-
Notifications
You must be signed in to change notification settings - Fork 17
/
lexer.lua
491 lines (454 loc) · 15.4 KB
/
lexer.lua
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
--lexer.lua is part of Penlight http://stevedonovan.github.com/Penlight/
--[[
Copyright (C) 2009 Steve Donovan, David Manura.
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
associated documentation files (the "Software"), to deal in the Software without restriction,
including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense,
and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so,
subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
]]
--- Lexical scanner for creating a sequence of tokens from text.
-- `lexer.scan(s)` returns an iterator over all tokens found in the
-- string `s`. This iterator returns two values, a token type string
-- (such as 'string' for quoted string, 'iden' for identifier) and the value of the
-- token.
--
-- Versions specialized for Lua and C are available; these also handle block comments
-- and classify keywords as 'keyword' tokens. For example:
--
-- > s = 'for i=1,n do'
-- > for t,v in lexer.lua(s) do print(t,v) end
-- keyword for
-- iden i
-- = =
-- number 1
-- , ,
-- iden n
-- keyword do
--
-- See the Guide for further @{06-data.md.Lexical_Scanning|discussion}
-- @module pl.lexer
local yield,wrap = coroutine.yield,coroutine.wrap
local strfind = string.find
local strsub = string.sub
local append = table.insert
local function assert_arg(idx,val,tp)
if type(val) ~= tp then
error("argument "..idx.." must be "..tp, 2)
end
end
local lexer = {}
local NUMBER1 = '^[%+%-]?%d+%.?%d*[eE][%+%-]?%d+'
local NUMBER2 = '^[%+%-]?%d+%.?%d*'
local NUMBER3 = '^0x[%da-fA-F]+'
local NUMBER4 = '^%d+%.?%d*[eE][%+%-]?%d+'
local NUMBER5 = '^%d+%.?%d*'
local IDEN = '^[%a_][%w_]*'
local WSPACE = '^%s+'
local STRING1 = "^(['\"])%1" -- empty string
local STRING2 = [[^(['"])(\*)%2%1]]
local STRING3 = [[^(['"]).-[^\](\*)%2%1]]
local CHAR1 = "^''"
local CHAR2 = [[^'(\*)%1']]
local CHAR3 = [[^'.-[^\](\*)%1']]
local PREPRO = '^#.-[^\\]\n'
local plain_matches,lua_matches,cpp_matches,lua_keyword,cpp_keyword
local function tdump(tok)
return yield(tok,tok)
end
local function ndump(tok,options)
if options and options.number then
tok = tonumber(tok)
end
return yield("number",tok)
end
-- regular strings, single or double quotes; usually we want them
-- without the quotes
local function sdump(tok,options)
if options and options.string then
tok = tok:sub(2,-2)
end
return yield("string",tok)
end
-- long Lua strings need extra work to get rid of the quotes
local function sdump_l(tok,options,findres)
if options and options.string then
local quotelen = 3
if findres[3] then
quotelen = quotelen + findres[3]:len()
end
tok = tok:sub(quotelen, -quotelen)
if tok:sub(1, 1) == "\n" then
tok = tok:sub(2)
end
end
return yield("string",tok)
end
local function chdump(tok,options)
if options and options.string then
tok = tok:sub(2,-2)
end
return yield("char",tok)
end
local function cdump(tok)
return yield('comment',tok)
end
local function wsdump (tok)
return yield("space",tok)
end
local function pdump (tok)
return yield('prepro',tok)
end
local function plain_vdump(tok)
return yield("iden",tok)
end
local function lua_vdump(tok)
if lua_keyword[tok] then
return yield("keyword",tok)
else
return yield("iden",tok)
end
end
local function cpp_vdump(tok)
if cpp_keyword[tok] then
return yield("keyword",tok)
else
return yield("iden",tok)
end
end
--- create a plain token iterator from a string or file-like object.
-- @tparam string|file s a string or a file-like object with `:read()` method returning lines.
-- @tab matches an optional match table - array of token descriptions.
-- A token is described by a `{pattern, action}` pair, where `pattern` should match
-- token body and `action` is a function called when a token of described type is found.
-- @tab[opt] filter a table of token types to exclude, by default `{space=true}`
-- @tab[opt] options a table of options; by default, `{number=true,string=true}`,
-- which means convert numbers and strip string quotes.
function lexer.scan(s,matches,filter,options)
local file = type(s) ~= 'string' and s
filter = filter or {space=true}
options = options or {number=true,string=true}
if filter then
if filter.space then filter[wsdump] = true end
if filter.comments then
filter[cdump] = true
end
end
if not matches then
if not plain_matches then
plain_matches = {
{WSPACE,wsdump},
{NUMBER3,ndump},
{IDEN,plain_vdump},
{NUMBER1,ndump},
{NUMBER2,ndump},
{STRING1,sdump},
{STRING2,sdump},
{STRING3,sdump},
{'^.',tdump}
}
end
matches = plain_matches
end
local function lex()
local line_nr = 0
local next_line = file and file:read()
local sz = file and 0 or #s
local idx = 1
while true do
if idx > sz then
if file then
if not next_line then return end
s = next_line
line_nr = line_nr + 1
next_line = file:read()
if next_line then
s = s .. '\n'
end
idx, sz = 1, #s
else
return
end
end
for _,m in ipairs(matches) do
local pat = m[1]
local fun = m[2]
local findres = {strfind(s,pat,idx)}
local i1, i2 = findres[1], findres[2]
if i1 then
local tok = strsub(s,i1,i2)
idx = i2 + 1
local res
if not (filter and filter[fun]) then
lexer.finished = idx > sz
res = fun(tok, options, findres)
end
if res then
local tp = type(res)
-- insert a token list
if tp == 'table' then
yield('','')
for _,t in ipairs(res) do
yield(t[1],t[2])
end
elseif tp == 'string' then -- or search up to some special pattern
i1,i2 = strfind(s,res,idx)
if i1 then
tok = strsub(s,i1,i2)
idx = i2 + 1
yield('',tok)
else
yield('','')
idx = sz + 1
end
else
yield(line_nr,idx)
end
end
break
end
end
end
end
return wrap(lex)
end
local function isstring (s)
return type(s) == 'string'
end
--- insert tokens into a stream.
-- @param tok a token stream
-- @param a1 a string is the type, a table is a token list and
-- a function is assumed to be a token-like iterator (returns type & value)
-- @string a2 a string is the value
function lexer.insert (tok,a1,a2)
if not a1 then return end
local ts
if isstring(a1) and isstring(a2) then
ts = {{a1,a2}}
elseif type(a1) == 'function' then
ts = {}
for t,v in a1() do
append(ts,{t,v})
end
else
ts = a1
end
tok(ts)
end
--- get everything in a stream upto a newline.
-- @param tok a token stream
-- @return a string
function lexer.getline (tok)
local t,v = tok('.-\n')
return v
end
--- get current line number.
-- Only available if the input source is a file-like object.
-- @param tok a token stream
-- @return the line number and current column
function lexer.lineno (tok)
return tok(0)
end
--- get the rest of the stream.
-- @param tok a token stream
-- @return a string
function lexer.getrest (tok)
local t,v = tok('.+')
return v
end
--- get the Lua keywords as a set-like table.
-- So `res["and"]` etc would be `true`.
-- @return a table
function lexer.get_keywords ()
if not lua_keyword then
lua_keyword = {
["and"] = true, ["break"] = true, ["do"] = true,
["else"] = true, ["elseif"] = true, ["end"] = true,
["false"] = true, ["for"] = true, ["function"] = true,
["if"] = true, ["in"] = true, ["local"] = true, ["nil"] = true,
["not"] = true, ["or"] = true, ["repeat"] = true,
["return"] = true, ["then"] = true, ["true"] = true,
["until"] = true, ["while"] = true
}
end
return lua_keyword
end
--- create a Lua token iterator from a string or file-like object.
-- Will return the token type and value.
-- @string s the string
-- @tab[opt] filter a table of token types to exclude, by default `{space=true,comments=true}`
-- @tab[opt] options a table of options; by default, `{number=true,string=true}`,
-- which means convert numbers and strip string quotes.
function lexer.lua(s,filter,options)
filter = filter or {space=true,comments=true}
lexer.get_keywords()
if not lua_matches then
lua_matches = {
{WSPACE,wsdump},
{NUMBER3,ndump},
{IDEN,lua_vdump},
{NUMBER4,ndump},
{NUMBER5,ndump},
{STRING1,sdump},
{STRING2,sdump},
{STRING3,sdump},
{'^%-%-%[(=*)%[.-%]%1%]',cdump},
{'^%-%-.-\n',cdump},
{'^%[(=*)%[.-%]%1%]',sdump_l},
{'^==',tdump},
{'^~=',tdump},
{'^<=',tdump},
{'^>=',tdump},
{'^%.%.%.',tdump},
{'^%.%.',tdump},
{'^.',tdump}
}
end
return lexer.scan(s,lua_matches,filter,options)
end
--- create a C/C++ token iterator from a string or file-like object.
-- Will return the token type type and value.
-- @string s the string
-- @tab[opt] filter a table of token types to exclude, by default `{space=true,comments=true}`
-- @tab[opt] options a table of options; by default, `{number=true,string=true}`,
-- which means convert numbers and strip string quotes.
function lexer.cpp(s,filter,options)
filter = filter or {space=true,comments=true}
if not cpp_keyword then
cpp_keyword = {
["class"] = true, ["break"] = true, ["do"] = true, ["sizeof"] = true,
["else"] = true, ["continue"] = true, ["struct"] = true,
["false"] = true, ["for"] = true, ["public"] = true, ["void"] = true,
["private"] = true, ["protected"] = true, ["goto"] = true,
["if"] = true, ["static"] = true, ["const"] = true, ["typedef"] = true,
["enum"] = true, ["char"] = true, ["int"] = true, ["bool"] = true,
["long"] = true, ["float"] = true, ["true"] = true, ["delete"] = true,
["double"] = true, ["while"] = true, ["new"] = true,
["namespace"] = true, ["try"] = true, ["catch"] = true,
["switch"] = true, ["case"] = true, ["extern"] = true,
["return"] = true,["default"] = true,['unsigned'] = true,['signed'] = true,
["union"] = true, ["volatile"] = true, ["register"] = true,["short"] = true,
}
end
if not cpp_matches then
cpp_matches = {
{WSPACE,wsdump},
{PREPRO,pdump},
{NUMBER3,ndump},
{IDEN,cpp_vdump},
{NUMBER4,ndump},
{NUMBER5,ndump},
{CHAR1,chdump},
{CHAR2,chdump},
{CHAR3,chdump},
{STRING1,sdump},
{STRING2,sdump},
{STRING3,sdump},
{'^//.-\n',cdump},
{'^/%*.-%*/',cdump},
{'^==',tdump},
{'^!=',tdump},
{'^<=',tdump},
{'^>=',tdump},
{'^->',tdump},
{'^&&',tdump},
{'^||',tdump},
{'^%+%+',tdump},
{'^%-%-',tdump},
{'^%+=',tdump},
{'^%-=',tdump},
{'^%*=',tdump},
{'^/=',tdump},
{'^|=',tdump},
{'^%^=',tdump},
{'^::',tdump},
{'^.',tdump}
}
end
return lexer.scan(s,cpp_matches,filter,options)
end
--- get a list of parameters separated by a delimiter from a stream.
-- @param tok the token stream
-- @string[opt=')'] endtoken end of list. Can be '\n'
-- @string[opt=','] delim separator
-- @return a list of token lists.
function lexer.get_separated_list(tok,endtoken,delim)
endtoken = endtoken or ')'
delim = delim or ','
local parm_values = {}
local level = 1 -- used to count ( and )
local tl = {}
local function tappend (tl,t,val)
val = val or t
append(tl,{t,val})
end
local is_end
if endtoken == '\n' then
is_end = function(t,val)
return t == 'space' and val:find '\n'
end
else
is_end = function (t)
return t == endtoken
end
end
local token,value
while true do
token,value=tok()
if not token then return nil,'EOS' end -- end of stream is an error!
if is_end(token,value) and level == 1 then
append(parm_values,tl)
break
elseif token == '(' then
level = level + 1
tappend(tl,'(')
elseif token == ')' then
level = level - 1
if level == 0 then -- finished with parm list
append(parm_values,tl)
break
else
tappend(tl,')')
end
elseif token == delim and level == 1 then
append(parm_values,tl) -- a new parm
tl = {}
else
tappend(tl,token,value)
end
end
return parm_values,{token,value}
end
--- get the next non-space token from the stream.
-- @param tok the token stream.
function lexer.skipws (tok)
local t,v = tok()
while t == 'space' do
t,v = tok()
end
return t,v
end
local skipws = lexer.skipws
--- get the next token, which must be of the expected type.
-- Throws an error if this type does not match!
-- @param tok the token stream
-- @string expected_type the token type
-- @bool no_skip_ws whether we should skip whitespace
function lexer.expecting (tok,expected_type,no_skip_ws)
assert_arg(1,tok,'function')
assert_arg(2,expected_type,'string')
local t,v
if no_skip_ws then
t,v = tok()
else
t,v = skipws(tok)
end
if t ~= expected_type then error ("expecting "..expected_type,2) end
return v
end
return lexer