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
|
//go:generate maleeni compile lexspec.json -o clexspec.json
//go:generate maleeni-go clexspec.json --package parser
package parser
import (
_ "embed"
"fmt"
"io"
"regexp"
"strings"
verr "urubu/error"
)
type tokenKind string
const (
tokenKindKWFragment = tokenKind("fragment")
tokenKindID = tokenKind("id")
tokenKindTerminalPattern = tokenKind("terminal pattern")
tokenKindStringLiteral = tokenKind("string")
tokenKindColon = tokenKind(":")
tokenKindOr = tokenKind("|")
tokenKindSemicolon = tokenKind(";")
tokenKindLabelMarker = tokenKind("@")
tokenKindDirectiveMarker = tokenKind("#")
tokenKindExpantion = tokenKind("...")
tokenKindOrderedSymbolMarker = tokenKind("$")
tokenKindLParen = tokenKind("(")
tokenKindRParen = tokenKind(")")
tokenKindNewline = tokenKind("newline")
tokenKindEOF = tokenKind("eof")
tokenKindInvalid = tokenKind("invalid")
)
var (
reIDChar = regexp.MustCompile(`^[0-9a-z_]+$`)
reIDInvalidDigitsPos = regexp.MustCompile(`^[0-9]`)
)
type Position struct {
Row int
Col int
}
func newPosition(row, col int) Position {
return Position{
Row: row,
Col: col,
}
}
type token struct {
kind tokenKind
text string
pos Position
}
func newSymbolToken(kind tokenKind, pos Position) *token {
return &token{
kind: kind,
pos: pos,
}
}
func newIDToken(text string, pos Position) *token {
return &token{
kind: tokenKindID,
text: text,
pos: pos,
}
}
func newTerminalPatternToken(text string, pos Position) *token {
return &token{
kind: tokenKindTerminalPattern,
text: text,
pos: pos,
}
}
func newStringLiteralToken(text string, pos Position) *token {
return &token{
kind: tokenKindStringLiteral,
text: text,
pos: pos,
}
}
func newEOFToken() *token {
return &token{
kind: tokenKindEOF,
}
}
func newInvalidToken(text string, pos Position) *token {
return &token{
kind: tokenKindInvalid,
text: text,
pos: pos,
}
}
type lexer struct {
d *Lexer
buf *token
}
func newLexer(src io.Reader) (*lexer, error) {
d, err := NewLexer(NewLexSpec(), src)
if err != nil {
return nil, err
}
return &lexer{
d: d,
}, nil
}
func (l *lexer) next() (*token, error) {
if l.buf != nil {
tok := l.buf
l.buf = nil
return tok, nil
}
var newline *token
for {
tok, err := l.lexAndSkipWSs()
if err != nil {
return nil, err
}
if tok.kind == tokenKindNewline {
newline = tok
continue
}
if newline != nil {
l.buf = tok
return newline, nil
}
return tok, nil
}
}
func (l *lexer) lexAndSkipWSs() (*token, error) {
var tok *Token
for {
var err error
tok, err = l.d.Next()
if err != nil {
return nil, err
}
if tok.Invalid {
return newInvalidToken(string(tok.Lexeme), newPosition(tok.Row+1, tok.Col+1)), nil
}
if tok.EOF {
return newEOFToken(), nil
}
switch tok.KindID {
case KindIDWhiteSpace:
continue
case KindIDLineComment:
continue
}
break
}
switch tok.KindID {
case KindIDNewline:
return newSymbolToken(tokenKindNewline, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDKwFragment:
return newSymbolToken(tokenKindKWFragment, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDIdentifier:
if !reIDChar.Match(tok.Lexeme) {
return nil, &verr.SpecError{
Cause: synErrIDInvalidChar,
Detail: string(tok.Lexeme),
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
if strings.HasPrefix(string(tok.Lexeme), "_") || strings.HasSuffix(string(tok.Lexeme), "_") {
return nil, &verr.SpecError{
Cause: synErrIDInvalidUnderscorePos,
Detail: string(tok.Lexeme),
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
if strings.Contains(string(tok.Lexeme), "__") {
return nil, &verr.SpecError{
Cause: synErrIDConsecutiveUnderscores,
Detail: string(tok.Lexeme),
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
if reIDInvalidDigitsPos.Match(tok.Lexeme) {
return nil, &verr.SpecError{
Cause: synErrIDInvalidDigitsPos,
Detail: string(tok.Lexeme),
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
return newIDToken(string(tok.Lexeme), newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDTerminalOpen:
var b strings.Builder
for {
tok, err := l.d.Next()
if err != nil {
return nil, err
}
if tok.EOF {
return nil, &verr.SpecError{
Cause: synErrUnclosedTerminal,
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
switch tok.KindID {
case KindIDPattern:
// The escape sequences in a pattern string are interpreted by the lexer, except for the \".
// We must interpret the \" before passing them to the lexer because they are delimiters for
// the pattern strings.
fmt.Fprint(&b, strings.ReplaceAll(string(tok.Lexeme), `\"`, `"`))
case KindIDEscapeSymbol:
return nil, &verr.SpecError{
Cause: synErrIncompletedEscSeq,
Row: tok.Row + 1,
Col: tok.Col + 1,
}
case KindIDTerminalClose:
pat := b.String()
if pat == "" {
return nil, &verr.SpecError{
Cause: synErrEmptyPattern,
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
return newTerminalPatternToken(pat, newPosition(tok.Row+1, tok.Col+1)), nil
}
}
case KindIDStringLiteralOpen:
var b strings.Builder
for {
tok, err := l.d.Next()
if err != nil {
return nil, err
}
if tok.EOF {
return nil, &verr.SpecError{
Cause: synErrUnclosedString,
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
switch tok.KindID {
case KindIDCharSeq:
fmt.Fprint(&b, string(tok.Lexeme))
case KindIDStringLiteralClose:
str := b.String()
if str == "" {
return nil, &verr.SpecError{
Cause: synErrEmptyString,
Row: tok.Row + 1,
Col: tok.Col + 1,
}
}
return newStringLiteralToken(str, newPosition(tok.Row+1, tok.Col+1)), nil
}
}
case KindIDColon:
return newSymbolToken(tokenKindColon, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDOr:
return newSymbolToken(tokenKindOr, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDSemicolon:
return newSymbolToken(tokenKindSemicolon, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDLabelMarker:
return newSymbolToken(tokenKindLabelMarker, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDDirectiveMarker:
return newSymbolToken(tokenKindDirectiveMarker, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDExpansion:
return newSymbolToken(tokenKindExpantion, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDOrderedSymbolMarker:
return newSymbolToken(tokenKindOrderedSymbolMarker, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDLParen:
return newSymbolToken(tokenKindLParen, newPosition(tok.Row+1, tok.Col+1)), nil
case KindIDRParen:
return newSymbolToken(tokenKindRParen, newPosition(tok.Row+1, tok.Col+1)), nil
default:
return newInvalidToken(string(tok.Lexeme), newPosition(tok.Row+1, tok.Col+1)), nil
}
}
|
