=================================================================== RCS file: /cvs/mandoc/mandoc.c,v retrieving revision 1.50 retrieving revision 1.64 diff -u -p -r1.50 -r1.64 --- mandoc/mandoc.c 2011/05/14 16:06:09 1.50 +++ mandoc/mandoc.c 2012/05/31 22:34:06 1.64 @@ -1,7 +1,7 @@ -/* $Id: mandoc.c,v 1.50 2011/05/14 16:06:09 kristaps Exp $ */ +/* $Id: mandoc.c,v 1.64 2012/05/31 22:34:06 schwarze Exp $ */ /* - * Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons - * Copyright (c) 2011 Ingo Schwarze + * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons + * Copyright (c) 2011, 2012 Ingo Schwarze * * Permission to use, copy, modify, and distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -37,71 +37,13 @@ static int a2time(time_t *, const char *, const char *); static char *time2a(time_t); -static int numescape(const char *); -/* - * Pass over recursive numerical expressions. This context of this - * function is important: it's only called within character-terminating - * escapes (e.g., \s[xxxyyy]), so all we need to do is handle initial - * recursion: we don't care about what's in these blocks. - * This returns the number of characters skipped or -1 if an error - * occurs (the caller should bail). - */ -static int -numescape(const char *start) -{ - int i; - size_t sz; - const char *cp; - i = 0; - - /* The expression consists of a subexpression. */ - - if ('\\' == start[i]) { - cp = &start[++i]; - /* - * Read past the end of the subexpression. - * Bail immediately on errors. - */ - if (ESCAPE_ERROR == mandoc_escape(&cp, NULL, NULL)) - return(-1); - return(i + cp - &start[i]); - } - - if ('(' != start[i++]) - return(0); - - /* - * A parenthesised subexpression. Read until the closing - * parenthesis, making sure to handle any nested subexpressions - * that might ruin our parse. - */ - - while (')' != start[i]) { - sz = strcspn(&start[i], ")\\"); - i += (int)sz; - - if ('\0' == start[i]) - return(-1); - else if ('\\' != start[i]) - continue; - - cp = &start[++i]; - if (ESCAPE_ERROR == mandoc_escape(&cp, NULL, NULL)) - return(-1); - i += cp - &start[i]; - } - - /* Read past the terminating ')'. */ - return(++i); -} - enum mandoc_esc mandoc_escape(const char **end, const char **start, int *sz) { - char c, term, numeric; - int i, lim, ssz, rlim; + char c, term; + int i, rlim; const char *cp, *rstart; enum mandoc_esc gly; @@ -109,9 +51,9 @@ mandoc_escape(const char **end, const char **start, in rstart = cp; if (start) *start = rstart; - i = lim = 0; + i = rlim = 0; gly = ESCAPE_ERROR; - term = numeric = '\0'; + term = '\0'; switch ((c = cp[i++])) { /* @@ -121,10 +63,18 @@ mandoc_escape(const char **end, const char **start, in */ case ('('): gly = ESCAPE_SPECIAL; - lim = 2; + rlim = 2; break; case ('['): gly = ESCAPE_SPECIAL; + /* + * Unicode escapes are defined in groff as \[uXXXX] to + * \[u10FFFF], where the contained value must be a valid + * Unicode codepoint. Here, however, only check whether + * it's not a zero-width escape. + */ + if ('u' == cp[i] && ']' != cp[i + 1]) + gly = ESCAPE_UNICODE; term = ']'; break; case ('C'): @@ -135,6 +85,16 @@ mandoc_escape(const char **end, const char **start, in break; /* + * The \z escape is supposed to output the following + * character without advancing the cursor position. + * Since we are mostly dealing with terminal mode, + * let us just skip the next character. + */ + case ('z'): + (*end)++; + return(ESCAPE_SKIPCHAR); + + /* * Handle all triggers matching \X(xy, \Xx, and \X[xxxx], where * 'X' is the trigger. These have opaque sub-strings. */ @@ -153,13 +113,8 @@ mandoc_escape(const char **end, const char **start, in case ('V'): /* FALLTHROUGH */ case ('Y'): - if (ESCAPE_ERROR == gly) - gly = ESCAPE_IGNORE; + gly = ESCAPE_IGNORE; /* FALLTHROUGH */ - case ('*'): - if (ESCAPE_ERROR == gly) - gly = ESCAPE_PREDEF; - /* FALLTHROUGH */ case ('f'): if (ESCAPE_ERROR == gly) gly = ESCAPE_FONT; @@ -170,13 +125,13 @@ mandoc_escape(const char **end, const char **start, in switch (cp[i++]) { case ('('): - lim = 2; + rlim = 2; break; case ('['): term = ']'; break; default: - lim = 1; + rlim = 1; i--; break; } @@ -218,11 +173,8 @@ mandoc_escape(const char **end, const char **start, in case ('L'): /* FALLTHROUGH */ case ('l'): + gly = ESCAPE_NUMBERED; /* FALLTHROUGH */ - case ('N'): - if (ESCAPE_ERROR == gly) - gly = ESCAPE_NUMBERED; - /* FALLTHROUGH */ case ('S'): /* FALLTHROUGH */ case ('v'): @@ -234,9 +186,29 @@ mandoc_escape(const char **end, const char **start, in gly = ESCAPE_IGNORE; if ('\'' != cp[i++]) return(ESCAPE_ERROR); - term = numeric = '\''; + term = '\''; break; + /* + * Special handling for the numbered character escape. + * XXX Do any other escapes need similar handling? + */ + case ('N'): + if ('\0' == cp[i]) + return(ESCAPE_ERROR); + *end = &cp[++i]; + if (isdigit((unsigned char)cp[i-1])) + return(ESCAPE_IGNORE); + while (isdigit((unsigned char)**end)) + (*end)++; + if (start) + *start = &cp[i]; + if (sz) + *sz = *end - &cp[i]; + if ('\0' != **end) + (*end)++; + return(ESCAPE_NUMBERED); + /* * Sizes get a special category of their own. */ @@ -254,16 +226,16 @@ mandoc_escape(const char **end, const char **start, in switch (cp[i++]) { case ('('): - lim = 2; + rlim = 2; break; case ('['): - term = numeric = ']'; + term = ']'; break; case ('\''): - term = numeric = '\''; + term = '\''; break; default: - lim = 1; + rlim = 1; i--; break; } @@ -280,77 +252,61 @@ mandoc_escape(const char **end, const char **start, in */ default: gly = ESCAPE_SPECIAL; - lim = 1; + rlim = 1; i--; break; } assert(ESCAPE_ERROR != gly); - rstart = &cp[i]; + *end = rstart = &cp[i]; if (start) *start = rstart; /* - * If a terminating block has been specified, we need to - * handle the case of recursion, which could have their - * own terminating blocks that mess up our parse. This, by the - * way, means that the "start" and "size" values will be - * effectively meaningless. + * Read up to the terminating character, + * paying attention to nested escapes. */ - ssz = 0; - if (numeric && -1 == (ssz = numescape(&cp[i]))) - return(ESCAPE_ERROR); - - i += ssz; - rlim = -1; - - /* - * We have a character terminator. Try to read up to that - * character. If we can't (i.e., we hit the nil), then return - * an error; if we can, calculate our length, read past the - * terminating character, and exit. - */ - if ('\0' != term) { - *end = strchr(&cp[i], term); - if ('\0' == *end) + while (**end != term) { + switch (**end) { + case ('\0'): + return(ESCAPE_ERROR); + case ('\\'): + (*end)++; + if (ESCAPE_ERROR == + mandoc_escape(end, NULL, NULL)) + return(ESCAPE_ERROR); + break; + default: + (*end)++; + break; + } + } + rlim = (*end)++ - rstart; + } else { + assert(rlim > 0); + if ((size_t)rlim > strlen(rstart)) return(ESCAPE_ERROR); - - rlim = *end - &cp[i]; - if (sz) - *sz = rlim; - (*end)++; - goto out; + *end += rlim; } - - assert(lim > 0); - - /* - * We have a numeric limit. If the string is shorter than that, - * stop and return an error. Else adjust our endpoint, length, - * and return the current glyph. - */ - - if ((size_t)lim > strlen(&cp[i])) - return(ESCAPE_ERROR); - - rlim = lim; if (sz) *sz = rlim; - *end = &cp[i] + lim; - -out: - assert(rlim >= 0 && rstart); - /* Run post-processors. */ switch (gly) { case (ESCAPE_FONT): - if (1 != rlim) + /* + * Pretend that the constant-width font modes are the + * same as the regular font modes. + */ + if (2 == rlim && 'C' == *rstart) + rstart++; + else if (1 != rlim) break; + switch (*rstart) { case ('3'): /* FALLTHROUGH */ @@ -428,7 +384,17 @@ mandoc_realloc(void *ptr, size_t size) return(ptr); } +char * +mandoc_strndup(const char *ptr, size_t sz) +{ + char *p; + p = mandoc_malloc(sz + 1); + memcpy(p, ptr, sz); + p[(int)sz] = '\0'; + return(p); +} + char * mandoc_strdup(const char *ptr) { @@ -528,7 +494,10 @@ a2time(time_t *t, const char *fmt, const char *p) memset(&tm, 0, sizeof(struct tm)); + pp = NULL; +#ifdef HAVE_STRPTIME pp = strptime(p, fmt, &tm); +#endif if (NULL != pp && '\0' == *pp) { *t = mktime(&tm); return(1); @@ -540,12 +509,12 @@ a2time(time_t *t, const char *fmt, const char *p) static char * time2a(time_t t) { - struct tm tm; + struct tm *tm; char *buf, *p; size_t ssz; int isz; - localtime_r(&t, &tm); + tm = localtime(&t); /* * Reserve space: @@ -555,15 +524,15 @@ time2a(time_t t) */ p = buf = mandoc_malloc(10 + 4 + 4 + 1); - if (0 == (ssz = strftime(p, 10 + 1, "%B ", &tm))) + if (0 == (ssz = strftime(p, 10 + 1, "%B ", tm))) goto fail; p += (int)ssz; - if (-1 == (isz = snprintf(p, 4 + 1, "%d, ", tm.tm_mday))) + if (-1 == (isz = snprintf(p, 4 + 1, "%d, ", tm->tm_mday))) goto fail; p += isz; - if (0 == strftime(p, 4 + 1, "%Y", &tm)) + if (0 == strftime(p, 4 + 1, "%Y", tm)) goto fail; return(buf); @@ -583,9 +552,10 @@ mandoc_normdate(struct mparse *parse, char *in, int ln mandoc_msg(MANDOCERR_NODATE, parse, ln, pos, NULL); time(&t); } + else if (a2time(&t, "%Y-%m-%d", in)) + t = 0; else if (!a2time(&t, "$" "Mdocdate: %b %d %Y $", in) && - !a2time(&t, "%b %d, %Y", in) && - !a2time(&t, "%Y-%m-%d", in)) { + !a2time(&t, "%b %d, %Y", in)) { mandoc_msg(MANDOCERR_BADDATE, parse, ln, pos, NULL); t = 0; } @@ -636,33 +606,6 @@ mandoc_eos(const char *p, size_t sz, int enclosed) return(found && !enclosed); } -int -mandoc_hyph(const char *start, const char *c) -{ - - /* - * Choose whether to break at a hyphenated character. We only - * do this if it's free-standing within a word. - */ - - /* Skip first/last character of buffer. */ - if (c == start || '\0' == *(c + 1)) - return(0); - /* Skip first/last character of word. */ - if ('\t' == *(c + 1) || '\t' == *(c - 1)) - return(0); - if (' ' == *(c + 1) || ' ' == *(c - 1)) - return(0); - /* Skip double invocations. */ - if ('-' == *(c + 1) || '-' == *(c - 1)) - return(0); - /* Skip escapes. */ - if ('\\' == *(c - 1)) - return(0); - - return(1); -} - /* * Find out whether a line is a macro line or not. If it is, adjust the * current position and return one; if it isn't, return zero and don't @@ -694,7 +637,7 @@ mandoc_getcontrol(const char *cp, int *ppos) * If the string is invalid, or is less than 0, return -1. */ int -mandoc_strntou(const char *p, size_t sz, int base) +mandoc_strntoi(const char *p, size_t sz, int base) { char buf[32]; char *ep; @@ -704,7 +647,7 @@ mandoc_strntou(const char *p, size_t sz, int base) return(-1); memcpy(buf, p, sz); - buf[sz] = '\0'; + buf[(int)sz] = '\0'; errno = 0; v = strtol(buf, &ep, base); @@ -712,11 +655,10 @@ mandoc_strntou(const char *p, size_t sz, int base) if (buf[0] == '\0' || *ep != '\0') return(-1); - if ((errno == ERANGE && - (v == LONG_MAX || v == LONG_MIN)) || - (v > INT_MAX || v < 0)) - return(-1); + if (v > INT_MAX) + v = INT_MAX; + if (v < INT_MIN) + v = INT_MIN; return((int)v); } -