File size: 6,288 Bytes
89ce340
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import { startsWith, endsWith } from 'lodash'
import type { Token } from './types'
import { childlessTags } from './tags'

interface State {
  str: string
  position: number
  tokens: Token[]
}

const jumpPosition = (state: State, end: number) => {
  const len = end - state.position
  movePositopn(state, len)
}

const movePositopn = (state: State, len: number) => {
  state.position = state.position + len
}

const findTextEnd = (str: string, index: number) => {
  const isEnd = false
  while (!isEnd) {
    const textEnd = str.indexOf('<', index)
    if (textEnd === -1) {
      return textEnd
    }
    const char = str.charAt(textEnd + 1)
    if (char === '/' || char === '!' || /[A-Za-z0-9]/.test(char)) {
      return textEnd
    }
    index = textEnd + 1
  }
  return -1
}

const lexText = (state: State) => {
  const { str } = state
  let textEnd = findTextEnd(str, state.position)
  if (textEnd === state.position) return
  if (textEnd === -1) {
    textEnd = str.length
  }

  const content = str.slice(state.position, textEnd)
  jumpPosition(state, textEnd)

  state.tokens.push({
    type: 'text', 
    content, 
  })
}

const lexComment = (state: State) => {
  const { str } = state

  movePositopn(state, 4)
  let contentEnd = str.indexOf('-->', state.position)
  let commentEnd = contentEnd + 3
  if (contentEnd === -1) {
    contentEnd = commentEnd = str.length
  }

  const content = str.slice(state.position, contentEnd)
  jumpPosition(state, commentEnd)

  state.tokens.push({
    type: 'comment',
    content,
  })
}

const lexTagName = (state: State) => {
  const { str } = state
  const len = str.length
  let start = state.position

  while (start < len) {
    const char = str.charAt(start)
    const isTagChar = !(/\s/.test(char) || char === '/' || char === '>')
    if (isTagChar) break
    start++
  }

  let end = start + 1
  while (end < len) {
    const char = str.charAt(end)
    const isTagChar = !(/\s/.test(char) || char === '/' || char === '>')
    if (!isTagChar) break
    end++
  }

  jumpPosition(state, end)
  const tagName = str.slice(start, end)
  state.tokens.push({
    type: 'tag',
    content: tagName
  })
  return tagName
}

const lexTagAttributes = (state: State) => {
  const { str, tokens } = state
  let cursor = state.position
  let quote = null
  let wordBegin = cursor
  const words = []
  const len = str.length
  while (cursor < len) {
    const char = str.charAt(cursor)
    if (quote) {
      const isQuoteEnd = char === quote
      if (isQuoteEnd) quote = null
      cursor++
      continue
    }

    const isTagEnd = char === '/' || char === '>'
    if (isTagEnd) {
      if (cursor !== wordBegin) words.push(str.slice(wordBegin, cursor))
      break
    }

    const isWordEnd = /\s/.test(char)
    if (isWordEnd) {
      if (cursor !== wordBegin) words.push(str.slice(wordBegin, cursor))
      wordBegin = cursor + 1
      cursor++
      continue
    }

    const isQuoteStart = char === '\'' || char === '"'
    if (isQuoteStart) {
      quote = char
      cursor++
      continue
    }

    cursor++
  }
  jumpPosition(state, cursor)

  const type = 'attribute'
  for (let i = 0; i < words.length; i++) {
    const word = words[i]

    const isNotPair = word.indexOf('=') === -1
    if (isNotPair) {
      const secondWord = words[i + 1]
      if (secondWord && startsWith(secondWord, '=')) {
        if (secondWord.length > 1) {
          const newWord = word + secondWord
          tokens.push({ type, content: newWord })
          i += 1
          continue
        }
        const thirdWord = words[i + 2]
        i += 1
        if (thirdWord) {
          const newWord = word + '=' + thirdWord
          tokens.push({ type, content: newWord })
          i += 1
          continue
        }
      }
    }
    if (endsWith(word, '=')) {
      const secondWord = words[i + 1]
      if (secondWord && secondWord.indexOf('=') === -1) {
        const newWord = word + secondWord
        tokens.push({ type, content: newWord })
        i += 1
        continue
      }

      const newWord = word.slice(0, -1)
      tokens.push({ type, content: newWord })
      continue
    }

    tokens.push({ type, content: word })
  }
}

const lexSkipTag = (tagName: string, state: State) => {
  const { str, tokens } = state
  const safeTagName = tagName.toLowerCase()
  const len = str.length
  let index = state.position
  
  while (index < len) {
    const nextTag = str.indexOf('</', index)
    if (nextTag === -1) {
      lexText(state)
      break
    }

    const tagState = {
      str,
      position: state.position,
      tokens: [],
    }
    jumpPosition(tagState, nextTag)
    const name = lexTag(tagState)
    if (safeTagName !== name.toLowerCase()) {
      index = tagState.position
      continue
    }

    if (nextTag !== state.position) {
      const textStart = state.position
      jumpPosition(state, nextTag)
      tokens.push({
        type: 'text',
        content: str.slice(textStart, nextTag),
      })
    }

    tokens.push(...tagState.tokens)
    jumpPosition(state, tagState.position)
    break
  }
}

const lexTag = (state: State) => {
  const { str } = state
  const secondChar = str.charAt(state.position + 1)
  const tagStartClose = secondChar === '/'
  movePositopn(state, tagStartClose ? 2 : 1)
  state.tokens.push({
    type: 'tag-start',
    close: tagStartClose,
  })

  const tagName = lexTagName(state)
  lexTagAttributes(state)

  const firstChar = str.charAt(state.position)
  const tagEndClose = firstChar === '/'
  movePositopn(state, tagEndClose ? 2 : 1)
  state.tokens.push({
    type: 'tag-end',
    close: tagEndClose,
  })
  return tagName
}

const lex = (state: State) => {
  const str = state.str
  const len = str.length

  while (state.position < len) {
    const start = state.position
    lexText(state)

    if (state.position === start) {
      const isComment = startsWith(str, '!--', start + 1)
      if (isComment) lexComment(state)
      else {
        const tagName = lexTag(state)
        const safeTag = tagName.toLowerCase()
        if (childlessTags.includes(safeTag)) lexSkipTag(tagName, state)
      }
    }
  }
}

export const lexer = (str: string): Token[] => {
  const state = {
    str,
    position: 0,
    tokens: [],
  }
  lex(state)
  return state.tokens
}