blob: 80482c9aedd5a69821040d2e803a42cb899d1b1d (
plain)
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
|
/**
* This is a tiny purpose-built HTML parser/processor. This basically detects
* any type of visual newline and converts entire HTML into a array structure.
*
* Text nodes are represented as object with single property - text - containing
* the visual line. Intended usage is to process the array with .map() in which
* map function returns a string and resulting array can be converted back to html
* with a .join('').
*
* Generally this isn't very useful except for when you really need to either
* modify visual lines (greentext i.e. simple quoting) or do something with
* first/last line.
*
* known issue: doesn't handle CDATA so nested CDATA might not work well
*
* @param {Object} input - input data
* @return {(string|{ text: string })[]} processed html in form of a list.
*/
export const convertHtmlToLines = (html) => {
const handledTags = new Set(['p', 'br', 'div'])
const openCloseTags = new Set(['p', 'div'])
let buffer = [] // Current output buffer
const level = [] // How deep we are in tags and which tags were there
let textBuffer = '' // Current line content
let tagBuffer = null // Current tag buffer, if null = we are not currently reading a tag
// Extracts tag name from tag, i.e. <span a="b"> => span
const getTagName = (tag) => {
const result = /(?:<\/(\w+)>|<(\w+)\s?[^/]*?\/?>)/gi.exec(tag)
return result && (result[1] || result[2])
}
const flush = () => { // Processes current line buffer, adds it to output buffer and clears line buffer
if (textBuffer.trim().length > 0) {
buffer.push({ text: textBuffer })
} else {
buffer.push(textBuffer)
}
textBuffer = ''
}
const handleBr = (tag) => { // handles single newlines/linebreaks/selfclosing
flush()
buffer.push(tag)
}
const handleOpen = (tag) => { // handles opening tags
flush()
buffer.push(tag)
level.push(tag)
}
const handleClose = (tag) => { // handles closing tags
flush()
buffer.push(tag)
if (level[level.length - 1] === tag) {
level.pop()
}
}
for (let i = 0; i < html.length; i++) {
const char = html[i]
if (char === '<' && tagBuffer === null) {
tagBuffer = char
} else if (char !== '>' && tagBuffer !== null) {
tagBuffer += char
} else if (char === '>' && tagBuffer !== null) {
tagBuffer += char
const tagFull = tagBuffer
tagBuffer = null
const tagName = getTagName(tagFull)
if (handledTags.has(tagName)) {
if (tagName === 'br') {
handleBr(tagFull)
} else if (openCloseTags.has(tagName)) {
if (tagFull[1] === '/') {
handleClose(tagFull)
} else if (tagFull[tagFull.length - 2] === '/') {
// self-closing
handleBr(tagFull)
} else {
handleOpen(tagFull)
}
}
} else {
textBuffer += tagFull
}
} else if (char === '\n') {
handleBr(char)
} else {
textBuffer += char
}
}
if (tagBuffer) {
textBuffer += tagBuffer
}
flush()
return buffer
}
|
