Merge branch 'vendor/MDOCML'
[dragonfly.git] / contrib / mdocml / chars.c
1 /*      $Id: chars.c,v 1.78 2018/12/15 19:30:26 schwarze Exp $ */
2 /*
3  * Copyright (c) 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
4  * Copyright (c) 2011,2014,2015,2017,2018 Ingo Schwarze <schwarze@openbsd.org>
5  *
6  * Permission to use, copy, modify, and distribute this software for any
7  * purpose with or without fee is hereby granted, provided that the above
8  * copyright notice and this permission notice appear in all copies.
9  *
10  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
11  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
12  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
13  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
14  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
15  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
16  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
17  */
18 #include "config.h"
19
20 #include <sys/types.h>
21
22 #include <assert.h>
23 #include <ctype.h>
24 #include <stddef.h>
25 #include <stdint.h>
26 #include <stdio.h>
27 #include <stdlib.h>
28 #include <string.h>
29
30 #include "mandoc.h"
31 #include "mandoc_aux.h"
32 #include "mandoc_ohash.h"
33 #include "libmandoc.h"
34
35 struct  ln {
36         const char        roffcode[16];
37         const char       *ascii;
38         int               unicode;
39 };
40
41 /* Special break control characters. */
42 static const char ascii_nbrsp[2] = { ASCII_NBRSP, '\0' };
43 static const char ascii_break[2] = { ASCII_BREAK, '\0' };
44
45 static struct ln lines[] = {
46
47         /* Spacing. */
48         { " ",                  ascii_nbrsp,    0x00a0  },
49         { "~",                  ascii_nbrsp,    0x00a0  },
50         { "0",                  " ",            0x2002  },
51         { ":",                  ascii_break,    0       },
52
53         /* Lines. */
54         { "ba",                 "|",            0x007c  },
55         { "br",                 "|",            0x2502  },
56         { "ul",                 "_",            0x005f  },
57         { "_",                  "_",            0x005f  },
58         { "ru",                 "_",            0x005f  },
59         { "rn",                 "-",            0x203e  },
60         { "bb",                 "|",            0x00a6  },
61         { "sl",                 "/",            0x002f  },
62         { "rs",                 "\\",           0x005c  },
63
64         /* Text markers. */
65         { "ci",                 "O",            0x25cb  },
66         { "bu",                 "+\bo",         0x2022  },
67         { "dd",                 "<**>",         0x2021  },
68         { "dg",                 "<*>",          0x2020  },
69         { "lz",                 "<>",           0x25ca  },
70         { "sq",                 "[]",           0x25a1  },
71         { "ps",                 "<paragraph>",  0x00b6  },
72         { "sc",                 "<section>",    0x00a7  },
73         { "lh",                 "<=",           0x261c  },
74         { "rh",                 "=>",           0x261e  },
75         { "at",                 "@",            0x0040  },
76         { "sh",                 "#",            0x0023  },
77         { "CR",                 "<cr>",         0x21b5  },
78         { "OK",                 "\\/",          0x2713  },
79         { "CL",                 "C",            0x2663  },
80         { "SP",                 "S",            0x2660  },
81         { "HE",                 "H",            0x2665  },
82         { "DI",                 "D",            0x2666  },
83
84         /* Legal symbols. */
85         { "co",                 "(C)",          0x00a9  },
86         { "rg",                 "(R)",          0x00ae  },
87         { "tm",                 "tm",           0x2122  },
88
89         /* Punctuation. */
90         { "em",                 "--",           0x2014  },
91         { "en",                 "-",            0x2013  },
92         { "hy",                 "-",            0x2010  },
93         { "e",                  "\\",           0x005c  },
94         { ".",                  ".",            0x002e  },
95         { "r!",                 "!",            0x00a1  },
96         { "r?",                 "?",            0x00bf  },
97
98         /* Quotes. */
99         { "Bq",                 ",,",           0x201e  },
100         { "bq",                 ",",            0x201a  },
101         { "lq",                 "\"",           0x201c  },
102         { "rq",                 "\"",           0x201d  },
103         { "Lq",                 "\"",           0x201c  },
104         { "Rq",                 "\"",           0x201d  },
105         { "oq",                 "`",            0x2018  },
106         { "cq",                 "\'",           0x2019  },
107         { "aq",                 "\'",           0x0027  },
108         { "dq",                 "\"",           0x0022  },
109         { "Fo",                 "<<",           0x00ab  },
110         { "Fc",                 ">>",           0x00bb  },
111         { "fo",                 "<",            0x2039  },
112         { "fc",                 ">",            0x203a  },
113
114         /* Brackets. */
115         { "lB",                 "[",            0x005b  },
116         { "rB",                 "]",            0x005d  },
117         { "lC",                 "{",            0x007b  },
118         { "rC",                 "}",            0x007d  },
119         { "la",                 "<",            0x27e8  },
120         { "ra",                 ">",            0x27e9  },
121         { "bv",                 "|",            0x23aa  },
122         { "braceex",            "|",            0x23aa  },
123         { "bracketlefttp",      "|",            0x23a1  },
124         { "bracketleftbt",      "|",            0x23a3  },
125         { "bracketleftex",      "|",            0x23a2  },
126         { "bracketrighttp",     "|",            0x23a4  },
127         { "bracketrightbt",     "|",            0x23a6  },
128         { "bracketrightex",     "|",            0x23a5  },
129         { "lt",                 ",-",           0x23a7  },
130         { "bracelefttp",        ",-",           0x23a7  },
131         { "lk",                 "{",            0x23a8  },
132         { "braceleftmid",       "{",            0x23a8  },
133         { "lb",                 "`-",           0x23a9  },
134         { "braceleftbt",        "`-",           0x23a9  },
135         { "braceleftex",        "|",            0x23aa  },
136         { "rt",                 "-.",           0x23ab  },
137         { "bracerighttp",       "-.",           0x23ab  },
138         { "rk",                 "}",            0x23ac  },
139         { "bracerightmid",      "}",            0x23ac  },
140         { "rb",                 "-\'",          0x23ad  },
141         { "bracerightbt",       "-\'",          0x23ad  },
142         { "bracerightex",       "|",            0x23aa  },
143         { "parenlefttp",        "/",            0x239b  },
144         { "parenleftbt",        "\\",           0x239d  },
145         { "parenleftex",        "|",            0x239c  },
146         { "parenrighttp",       "\\",           0x239e  },
147         { "parenrightbt",       "/",            0x23a0  },
148         { "parenrightex",       "|",            0x239f  },
149
150         /* Arrows and lines. */
151         { "<-",                 "<-",           0x2190  },
152         { "->",                 "->",           0x2192  },
153         { "<>",                 "<->",          0x2194  },
154         { "da",                 "|\bv",         0x2193  },
155         { "ua",                 "|\b^",         0x2191  },
156         { "va",                 "^v",           0x2195  },
157         { "lA",                 "<=",           0x21d0  },
158         { "rA",                 "=>",           0x21d2  },
159         { "hA",                 "<=>",          0x21d4  },
160         { "uA",                 "=\b^",         0x21d1  },
161         { "dA",                 "=\bv",         0x21d3  },
162         { "vA",                 "^=v",          0x21d5  },
163         { "an",                 "-",            0x23af  },
164
165         /* Logic. */
166         { "AN",                 "^",            0x2227  },
167         { "OR",                 "v",            0x2228  },
168         { "no",                 "~",            0x00ac  },
169         { "tno",                "~",            0x00ac  },
170         { "te",                 "<there\037exists>", 0x2203 },
171         { "fa",                 "<for\037all>", 0x2200  },
172         { "st",                 "<such\037that>", 0x220b },
173         { "tf",                 "<therefore>",  0x2234  },
174         { "3d",                 "<therefore>",  0x2234  },
175         { "or",                 "|",            0x007c  },
176
177         /* Mathematicals. */
178         { "pl",                 "+",            0x002b  },
179         { "mi",                 "-",            0x2212  },
180         { "-",                  "-",            0x002d  },
181         { "-+",                 "-+",           0x2213  },
182         { "+-",                 "+-",           0x00b1  },
183         { "t+-",                "+-",           0x00b1  },
184         { "pc",                 ".",            0x00b7  },
185         { "md",                 ".",            0x22c5  },
186         { "mu",                 "x",            0x00d7  },
187         { "tmu",                "x",            0x00d7  },
188         { "c*",                 "O\bx",         0x2297  },
189         { "c+",                 "O\b+",         0x2295  },
190         { "di",                 "/",            0x00f7  },
191         { "tdi",                "/",            0x00f7  },
192         { "f/",                 "/",            0x2044  },
193         { "**",                 "*",            0x2217  },
194         { "<=",                 "<=",           0x2264  },
195         { ">=",                 ">=",           0x2265  },
196         { "<<",                 "<<",           0x226a  },
197         { ">>",                 ">>",           0x226b  },
198         { "eq",                 "=",            0x003d  },
199         { "!=",                 "!=",           0x2260  },
200         { "==",                 "==",           0x2261  },
201         { "ne",                 "!==",          0x2262  },
202         { "ap",                 "~",            0x223c  },
203         { "|=",                 "-~",           0x2243  },
204         { "=~",                 "=~",           0x2245  },
205         { "~~",                 "~~",           0x2248  },
206         { "~=",                 "~=",           0x2248  },
207         { "pt",                 "<proportional\037to>", 0x221d },
208         { "es",                 "{}",           0x2205  },
209         { "mo",                 "<element\037of>", 0x2208 },
210         { "nm",                 "<not\037element\037of>", 0x2209 },
211         { "sb",                 "<proper\037subset>", 0x2282 },
212         { "nb",                 "<not\037subset>", 0x2284 },
213         { "sp",                 "<proper\037superset>", 0x2283 },
214         { "nc",                 "<not\037superset>", 0x2285 },
215         { "ib",                 "<subset\037or\037equal>", 0x2286 },
216         { "ip",                 "<superset\037or\037equal>", 0x2287 },
217         { "ca",                 "<intersection>", 0x2229 },
218         { "cu",                 "<union>",      0x222a  },
219         { "/_",                 "<angle>",      0x2220  },
220         { "pp",                 "<perpendicular>", 0x22a5 },
221         { "is",                 "<integral>",   0x222b  },
222         { "integral",           "<integral>",   0x222b  },
223         { "sum",                "<sum>",        0x2211  },
224         { "product",            "<product>",    0x220f  },
225         { "coproduct",          "<coproduct>",  0x2210  },
226         { "gr",                 "<nabla>",      0x2207  },
227         { "sr",                 "<sqrt>",       0x221a  },
228         { "sqrt",               "<sqrt>",       0x221a  },
229         { "lc",                 "|~",           0x2308  },
230         { "rc",                 "~|",           0x2309  },
231         { "lf",                 "|_",           0x230a  },
232         { "rf",                 "_|",           0x230b  },
233         { "if",                 "<infinity>",   0x221e  },
234         { "Ah",                 "<Aleph>",      0x2135  },
235         { "Im",                 "<Im>",         0x2111  },
236         { "Re",                 "<Re>",         0x211c  },
237         { "wp",                 "p",            0x2118  },
238         { "pd",                 "<del>",        0x2202  },
239         { "-h",                 "/h",           0x210f  },
240         { "hbar",               "/h",           0x210f  },
241         { "12",                 "1/2",          0x00bd  },
242         { "14",                 "1/4",          0x00bc  },
243         { "34",                 "3/4",          0x00be  },
244         { "18",                 "1/8",          0x215B  },
245         { "38",                 "3/8",          0x215C  },
246         { "58",                 "5/8",          0x215D  },
247         { "78",                 "7/8",          0x215E  },
248         { "S1",                 "^1",           0x00B9  },
249         { "S2",                 "^2",           0x00B2  },
250         { "S3",                 "^3",           0x00B3  },
251
252         /* Ligatures. */
253         { "ff",                 "ff",           0xfb00  },
254         { "fi",                 "fi",           0xfb01  },
255         { "fl",                 "fl",           0xfb02  },
256         { "Fi",                 "ffi",          0xfb03  },
257         { "Fl",                 "ffl",          0xfb04  },
258         { "AE",                 "AE",           0x00c6  },
259         { "ae",                 "ae",           0x00e6  },
260         { "OE",                 "OE",           0x0152  },
261         { "oe",                 "oe",           0x0153  },
262         { "ss",                 "ss",           0x00df  },
263         { "IJ",                 "IJ",           0x0132  },
264         { "ij",                 "ij",           0x0133  },
265
266         /* Accents. */
267         { "a\"",                "\"",           0x02dd  },
268         { "a-",                 "-",            0x00af  },
269         { "a.",                 ".",            0x02d9  },
270         { "a^",                 "^",            0x005e  },
271         { "aa",                 "\'",           0x00b4  },
272         { "\'",                 "\'",           0x00b4  },
273         { "ga",                 "`",            0x0060  },
274         { "`",                  "`",            0x0060  },
275         { "ab",                 "'\b`",         0x02d8  },
276         { "ac",                 ",",            0x00b8  },
277         { "ad",                 "\"",           0x00a8  },
278         { "ah",                 "v",            0x02c7  },
279         { "ao",                 "o",            0x02da  },
280         { "a~",                 "~",            0x007e  },
281         { "ho",                 ",",            0x02db  },
282         { "ha",                 "^",            0x005e  },
283         { "ti",                 "~",            0x007e  },
284         { "u02DC",              "~",            0x02dc  },
285
286         /* Accented letters. */
287         { "'A",                 "'\bA",         0x00c1  },
288         { "'E",                 "'\bE",         0x00c9  },
289         { "'I",                 "'\bI",         0x00cd  },
290         { "'O",                 "'\bO",         0x00d3  },
291         { "'U",                 "'\bU",         0x00da  },
292         { "'Y",                 "'\bY",         0x00dd  },
293         { "'a",                 "'\ba",         0x00e1  },
294         { "'e",                 "'\be",         0x00e9  },
295         { "'i",                 "'\bi",         0x00ed  },
296         { "'o",                 "'\bo",         0x00f3  },
297         { "'u",                 "'\bu",         0x00fa  },
298         { "'y",                 "'\by",         0x00fd  },
299         { "`A",                 "`\bA",         0x00c0  },
300         { "`E",                 "`\bE",         0x00c8  },
301         { "`I",                 "`\bI",         0x00cc  },
302         { "`O",                 "`\bO",         0x00d2  },
303         { "`U",                 "`\bU",         0x00d9  },
304         { "`a",                 "`\ba",         0x00e0  },
305         { "`e",                 "`\be",         0x00e8  },
306         { "`i",                 "`\bi",         0x00ec  },
307         { "`o",                 "`\bo",         0x00f2  },
308         { "`u",                 "`\bu",         0x00f9  },
309         { "~A",                 "~\bA",         0x00c3  },
310         { "~N",                 "~\bN",         0x00d1  },
311         { "~O",                 "~\bO",         0x00d5  },
312         { "~a",                 "~\ba",         0x00e3  },
313         { "~n",                 "~\bn",         0x00f1  },
314         { "~o",                 "~\bo",         0x00f5  },
315         { ":A",                 "\"\bA",        0x00c4  },
316         { ":E",                 "\"\bE",        0x00cb  },
317         { ":I",                 "\"\bI",        0x00cf  },
318         { ":O",                 "\"\bO",        0x00d6  },
319         { ":U",                 "\"\bU",        0x00dc  },
320         { ":a",                 "\"\ba",        0x00e4  },
321         { ":e",                 "\"\be",        0x00eb  },
322         { ":i",                 "\"\bi",        0x00ef  },
323         { ":o",                 "\"\bo",        0x00f6  },
324         { ":u",                 "\"\bu",        0x00fc  },
325         { ":y",                 "\"\by",        0x00ff  },
326         { "^A",                 "^\bA",         0x00c2  },
327         { "^E",                 "^\bE",         0x00ca  },
328         { "^I",                 "^\bI",         0x00ce  },
329         { "^O",                 "^\bO",         0x00d4  },
330         { "^U",                 "^\bU",         0x00db  },
331         { "^a",                 "^\ba",         0x00e2  },
332         { "^e",                 "^\be",         0x00ea  },
333         { "^i",                 "^\bi",         0x00ee  },
334         { "^o",                 "^\bo",         0x00f4  },
335         { "^u",                 "^\bu",         0x00fb  },
336         { ",C",                 ",\bC",         0x00c7  },
337         { ",c",                 ",\bc",         0x00e7  },
338         { "/L",                 "/\bL",         0x0141  },
339         { "/l",                 "/\bl",         0x0142  },
340         { "/O",                 "/\bO",         0x00d8  },
341         { "/o",                 "/\bo",         0x00f8  },
342         { "oA",                 "o\bA",         0x00c5  },
343         { "oa",                 "o\ba",         0x00e5  },
344
345         /* Special letters. */
346         { "-D",                 "Dh",           0x00d0  },
347         { "Sd",                 "dh",           0x00f0  },
348         { "TP",                 "Th",           0x00de  },
349         { "Tp",                 "th",           0x00fe  },
350         { ".i",                 "i",            0x0131  },
351         { ".j",                 "j",            0x0237  },
352
353         /* Currency. */
354         { "Do",                 "$",            0x0024  },
355         { "ct",                 "/\bc",         0x00a2  },
356         { "Eu",                 "EUR",          0x20ac  },
357         { "eu",                 "EUR",          0x20ac  },
358         { "Ye",                 "=\bY",         0x00a5  },
359         { "Po",                 "-\bL",         0x00a3  },
360         { "Cs",                 "o\bx",         0x00a4  },
361         { "Fn",                 ",\bf",         0x0192  },
362
363         /* Units. */
364         { "de",                 "<degree>",     0x00b0  },
365         { "%0",                 "<permille>",   0x2030  },
366         { "fm",                 "\'",           0x2032  },
367         { "sd",                 "''",           0x2033  },
368         { "mc",                 "<micro>",      0x00b5  },
369         { "Of",                 "_\ba",         0x00aa  },
370         { "Om",                 "_\bo",         0x00ba  },
371
372         /* Greek characters. */
373         { "*A",                 "A",            0x0391  },
374         { "*B",                 "B",            0x0392  },
375         { "*G",                 "<Gamma>",      0x0393  },
376         { "*D",                 "<Delta>",      0x0394  },
377         { "*E",                 "E",            0x0395  },
378         { "*Z",                 "Z",            0x0396  },
379         { "*Y",                 "H",            0x0397  },
380         { "*H",                 "<Theta>",      0x0398  },
381         { "*I",                 "I",            0x0399  },
382         { "*K",                 "K",            0x039a  },
383         { "*L",                 "<Lambda>",     0x039b  },
384         { "*M",                 "M",            0x039c  },
385         { "*N",                 "N",            0x039d  },
386         { "*C",                 "<Xi>",         0x039e  },
387         { "*O",                 "O",            0x039f  },
388         { "*P",                 "<Pi>",         0x03a0  },
389         { "*R",                 "P",            0x03a1  },
390         { "*S",                 "<Sigma>",      0x03a3  },
391         { "*T",                 "T",            0x03a4  },
392         { "*U",                 "Y",            0x03a5  },
393         { "*F",                 "<Phi>",        0x03a6  },
394         { "*X",                 "X",            0x03a7  },
395         { "*Q",                 "<Psi>",        0x03a8  },
396         { "*W",                 "<Omega>",      0x03a9  },
397         { "*a",                 "<alpha>",      0x03b1  },
398         { "*b",                 "<beta>",       0x03b2  },
399         { "*g",                 "<gamma>",      0x03b3  },
400         { "*d",                 "<delta>",      0x03b4  },
401         { "*e",                 "<epsilon>",    0x03b5  },
402         { "*z",                 "<zeta>",       0x03b6  },
403         { "*y",                 "<eta>",        0x03b7  },
404         { "*h",                 "<theta>",      0x03b8  },
405         { "*i",                 "<iota>",       0x03b9  },
406         { "*k",                 "<kappa>",      0x03ba  },
407         { "*l",                 "<lambda>",     0x03bb  },
408         { "*m",                 "<mu>",         0x03bc  },
409         { "*n",                 "<nu>",         0x03bd  },
410         { "*c",                 "<xi>",         0x03be  },
411         { "*o",                 "o",            0x03bf  },
412         { "*p",                 "<pi>",         0x03c0  },
413         { "*r",                 "<rho>",        0x03c1  },
414         { "*s",                 "<sigma>",      0x03c3  },
415         { "*t",                 "<tau>",        0x03c4  },
416         { "*u",                 "<upsilon>",    0x03c5  },
417         { "*f",                 "<phi>",        0x03d5  },
418         { "*x",                 "<chi>",        0x03c7  },
419         { "*q",                 "<psi>",        0x03c8  },
420         { "*w",                 "<omega>",      0x03c9  },
421         { "+h",                 "<theta>",      0x03d1  },
422         { "+f",                 "<phi>",        0x03c6  },
423         { "+p",                 "<pi>",         0x03d6  },
424         { "+e",                 "<epsilon>",    0x03f5  },
425         { "ts",                 "<sigma>",      0x03c2  },
426 };
427
428 static  struct ohash      mchars;
429
430
431 void
432 mchars_free(void)
433 {
434
435         ohash_delete(&mchars);
436 }
437
438 void
439 mchars_alloc(void)
440 {
441         size_t            i;
442         unsigned int      slot;
443
444         mandoc_ohash_init(&mchars, 9, offsetof(struct ln, roffcode));
445         for (i = 0; i < sizeof(lines)/sizeof(lines[0]); i++) {
446                 slot = ohash_qlookup(&mchars, lines[i].roffcode);
447                 assert(ohash_find(&mchars, slot) == NULL);
448                 ohash_insert(&mchars, slot, lines + i);
449         }
450 }
451
452 int
453 mchars_spec2cp(const char *p, size_t sz)
454 {
455         const struct ln *ln;
456         const char      *end;
457
458         end = p + sz;
459         ln = ohash_find(&mchars, ohash_qlookupi(&mchars, p, &end));
460         return ln != NULL ? ln->unicode : -1;
461 }
462
463 int
464 mchars_num2char(const char *p, size_t sz)
465 {
466         int       i;
467
468         i = mandoc_strntoi(p, sz, 10);
469         return i >= 0 && i < 256 ? i : -1;
470 }
471
472 int
473 mchars_num2uc(const char *p, size_t sz)
474 {
475         int      i;
476
477         i = mandoc_strntoi(p, sz, 16);
478         assert(i >= 0 && i <= 0x10FFFF);
479         return i;
480 }
481
482 const char *
483 mchars_spec2str(const char *p, size_t sz, size_t *rsz)
484 {
485         const struct ln *ln;
486         const char      *end;
487
488         end = p + sz;
489         ln = ohash_find(&mchars, ohash_qlookupi(&mchars, p, &end));
490         if (ln == NULL)
491                 return NULL;
492
493         *rsz = strlen(ln->ascii);
494         return ln->ascii;
495 }
496
497 const char *
498 mchars_uc2str(int uc)
499 {
500         size_t    i;
501
502         for (i = 0; i < sizeof(lines)/sizeof(lines[0]); i++)
503                 if (uc == lines[i].unicode)
504                         return lines[i].ascii;
505         return "<?>";
506 }