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
|
if not modules then modules = { } end modules ['l-lpeg'] = {
version = 1.001,
comment = "companion to luat-lib.mkiv",
author = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
copyright = "PRAGMA ADE / ConTeXt Development Team",
license = "see context related readme files"
}
local lpeg = require("lpeg")
local type = type
-- Beware, we predefine a bunch of patterns here and one reason for doing so
-- is that we get consistent behaviour in some of the visualizers.
lpeg.patterns = lpeg.patterns or { } -- so that we can share
local patterns = lpeg.patterns
local P, R, S, V, match = lpeg.P, lpeg.R, lpeg.S, lpeg.V, lpeg.match
local Ct, C, Cs, Cc = lpeg.Ct, lpeg.C, lpeg.Cs, lpeg.Cc
local lpegtype = lpeg.type
local utfcharacters = string.utfcharacters
local utfgmatch = unicode and unicode.utf8.gmatch
local anything = P(1)
local endofstring = P(-1)
local alwaysmatched = P(true)
patterns.anything = anything
patterns.endofstring = endofstring
patterns.beginofstring = alwaysmatched
patterns.alwaysmatched = alwaysmatched
local digit, sign = R('09'), S('+-')
local cr, lf, crlf = P("\r"), P("\n"), P("\r\n")
local newline = crlf + cr + lf
local escaped = P("\\") * anything
local squote = P("'")
local dquote = P('"')
local space = P(" ")
local utfbom_32_be = P('\000\000\254\255')
local utfbom_32_le = P('\255\254\000\000')
local utfbom_16_be = P('\255\254')
local utfbom_16_le = P('\254\255')
local utfbom_8 = P('\239\187\191')
local utfbom = utfbom_32_be + utfbom_32_le
+ utfbom_16_be + utfbom_16_le
+ utfbom_8
local utftype = utfbom_32_be / "utf-32-be" + utfbom_32_le / "utf-32-le"
+ utfbom_16_be / "utf-16-be" + utfbom_16_le / "utf-16-le"
+ utfbom_8 / "utf-8" + alwaysmatched / "unknown"
local utf8next = R("\128\191")
patterns.utf8one = R("\000\127")
patterns.utf8two = R("\194\223") * utf8next
patterns.utf8three = R("\224\239") * utf8next * utf8next
patterns.utf8four = R("\240\244") * utf8next * utf8next * utf8next
patterns.utfbom = utfbom
patterns.utftype = utftype
local utf8char = patterns.utf8one + patterns.utf8two + patterns.utf8three + patterns.utf8four
local validutf8char = utf8char^0 * endofstring * Cc(true) + Cc(false)
patterns.utf8 = utf8char
patterns.utf8char = utf8char
patterns.validutf8 = validutf8char
patterns.validutf8char = validutf8char
patterns.digit = digit
patterns.sign = sign
patterns.cardinal = sign^0 * digit^1
patterns.integer = sign^0 * digit^1
patterns.float = sign^0 * digit^0 * P('.') * digit^1
patterns.cfloat = sign^0 * digit^0 * P(',') * digit^1
patterns.number = patterns.float + patterns.integer
patterns.cnumber = patterns.cfloat + patterns.integer
patterns.oct = P("0") * R("07")^1
patterns.octal = patterns.oct
patterns.HEX = P("0x") * R("09","AF")^1
patterns.hex = P("0x") * R("09","af")^1
patterns.hexadecimal = P("0x") * R("09","AF","af")^1
patterns.lowercase = R("az")
patterns.uppercase = R("AZ")
patterns.letter = patterns.lowercase + patterns.uppercase
patterns.space = space
patterns.tab = P("\t")
patterns.spaceortab = patterns.space + patterns.tab
patterns.eol = S("\n\r")
patterns.spacer = S(" \t\f\v") -- + string.char(0xc2, 0xa0) if we want utf (cf mail roberto)
patterns.newline = newline
patterns.emptyline = newline^1
patterns.nonspacer = 1 - patterns.spacer
patterns.whitespace = patterns.eol + patterns.spacer
patterns.nonwhitespace = 1 - patterns.whitespace
patterns.equal = P("=")
patterns.comma = P(",")
patterns.commaspacer = P(",") * patterns.spacer^0
patterns.period = P(".")
patterns.colon = P(":")
patterns.semicolon = P(";")
patterns.underscore = P("_")
patterns.escaped = escaped
patterns.squote = squote
patterns.dquote = dquote
patterns.nosquote = (escaped + (1-squote))^0
patterns.nodquote = (escaped + (1-dquote))^0
patterns.unsingle = (squote/"") * patterns.nosquote * (squote/"")
patterns.undouble = (dquote/"") * patterns.nodquote * (dquote/"")
patterns.unquoted = patterns.undouble + patterns.unsingle -- more often undouble
patterns.unspacer = ((patterns.spacer^1)/"")^0
patterns.somecontent = (anything - newline - space)^1 -- (utf8char - newline - space)^1
patterns.beginline = #(1-newline)
local unquoted = Cs(patterns.unquoted * endofstring) -- not C
function string.unquoted(str)
return match(unquoted,str) or str
end
--~ print(string.unquoted("test"))
--~ print(string.unquoted([["t\"est"]]))
--~ print(string.unquoted([["t\"est"x]]))
--~ print(string.unquoted("\'test\'"))
function lpeg.anywhere(pattern) --slightly adapted from website
return P { P(pattern) + 1 * V(1) } -- why so complex?
end
function lpeg.splitter(pattern, action)
return (((1-P(pattern))^1)/action+1)^0
end
local splitters_s, splitters_m = { }, { }
local function splitat(separator,single)
local splitter = (single and splitters_s[separator]) or splitters_m[separator]
if not splitter then
separator = P(separator)
local other = C((1 - separator)^0)
if single then
local any = anything
splitter = other * (separator * C(any^0) + "") -- ?
splitters_s[separator] = splitter
else
splitter = other * (separator * other)^0
splitters_m[separator] = splitter
end
end
return splitter
end
lpeg.splitat = splitat
--~ local p = splitat("->",false) print(match(p,"oeps->what->more")) -- oeps what more
--~ local p = splitat("->",true) print(match(p,"oeps->what->more")) -- oeps what->more
--~ local p = splitat("->",false) print(match(p,"oeps")) -- oeps
--~ local p = splitat("->",true) print(match(p,"oeps")) -- oeps
local cache = { }
function lpeg.split(separator,str)
local c = cache[separator]
if not c then
c = Ct(splitat(separator))
cache[separator] = c
end
return match(c,str)
end
function string.split(str,separator)
local c = cache[separator]
if not c then
c = Ct(splitat(separator))
cache[separator] = c
end
return match(c,str)
end
local spacing = patterns.spacer^0 * newline -- sort of strip
local empty = spacing * Cc("")
local nonempty = Cs((1-spacing)^1) * spacing^-1
local content = (empty + nonempty)^1
patterns.textline = content
--~ local linesplitter = Ct(content^0)
--~
--~ function string.splitlines(str)
--~ return match(linesplitter,str)
--~ end
local linesplitter = Ct(splitat(newline))
patterns.linesplitter = linesplitter
function string.splitlines(str)
return match(linesplitter,str)
end
local utflinesplitter = utfbom^-1 * Ct(splitat(newline))
patterns.utflinesplitter = utflinesplitter
function string.utfsplitlines(str)
return match(utflinesplitter,str)
end
--~ lpeg.splitters = cache -- no longer public
local cache = { }
function lpeg.checkedsplit(separator,str)
local c = cache[separator]
if not c then
separator = P(separator)
local other = C((1 - separator)^1)
c = Ct(separator^0 * other * (separator^1 * other)^0)
cache[separator] = c
end
return match(c,str)
end
function string.checkedsplit(str,separator)
local c = cache[separator]
if not c then
separator = P(separator)
local other = C((1 - separator)^1)
c = Ct(separator^0 * other * (separator^1 * other)^0)
cache[separator] = c
end
return match(c,str)
end
--~ from roberto's site:
local f1 = string.byte
local function f2(s) local c1, c2 = f1(s,1,2) return c1 * 64 + c2 - 12416 end
local function f3(s) local c1, c2, c3 = f1(s,1,3) return (c1 * 64 + c2) * 64 + c3 - 925824 end
local function f4(s) local c1, c2, c3, c4 = f1(s,1,4) return ((c1 * 64 + c2) * 64 + c3) * 64 + c4 - 63447168 end
local utf8byte = patterns.utf8one/f1 + patterns.utf8two/f2 + patterns.utf8three/f3 + patterns.utf8four/f4
patterns.utf8byte = utf8byte
--~ local str = " a b c d "
--~ local s = lpeg.stripper(lpeg.R("az")) print("["..lpeg.match(s,str).."]")
--~ local s = lpeg.keeper(lpeg.R("az")) print("["..lpeg.match(s,str).."]")
--~ local s = lpeg.stripper("ab") print("["..lpeg.match(s,str).."]")
--~ local s = lpeg.keeper("ab") print("["..lpeg.match(s,str).."]")
local cache = { }
function lpeg.stripper(str)
if type(str) == "string" then
local s = cache[str]
if not s then
s = Cs(((S(str)^1)/"" + 1)^0)
cache[str] = s
end
return s
else
return Cs(((str^1)/"" + 1)^0)
end
end
local cache = { }
function lpeg.keeper(str)
if type(str) == "string" then
local s = cache[str]
if not s then
s = Cs((((1-S(str))^1)/"" + 1)^0)
cache[str] = s
end
return s
else
return Cs((((1-str)^1)/"" + 1)^0)
end
end
function lpeg.frontstripper(str) -- or pattern (yet undocumented)
return (P(str) + P(true)) * Cs(P(1)^0)
end
function lpeg.endstripper(str) -- or pattern (yet undocumented)
return Cs((1 - P(str) * P(-1))^0)
end
-- Just for fun I looked at the used bytecode and
-- p = (p and p + pp) or pp gets one more (testset).
function lpeg.replacer(one,two)
if type(one) == "table" then
local no = #one
if no > 0 then
local p
for i=1,no do
local o = one[i]
local pp = P(o[1]) / o[2]
if p then
p = p + pp
else
p = pp
end
end
return Cs((p + 1)^0)
end
else
two = two or ""
return Cs((P(one)/two + 1)^0)
end
end
local splitters_f, splitters_s = { }, { }
function lpeg.firstofsplit(separator) -- always return value
local splitter = splitters_f[separator]
if not splitter then
separator = P(separator)
splitter = C((1 - separator)^0)
splitters_f[separator] = splitter
end
return splitter
end
function lpeg.secondofsplit(separator) -- nil if not split
local splitter = splitters_s[separator]
if not splitter then
separator = P(separator)
splitter = (1 - separator)^0 * separator * C(anything^0)
splitters_s[separator] = splitter
end
return splitter
end
function lpeg.balancer(left,right)
left, right = P(left), P(right)
return P { left * ((1 - left - right) + V(1))^0 * right }
end
--~ print(1,match(lpeg.firstofsplit(":"),"bc:de"))
--~ print(2,match(lpeg.firstofsplit(":"),":de")) -- empty
--~ print(3,match(lpeg.firstofsplit(":"),"bc"))
--~ print(4,match(lpeg.secondofsplit(":"),"bc:de"))
--~ print(5,match(lpeg.secondofsplit(":"),"bc:")) -- empty
--~ print(6,match(lpeg.secondofsplit(":",""),"bc"))
--~ print(7,match(lpeg.secondofsplit(":"),"bc"))
--~ print(9,match(lpeg.secondofsplit(":","123"),"bc"))
--~ -- slower:
--~
--~ function lpeg.counter(pattern)
--~ local n, pattern = 0, (lpeg.P(pattern)/function() n = n + 1 end + lpeg.anything)^0
--~ return function(str) n = 0 ; lpegmatch(pattern,str) ; return n end
--~ end
local nany = utf8char/""
function lpeg.counter(pattern)
pattern = Cs((P(pattern)/" " + nany)^0)
return function(str)
return #match(pattern,str)
end
end
if utfgmatch then
function lpeg.count(str,what) -- replaces string.count
if type(what) == "string" then
local n = 0
for _ in utfgmatch(str,what) do
n = n + 1
end
return n
else -- 4 times slower but still faster than / function
return #match(Cs((P(what)/" " + nany)^0),str)
end
end
else
local cache = { }
function lpeg.count(str,what) -- replaces string.count
if type(what) == "string" then
local p = cache[what]
if not p then
p = Cs((P(what)/" " + nany)^0)
cache[p] = p
end
return #match(p,str)
else -- 4 times slower but still faster than / function
return #match(Cs((P(what)/" " + nany)^0),str)
end
end
end
local patterns_escapes = { -- also defines in l-string
["%"] = "%%",
["."] = "%.",
["+"] = "%+", ["-"] = "%-", ["*"] = "%*",
["["] = "%[", ["]"] = "%]",
["("] = "%)", [")"] = "%)",
-- ["{"] = "%{", ["}"] = "%}"
-- ["^"] = "%^", ["$"] = "%$",
}
local simple_escapes = { -- also defines in l-string
["-"] = "%-",
["."] = "%.",
["?"] = ".",
["*"] = ".*",
}
local p = Cs((S("-.+*%()[]") / patterns_escapes + anything)^0)
local s = Cs((S("-.+*%()[]") / simple_escapes + anything)^0)
function string.escapedpattern(str,simple)
return match(simple and s or p,str)
end
-- utf extensies
lpeg.UP = lpeg.P
if utfcharacters then
function lpeg.US(str)
local p
for uc in utfcharacters(str) do
if p then
p = p + P(uc)
else
p = P(uc)
end
end
return p
end
elseif utfgmatch then
function lpeg.US(str)
local p
for uc in utfgmatch(str,".") do
if p then
p = p + P(uc)
else
p = P(uc)
end
end
return p
end
else
function lpeg.US(str)
local p
local f = function(uc)
if p then
p = p + P(uc)
else
p = P(uc)
end
end
match((utf8char/f)^0,str)
return p
end
end
local range = Cs(utf8byte) * (Cs(utf8byte) + Cc(false))
local utfchar = unicode and unicode.utf8 and unicode.utf8.char
function lpeg.UR(str,more)
local first, last
if type(str) == "number" then
first = str
last = more or first
else
first, last = match(range,str)
if not last then
return P(str)
end
end
if first == last then
return P(str)
elseif utfchar and last - first < 8 then -- a somewhat arbitrary criterium
local p
for i=first,last do
if p then
p = p + P(utfchar(i))
else
p = P(utfchar(i))
end
end
return p -- nil when invalid range
else
local f = function(b)
return b >= first and b <= last
end
return utf8byte / f -- nil when invalid range
end
end
--~ lpeg.print(lpeg.R("ab","cd","gh"))
--~ lpeg.print(lpeg.P("a","b","c"))
--~ lpeg.print(lpeg.S("a","b","c"))
--~ print(lpeg.count("äáàa",lpeg.P("á") + lpeg.P("à")))
--~ print(lpeg.count("äáàa",lpeg.UP("áà")))
--~ print(lpeg.count("äáàa",lpeg.US("àá")))
--~ print(lpeg.count("äáàa",lpeg.UR("aá")))
--~ print(lpeg.count("äáàa",lpeg.UR("àá")))
--~ print(lpeg.count("äáàa",lpeg.UR(0x0000,0xFFFF)))
function lpeg.oneof(list,...) -- lpeg.oneof("elseif","else","if","then")
if type(list) ~= "table" then
list = { list, ... }
end
-- sort(list) -- longest match first
local p = P(list[1])
for l=2,#list do
p = p + P(list[l])
end
return p
end
function lpeg.is_lpeg(p)
return p and lpegtype(p) == "pattern"
end
--~ Cf(Ct("") * (Cg(C(...) * "=" * Cs(...)))^0, rawset)
|