gearsco.de
A JavaScript lexer and syntax highlighter for Gleam!
Switch to using `next` function
+100
-161
+98
-161
src/just.gleam
+98
-161
src/just.gleam
···
55
}
56
57
fn do_tokenise(lexer: Lexer, tokens: List(Token)) -> List(Token) {
58
case lexer.source {
59
-
"" -> list.reverse(tokens)
60
61
"\u{0009}" as space <> source
62
| "\u{000B}" as space <> source
···
78
| "\u{205F}" as space <> source
79
| "\u{3000}" as space <> source
80
| "\u{FEFF}" as space <> source -> {
81
-
let #(lexer, tokens) = whitespace(advance(lexer, source), tokens, space)
82
-
do_tokenise(lexer, tokens)
83
}
84
85
"\u{000A}" as space <> source
86
| "\u{000D}" as space <> source
87
| "\u{2028}" as space <> source
88
-
| "\u{2029}" as space <> source ->
89
-
do_tokenise(advance(lexer, source), case lexer.ignore_whitespace {
90
-
True -> tokens
91
-
False -> [token.LineTerminator(space), ..tokens]
92
-
})
93
94
-
"0b" as prefix <> source -> {
95
-
let #(lexer, token) =
96
-
lex_radix_number(advance(lexer, source), 2, prefix, False)
97
-
do_tokenise(lexer, [token, ..tokens])
98
-
}
99
-
"0o" as prefix <> source -> {
100
-
let #(lexer, token) =
101
-
lex_radix_number(advance(lexer, source), 8, prefix, False)
102
-
do_tokenise(lexer, [token, ..tokens])
103
-
}
104
-
"0x" as prefix <> source -> {
105
-
let #(lexer, token) =
106
-
lex_radix_number(advance(lexer, source), 16, prefix, False)
107
-
do_tokenise(lexer, [token, ..tokens])
108
-
}
109
110
"00" as digit <> source
111
| "01" as digit <> source
···
114
| "04" as digit <> source
115
| "05" as digit <> source
116
| "06" as digit <> source
117
-
| "07" as digit <> source -> {
118
-
let #(lexer, token) =
119
-
lex_leading_zero_number(advance(lexer, source), digit)
120
-
do_tokenise(lexer, [token, ..tokens])
121
-
}
122
123
"1" as digit <> source
124
| "2" as digit <> source
···
129
| "7" as digit <> source
130
| "8" as digit <> source
131
| "9" as digit <> source
132
-
| "0" as digit <> source -> {
133
-
let #(lexer, token) =
134
-
lex_number(advance(lexer, source), digit, Initial, AfterNumber)
135
-
do_tokenise(lexer, [token, ..tokens])
136
-
}
137
138
".1" as digit <> source
139
| ".2" as digit <> source
···
144
| ".7" as digit <> source
145
| ".8" as digit <> source
146
| ".9" as digit <> source
147
-
| ".0" as digit <> source -> {
148
-
let #(lexer, token) =
149
-
lex_number(advance(lexer, source), digit, Decimal, AfterNumber)
150
-
do_tokenise(lexer, [token, ..tokens])
151
-
}
152
153
-
"{" <> source ->
154
-
do_tokenise(advance(lexer, source), [token.LeftBrace, ..tokens])
155
-
"}" <> source ->
156
-
do_tokenise(advance(lexer, source), [token.RightBrace, ..tokens])
157
-
"(" <> source ->
158
-
do_tokenise(advance(lexer, source), [token.LeftParen, ..tokens])
159
-
")" <> source ->
160
-
do_tokenise(advance(lexer, source), [token.RightParen, ..tokens])
161
-
"[" <> source ->
162
-
do_tokenise(advance(lexer, source), [token.LeftSquare, ..tokens])
163
-
"]" <> source ->
164
-
do_tokenise(advance(lexer, source), [token.RightSquare, ..tokens])
165
166
-
"..." <> source ->
167
-
do_tokenise(advance(lexer, source), [token.TripleDot, ..tokens])
168
-
"." <> source -> do_tokenise(advance(lexer, source), [token.Dot, ..tokens])
169
-
";" <> source ->
170
-
do_tokenise(advance(lexer, source), [token.Semicolon, ..tokens])
171
-
"," <> source ->
172
-
do_tokenise(advance(lexer, source), [token.Comma, ..tokens])
173
-
":" <> source ->
174
-
do_tokenise(advance(lexer, source), [token.Colon, ..tokens])
175
-
"=>" <> source ->
176
-
do_tokenise(advance(lexer, source), [token.Arrow, ..tokens])
177
178
-
"<=" <> source ->
179
-
do_tokenise(advance(lexer, source), [token.LessEqual, ..tokens])
180
-
">=" <> source ->
181
-
do_tokenise(advance(lexer, source), [token.GreaterEqual, ..tokens])
182
-
"===" <> source ->
183
-
do_tokenise(advance(lexer, source), [token.TripleEqual, ..tokens])
184
-
"!==" <> source ->
185
-
do_tokenise(advance(lexer, source), [token.BangDoubleEqual, ..tokens])
186
-
"==" <> source ->
187
-
do_tokenise(advance(lexer, source), [token.DoubleEqual, ..tokens])
188
-
"!=" <> source ->
189
-
do_tokenise(advance(lexer, source), [token.BangEqual, ..tokens])
190
191
-
"=" <> source ->
192
-
do_tokenise(advance(lexer, source), [token.Equal, ..tokens])
193
-
"+=" <> source ->
194
-
do_tokenise(advance(lexer, source), [token.PlusEqual, ..tokens])
195
-
"-=" <> source ->
196
-
do_tokenise(advance(lexer, source), [token.MinusEqual, ..tokens])
197
-
"*=" <> source ->
198
-
do_tokenise(advance(lexer, source), [token.StarEqual, ..tokens])
199
-
"/=" <> source ->
200
-
do_tokenise(advance(lexer, source), [token.SlashEqual, ..tokens])
201
-
"%=" <> source ->
202
-
do_tokenise(advance(lexer, source), [token.PercentEqual, ..tokens])
203
-
"**=" <> source ->
204
-
do_tokenise(advance(lexer, source), [token.DoubleStarEqual, ..tokens])
205
-
"<<=" <> source ->
206
-
do_tokenise(advance(lexer, source), [token.DoubleLessEqual, ..tokens])
207
-
">>=" <> source ->
208
-
do_tokenise(advance(lexer, source), [token.DoubleGreaterEqual, ..tokens])
209
-
">>>=" <> source ->
210
-
do_tokenise(advance(lexer, source), [token.TripleGreaterEqual, ..tokens])
211
-
"&=" <> source ->
212
-
do_tokenise(advance(lexer, source), [token.AmpersandEqual, ..tokens])
213
-
"|=" <> source ->
214
-
do_tokenise(advance(lexer, source), [token.PipeEqual, ..tokens])
215
-
"^=" <> source ->
216
-
do_tokenise(advance(lexer, source), [token.CaratEqual, ..tokens])
217
-
"&&=" <> source ->
218
-
do_tokenise(advance(lexer, source), [token.DoubleAmpersandEqual, ..tokens])
219
-
"||=" <> source ->
220
-
do_tokenise(advance(lexer, source), [token.DoublePipeEqual, ..tokens])
221
-
"??=" <> source ->
222
-
do_tokenise(advance(lexer, source), [token.DoubleQuestionEqual, ..tokens])
223
224
-
"<<" <> source ->
225
-
do_tokenise(advance(lexer, source), [token.DoubleLess, ..tokens])
226
-
">>>" <> source ->
227
-
do_tokenise(advance(lexer, source), [token.TripleGreater, ..tokens])
228
-
">>" <> source ->
229
-
do_tokenise(advance(lexer, source), [token.DoubleGreater, ..tokens])
230
231
-
"!" <> source -> do_tokenise(advance(lexer, source), [token.Bang, ..tokens])
232
-
"&&" <> source ->
233
-
do_tokenise(advance(lexer, source), [token.DoubleAmpersand, ..tokens])
234
-
"||" <> source ->
235
-
do_tokenise(advance(lexer, source), [token.DoublePipe, ..tokens])
236
-
"??" <> source ->
237
-
do_tokenise(advance(lexer, source), [token.DoubleQuestion, ..tokens])
238
-
"?." <> source ->
239
-
do_tokenise(advance(lexer, source), [token.QuestionDot, ..tokens])
240
-
"?" <> source ->
241
-
do_tokenise(advance(lexer, source), [token.Question, ..tokens])
242
243
-
"<" <> source -> do_tokenise(advance(lexer, source), [token.Less, ..tokens])
244
-
">" <> source ->
245
-
do_tokenise(advance(lexer, source), [token.Greater, ..tokens])
246
247
-
"**" <> source ->
248
-
do_tokenise(advance(lexer, source), [token.DoubleStar, ..tokens])
249
-
"++" <> source ->
250
-
do_tokenise(advance(lexer, source), [token.DoublePlus, ..tokens])
251
-
"--" <> source ->
252
-
do_tokenise(advance(lexer, source), [token.DoubleMinus, ..tokens])
253
-
"+" <> source -> do_tokenise(advance(lexer, source), [token.Plus, ..tokens])
254
-
"-" <> source ->
255
-
do_tokenise(advance(lexer, source), [token.Minus, ..tokens])
256
-
"*" <> source -> do_tokenise(advance(lexer, source), [token.Star, ..tokens])
257
-
"/" <> source ->
258
-
do_tokenise(advance(lexer, source), [token.Slash, ..tokens])
259
-
"%" <> source ->
260
-
do_tokenise(advance(lexer, source), [token.Percent, ..tokens])
261
-
"&" <> source ->
262
-
do_tokenise(advance(lexer, source), [token.Ampersand, ..tokens])
263
-
"|" <> source -> do_tokenise(advance(lexer, source), [token.Pipe, ..tokens])
264
-
"^" <> source ->
265
-
do_tokenise(advance(lexer, source), [token.Caret, ..tokens])
266
-
"~" <> source ->
267
-
do_tokenise(advance(lexer, source), [token.Tilde, ..tokens])
268
269
"#" <> source -> {
270
let #(lexer, name) = lex_identifier(advance(lexer, source), "")
271
-
do_tokenise(lexer, [token.PrivateIdentifier(name), ..tokens])
272
}
273
274
"_" as character <> source
···
328
let #(lexer, name) = lex_identifier(advance(lexer, source), character)
329
330
let token = identifier_token(name, lexer.strict_mode)
331
-
332
-
do_tokenise(lexer, [token, ..tokens])
333
}
334
335
"'" as quote <> source | "\"" as quote <> source -> {
336
let #(lexer, string) = lex_string(advance(lexer, source), quote, "")
337
-
do_tokenise(lexer, [token.String(quote, string), ..tokens])
338
}
339
340
-
_ -> list.reverse(tokens)
341
}
342
}
343
···
642
}
643
}
644
645
-
fn whitespace(
646
-
lexer: Lexer,
647
-
tokens: List(Token),
648
-
lexed: String,
649
-
) -> #(Lexer, List(Token)) {
650
case lexer.source {
651
"\t" as space <> source
652
| "\u{000B}" as space <> source
···
668
| "\u{205F}" as space <> source
669
| "\u{3000}" as space <> source
670
| "\u{FEFF}" as space <> source ->
671
-
whitespace(advance(lexer, source), tokens, lexed <> space)
672
673
-
_ -> #(lexer, case lexer.ignore_whitespace {
674
-
True -> tokens
675
-
False -> [token.Whitespace(lexed), ..tokens]
676
-
})
677
}
678
}
679
···
55
}
56
57
fn do_tokenise(lexer: Lexer, tokens: List(Token)) -> List(Token) {
58
+
case next(lexer) {
59
+
#(_, token.EndOfFile) -> list.reverse([token.EndOfFile, ..tokens])
60
+
#(lexer, token) -> do_tokenise(lexer, [token, ..tokens])
61
+
}
62
+
}
63
+
64
+
fn next(lexer: Lexer) -> #(Lexer, Token) {
65
case lexer.source {
66
+
"" -> #(lexer, token.EndOfFile)
67
68
"\u{0009}" as space <> source
69
| "\u{000B}" as space <> source
···
85
| "\u{205F}" as space <> source
86
| "\u{3000}" as space <> source
87
| "\u{FEFF}" as space <> source -> {
88
+
whitespace(advance(lexer, source), space)
89
}
90
91
"\u{000A}" as space <> source
92
| "\u{000D}" as space <> source
93
| "\u{2028}" as space <> source
94
+
| "\u{2029}" as space <> source -> {
95
+
let lexer = advance(lexer, source)
96
+
case lexer.ignore_whitespace {
97
+
True -> next(lexer)
98
+
False -> #(lexer, token.LineTerminator(space))
99
+
}
100
+
}
101
102
+
"0b" as prefix <> source ->
103
+
lex_radix_number(advance(lexer, source), 2, prefix, False)
104
+
105
+
"0o" as prefix <> source ->
106
+
lex_radix_number(advance(lexer, source), 8, prefix, False)
107
+
108
+
"0x" as prefix <> source ->
109
+
lex_radix_number(advance(lexer, source), 16, prefix, False)
110
111
"00" as digit <> source
112
| "01" as digit <> source
···
115
| "04" as digit <> source
116
| "05" as digit <> source
117
| "06" as digit <> source
118
+
| "07" as digit <> source ->
119
+
lex_leading_zero_number(advance(lexer, source), digit)
120
121
"1" as digit <> source
122
| "2" as digit <> source
···
127
| "7" as digit <> source
128
| "8" as digit <> source
129
| "9" as digit <> source
130
+
| "0" as digit <> source ->
131
+
lex_number(advance(lexer, source), digit, Initial, AfterNumber)
132
133
".1" as digit <> source
134
| ".2" as digit <> source
···
139
| ".7" as digit <> source
140
| ".8" as digit <> source
141
| ".9" as digit <> source
142
+
| ".0" as digit <> source ->
143
+
lex_number(advance(lexer, source), digit, Decimal, AfterNumber)
144
145
+
"{" <> source -> #(advance(lexer, source), token.LeftBrace)
146
+
"}" <> source -> #(advance(lexer, source), token.RightBrace)
147
+
"(" <> source -> #(advance(lexer, source), token.LeftParen)
148
+
")" <> source -> #(advance(lexer, source), token.RightParen)
149
+
"[" <> source -> #(advance(lexer, source), token.LeftSquare)
150
+
"]" <> source -> #(advance(lexer, source), token.RightSquare)
151
152
+
"..." <> source -> #(advance(lexer, source), token.TripleDot)
153
+
"." <> source -> #(advance(lexer, source), token.Dot)
154
+
";" <> source -> #(advance(lexer, source), token.Semicolon)
155
+
"," <> source -> #(advance(lexer, source), token.Comma)
156
+
":" <> source -> #(advance(lexer, source), token.Colon)
157
+
"=>" <> source -> #(advance(lexer, source), token.Arrow)
158
159
+
"<=" <> source -> #(advance(lexer, source), token.LessEqual)
160
+
">=" <> source -> #(advance(lexer, source), token.GreaterEqual)
161
+
"===" <> source -> #(advance(lexer, source), token.TripleEqual)
162
+
"!==" <> source -> #(advance(lexer, source), token.BangDoubleEqual)
163
+
"==" <> source -> #(advance(lexer, source), token.DoubleEqual)
164
+
"!=" <> source -> #(advance(lexer, source), token.BangEqual)
165
166
+
"=" <> source -> #(advance(lexer, source), token.Equal)
167
+
"+=" <> source -> #(advance(lexer, source), token.PlusEqual)
168
+
"-=" <> source -> #(advance(lexer, source), token.MinusEqual)
169
+
"*=" <> source -> #(advance(lexer, source), token.StarEqual)
170
+
"/=" <> source -> #(advance(lexer, source), token.SlashEqual)
171
+
"%=" <> source -> #(advance(lexer, source), token.PercentEqual)
172
+
"**=" <> source -> #(advance(lexer, source), token.DoubleStarEqual)
173
+
"<<=" <> source -> #(advance(lexer, source), token.DoubleLessEqual)
174
+
">>=" <> source -> #(advance(lexer, source), token.DoubleGreaterEqual)
175
+
">>>=" <> source -> #(advance(lexer, source), token.TripleGreaterEqual)
176
+
"&=" <> source -> #(advance(lexer, source), token.AmpersandEqual)
177
+
"|=" <> source -> #(advance(lexer, source), token.PipeEqual)
178
+
"^=" <> source -> #(advance(lexer, source), token.CaratEqual)
179
+
"&&=" <> source -> #(advance(lexer, source), token.DoubleAmpersandEqual)
180
+
"||=" <> source -> #(advance(lexer, source), token.DoublePipeEqual)
181
+
"??=" <> source -> #(advance(lexer, source), token.DoubleQuestionEqual)
182
183
+
"<<" <> source -> #(advance(lexer, source), token.DoubleLess)
184
+
">>>" <> source -> #(advance(lexer, source), token.TripleGreater)
185
+
">>" <> source -> #(advance(lexer, source), token.DoubleGreater)
186
187
+
"!" <> source -> #(advance(lexer, source), token.Bang)
188
+
"&&" <> source -> #(advance(lexer, source), token.DoubleAmpersand)
189
+
"||" <> source -> #(advance(lexer, source), token.DoublePipe)
190
+
"??" <> source -> #(advance(lexer, source), token.DoubleQuestion)
191
+
"?." <> source -> #(advance(lexer, source), token.QuestionDot)
192
+
"?" <> source -> #(advance(lexer, source), token.Question)
193
194
+
"<" <> source -> #(advance(lexer, source), token.Less)
195
+
">" <> source -> #(advance(lexer, source), token.Greater)
196
197
+
"**" <> source -> #(advance(lexer, source), token.DoubleStar)
198
+
"++" <> source -> #(advance(lexer, source), token.DoublePlus)
199
+
"--" <> source -> #(advance(lexer, source), token.DoubleMinus)
200
+
"+" <> source -> #(advance(lexer, source), token.Plus)
201
+
"-" <> source -> #(advance(lexer, source), token.Minus)
202
+
"*" <> source -> #(advance(lexer, source), token.Star)
203
+
"/" <> source -> #(advance(lexer, source), token.Slash)
204
+
"%" <> source -> #(advance(lexer, source), token.Percent)
205
+
"&" <> source -> #(advance(lexer, source), token.Ampersand)
206
+
"|" <> source -> #(advance(lexer, source), token.Pipe)
207
+
"^" <> source -> #(advance(lexer, source), token.Caret)
208
+
"~" <> source -> #(advance(lexer, source), token.Tilde)
209
210
"#" <> source -> {
211
let #(lexer, name) = lex_identifier(advance(lexer, source), "")
212
+
#(lexer, token.PrivateIdentifier(name))
213
}
214
215
"_" as character <> source
···
269
let #(lexer, name) = lex_identifier(advance(lexer, source), character)
270
271
let token = identifier_token(name, lexer.strict_mode)
272
+
#(lexer, token)
273
}
274
275
"'" as quote <> source | "\"" as quote <> source -> {
276
let #(lexer, string) = lex_string(advance(lexer, source), quote, "")
277
+
#(lexer, token.String(quote, string))
278
}
279
280
+
_ -> #(lexer, token.EndOfFile)
281
}
282
}
283
···
582
}
583
}
584
585
+
fn whitespace(lexer: Lexer, lexed: String) -> #(Lexer, Token) {
586
case lexer.source {
587
"\t" as space <> source
588
| "\u{000B}" as space <> source
···
604
| "\u{205F}" as space <> source
605
| "\u{3000}" as space <> source
606
| "\u{FEFF}" as space <> source ->
607
+
whitespace(advance(lexer, source), lexed <> space)
608
609
+
_ ->
610
+
case lexer.ignore_whitespace {
611
+
True -> next(lexer)
612
+
False -> #(lexer, token.Whitespace(lexed))
613
+
}
614
}
615
}
616
+2
src/just/token.gleam
+2
src/just/token.gleam
···
5
HashBangComment(String)
6
Whitespace(String)
7
LineTerminator(String)
8
+
EndOfFile
9
10
// Literals
11
Identifier(String)
···
179
HashBangComment(value) -> "#!" <> value
180
Whitespace(value) -> value
181
LineTerminator(value) -> value
182
+
EndOfFile -> ""
183
184
// Literals
185
Identifier(value) -> value