summary refs log tree commit diff stats
path: root/lib/pure/yamllexer.nim
blob: 4640179c192743b7c09e8a9e42f645b0bf1cbd19 (plain) (blame)
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
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
#
#
#            Nimrod's Runtime Library
#        (c) Copyright 2010 Andreas Rumpf
#
#    See the file "copying.txt", included in this
#    distribution, for details about the copyright.
#

## This module implements a simple high performance `YAML`:idx:
## lexer. This is used by the ``yamlparser`` module, but it can be useful
## to avoid ``yamlparser`` for its overhead. 

import 
  hashes, strutils, lexbase, streams, unicode

type 
  TTokenKind* = enum ## YAML tokens
    tkError,
    tkEof,
    tkString,
    tkNumber,
    tkTrue,
    tkFalse,
    tkNull,
    tkCurlyLe,
    tkCurlyRi,
    tkBracketLe,
    tkBracketRi,
    tkColon,
    tkComma

  TYamlLexer* = object of TBaseLexer ## the lexer object.
    a: string
    kind: TJsonEventKind
    err: TJsonError
    state: seq[TParserState]
    filename: string
 
proc open*(my: var TYamlLexer, input: PStream, filename: string) =
  ## initializes the parser with an input stream. `Filename` is only used
  ## for nice error messages.
  lexbase.open(my, input)
  my.filename = filename
  my.state = @[stateNormal]
  my.kind = jsonError
  my.a = ""
  
proc close*(my: var TYamlLexer) {.inline.} = 
  ## closes the parser `my` and its associated input stream.
  lexbase.close(my)

proc getColumn*(my: TYamlLexer): int {.inline.} = 
  ## get the current column the parser has arrived at.
  result = getColNumber(my, my.bufPos)

proc getLine*(my: TYamlLexer): int {.inline.} = 
  ## get the current line the parser has arrived at.
  result = my.linenumber

proc getFilename*(my: TYamlLexer): string {.inline.} = 
  ## get the filename of the file that the parser processes.
  result = my.filename
  
proc handleHexChar(c: Char, x: var TRune): bool = 
  result = true # Success
  case c
  of '0'..'9': x = (x shl 4) or (ord(c) - ord('0'))
  of 'a'..'f': x = (x shl 4) or (ord(c) - ord('a') + 10)
  of 'A'..'F': x = (x shl 4) or (ord(c) - ord('A') + 10)
  else: result = false # error

proc parseString(my: var TYamlLexer): TTokKind =
  result = tkString
  var pos = my.bufpos + 1
  var buf = my.buf
  while true:
    case buf[pos] 
    of '\0': 
      my.err = errQuoteExpected
      result = tkError
      break
    of '"':
      inc(pos)
      break
    of '\\':
      case buf[pos+1]
      of '\\', '"', '\'', '/': 
        add(my.a, buf[pos+1])
        inc(pos, 2)
      of 'b':
        add(my.a, '\b')
        inc(pos, 2)      
      of 'f':
        add(my.a, '\f')
        inc(pos, 2)      
      of 'n':
        add(my.a, '\L')
        inc(pos, 2)      
      of 'r':
        add(my.a, '\C')
        inc(pos, 2)    
      of 't':
        add(my.a, '\t')
        inc(pos, 2)
      of 'u':
        inc(pos, 2)
        var r: TRune
        if handleHexChar(buf[pos], r): inc(pos)
        if handleHexChar(buf[pos], r): inc(pos)
        if handleHexChar(buf[pos], r): inc(pos)
        if handleHexChar(buf[pos], r): inc(pos)
        add(my.a, toUTF8(r))
      else: 
        # don't bother with the error
        add(my.a, buf[pos])
        inc(pos)
    of '\c': 
      pos = lexbase.HandleCR(my, pos)
      buf = my.buf
      add(my.a, '\c')
    of '\L': 
      pos = lexbase.HandleLF(my, pos)
      buf = my.buf
      add(my.a, '\L')
    else:
      add(my.a, buf[pos])
      inc(pos)
  my.bufpos = pos # store back
  
proc skip(my: var TYamlLexer) = 
  var pos = my.bufpos
  var buf = my.buf
  while true: 
    case buf[pos]
    of '#':
      # skip line comment:
      inc(pos)
      while true:
        case buf[pos] 
        of '\0': break
        of '\c': 
          pos = lexbase.HandleCR(my, pos)
          buf = my.buf
          break
        of '\L': 
          pos = lexbase.HandleLF(my, pos)
          buf = my.buf
          break
        else:
          inc(pos)
    of '/': 
      if buf[pos+1] == '/': 
        # skip line comment:
        inc(pos, 2)
        while true:
          case buf[pos] 
          of '\0': 
            break
          of '\c': 
            pos = lexbase.HandleCR(my, pos)
            buf = my.buf
            break
          of '\L': 
            pos = lexbase.HandleLF(my, pos)
            buf = my.buf
            break
          else:
            inc(pos)
      elif buf[pos+1] == '*':
        # skip long comment:
        inc(pos, 2)
        while true:
          case buf[pos] 
          of '\0': 
            my.err = errEOC_Expected
            break
          of '\c': 
            pos = lexbase.HandleCR(my, pos)
            buf = my.buf
          of '\L': 
            pos = lexbase.HandleLF(my, pos)
            buf = my.buf
          of '*':
            inc(pos)
            if buf[pos] == '/': 
              inc(pos)
              break
          else:
            inc(pos)
      else: 
        break
    of ' ', '\t': 
      Inc(pos)
    of '\c':  
      pos = lexbase.HandleCR(my, pos)
      buf = my.buf
    of '\L': 
      pos = lexbase.HandleLF(my, pos)
      buf = my.buf
    else:
      break
  my.bufpos = pos

proc parseDirective(my: var TYamlLexer) = 
  var pos = my.bufpos
  var buf = my.buf
  inc(pos)
  while buf[pos] in {'\t', ' '}: inc(pos)
  while true:
    case buf[pos] 
    of '\0': break
    of '\c': 
      pos = lexbase.HandleCR(my, pos)
      buf = my.buf
      break
    of '\L': 
      pos = lexbase.HandleLF(my, pos)
      buf = my.buf
      break
    else:
      add(my.a, buf[pos])
      inc(pos)

proc parseNumber(my: var TYamlLexer) = 
  var pos = my.bufpos
  var buf = my.buf
  if buf[pos] == '-': 
    add(my.a, '-')
    inc(pos)
  if buf[pos] == '.': 
    add(my.a, "0.")
    inc(pos)
  else:
    while buf[pos] in Digits:
      add(my.a, buf[pos])
      inc(pos)
    if buf[pos] == '.':
      add(my.a, '.')
      inc(pos)
  # digits after the dot:
  while buf[pos] in Digits:
    add(my.a, buf[pos])
    inc(pos)
  if buf[pos] in {'E', 'e'}:
    add(my.a, buf[pos])
    inc(pos)
    if buf[pos] in {'+', '-'}:
      add(my.a, buf[pos])
      inc(pos)
    while buf[pos] in Digits:
      add(my.a, buf[pos])
      inc(pos)
  my.bufpos = pos

proc parseName(my: var TYamlLexer) = 
  var pos = my.bufpos
  var buf = my.buf
  if buf[pos] in IdentStartChars:
    while buf[pos] in IdentChars:
      add(my.a, buf[pos])
      inc(pos)
  my.bufpos = pos

proc getTok(my: var TYamlLexer): TTokKind = 
  setLen(my.a, 0)
  skip(my) # skip whitespace, comments
  case my.buf[my.bufpos]
  of '-': 
    inc(my.bufpos)
    result = tkHyphen
  of '-', '.', '0'..'9': 
    parseNumber(my)
    result = tkNumber
  of '"':
    result = parseString(my)
  of '\'':
    result = parseSingleQuote(my)
  of '[':
    inc(my.bufpos)
    result = tkBracketLe
  of '{':
    inc(my.bufpos)
    result = tkCurlyLe
  of ']':
    inc(my.bufpos)
    result = tkBracketRi
  of '}':
    inc(my.bufpos)
    result = tkCurlyRi
  of ',':
    inc(my.bufpos)
    result = tkComma
  of ':':
    inc(my.bufpos)
    result = tkColon
  of '?':
    inc(my.bufpos)
    result = tkQust
  of '!':
    inc(my.bufpos)
    result = tkExcl
  of '&':
    inc(my.bufpos)
    result = tkAmp
  of '*':
    inc(my.bufpos)
    result = tkStar
  of '|':
    parseLiteralBlockScalar(my)
    result = tkLiteralBlockScalar
  of '>':
    parseFoldedBlockScalar(my)
    result = tkFoldedBlockScalar
  of '%': 
    parseDirective(my)
    result = tkDirective
  of '@', '`': 
    inc(my.bufpos)
    result = tkReserved
  of 'a'..'z', 'A'..'Z', '_':
    parseName(my)
    case my.a 
    of "null": result = tkNull
    of "true": result = tkTrue
    of "false": result = tkFalse
    else: result = tkError
  of '\0':
    result = tkEof
  else: 
    inc(my.bufpos)
    result = tkError
  
when isMainModule:
  import os
  var s = newFileStream(ParamStr(1), fmRead)
  if s == nil: quit("cannot open the file" & ParamStr(1))
  var x: TYamlLexer
  open(x, s, ParamStr(1))
  while true:
    next(x)
    case x.kind
    of jsonError: Echo(x.errorMsg())
    of jsonEof: break
    of jsonString, jsonNumber: echo(x.str)
    of jsonTrue: Echo("!TRUE")
    of jsonFalse: Echo("!FALSE")
    of jsonNull: Echo("!NULL")
    of jsonObjectStart: Echo("{")
    of jsonObjectEnd: Echo("}")
    of jsonArrayStart: Echo("[")
    of jsonArrayEnd: Echo("]")
    
  close(x)