-
Notifications
You must be signed in to change notification settings - Fork 6
/
Copy pathsyntax_test.clj
413 lines (359 loc) · 14.9 KB
/
syntax_test.clj
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
;; Authors: Sung Pae <[email protected]>
;; Joel Holdbrooks <[email protected]>
(ns vim-clojure-static.syntax-test
(:require [vim-clojure-static.test :refer [defpredicates defsyntaxtest]]))
;; defpredicates also register not-equal vars, this is just for clj-kondo
(declare !number !regexp-escape !regexp-posix-char-class !regexp-quantifier)
(defpredicates number :clojureNumber)
(defpredicates kw :clojureKeyword)
(defpredicates character :clojureCharacter)
(defpredicates regexp :clojureRegexp)
(defpredicates regexp-escape :clojureRegexpEscape)
(defpredicates regexp-char-class :clojureRegexpCharClass)
(defpredicates regexp-predefined-char-class :clojureRegexpPredefinedCharClass)
(defpredicates regexp-posix-char-class :clojureRegexpPosixCharClass)
(defpredicates regexp-java-char-class :clojureRegexpJavaCharClass)
(defpredicates regexp-unicode-char-class :clojureRegexpUnicodeCharClass)
(defpredicates regexp-boundary :clojureRegexpBoundary)
(defpredicates regexp-quantifier :clojureRegexpQuantifier)
(defpredicates regexp-back-ref :clojureRegexpBackRef)
(defpredicates regexp-or :clojureRegexpOr)
(defpredicates regexp-group :clojureRegexpGroup)
(defn regexp-mod [xs] (= (second xs) :clojureRegexpMod))
(def !regexp-mod (complement regexp-mod))
(defsyntaxtest test-number-literals
["%s"
["1234567890" number "+1" number "-1" number ; Integer
"0" number "+0" number "-0" number ; Integer zero
"0.12" number "+0.12" number "-0.12" number ; Float
"1." number "+1." number "-1." number ; Float
"0.0" number "+0.0" number "-0.0" number ; Float zero
"01234567" number "+07" number "-07" number ; Octal
"00" number "+00" number "-00" number ; Octal zero
"0x09abcdef" number "+0xf" number "-0xf" number ; Hexadecimal
"0x0" number "+0x0" number "-0x0" number ; Hexadecimal zero
"3/2" number "+3/2" number "-3/2" number ; Rational
"0/0" number "+0/0" number "-0/0" number ; Rational (not a syntax error)
"36r0XYZ" number "16rFF" number "8r077" number ; Radix
"2r1" number "+2r1" number "-2r1" number ; Radix
"36R1" number "+36R1" number "-36R1" number ; Radix
;; Illegal literals (some are accepted by the reader, but are bad style)
".1" !number
"01.2" !number
"089" !number
"0xfg" !number
"1.0/1" !number
"01/2" !number
"1/02" !number
; "2r2" !number ;; Removed for performance
"1r0" !number
"37r36" !number
;; BigInt
"0N" number
"+0.1N" !number
"-07N" number
"08N" !number
"+0x0fN" number
"1/2N" !number
;; BigDecimal
"0M" number
"+0.1M" number
"08M" !number
"08.9M" !number
"0x1fM" !number
"3/4M" !number
; "2r1M" !number ;; Removed for performance
;; Exponential notation
"0e0" number
"+0.1e-1" number
"-1e-1" number
"08e1" !number
"07e1" !number
"0xfe-1" !number
"2r1e-1" !number]])
(comment (test #'test-number-literals))
(defsyntaxtest test-character-literals
["[%s]"
["\\0" character "\\a" character "\\Z" character
"\\." character "\\\\" character "\\❤" character
"\\o7" character "\\o07" character "\\o307" character
"\\o8" !character "\\o477" !character "\\o0007" !character
"\\u09af" character
"\\u0" !character "\\u01" !character "\\u012" !character
"\\u01234" !character "\\u0123g" !character
"\\newline" character "\\new" !character
"\\tab" character "\\ta" !character
"\\space" character "\\sp" !character
"\\return" character "\\ret" !character
"\\backspace" character "\\bs" !character
"\\formfeed" character "\\ff" !character]])
(comment (test #'test-character-literals))
(defsyntaxtest keywords-test
["%s"
[":1" kw
":A" kw
":a" kw
":αβγ" kw
"::a" kw
":a/b" kw
":a:b" kw
":a:b/:c:b" kw
":a/b/c/d" kw
"::a/b" kw
"::" !kw
":a:" !kw
":a/" !kw
; ":/" !kw ; This is legal, but for simplicity we do not match it
":" !kw]])
(comment (test #'keywords-test))
(defsyntaxtest test-java-regexp-literals
["#\"%s\""
[;; http://docs.oracle.com/javase/7/docs/api/java/util/regex/Pattern.html
;;
;; Characters
;; x The character x
" 0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz" regexp
"λ❤" regexp
;; \\ The backslash character
"\\\\" regexp-escape
;; \0n The character with octal value 0n (0 <= n <= 7)
"\\07" regexp-escape
"\\08" !regexp-escape
;; \0nn The character with octal value 0nn (0 <= n <= 7)
"\\077" regexp-escape
"\\078" !regexp-escape
;; \0mnn The character with octal value 0mnn (0 <= m <= 3, 0 <= n <= 7)
"\\0377" regexp-escape
"\\0378" !regexp-escape
"\\0400" !regexp-escape
;; \xhh The character with hexadecimal value 0xhh
"\\xff" regexp-escape
"\\xfg" !regexp-escape
"\\xfff" !regexp-escape
;; \uhhhh The character with hexadecimal value 0xhhhh
"\\uffff" regexp-escape
"\\ufff" !regexp-escape
"\\ufffff" !regexp-escape
;; \x{h...h} The character with hexadecimal value 0xh...h (Character.MIN_CODE_POINT <= 0xh...h <= Character.MAX_CODE_POINT)
;; \t The tab character ('\u0009')
"\\t" regexp-escape
"\\T" !regexp-escape
;; \n The newline (line feed) character ('\u000A')
"\\n" regexp-escape
"\\N" !regexp-escape
;; \r The carriage-return character ('\u000D')
"\\r" regexp-escape
"\\R" !regexp-escape
;; \f The form-feed character ('\u000C')
"\\f" regexp-escape
"\\F" !regexp-escape
;; \a The alert (bell) character ('\u0007')
"\\a" regexp-escape
"\\A" !regexp-escape
;; \e The escape character ('\u001B')
"\\e" regexp-escape
"\\E" !regexp-escape
;; \cx The control character corresponding to x
"\\cA" regexp-escape
"\\c1" !regexp-escape
"\\c" !regexp-escape
;; Special character escapes
"\\(\\)\\[\\]\\{\\}\\^\\$\\*\\?\\+\\." regexp-escape
;;;; Character classes
;; [abc] a, b, or c (simple class)
"[abc]" regexp-char-class
;; [^abc] Any character except a, b, or c (negation)
"[^abc]" regexp-char-class
;; [a-zA-Z] a through z or A through Z, inclusive (range)
;; [a-d[m-p]] a through d, or m through p: [a-dm-p] (union)
;; [a-z&&[def]] d, e, or f (intersection)
;; [a-z&&[^bc]] a through z, except for b and c: [ad-z] (subtraction)
;; [a-z&&[^m-p]] a through z, and not m through p: [a-lq-z](subtraction)
;;;; Predefined character classes
;; . Any character (may or may not match line terminators)
"." regexp-predefined-char-class
;; \d A digit: [0-9]
"\\d" regexp-predefined-char-class
;; \D A non-digit: [^0-9]
"\\D" regexp-predefined-char-class
;; \s A whitespace character: [ \t\n\x0B\f\r]
"\\s" regexp-predefined-char-class
;; \S A non-whitespace character: [^\s]
"\\S" regexp-predefined-char-class
;; \w A word character: [a-zA-Z_0-9]
"\\w" regexp-predefined-char-class
;; \W A non-word character: [^\w]
"\\W" regexp-predefined-char-class
;;;; POSIX character classes (US-ASCII only)
;; \p{Lower} A lower-case alphabetic character: [a-z]
"\\p{Lower}" regexp-posix-char-class
;; \p{Upper} An upper-case alphabetic character:[A-Z]
"\\p{Upper}" regexp-posix-char-class
;; \p{ASCII} All ASCII:[\x00-\x7F]
"\\p{ASCII}" regexp-posix-char-class
;; \p{Alpha} An alphabetic character:[\p{Lower}\p{Upper}]
"\\p{Alpha}" regexp-posix-char-class
;; \p{Digit} A decimal digit: [0-9]
"\\p{Digit}" regexp-posix-char-class
;; \p{Alnum} An alphanumeric character:[\p{Alpha}\p{Digit}]
"\\p{Alnum}" regexp-posix-char-class
;; \p{Punct} Punctuation: One of !"#$%&'()*+,-./:;<=>?@[\]^_`{|}~
"\\p{Punct}" regexp-posix-char-class
;; \p{Graph} A visible character: [\p{Alnum}\p{Punct}]
"\\p{Graph}" regexp-posix-char-class
;; \p{Print} A printable character: [\p{Graph}\x20]
"\\p{Print}" regexp-posix-char-class
;; \p{Blank} A space or a tab: [ \t]
"\\p{Blank}" regexp-posix-char-class
;; \p{Cntrl} A control character: [\x00-\x1F\x7F]
"\\p{Cntrl}" regexp-posix-char-class
;; \p{XDigit} A hexadecimal digit: [0-9a-fA-F]
"\\p{XDigit}" regexp-posix-char-class
;; \p{Space} A whitespace character: [ \t\n\x0B\f\r]
"\\p{Space}" regexp-posix-char-class
;;;; java.lang.Character classes (simple java character type)
;; \p{javaLowerCase} Equivalent to java.lang.Character.isLowerCase()
"\\p{javaLowerCase}" regexp-java-char-class
;; \p{javaUpperCase} Equivalent to java.lang.Character.isUpperCase()
"\\p{javaUpperCase}" regexp-java-char-class
;; \p{javaWhitespace} Equivalent to java.lang.Character.isWhitespace()
"\\p{javaWhitespace}" regexp-java-char-class
;; \p{javaMirrored} Equivalent to java.lang.Character.isMirrored()
"\\p{javaMirrored}" regexp-java-char-class
;;;; Classes for Unicode scripts, blocks, categories and binary properties
;; \p{IsLatin} A Latin script character (script)
"\\p{IsLatin}" regexp-unicode-char-class
;; \p{InGreek} A character in the Greek block (block)
"\\p{InGreek}" regexp-unicode-char-class
;; \p{IsAlphabetic} An alphabetic character (binary property)
"\\p{IsAlphabetic}" regexp-unicode-char-class
;; \p{Sc} A currency symbol
"\\p{Sc}" regexp-unicode-char-class
;; \P{InGreek} Any character except one in the Greek block (negation)
"\\P{InGreek}" regexp-unicode-char-class
;; [\p{L}&&[^\p{Lu}]] Any letter except an uppercase letter (subtraction)
;; Abbreviated categories
"\\pL" regexp-unicode-char-class
"\\p{L}" regexp-unicode-char-class
"\\p{Lu}" regexp-unicode-char-class
"\\p{gc=L}" regexp-unicode-char-class
"\\p{IsLu}" regexp-unicode-char-class
;;;; Invalid classes
"\\P{Xzibit}" !regexp-posix-char-class
"\\p{YoDawg}" !regexp-posix-char-class
;;;; Boundary matchers
;; ^ The beginning of a line
"^" regexp-boundary
;; $ The end of a line
"$" regexp-boundary
;; \b A word boundary
"\\b" regexp-boundary
;; \B A non-word boundary
"\\B" regexp-boundary
;; \A The beginning of the input
"\\A" regexp-boundary
;; \G The end of the previous match
"\\G" regexp-boundary
;; \Z The end of the input but for the final terminator, if any
"\\Z" regexp-boundary
;; \z The end of the input
"\\z" regexp-boundary
;;;; Greedy quantifiers
;; X? X, once or not at all
"?" regexp-quantifier
;; X* X, zero or more times
"*" regexp-quantifier
;; X+ X, one or more times
"+" regexp-quantifier
;; X{n} X, exactly n times
"{0}" regexp-quantifier
;; X{n,} X, at least n times
"{0,}" regexp-quantifier
;; X{n,m} X, at least n but not more than m times
"{0,1}" regexp-quantifier
;;;; Reluctant quantifiers
;; X?? X, once or not at all
"??" regexp-quantifier
;; X*? X, zero or more times
"*?" regexp-quantifier
;; X+? X, one or more times
"+?" regexp-quantifier
;; X{n}? X, exactly n times
"{0}?" regexp-quantifier
;; X{n,}? X, at least n times
"{0,}?" regexp-quantifier
;; X{n,m}? X, at least n but not more than m times
"{0,1}?" regexp-quantifier
;;;; Possessive quantifiers
;; X?+ X, once or not at all
"?+" regexp-quantifier
;; X*+ X, zero or more times
"*+" regexp-quantifier
;; X++ X, one or more times
"++" regexp-quantifier
;; X{n}+ X, exactly n times
"{0}+" regexp-quantifier
;; X{n,}+ X, at least n times
"{0,}+" regexp-quantifier
;; X{n,m}+ X, at least n but not more than m times
"{0,1}+" regexp-quantifier
"{-1}" !regexp-quantifier
"{-1,}" !regexp-quantifier
"{-1,-2}" !regexp-quantifier
"{-1}?" !regexp-quantifier
"{-1,}?" !regexp-quantifier
"{-1,-2}?" !regexp-quantifier
"{-1}?" !regexp-quantifier
"{-1,}?" !regexp-quantifier
"{-1,-2}?" !regexp-quantifier
;;;; Logical operators
;; XY X followed by Y
;; XXX: Tested above (regexp)
;; X|Y Either X or Y
"|" regexp-or
;; (X) X, as a capturing group
"(X)" regexp-group
;;;; Back references
;; \n Whatever the nth capturing group matched
"\\1" regexp-back-ref
;; \k<name> Whatever the named-capturing group "name" matched
"\\k<name>" regexp-back-ref
;;;; Quotation
;; \ Nothing, but quotes the following character
;; XXX: Tested above
;; \Q Nothing, but quotes all characters until \E
;; \E Nothing, but ends quoting started by \Q
"\\Qa\\E" (partial = [:clojureRegexpQuote :clojureRegexpQuote :clojureRegexpQuoted :clojureRegexpQuote :clojureRegexpQuote])
"\\Qa\\\"" (partial = [:clojureRegexpQuote :clojureRegexpQuote :clojureRegexpQuoted :clojureRegexpQuoted :clojureRegexpQuoted])
"\\qa\\E" (partial not-any? #{:clojureRegexpQuote :clojureRegexpQuoted})
;;;; Special constructs (named-capturing and non-capturing)
;; (?<name>X) X, as a named-capturing group
"(?<name>X)" regexp-mod
;; (?:X) X, as a non-capturing group
"(?:X)" regexp-mod
;; (?idmsuxU-idmsuxU) Nothing, but turns match flags i d m s u x U on - off
"(?idmsuxU-idmsuxU)" regexp-mod
"(?idmsuxU)" regexp-mod
"(?-idmsuxU)" regexp-mod
;; (?idmsux-idmsux:X) X, as a non-capturing group with the given flags i d m s u x on - off
"(?idmsuxU-idmsuxU:X)" regexp-mod
"(?idmsuxU:)" regexp-mod
"(?-idmsuxU:)" regexp-mod
;; (?=X) X, via zero-width positive lookahead
"(?=X)" regexp-mod
;; (?!X) X, via zero-width negative lookahead
"(?!X)" regexp-mod
;; (?<=X) X, via zero-width positive lookbehind
"(?<=X)" regexp-mod
;; (?<!X) X, via zero-width negative lookbehind
"(?<!X)" regexp-mod
;; (?>X) X, as an independent, non-capturing group
"(?>X)" regexp-mod
"(?X)" !regexp-mod
]]
["#%s"
[;; Backslashes with character classes
"\"[\\\\]\"" (partial = [:clojureRegexp :clojureRegexpCharClass :clojureRegexpCharClass :clojureRegexpCharClass :clojureRegexpCharClass :clojureRegexp])
"\"\\[]\"" (partial = [:clojureRegexp :clojureRegexpEscape :clojureRegexpEscape :clojureRegexp :clojureRegexp])
"\"\\\\[]\"" (partial = [:clojureRegexp :clojureRegexpEscape :clojureRegexpEscape :clojureRegexpCharClass :clojureRegexpCharClass :clojureRegexp])]])
(comment (test #'test-java-regexp-literals))