summaryrefslogtreecommitdiff
path: root/tools/coqdoc/cpretty.mll
blob: 177058b3a9f4d4ce32e0445f63bfd0ff47b71e8e (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
(* -*- compile-command: "make -C ../.. bin/coqdoc" -*- *)
(************************************************************************)
(*  v      *   The Coq Proof Assistant  /  The Coq Development Team     *)
(* <O___,, *   INRIA - CNRS - LIX - LRI - PPS - Copyright 1999-2010     *)
(*   \VV/  **************************************************************)
(*    //   *      This file is distributed under the terms of the       *)
(*         *       GNU Lesser General Public License Version 2.1        *)
(************************************************************************)

(*i $Id: cpretty.mll 13692 2010-12-06 23:55:10Z herbelin $ i*)

(*s Utility functions for the scanners *)

{
  open Printf
  open Lexing

  (* A function that emulates Lexing.new_line (which does not exist in OCaml < 3.11.0) *)
  let new_line lexbuf =
    let pos = lexbuf.lex_curr_p in
      lexbuf.lex_curr_p <- { pos with
	pos_lnum = pos.pos_lnum + 1;
	pos_bol = pos.pos_cnum }

  (* A list function we need *)
  let rec take n ls =
    if n = 0 then [] else
      match ls with
        | [] -> []
        | (l :: ls) -> l :: (take (n-1) ls)

  (* count the number of spaces at the beginning of a string *)
  let count_spaces s =
    let n = String.length s in
    let rec count c i =
      if i == n then c,i else match s.[i] with
	| '\t' -> count (c + (8 - (c mod 8))) (i + 1)
	| ' ' -> count (c + 1) (i + 1)
	| _ -> c,i
    in
      count 0 0

  let remove_newline s =
    let n = String.length s in
    let rec count i = if i == n || s.[i] <> '\n' then i else count (i + 1) in
    let i = count 0 in
    i, String.sub s i (n - i)

  let count_dashes s =
    let c = ref 0 in
    for i = 0 to String.length s - 1 do if s.[i] = '-' then incr c done;
    !c

  let cut_head_tail_spaces s =
    let n = String.length s in
    let rec look_up i = if i == n || s.[i] <> ' ' then i else look_up (i+1) in
    let rec look_dn i = if i == -1 || s.[i] <> ' ' then i else look_dn (i-1) in
    let l = look_up 0 in
    let r = look_dn (n-1) in
    if l <= r then String.sub s l (r-l+1) else s

  let sec_title s =
    let rec count lev i =
      if s.[i] = '*' then
	count (succ lev) (succ i)
      else
	let t = String.sub s i (String.length s - i) in
	lev, cut_head_tail_spaces t
    in
    count 0 (String.index s '*')

  let strip_eol s =
    let eol = s.[String.length s - 1] = '\n' in
    (eol, if eol then String.sub s 1 (String.length s - 1) else s)


  let formatted = ref false
  let brackets = ref 0
  let comment_level = ref 0
  let in_proof = ref None
  let in_emph = ref false

  let start_emph () = in_emph := true; Output.start_emph ()
  let stop_emph () = if !in_emph then (Output.stop_emph (); in_emph := false)

  let backtrack lexbuf = lexbuf.lex_curr_pos <- lexbuf.lex_start_pos;
    lexbuf.lex_curr_p <- lexbuf.lex_start_p

  let backtrack_past_newline lexbuf =
    let buf = lexeme lexbuf in
    let splits = Str.bounded_split_delim (Str.regexp "['\n']") buf 2 in
      match splits with
        | [] -> ()
        | (_ :: []) -> ()
        | (s1 :: rest :: _) ->
            let length_skip = 1 + String.length s1 in
              lexbuf.lex_curr_pos <- lexbuf.lex_start_pos + length_skip

  let is_space = function ' ' | '\t' | '\n' | '\r' -> true | _ -> false

  (* saving/restoring the PP state *)

  type state = {
    st_gallina : bool;
    st_light : bool
  }

  let state_stack = Stack.create ()

  let save_state () =
    Stack.push { st_gallina = !Cdglobals.gallina; st_light = !Cdglobals.light } state_stack

  let restore_state () =
    let s = Stack.pop state_stack in
    Cdglobals.gallina := s.st_gallina;
    Cdglobals.light := s.st_light

  let without_ref r f x = save_state (); r := false; f x; restore_state ()

  let without_gallina = without_ref Cdglobals.gallina

  let without_light = without_ref Cdglobals.light

  let show_all f = without_gallina (without_light f)

  let begin_show () = save_state (); Cdglobals.gallina := false; Cdglobals.light := false
  let end_show () = restore_state ()

  (* Reset the globals *)

  let reset () =
    formatted := false;
    brackets := 0;
    comment_level := 0

  (* erasing of Section/End *)

  let section_re = Str.regexp "[ \t]*Section"
  let end_re = Str.regexp "[ \t]*End"
  let is_section s = Str.string_match section_re s 0
  let is_end s = Str.string_match end_re s 0

  let sections_to_close = ref 0

  let section_or_end s =
    if is_section s then begin
      incr sections_to_close; true
    end else if is_end s then begin
      if !sections_to_close > 0 then begin
	decr sections_to_close; true
      end else
	false
    end else
      true

  (* for item lists *)
  type list_compare =
      | Before
      | StartLevel of int
      | InLevel of int * bool

  (* Before : we're before any levels
     StartLevel : at the same column as the dash in a level
     InLevel : after the dash of this level, but before any deeper dashes.
               bool is true if this is the last level *)
  let find_level levels cur_indent =
    match levels with
    | [] -> Before
    | (l::ls) ->
        if cur_indent < l then Before
        else
          (* cur_indent will never be less than the head of the list *)
          let rec findind ls n =
            match ls with
            | [] -> InLevel (n,true)
            | (l :: []) -> if cur_indent = l then StartLevel n
                           else InLevel (n,true)
            | (l1 :: l2 :: ls) ->
                if cur_indent = l1 then StartLevel n
                else if cur_indent < l2 then InLevel (n,false)
                     else findind (l2 :: ls) (n+1)
          in
            findind (l::ls) 1

  type is_start_list =
    | Rule
    | List of int
    | Neither

  let check_start_list str =
    let n_dashes = count_dashes str in
    let (n_spaces,_) = count_spaces str in
      if n_dashes >= 4 && not !Cdglobals.plain_comments then
        Rule
      else
        if n_dashes = 1 && not !Cdglobals.plain_comments then
          List n_spaces
        else
          Neither

   (* examine a string for subtitleness *)
  let subtitle m s =
    match Str.split_delim (Str.regexp ":") s with
    | [] -> false
    | (name::_) ->
        if (cut_head_tail_spaces name) = m then
          true
        else
          false


  (* tokens pretty-print *)

  let token_buffer = Buffer.create 1024

  let token_re =
    Str.regexp "[ \t]*(\\*\\*[ \t]+printing[ \t]+\\([^ \t]+\\)"
  let printing_token_re =
    Str.regexp
      "[ \t]*\\(\\(%\\([^%]*\\)%\\)\\|\\(\\$[^$]*\\$\\)\\)?[ \t]*\\(#\\(\\(&#\\|[^#]\\)*\\)#\\)?"

  let add_printing_token toks pps =
    try
      if Str.string_match token_re toks 0 then
	let tok = Str.matched_group 1 toks in
	if Str.string_match printing_token_re pps 0 then
	  let pp =
	    (try Some (Str.matched_group 3 pps) with _ ->
             try Some (Str.matched_group 4 pps) with _ -> None),
	    (try Some (Str.matched_group 6 pps) with _ -> None)
	  in
	  Output.add_printing_token tok pp
    with _ ->
      ()

  let remove_token_re =
    Str.regexp
      "[ \t]*(\\*\\*[ \t]+remove[ \t]+printing[ \t]+\\([^ \t]+\\)[ \t]*\\*)"

  let remove_printing_token toks =
    try
      if Str.string_match remove_token_re toks 0 then
	let tok = Str.matched_group 1 toks in
	Output.remove_printing_token tok
    with _ ->
      ()

  let extract_ident_re = Str.regexp "([ \t]*\\([^ \t]+\\)[ \t]*:="
  let extract_ident s =
    assert (String.length s >= 3);
    if Str.string_match extract_ident_re s 0 then
      Str.matched_group 1 s
    else
      String.sub s 1 (String.length s - 3)

  let output_indented_keyword s lexbuf =
    let nbsp,isp = count_spaces s in
    Output.indentation nbsp;
    let s = String.sub s isp (String.length s - isp) in
    Output.ident s (lexeme_start lexbuf + isp)

}

(*s Regular expressions *)

let space = [' ' '\t']
let space_nl = [' ' '\t' '\n' '\r']
let nl = "\r\n" | '\n'

let firstchar =
  ['A'-'Z' 'a'-'z' '_'] |
  (* superscript 1 *)
  '\194' '\185' |
  (* utf-8 latin 1 supplement *)
  '\195' ['\128'-'\150'] |
  '\195' ['\152'-'\182'] |
  '\195' ['\184'-'\191'] |
  (* utf-8 letterlike symbols *)
  (* '\206' ([ '\145' - '\183'] | '\187') | *)
  (* '\xCF' [ '\x00' - '\xCE' ] |  *)
  (* utf-8 letterlike symbols *)
  '\206' ('\160' | [ '\177'-'\183'] | '\187') |
  '\226' ('\130' [ '\128'-'\137' ] (* subscripts *)
    | '\129' [ '\176'-'\187' ] (* superscripts *)
    | '\132' ['\128'-'\191'] | '\133' ['\128'-'\143'])
let identchar =
  firstchar | ['\'' '0'-'9' '@' ]
let id = firstchar identchar*
let pfx_id = (id '.')*
let identifier =
  id | pfx_id id

(* This misses unicode stuff, and it adds "[" and "]".  It's only an
   approximation of idents - used for detecting whether an underscore
   is part of an identifier or meant to indicate emphasis *)
let nonidentchar = [^ 'A'-'Z' 'a'-'z' '_' '[' ']' '\'' '0'-'9' '@' ]

let printing_token = [^ ' ' '\t']*

let thm_token =
  "Theorem"
  | "Lemma"
  | "Fact"
  | "Remark"
  | "Corollary"
  | "Proposition"
  | "Property"
  | "Goal"

let prf_token =
  "Next" space+ "Obligation"
  | "Proof" (space* "." | space+ "with")

let def_token =
  "Definition"
  | "Let"
  | "Class"
  | "SubClass"
  | "Example"
  | "Fixpoint"
  | "Boxed"
  | "CoFixpoint"
  | "Record"
  | "Structure"
  | "Scheme"
  | "Inductive"
  | "CoInductive"
  | "Equations"
  | "Instance"
  | "Declare" space+ "Instance"
  | "Global" space+ "Instance"

let decl_token =
  "Hypothesis"
  | "Hypotheses"
  | "Parameter"
  | "Axiom" 's'?
  | "Conjecture"

let gallina_ext =
  "Module"
  | "Include" space+ "Type"
  | "Include"
  | "Declare" space+ "Module"
  | "Transparent"
  | "Opaque"
  | "Canonical"
  | "Coercion"
  | "Identity"
  | "Implicit"
  | "Tactic" space+ "Notation"
  | "Section"
  | "Context"
  | "Variable" 's'?
  | ("Hypothesis" | "Hypotheses")
  | "End"

let notation_kw =
    "Notation"
  | "Infix"
  | "Reserved" space+ "Notation"

let commands =
  "Pwd"
  | "Cd"
  | "Drop"
  | "ProtectedLoop"
  | "Quit"
  | "Load"
  | "Add"
  | "Remove" space+ "Loadpath"
  | "Print"
  | "Inspect"
  | "About"
  | "Search"
  | "Eval"
  | "Reset"
  | "Check"
  | "Type"

  | "Section"
  | "Chapter"
  | "Variable" 's'?
  | ("Hypothesis" | "Hypotheses")
  | "End"

let end_kw = "Qed" | "Defined" | "Save" | "Admitted" | "Abort"

let extraction =
  "Extraction"
  | "Recursive" space+ "Extraction"
  | "Extract"

let gallina_kw = thm_token | def_token | decl_token | gallina_ext | commands | extraction

let prog_kw =
  "Program" space+ gallina_kw
  | "Obligation"
  | "Obligations"
  | "Solve"

let gallina_kw_to_hide =
    "Implicit" space+ "Arguments"
  | "Ltac"
  | "Require"
  | "Import"
  | "Export"
  | "Load"
  | "Hint"
  | "Open"
  | "Close"
  | "Delimit"
  | "Transparent"
  | "Opaque"
  | ("Declare" space+ ("Morphism" | "Step") )
  | ("Set" | "Unset") space+ "Printing" space+ "Coercions"
  | "Declare" space+ ("Left" | "Right") space+ "Step"


let section = "*" | "**" | "***" | "****"

let item_space = "    "

let begin_hide = "(*" space* "begin" space+ "hide" space* "*)" space* nl
let end_hide = "(*" space* "end" space+ "hide" space* "*)" space* nl
let begin_show = "(*" space* "begin" space+ "show" space* "*)" space* nl
let end_show = "(*" space* "end" space+ "show" space* "*)" space* nl
(*
let begin_verb = "(*" space* "begin" space+ "verb" space* "*)"
let end_verb = "(*" space* "end" space+ "verb" space* "*)"
*)

(*s Scanning Coq, at beginning of line *)

rule coq_bol = parse
  | space* nl+
      { if not (!in_proof <> None && (!Cdglobals.gallina || !Cdglobals.light))
        then Output.empty_line_of_code ();
        coq_bol lexbuf }
  | space* "(**" space_nl
      { Output.end_coq (); Output.start_doc ();
	let eol = doc_bol lexbuf in
	  Output.end_doc (); Output.start_coq ();
	  if eol then coq_bol lexbuf else coq lexbuf }
  | space* "Comments" space_nl
      { Output.end_coq (); Output.start_doc (); comments lexbuf; Output.end_doc ();
	Output.start_coq (); coq lexbuf }
  | space* begin_hide
      { skip_hide lexbuf; coq_bol lexbuf }
  | space* begin_show
      { begin_show (); coq_bol lexbuf }
  | space* end_show
      { end_show (); coq_bol lexbuf }
  | space* ("Local"|"Global")
      {
	in_proof := None;
	let s = lexeme lexbuf in
	output_indented_keyword s lexbuf;
	coq_bol lexbuf }
  | space* gallina_kw_to_hide
      { let s = lexeme lexbuf in
	  if !Cdglobals.light && section_or_end s then
	    let eol = skip_to_dot lexbuf in
	      if eol then (coq_bol lexbuf) else coq lexbuf
	  else
	    begin
	      output_indented_keyword s lexbuf;
	      let eol = body lexbuf in
	      if eol then coq_bol lexbuf else coq lexbuf
	    end }
  | space* thm_token
      { let s = lexeme lexbuf in
        output_indented_keyword s lexbuf;
        let eol = body lexbuf in
	in_proof := Some eol;
	if eol then coq_bol lexbuf else coq lexbuf }
  | space* prf_token
      { in_proof := Some true;
	let eol =
	  if not !Cdglobals.gallina then
	    begin backtrack lexbuf; body_bol lexbuf end
	  else
	    let s = lexeme lexbuf in
	      if s.[String.length s - 1] = '.' then false
	      else skip_to_dot lexbuf
	in if eol then coq_bol lexbuf else coq lexbuf }
  | space* end_kw {
      let eol =
	if not (!in_proof <> None && !Cdglobals.gallina) then
	  begin backtrack lexbuf; body_bol lexbuf end
	else skip_to_dot lexbuf
      in
	in_proof := None;
	if eol then coq_bol lexbuf else coq lexbuf }
  | space* gallina_kw
      {
	in_proof := None;
	let s = lexeme lexbuf in
	output_indented_keyword s lexbuf;
	let eol= body lexbuf in
	if eol then coq_bol lexbuf else coq lexbuf }
  | space* prog_kw
      {
	in_proof := None;
	let s = lexeme lexbuf in
	output_indented_keyword s lexbuf;
	let eol= body lexbuf in
	if eol then coq_bol lexbuf else coq lexbuf }
  | space* notation_kw space*
      {	let s = lexeme lexbuf in
	output_indented_keyword s lexbuf;
	let eol= start_notation_string lexbuf in
	if eol then coq_bol lexbuf else coq lexbuf }

  | space* "(**" space+ "printing" space+ printing_token space+
      { let tok = lexeme lexbuf in
	let s = printing_token_body lexbuf in
	  add_printing_token tok s;
	  coq_bol lexbuf }
  | space* "(**" space+ "printing" space+
      { eprintf "warning: bad 'printing' command at character %d\n"
	  (lexeme_start lexbuf); flush stderr;
	comment_level := 1;
	ignore (comment lexbuf);
	coq_bol lexbuf }
  | space* "(**" space+ "remove" space+ "printing" space+
      printing_token space* "*)"
      { remove_printing_token (lexeme lexbuf);
	coq_bol lexbuf }
  | space* "(**" space+ "remove" space+ "printing" space+
      { eprintf "warning: bad 'remove printing' command at character %d\n"
	  (lexeme_start lexbuf); flush stderr;
	comment_level := 1;
	ignore (comment lexbuf);
	coq_bol lexbuf }
  | space* "(*"
      { comment_level := 1;
	if !Cdglobals.parse_comments then begin
	  let s = lexeme lexbuf in
	  let nbsp,isp = count_spaces s in
	    Output.indentation nbsp;
	    Output.start_comment ();
	end;
	let eol = comment lexbuf in
	  if eol then coq_bol lexbuf else coq lexbuf }
  | eof
      { () }
  | _
      { let eol =
	  if not !Cdglobals.gallina then
	    begin backtrack lexbuf; body_bol lexbuf end
	  else
	    skip_to_dot lexbuf
	in
	  if eol then coq_bol lexbuf else coq lexbuf }

(*s Scanning Coq elsewhere *)

and coq = parse
  | nl
      { if not (!in_proof <> None && !Cdglobals.gallina) then Output.line_break(); coq_bol lexbuf }
  | "(**" space_nl
      { Output.end_coq (); Output.start_doc ();
	let eol = doc_bol lexbuf in
	  Output.end_doc (); Output.start_coq ();
	  if eol then coq_bol lexbuf else coq lexbuf }
  | "(*"
      { comment_level := 1;
	if !Cdglobals.parse_comments then begin
	  let s = lexeme lexbuf in
	  let nbsp,isp = count_spaces s in
	    Output.indentation nbsp;
	    Output.start_comment ();
	end;
	let eol = comment lexbuf in
	  if eol then coq_bol lexbuf
          else coq lexbuf
      }
  | nl+ space* "]]"
      { if not !formatted then
	begin
	  (* Isn't this an anomaly *)
	  let s = lexeme lexbuf in
	  let nlsp,s = remove_newline s in
	  let nbsp,isp = count_spaces s in
	  Output.indentation nbsp;
	  let loc = lexeme_start lexbuf + isp + nlsp in
	  Output.sublexer ']' loc;
	  Output.sublexer ']' (loc+1);
	  coq lexbuf
	end }
  | eof
      { () }
  | gallina_kw_to_hide
      { let s = lexeme lexbuf in
	  if !Cdglobals.light && section_or_end s then
	    begin
	      let eol = skip_to_dot lexbuf in
		if eol then coq_bol lexbuf else coq lexbuf
	    end
	  else
	    begin
	      Output.ident s (lexeme_start lexbuf);
	      let eol=body lexbuf in
		if eol then coq_bol lexbuf else coq lexbuf
	    end }
  | prf_token
      { let eol =
	  if not !Cdglobals.gallina then
	    begin backtrack lexbuf; body_bol lexbuf end
	  else
	    let s = lexeme lexbuf in
	    let eol =
	      if s.[String.length s - 1] = '.' then false
	      else skip_to_dot lexbuf
	    in
	      eol
	in if eol then coq_bol lexbuf else coq lexbuf }
  | end_kw {
      let eol =
	if not !Cdglobals.gallina then
	  begin backtrack lexbuf; body lexbuf end
	else
	  let eol = skip_to_dot lexbuf in
	    if !in_proof <> Some true && eol then
	      Output.line_break ();
	    eol
      in
	in_proof := None;
	if eol then coq_bol lexbuf else coq lexbuf }
  | gallina_kw
      { let s = lexeme lexbuf in
	  Output.ident s (lexeme_start lexbuf);
	let eol = body lexbuf in
	  if eol then coq_bol lexbuf else coq lexbuf }
  | notation_kw space*
      { let s = lexeme lexbuf in
	Output.ident s (lexeme_start lexbuf);
	let eol= start_notation_string lexbuf in
	if eol then coq_bol lexbuf else coq lexbuf }
  | prog_kw
      { let s = lexeme lexbuf in
	  Output.ident s (lexeme_start lexbuf);
	let eol = body lexbuf in
	  if eol then coq_bol lexbuf else coq lexbuf }
  | space+ { Output.char ' '; coq lexbuf }
  | eof
      { () }
  | _ {	let eol =
	  if not !Cdglobals.gallina then
	    begin backtrack lexbuf; body lexbuf end
	  else
	    skip_to_dot lexbuf
	in
	  if eol then coq_bol lexbuf else coq lexbuf}

(*s Scanning documentation, at beginning of line *)

and doc_bol = parse
  | space* nl+
      { Output.paragraph (); doc_bol lexbuf }
  | space* section space+ ([^'\n' '*'] | '*'+ [^'\n' ')' '*'])* ('*'+ '\n')?
      { let eol, lex = strip_eol (lexeme lexbuf) in
        let lev, s = sec_title lex in
          if (!Cdglobals.lib_subtitles) &&
             (subtitle (Output.get_module false) s) then
            ()
          else
            Output.section lev (fun () -> ignore (doc None (from_string s)));
	    if eol then doc_bol lexbuf else doc None lexbuf }
  | space* nl space* '-'+
      { (* adding this production instead of just letting the paragraph
           production and the begin list production fire eliminates
           extra vertical whitespace. *)
        let buf' = lexeme lexbuf in
        let buf =
          let bufs = Str.split_delim (Str.regexp "['\n']") buf' in
            match bufs with
              | (_ :: s :: []) -> s
              | (_ :: _ :: s :: _) -> s
              | _ -> eprintf "Internal error bad_split1 - please report\n";
                     exit 1
        in
          match check_start_list buf with
          | Neither -> backtrack_past_newline lexbuf; doc None lexbuf
          | List n -> Output.item 1; doc (Some [n]) lexbuf
          | Rule -> Output.rule (); doc None lexbuf
      }
  | space* '-'+
      { let buf = lexeme lexbuf in
          match check_start_list buf with
          | Neither -> backtrack lexbuf; doc None lexbuf
          | List n -> Output.item 1; doc (Some [n]) lexbuf
          | Rule -> Output.rule (); doc None lexbuf
      }
  | "<<" space*
      { Output.start_verbatim (); verbatim lexbuf; doc_bol lexbuf }
  | eof
      { true }
  | '_'
      { if !Cdglobals.plain_comments then Output.char '_' else start_emph ();
        doc None lexbuf }
  | _
      { backtrack lexbuf; doc None lexbuf }

(*s Scanning lists - using whitespace *)
and doc_list_bol indents = parse
  | space* '-'
      { let (n_spaces,_) = count_spaces (lexeme lexbuf) in
        match find_level indents n_spaces with
        | Before -> backtrack lexbuf; doc_bol lexbuf
        | StartLevel n -> Output.item n; doc (Some (take n indents)) lexbuf
        | InLevel (n,true) ->
            let items = List.length indents in
              Output.item (items+1);
              doc (Some (List.append indents [n_spaces])) lexbuf
        | InLevel (_,false) ->
            backtrack lexbuf; doc_bol lexbuf
      }
  | "<<" space*
      { Output.start_verbatim ();
        verbatim lexbuf;
        doc_list_bol indents lexbuf }
  | "[[" nl
      { formatted := true;
        Output.start_inline_coq_block ();
        ignore(body_bol lexbuf);
        Output.end_inline_coq_block ();
        formatted := false;
        doc_list_bol indents lexbuf }
  | space* nl space* '-'
      { (* Like in the doc_bol production, these two productions
           exist only to deal properly with whitespace *)
        Output.paragraph ();
        backtrack_past_newline lexbuf;
        doc_list_bol indents lexbuf }
  | space* nl space* _
      { let buf' = lexeme lexbuf in
        let buf =
          let bufs = Str.split_delim (Str.regexp "['\n']") buf' in
            match bufs with
              | (_ :: s :: []) -> s
              | (_ :: _ :: s :: _) -> s
              | _ -> eprintf "Internal error bad_split2 - please report\n";
                     exit 1
        in
        let (n_spaces,_) = count_spaces buf in
        match find_level indents n_spaces with
        | InLevel _ ->
            Output.paragraph ();
            backtrack_past_newline lexbuf;
            doc_list_bol indents lexbuf
        | StartLevel n ->
            if n = 1 then
              begin
                Output.stop_item ();
                backtrack_past_newline lexbuf;
                doc_bol lexbuf
              end
            else
              begin
                Output.paragraph ();
                backtrack_past_newline lexbuf;
                doc_list_bol indents lexbuf
              end
        | Before -> Output.stop_item ();
                    backtrack_past_newline lexbuf;
                    doc_bol lexbuf

      }
  | space* _
      { let (n_spaces,_) = count_spaces (lexeme lexbuf) in
        match find_level indents n_spaces with
        | Before -> Output.stop_item (); backtrack lexbuf;
                    doc_bol lexbuf
        | StartLevel n ->
            Output.reach_item_level (n-1);
            backtrack lexbuf;
            doc (Some (take (n-1) indents)) lexbuf
        | InLevel (n,_) ->
            Output.reach_item_level n;
            backtrack lexbuf;
            doc (Some (take n indents)) lexbuf
      }

(*s Scanning documentation elsewhere *)
and doc indents = parse
  | nl
      { Output.char '\n';
        match indents with
        | Some ls -> doc_list_bol ls lexbuf
        | None -> doc_bol lexbuf }
  | "[[" nl
      { if !Cdglobals.plain_comments
        then (Output.char '['; Output.char '['; doc indents lexbuf)
        else (formatted := true;
              Output.start_inline_coq_block ();
	      let eol = body_bol lexbuf in
	        Output.end_inline_coq_block (); formatted := false;
	        if eol then
		  match indents with
		  | Some ls -> doc_list_bol ls lexbuf
		  | None -> doc_bol lexbuf
		else doc indents lexbuf)}
  | "[]"
      { Output.proofbox (); doc indents lexbuf }
  | "["
      { if !Cdglobals.plain_comments then Output.char '['
        else (brackets := 1;  Output.start_inline_coq (); escaped_coq lexbuf;
              Output.end_inline_coq ()); doc indents lexbuf }
  | "(*"
      { backtrack lexbuf ;
        let bol_parse = match indents with
                        | Some is -> doc_list_bol is
                        | None   -> doc_bol
        in
        let eol = comment lexbuf in
          if eol then bol_parse lexbuf else doc indents lexbuf
      }
  | '*'* "*)" space* nl
      { true }
  | '*'* "*)"
      { false }
  | "$"
      { if !Cdglobals.plain_comments then Output.char '$'
        else (Output.start_latex_math (); escaped_math_latex lexbuf);
        doc indents lexbuf }
  | "$$"
      { if !Cdglobals.plain_comments then Output.char '$';
        Output.char '$'; doc indents lexbuf }
  | "%"
      { if !Cdglobals.plain_comments then Output.char '%'
        else escaped_latex lexbuf; doc indents lexbuf }
  | "%%"
      { if !Cdglobals.plain_comments then Output.char '%';
        Output.char '%'; doc indents lexbuf }
  | "#"
      { if !Cdglobals.plain_comments then Output.char '#'
        else escaped_html lexbuf; doc indents lexbuf }
  | "##"
      { if !Cdglobals.plain_comments then Output.char '#';
        Output.char '#'; doc indents lexbuf }
  | nonidentchar '_' nonidentchar
      { List.iter (fun x -> Output.char (lexeme_char lexbuf x)) [0;1;2];
        doc indents lexbuf}
  | nonidentchar '_'
      { Output.char (lexeme_char lexbuf 0);
        if !Cdglobals.plain_comments then Output.char '_' else  start_emph () ;
        doc indents lexbuf }
  | '_' nonidentchar
      { if !Cdglobals.plain_comments then Output.char '_' else stop_emph () ;
        Output.char (lexeme_char lexbuf 1);
        doc indents lexbuf }
  | eof
      { false }
  | _
      { Output.char (lexeme_char lexbuf 0); doc indents lexbuf }

(*s Various escapings *)

and escaped_math_latex = parse
  | "$" { Output.stop_latex_math () }
  | eof { Output.stop_latex_math () }
  | _   { Output.latex_char (lexeme_char lexbuf 0); escaped_math_latex lexbuf }

and escaped_latex = parse
  | "%" { () }
  | eof { () }
  | _   { Output.latex_char (lexeme_char lexbuf 0); escaped_latex lexbuf }

and escaped_html = parse
  | "#" { () }
  | "&#"
        { Output.html_char '&'; Output.html_char '#'; escaped_html lexbuf }
  | "##"
        { Output.html_char '#'; escaped_html lexbuf }
  | eof { () }
  | _   { Output.html_char (lexeme_char lexbuf 0); escaped_html lexbuf }

and verbatim = parse
  | nl ">>" space* nl { Output.verbatim_char '\n'; Output.stop_verbatim () }
  | nl ">>" { Output.verbatim_char '\n'; Output.stop_verbatim () }
  | eof { Output.stop_verbatim () }
  | _ { Output.verbatim_char (lexeme_char lexbuf 0); verbatim lexbuf }

(*s Coq, inside quotations *)

and escaped_coq = parse
  | "]"
      { decr brackets;
	if !brackets > 0 then
	  (Output.sublexer ']' (lexeme_start lexbuf); escaped_coq lexbuf)
	else Tokens.flush_sublexer () }
  | "["
      { incr brackets;
        Output.sublexer '[' (lexeme_start lexbuf); escaped_coq lexbuf }
  | "(*"
      { Tokens.flush_sublexer (); comment_level := 1;
        ignore (comment lexbuf); escaped_coq lexbuf }
  | "*)"
      { (* likely to be a syntax error: we escape *) backtrack lexbuf }
  | eof
      { Tokens.flush_sublexer () }
  | (identifier '.')* identifier
      { Output.ident (lexeme lexbuf) (lexeme_start lexbuf); escaped_coq lexbuf }
  | space
      { Tokens.flush_sublexer(); Output.char (lexeme_char lexbuf 0);
        escaped_coq lexbuf }
  | _
      { Output.sublexer (lexeme_char lexbuf 0) (lexeme_start lexbuf);
        escaped_coq lexbuf }

(*s Coq "Comments" command. *)

and comments = parse
  | space_nl+
      { Output.char ' '; comments lexbuf }
  | '"' [^ '"']* '"'
      { let s = lexeme lexbuf in
	let s = String.sub s 1 (String.length s - 2) in
	ignore (doc None (from_string s)); comments lexbuf }
  | ([^ '.' '"'] | '.' [^ ' ' '\t' '\n'])+
      { escaped_coq (from_string (lexeme lexbuf)); comments lexbuf }
  | "." (space_nl | eof)
      { () }
  | eof
      { () }
  | _
      { Output.char (lexeme_char lexbuf 0); comments lexbuf }

(*s Skip comments *)

and comment = parse
  | "(*" { incr comment_level;
	   if !Cdglobals.parse_comments then Output.start_comment ();
	   comment lexbuf }
  | "*)" space* nl {
      if !Cdglobals.parse_comments then
	(Output.end_comment (); Output.line_break ());
      decr comment_level; if !comment_level > 0 then comment lexbuf else true }
  | "*)" {
      if !Cdglobals.parse_comments then (Output.end_comment ());
      decr comment_level; if !comment_level > 0 then comment lexbuf else false }
  | "[" {
      if !Cdglobals.parse_comments then
	if !Cdglobals.plain_comments then Output.char '['
        else (brackets := 1; Output.start_inline_coq ();
              escaped_coq lexbuf; Output.end_inline_coq ());
      comment lexbuf }
  | "[[" nl {
      if !Cdglobals.parse_comments then
        if !Cdglobals.plain_comments then (Output.char '['; Output.char '[')
        else (formatted := true;
              Output.start_inline_coq_block ();
              let _ = body_bol lexbuf in
                Output.end_inline_coq_block (); formatted := false);
      comment lexbuf}
  | "$"
      { if !Cdglobals.parse_comments then
          if !Cdglobals.plain_comments then Output.char '$'
          else (Output.start_latex_math (); escaped_math_latex lexbuf);
        comment lexbuf }
  | "$$"
      { if !Cdglobals.parse_comments
        then
          (if !Cdglobals.plain_comments then Output.char '$'; Output.char '$');
        doc None lexbuf }
  | "%"
      { if !Cdglobals.parse_comments
          then
            if !Cdglobals.plain_comments then Output.char '%'
            else escaped_latex lexbuf; comment lexbuf }
  | "%%"
      { if !Cdglobals.parse_comments
        then
          (if !Cdglobals.plain_comments then Output.char '%'; Output.char '%');
        comment lexbuf }
  | "#"
      { if !Cdglobals.parse_comments
        then
          if !Cdglobals.plain_comments then Output.char '$'
          else escaped_html lexbuf; comment lexbuf }
  | "##"
      { if !Cdglobals.parse_comments
        then
          (if !Cdglobals.plain_comments then Output.char '#'; Output.char '#');
        comment lexbuf }
  | eof  { false }
  | space+ { if !Cdglobals.parse_comments
             then Output.indentation (fst (count_spaces (lexeme lexbuf)));
             comment lexbuf }
  | nl   { if !Cdglobals.parse_comments
           then Output.line_break (); comment lexbuf }
  | _    { if !Cdglobals.parse_comments then Output.char (lexeme_char lexbuf 0);
           comment lexbuf }

and skip_to_dot = parse
  | '.' space* nl { true }
  | eof | '.' space+ { false }
  | "(*" { comment_level := 1; ignore (comment lexbuf); skip_to_dot lexbuf }
  | _ { skip_to_dot lexbuf }

and body_bol = parse
  | space+
      { Output.indentation (fst (count_spaces (lexeme lexbuf))); body lexbuf }
  | _ { backtrack lexbuf; Output.indentation 0; body lexbuf }

and body = parse
  | nl {Tokens.flush_sublexer(); Output.line_break(); new_line lexbuf; body_bol lexbuf}
  | nl+ space* "]]" space* nl
      { Tokens.flush_sublexer();
        if not !formatted then
          begin
            let s = lexeme lexbuf in
            let nlsp,s = remove_newline s in
            let _,isp = count_spaces s in
            let loc = lexeme_start lexbuf + nlsp + isp in
            Output.sublexer ']' loc;
            Output.sublexer ']' (loc+1);
            Tokens.flush_sublexer();
            body lexbuf
          end
        else
          begin
            Output.paragraph ();
            true
          end }
  | "]]" space* nl
      { Tokens.flush_sublexer();
        if not !formatted then
          begin
	    let loc = lexeme_start lexbuf in
	    Output.sublexer ']' loc;
	    Output.sublexer ']' (loc+1);
	    Tokens.flush_sublexer();
	    Output.line_break();
            body lexbuf
          end
        else
          begin
            Output.paragraph ();
            true
          end }
  | eof { Tokens.flush_sublexer(); false }
  | '.' space* nl | '.' space* eof
	{ Tokens.flush_sublexer(); Output.char '.'; Output.line_break();
	  if not !formatted then true else body_bol lexbuf }
  | '.' space* nl "]]" space* nl
	{ Tokens.flush_sublexer(); Output.char '.';
        if not !formatted then
          begin
            eprintf "Error: stray ]] at %d\n"  (lexeme_start lexbuf);
            flush stderr;
            exit 1
          end
	  else
          begin
            Output.paragraph ();
            true
          end
      }
  | '.' space+
        { Tokens.flush_sublexer(); Output.char '.'; Output.char ' ';
	  if not !formatted then false else body lexbuf }
  | "(**" space_nl
      { Tokens.flush_sublexer(); Output.end_coq (); Output.start_doc ();
	let eol = doc_bol lexbuf in
	  Output.end_doc (); Output.start_coq ();
	  if eol then body_bol lexbuf else body lexbuf }
  | "(*" { Tokens.flush_sublexer(); comment_level := 1;
	   if !Cdglobals.parse_comments then Output.start_comment ();
	   let eol = comment lexbuf in
	     if eol
	     then begin if not !Cdglobals.parse_comments then Output.line_break(); body_bol lexbuf end
	     else body lexbuf }
  | "where" space*
      { Tokens.flush_sublexer();
        Output.ident (lexeme lexbuf) (lexeme_start lexbuf);
	start_notation_string lexbuf }
  | identifier
      { Tokens.flush_sublexer();
        Output.ident (lexeme lexbuf) (lexeme_start lexbuf);
	body lexbuf }
  | ".."
      { Tokens.flush_sublexer(); Output.char '.'; Output.char '.';
        body lexbuf }
  | '"'
      { Tokens.flush_sublexer(); Output.char '"';
        string lexbuf;
        body lexbuf }
  | space
      { Tokens.flush_sublexer(); Output.char (lexeme_char lexbuf 0);
        body lexbuf }

  | _ { let c = lexeme_char lexbuf 0 in
	Output.sublexer c (lexeme_start lexbuf);
        body lexbuf }

and start_notation_string = parse
  | '"' (* a true notation *)
      { Output.sublexer '"' (lexeme_start lexbuf);
        notation_string lexbuf;
	body lexbuf }
  | _ (* an abbreviation *)
      { backtrack lexbuf; body lexbuf }

and notation_string = parse
  | "\"\""
      { Output.char '"'; Output.char '"'; (* Unlikely! *)
        notation_string lexbuf }
  | '"'
      { Tokens.flush_sublexer(); Output.char '"' }
  | _ { let c = lexeme_char lexbuf 0 in
        Output.sublexer c (lexeme_start lexbuf);
        notation_string lexbuf }

and string = parse
  | "\"\"" { Output.char '"'; Output.char '"'; string lexbuf }
  | '"'    { Output.char '"' }
  | _      { let c = lexeme_char lexbuf 0 in Output.char c; string lexbuf }

and skip_hide = parse
  | eof | end_hide { () }
  | _ { skip_hide lexbuf }

(*s Reading token pretty-print *)

and printing_token_body = parse
  | "*)" nl? | eof
	{ let s = Buffer.contents token_buffer in
	  Buffer.clear token_buffer;
	  s }
  | _   { Buffer.add_string token_buffer (lexeme lexbuf);
	  printing_token_body lexbuf }

(*s A small scanner to support the chapter subtitle feature *)
and st_start m = parse
  | "(*" "*"+ space+ "*" space+
      { st_modname m lexbuf }
  | _
      { None }

and st_modname m = parse
  | identifier space* ":" space*
      { if subtitle m (lexeme lexbuf) then
          st_subtitle lexbuf
        else
          None
      }
  | _
      { None }

and st_subtitle = parse
  | [^ '\n']* '\n'
      { let st = lexeme lexbuf in
        let i = try Str.search_forward (Str.regexp "\\**)") st 0 with
                   Not_found ->
                     (eprintf "unterminated comment at beginning of file\n";
                      exit 1)
        in
          Some (cut_head_tail_spaces (String.sub st 0 i))
      }
  | _
      { None }
(*s Applying the scanners to files *)

{
  let coq_file f m =
    reset ();
    let c = open_in f in
    let lb = from_channel c in
      (Index.current_library := m;
       Output.initialize ();
       Output.start_module ();
       Output.start_coq (); coq_bol lb; Output.end_coq ();
       close_in c)

  let detect_subtitle f m =
    let c = open_in f in
    let lb = from_channel c in
    let sub = st_start m lb in
      close_in c;
      sub
}