summaryrefslogtreecommitdiff
path: root/mod/tex/context/third/rst/rst_context.lua
blob: 7d0f2b86acef902f062fe1471a82813ab86247b8 (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
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
#!/usr/bin/env texlua
--------------------------------------------------------------------------------
--         FILE:  rst_context.lua
--        USAGE:  called by rst_parser.lua
--  DESCRIPTION:  Complement to the reStructuredText parser
--       AUTHOR:  Philipp Gesang (Phg), <phg42.2a@gmail.com>
--      CHANGED:  2013-03-26 22:46:17+0100
--------------------------------------------------------------------------------
--
--- TODO
---   Find an appropriate way to handle generic tables irrespective of the grid
---   settings. The problem is:
---   http://archive.contextgarden.net/message/20100912.112605.8a1aaf13.en.html
---   Seems we'll have to choose either the grid or split tables as default. Not
---   good.


local helpers        = helpers        or thirddata and thirddata.rst_helpers
local rst_directives = rst_directives or thirddata and thirddata.rst_directives

local utf         = unicode.utf8
local utflen      = utf.len
local utflower    = utf.lower
local utfupper    = utf.upper
local iowrite     = io.write
local tableconcat = table.concat

local stringmatch  = string.match
local stringgmatch = string.gmatch
local stringgsub   = string.gsub

local dbg_write = helpers.dbg_writef

local C,  Cb, Cc, Cg, Cmt, Cp,
      Cs, Ct, P,  R,  S,   V,  lpegmatch
      = lpeg.C,  lpeg.Cb, lpeg.Cc, lpeg.Cg, lpeg.Cmt, lpeg.Cp,
        lpeg.Cs, lpeg.Ct, lpeg.P,  lpeg.R,  lpeg.S,   lpeg.V,  lpeg.match

-- This one should ignore escaped spaces.
do
    local stripper = P{
        [1] = "stripper",
        stripper = V"space"^0 * C((V"space"^0 * (V"escaped" + V"nospace")^1)^0),
        space    = S(" \t\v\n"),
        nospace  = 1 - V"space",
        escaped  = P"\\" * V"space"
    }
    function string.strip(str)
        return lpegmatch(stripper, str) or ""
    end
end
local stringstrip  = string.strip
local stringformat = string.format

local err = function(str)
    if str then
        iowrite("\n*[rstctx] Error: " .. str .. "\n\n")
    end
end

local rst_context = thirddata.rst

rst_context.collected_adornments = {}
rst_context.last_section_level   = 0
rst_context.anonymous_targets    = 0
rst_context.anonymous_links      = {}

rst_context.collected_references = {}
rst_context.context_references   = {}
rst_context.structure_references = {}
rst_context.anonymous_set        = {}

rst_context.substitutions        = {}
rst_context.lastitemnumber       = 0  -- enumerations in RST allow arbitrary skips

rst_context.current_footnote_number   = 0
rst_context.current_symbolnote_number = 0

function rst_context.addsetups(item)
    local state = thirddata.rst.state
    state.addme[item] = state.addme[item] or true
    return 0
end

function rst_context.footnote_reference (label)
    local tf = thirddata.rst.state.footnotes
    if stringmatch(label, "^%d+$") then -- all digits
        local c = tonumber(label)
        return [[\\footnote{\\getbuffer[__footnote_number_]].. c .."]}"
    elseif label == "#" then --autonumber
        local rc = rst_context.current_footnote_number
        rc = rc + 1
        rst_context.current_footnote_number = rc
        return [[\\footnote{\\getbuffer[__footnote_number_]].. rc .."]}"
    elseif stringmatch(label, "^#.+$") then
        local thelabel = stringmatch(label, "^#(.+)$")
        return [[\\footnote{\\getbuffer[__footnote_label_]].. thelabel .."]}"
    elseif label == "*" then
        local rc = rst_context.current_symbolnote_number
        rc = rc + 1
        rst_context.current_symbolnote_number = rc
        return [[\\symbolnote{\\getbuffer[__footnote_symbol_]].. rc .."]}"
    else -- “citation reference” for now treating them like footnotes
        rst_context.addsetups("citations")
        return [[\\cite{]] .. label .. [[}]]
    end
end

do
    local w = S" \v\t\n" / "_"
    local wp = Cs((w + 1)^1)
    function rst_context.whitespace_to_underscore(str)
        return  str and lpegmatch(wp, str) or ""
    end
end

--- So we can use crefs[n][2] to refer to the place where the reference was
--- created.
local function get_context_reference (str)
    local crefs = rst_context.context_references
    local srefs = rst_context.structure_references
    srefs[str] = true
    refstring = "__target_" .. rst_context.whitespace_to_underscore(str)
    crefs[#crefs + 1] = { refstring, str }
    return refstring
end

function rst_context.emphasis (str)
    return [[{\\em ]] .. str .. [[}]]
end

function rst_context.strong_emphasis (str)
    return [[{\\sc ]] .. str .. [[}]]
end

function rst_context.literal (str)
    return [[\\type{]] .. str .. [[}]]
end

--- ROLES for interpreted text

rst_context.roles = {}
rst_context.roles.emphasis = rst_context.emphasis
rst_context.roles.strong_emphasis = rst_context.strong_emphasis
rst_context.roles.literal = rst_context.literal
rst_context.roles.bold = function(str)
    return [[{\\bold ]] .. str .. [[}]]
end
rst_context.roles.bf = rst_context.roles.bold

rst_context.roles.italic = function(str)
    return [[{\\italic ]] .. str .. [[}]]
end
rst_context.roles.it = rst_context.roles.italic

rst_context.roles.sans = function(str)
    return [[{\\ss ]] .. str .. [[}]]
end
rst_context.roles.sans_serif = rst_context.roles.sans
rst_context.roles.ss         = rst_context.roles.sans

rst_context.roles.uppercase = function(str)
    return utfupper(str)
end

rst_context.roles.lowercase = function(str)
    return utflower(str)
end

rst_context.roles.color = function(color, str)
    local p = helpers.patterns
    local definition = stringmatch(color, "^color_(.+)$")
    if stringmatch(definition, "^rgb_") then -- assume rgb
        local rgb = lpegmatch(p.rgbvalues, definition)
        definition = stringformat([[r=%s,g=%s,b=%s]], rgb[1], rgb[2], rgb[3])
    end
    return stringformat([[\\colored[%s]{%s}]], definition, str)
end

--------------------------------------------------------------------------------
--- Inofficial text roles for my private bib
--------------------------------------------------------------------------------

-- Afterthought:
-- Different citation commands are essentially typographical instructions:
-- they are concerned with the final representation of the data with respect to
-- a concrete implementation. Not the thing at all that would make reST
-- portable. But then its support for Python-style string escaping &c. ain’t at
-- all portable either. The problem is the same with XML written to be
-- processed with ConTeXt -- when processing the text directly in MkIV you’ll
-- always find yourself adding setups that allow fine-grained control of the
-- typeset output. At the same time those instructions directly contradict the
-- main reason for XML: to provide an application-independent data markup.
-- Typesetting XML (and now reST) with TeX, you will always end up writing TeX
-- code disguised in XML brackets. (Btw. the docutils reST specification has
-- the same kind of inclination to HTML -- some of its components don’t even
-- have a meaning save in HTML peculiarities.) If you strive to avoid this
-- *and* would like to have decent typesetting, you should use the
-- automatically generated TeX code as a starting point for the actual
-- typesetting job. Wish it was possible to have both -- the data in a
-- universal form and the output in the Optimal Typesetting System -- but
-- that’s a dream for now. If you really read these musings, then prove me
-- wrong if you can! Or go tell those digital publishers and their willing
-- subordinates, the authors, who think they can save a few pennys,
-- substituting the typesetter and editor by some fancy software. Keep in mind
-- that zapf.tex is not just random dummy text. </rant>

function rst_context.roles.ctsh(str) -- shorthand
    rst_context.addsetups("citator")
    return [[\\ctsh{]] .. str .. [[}]]
end

function rst_context.roles.ctas(str) -- short cite
    rst_context.addsetups("citator")
    return [[\\ctas{]] .. str .. [[}]]
end

function rst_context.roles.ctau(str) -- author only
    rst_context.addsetups("citator")
    return [[\\ctau{]] .. str .. [[}]]
end

function rst_context.roles.cttt(str) -- title only
    rst_context.addsetups("citator")
    return [[\\cttt{]] .. str .. [[}]]
end

function rst_context.roles.ctay(str) -- author year
    rst_context.addsetups("citator")
    return [[\\ctay{]] .. str .. [[}]]
end

function rst_context.roles.ctfu(str) -- full cite
    rst_context.addsetups("citator")
    return [[\\ctfu{]] .. str .. [[}]]
end

function rst_context.roles.nocite(str) -- nocite
    rst_context.addsetups("citator")
    return [[\\nocite[]] .. str .. [=[]]=]
end

--------------------------------------------------------------------------------
--- End citator roles
--------------------------------------------------------------------------------

--------------------------------------------------------------------------------
--- Experimental roles.
--------------------------------------------------------------------------------

--- Feature request by Philipp A.
function rst_context.roles.math(str)
    return [[\\mathematics{]] .. str .. [[}]]
end

--------------------------------------------------------------------------------
--- End roles
--------------------------------------------------------------------------------

function rst_context.interpreted_text (...)
    local tab = { ... }
    local role, str
    role = stringmatch(tab[1], "^:(.*):$") or stringmatch(tab[3], "^:(.*):$")
    str  = tab[2]

    if not role then -- implicit role
        role = "emphasis"
    end

    if stringmatch(role, "^color_") then
        return rst_context.roles.color(role, str)
    end

    return rst_context.roles[role](str)
end

function rst_context.link_standalone (str)
    return "\n"
        .. [[\\goto{\\hyphenatedurl{]] .. str .. [[}}[url(]] .. str .. [=[)]]=]
end

function rst_context.reference (str)
    rst_context.addsetups("references")
    str = stringmatch(str, "^`?([^`]+)`?_$")
    return [[\\RSTchoosegoto{__target_]] .. rst_context.whitespace_to_underscore(str) .. "}{"
            .. str .. "}"
end

function rst_context.anon_reference (str)
    rst_context.addsetups("references")
    str = stringmatch(str, "^`?([^`]+)`?__$")
    rst_context.anonymous_links[#rst_context.anonymous_links+1] = str
    link = "__target_anon_" .. #rst_context.anonymous_links
    return stringformat([[\\RSTchoosegoto{%s}{%s}]], link, str)
end

local whitespace = S" \n\t\v"
local nowhitespace = 1 - whitespace
local removewhitespace = Cs((nowhitespace^1 + Cs(whitespace / ""))^0)

function rst_context.target (tab)
    rst_context.addsetups("references")
    --local tab = { ... }
    local  refs = rst_context.collected_references
    local arefs = rst_context.anonymous_set
    local target = tab[#tab] -- Ct + C could be clearer but who cares
    tab[#tab] = nil

    local function create_anonymous ()
        rst_context.anonymous_targets = rst_context.anonymous_targets + 1
        return { "anon_" .. rst_context.anonymous_targets, rst_context.anonymous_targets }
    end

    local insert = ""

    if target == "" then -- links here
        for _, id in next, tab do
            insert = insert .. "\n\\reference[__target_" .. id .. "]{}"
        end
    else
        for i=1,#tab do
            local id = tab[i]
            if id == "" then -- anonymous
                local anon = create_anonymous()
                id, arefs[anon[1]] = anon[1], anon[2]
            else
                local tmp = tab[i]
                tmp = stringgsub(tmp, "\\:",":")
                tmp = stringmatch(tmp, "`?([^`]+)`?")
                id = tmp
                --id = tab[i]:gsub("\\:",":"):match("`?([^`]+)`?") -- deescaping
            end
            if id then
                refs[id] = refs[id] or target
            end
        end
    end

    return insert
end

function rst_context.inline_internal_target (str)
    return "\\\\reference[__target_" .. rst_context.whitespace_to_underscore(str) .."]{}"
end

function rst_context.substitution_reference (str, underscores)
    local sub = ""
    rst_context.addsetups("substitutions")
    if underscores == "_" then -- normal reference
        sub = sub .. [[\\reference[__target_]] .. rst_context.whitespace_to_underscore(stringstrip(str)) .. "]{}"
    elseif underscores == "__" then -- normal reference
        rst_context.anonymous_targets = rst_context.anonymous_targets + 1
        sub = sub .. [[\\reference[__target_anon_]] .. rst_context.anonymous_targets .. "]{}"
    end
    return sub .. [[{\\RSTsubstitution]] .. str:gsub("%s", "") .. "}"
end

do
    -- see catc-sym.tex
    local escape_me = {
        ["&"]   = [[\letterampersand ]],
        ["$"]   = [[\letterdollar ]],
        ["#"]   = [[\letterhash ]],
        ["^"]   = [[\letterhat ]],
        ["_"]   = [[\letterunderscore ]],
    }

    local chars
    for chr, repl in next, escape_me do
        chars = chars and chars + (P(chr) / repl) or P(chr) / repl
    end

    local p_escape = P{
        [1]      = Cs((V"skip"
                 --+ V"literal" -- achieved via gsub later
                 + chars
                 + 1)^1),
        skip1    = P"\\starttyping" * (1 - P"\\stoptyping")^1,
        balanced = P"{" * (V"balanced" + (1 - P"}"))^0 * P"}",
        skip2    = P"\\type" * V"balanced",
        skip3    = P"\\mathematics" * V"balanced",
        skip     = V"skip1" + V"skip2" + V"skip3",
        --literal  = Cs(P"\\" / "") * 1
    }

    function rst_context.escape (str)
        str = stringgsub(str, "\\(.)", "%1")
        return lpegmatch(p_escape, str)
    end
end

function rst_context.joinindented (tab)
    return tableconcat (tab, "")
end

local corresponding = {
    ['"'] = '"',
    ["'"] = "'",
    ["{"] = "}",
    ["("] = ")",
    ["["] = "]",
    ["<"] = ">",
}

local inline_parser = P{
    [1] = "block",

    block = Cs(V"inline_as_first"^-1 * (V"except" + V"inline_element" + V"normal_char")^0),

    inline_element = V"precede_inline"
                   * Cs(V"inline_do_elements")
                   * #V"succede_inline"
                   + V"footnote_reference"
                   ,

    -- Ugly but needed in case the first element of a paragraph is inline
    -- formatted.
    inline_as_first = V"inline_do_elements" * #V"succede_inline",

    except = P"\\starttyping" * (1 - P"\\stoptyping")^1 * P"\\stoptyping"
           + V"enclosed"
           ,

    inline_do_elements = V"strong_emphasis"
                       + V"substitution_reference"
                       + V"anon_reference"
                       + V"inline_literal"
                       + V"reference"
                       + V"emphasis"
                       + V"interpreted_text"
                       + V"inline_internal_target"
                       + V"link_standalone"
                       ,

    precede_inline = V"spacing"
                   + V"eol"
                   + -P(1)
                   + S[['"([{<-/:]]
                   + P"‘" + P"“" + P"’" + P"«" + P"¡" + P"¿"
                   + V"inline_delimiter"
                   + P"„", -- not in standard Murkin reST

    succede_inline = V"spacing"
                   + V"eol"
                   + S[['")]}>-/:.,;!?\]]
                   + P"’" + P"”" + P"»"
                   + V"inline_delimiter"
                   + -P(1)
                   + P"“" -- non-standard again but who cares
                   ,

    enclosed = V"precede_inline"^-1
             * Cg(V"quote_single" + V"quote_double" + V"leftpar", "lastgroup")
             * V"inline_delimiter"
             * Cmt(C(V"quote_single" + V"quote_double" + V"rightpar") * Cb("lastgroup"), function(s, i, char, oldchar)
                    return corresponding[oldchar] == char
                end)
             * V"succede_inline"^-1
             * -V"underscore"
             ,

    space = P" ",
    whitespace = (P" " + Cs(P"\t") / "        " + Cs(S"\v") / " "),
    spacing = V"whitespace"^1,

    eol = P"\n",
    --inline_delimiters = P"‐" + P"‑" + P"‒" + P"–" + V"emdash" + V"space",        -- inline markup
    inline_delimiter = P"‐" + P"‑" + P"‒" + P"–" + V"emdash" + V"space"
                     + V"bareia"
                     + V"asterisk"
                     + V"bar"
                     + V"lsquare" + V"rsquare"
                     ,        -- inline markup
    asterisk = P"*",
    quote_single = P"'",
    quote_double = P'"',
    double_asterisk = V"asterisk" * V"asterisk",
    bareia = P"`",
    backslash = P"\\",
    bar = P"|",
    double_bareia = V"bareia" * V"bareia",
    escaped_bareia = (Cs(V"backslash") / "" * V"bareia") + 1,
    colon = P":",
    escaped_colon = (Cs(V"backslash") / "" * V"colon") + 1,
    semicolon = P";",
    underscore = P"_",
    double_underscore = V"underscore" * V"underscore",
    dot = P".",
    interpunct = P"·",
    comma = P",",
    dash = P"-",
    emdash = P"—",
    ellipsis   = P"…" + P"...",
    exclamationmark = P"!",
    questionmark = P"?",
    interrobang = P"‽",
    double_dash = V"dash" * V"dash",
    triple_dash = V"double_dash" * V"dash",
    hyphen = P"‐",
    dashes = V"dash" + P"‒" + P"–" + V"emdash" + P"―",

    lparenthesis = P"(",
    rparenthesis = P")",
    lsquare = P"[" / [[{\\letterleftbracket}]],
    rsquare = P"]" / [[{\\letterrightbracket}]],
    lbrace  = P"{" / [[{\\letterleftbrace}]],
    rbrace  = P"}" / [[{\\letterrightbrace}]],
    less    = P"<",
    greater = P">",
    leftpar  = V"lparenthesis" + V"lsquare" + V"lbrace" + V"less",
    rightpar = V"rparenthesis" + V"rsquare" + V"rbrace" + V"greater",

    normal_char = V"lbrace" + V"rbrace" + V"lsquare" + V"rsquare" -- escape those if in input
                + 1
                ,

    --groupchars = S"()[]{}",
    groupchars = V"leftpar" + V"rightpar",
    apostrophe = P"’" + P"'",

    guillemets = P"«" + P"»",
    quotationmarks= P"‘" + P"’" + P"“" + P"”",
    solidus= P"⁄",
    slash = P"/",

    gartenzaun = P"#",
    digit  = R"09",
    letter = R"az" + R"AZ",

    punctuation = V"apostrophe"
                + V"colon"
                + V"comma"
                + V"dashes"
                + V"dot"
                + V"ellipsis"
                + V"exclamationmark"
                + V"guillemets"
                + V"hyphen"
                + V"interpunct"
                + V"interrobang"
                + V"questionmark"
                + V"quotationmarks"
                + V"semicolon"
                + V"slash"
                + V"solidus"
                + V"underscore"
                ,

    emphasis        = (V"asterisk" - V"double_asterisk")
                    * Cs((V"normal_char" - V"spacing" - V"eol" - V"asterisk")
                       * ((V"normal_char" - (V"normal_char" * V"asterisk"))^0
                        * (V"normal_char" - V"spacing" - V"eol" - V"asterisk"))^-1)
                    * V"asterisk"
                    / rst_context.emphasis,

    strong_emphasis = V"double_asterisk"
                    * Cs((V"normal_char" - V"spacing" - V"eol" - V"asterisk")
                       * ((V"normal_char" - (V"normal_char" * V"double_asterisk"))^0
                        * (V"normal_char" - V"spacing" - V"eol" - V"asterisk"))^-1)
                    * V"double_asterisk"
                    / rst_context.strong_emphasis,

    inline_literal  = V"double_bareia"
                    * C ((V"escaped_bareia" - V"spacing" - V"eol" - V"bareia")
                       * ((V"escaped_bareia" - (V"normal_char" * V"double_bareia"))^0
                        * (V"escaped_bareia" - V"spacing" - V"eol" - V"bareia"))^-1)
                    * V"double_bareia"
                    / rst_context.literal,

    interpreted_single_char = (V"normal_char" - V"spacing" - V"eol" - V"bareia") * #V"bareia",
    interpreted_multi_char  = (V"normal_char" - V"spacing" - V"eol" - V"bareia") * (V"normal_char" - (1 * V"bareia"))^0 * (1 - V"spacing" - V"eol" - V"bareia"),

    interpreted_text = C(V"role_marker"^-1)
                     * (V"bareia" - V"double_bareia")
                     * C(V"interpreted_single_char" + V"interpreted_multi_char")
                     * V"bareia"
                     * C(V"role_marker"^-1)
                     / rst_context.interpreted_text,

    role_marker = V"colon" * (V"backslash" * V"colon" + V"letter" + V"digit" + V"dash" + V"underscore" + V"dot")^1 * V"colon",

    link_standalone = C(V"uri")
                    / rst_context.link_standalone,

    anon_reference = Cs(V"anon_phrase_reference" + V"anon_normal_reference")
              / rst_context.anon_reference,

    anon_normal_reference = C((1 - V"underscore" - V"spacing" - V"eol" - V"punctuation" - V"groupchars")^1) * V"double_underscore",

    anon_phrase_reference = (V"bareia" - V"double_bareia")
                          * C((1 - V"bareia")^1)
                          * V"bareia" * V"double_underscore"
                          ,

    reference = Cs(V"normal_reference" + V"phrase_reference")
              / rst_context.reference,

    normal_reference = (1 - V"underscore" - V"spacing" - V"eol" - V"punctuation" - V"groupchars")^1 * V"underscore",

    phrase_reference = (V"bareia" - V"double_bareia")
                     * C((1 - V"bareia")^1)
                     * V"bareia" * V"underscore"
                     ,

    footnote_reference = V"lsquare"
                       * Cs(V"footnote_label" + V"citation_reference_label")
                       * V"rsquare"
                       * V"underscore"
                       / rst_context.footnote_reference
                       ,

    footnote_label = V"digit"^1
                   + V"gartenzaun" * V"letter"^1
                   + V"gartenzaun"
                   + V"asterisk"
                   ,

    citation_reference_label = V"letter" * (1 - V"rsquare")^1,

    inline_internal_target = V"underscore"
                           * V"bareia"
                           * Cs((1 - V"bareia")^1)
                           * V"bareia"
                           / rst_context.inline_internal_target
                           ,

    substitution_reference = V"bar"
                           * C((1 - V"bar")^1)
                           * V"bar"
                           * C((V"double_underscore" + V"underscore")^-1)
                           / rst_context.substitution_reference
                           ,

--------------------------------------------------------------------------------
-- Urls
--------------------------------------------------------------------------------
    uri = V"url_protocol" * V"url_domain" * V"url_path_char"^0,

    url_protocol = (P"http" + P"ftp" + P"shttp" + P"sftp") * P"://",
    url_domain_char = 1 - V"dot" - V"spacing" - V"eol" - V"punctuation",
    url_domain = V"url_domain_char"^1 * (V"dot" * V"url_domain_char"^1)^0,
    url_path_char = R("az", "AZ", "09") + S[[-_.!~*'()/]],
}

rst_context.inline_parser = inline_parser

function rst_context.paragraph (data)
    local str
    if not data then
        return ""
    elseif type(data) == "table" then
--        str = #data > 1 and  helpers.string.wrapat(lpegmatch(inline_parser, tableconcat(data, " ")), 65) 
--                        or   inline_parser:match(data[1])
        if #data > 1 then
            str = helpers.string.wrapat(
                lpegmatch(inline_parser, tableconcat(data, " "))
                , 65)
        else
            str = lpegmatch(inline_parser, data[1])
        end
    else
        str = data
    end
    return stringformat([[

\\startparagraph
%s
\\stopparagraph
]], str)
end

local sectionlevels = {
    [1] = "chapter",
    [2] = "section",
    [3] = "subsection",
    [4] = "subsubsection",
    [5] = "subsubsubsection",
}

local function get_line_pattern (chr)
    return P(chr)^1 * (-P(1))
end

function rst_context.section (...)  -- TODO general cleanup; move validity
    local tab = { ... }             -- checking to parser.
    local section, str = true, ""
    local adornchar 
    local ulen = utflen
    if #tab == 3 then -- TODO use unicode length with ConTeXt
        adornchar = tab[1]:sub(1,1)
        section = ulen(tab[1]) >= ulen(tab[2])
        str = stringstrip(tab[2])
    else -- no overline
        adornchar = tab[2]:sub(1,1)
        section = ulen(tab[1]) <= ulen(tab[2])
        str = tab[1]
    end

    if section then -- determine level
        local level = rst_context.last_section_level
        local rca = rst_context.collected_adornments
        if rca[adornchar] then
            level = rca[adornchar]
        else
            level = level + 1
            rca[adornchar] = level
            rst_context.last_section_level = level
        end

        ref = get_context_reference (str)

        str = stringformat("\n\\\\%s[%s]{%s}\n", sectionlevels[level], ref, str)
    else
        return [[{\\bf fix your sectioning!}\\endgraf}]]
    end

    return section and str or ""
end

-- Prime time for the fancybreak module.
function rst_context.transition (str)
    rst_context.addsetups("breaks")
    --return "\\fancybreak\n"
    return "\\fancybreak{$* * *$}\n"
end

function rst_context.bullet_marker(str)
    return "marker"
end

-- This one should ignore escaped spaces.
do
    local stripper = P{
        [1] = "stripper",
        stripper = V"space"^0 * C((V"space"^0 * V"nospace"^1)^0),
        space    = S(" \t\v\n"),
        escaped  = P"\\" * V"space",
        nospace  = V"escaped" + (1 - V"space"),
    }
    function stringstrip(str)
        return lpegmatch(stripper, str) or ""
    end 
end

local enumeration_types = {
    ["*"] = "*", -- unordered bulleted
    ["+"] = "*",
    ["-"] = "*",
    ["•"] = "*",
    ["‣"] = "*",
    ["⁃"] = "*",

    ["#"] = "n", -- numbered lists and conversion
    ["A"] = "A",
    ["a"] = "a",
    ["I"] = "R",
    ["i"] = "r",
}

-- \setupitemize[left=(, right=), margin=4em, stopper=]

local stripme   = S"()."
local dontstrip = 1 - stripme
local itemstripper = stripme^0 * C(dontstrip^1) * stripme^0

local function parse_itemstring(str)
    local offset = nil
    local setup = ",fit][itemalign=flushright,"
    if stringmatch(str, "^%(") then
        setup = setup .. [[left=(,]]
    end
    if stringmatch(str, "%)$") then
        setup = setup .. [[right=)]]
    end
    if stringmatch(str, "%.$") then
        setup = setup .. [[stopper={.\\space}]]
    end
    local num = stringmatch(str, "^%d")
    if num then
        -- http://thread.gmane.org/gmane.comp.tex.context/61728/focus=61729
        setup = setup .. ",start=" .. num
        str = "n"
    end

    str = lpegmatch(itemstripper, str)
    str = enumeration_types[str] or str
    return { setup = setup, str = str }
end

function rst_context.startitemize(str)
    local setup = ""
    local result = ""
    str = stringstrip(str)

    local listtype = enumeration_types[str] or parse_itemstring(str)

    if type(listtype) == "table" then
        setup = listtype.setup
        listtype = listtype.str
    end

    result = [[
\\startitemize[]] .. listtype .. setup .. [[]
]] 
    return result
end

local last_item = {} -- stack
local current_itemdepth = 0
function rst_context.stopitemize(str)
    last_item[current_itemdepth] = nil
    current_itemdepth = current_itemdepth - 1
    return str .. [[
\\stopitemize
]]
end

function rst_context.bullet_item (tab)
    local li = last_item
    -- The capture of the first item has the \startitemize as 
    -- *second* element in the array.
    local content  = #tab == 2 and tab[2] or tab[3]
    local startstr = #tab == 3 and tab[2] or nil
    local itemtype = tab[1]
    local result = startstr or ""
    if startstr then
        current_itemdepth = current_itemdepth + 1
        li[current_itemdepth] = itemtype
    elseif li[current_itemdepth] then
        if helpers.list.successor(itemtype, li[current_itemdepth]) then
            -- just leave it alone
        elseif helpers.list.greater(itemtype, li[current_itemdepth]) then
            local itemnum = tonumber(stringstrip(itemtype)) or helpers.list.get_decimal(itemtype)
            result = result .. stringformat([[
\\setnumber[itemgroup:itemize]{%s}
]], itemnum)
        end
        li[current_itemdepth] = itemtype
    end

    return result .. [[

\\item ]] .. lpegmatch(inline_parser, content) .. [[

]]
end

--------------------------------------------------------------------------------
-- Definition lists 
--------------------------------------------------------------------------------
-- TODO define proper setups (probably bnf-like and some narrower for def-paragraphs)

function rst_context.deflist (list)
    rst_context.addsetups("deflist")

    local deflist = [[
\\startRSTdefinitionlist
]] 
    for nd=1, #list do
        local item = list[nd]
        local term = item[1]
        local nc = 2
        local tmp = [[

  \\RSTdeflistterm{]] .. stringstrip(term) .. "}"
        if #item > 2 then
            while nc < #item do
                tmp = tmp .. [[

  \\RSTdeflistclassifier{]] .. stringstrip(item[nc]) .. "}"
                nc = nc + 1
            end
        end
        tmp = tmp .. [[

  \\RSTdeflistdefinition{%
]]
        local final = item[#item]
        for np=1, #final do
            local par = final[np]
            tmp = tmp .. [[
    \\RSTdeflistparagraph{%
]] .. lpegmatch(inline_parser, par) .. "}\n"
        end
        tmp = tmp .. "  }"
        deflist = deflist .. tmp
    end
    return deflist .. [[

\\stopRSTdefinitionlist
]]
end

--------------------------------------------------------------------------------
-- Field lists
--------------------------------------------------------------------------------

-- TODO Do something useful with field lists. For now I'm not sure what as the
-- bibliography directives from the reST specification seem to make sense only
-- when using docinfo and, after all, we have .bib files that are portable.

function rst_context.field_list (str)
    rst_context.addsetups("fieldlist")
    return [[

\\startRSTfieldlist]] .. str .. [[\\eTABLEbody\\stopRSTfieldlist
]]
end

function rst_context.field_name (str)
    return [[\\fieldname{]] .. str .. [[}]]
end

function rst_context.field_body (str)
    return [[\\fieldbody{]] .. lpegmatch(inline_parser, str) .. [[}]]
end

function rst_context.field (tab)
    local name, body = tab[1], tab[2]
    return stringformat([[

    \\RSTfieldname{%s}
    \\RSTfieldbody{%s}
]], name, lpegmatch(inline_parser, body))
end

function rst_context.line_comment (str)
    return "% " .. str
end

function rst_context.block_comment (str)
    return stringformat([[

\iffalse %% start block comment
%s\fi %% stop block comment
]], str)
end

function rst_context.option_list (str)
    return [[
\\setupTABLE[c][first] [background=color, backgroundcolor=grey, style=\tt]
\\setupTABLE[c][each]  [frame=off]
\\setupTABLE[r][each]  [frame=off]
\\bTABLE[split=yes,option=stretch]
\\bTABLEhead
\\bTR
  \\bTH  Option \\eTH
  \\bTH  Description \\eTH
\\eTR
\\eTABLEhead
\\bTABLEbody
]] .. lpegmatch(inline_parser, str) .. [[

\\eTABLEbody
\\eTABLE
]]
end

function rst_context.option_item (tab)
    return stringformat([[\\bTR\\bTC %s \\eTC\\bTC %s \\eTC\\eTR
]], tab[1], tab[2])
end

function rst_context.test(str)
    return ":"
end

function rst_context.literal_block (str, included)
    local indent = P" "^1
    local stripme = #str
    for line in stringgmatch(str, "[^\n]+") do
        -- setting to the lowest indend of all lines
        local idt = lpegmatch(indent, line)
        if line and idt then
            stripme = idt < stripme and idt or stripme
        end
    end

    local strip = P{
        [1] = "strip",
        strip = Cs(V"line"^1),
        eol = P"\n",
        restofline = (1 - V"eol")^0,
        stop = Cs(V"eol" * P" "^0) * -P(1) / "", -- remove trailing blank lines
        line = Cs(V"restofline" * (V"stop" + V"eol")) / function (line)
            return #line > stripme and line:sub(stripme) or line
        end,
    }

    str = lpegmatch(strip, str)
    str = [[

\starttyping[lines=hyphenated]
]] .. str .. [[

\stoptyping
]]
    if included then -- escaping can ruin your day
        str = str:gsub("\\", "\\\\")
    end
    return str
end

function rst_context.included_literal_block (str)
    return rst_context.literal_block(str, true)
end

function rst_context.line_block (str)
    rst_context.addsetups("lines")
    return [[

\\startlines
]] .. lpegmatch(inline_parser, str) .. [[\\stoplines
]]
end

function rst_context.line_block_line(str)
    str = str:gsub("\n", " ")
    return str .. "\n"
end

function rst_context.line_block_empty()
    return "\n"
end

function rst_context.block_quote (tab)
    rst_context.addsetups("blockquote")
    local str = [[
\\startlinecorrection
\\blank[small]
\\startblockquote
]] .. lpegmatch(inline_parser, tab[1]) .. [[

\\stopblockquote
]]

    return tab[2] and str .. [[
\\blank[small]
\\startattribution
]] .. lpegmatch(inline_parser, tab[2]) .. [[
\\stopattribution
\\blank[small]
\\stoplinecorrection
]]  or str .. [[
\\blank[small]
\\stoplinecorrection
]] 
end

--function rst_context.table (str)
    --return [[
--\\startlinecorrection
--]] .. str .. [[

--\\stoplinecorrection
--]]
--end

function rst_context.grid_table (tab)
    local body = ""
    local nr = 1
    local head
    if tab.has_head then
        head = [[
\\setupTABLE[c][each]  [frame=off]
\\setupTABLE[r][each]  [frame=off]
%\\startlinecorrection
\\bTABLE[split=repeat,option=stretch]
\\bTABLEhead
]]
        while nr <= tab.head_end do
            local r = tab.rows[nr]
            local isempty = true
            for n=1, #r do
                local cell = r[n]
                if cell.variant == "normal" then
                    isempty = false
                    break
                end
            end

            if not isempty then
                local row = [[\\bTR]]
                for n=1, #r do
                    local c = r[n]
                    if not (c.parent or
                            c.variant == "separator") then
                        local celltext = lpegmatch(inline_parser, c.stripped)
                        if c.span.x or c.span.y then
                            local span_exp = "["
                            if c.span.x then
                                span_exp = span_exp .. "nc=" .. c.span.x .. ","
                            end
                            if c.span.y then
                                span_exp = span_exp .. "nr=" .. c.span.y
                            end
                            celltext  = span_exp .. "] " .. celltext

                        end

                        row = row .. "\n  " .. [[\\bTH ]] .. celltext .. [[\\eTH]]
                    end
                end
                head = head .. row .. "\n" .. [[\\eTR]] .. "\n"
            end
            nr = nr + 1
        end
        head = head .. [[
\\eTABLEhead
\\bTABLEbody
]] 
    else
        head = [[
\\setupTABLE[c][each]  [frame=off]
\\setupTABLE[r][each]  [frame=off]
%\\startlinecorrection
\\bTABLE[split=repeat,option=stretch]
\\bTABLEbody
]] 
    end
    while nr <= #tab.rows do
        local r = tab.rows[nr]
        local isempty = true
        for n=1, #r do
            local cell = r[n]
            if cell.variant == "normal" then
                isempty = false
                break
            end
        end

        if not isempty then
            local row = [[\\bTR]]
            for n=1, #r do
                local c = r[n]
                if not (c.parent or
                        c.variant == "separator") then
                    local celltext = lpegmatch(inline_parser, c.stripped)
                    if c.span.x or c.span.y then
                        local span_exp = "["
                        if c.span.x then
                            span_exp = span_exp .. "nc=" .. c.span.x .. ","
                        end
                        if c.span.y then
                            span_exp = span_exp .. "nr=" .. c.span.y
                        end
                        celltext  = span_exp .. "] " .. celltext

                    end

                    row = row .. "\n  " .. [[\\bTC ]] .. celltext .. [[\\eTC]]
                end
            end
            body = body .. row .. "\n" .. [[\\eTR]] .. "\n"
        end
        nr = nr + 1
    end
    local tail = [[
\\eTABLEbody
\\eTABLE
%\\stoplinecorrection
]]
    return head .. body .. tail
end


function rst_context.simple_table(tab)
    local head
    local nr = 1
    if tab.head_end then
        head = [[
\\setupTABLE[c][each]  [frame=off]
\\setupTABLE[r][each]  [frame=off]
%\\startlinecorrection
\\bTABLE[split=yes,option=stretch]
\\bTABLEhead
]]
        while nr <= tab.head_end do
            local row = tab[nr]
            if not row.ignore then
                dbg_write(">hr>" .. #row)
                head = head .. [[\\bTR]]
                for nc=1, #row do
                    local cell = row[nc]
                    dbg_write("%7s | ", cell.content)
                    local celltext = lpegmatch(inline_parser, cell.content)
                    if cell.span then
                        head = head .. stringformat([=[\\bTH[nc=%s]%s\\eTH]=], cell.span.x, celltext or "")
                    else
                        head = head .. [[\\bTH ]] .. celltext .. [[\\eTH]]
                    end
                end
                dbg_write("\n")
                head = head .. "\\\\eTR\n"
            end
            nr = nr + 1
        end

        head = head .. [[
\\eTABLEhead
\\bTABLEbody
]] 
    else
        head = [[
\\setupTABLE[c][each]  [frame=off]
\\setupTABLE[r][each]  [frame=off]
%\\startlinecorrection
\\bTABLE[split=yes,option=stretch]
\\bTABLEbody
]] 
    end
    local tail = [[
\\eTABLEbody
\\eTABLE
%\\stoplinecorrection
]]
    local body = ""
    while nr <= #tab do
        local row = tab[nr]
        if not row.ignore then
            dbg_write(">tr>" .. #row)
            body = body .. [[\\bTR]]
            for nc=1, #row do
                local cell = row[nc]
                dbg_write("%7s | ", cell.content)
                local celltext = lpegmatch(inline_parser, cell.content)
                if cell.span then
                    body = body .. stringformat([=[\\bTC[nc=%s]%s\\eTC]=], cell.span.x, celltext or "")
                else
                    body = body .. [[\\bTC ]] .. celltext .. [[\\eTC]]
                end
            end
            dbg_write("\n")
            body = body .. "\\\\eTR\n"
        end
        nr = nr + 1
    end
    return head .. body .. tail
end

function rst_context.footnote (label, content)
    local tf = thirddata.rst.state.footnotes
    rst_context.addsetups("footnotes")
    if stringmatch(label, "^%d+$") then -- all digits
        tf.numbered[tonumber(label)] =
            rst_context.escape(lpegmatch(inline_parser, content))
    elseif label == "#" then --autonumber
        repeat -- until next unrequested number
            tf.autonumber = tf.autonumber + 1
        until tf.numbered[tf.autonumber] == nil
        tf.numbered[tf.autonumber] =
            rst_context.escape(lpegmatch(inline_parser, content))
    elseif stringmatch(label, "^#.+$") then
        local thelabel = stringmatch(label, "^#(.+)$")
        tf.autolabel[thelabel] =
            rst_context.escape(lpegmatch(inline_parser, content))
    elseif label == "*" then
        rst_context.addsetups("footnote_symbol")
        tf.symbol[#tf.symbol+1] =
            rst_context.escape(lpegmatch(inline_parser, content))
    else -- “citation reference” treated like ordinary footnote
        repeat -- until next unrequested number
            tf.autonumber = tf.autonumber + 1
        until tf.numbered[tf.autonumber] == nil
        tf.numbered[tf.autonumber] =
            rst_context.escape(lpegmatch(inline_parser, content))
    end
    return ""
end

function rst_context.substitution_definition (subtext, directive, data)
    local tmp
    if data.first ~= "" then
        tmp = { data.first }
    else
        tmp = { }
    end
    data.first = nil
    for i=1, #data do -- paragraphs
        local current = tableconcat(data[i], "\n")
        --current = lpegmatch(inline_parser, current)
        --current = rst_context.escape(current)
        tmp[#tmp+1] = current
    end
    data = tableconcat(tmp, "\n\n")
    rst_context.substitutions[subtext] = { directive = directive,
                                           data      = data }
    return ""
end

-- not to be confused with the directive definition table rst_directives
function rst_context.directive(directive, data)
    local fun  = rst_directives[directive]
    if fun then
        rst_context.addsetups("directive")
        local result = ""
        result = fun(data)
        return result
    end
    return ""
end

-- vim:ft=lua:sw=4:ts=4:expandtab