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
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
|
package lexer
import (
"bytes"
"fmt"
"regexp"
"strings"
"unicode/utf8"
"github.com/graphql-go/graphql/gqlerrors"
"github.com/graphql-go/graphql/language/source"
)
const (
EOF = iota + 1
BANG
DOLLAR
PAREN_L
PAREN_R
SPREAD
COLON
EQUALS
AT
BRACKET_L
BRACKET_R
BRACE_L
PIPE
BRACE_R
NAME
INT
FLOAT
STRING
BLOCK_STRING
)
var TokenKind map[int]int
var tokenDescription map[int]string
func init() {
TokenKind = make(map[int]int)
tokenDescription = make(map[int]string)
TokenKind[EOF] = EOF
TokenKind[BANG] = BANG
TokenKind[DOLLAR] = DOLLAR
TokenKind[PAREN_L] = PAREN_L
TokenKind[PAREN_R] = PAREN_R
TokenKind[SPREAD] = SPREAD
TokenKind[COLON] = COLON
TokenKind[EQUALS] = EQUALS
TokenKind[AT] = AT
TokenKind[BRACKET_L] = BRACKET_L
TokenKind[BRACKET_R] = BRACKET_R
TokenKind[BRACE_L] = BRACE_L
TokenKind[PIPE] = PIPE
TokenKind[BRACE_R] = BRACE_R
TokenKind[NAME] = NAME
TokenKind[INT] = INT
TokenKind[FLOAT] = FLOAT
TokenKind[STRING] = STRING
TokenKind[BLOCK_STRING] = BLOCK_STRING
tokenDescription[TokenKind[EOF]] = "EOF"
tokenDescription[TokenKind[BANG]] = "!"
tokenDescription[TokenKind[DOLLAR]] = "$"
tokenDescription[TokenKind[PAREN_L]] = "("
tokenDescription[TokenKind[PAREN_R]] = ")"
tokenDescription[TokenKind[SPREAD]] = "..."
tokenDescription[TokenKind[COLON]] = ":"
tokenDescription[TokenKind[EQUALS]] = "="
tokenDescription[TokenKind[AT]] = "@"
tokenDescription[TokenKind[BRACKET_L]] = "["
tokenDescription[TokenKind[BRACKET_R]] = "]"
tokenDescription[TokenKind[BRACE_L]] = "{"
tokenDescription[TokenKind[PIPE]] = "|"
tokenDescription[TokenKind[BRACE_R]] = "}"
tokenDescription[TokenKind[NAME]] = "Name"
tokenDescription[TokenKind[INT]] = "Int"
tokenDescription[TokenKind[FLOAT]] = "Float"
tokenDescription[TokenKind[STRING]] = "String"
tokenDescription[TokenKind[BLOCK_STRING]] = "BlockString"
}
// Token is a representation of a lexed Token. Value only appears for non-punctuation
// tokens: NAME, INT, FLOAT, and STRING.
type Token struct {
Kind int
Start int
End int
Value string
}
type Lexer func(resetPosition int) (Token, error)
func Lex(s *source.Source) Lexer {
var prevPosition int
return func(resetPosition int) (Token, error) {
if resetPosition == 0 {
resetPosition = prevPosition
}
token, err := readToken(s, resetPosition)
if err != nil {
return token, err
}
prevPosition = token.End
return token, nil
}
}
// Reads an alphanumeric + underscore name from the source.
// [_A-Za-z][_0-9A-Za-z]*
// position: Points to the byte position in the byte array
// runePosition: Points to the rune position in the byte array
func readName(source *source.Source, position, runePosition int) Token {
body := source.Body
bodyLength := len(body)
endByte := position + 1
endRune := runePosition + 1
for {
code, _ := runeAt(body, endByte)
if (endByte != bodyLength) &&
(code == '_' || // _
code >= '0' && code <= '9' || // 0-9
code >= 'A' && code <= 'Z' || // A-Z
code >= 'a' && code <= 'z') { // a-z
endByte++
endRune++
continue
} else {
break
}
}
return makeToken(TokenKind[NAME], runePosition, endRune, string(body[position:endByte]))
}
// Reads a number token from the source file, either a float
// or an int depending on whether a decimal point appears.
// Int: -?(0|[1-9][0-9]*)
// Float: -?(0|[1-9][0-9]*)(\.[0-9]+)?((E|e)(+|-)?[0-9]+)?
func readNumber(s *source.Source, start int, firstCode rune, codeLength int) (Token, error) {
code := firstCode
body := s.Body
position := start
isFloat := false
if code == '-' { // -
position += codeLength
code, codeLength = runeAt(body, position)
}
if code == '0' { // 0
position += codeLength
code, codeLength = runeAt(body, position)
if code >= '0' && code <= '9' {
description := fmt.Sprintf("Invalid number, unexpected digit after 0: %v.", printCharCode(code))
return Token{}, gqlerrors.NewSyntaxError(s, position, description)
}
} else {
p, err := readDigits(s, position, code, codeLength)
if err != nil {
return Token{}, err
}
position = p
code, codeLength = runeAt(body, position)
}
if code == '.' { // .
isFloat = true
position += codeLength
code, codeLength = runeAt(body, position)
p, err := readDigits(s, position, code, codeLength)
if err != nil {
return Token{}, err
}
position = p
code, codeLength = runeAt(body, position)
}
if code == 'E' || code == 'e' { // E e
isFloat = true
position += codeLength
code, codeLength = runeAt(body, position)
if code == '+' || code == '-' { // + -
position += codeLength
code, codeLength = runeAt(body, position)
}
p, err := readDigits(s, position, code, codeLength)
if err != nil {
return Token{}, err
}
position = p
}
kind := TokenKind[INT]
if isFloat {
kind = TokenKind[FLOAT]
}
return makeToken(kind, start, position, string(body[start:position])), nil
}
// Returns the new position in the source after reading digits.
func readDigits(s *source.Source, start int, firstCode rune, codeLength int) (int, error) {
body := s.Body
position := start
code := firstCode
if code >= '0' && code <= '9' { // 0 - 9
for {
if code >= '0' && code <= '9' { // 0 - 9
position += codeLength
code, codeLength = runeAt(body, position)
continue
} else {
break
}
}
return position, nil
}
var description string
description = fmt.Sprintf("Invalid number, expected digit but got: %v.", printCharCode(code))
return position, gqlerrors.NewSyntaxError(s, position, description)
}
func readString(s *source.Source, start int) (Token, error) {
body := s.Body
position := start + 1
runePosition := start + 1
chunkStart := position
var code rune
var n int
var valueBuffer bytes.Buffer
for {
code, n = runeAt(body, position)
if position < len(body) &&
// not LineTerminator
code != 0x000A && code != 0x000D &&
// not Quote (")
code != '"' {
// SourceCharacter
if code < 0x0020 && code != 0x0009 {
return Token{}, gqlerrors.NewSyntaxError(s, runePosition, fmt.Sprintf(`Invalid character within String: %v.`, printCharCode(code)))
}
position += n
runePosition++
if code == '\\' { // \
valueBuffer.Write(body[chunkStart : position-1])
code, n = runeAt(body, position)
switch code {
case '"':
valueBuffer.WriteRune('"')
break
case '/':
valueBuffer.WriteRune('/')
break
case '\\':
valueBuffer.WriteRune('\\')
break
case 'b':
valueBuffer.WriteRune('\b')
break
case 'f':
valueBuffer.WriteRune('\f')
break
case 'n':
valueBuffer.WriteRune('\n')
break
case 'r':
valueBuffer.WriteRune('\r')
break
case 't':
valueBuffer.WriteRune('\t')
break
case 'u':
// Check if there are at least 4 bytes available
if len(body) <= position+4 {
return Token{}, gqlerrors.NewSyntaxError(s, runePosition,
fmt.Sprintf("Invalid character escape sequence: "+
"\\u%v", string(body[position+1:])))
}
charCode := uniCharCode(
rune(body[position+1]),
rune(body[position+2]),
rune(body[position+3]),
rune(body[position+4]),
)
if charCode < 0 {
return Token{}, gqlerrors.NewSyntaxError(s, runePosition,
fmt.Sprintf("Invalid character escape sequence: "+
"\\u%v", string(body[position+1:position+5])))
}
valueBuffer.WriteRune(charCode)
position += 4
runePosition += 4
break
default:
return Token{}, gqlerrors.NewSyntaxError(s, runePosition,
fmt.Sprintf(`Invalid character escape sequence: \\%c.`, code))
}
position += n
runePosition++
chunkStart = position
}
continue
} else {
break
}
}
if code != '"' { // quote (")
return Token{}, gqlerrors.NewSyntaxError(s, runePosition, "Unterminated string.")
}
stringContent := body[chunkStart:position]
valueBuffer.Write(stringContent)
value := valueBuffer.String()
return makeToken(TokenKind[STRING], start, position+1, value), nil
}
// readBlockString reads a block string token from the source file.
//
// """("?"?(\\"""|\\(?!=""")|[^"\\]))*"""
func readBlockString(s *source.Source, start int) (Token, error) {
body := s.Body
position := start + 3
runePosition := start + 3
chunkStart := position
var valueBuffer bytes.Buffer
for {
// Stop if we've reached the end of the buffer
if position >= len(body) {
break
}
code, n := runeAt(body, position)
// Closing Triple-Quote (""")
if code == '"' {
x, _ := runeAt(body, position+1)
y, _ := runeAt(body, position+2)
if x == '"' && y == '"' {
stringContent := body[chunkStart:position]
valueBuffer.Write(stringContent)
value := blockStringValue(valueBuffer.String())
return makeToken(TokenKind[BLOCK_STRING], start, position+3, value), nil
}
}
// SourceCharacter
if code < 0x0020 &&
code != 0x0009 &&
code != 0x000a &&
code != 0x000d {
return Token{}, gqlerrors.NewSyntaxError(s, runePosition, fmt.Sprintf(`Invalid character within String: %v.`, printCharCode(code)))
}
// Escape Triple-Quote (\""")
if code == '\\' { // \
x, _ := runeAt(body, position+1)
y, _ := runeAt(body, position+2)
z, _ := runeAt(body, position+3)
if x == '"' && y == '"' && z == '"' {
stringContent := append(body[chunkStart:position], []byte(`"""`)...)
valueBuffer.Write(stringContent)
position += 4 // account for `"""` characters
runePosition += 4 // " " " "
chunkStart = position
continue
}
}
position += n
runePosition++
}
return Token{}, gqlerrors.NewSyntaxError(s, runePosition, "Unterminated string.")
}
var splitLinesRegex = regexp.MustCompile("\r\n|[\n\r]")
// This implements the GraphQL spec's BlockStringValue() static algorithm.
//
// Produces the value of a block string from its parsed raw value, similar to
// Coffeescript's block string, Python's docstring trim or Ruby's strip_heredoc.
//
// Spec: http://facebook.github.io/graphql/draft/#BlockStringValue()
// Heavily borrows from: https://github.com/graphql/graphql-js/blob/8e0c599ceccfa8c40d6edf3b72ee2a71490b10e0/src/language/blockStringValue.js
func blockStringValue(in string) string {
// Expand a block string's raw value into independent lines.
lines := splitLinesRegex.Split(in, -1)
// Remove common indentation from all lines but first
commonIndent := -1
for i := 1; i < len(lines); i++ {
line := lines[i]
indent := leadingWhitespaceLen(line)
if indent < len(line) && (commonIndent == -1 || indent < commonIndent) {
commonIndent = indent
if commonIndent == 0 {
break
}
}
}
if commonIndent > 0 {
for i, line := range lines {
if commonIndent > len(line) {
continue
}
lines[i] = line[commonIndent:]
}
}
// Remove leading blank lines.
for {
if isBlank := lineIsBlank(lines[0]); !isBlank {
break
}
lines = lines[1:]
}
// Remove trailing blank lines.
for {
i := len(lines) - 1
if isBlank := lineIsBlank(lines[i]); !isBlank {
break
}
lines = append(lines[:i], lines[i+1:]...)
}
// Return a string of the lines joined with U+000A.
return strings.Join(lines, "\n")
}
// leadingWhitespaceLen returns count of whitespace characters on given line.
func leadingWhitespaceLen(in string) (n int) {
for _, ch := range in {
if ch == ' ' || ch == '\t' {
n++
} else {
break
}
}
return
}
// lineIsBlank returns true when given line has no content.
func lineIsBlank(in string) bool {
return leadingWhitespaceLen(in) == len(in)
}
// Converts four hexidecimal chars to the integer that the
// string represents. For example, uniCharCode('0','0','0','f')
// will return 15, and uniCharCode('0','0','f','f') returns 255.
// Returns a negative number on error, if a char was invalid.
// This is implemented by noting that char2hex() returns -1 on error,
// which means the result of ORing the char2hex() will also be negative.
func uniCharCode(a, b, c, d rune) rune {
return rune(char2hex(a)<<12 | char2hex(b)<<8 | char2hex(c)<<4 | char2hex(d))
}
// Converts a hex character to its integer value.
// '0' becomes 0, '9' becomes 9
// 'A' becomes 10, 'F' becomes 15
// 'a' becomes 10, 'f' becomes 15
// Returns -1 on error.
func char2hex(a rune) int {
if a >= 48 && a <= 57 { // 0-9
return int(a) - 48
} else if a >= 65 && a <= 70 { // A-F
return int(a) - 55
} else if a >= 97 && a <= 102 {
// a-f
return int(a) - 87
}
return -1
}
func makeToken(kind int, start int, end int, value string) Token {
return Token{Kind: kind, Start: start, End: end, Value: value}
}
func printCharCode(code rune) string {
// NaN/undefined represents access beyond the end of the file.
if code < 0 {
return "<EOF>"
}
// print as ASCII for printable range
if code >= 0x0020 && code < 0x007F {
return fmt.Sprintf(`"%c"`, code)
}
// Otherwise print the escaped form. e.g. `"\\u0007"`
return fmt.Sprintf(`"\\u%04X"`, code)
}
func readToken(s *source.Source, fromPosition int) (Token, error) {
body := s.Body
bodyLength := len(body)
position, runePosition := positionAfterWhitespace(body, fromPosition)
if position >= bodyLength {
return makeToken(TokenKind[EOF], position, position, ""), nil
}
code, codeLength := runeAt(body, position)
// SourceCharacter
if code < 0x0020 && code != 0x0009 && code != 0x000A && code != 0x000D {
return Token{}, gqlerrors.NewSyntaxError(s, runePosition, fmt.Sprintf(`Invalid character %v`, printCharCode(code)))
}
switch code {
// !
case '!':
return makeToken(TokenKind[BANG], position, position+1, ""), nil
// $
case '$':
return makeToken(TokenKind[DOLLAR], position, position+1, ""), nil
// (
case '(':
return makeToken(TokenKind[PAREN_L], position, position+1, ""), nil
// )
case ')':
return makeToken(TokenKind[PAREN_R], position, position+1, ""), nil
// .
case '.':
next1, _ := runeAt(body, position+1)
next2, _ := runeAt(body, position+2)
if next1 == '.' && next2 == '.' {
return makeToken(TokenKind[SPREAD], position, position+3, ""), nil
}
break
// :
case ':':
return makeToken(TokenKind[COLON], position, position+1, ""), nil
// =
case '=':
return makeToken(TokenKind[EQUALS], position, position+1, ""), nil
// @
case '@':
return makeToken(TokenKind[AT], position, position+1, ""), nil
// [
case '[':
return makeToken(TokenKind[BRACKET_L], position, position+1, ""), nil
// ]
case ']':
return makeToken(TokenKind[BRACKET_R], position, position+1, ""), nil
// {
case '{':
return makeToken(TokenKind[BRACE_L], position, position+1, ""), nil
// |
case '|':
return makeToken(TokenKind[PIPE], position, position+1, ""), nil
// }
case '}':
return makeToken(TokenKind[BRACE_R], position, position+1, ""), nil
// A-Z
case 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N',
'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z':
return readName(s, position, runePosition), nil
// _
// a-z
case '_', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n',
'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z':
return readName(s, position, runePosition), nil
// -
// 0-9
case '-', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
token, err := readNumber(s, position, code, codeLength)
if err != nil {
return token, err
}
return token, nil
// "
case '"':
var token Token
var err error
x, _ := runeAt(body, position+1)
y, _ := runeAt(body, position+2)
if x == '"' && y == '"' {
token, err = readBlockString(s, position)
} else {
token, err = readString(s, position)
}
return token, err
}
description := fmt.Sprintf("Unexpected character %v.", printCharCode(code))
return Token{}, gqlerrors.NewSyntaxError(s, runePosition, description)
}
// Gets the rune from the byte array at given byte position and it's width in bytes
func runeAt(body []byte, position int) (code rune, charWidth int) {
if len(body) <= position {
// <EOF>
return -1, utf8.RuneError
}
c := body[position]
if c < utf8.RuneSelf {
return rune(c), 1
}
r, n := utf8.DecodeRune(body[position:])
return r, n
}
// Reads from body starting at startPosition until it finds a non-whitespace
// or commented character, then returns the position of that character for lexing.
// lexing.
// Returns both byte positions and rune position
func positionAfterWhitespace(body []byte, startPosition int) (position int, runePosition int) {
bodyLength := len(body)
position = startPosition
runePosition = startPosition
for {
if position < bodyLength {
code, n := runeAt(body, position)
// Skip Ignored
if code == 0xFEFF || // BOM
// White Space
code == 0x0009 || // tab
code == 0x0020 || // space
// Line Terminator
code == 0x000A || // new line
code == 0x000D || // carriage return
// Comma
code == 0x002C {
position += n
runePosition++
} else if code == 35 { // #
position += n
runePosition++
for {
code, n := runeAt(body, position)
if position < bodyLength &&
code != 0 &&
// SourceCharacter but not LineTerminator
(code > 0x001F || code == 0x0009) && code != 0x000A && code != 0x000D {
position += n
runePosition++
continue
} else {
break
}
}
} else {
break
}
continue
} else {
break
}
}
return position, runePosition
}
func GetTokenDesc(token Token) string {
if token.Value == "" {
return GetTokenKindDesc(token.Kind)
}
return fmt.Sprintf("%s \"%s\"", GetTokenKindDesc(token.Kind), token.Value)
}
func GetTokenKindDesc(kind int) string {
return tokenDescription[kind]
}
|