forked from RefPerSys/RefPerSys
-
Notifications
You must be signed in to change notification settings - Fork 0
/
lexer_rps.cc
1217 lines (1164 loc) · 47.4 KB
/
lexer_rps.cc
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
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/****************************************************************
* file lexer_rps.cc
* SPDX-License-Identifier: GPL-3.0-or-later
*
* Description:
* This file is part of the Reflective Persistent System.
*
* It has the lexer support for the Read Eval Print Loop
*
* Author(s):
* Basile Starynkevitch <[email protected]>
* Abhishek Chakravarti <[email protected]>
* Nimesh Neema <[email protected]>
*
* © Copyright 2019 - 2022 The Reflective Persistent System Team
* [email protected] & http://refpersys.org/
*
* License:
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
******************************************************************************/
#include "refpersys.hh"
/// libunistring www.gnu.org/software/libunistring/
#include "unictype.h"
#include "uniconv.h"
#include <termios.h>
#include <wordexp.h>
extern "C" const char rps_lexer_gitid[];
const char rps_lexer_gitid[]= RPS_GITID;
extern "C" const char rps_lexer_date[];
const char rps_lexer_date[]= __DATE__;
extern "C" Rps_StringValue rps_lexer_token_name_str_val;
Rps_StringValue rps_lexer_token_name_str_val(nullptr);
Rps_TokenSource::Rps_TokenSource(std::string name)
: toksrc_name(name), toksrc_line(0), toksrc_col(0), toksrc_counter(0),
toksrc_linebuf{},
toksrc_ptrnameval(nullptr)
{
} // end Rps_TokenSource::Rps_TokenSource
void
Rps_TokenSource::gc_mark(Rps_GarbageCollector&gc, unsigned depth)
{
RPS_ASSERT(gc.is_valid_garbcoll());
really_gc_mark(gc,depth);
} // end Rps_TokenSource::gc_mark
void
Rps_TokenSource::really_gc_mark(Rps_GarbageCollector&gc, unsigned depth)
{
RPS_ASSERT(gc.is_valid_garbcoll());
RPS_ASSERT(depth < max_gc_depth);
if (rps_lexer_token_name_str_val)
rps_lexer_token_name_str_val.gc_mark(gc,depth);
if (toksrc_ptrnameval)
toksrc_ptrnameval->gc_mark(gc, depth+1);
} // end Rps_TokenSource::really_gc_mark
/// the current token source name is needed as a string value for
/// constructing Rps_LexTokenValue-s. We want to avoid creating that
/// source name, as a RefPerSys string, at every lexical token. So we
/// try to memoize it in rps_lexer_token_name_str_val;
Rps_Value
Rps_TokenSource::name_val(Rps_CallFrame*callframe)
{
RPS_ASSERT(callframe==nullptr || callframe->is_good_call_frame());
RPS_ASSERT(rps_is_main_thread());
if (rps_lexer_token_name_str_val && rps_lexer_token_name_str_val.is_string()
&& rps_lexer_token_name_str_val.to_cppstring() == toksrc_name)
return rps_lexer_token_name_str_val;
rps_lexer_token_name_str_val = Rps_String::make(toksrc_name);
return rps_lexer_token_name_str_val;
} // end Rps_TokenSource::name_val
const Rps_LexTokenZone*
Rps_TokenSource::make_token(Rps_CallFrame*callframe,
Rps_ObjectRef lexkindarg, Rps_Value lexvalarg,
const Rps_String*sourcev)
{
RPS_LOCALFRAME(RPS_ROOT_OB(_0S6DQvp3Gop015zXhL), //lexical_token∈class
/*callerframe:*/callframe,
Rps_ObjectRef lexkindob;
Rps_Value lexval;
Rps_LexTokenZone*tokenp;
Rps_Value namestrv;
const Rps_String* nstrv;
const Rps_String* srcv;
);
RPS_ASSERT(rps_is_main_thread());
_f.lexkindob = lexkindarg;
_f.lexval = lexvalarg;
_f.namestrv = name_val(&_);
_f.nstrv = _f.namestrv.as_string();
_f.srcv = sourcev;
RPS_ASSERT (!_f.srcv || _f.srcv->stored_type() == Rps_Type::String);
_f.tokenp =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,
Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this, _f.lexkindob, _f.lexval, _f.nstrv,
toksrc_line, toksrc_col);
#warning Rps_TokenSource::make_token should probably use _f.srcv
return _f.tokenp;
} // end Rps_TokenSource::make_token
const std::string
Rps_TokenSource::position_str(int col) const
{
if (col<0) col = toksrc_col;
std::ostringstream outs;
outs << toksrc_name << ":L" << toksrc_line << ",C:" << col << std::flush;
return outs.str();
} // end Rps_TokenSource::position_str
Rps_TokenSource::~Rps_TokenSource()
{
toksrc_name.clear();
toksrc_line= -1;
toksrc_col= -1;
toksrc_linebuf.clear();
} // end Rps_TokenSource::~Rps_TokenSource
Rps_StreamTokenSource::Rps_StreamTokenSource(std::string path)
: Rps_TokenSource(""), toksrc_input_stream()
{
wordexp_t wx= {};
int err = wordexp(path.c_str(), &wx, WRDE_SHOWERR);
if (err)
{
RPS_WARNOUT("stream token source for '" << Rps_Cjson_String(path) << "' failed: error#" << err);
throw std::runtime_error(std::string{"bad stream token source:"} + path);
}
if (wx.we_wordc == 0)
{
RPS_WARNOUT("no stream token source for '" << (Rps_Cjson_String(path)) << "'");
throw std::runtime_error(std::string{"no stream token source:"} + path);
}
else if (wx.we_wordc > 1)
{
RPS_WARNOUT("ambiguous stream token source for '" << path << "' expanded to "
<< wx.we_wordv[0] << " and " << wx.we_wordv[1]
<< ((wx.we_wordc>2)?" etc...":" files"));
throw std::runtime_error(std::string{"ambiguous stream token source:"} + path);
};
char* curword = wx.we_wordv[0];
toksrc_input_stream.open(curword);
set_name(std::string(curword));
} // end Rps_StreamTokenSource::Rps_StreamTokenSource
Rps_StreamTokenSource::~Rps_StreamTokenSource()
{
toksrc_input_stream.close();
} // end ps_StreamTokenSource::~Rps_StreamTokenSource
bool
Rps_StreamTokenSource::get_line(void)
{
std::getline( toksrc_input_stream, toksrc_linebuf);
if (!toksrc_input_stream && toksrc_linebuf.empty()) return false;
starting_new_input_line();
return true;
} // end Rps_StreamTokenSource::get_line
Rps_CinTokenSource::Rps_CinTokenSource()
: Rps_TokenSource("-")
{
}; // end Rps_CinTokenSource::Rps_CinTokenSource
Rps_CinTokenSource::~Rps_CinTokenSource()
{
}; // end Rps_CinTokenSource::~Rps_CinTokenSource
bool
Rps_CinTokenSource::get_line(void)
{
std::getline(std::cin, toksrc_linebuf);
if (!std::cin && toksrc_linebuf.empty()) return false;
starting_new_input_line();
return true;
} // end Rps_CinTokenSource::get_line
////////////////
Rps_StringTokenSource::Rps_StringTokenSource(std::string inptstr, std::string name)
: Rps_TokenSource(name), toksrcstr_inp(inptstr)
{
} // end Rps_StringTokenSource::Rps_StringTokenSource
Rps_StringTokenSource::~Rps_StringTokenSource()
{
} // end Rps_StringTokenSource::~Rps_StringTokenSource
bool
Rps_StringTokenSource::get_line()
{
std::getline(toksrcstr_inp, toksrc_linebuf);
if (!toksrcstr_inp && toksrc_linebuf.empty())
return false;
return true;
} // end Rps_StringTokenSource::get_line()
////////////////
Rps_LexTokenValue
Rps_TokenSource::get_token(Rps_CallFrame*callframe)
{
RPS_ASSERT(callframe==nullptr || callframe->is_good_call_frame());
RPS_LOCALFRAME(/*descr:*/RPS_ROOT_OB(_0S6DQvp3Gop015zXhL), //lexical_token∈class
/*callerframe:*/callframe,
Rps_Value res;
Rps_ObjectRef lexkindob;
Rps_Value lextokv;
Rps_ObjectRef oblex;
Rps_Value namev;
Rps_Value delimv;
Rps_ObjectRef obdelim;
);
const char* curp = curcptr();
if (curp)
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::get_token start curp='" << Rps_Cjson_String(curp) << "' at " << position_str());
else
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::get_token start no curp at " << position_str());
ucs4_t curuc=0;
int ulen= -1;
size_t linelen = toksrc_linebuf.size();
// check that we have a proper UTF-8 character
ulen=curp?u8_strmbtouc(&curuc, (const uint8_t*)curp):0; // length in bytes
if (ulen<0)
{
std::ostringstream errout;
errout << "bad UTF-8 encoding in " << toksrc_name << ":L" << toksrc_line << ",C" << toksrc_col << std::flush;
RPS_WARNOUT("Rps_TokenSource::get_token: " << errout.str());
throw std::runtime_error(errout.str());
}
while (curp && isspace(*curp) && toksrc_col<(int)linelen)
curp++, toksrc_col++;
if (curp)
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::get_token curp='" << Rps_Cjson_String(curp) << "' at " << position_str());
else
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::get_token no curp at " << position_str());
if (toksrc_col>=(int)linelen)
return nullptr;
ulen=curp?u8_strmbtouc(&curuc, (const uint8_t*)curp):0; // length in bytes
/// lex numbers?
if (isdigit(*curp) ||
((curp[0] == '+' || curp[0] == '-') && isdigit(curp[1])))
{
int curlin = toksrc_line;
int curcol = toksrc_col;
char*endint=nullptr;
char*endfloat=nullptr;
const char*startnum = curp;
long long l = strtoll(startnum, &endint, 0);
double d = strtod(startnum, &endfloat);
RPS_ASSERT(endint != nullptr && endfloat != nullptr);
if (endfloat > endint)
{
toksrc_col += endfloat - startnum;
_f.lextokv = Rps_DoubleValue(d);
_f.lexkindob = RPS_ROOT_OB(_98sc8kSOXV003i86w5); //double∈class
}
else
{
toksrc_col += endint - startnum;
_f.lextokv = Rps_Value::make_tagged_int(l);
_f.lexkindob = RPS_ROOT_OB(_2A2mrPpR3Qf03p6o5b); //int∈class
}
_f.namev = name_val(&_);
const Rps_String* str = _f.namev.to_string();
Rps_LexTokenZone* lextok =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this,_f.lexkindob, _f.lextokv,
str,
curlin, curcol);
_f.res = Rps_LexTokenValue(lextok);
lextok->set_serial(++toksrc_counter);
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter << " number :-◑> " << _f.res << " @! " << position_str());
return _f.res;
} //- end lexing numbers
///
/// lex infinities (double) - but not NAN
else if ((!strncmp(curp, "+INF", 4)
|| !strncmp(curp, "-INF", 4))
&& !isalnum(curp[4]))
{
int curlin = toksrc_line;
int curcol = toksrc_col;
bool pos = *curp == '+';
double infd = (pos
?std::numeric_limits<double>::infinity()
: -std::numeric_limits<double>::infinity());
toksrc_col += 4;
_f.lextokv = Rps_DoubleValue(infd);
_f.lexkindob = RPS_ROOT_OB(_98sc8kSOXV003i86w5); //double∈class
_f.namev= name_val(&_);
const Rps_String* str = _f.namev.to_string();
Rps_LexTokenZone* lextok =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this,_f.lexkindob, _f.lextokv,
str,
curlin, curcol);
_f.res = Rps_LexTokenValue(lextok);
lextok->set_serial(++toksrc_counter);
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter
<<" infinity :-◑> " << _f.res << " @! " << position_str());
return _f.res;
} //- end lexing infinities
/// lex names or objectids
else if (isalpha(*curp) || *curp == '_')
{
const char*startname = curp;
int curlin = toksrc_line;
int curcol = toksrc_col;
int startcol = curcol;
while ((isalpha(*curp) || *curp == '_') && toksrc_col<(int)linelen)
curp++, toksrc_col++;
std::string namestr(startname, toksrc_col-startcol);
_f.namev = name_val(&_);
RPS_DEBUG_LOG(REPL, "get_token oid|name '" << namestr << "' namev=" << _f.namev << " at "
<< position_str(startcol) << " ... " << position_str());
_f.oblex = Rps_ObjectRef::find_object_or_null_by_string(&_, namestr);
RPS_DEBUG_LOG(REPL, "get_token oid|name '" << namestr << "' oblex=" << _f.oblex);
const Rps_String* str = _f.namev.to_string();
RPS_DEBUG_LOG(REPL, "get_token namestr='" << Rps_Cjson_String(namestr) << "' oblex=" << _f.oblex
<< " namev=" << _f.namev << ", str=" << Rps_Value(str));
if (_f.oblex)
{
_f.lexkindob = RPS_ROOT_OB(_5yhJGgxLwLp00X0xEQ); //object∈class
_f.lextokv = _f.oblex;
Rps_LexTokenZone* lextokz =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this, _f.lexkindob, _f.lextokv,
str,
curlin, curcol);
_f.res = Rps_LexTokenValue(lextokz);
lextokz->set_serial(++toksrc_counter);
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter
<< " object :-◑> " << _f.res << " @! " << position_str());
return _f.res;
}
else if (isalpha(namestr[0])) // new symbol
{
_f.lexkindob = RPS_ROOT_OB(_36I1BY2NetN03WjrOv); //symbol∈class
_f.lextokv = Rps_StringValue(namestr);
Rps_LexTokenZone* lextok =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this, _f.lexkindob, _f.lextokv,
str,
curlin, curcol);
_f.res = Rps_LexTokenValue(lextok);
lextok->set_serial(++toksrc_counter);
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter
<< " symbol :-◑> " << _f.res << " @! " << position_str());
return _f.res;
}
else // bad name
{
toksrc_col = startcol;
RPS_DEBUG_LOG(REPL, "get_token FAIL bad name " << _f.namev << " @! " << position_str());
return nullptr;
}
}
//// literal single line strings are like in C++
else if (*curp == '"') /// plain literal string, on a single line
{
int linestart = toksrc_line;
int colstart = toksrc_col;
std::string litstr = lex_quoted_literal_string(&_);
_f.namev= name_val(&_);
const Rps_String* str = _f.namev.to_string();
_f.lexkindob = RPS_ROOT_OB(_62LTwxwKpQ802SsmjE); //string∈class
_f.lextokv = Rps_String::make(litstr);
Rps_LexTokenZone* lextok =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this,_f.lexkindob, _f.lextokv,
str,
linestart, colstart);
_f.res = Rps_LexTokenValue(lextok);
lextok->set_serial(++toksrc_counter);
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter
<< " single-line string :-◑> " << _f.res << " @! " << position_str());
return _f.res;
} // end single-line literal string token
//// raw literal strings may span across several lines, like in C++
//// see https://en.cppreference.com/w/cpp/language/string_literal
else if (*curp == 'R'
&& curp[0] == 'R' && curp[1] == '"' && isalpha(curp[2]))
{
int linestart = toksrc_line;
int colstart = toksrc_col;
std::string litstr = lex_raw_literal_string(&_);
_f.namev= name_val(&_);
const Rps_String* str = _f.namev.to_string();
_f.lexkindob = RPS_ROOT_OB(_62LTwxwKpQ802SsmjE); //string∈class
_f.lextokv = Rps_String::make(litstr);
Rps_LexTokenZone* lextok =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this,_f.lexkindob, _f.lextokv,
str,
linestart, colstart);
_f.res = Rps_LexTokenValue(lextok);
lextok->set_serial(++toksrc_counter);
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter
<< " multi-line literal string :-◑> " << _f.res << " @! " << position_str());
return _f.res;
} // end possibly multi-line raw literal strings
//// a code chunk or macro string is mixing strings and
//// objects.... Inspired by GCC MELT see
//// starynkevitch.net/Basile/gcc-melt/MELT-Starynkevitch-DSL2011.pdf
/* Improvement over GCC MELT: a macro string can start with "#{"
ending with "}#" or "#a{" ending with "}a#" or "#ab{" ending with
"}ab#" or "#abc{" ending with "}abc#" or "#abcd{" ending with
"}abcd#" or "#abcde{" ending with "}abcde#" or "#abcdef{" ending
with "}abcdef#" with the letters being arbitrary latin letters,
upper or lowercase. but no more than 7 letters. */
else if (curp[0] == '#'
&& (
curp[1] == '{'
|| (isalpha(curp[1])
&& (curp[2] == '{'
|| (isalpha(curp[2])
&& (curp[3] == '{'
|| (isalpha(curp[3])
&& (curp[4] == '{'
|| (isalpha(curp[4])
&& (curp[5] == '{'
|| (isalpha(curp[6])
&& (curp[6] == '{'
|| (isalpha(curp[7])
&& (curp[7] == '{'
|| (isalpha(curp[7])
&& (curp[8] == '{'
|| (isalpha(curp[8])
&& curp[9] == '{')
)
)
)
)
)
)
)
)
)
)
)
)
)
)
)
)
{
int linestart = toksrc_line;
int colstart = toksrc_col;
RPS_DEBUG_LOG(REPL, "get_token code_chunk starting at " << position_str() << curp);
_f.namev= name_val(&_);
const Rps_String* str = _f.namev.to_string();
_f.lextokv = lex_code_chunk(&_);
_f.lexkindob = RPS_ROOT_OB(_3rXxMck40kz03RxRLM); //code_chunk∈class
Rps_LexTokenZone* lextok =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this,_f.lexkindob, _f.lextokv,
str,
linestart, colstart);
_f.res = Rps_LexTokenValue(lextok);
lextok->set_serial(++toksrc_counter);
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter
<< " code_chunk :-◑> " << _f.res << " @! " << position_str());
return _f.res;
} // end lexing code chunk
//// sequence of at most four ASCII or UTF-8 punctuation
else if (ispunct(*curp) || uc_is_punct(curuc))
{
RPS_DEBUG_LOG(REPL, "get_token start punctuation curp='" << Rps_Cjson_String(curp) << "' at " << position_str());
std::string delimpos = position_str();
int startcol = toksrc_col;
_f.delimv = get_delimiter(&_);
std::string delimstartstr {curp};
RPS_DEBUG_LOG(REPL, "get_token after get_delimiter_object delimv=" << _f.delimv << " at " << position_str());
if (!_f.delimv)
{
RPS_WARNOUT("invalid delimiter " << Rps_Cjson_String(delimstartstr) << " at " << delimpos);
std::string warndelimstr{"invalid delimiter "};
warndelimstr += Rps_Cjson_String(delimstartstr);
warndelimstr += " at ";
warndelimstr += delimpos;
throw std::runtime_error(warndelimstr);
}
toksrc_counter++;
RPS_DEBUG_LOG(REPL, "get_token#" << toksrc_counter
<< " delimiter :-◑> " << _f.delimv << " at " << position_str());
return _f.delimv;
}
#warning Rps_TokenSource::get_token unimplemented
RPS_FATALOUT("unimplemented Rps_TokenSource::get_token @ " << name() << " @! " << position_str());
// we should refactor properly the rps_repl_lexer & Rps_LexTokenZone constructor here
} // end Rps_TokenSource::get_token
Rps_Value
Rps_TokenSource::get_delimiter(Rps_CallFrame*callframe)
{
RPS_LOCALFRAME(/*descr:*/nullptr,
/*callerframe:*/callframe,
Rps_Value res;
Rps_ObjectRef obdictdelim;
Rps_Value delimv;
Rps_Value namev;
Rps_ObjectRef lexkindob;
Rps_Value lextokv;
);
const char*curp=nullptr;
RPS_ASSERT(callframe && callframe->is_good_call_frame());
std::string startpos = position_str();
_f.obdictdelim = RPS_ROOT_OB(_627ngdqrVfF020ugC5); //"repl_delim"∈string_dictionary
auto paylstrdict = _f.obdictdelim->get_dynamic_payload<Rps_PayloadStringDict>();
RPS_ASSERT (paylstrdict != nullptr);
std::string delimstr;
int nbdelimch=0; // number of delimiter UTF8 characters
bool again=false;
const char* startp = curcptr();
unsigned startcol = toksrc_col;
ucs4_t curuc=0;
RPS_ASSERT(startp);
curp = startp;
do
{
curuc = 0;
int ulen= -1;
again=false;
if (!curp)
break;
if (isspace(*curp))
break;
// FIXME: maybe we should remember the byte position of every
// delimiter character (it can be UTF-8 like °)
if (*curp < 127 && ispunct(*curp))
{
delimstr.push_back(*curp);
curp ++;
nbdelimch ++;
again = true;
}
else if (*(const uint8_t*)curp > 128
&& (ulen=u8_strmbtouc(&curuc, (const uint8_t*)curp) // length in bytes
> 0)
&& uc_is_punct(curuc))
{
delimstr.append(curp, ulen);
curp += ulen;
nbdelimch ++;
again = true;
}
else
again = false;
}
while (again);
RPS_DEBUG_LOG(REPL, "get_delimiter delimstr='" << Rps_Cjson_String(delimstr) << "' nbdelimch="
<< nbdelimch << " startpos:" << startpos);
/***
* TODO: we need to find the longest substring in delimstr which is a known delimiter
***/
int loopcnt = 0;
static constexpr int maxloopdelim = 16;
while (!delimstr.empty() && loopcnt < maxloopdelim)
{
loopcnt ++;
_f.delimv = paylstrdict->find(delimstr);
RPS_DEBUG_LOG(REPL, "get_delimiter punctuation delimv=" << _f.delimv << " for delimstr='"
<< Rps_Cjson_String(delimstr) << "' loopcnt#" << loopcnt);
if (_f.delimv)
{
_f.lexkindob = RPS_ROOT_OB(_2wdmxJecnFZ02VGGFK); //repl_delimiter∈class
_f.lextokv = _f.delimv;
toksrc_col += delimstr.size();
const Rps_String* strv = _f.namev.to_string();
Rps_LexTokenZone* lextok =
Rps_QuasiZone::rps_allocate6<Rps_LexTokenZone,Rps_TokenSource*,Rps_ObjectRef,Rps_Value,const Rps_String*,int,int>
(this,_f.lexkindob, _f.lextokv,
strv,
toksrc_line, startcol);
lextok->set_serial(++toksrc_counter);
_f.res = Rps_LexTokenValue(lextok);
RPS_DEBUG_LOG(REPL, "get_delimiter delimiter :-◑> " << _f.res << " at " << position_str()
<< " at " << startpos << std::endl
<< RPS_FULL_BACKTRACE_HERE(1, "Rps_TokenSource::get_delimiter"));
return _f.res;
};
/// truncate the delimstr by one ending UTF-8
const uint8_t* prevu8 = u8_prev(&curuc,
reinterpret_cast<const uint8_t*>
(delimstr.c_str()+delimstr.size()),
reinterpret_cast<const uint8_t*>(delimstr.c_str()));
RPS_DEBUG_LOG(REPL, "get_delimiter prevu8='" << (const char*)prevu8
<< "' for delimstr='" << delimstr << "' with curuc#" << (int)curuc
<< " at " << startpos << " loopcnt#" << loopcnt);
if (!prevu8)
break;
unsigned curlen = delimstr.size();
unsigned prevlen = (delimstr.c_str()+delimstr.size() - (const char*)prevu8) +1;
RPS_DEBUG_LOG(REPL, "get_delimiter for delimstr='" << delimstr <<"' curlen=" << curlen
<< " prevlen=" << prevlen);
if (prevlen==0 || prevlen > delimstr.size())
break;
delimstr[prevlen] = (char)0; /// facilitates debugging, in principle useless
delimstr.resize(prevlen);
RPS_DEBUG_LOG(REPL, "get_delimiter now delimstr='" << delimstr << "' at " << startpos
<< " prevlen=" << prevlen << " curlen=" << curlen
<< " loopcnt#" << loopcnt << std::endl);
usleep (250000);
}
RPS_WARNOUT("Rps_TokenSource::get_delimiter failing at " << startpos
<< " for " << startp);
std::string failmsg {"Rps_TokenSource::get_delimiter failing at "};
failmsg += startpos;
throw std::runtime_error{failmsg};
} // end Rps_TokenSource::get_delimiter
std::string
Rps_TokenSource::lex_quoted_literal_string(Rps_CallFrame*callframe)
{
RPS_ASSERT(callframe && callframe->is_good_call_frame());
std::string rstr;
const char* curp = curcptr();
size_t linelen = toksrc_linebuf.size();
const char*eol = curp + (linelen-toksrc_col);
rstr.reserve(4+2*(eol-curp)/3);
RPS_ASSERT(*curp == '"');
toksrc_col++, curp++;
char curch = 0;
while ((curch=(*curp)) != (char)0)
{
if (curch == '"')
{
toksrc_col++;
return rstr;
}
else if (curch == '\\')
{
char nextch = curp[1];
char shortbuf[16];
memset(shortbuf, 0, sizeof(shortbuf));
switch (nextch)
{
case '\'':
case '\"':
case '\\':
rstr.push_back (nextch);
toksrc_col += 2;
continue;
case 'a':
rstr.push_back ('\a');
toksrc_col += 2;
continue;
case 'b':
rstr.push_back ('\b');
toksrc_col += 2;
continue;
case 'f':
rstr.push_back ('\f');
toksrc_col += 2;
continue;
case 'e': // ESCAPE
rstr.push_back ('\033');
toksrc_col += 2;
continue;
case 'n':
rstr.push_back ('\n');
toksrc_col += 2;
continue;
case 'r':
rstr.push_back ('\r');
toksrc_col += 2;
continue;
case 't':
rstr.push_back ('\t');
toksrc_col += 2;
continue;
case 'v':
rstr.push_back ('\v');
toksrc_col += 2;
continue;
case 'x':
{
int p = -1;
int c = 0;
if (sscanf (curp + 2, "%02x%n", &c, &p) > 0 && p > 0)
{
rstr.push_back ((char)c);
toksrc_col += p + 2;
continue;
}
else
goto lexical_error_backslash;
}
case 'u': // four hexdigit escape Unicode
{
int p = -1;
int c = 0;
if (sscanf (curp + 2, "%04x%n", &c, &p) > 0 && p > 0)
{
int l =
u8_uctomb ((uint8_t *) shortbuf, (ucs4_t) c, sizeof(shortbuf));
if (l > 0)
{
rstr.append(shortbuf);
toksrc_col += p + l;
continue;
}
else
goto lexical_error_backslash;
}
else
goto lexical_error_backslash;
}
case 'U': // eight hexdigit escape Unicode
{
int p = -1;
int c = 0;
if (sscanf (curp + 2, "%08x%n", &c, &p) > 0 && p > 0)
{
int l =
u8_uctomb ((uint8_t *) shortbuf, (ucs4_t) c, sizeof(shortbuf));
if (l > 0)
{
rstr.append(shortbuf);
toksrc_col += p + l;
continue;
}
else
goto lexical_error_backslash;
}
}
default:
goto lexical_error_backslash;
} // end switch nextch
} // end if curch is '\\'
else if (curch >= ' ' && curch < 0x7f)
{
rstr.push_back (curch);
toksrc_col++;
curp++;
continue;
}
/// accepts any correctly encoded UTF-8
else if (int l = u8_mblen ((uint8_t *)(curp), eol-curp); l>0)
{
rstr.append(curp, l);
toksrc_col += l;
curp += l;
continue;
}
/// improbable lexical error....
else
{
RPS_WARNOUT("Rps_TokenSource::lex_quoted_literal_string : lexical error at "
<< position_str());
throw std::runtime_error("lexical error");
}
} // end while
lexical_error_backslash:
RPS_WARNOUT("Rps_TokenSource::lex_quoted_literal_string : bad backslash escape at "
<< position_str());
throw std::runtime_error("lexical bad backslash escape");
} // end Rps_TokenSource::lex_quoted_literal_string
std::string
Rps_TokenSource::lex_raw_literal_string(Rps_CallFrame*callframe)
{
std::string result;
#warning some code from rps_lex_raw_literal_string file repl_rps.cc lines 1050-1115 should go here
RPS_ASSERT(callframe && callframe->is_good_call_frame());
RPS_ASSERT(rps_is_main_thread());
const char* curp = curcptr();
size_t linelen = toksrc_linebuf.size();
/// For C++, raw literal strings are multi-line, and explained in
/// en.cppreference.com/w/cpp/language/string_literal ... For
/// example R"delim(raw characters \)delim" In RefPerSys, we
/// restrict the <delim> to contain only letters, up to 15 of
/// them...
char delim[16];
memset (delim, 0, sizeof(delim));
int pos= -1;
int startlineno= toksrc_line;
int startcolno= toksrc_col;
std::string locname = toksrc_name;
if (sscanf(curp, "R\"%15[A-Za-z](%n", delim, &pos) < 1
|| !isalpha(delim[0])
|| pos<=1)
/// should never happen
RPS_FATALOUT("corrupted Rps_TokenSource::lex_raw_literal_string '"
<< Rps_Cjson_String(curp) << "'"
<< std::endl
<< Rps_ShowCallFrame(callframe));
toksrc_col += pos;
RPS_ASSERT(strlen(delim)>0 && strlen(delim)<15);
char endstr[24];
memset(endstr, 0, sizeof(endstr));
snprintf(endstr, sizeof(endstr), ")%s\"", delim);
RPS_DEBUG_LOG(REPL, "lex_raw_literal_string start L" << startlineno
<< ",C" << startcolno
<< "@" << toksrc_name
<< " endstr " << endstr);
const char*endp = nullptr;
while ((curp = curcptr()) != nullptr
&& (endp=strstr(curp, endstr)) == nullptr)
{
std::string reststr{curp};
if (!get_line())
{
RPS_WARNOUT("Rps_TokenSource::lex_raw_literal_string without end of string "
<< endstr
<< " starting L" << startlineno
<< ",C" << startcolno
<< "@" << toksrc_name
<< std::endl
<< Rps_ShowCallFrame(callframe));
throw std::runtime_error(std::string{"lex_raw_literal_string failed to find "}
+ endstr);
}
result += reststr;
}; // end while curp....
if (endp)
toksrc_col += endp - curp;
RPS_DEBUG_LOG(REPL, "lex_raw_literal_string gives '"
<< Rps_Cjson_String(result)
<< "' at " << position_str());
return result;
} // end Rps_TokenSource::lex_raw_literal_string
Rps_Value
Rps_TokenSource::lex_code_chunk(Rps_CallFrame*callframe)
{
RPS_LOCALFRAME(/*descr:*/RPS_ROOT_OB(_3rXxMck40kz03RxRLM), //code_chunk∈class
/*callerframe:*/callframe,
Rps_ObjectRef obchunk;
Rps_Value namev;
Rps_Value res;
Rps_Value chunkelemv;
);
RPS_ASSERT(callframe && callframe->is_good_call_frame());
RPS_ASSERT(rps_is_main_thread());
struct Rps_ChunkData_st chkdata = {};
chkdata.chunkdata_magic = rps_chunkdata_magicnum;
chkdata.chunkdata_lineno = toksrc_line;
chkdata.chunkdata_colno = toksrc_col;
chkdata.chunkdata_name = toksrc_name;
const char* curp = curcptr();
_f.namev= name_val(&_);
RPS_ASSERT(curp != nullptr && *curp != (char)0);
char startchunk[12];
memset(startchunk, 0, sizeof(startchunk));
int pos= -1;
if (!strncmp(curp, "#{", 2))
{
pos = 2;
startchunk[0] = (char)0;
strcpy(chkdata.chunkdata_endstr, "}#");
}
else if (sscanf(curp, "#%6[a-zA-Z]{%n", startchunk, &pos)>0 && pos>0 && isalpha(startchunk[0]))
{
snprintf(chkdata.chunkdata_endstr, sizeof(chkdata.chunkdata_endstr), "}%s#", startchunk);
}
else // should never happen
RPS_FATALOUT("corrupted Rps_TokenSource::lex_code_chunk @ " << position_str()
<< " " << curp
<< std::endl);
_f.obchunk =
Rps_ObjectRef::make_object(&_,
RPS_ROOT_OB(_3rXxMck40kz03RxRLM), //code_chunk∈class
nullptr);
_f.obchunk->put_attr2(RPS_ROOT_OB(_1B7ITSHTZWp00ektj1), //input∈symbol
_f.namev,
RPS_ROOT_OB(_5FMX3lrhiw601iqPy5), //line∈symbol
Rps_Value((intptr_t)chkdata.chunkdata_lineno, Rps_Value::Rps_IntTag{})
);
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_code_chunk @ " << position_str()
<< " start obchunk:" << _f.obchunk
<< " endstr:'" << chkdata.chunkdata_endstr << "'");
auto paylvec = _f.obchunk->put_new_plain_payload<Rps_PayloadVectVal>();
RPS_ASSERT(paylvec);
int oldline = -1;
int oldcol = -1;
toksrc_col += strlen(chkdata.chunkdata_endstr);
chkdata.chunkdata_colno += strlen(chkdata.chunkdata_endstr);
do
{
oldline = toksrc_line;
oldcol = toksrc_col;
_f.chunkelemv = lex_chunk_element(&_, _f.obchunk, &chkdata);
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_code_chunk @ " << name()
<< ":L" << toksrc_line << ",C" << toksrc_col
<< std::endl
<< " obchunk=" << _f.obchunk
<< ", chunkelemv=" << _f.chunkelemv);
if (_f.chunkelemv)
paylvec->push_back(_f.chunkelemv);
/// for $. chunkelemv is null, but position changed...
///
/// possibly related:
/// https://framalistes.org/sympa/arc/refpersys-forum/2020-12/msg00036.html
}
while (_f.chunkelemv || toksrc_col>oldcol || toksrc_line>oldline);
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_code_chunk "
<< " :-◑> obchunk=" << _f.obchunk << " @!" << position_str());
return _f.obchunk;
} // end of Rps_TokenSource::lex_code_chunk
Rps_Value
Rps_TokenSource::lex_chunk_element(Rps_CallFrame*callframe, Rps_ObjectRef obchkarg, Rps_ChunkData_st*chkdata)
{
RPS_ASSERT(callframe && callframe->is_good_call_frame());
RPS_ASSERT(rps_is_main_thread());
RPS_ASSERT(chkdata && chkdata->chunkdata_magic == rps_chunkdata_magicnum);
RPS_LOCALFRAME(/*descr:*/RPS_ROOT_OB(_3rXxMck40kz03RxRLM), //code_chunk∈class
/*callerframe:*/callframe,
Rps_Value res;
Rps_ObjectRef obchunk;
Rps_ObjectRef namedob;
);
_f.obchunk = obchkarg;
RPS_DEBUG_LOG(LOW_REPL, "Rps_TokenSource::lex_chunk_element chunkdata_colno=" << chkdata->chunkdata_colno
<< " curpos:" << position_str()
<< " linebuf:'" << toksrc_linebuf << "' of size:" << toksrc_linebuf.size());
RPS_ASSERT(chkdata->chunkdata_colno>=0
&& chkdata->chunkdata_colno <= (int)toksrc_linebuf.size());
const char*pc = toksrc_linebuf.c_str() + chkdata->chunkdata_colno;
const char*eol = toksrc_linebuf.c_str() + toksrc_linebuf.size();
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_chunk_element pc='" << Rps_Cjson_String(pc) << "'"
<< " @" << position_str(chkdata->chunkdata_colno));
if (!pc || pc[0] == (char)0 || pc == eol)
{
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_chunk_element end-of-line");
toksrc_col = toksrc_linebuf.size();
return nullptr;
}
// name-like chunk element
if (isalpha(*pc))
{
/// For C name-like things, we return the object naming them or else a string
int startnamecol = chkdata->chunkdata_colno;
const char*startname = pc;
const char*endname = pc;
const char*eol = toksrc_linebuf.c_str() + toksrc_linebuf.size();
while ((isalnum(*endname) || *endname=='_') && endname<eol)
endname++;
std::string curname(startname, endname - startname);
_f.namedob = Rps_ObjectRef::find_object_or_null_by_string(&_, curname);
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_chunk_element curname='" << curname
<< "' in " << position_str(startnamecol)
<< " namedob=" << _f.namedob);
chkdata->chunkdata_colno += endname - startname;
if (_f.namedob)
_f.res = Rps_ObjectValue(_f.namedob);
else
_f.res = Rps_StringValue(curname);
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_chunk_element curname='" << curname
<< "' res=" << _f.res << " at " << position_str(startnamecol));
return _f.res;
}
// integer (base 10) chunk element
else if (isdigit(*pc) || (pc[0] == '-' && isdigit(pc[1])))
{
char* endnum = nullptr;
long long ll = strtoll(pc, &endnum, 10);
int startcol = chkdata->chunkdata_colno ;
chkdata->chunkdata_colno += endnum - pc;
_f.res = Rps_Value((intptr_t)ll,
Rps_Value::Rps_IntTag{});
RPS_DEBUG_LOG(REPL, "Rps_TokenSource::lex_chunk_element number=" << ll
<< " res=" << _f.res << " at " << position_str(startcol));