mirror of
https://gitee.com/docsifyjs/docsify.git
synced 2024-12-01 19:50:32 +08:00
fix(search): clean markdown elements in search contents (#2457)
Co-authored-by: John Hildenbiddle <jhildenbiddle@users.noreply.github.com>
This commit is contained in:
parent
298cc4441d
commit
95901eb8a8
@ -49,12 +49,13 @@ function doSearch(value) {
|
||||
|
||||
let html = '';
|
||||
matches.forEach((post, i) => {
|
||||
const content = post.content ? `...${post.content}...` : '';
|
||||
const title = (post.title || '').replace(/<[^>]+>/g, '');
|
||||
html += /* html */ `
|
||||
<div class="matching-post" aria-label="search result ${i + 1}">
|
||||
<a href="${post.url}" title="${title}">
|
||||
<p class="title clamp-1">${post.title}</p>
|
||||
<p class="content clamp-2">${post.content}</p>
|
||||
<p class="content clamp-2">${content}</p>
|
||||
</a>
|
||||
</div>
|
||||
`;
|
||||
|
197
src/plugins/search/markdown-to-txt.js
Normal file
197
src/plugins/search/markdown-to-txt.js
Normal file
@ -0,0 +1,197 @@
|
||||
/**
|
||||
* This is a function to convert markdown to txt based on markedjs v13+.
|
||||
* Copies the escape/unescape functions from [lodash](https://www.npmjs.com/package/lodash) instead import to reduce the size.
|
||||
*/
|
||||
import { marked } from 'marked';
|
||||
|
||||
const reEscapedHtml = /&(?:amp|lt|gt|quot|#(0+)?39);/g;
|
||||
const reHasEscapedHtml = RegExp(reEscapedHtml.source);
|
||||
const htmlUnescapes = {
|
||||
'&': '&',
|
||||
'<': '<',
|
||||
'>': '>',
|
||||
'"': '"',
|
||||
''': "'",
|
||||
};
|
||||
|
||||
function unescape(string) {
|
||||
return string && reHasEscapedHtml.test(string)
|
||||
? string.replace(reEscapedHtml, entity => htmlUnescapes[entity] || "'")
|
||||
: string || '';
|
||||
}
|
||||
|
||||
const reUnescapedHtml = /[&<>"']/g;
|
||||
const reHasUnescapedHtml = RegExp(reUnescapedHtml.source);
|
||||
const htmlEscapes = {
|
||||
'&': '&',
|
||||
'<': '<',
|
||||
'>': '>',
|
||||
'"': '"',
|
||||
"'": ''',
|
||||
};
|
||||
|
||||
function escape(string) {
|
||||
return string && reHasUnescapedHtml.test(string)
|
||||
? string.replace(reUnescapedHtml, chr => htmlEscapes[chr])
|
||||
: string || '';
|
||||
}
|
||||
|
||||
function helpersCleanup(string) {
|
||||
return string && string.replace('!>', '').replace('?>', '');
|
||||
}
|
||||
|
||||
const markdownToTxtRenderer = {
|
||||
space() {
|
||||
return '';
|
||||
},
|
||||
|
||||
code({ text }) {
|
||||
const code = text.replace(/\n$/, '');
|
||||
return escape(code);
|
||||
},
|
||||
|
||||
blockquote({ tokens }) {
|
||||
return this.parser?.parse(tokens) || '';
|
||||
},
|
||||
|
||||
html() {
|
||||
return '';
|
||||
},
|
||||
|
||||
heading({ tokens }) {
|
||||
return this.parser?.parse(tokens) || '';
|
||||
},
|
||||
|
||||
hr() {
|
||||
return '';
|
||||
},
|
||||
|
||||
list(token) {
|
||||
let body = '';
|
||||
for (let j = 0; j < token.items.length; j++) {
|
||||
const item = token.items[j];
|
||||
body += this.listitem?.(item);
|
||||
}
|
||||
|
||||
return body;
|
||||
},
|
||||
|
||||
listitem(item) {
|
||||
let itemBody = '';
|
||||
if (item.task) {
|
||||
const checkbox = this.checkbox?.({ checked: !!item.checked });
|
||||
if (item.loose) {
|
||||
if (item.tokens.length > 0 && item.tokens[0].type === 'paragraph') {
|
||||
item.tokens[0].text = checkbox + ' ' + item.tokens[0].text;
|
||||
if (
|
||||
item.tokens[0].tokens &&
|
||||
item.tokens[0].tokens.length > 0 &&
|
||||
item.tokens[0].tokens[0].type === 'text'
|
||||
) {
|
||||
item.tokens[0].tokens[0].text =
|
||||
checkbox + ' ' + item.tokens[0].tokens[0].text;
|
||||
}
|
||||
} else {
|
||||
item.tokens.unshift({
|
||||
type: 'text',
|
||||
raw: checkbox + ' ',
|
||||
text: checkbox + ' ',
|
||||
});
|
||||
}
|
||||
} else {
|
||||
itemBody += checkbox + ' ';
|
||||
}
|
||||
}
|
||||
|
||||
itemBody += this.parser?.parse(item.tokens, !!item.loose);
|
||||
|
||||
return `${itemBody || ''}`;
|
||||
},
|
||||
|
||||
checkbox() {
|
||||
return '';
|
||||
},
|
||||
|
||||
paragraph({ tokens }) {
|
||||
return this.parser?.parseInline(tokens) || '';
|
||||
},
|
||||
|
||||
table(token) {
|
||||
let header = '';
|
||||
|
||||
let cell = '';
|
||||
for (let j = 0; j < token.header.length; j++) {
|
||||
cell += this.tablecell?.(token.header[j]);
|
||||
}
|
||||
header += this.tablerow?.({ text: cell });
|
||||
|
||||
let body = '';
|
||||
for (let j = 0; j < token.rows.length; j++) {
|
||||
const row = token.rows[j];
|
||||
|
||||
cell = '';
|
||||
for (let k = 0; k < row.length; k++) {
|
||||
cell += this.tablecell?.(row[k]);
|
||||
}
|
||||
|
||||
body += this.tablerow?.({ text: cell });
|
||||
}
|
||||
|
||||
return header + ' ' + body;
|
||||
},
|
||||
|
||||
tablerow({ text }) {
|
||||
return text;
|
||||
},
|
||||
|
||||
tablecell(token) {
|
||||
return this.parser?.parseInline(token.tokens) || '';
|
||||
},
|
||||
|
||||
strong({ text }) {
|
||||
return text;
|
||||
},
|
||||
|
||||
em({ tokens }) {
|
||||
return this.parser?.parseInline(tokens) || '';
|
||||
},
|
||||
|
||||
codespan({ text }) {
|
||||
return text;
|
||||
},
|
||||
|
||||
br() {
|
||||
return ' ';
|
||||
},
|
||||
|
||||
del({ tokens }) {
|
||||
return this.parser?.parseInline(tokens);
|
||||
},
|
||||
|
||||
link({ tokens, href, title }) {
|
||||
// Remain the href and title attributes for searching, so is the image
|
||||
// e.g. [filename](_media/example.js ':include :type=code :fragment=demo')
|
||||
// Result: filename _media/example.js :include :type=code :fragment=demo
|
||||
return `${this.parser?.parseInline(tokens) || ''} ${href || ''} ${title || ''}`;
|
||||
},
|
||||
|
||||
image({ title, text, href }) {
|
||||
return `${text || ''} ${href || ''} ${title || ''}`;
|
||||
},
|
||||
|
||||
text(token) {
|
||||
return token.tokens
|
||||
? this.parser?.parseInline(token.tokens) || ''
|
||||
: token.text || '';
|
||||
},
|
||||
};
|
||||
const _marked = marked.setOptions({ renderer: markdownToTxtRenderer });
|
||||
|
||||
export function markdownToTxt(markdown) {
|
||||
const unmarked = _marked.parse(markdown);
|
||||
const unescaped = unescape(unmarked);
|
||||
const helpersCleaned = helpersCleanup(unescaped);
|
||||
return helpersCleaned.trim();
|
||||
}
|
||||
|
||||
export default markdownToTxt;
|
@ -2,6 +2,7 @@ import {
|
||||
getAndRemoveConfig,
|
||||
getAndRemoveDocsifyIgnoreConfig,
|
||||
} from '../../core/render/utils.js';
|
||||
import { markdownToTxt } from './markdown-to-txt.js';
|
||||
import Dexie from 'dexie';
|
||||
|
||||
let INDEXES = {};
|
||||
@ -134,7 +135,7 @@ export function genIndex(path, content = '', router, depth, indexKey) {
|
||||
index[slug] = {
|
||||
slug,
|
||||
title: path !== '/' ? path.slice(1) : 'Home Page',
|
||||
body: token.text || '',
|
||||
body: markdownToTxt(token.text || ''),
|
||||
path: path,
|
||||
indexKey: indexKey,
|
||||
};
|
||||
@ -150,12 +151,12 @@ export function genIndex(path, content = '', router, depth, indexKey) {
|
||||
token.text = getTableData(token);
|
||||
token.text = getListData(token);
|
||||
|
||||
index[slug].body += '\n' + (token.text || '');
|
||||
index[slug].body += '\n' + markdownToTxt(token.text || '');
|
||||
} else {
|
||||
token.text = getTableData(token);
|
||||
token.text = getListData(token);
|
||||
|
||||
index[slug].body = token.text || '';
|
||||
index[slug].body = markdownToTxt(token.text || '');
|
||||
}
|
||||
|
||||
index[slug].path = path;
|
||||
@ -229,8 +230,8 @@ export function search(query) {
|
||||
start = indexContent < 11 ? 0 : indexContent - 10;
|
||||
end = start === 0 ? 100 : indexContent + keyword.length + 90;
|
||||
|
||||
if (postContent && end > postContent.length) {
|
||||
end = postContent.length;
|
||||
if (handlePostContent && end > handlePostContent.length) {
|
||||
end = handlePostContent.length;
|
||||
}
|
||||
|
||||
const matchContent =
|
||||
|
@ -232,4 +232,105 @@ test.describe('Search Plugin Tests', () => {
|
||||
await page.keyboard.press('z');
|
||||
await expect(searchFieldElm).toBeFocused();
|
||||
});
|
||||
test('search result should remove markdown code block', async ({ page }) => {
|
||||
const docsifyInitConfig = {
|
||||
markdown: {
|
||||
homepage: `
|
||||
# Hello World
|
||||
|
||||
searchHere
|
||||
\`\`\`js
|
||||
console.log('Hello World');
|
||||
\`\`\`
|
||||
`,
|
||||
},
|
||||
scriptURLs: ['/dist/plugins/search.js'],
|
||||
};
|
||||
|
||||
const searchFieldElm = page.locator('input[type=search]');
|
||||
const resultsHeadingElm = page.locator('.results-panel .content');
|
||||
|
||||
await docsifyInit(docsifyInitConfig);
|
||||
await searchFieldElm.fill('searchHere');
|
||||
// there is a newline after searchHere and the markdown part ```js ``` it should be removed
|
||||
expect(await resultsHeadingElm.textContent()).toContain(
|
||||
"...searchHere\nconsole.log('Hello World');...",
|
||||
);
|
||||
});
|
||||
|
||||
test('search result should remove file markdown and keep href attribution for files', async ({
|
||||
page,
|
||||
}) => {
|
||||
const docsifyInitConfig = {
|
||||
markdown: {
|
||||
homepage: `
|
||||
# Hello World
|
||||
![filename](_media/example.js ':include :type=code :fragment=demo')
|
||||
`,
|
||||
},
|
||||
scriptURLs: ['/dist/plugins/search.js'],
|
||||
};
|
||||
|
||||
const searchFieldElm = page.locator('input[type=search]');
|
||||
const resultsHeadingElm = page.locator('.results-panel .content');
|
||||
|
||||
await docsifyInit(docsifyInitConfig);
|
||||
await searchFieldElm.fill('filename');
|
||||
expect(await resultsHeadingElm.textContent()).toContain(
|
||||
'...filename _media/example.js :include :type=code :fragment=demo...',
|
||||
);
|
||||
});
|
||||
|
||||
test('search result should remove checkbox markdown and keep related values', async ({
|
||||
page,
|
||||
}) => {
|
||||
const docsifyInitConfig = {
|
||||
markdown: {
|
||||
homepage: `
|
||||
# Hello World
|
||||
|
||||
- [ ] Task 1
|
||||
- [x] SearchHere
|
||||
- [ ] Task 3
|
||||
`,
|
||||
},
|
||||
scriptURLs: ['/dist/plugins/search.js'],
|
||||
};
|
||||
|
||||
const searchFieldElm = page.locator('input[type=search]');
|
||||
const resultsHeadingElm = page.locator('.results-panel .content');
|
||||
|
||||
await docsifyInit(docsifyInitConfig);
|
||||
await searchFieldElm.fill('SearchHere');
|
||||
// remove the checkbox markdown and keep the related values
|
||||
expect(await resultsHeadingElm.textContent()).toContain(
|
||||
'...Task 1 SearchHere Task 3...',
|
||||
);
|
||||
});
|
||||
|
||||
test('search result should remove docsify self helper markdown and keep related values', async ({
|
||||
page,
|
||||
}) => {
|
||||
const docsifyInitConfig = {
|
||||
markdown: {
|
||||
homepage: `
|
||||
# Hello World
|
||||
|
||||
!> SearchHere to check it!
|
||||
|
||||
`,
|
||||
},
|
||||
scriptURLs: ['/dist/plugins/search.js'],
|
||||
};
|
||||
|
||||
const searchFieldElm = page.locator('input[type=search]');
|
||||
const resultsHeadingElm = page.locator('.results-panel .content');
|
||||
|
||||
await docsifyInit(docsifyInitConfig);
|
||||
await searchFieldElm.fill('SearchHere');
|
||||
// remove the helper markdown and keep the related values
|
||||
expect(await resultsHeadingElm.textContent()).toContain(
|
||||
'...SearchHere to check it!...',
|
||||
);
|
||||
});
|
||||
});
|
||||
|
Loading…
Reference in New Issue
Block a user