-
Notifications
You must be signed in to change notification settings - Fork 89
Expand file tree
/
Copy pathsearch.ts
More file actions
302 lines (247 loc) · 6.76 KB
/
search.ts
File metadata and controls
302 lines (247 loc) · 6.76 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
import PageData from '../models/page.js';
import Pages from '../controllers/pages.js';
import urlify from '../utils/urlify.js';
import Page from '../models/page.js';
let globalWords: { [key: string]: {[key: string]: number} } = Object.create(null);
let globalPages: PageData[] = [];
class Search {
/**
* Initialize search
*/
public async init() {
if (globalWords && Object.keys(globalWords).length) {
return Promise.resolve();
}
await this.syncDB();
}
/**
* Load all pages from DB and update globalWords
* Use this method when any page was updated
*/
public async syncDB() {
globalWords = Object.create(null);
globalPages = await this.getPages();
/**
* Process all pages
*/
for await (const page of globalPages) {
/**
* Read content blocks from page
*/
for await (const block of page.body.blocks) {
const blockRatio = this.getBlockRatio(block);
const blockContent = this.getCleanTextFromBlock(block);
const blockWords: string[] = this.splitTextToWords(blockContent);
/**
* Process list of words in a block
*/
for await (const word of blockWords) {
if (!globalWords[word]) {
globalWords[word] = Object.create(null);
}
if (page._id) {
if (!globalWords[word][page._id]) {
globalWords[word][page._id] = 0;
}
/**
* Add page id to the list of pages with this word
*/
globalWords[word][page._id] += blockRatio;
}
}
}
}
console.log('Done');
}
/**
* Search for pages by given query
* @param searchString
*/
public async query(searchString: string) {
await this.init();
const searchWords = this.splitTextToWords(searchString);
const goodPages = (await this.getPagesByWords(searchWords))
.slice(0, 10);
const returnPages: {[key: string]: string|number, ratio: number}[] = [];
goodPages.forEach(({ pageId, ratio }) => {
const page = globalPages.filter(page => page._id === pageId).pop();
if (!page) {
return;
}
let section = '';
page.body.blocks.forEach((block: any) => {
let koef = 1;
let blockContent = this.getCleanTextFromBlock(block);
let shortBody = blockContent;
if (block.type === 'header') {
section = blockContent;
}
searchWords.forEach(word => {
if (blockContent.toLowerCase().indexOf(word) !== -1) {
koef *= 10;
}
})
shortBody = this.highlightSubstring(shortBody, searchWords);
if (koef > 0) {
returnPages.push({
...page,
shortBody,
anchor: urlify(section),
section,
ratio: ratio * koef,
})
}
});
});
return {
suggestions: ['description', 'about', 'contact'],
pages: returnPages
.sort((a, b) => b.ratio - a.ratio)
.slice(0, 15)
}
}
/**
*
* @private
*/
private async getPages(): Promise<Page[]> {
return await Pages.getAll();
}
/**
* Return list of pages with a given words
* @param words
* @private
*/
private async getPagesByWords(words: string[]) {
const pagesList: {[key: string]: number} = {};
/**
* Get list of words starting with a words from the search query
*/
const validWords = Object.keys(globalWords)
.filter(word => {
return !!words.filter(searchWord => word.indexOf(searchWord) !== -1).length
});
/**
* For each word get list of pages with this word
*/
validWords.forEach(word => {
Object.keys(globalWords[word])
.forEach(pageId => {
if (!pagesList[pageId]) {
pagesList[pageId] = 0;
}
pagesList[pageId] += globalWords[word][pageId]
})
})
/**
* Sort pages by frequency of given words
*/
const sortedPagesList = Object.keys(pagesList)
.map(pageId => {
return {
pageId,
ratio: pagesList[pageId]
}
})
.sort((a, b) => b.ratio - a.ratio);
return sortedPagesList;
}
/**
* Get block's ratio. It is used to calculate the weight of the words in the block
* @param block
* @private
*/
private getBlockRatio(block: any) {
switch (block.type) {
case 'header':
if (block.data.level === 1) {
return 16;
} else {
return 2;
}
case 'paragraph':
return 1.1;
case 'list':
return 1;
default:
return 0;
}
}
/**
* Return clear text content from block without HTML tags and special characters
* @param block
* @private
*/
private getCleanTextFromBlock(block: any): string {
let blockContent = '';
switch (block.type) {
case 'header':
blockContent = block.data.text;
break;
case 'paragraph':
blockContent = block.data.text
break;
case 'list':
blockContent = block.data.items.join(' ');
break;
default:
return blockContent;
}
blockContent = this.removeHTMLTags(blockContent);
blockContent = this.removeHTMLSpecialCharacters(blockContent);
return blockContent;
}
/**
* Remove HTML tags from string. Only content inside tags will be left
* @param text
* @private
*/
private removeHTMLTags(text: string) {
return text.replace(/<[^>]*>?/gm, '');
}
/**
* Remove special characters from text. For example: & " < >
* @param text
* @private
*/
private removeHTMLSpecialCharacters(text: string) {
return text.replace(/&[^;]*;?/gm, '');
}
/**
* Split text to words
* @param text
* @private
*/
private splitTextToWords(text: string): string[] {
return text
// lowercase all words
.toLowerCase()
// remove punctuation
.replace(/[.,;:]/gi, '')
// left only letters (+cyrillic) and numbers
.replace(/[^a-zа-я0-9]/gi, ' ')
// remove multiple spaces
.replace(/\s+/g, ' ')
// remove spaces at the beginning and at the end
.trim()
// split to words by spaces
.split(' ')
// ignore words shorter than 3 chars
.filter(word => word.length >= 3);
}
/**
* Highlight substring in string with a span wrapper
*/
private highlightSubstring(text: string, words: string|string[]) {
if (typeof words === 'string') {
words = [words];
}
const wordRegExp = new RegExp(words.join('|'), "ig");
const CLASS_STYLE = 'search-word';
return text.replace(wordRegExp, `<span class="${CLASS_STYLE}">$&</span>`);
}
}
/**
* Export initialized instance
*/
export default new Search();