1
0
mirror of https://github.com/laurent22/joplin.git synced 2025-02-01 19:15:01 +02:00

More fixes to search engine and better handling of non-ASCII searches

This commit is contained in:
Laurent Cozic 2019-01-14 19:11:54 +00:00
parent a1f0bd1e6c
commit 2e12b2655b
17 changed files with 330 additions and 130 deletions

View File

@ -555,6 +555,11 @@
"resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-1.0.3.tgz",
"integrity": "sha1-+hN8S9aY7fVc1c0CrFWfkaTEups="
},
"diacritics": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/diacritics/-/diacritics-1.3.0.tgz",
"integrity": "sha1-PvqHMj67hj5mls67AILUj/PW96E="
},
"domexception": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/domexception/-/domexception-1.0.1.tgz",

View File

@ -31,6 +31,7 @@
"async-mutex": "^0.1.3",
"base-64": "^0.1.0",
"compare-version": "^0.1.2",
"diacritics": "^1.3.0",
"es6-promise-pool": "^2.5.0",
"follow-redirects": "^1.2.4",
"form-data": "^2.1.4",

View File

@ -29,6 +29,7 @@ npm test tests-build/models_BaseItem.js
npm test tests-build/models_Folder.js
npm test tests-build/models_Note.js
npm test tests-build/models_Tag.js
npm test tests-build/models_ItemChange.js
npm test tests-build/models_Setting.js
npm test tests-build/pathUtils.js
npm test tests-build/StringUtils.js

View File

@ -0,0 +1,53 @@
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
const { asyncTest, fileContentEqual, setupDatabase, setupDatabaseAndSynchronizer, db, synchronizer, fileApi, sleep, clearDatabase, switchClient, syncTargetId, objectsEqual, checkThrowAsync } = require('test-utils.js');
const SearchEngine = require('lib/services/SearchEngine');
const ResourceService = require('lib/services/ResourceService');
const ItemChangeUtils = require('lib/services/ItemChangeUtils');
const Note = require('lib/models/Note');
const Setting = require('lib/models/Setting');
const ItemChange = require('lib/models/ItemChange');
process.on('unhandledRejection', (reason, p) => {
console.log('Unhandled Rejection at: Promise', p, 'reason:', reason);
});
let searchEngine = null;
describe('models_ItemChange', function() {
beforeEach(async (done) => {
await setupDatabaseAndSynchronizer(1);
searchEngine = new SearchEngine();
searchEngine.setDb(db());
done();
});
it('should delete old changes that have been processed', asyncTest(async () => {
const n1 = await Note.save({ title: "abcd efgh" }); // 3
await ItemChange.waitForAllSaved();
expect(await ItemChange.lastChangeId()).toBe(1);
const resourceService = new ResourceService();
await searchEngine.syncTables();
// If we run this now, it should not delete any change because
// the resource service has not yet processed the change
await ItemChangeUtils.deleteProcessedChanges();
expect(await ItemChange.lastChangeId()).toBe(1);
await resourceService.indexNoteResources();
// Now that the resource service has processed the change,
// the change can be deleted.
await ItemChangeUtils.deleteProcessedChanges();
expect(await ItemChange.lastChangeId()).toBe(0);
}));
});

View File

@ -1,9 +1,11 @@
require('app-module-path').addPath(__dirname);
const { time } = require('lib/time-utils.js');
const { fileContentEqual, setupDatabase, setupDatabaseAndSynchronizer, db, synchronizer, fileApi, sleep, clearDatabase, switchClient, syncTargetId, objectsEqual, checkThrowAsync } = require('test-utils.js');
const { fileContentEqual, setupDatabase, setupDatabaseAndSynchronizer, asyncTest, db, synchronizer, fileApi, sleep, clearDatabase, switchClient, syncTargetId, objectsEqual, checkThrowAsync } = require('test-utils.js');
const SearchEngine = require('lib/services/SearchEngine');
const Note = require('lib/models/Note');
const ItemChange = require('lib/models/ItemChange');
const Setting = require('lib/models/Setting');
process.on('unhandledRejection', (reason, p) => {
console.log('Unhandled Rejection at: Promise', p, 'reason:', reason);
@ -23,7 +25,7 @@ describe('services_SearchEngine', function() {
done();
});
it('should keep the content and FTS table in sync', async (done) => {
it('should keep the content and FTS table in sync', asyncTest(async () => {
let rows, n1, n2, n3;
n1 = await Note.save({ title: "a" });
@ -56,11 +58,25 @@ describe('services_SearchEngine', function() {
await engine.syncTables();
rows = await engine.search('c');
expect(rows.length).toBe(1);
}));
done();
});
it('should, after initial indexing, save the last change ID', asyncTest(async () => {
const n1 = await Note.save({ title: "abcd efgh" }); // 3
const n2 = await Note.save({ title: "abcd aaaaa abcd abcd" }); // 1
it('should order search results by relevance (1)', async (done) => {
expect(Setting.value('searchEngine.initialIndexingDone')).toBe(false);
await ItemChange.waitForAllSaved();
const lastChangeId = await ItemChange.lastChangeId();
await engine.syncTables();
expect(Setting.value('searchEngine.lastProcessedChangeId')).toBe(lastChangeId);
expect(Setting.value('searchEngine.initialIndexingDone')).toBe(true);
}));
it('should order search results by relevance (1)', asyncTest(async () => {
const n1 = await Note.save({ title: "abcd efgh" }); // 3
const n2 = await Note.save({ title: "abcd aaaaa abcd abcd" }); // 1
const n3 = await Note.save({ title: "abcd aaaaa bbbb eeee abcd" }); // 2
@ -71,11 +87,9 @@ describe('services_SearchEngine', function() {
expect(rows[0].id).toBe(n2.id);
expect(rows[1].id).toBe(n3.id);
expect(rows[2].id).toBe(n1.id);
}));
done();
});
it('should order search results by relevance (2)', async (done) => {
it('should order search results by relevance (2)', asyncTest(async () => {
// 1
const n1 = await Note.save({ title: "abcd efgh", body: "XX abcd XX efgh" });
// 4
@ -95,11 +109,9 @@ describe('services_SearchEngine', function() {
expect(rows[2].id).toBe(n3.id);
expect(rows[3].id).toBe(n2.id);
expect(rows[4].id).toBe(n5.id);
}));
done();
});
it('should supports various query types', async (done) => {
it('should supports various query types', asyncTest(async () => {
let rows;
const n1 = await Note.save({ title: "abcd efgh ijkl", body: "aaaa bbbb" });
@ -148,11 +160,51 @@ describe('services_SearchEngine', function() {
rows = await engine.search('сообщило');
expect(rows.length).toBe(1);
}));
done();
});
it('should support queries with or without accents', asyncTest(async () => {
let rows;
const n1 = await Note.save({ title: "père noël" });
it('should parse normal query strings', async (done) => {
await engine.syncTables();
expect((await engine.search('père')).length).toBe(1);
expect((await engine.search('pere')).length).toBe(1);
expect((await engine.search('noe*')).length).toBe(1);
expect((await engine.search('noë*')).length).toBe(1);
}));
it('should support queries with Chinese characters', asyncTest(async () => {
let rows;
const n1 = await Note.save({ title: "我是法国人" });
await engine.syncTables();
expect((await engine.search('我')).length).toBe(1);
expect((await engine.search('法国人')).length).toBe(1);
}));
it('should support queries with Japanese characters', asyncTest(async () => {
let rows;
const n1 = await Note.save({ title: "私は日本語を話すことができません" });
await engine.syncTables();
expect((await engine.search('日本')).length).toBe(1);
expect((await engine.search('できません')).length).toBe(1);
}));
it('should support queries with Korean characters', asyncTest(async () => {
let rows;
const n1 = await Note.save({ title: "이것은 한국말이다" });
await engine.syncTables();
expect((await engine.search('이것은')).length).toBe(1);
expect((await engine.search('말')).length).toBe(1);
}));
it('should parse normal query strings', asyncTest(async () => {
let rows;
const testCases = [
@ -173,11 +225,9 @@ describe('services_SearchEngine', function() {
expect(JSON.stringify(actual.terms.title)).toBe(JSON.stringify(expected.title));
expect(JSON.stringify(actual.terms.body)).toBe(JSON.stringify(expected.body));
}
}));
done();
});
it('should parse query strings with wildcards', async (done) => {
it('should parse query strings with wildcards', asyncTest(async () => {
let rows;
const testCases = [
@ -202,8 +252,6 @@ describe('services_SearchEngine', function() {
}
expect(engine.parseQuery('*').termCount).toBe(0);
done();
});
}));
});

View File

@ -796,6 +796,7 @@ class Application extends BaseApplication {
SearchEngine.instance().setDb(reg.db());
SearchEngine.instance().setLogger(reg.logger());
SearchEngine.runInBackground();
if (Setting.value('env') === 'dev') {
AlarmService.updateAllNotifications();

View File

@ -279,9 +279,13 @@ class NoteListComponent extends React.Component {
const w = highlightedWords[i];
if (w.type === 'regex') {
mark.markRegExp(new RegExp(w.value, 'gmi'), { acrossElements: true });
mark.markRegExp(new RegExp('\\b' + w.value + '\\b', 'gmi'), {
acrossElements: true,
});
} else {
mark.mark([w]);
mark.mark([w], {
accuracy: 'exactly',
});
}
}

View File

@ -226,6 +226,8 @@
function setMarkers(keywords, options = null) {
if (!options) options = {};
// TODO: It should highlight queries without accents - eg "penche*" should highlight "penchés"
if (!mark_) {
mark_ = new Mark(document.getElementById('content'), {
exclude: ['img'],
@ -258,14 +260,14 @@
const keyword = keywords[i];
if (keyword.type === 'regex') {
mark_.markRegExp(new RegExp(keyword.value, 'gmi'), {
mark_.markRegExp(new RegExp('\\b' + keyword.value + '\\b', 'gmi'), {
each: onEachElement,
acrossElements: true,
});
} else {
mark_.mark([keyword], {
each: onEachElement,
accuracy: 'exactly',
accuracy: 'exactly',
});
}
}

View File

@ -1841,6 +1841,11 @@
"resolved": "https://registry.npmjs.org/detect-libc/-/detect-libc-1.0.3.tgz",
"integrity": "sha1-+hN8S9aY7fVc1c0CrFWfkaTEups="
},
"diacritics": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/diacritics/-/diacritics-1.3.0.tgz",
"integrity": "sha1-PvqHMj67hj5mls67AILUj/PW96E="
},
"diff-match-patch": {
"version": "1.0.4",
"resolved": "https://registry.npmjs.org/diff-match-patch/-/diff-match-patch-1.0.4.tgz",

View File

@ -84,6 +84,7 @@
"base-64": "^0.1.0",
"chokidar": "^2.0.3",
"compare-versions": "^3.2.1",
"diacritics": "^1.3.0",
"electron-context-menu": "^0.9.1",
"electron-is-dev": "^0.3.0",
"electron-window-state": "^4.1.1",

View File

@ -47,6 +47,11 @@ class ItemChange extends BaseModel {
});
}
static async deleteOldChanges(lowestChangeId) {
if (!lowestChangeId) return;
return this.db().exec('DELETE FROM item_changes WHERE id <= ?', [lowestChangeId]);
}
}
ItemChange.addChangeMutex_ = new Mutex();

View File

@ -0,0 +1,18 @@
const Setting = require('lib/models/Setting');
const ItemChange = require('lib/models/ItemChange');
class ItemChangeUtils {
static async deleteProcessedChanges() {
const lastProcessedChangeIds = [
Setting.value('resourceService.lastProcessedChangeId'),
Setting.value('searchEngine.lastProcessedChangeId'),
];
const lowestChangeId = Math.min(...lastProcessedChangeIds);
await ItemChange.deleteOldChanges(lowestChangeId);
}
}
module.exports = ItemChangeUtils;

View File

@ -6,6 +6,7 @@ const BaseModel = require('lib/BaseModel');
const BaseService = require('lib/services/BaseService');
const Setting = require('lib/models/Setting');
const { shim } = require('lib/shim');
const ItemChangeUtils = require('lib/services/ItemChangeUtils');
class ResourceService extends BaseService {
@ -66,6 +67,8 @@ class ResourceService extends BaseService {
await NoteResource.addOrphanedResources();
await ItemChangeUtils.deleteProcessedChanges();
this.logger().info('ResourceService::indexNoteResources: Completed');
}

View File

@ -4,7 +4,9 @@ const ItemChange = require('lib/models/ItemChange.js');
const Setting = require('lib/models/Setting.js');
const Note = require('lib/models/Note.js');
const BaseModel = require('lib/BaseModel.js');
const { pregQuote } = require('lib/string-utils.js');
const ItemChangeUtils = require('lib/services/ItemChangeUtils');
const { pregQuote, scriptType } = require('lib/string-utils.js');
const removeDiacritics = require('diacritics').remove;
class SearchEngine {
@ -49,15 +51,14 @@ class SearchEngine {
}
async initialIndexing() {
async rebuildIndex() {
let noteIds = await this.db().selectAll('SELECT id FROM notes WHERE is_conflict = 0 AND encryption_applied = 0');
noteIds = noteIds.map(n => n.id);
// TODO: get last change id HERE
const lastChangeId = await ItemChange.lastChangeId();
// First delete content of note_normalized, in case the previous initial indexing failed
await this.db().exec('DELETE FROM note_normalized');
await this.db().exec('DELETE FROM notes_normalized');
while (noteIds.length) {
const currentIds = noteIds.splice(0, 100);
@ -73,8 +74,7 @@ class SearchEngine {
await this.db().transactionExecBatch(queries);
}
// TODO: SET last chnage ID here
Setting.setValue('searchEngine.lastProcessedChangeId', lastChangeId);
}
async syncTables() {
@ -83,7 +83,8 @@ class SearchEngine {
await ItemChange.waitForAllSaved();
if (!Setting.value('searchEngine.initialIndexingDone')) {
await this.initialIndexing();
await this.rebuildIndex();
Setting.setValue('searchEngine.initialIndexingDone', true)
return;
}
@ -131,6 +132,8 @@ class SearchEngine {
await Setting.saveAll();
}
await ItemChangeUtils.deleteProcessedChanges();
this.logger().info('SearchEngine: Updated FTS table in ' + (Date.now() - startTime) + 'ms');
}
@ -306,7 +309,7 @@ class SearchEngine {
}
normalizeText_(text) {
return text.normalize().toLowerCase();
return removeDiacritics(text.normalize().toLowerCase());
}
normalizeNote_(note) {
@ -316,13 +319,47 @@ class SearchEngine {
return n;
}
async basicSearch(query) {
let p = query.split(' ');
let temp = [];
for (let i = 0; i < p.length; i++) {
let t = p[i].trim();
if (!t) continue;
temp.push(t);
}
return await Note.previews(null, {
anywherePattern: '*' + temp.join('*') + '*',
});
}
async search(query) {
query = this.normalizeText_(query);
const parsedQuery = this.parseQuery(query);
const sql = 'SELECT id, title, offsets(notes_fts) AS offsets FROM notes_fts WHERE notes_fts MATCH ?'
const rows = await this.db().selectAll(sql, [query]);
this.orderResults_(rows, parsedQuery);
return rows;
const st = scriptType(query);
if (!Setting.value('db.ftsEnabled') || ['ja', 'zh', 'ko'].indexOf(st) >= 0) {
// Non-alphabetical languages aren't support by SQLite FTS (except with extensions which are not available in all platforms)
return this.basicSearch(query);
} else {
const parsedQuery = this.parseQuery(query);
const sql = 'SELECT id, title, offsets(notes_fts) AS offsets FROM notes_fts WHERE notes_fts MATCH ?'
const rows = await this.db().selectAll(sql, [query]);
this.orderResults_(rows, parsedQuery);
return rows;
}
}
static runInBackground() {
if (this.isRunningInBackground_) return;
this.isRunningInBackground_ = true;
this.instance().syncTables();
setTimeout(() => {
this.instance().syncTables();
}, 1000 * 60 * 5);
}
}

View File

@ -1,92 +1,91 @@
const defaultDiacriticsRemovalMap = [
{'base':'A', 'letters':/[\u0041\u24B6\uFF21\u00C0\u00C1\u00C2\u1EA6\u1EA4\u1EAA\u1EA8\u00C3\u0100\u0102\u1EB0\u1EAE\u1EB4\u1EB2\u0226\u01E0\u00C4\u01DE\u1EA2\u00C5\u01FA\u01CD\u0200\u0202\u1EA0\u1EAC\u1EB6\u1E00\u0104\u023A\u2C6F]/g},
{'base':'AA','letters':/[\uA732]/g},
{'base':'AE','letters':/[\u00C6\u01FC\u01E2]/g},
{'base':'AO','letters':/[\uA734]/g},
{'base':'AU','letters':/[\uA736]/g},
{'base':'AV','letters':/[\uA738\uA73A]/g},
{'base':'AY','letters':/[\uA73C]/g},
{'base':'B', 'letters':/[\u0042\u24B7\uFF22\u1E02\u1E04\u1E06\u0243\u0182\u0181]/g},
{'base':'C', 'letters':/[\u0043\u24B8\uFF23\u0106\u0108\u010A\u010C\u00C7\u1E08\u0187\u023B\uA73E]/g},
{'base':'D', 'letters':/[\u0044\u24B9\uFF24\u1E0A\u010E\u1E0C\u1E10\u1E12\u1E0E\u0110\u018B\u018A\u0189\uA779]/g},
{'base':'DZ','letters':/[\u01F1\u01C4]/g},
{'base':'Dz','letters':/[\u01F2\u01C5]/g},
{'base':'E', 'letters':/[\u0045\u24BA\uFF25\u00C8\u00C9\u00CA\u1EC0\u1EBE\u1EC4\u1EC2\u1EBC\u0112\u1E14\u1E16\u0114\u0116\u00CB\u1EBA\u011A\u0204\u0206\u1EB8\u1EC6\u0228\u1E1C\u0118\u1E18\u1E1A\u0190\u018E]/g},
{'base':'F', 'letters':/[\u0046\u24BB\uFF26\u1E1E\u0191\uA77B]/g},
{'base':'G', 'letters':/[\u0047\u24BC\uFF27\u01F4\u011C\u1E20\u011E\u0120\u01E6\u0122\u01E4\u0193\uA7A0\uA77D\uA77E]/g},
{'base':'H', 'letters':/[\u0048\u24BD\uFF28\u0124\u1E22\u1E26\u021E\u1E24\u1E28\u1E2A\u0126\u2C67\u2C75\uA78D]/g},
{'base':'I', 'letters':/[\u0049\u24BE\uFF29\u00CC\u00CD\u00CE\u0128\u012A\u012C\u0130\u00CF\u1E2E\u1EC8\u01CF\u0208\u020A\u1ECA\u012E\u1E2C\u0197]/g},
{'base':'J', 'letters':/[\u004A\u24BF\uFF2A\u0134\u0248]/g},
{'base':'K', 'letters':/[\u004B\u24C0\uFF2B\u1E30\u01E8\u1E32\u0136\u1E34\u0198\u2C69\uA740\uA742\uA744\uA7A2]/g},
{'base':'L', 'letters':/[\u004C\u24C1\uFF2C\u013F\u0139\u013D\u1E36\u1E38\u013B\u1E3C\u1E3A\u0141\u023D\u2C62\u2C60\uA748\uA746\uA780]/g},
{'base':'LJ','letters':/[\u01C7]/g},
{'base':'Lj','letters':/[\u01C8]/g},
{'base':'M', 'letters':/[\u004D\u24C2\uFF2D\u1E3E\u1E40\u1E42\u2C6E\u019C]/g},
{'base':'N', 'letters':/[\u004E\u24C3\uFF2E\u01F8\u0143\u00D1\u1E44\u0147\u1E46\u0145\u1E4A\u1E48\u0220\u019D\uA790\uA7A4]/g},
{'base':'NJ','letters':/[\u01CA]/g},
{'base':'Nj','letters':/[\u01CB]/g},
{'base':'O', 'letters':/[\u004F\u24C4\uFF2F\u00D2\u00D3\u00D4\u1ED2\u1ED0\u1ED6\u1ED4\u00D5\u1E4C\u022C\u1E4E\u014C\u1E50\u1E52\u014E\u022E\u0230\u00D6\u022A\u1ECE\u0150\u01D1\u020C\u020E\u01A0\u1EDC\u1EDA\u1EE0\u1EDE\u1EE2\u1ECC\u1ED8\u01EA\u01EC\u00D8\u01FE\u0186\u019F\uA74A\uA74C]/g},
{'base':'OI','letters':/[\u01A2]/g},
{'base':'OO','letters':/[\uA74E]/g},
{'base':'OU','letters':/[\u0222]/g},
{'base':'P', 'letters':/[\u0050\u24C5\uFF30\u1E54\u1E56\u01A4\u2C63\uA750\uA752\uA754]/g},
{'base':'Q', 'letters':/[\u0051\u24C6\uFF31\uA756\uA758\u024A]/g},
{'base':'R', 'letters':/[\u0052\u24C7\uFF32\u0154\u1E58\u0158\u0210\u0212\u1E5A\u1E5C\u0156\u1E5E\u024C\u2C64\uA75A\uA7A6\uA782]/g},
{'base':'S', 'letters':/[\u0053\u24C8\uFF33\u1E9E\u015A\u1E64\u015C\u1E60\u0160\u1E66\u1E62\u1E68\u0218\u015E\u2C7E\uA7A8\uA784]/g},
{'base':'T', 'letters':/[\u0054\u24C9\uFF34\u1E6A\u0164\u1E6C\u021A\u0162\u1E70\u1E6E\u0166\u01AC\u01AE\u023E\uA786]/g},
{'base':'TZ','letters':/[\uA728]/g},
{'base':'U', 'letters':/[\u0055\u24CA\uFF35\u00D9\u00DA\u00DB\u0168\u1E78\u016A\u1E7A\u016C\u00DC\u01DB\u01D7\u01D5\u01D9\u1EE6\u016E\u0170\u01D3\u0214\u0216\u01AF\u1EEA\u1EE8\u1EEE\u1EEC\u1EF0\u1EE4\u1E72\u0172\u1E76\u1E74\u0244]/g},
{'base':'V', 'letters':/[\u0056\u24CB\uFF36\u1E7C\u1E7E\u01B2\uA75E\u0245]/g},
{'base':'VY','letters':/[\uA760]/g},
{'base':'W', 'letters':/[\u0057\u24CC\uFF37\u1E80\u1E82\u0174\u1E86\u1E84\u1E88\u2C72]/g},
{'base':'X', 'letters':/[\u0058\u24CD\uFF38\u1E8A\u1E8C]/g},
{'base':'Y', 'letters':/[\u0059\u24CE\uFF39\u1EF2\u00DD\u0176\u1EF8\u0232\u1E8E\u0178\u1EF6\u1EF4\u01B3\u024E\u1EFE]/g},
{'base':'Z', 'letters':/[\u005A\u24CF\uFF3A\u0179\u1E90\u017B\u017D\u1E92\u1E94\u01B5\u0224\u2C7F\u2C6B\uA762]/g},
{'base':'a', 'letters':/[\u0061\u24D0\uFF41\u1E9A\u00E0\u00E1\u00E2\u1EA7\u1EA5\u1EAB\u1EA9\u00E3\u0101\u0103\u1EB1\u1EAF\u1EB5\u1EB3\u0227\u01E1\u00E4\u01DF\u1EA3\u00E5\u01FB\u01CE\u0201\u0203\u1EA1\u1EAD\u1EB7\u1E01\u0105\u2C65\u0250]/g},
{'base':'aa','letters':/[\uA733]/g},
{'base':'ae','letters':/[\u00E6\u01FD\u01E3]/g},
{'base':'ao','letters':/[\uA735]/g},
{'base':'au','letters':/[\uA737]/g},
{'base':'av','letters':/[\uA739\uA73B]/g},
{'base':'ay','letters':/[\uA73D]/g},
{'base':'b', 'letters':/[\u0062\u24D1\uFF42\u1E03\u1E05\u1E07\u0180\u0183\u0253]/g},
{'base':'c', 'letters':/[\u0063\u24D2\uFF43\u0107\u0109\u010B\u010D\u00E7\u1E09\u0188\u023C\uA73F\u2184]/g},
{'base':'d', 'letters':/[\u0064\u24D3\uFF44\u1E0B\u010F\u1E0D\u1E11\u1E13\u1E0F\u0111\u018C\u0256\u0257\uA77A]/g},
{'base':'dz','letters':/[\u01F3\u01C6]/g},
{'base':'e', 'letters':/[\u0065\u24D4\uFF45\u00E8\u00E9\u00EA\u1EC1\u1EBF\u1EC5\u1EC3\u1EBD\u0113\u1E15\u1E17\u0115\u0117\u00EB\u1EBB\u011B\u0205\u0207\u1EB9\u1EC7\u0229\u1E1D\u0119\u1E19\u1E1B\u0247\u025B\u01DD]/g},
{'base':'f', 'letters':/[\u0066\u24D5\uFF46\u1E1F\u0192\uA77C]/g},
{'base':'g', 'letters':/[\u0067\u24D6\uFF47\u01F5\u011D\u1E21\u011F\u0121\u01E7\u0123\u01E5\u0260\uA7A1\u1D79\uA77F]/g},
{'base':'h', 'letters':/[\u0068\u24D7\uFF48\u0125\u1E23\u1E27\u021F\u1E25\u1E29\u1E2B\u1E96\u0127\u2C68\u2C76\u0265]/g},
{'base':'hv','letters':/[\u0195]/g},
{'base':'i', 'letters':/[\u0069\u24D8\uFF49\u00EC\u00ED\u00EE\u0129\u012B\u012D\u00EF\u1E2F\u1EC9\u01D0\u0209\u020B\u1ECB\u012F\u1E2D\u0268\u0131]/g},
{'base':'j', 'letters':/[\u006A\u24D9\uFF4A\u0135\u01F0\u0249]/g},
{'base':'k', 'letters':/[\u006B\u24DA\uFF4B\u1E31\u01E9\u1E33\u0137\u1E35\u0199\u2C6A\uA741\uA743\uA745\uA7A3]/g},
{'base':'l', 'letters':/[\u006C\u24DB\uFF4C\u0140\u013A\u013E\u1E37\u1E39\u013C\u1E3D\u1E3B\u017F\u0142\u019A\u026B\u2C61\uA749\uA781\uA747]/g},
{'base':'lj','letters':/[\u01C9]/g},
{'base':'m', 'letters':/[\u006D\u24DC\uFF4D\u1E3F\u1E41\u1E43\u0271\u026F]/g},
{'base':'n', 'letters':/[\u006E\u24DD\uFF4E\u01F9\u0144\u00F1\u1E45\u0148\u1E47\u0146\u1E4B\u1E49\u019E\u0272\u0149\uA791\uA7A5]/g},
{'base':'nj','letters':/[\u01CC]/g},
{'base':'o', 'letters':/[\u006F\u24DE\uFF4F\u00F2\u00F3\u00F4\u1ED3\u1ED1\u1ED7\u1ED5\u00F5\u1E4D\u022D\u1E4F\u014D\u1E51\u1E53\u014F\u022F\u0231\u00F6\u022B\u1ECF\u0151\u01D2\u020D\u020F\u01A1\u1EDD\u1EDB\u1EE1\u1EDF\u1EE3\u1ECD\u1ED9\u01EB\u01ED\u00F8\u01FF\u0254\uA74B\uA74D\u0275]/g},
{'base':'oi','letters':/[\u01A3]/g},
{'base':'ou','letters':/[\u0223]/g},
{'base':'oo','letters':/[\uA74F]/g},
{'base':'p','letters':/[\u0070\u24DF\uFF50\u1E55\u1E57\u01A5\u1D7D\uA751\uA753\uA755]/g},
{'base':'q','letters':/[\u0071\u24E0\uFF51\u024B\uA757\uA759]/g},
{'base':'r','letters':/[\u0072\u24E1\uFF52\u0155\u1E59\u0159\u0211\u0213\u1E5B\u1E5D\u0157\u1E5F\u024D\u027D\uA75B\uA7A7\uA783]/g},
{'base':'s','letters':/[\u0073\u24E2\uFF53\u00DF\u015B\u1E65\u015D\u1E61\u0161\u1E67\u1E63\u1E69\u0219\u015F\u023F\uA7A9\uA785\u1E9B]/g},
{'base':'t','letters':/[\u0074\u24E3\uFF54\u1E6B\u1E97\u0165\u1E6D\u021B\u0163\u1E71\u1E6F\u0167\u01AD\u0288\u2C66\uA787]/g},
{'base':'tz','letters':/[\uA729]/g},
{'base':'u','letters':/[\u0075\u24E4\uFF55\u00F9\u00FA\u00FB\u0169\u1E79\u016B\u1E7B\u016D\u00FC\u01DC\u01D8\u01D6\u01DA\u1EE7\u016F\u0171\u01D4\u0215\u0217\u01B0\u1EEB\u1EE9\u1EEF\u1EED\u1EF1\u1EE5\u1E73\u0173\u1E77\u1E75\u0289]/g},
{'base':'v','letters':/[\u0076\u24E5\uFF56\u1E7D\u1E7F\u028B\uA75F\u028C]/g},
{'base':'vy','letters':/[\uA761]/g},
{'base':'w','letters':/[\u0077\u24E6\uFF57\u1E81\u1E83\u0175\u1E87\u1E85\u1E98\u1E89\u2C73]/g},
{'base':'x','letters':/[\u0078\u24E7\uFF58\u1E8B\u1E8D]/g},
{'base':'y','letters':/[\u0079\u24E8\uFF59\u1EF3\u00FD\u0177\u1EF9\u0233\u1E8F\u00FF\u1EF7\u1E99\u1EF5\u01B4\u024F\u1EFF]/g},
{'base':'z','letters':/[\u007A\u24E9\uFF5A\u017A\u1E91\u017C\u017E\u1E93\u1E95\u01B6\u0225\u0240\u2C6C\uA763]/g}
];
function removeDiacritics(str) {
var defaultDiacriticsRemovalMap = [
{'base':'A', 'letters':/[\u0041\u24B6\uFF21\u00C0\u00C1\u00C2\u1EA6\u1EA4\u1EAA\u1EA8\u00C3\u0100\u0102\u1EB0\u1EAE\u1EB4\u1EB2\u0226\u01E0\u00C4\u01DE\u1EA2\u00C5\u01FA\u01CD\u0200\u0202\u1EA0\u1EAC\u1EB6\u1E00\u0104\u023A\u2C6F]/g},
{'base':'AA','letters':/[\uA732]/g},
{'base':'AE','letters':/[\u00C6\u01FC\u01E2]/g},
{'base':'AO','letters':/[\uA734]/g},
{'base':'AU','letters':/[\uA736]/g},
{'base':'AV','letters':/[\uA738\uA73A]/g},
{'base':'AY','letters':/[\uA73C]/g},
{'base':'B', 'letters':/[\u0042\u24B7\uFF22\u1E02\u1E04\u1E06\u0243\u0182\u0181]/g},
{'base':'C', 'letters':/[\u0043\u24B8\uFF23\u0106\u0108\u010A\u010C\u00C7\u1E08\u0187\u023B\uA73E]/g},
{'base':'D', 'letters':/[\u0044\u24B9\uFF24\u1E0A\u010E\u1E0C\u1E10\u1E12\u1E0E\u0110\u018B\u018A\u0189\uA779]/g},
{'base':'DZ','letters':/[\u01F1\u01C4]/g},
{'base':'Dz','letters':/[\u01F2\u01C5]/g},
{'base':'E', 'letters':/[\u0045\u24BA\uFF25\u00C8\u00C9\u00CA\u1EC0\u1EBE\u1EC4\u1EC2\u1EBC\u0112\u1E14\u1E16\u0114\u0116\u00CB\u1EBA\u011A\u0204\u0206\u1EB8\u1EC6\u0228\u1E1C\u0118\u1E18\u1E1A\u0190\u018E]/g},
{'base':'F', 'letters':/[\u0046\u24BB\uFF26\u1E1E\u0191\uA77B]/g},
{'base':'G', 'letters':/[\u0047\u24BC\uFF27\u01F4\u011C\u1E20\u011E\u0120\u01E6\u0122\u01E4\u0193\uA7A0\uA77D\uA77E]/g},
{'base':'H', 'letters':/[\u0048\u24BD\uFF28\u0124\u1E22\u1E26\u021E\u1E24\u1E28\u1E2A\u0126\u2C67\u2C75\uA78D]/g},
{'base':'I', 'letters':/[\u0049\u24BE\uFF29\u00CC\u00CD\u00CE\u0128\u012A\u012C\u0130\u00CF\u1E2E\u1EC8\u01CF\u0208\u020A\u1ECA\u012E\u1E2C\u0197]/g},
{'base':'J', 'letters':/[\u004A\u24BF\uFF2A\u0134\u0248]/g},
{'base':'K', 'letters':/[\u004B\u24C0\uFF2B\u1E30\u01E8\u1E32\u0136\u1E34\u0198\u2C69\uA740\uA742\uA744\uA7A2]/g},
{'base':'L', 'letters':/[\u004C\u24C1\uFF2C\u013F\u0139\u013D\u1E36\u1E38\u013B\u1E3C\u1E3A\u0141\u023D\u2C62\u2C60\uA748\uA746\uA780]/g},
{'base':'LJ','letters':/[\u01C7]/g},
{'base':'Lj','letters':/[\u01C8]/g},
{'base':'M', 'letters':/[\u004D\u24C2\uFF2D\u1E3E\u1E40\u1E42\u2C6E\u019C]/g},
{'base':'N', 'letters':/[\u004E\u24C3\uFF2E\u01F8\u0143\u00D1\u1E44\u0147\u1E46\u0145\u1E4A\u1E48\u0220\u019D\uA790\uA7A4]/g},
{'base':'NJ','letters':/[\u01CA]/g},
{'base':'Nj','letters':/[\u01CB]/g},
{'base':'O', 'letters':/[\u004F\u24C4\uFF2F\u00D2\u00D3\u00D4\u1ED2\u1ED0\u1ED6\u1ED4\u00D5\u1E4C\u022C\u1E4E\u014C\u1E50\u1E52\u014E\u022E\u0230\u00D6\u022A\u1ECE\u0150\u01D1\u020C\u020E\u01A0\u1EDC\u1EDA\u1EE0\u1EDE\u1EE2\u1ECC\u1ED8\u01EA\u01EC\u00D8\u01FE\u0186\u019F\uA74A\uA74C]/g},
{'base':'OI','letters':/[\u01A2]/g},
{'base':'OO','letters':/[\uA74E]/g},
{'base':'OU','letters':/[\u0222]/g},
{'base':'P', 'letters':/[\u0050\u24C5\uFF30\u1E54\u1E56\u01A4\u2C63\uA750\uA752\uA754]/g},
{'base':'Q', 'letters':/[\u0051\u24C6\uFF31\uA756\uA758\u024A]/g},
{'base':'R', 'letters':/[\u0052\u24C7\uFF32\u0154\u1E58\u0158\u0210\u0212\u1E5A\u1E5C\u0156\u1E5E\u024C\u2C64\uA75A\uA7A6\uA782]/g},
{'base':'S', 'letters':/[\u0053\u24C8\uFF33\u1E9E\u015A\u1E64\u015C\u1E60\u0160\u1E66\u1E62\u1E68\u0218\u015E\u2C7E\uA7A8\uA784]/g},
{'base':'T', 'letters':/[\u0054\u24C9\uFF34\u1E6A\u0164\u1E6C\u021A\u0162\u1E70\u1E6E\u0166\u01AC\u01AE\u023E\uA786]/g},
{'base':'TZ','letters':/[\uA728]/g},
{'base':'U', 'letters':/[\u0055\u24CA\uFF35\u00D9\u00DA\u00DB\u0168\u1E78\u016A\u1E7A\u016C\u00DC\u01DB\u01D7\u01D5\u01D9\u1EE6\u016E\u0170\u01D3\u0214\u0216\u01AF\u1EEA\u1EE8\u1EEE\u1EEC\u1EF0\u1EE4\u1E72\u0172\u1E76\u1E74\u0244]/g},
{'base':'V', 'letters':/[\u0056\u24CB\uFF36\u1E7C\u1E7E\u01B2\uA75E\u0245]/g},
{'base':'VY','letters':/[\uA760]/g},
{'base':'W', 'letters':/[\u0057\u24CC\uFF37\u1E80\u1E82\u0174\u1E86\u1E84\u1E88\u2C72]/g},
{'base':'X', 'letters':/[\u0058\u24CD\uFF38\u1E8A\u1E8C]/g},
{'base':'Y', 'letters':/[\u0059\u24CE\uFF39\u1EF2\u00DD\u0176\u1EF8\u0232\u1E8E\u0178\u1EF6\u1EF4\u01B3\u024E\u1EFE]/g},
{'base':'Z', 'letters':/[\u005A\u24CF\uFF3A\u0179\u1E90\u017B\u017D\u1E92\u1E94\u01B5\u0224\u2C7F\u2C6B\uA762]/g},
{'base':'a', 'letters':/[\u0061\u24D0\uFF41\u1E9A\u00E0\u00E1\u00E2\u1EA7\u1EA5\u1EAB\u1EA9\u00E3\u0101\u0103\u1EB1\u1EAF\u1EB5\u1EB3\u0227\u01E1\u00E4\u01DF\u1EA3\u00E5\u01FB\u01CE\u0201\u0203\u1EA1\u1EAD\u1EB7\u1E01\u0105\u2C65\u0250]/g},
{'base':'aa','letters':/[\uA733]/g},
{'base':'ae','letters':/[\u00E6\u01FD\u01E3]/g},
{'base':'ao','letters':/[\uA735]/g},
{'base':'au','letters':/[\uA737]/g},
{'base':'av','letters':/[\uA739\uA73B]/g},
{'base':'ay','letters':/[\uA73D]/g},
{'base':'b', 'letters':/[\u0062\u24D1\uFF42\u1E03\u1E05\u1E07\u0180\u0183\u0253]/g},
{'base':'c', 'letters':/[\u0063\u24D2\uFF43\u0107\u0109\u010B\u010D\u00E7\u1E09\u0188\u023C\uA73F\u2184]/g},
{'base':'d', 'letters':/[\u0064\u24D3\uFF44\u1E0B\u010F\u1E0D\u1E11\u1E13\u1E0F\u0111\u018C\u0256\u0257\uA77A]/g},
{'base':'dz','letters':/[\u01F3\u01C6]/g},
{'base':'e', 'letters':/[\u0065\u24D4\uFF45\u00E8\u00E9\u00EA\u1EC1\u1EBF\u1EC5\u1EC3\u1EBD\u0113\u1E15\u1E17\u0115\u0117\u00EB\u1EBB\u011B\u0205\u0207\u1EB9\u1EC7\u0229\u1E1D\u0119\u1E19\u1E1B\u0247\u025B\u01DD]/g},
{'base':'f', 'letters':/[\u0066\u24D5\uFF46\u1E1F\u0192\uA77C]/g},
{'base':'g', 'letters':/[\u0067\u24D6\uFF47\u01F5\u011D\u1E21\u011F\u0121\u01E7\u0123\u01E5\u0260\uA7A1\u1D79\uA77F]/g},
{'base':'h', 'letters':/[\u0068\u24D7\uFF48\u0125\u1E23\u1E27\u021F\u1E25\u1E29\u1E2B\u1E96\u0127\u2C68\u2C76\u0265]/g},
{'base':'hv','letters':/[\u0195]/g},
{'base':'i', 'letters':/[\u0069\u24D8\uFF49\u00EC\u00ED\u00EE\u0129\u012B\u012D\u00EF\u1E2F\u1EC9\u01D0\u0209\u020B\u1ECB\u012F\u1E2D\u0268\u0131]/g},
{'base':'j', 'letters':/[\u006A\u24D9\uFF4A\u0135\u01F0\u0249]/g},
{'base':'k', 'letters':/[\u006B\u24DA\uFF4B\u1E31\u01E9\u1E33\u0137\u1E35\u0199\u2C6A\uA741\uA743\uA745\uA7A3]/g},
{'base':'l', 'letters':/[\u006C\u24DB\uFF4C\u0140\u013A\u013E\u1E37\u1E39\u013C\u1E3D\u1E3B\u017F\u0142\u019A\u026B\u2C61\uA749\uA781\uA747]/g},
{'base':'lj','letters':/[\u01C9]/g},
{'base':'m', 'letters':/[\u006D\u24DC\uFF4D\u1E3F\u1E41\u1E43\u0271\u026F]/g},
{'base':'n', 'letters':/[\u006E\u24DD\uFF4E\u01F9\u0144\u00F1\u1E45\u0148\u1E47\u0146\u1E4B\u1E49\u019E\u0272\u0149\uA791\uA7A5]/g},
{'base':'nj','letters':/[\u01CC]/g},
{'base':'o', 'letters':/[\u006F\u24DE\uFF4F\u00F2\u00F3\u00F4\u1ED3\u1ED1\u1ED7\u1ED5\u00F5\u1E4D\u022D\u1E4F\u014D\u1E51\u1E53\u014F\u022F\u0231\u00F6\u022B\u1ECF\u0151\u01D2\u020D\u020F\u01A1\u1EDD\u1EDB\u1EE1\u1EDF\u1EE3\u1ECD\u1ED9\u01EB\u01ED\u00F8\u01FF\u0254\uA74B\uA74D\u0275]/g},
{'base':'oi','letters':/[\u01A3]/g},
{'base':'ou','letters':/[\u0223]/g},
{'base':'oo','letters':/[\uA74F]/g},
{'base':'p','letters':/[\u0070\u24DF\uFF50\u1E55\u1E57\u01A5\u1D7D\uA751\uA753\uA755]/g},
{'base':'q','letters':/[\u0071\u24E0\uFF51\u024B\uA757\uA759]/g},
{'base':'r','letters':/[\u0072\u24E1\uFF52\u0155\u1E59\u0159\u0211\u0213\u1E5B\u1E5D\u0157\u1E5F\u024D\u027D\uA75B\uA7A7\uA783]/g},
{'base':'s','letters':/[\u0073\u24E2\uFF53\u00DF\u015B\u1E65\u015D\u1E61\u0161\u1E67\u1E63\u1E69\u0219\u015F\u023F\uA7A9\uA785\u1E9B]/g},
{'base':'t','letters':/[\u0074\u24E3\uFF54\u1E6B\u1E97\u0165\u1E6D\u021B\u0163\u1E71\u1E6F\u0167\u01AD\u0288\u2C66\uA787]/g},
{'base':'tz','letters':/[\uA729]/g},
{'base':'u','letters':/[\u0075\u24E4\uFF55\u00F9\u00FA\u00FB\u0169\u1E79\u016B\u1E7B\u016D\u00FC\u01DC\u01D8\u01D6\u01DA\u1EE7\u016F\u0171\u01D4\u0215\u0217\u01B0\u1EEB\u1EE9\u1EEF\u1EED\u1EF1\u1EE5\u1E73\u0173\u1E77\u1E75\u0289]/g},
{'base':'v','letters':/[\u0076\u24E5\uFF56\u1E7D\u1E7F\u028B\uA75F\u028C]/g},
{'base':'vy','letters':/[\uA761]/g},
{'base':'w','letters':/[\u0077\u24E6\uFF57\u1E81\u1E83\u0175\u1E87\u1E85\u1E98\u1E89\u2C73]/g},
{'base':'x','letters':/[\u0078\u24E7\uFF58\u1E8B\u1E8D]/g},
{'base':'y','letters':/[\u0079\u24E8\uFF59\u1EF3\u00FD\u0177\u1EF9\u0233\u1E8F\u00FF\u1EF7\u1E99\u1EF5\u01B4\u024F\u1EFF]/g},
{'base':'z','letters':/[\u007A\u24E9\uFF5A\u017A\u1E91\u017C\u017E\u1E93\u1E95\u01B6\u0225\u0240\u2C6C\uA763]/g}
];
for(var i=0; i<defaultDiacriticsRemovalMap.length; i++) {
str = str.replace(defaultDiacriticsRemovalMap[i].letters, defaultDiacriticsRemovalMap[i].base);
}
@ -243,4 +242,15 @@ function surroundKeywords(keywords, text, prefix, suffix) {
return text.replace(re, prefix + '$1' + suffix);
}
module.exports = { removeDiacritics, escapeFilename, wrap, splitCommandString, padLeft, toTitleCase, urlDecode, escapeHtml, pregQuote, surroundKeywords };
const REGEX_JAPANESE = /[\u3000-\u303f]|[\u3040-\u309f]|[\u30a0-\u30ff]|[\uff00-\uff9f]|[\u4e00-\u9faf]|[\u3400-\u4dbf]/;
const REGEX_CHINESE = /[\u4e00-\u9fff]|[\u3400-\u4dbf]|[\u{20000}-\u{2a6df}]|[\u{2a700}-\u{2b73f}]|[\u{2b740}-\u{2b81f}]|[\u{2b820}-\u{2ceaf}]|[\uf900-\ufaff]|[\u3300-\u33ff]|[\ufe30-\ufe4f]|[\uf900-\ufaff]|[\u{2f800}-\u{2fa1f}]/u;
const REGEX_KOREAN = /[\uac00-\ud7af]|[\u1100-\u11ff]|[\u3130-\u318f]|[\ua960-\ua97f]|[\ud7b0-\ud7ff]/;
function scriptType(s) {
if (REGEX_JAPANESE.test(s)) return 'ja';
if (REGEX_CHINESE.test(s)) return 'zh';
if (REGEX_KOREAN.test(s)) return 'ko';
return 'en';
}
module.exports = { removeDiacritics, escapeFilename, wrap, splitCommandString, padLeft, toTitleCase, urlDecode, escapeHtml, pregQuote, surroundKeywords, scriptType };

View File

@ -2631,6 +2631,11 @@
"resolved": "https://registry.npmjs.org/detect-newline/-/detect-newline-2.1.0.tgz",
"integrity": "sha1-9B8cEL5LAOh7XxPaaAdZ8sW/0+I="
},
"diacritics": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/diacritics/-/diacritics-1.3.0.tgz",
"integrity": "sha1-PvqHMj67hj5mls67AILUj/PW96E="
},
"diff": {
"version": "3.4.0",
"resolved": "https://registry.npmjs.org/diff/-/diff-3.4.0.tgz",

View File

@ -13,6 +13,7 @@
"async-mutex": "^0.1.3",
"base-64": "^0.1.0",
"buffer": "^5.0.8",
"diacritics": "^1.3.0",
"events": "^1.1.1",
"form-data": "^2.1.4",
"html-entities": "^1.2.1",