`version' needs to be declared `extern'.
[sgt/halibut] / halibut.h
1 #ifndef HALIBUT_HALIBUT_H
2 #define HALIBUT_HALIBUT_H
3
4 #include <stdio.h>
5 #include <wchar.h>
6 #include <time.h>
7 #include <string.h>
8
9 #include "charset.h"
10
11 #ifdef __GNUC__
12 #define NORETURN __attribute__((__noreturn__))
13 #else
14 #define NORETURN /* nothing */
15 #endif
16
17 #ifndef TRUE
18 #define TRUE 1
19 #endif
20 #ifndef FALSE
21 #define FALSE 0
22 #endif
23
24 /* For suppressing unused-parameter warnings */
25 #define IGNORE(x) ( (x) = (x) )
26
27 #include "tree234.h"
28
29 /*
30 * Structure tags
31 */
32 typedef struct input_Tag input;
33 typedef struct filepos_Tag filepos;
34 typedef struct paragraph_Tag paragraph;
35 typedef struct word_Tag word;
36 typedef struct keywordlist_Tag keywordlist;
37 typedef struct keyword_Tag keyword;
38 typedef struct numberstate_Tag numberstate;
39 typedef struct indexdata_Tag indexdata;
40 typedef struct indextag_Tag indextag;
41 typedef struct indexentry_Tag indexentry;
42 typedef struct macrostack_Tag macrostack;
43
44 /*
45 * Data structure to hold a file name and index, a line and a
46 * column number, for reporting errors
47 */
48 struct filepos_Tag {
49 char *filename;
50 int line, col;
51 };
52
53 /*
54 * Data structure to hold all the file names etc for input
55 */
56 typedef struct pushback_Tag {
57 int chr;
58 filepos pos;
59 } pushback;
60 struct input_Tag {
61 char **filenames; /* complete list of input files */
62 int nfiles; /* how many in the list */
63 FILE *currfp; /* the currently open one */
64 int currindex; /* which one is that in the list */
65 pushback *pushback; /* pushed-back input characters */
66 int npushback, pushbacksize;
67 filepos pos;
68 int reportcols; /* report column numbers in errors */
69 macrostack *stack; /* macro expansions in force */
70 int defcharset, charset; /* character sets for input files */
71 charset_state csstate;
72 wchar_t wc[16]; /* wide chars from input conversion */
73 int nwc, wcpos; /* size of, and position in, wc[] */
74 char *pushback_chars; /* used to save input-encoding data */
75 };
76
77 /*
78 * Data structure to hold the input form of the source, ie a linked
79 * list of paragraphs
80 */
81 struct paragraph_Tag {
82 paragraph *next;
83 int type;
84 wchar_t *keyword; /* for most special paragraphs */
85 char *origkeyword; /* same again in original charset */
86 word *words; /* list of words in paragraph */
87 int aux; /* number, in a numbered paragraph
88 * or subsection level
89 */
90 word *kwtext; /* chapter/section indication */
91 word *kwtext2; /* numeric-only form of kwtext */
92 filepos fpos;
93
94 paragraph *parent, *child, *sibling; /* for hierarchy navigation */
95
96 void *private_data; /* for temp use in backends */
97 };
98 enum {
99 para_IM, /* index merge */
100 para_BR, /* bibliography rewrite */
101 para_Rule, /* random horizontal rule */
102 para_Chapter,
103 para_Appendix,
104 para_UnnumberedChapter,
105 para_Heading,
106 para_Subsect,
107 para_Normal,
108 para_Biblio, /* causes no output unless turned ... */
109 para_BiblioCited, /* ... into this paragraph type */
110 para_Bullet,
111 para_NumberedList,
112 para_DescribedThing,
113 para_Description,
114 para_Code,
115 para_Copyright,
116 para_NoCite,
117 para_Title,
118 para_VersionID,
119 para_Config, /* configuration directive */
120 para_LcontPush, /* begin continuation of list item */
121 para_LcontPop, /* end continuation of list item */
122 para_QuotePush, /* begin block quote */
123 para_QuotePop, /* end block quote */
124 /*
125 * Back ends may define their own paragraph types beyond here,
126 * in case they need to use them internally.
127 */
128 para_NotParaType /* placeholder value */
129 };
130
131 /*
132 * Data structure to hold an individual word
133 */
134 struct word_Tag {
135 word *next, *alt;
136 int type;
137 int aux;
138 int breaks; /* can a line break after it? */
139 wchar_t *text;
140 filepos fpos;
141
142 void *private_data; /* for temp use in backends */
143 };
144 enum {
145 /* ORDERING CONSTRAINT: these normal-word types ... */
146 word_Normal,
147 word_Emph,
148 word_Code, /* monospaced; `quoted' in text */
149 word_WeakCode, /* monospaced, normal in text */
150 /* ... must be in the same order as these space types ... */
151 word_WhiteSpace, /* text is NULL or ignorable */
152 word_EmphSpace, /* WhiteSpace when emphasised */
153 word_CodeSpace, /* WhiteSpace when code */
154 word_WkCodeSpace, /* WhiteSpace when weak code */
155 /* ... and must be in the same order as these quote types ... */
156 word_Quote, /* text is NULL or ignorable */
157 word_EmphQuote, /* Quote when emphasised */
158 word_CodeQuote, /* (can't happen) */
159 word_WkCodeQuote, /* (can't happen) */
160 /* END ORDERING CONSTRAINT */
161 word_internal_endattrs,
162 word_UpperXref, /* \K */
163 word_LowerXref, /* \k */
164 word_XrefEnd, /* (invisible; no text) */
165 word_IndexRef, /* (always an invisible one) */
166 word_HyperLink, /* (invisible) */
167 word_HyperEnd, /* (also invisible; no text) */
168 /*
169 * Back ends may define their own word types beyond here, in
170 * case they need to use them internally.
171 */
172 word_NotWordType /* placeholder value */
173 };
174 /* aux values for attributed words */
175 enum {
176 attr_Only = 0x0000, /* a lone word with the attribute */
177 attr_First = 0x0001, /* the first of a series */
178 attr_Last = 0x0002, /* the last of a series */
179 attr_Always = 0x0003, /* any other part of a series */
180 attr_mask = 0x0003,
181 };
182 /* aux values for quote-type words */
183 enum {
184 quote_Open = 0x0010,
185 quote_Close = 0x0020,
186 quote_mask = 0x0030,
187 };
188 #define isattr(x) ( ( (x) > word_Normal && (x) < word_WhiteSpace ) || \
189 ( (x) > word_WhiteSpace && (x) < word_internal_endattrs ) )
190 #define sameattr(x,y) ( (((x)-(y)) & 3) == 0 )
191 #define towordstyle(x) ( word_Normal + ((x) & 3) )
192 #define tospacestyle(x) ( word_WhiteSpace + ((x) & 3) )
193 #define toquotestyle(x) ( word_Quote + ((x) & 3) )
194 #define removeattr(x) ( word_Normal + ((x) &~ 3) )
195
196 #define attraux(x) ( (x) & attr_mask )
197 #define quoteaux(x) ( (x) & quote_mask )
198
199 /*
200 * error.c
201 */
202 void fatal(int code, ...) NORETURN;
203 void error(int code, ...);
204 enum {
205 err_nomemory, /* out of memory */
206 err_optnoarg, /* option `-%s' requires an argument */
207 err_nosuchopt, /* unrecognised option `-%s' */
208 err_cmdcharset, /* unrecognised charset %s (cmdline) */
209 err_futileopt, /* futile option `-%s'%s */
210 err_noinput, /* no input files */
211 err_cantopen, /* unable to open input file `%s' */
212 err_nodata, /* no data in input files */
213 err_brokencodepara, /* line in codepara didn't begin `\c' */
214 err_kwunclosed, /* expected `}' after keyword */
215 err_kwillegal, /* paragraph type expects no keyword */
216 err_kwexpected, /* paragraph type expects a keyword */
217 err_kwtoomany, /* paragraph type expects only 1 */
218 err_bodyillegal, /* paragraph type expects only kws! */
219 err_badparatype, /* invalid command at start of para */
220 err_badmidcmd, /* invalid command in mid-para */
221 err_unexbrace, /* unexpected brace */
222 err_explbr, /* expected `{' after command */
223 err_commenteof, /* EOF inside braced comment */
224 err_kwexprbr, /* expected `}' after cross-ref */
225 err_codequote, /* \q within \c is not supported */
226 err_missingrbrace, /* unclosed braces at end of para */
227 err_missingrbrace2, /* unclosed braces at end of file */
228 err_nestedstyles, /* unable to nest text styles */
229 err_nestedindex, /* unable to nest `\i' thingys */
230 err_indexcase, /* two \i differing only in case */
231 err_nosuchkw, /* unresolved cross-reference */
232 err_multiBR, /* multiple \BRs on same keyword */
233 err_nosuchidxtag, /* \IM on unknown index tag (warning) */
234 err_cantopenw, /* can't open output file for write */
235 err_macroexists, /* this macro already exists */
236 err_sectjump, /* jump a heading level, eg \C -> \S */
237 err_winhelp_ctxclash, /* WinHelp context ID hash clash */
238 err_multikw, /* keyword clash in sections */
239 err_misplacedlcont, /* \lcont not after a list item */
240 err_sectmarkerinblock, /* section marker appeared in block */
241 err_cfginsufarg, /* \cfg{%s} insufficient args (<%d) */
242 err_infonodechar, /* colon/comma in node name in info */
243 err_text_codeline, /* \c line too long in text backend */
244 err_htmlver, /* unrecognised HTML version keyword */
245 err_charset, /* unrecognised character set name */
246 err_whatever /* random error of another type */
247 };
248
249 /*
250 * malloc.c
251 */
252 #ifdef LOGALLOC
253 void *smalloc(char *file, int line, int size);
254 void *srealloc(char *file, int line, void *p, int size);
255 void sfree(char *file, int line, void *p);
256 #define smalloc(x) smalloc(__FILE__, __LINE__, x)
257 #define srealloc(x, y) srealloc(__FILE__, __LINE__, x, y)
258 #define sfree(x) sfree(__FILE__, __LINE__, x)
259 #else
260 void *smalloc(int size);
261 void *srealloc(void *p, int size);
262 void sfree(void *p);
263 #endif
264 void free_word_list(word *w);
265 void free_para_list(paragraph *p);
266 word *dup_word_list(word *w);
267 char *dupstr(char *s);
268
269 #define snew(type) ( (type *) smalloc (sizeof (type)) )
270 #define snewn(number, type) ( (type *) smalloc ((number) * sizeof (type)) )
271 #define sresize(array, number, type) \
272 ( (type *) srealloc ((array), (number) * sizeof (type)) )
273 #define lenof(array) ( sizeof(array) / sizeof(*(array)) )
274
275 /*
276 * ustring.c
277 */
278 wchar_t *ustrdup(wchar_t const *s);
279 char *ustrtoa(wchar_t const *s, char *outbuf, int size, int charset);
280 char *ustrtoa_careful(wchar_t const *s, char *outbuf, int size, int charset);
281 wchar_t *ustrfroma(char const *s, wchar_t *outbuf, int size, int charset);
282 char *utoa_dup(wchar_t const *s, int charset);
283 char *utoa_dup_len(wchar_t const *s, int charset, int *len);
284 char *utoa_careful_dup(wchar_t const *s, int charset);
285 wchar_t *ufroma_dup(char const *s, int charset);
286 char *utoa_locale_dup(wchar_t const *s);
287 wchar_t *ufroma_locale_dup(char const *s);
288 int ustrlen(wchar_t const *s);
289 wchar_t *uadv(wchar_t *s);
290 wchar_t *ustrcpy(wchar_t *dest, wchar_t const *source);
291 wchar_t *ustrncpy(wchar_t *dest, wchar_t const *source, int n);
292 wchar_t utolower(wchar_t);
293 int uisalpha(wchar_t);
294 int ustrcmp(wchar_t *lhs, wchar_t *rhs);
295 int ustricmp(wchar_t const *lhs, wchar_t const *rhs);
296 int ustrnicmp(wchar_t const *lhs, wchar_t const *rhs, int maxlen);
297 int utoi(wchar_t const *);
298 double utof(wchar_t const *);
299 int utob(wchar_t const *);
300 int uisdigit(wchar_t);
301 wchar_t *ustrlow(wchar_t *s);
302 wchar_t *ustrftime(const wchar_t *wfmt, const struct tm *timespec);
303 int cvt_ok(int charset, const wchar_t *s);
304 int charset_from_ustr(filepos *fpos, const wchar_t *name);
305
306 /*
307 * wcwidth.c
308 */
309 int strwid(char const *s, int charset);
310 int ustrwid(wchar_t const *s, int charset);
311
312 /*
313 * help.c
314 */
315 void help(void);
316 void usage(void);
317 void showversion(void);
318 void listcharsets(void);
319
320 /*
321 * licence.c
322 */
323 void licence(void);
324
325 /*
326 * version.c
327 */
328 extern const char *const version;
329
330 /*
331 * misc.c
332 */
333 char *adv(char *s);
334
335 typedef struct stackTag *stack;
336 stack stk_new(void);
337 void stk_free(stack);
338 void stk_push(stack, void *);
339 void *stk_pop(stack);
340 void *stk_top(stack);
341
342 typedef struct tagRdstring rdstring;
343 struct tagRdstring {
344 int pos, size;
345 wchar_t *text;
346 };
347 typedef struct tagRdstringc rdstringc;
348 struct tagRdstringc {
349 int pos, size;
350 char *text;
351 };
352 extern const rdstring empty_rdstring;
353 extern const rdstringc empty_rdstringc;
354 void rdadd(rdstring *rs, wchar_t c);
355 void rdadds(rdstring *rs, wchar_t const *p);
356 wchar_t *rdtrim(rdstring *rs);
357 void rdaddc(rdstringc *rs, char c);
358 void rdaddsc(rdstringc *rs, char const *p);
359 char *rdtrimc(rdstringc *rs);
360
361 int compare_wordlists(word *a, word *b);
362
363 void mark_attr_ends(word *words);
364
365 typedef struct tagWrappedLine wrappedline;
366 struct tagWrappedLine {
367 wrappedline *next;
368 word *begin, *end; /* first & last words of line */
369 int nspaces; /* number of whitespaces in line */
370 int shortfall; /* how much shorter than max width */
371 };
372 wrappedline *wrap_para(word *, int, int, int (*)(void *, word *), void *, int);
373 void wrap_free(wrappedline *);
374 void cmdline_cfg_add(paragraph *cfg, char *string);
375 paragraph *cmdline_cfg_new(void);
376 paragraph *cmdline_cfg_simple(char *string, ...);
377
378 /*
379 * input.c
380 */
381 paragraph *read_input(input *in, indexdata *idx);
382
383 /*
384 * keywords.c
385 */
386 struct keywordlist_Tag {
387 int nkeywords;
388 int size;
389 tree234 *keys; /* sorted by `key' field */
390 word **looseends; /* non-keyword list element numbers */
391 int nlooseends;
392 int looseendssize;
393 };
394 struct keyword_Tag {
395 wchar_t *key; /* the keyword itself */
396 word *text; /* "Chapter 2", "Appendix Q"... */
397 /* (NB: filepos are not set) */
398 paragraph *para; /* the paragraph referenced */
399 };
400 keyword *kw_lookup(keywordlist *, wchar_t *);
401 keywordlist *get_keywords(paragraph *);
402 void free_keywords(keywordlist *);
403 void subst_keywords(paragraph *, keywordlist *);
404
405 /*
406 * index.c
407 */
408
409 /*
410 * Data structure to hold both sides of the index.
411 */
412 struct indexdata_Tag {
413 tree234 *tags; /* holds type `indextag' */
414 tree234 *entries; /* holds type `indexentry' */
415 };
416
417 /*
418 * Data structure to hold an index tag (LHS of index).
419 */
420 struct indextag_Tag {
421 wchar_t *name;
422 word *implicit_text;
423 filepos implicit_fpos;
424 word **explicit_texts;
425 filepos *explicit_fpos;
426 int nexplicit, explicit_size;
427 int nrefs;
428 indexentry **refs; /* array of entries referenced by tag */
429 };
430
431 /*
432 * Data structure to hold an index entry (RHS of index).
433 */
434 struct indexentry_Tag {
435 word *text;
436 void *backend_data; /* private to back end */
437 filepos fpos;
438 };
439
440 indexdata *make_index(void);
441 void cleanup_index(indexdata *);
442 /* index_merge takes responsibility for freeing arg 3 iff implicit; never
443 * takes responsibility for arg 2 */
444 void index_merge(indexdata *, int is_explicit, wchar_t *, word *, filepos *);
445 void build_index(indexdata *);
446 void index_debug(indexdata *);
447 indextag *index_findtag(indexdata *idx, wchar_t *name);
448
449 /*
450 * contents.c
451 */
452 numberstate *number_init(void);
453 void number_cfg(numberstate *, paragraph *);
454 word *number_mktext(numberstate *, paragraph *, wchar_t *, int *, int *);
455 void number_free(numberstate *);
456
457 /*
458 * biblio.c
459 */
460 void gen_citations(paragraph *, keywordlist *);
461
462 /*
463 * bk_text.c
464 */
465 void text_backend(paragraph *, keywordlist *, indexdata *, void *);
466 paragraph *text_config_filename(char *filename);
467
468 /*
469 * bk_html.c
470 */
471 void html_backend(paragraph *, keywordlist *, indexdata *, void *);
472 paragraph *html_config_filename(char *filename);
473
474 /*
475 * bk_whlp.c
476 */
477 void whlp_backend(paragraph *, keywordlist *, indexdata *, void *);
478 paragraph *whlp_config_filename(char *filename);
479
480 /*
481 * bk_man.c
482 */
483 void man_backend(paragraph *, keywordlist *, indexdata *, void *);
484 paragraph *man_config_filename(char *filename);
485
486 /*
487 * bk_info.c
488 */
489 void info_backend(paragraph *, keywordlist *, indexdata *, void *);
490 paragraph *info_config_filename(char *filename);
491
492 /*
493 * bk_paper.c
494 */
495 void *paper_pre_backend(paragraph *, keywordlist *, indexdata *);
496
497 /*
498 * bk_ps.c
499 */
500 void ps_backend(paragraph *, keywordlist *, indexdata *, void *);
501 paragraph *ps_config_filename(char *filename);
502
503 /*
504 * bk_pdf.c
505 */
506 void pdf_backend(paragraph *, keywordlist *, indexdata *, void *);
507 paragraph *pdf_config_filename(char *filename);
508
509 #endif