]} groups
+ * @param {number} groupsStart
+ * @returns {?(import('japanese-util').FuriganaSegment[])}
+ */
+ _segmentizeFurigana(reading, readingNormalized, groups, groupsStart) {
+ const groupCount = groups.length - groupsStart;
+ if (groupCount <= 0) {
+ return reading.length === 0 ? [] : null;
+ }
+
+ const group = groups[groupsStart];
+ const {isKana, text} = group;
+ const textLength = text.length;
+ if (isKana) {
+ const {textNormalized} = group;
+ if (textNormalized !== null && readingNormalized.startsWith(textNormalized)) {
+ const segments = this._segmentizeFurigana(
+ reading.substring(textLength),
+ readingNormalized.substring(textLength),
+ groups,
+ groupsStart + 1
+ );
+ if (segments !== null) {
+ if (reading.startsWith(text)) {
+ segments.unshift(this._createFuriganaSegment(text, ''));
+ } else {
+ segments.unshift(...this._getFuriganaKanaSegments(text, reading));
}
+ return segments;
}
- return null;
- } else {
- let result = null;
- for (let i = reading.length; i >= textLength; --i) {
- const segments = this._segmentizeFurigana(
- reading.substring(i),
- readingNormalized.substring(i),
- groups,
- groupsStart + 1
- );
- if (segments !== null) {
- if (result !== null) {
- // More than one way to segmentize the tail; mark as ambiguous
- return null;
- }
- 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
- if (groupCount === 1) {
- break;
+ }
+ return null;
+ } else {
+ let result = null;
+ for (let i = reading.length; i >= textLength; --i) {
+ const segments = this._segmentizeFurigana(
+ reading.substring(i),
+ readingNormalized.substring(i),
+ groups,
+ groupsStart + 1
+ );
+ if (segments !== null) {
+ if (result !== null) {
+ // More than one way to segmentize the tail; mark as ambiguous
+ return null;
}
+ 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
+ if (groupCount === 1) {
+ break;
}
- return result;
- }
- }
-
- _getFuriganaKanaSegments(text, reading) {
- const textLength = text.length;
- const newSegments = [];
- let start = 0;
- let state = (reading[0] === text[0]);
- for (let i = 1; i < textLength; ++i) {
- const newState = (reading[i] === text[i]);
- if (state === newState) { continue; }
- newSegments.push(this._createFuriganaSegment(text.substring(start, i), state ? '' : reading.substring(start, i)));
- state = newState;
- start = i;
}
- newSegments.push(this._createFuriganaSegment(text.substring(start, textLength), state ? '' : reading.substring(start, textLength)));
- return newSegments;
+ return result;
}
+ }
- _getWanakana() {
- const wanakana = this._wanakana;
- if (wanakana === null) { throw new Error('Functions which use WanaKana are not supported in this context'); }
- return wanakana;
- }
+ /**
+ * @param {string} text
+ * @param {string} reading
+ * @returns {import('japanese-util').FuriganaSegment[]}
+ */
+ _getFuriganaKanaSegments(text, reading) {
+ const textLength = text.length;
+ const newSegments = [];
+ let start = 0;
+ let state = (reading[0] === text[0]);
+ for (let i = 1; i < textLength; ++i) {
+ const newState = (reading[i] === text[i]);
+ if (state === newState) { continue; }
+ newSegments.push(this._createFuriganaSegment(text.substring(start, i), state ? '' : reading.substring(start, i)));
+ state = newState;
+ start = i;
+ }
+ newSegments.push(this._createFuriganaSegment(text.substring(start, textLength), state ? '' : reading.substring(start, textLength)));
+ return newSegments;
+ }
- _convertAlphabeticPartToKana(text, sourceMap, sourceMapStart) {
- const wanakana = this._getWanakana();
- 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;
- }
+ /**
+ * @returns {import('wanakana')}
+ * @throws {Error}
+ */
+ _getWanakana() {
+ const wanakana = this._wanakana;
+ if (wanakana === null) { throw new Error('Functions which use WanaKana are not supported in this context'); }
+ return wanakana;
+ }
- // Merge characters
- const removals = iNext - i - 1;
- if (removals > 0) {
- sourceMap.combine(sourceMapStart, removals);
+ /**
+ * @param {string} text
+ * @param {?TextSourceMap} sourceMap
+ * @param {number} sourceMapStart
+ * @returns {string}
+ */
+ _convertAlphabeticPartToKana(text, sourceMap, sourceMapStart) {
+ const wanakana = this._getWanakana();
+ 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;
}
- ++sourceMapStart;
+ ++iNext;
+ }
- // Empty elements
- const additions = resultPosNext - resultPos - 1;
- for (let j = 0; j < additions; ++j) {
- sourceMap.insert(sourceMapStart, 0);
- ++sourceMapStart;
- }
+ // Merge characters
+ const removals = iNext - i - 1;
+ if (removals > 0) {
+ sourceMap.combine(sourceMapStart, removals);
+ }
+ ++sourceMapStart;
- i = iNext;
- resultPos = resultPosNext;
+ // Empty elements
+ const additions = resultPosNext - resultPos - 1;
+ for (let j = 0; j < additions; ++j) {
+ sourceMap.insert(sourceMapStart, 0);
+ ++sourceMapStart;
}
- }
- return result;
+ i = iNext;
+ resultPos = resultPosNext;
+ }
}
- _getStemLength(text1, text2) {
- const minLength = Math.min(text1.length, text2.length);
- if (minLength === 0) { return 0; }
+ return result;
+ }
- 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;
+ /**
+ * @param {string} text1
+ * @param {string} text2
+ * @returns {number}
+ */
+ _getStemLength(text1, text2) {
+ const minLength = Math.min(text1.length, text2.length);
+ if (minLength === 0) { return 0; }
+
+ let i = 0;
+ while (true) {
+ const char1 = /** @type {number} */ (text1.codePointAt(i));
+ const char2 = /** @type {number} */ (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;
}
+ return i;
}
-
-
- return JapaneseUtil;
-})();
+}