=================================================================== RCS file: /cvs/mandoc/mandoc.c,v retrieving revision 1.49 retrieving revision 1.65 diff -u -p -r1.49 -r1.65 --- mandoc/mandoc.c 2011/04/30 10:18:24 1.49 +++ mandoc/mandoc.c 2012/05/31 22:38:16 1.65 @@ -1,7 +1,7 @@ -/* $Id: mandoc.c,v 1.49 2011/04/30 10:18:24 kristaps Exp $ */ +/* $Id: mandoc.c,v 1.65 2012/05/31 22:38:16 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 @@ -23,6 +23,8 @@ #include #include +#include +#include #include #include #include @@ -35,83 +37,38 @@ 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) + +enum mandoc_esc +mandoc_escape(const char **end, const char **start, int *sz) { - int i; - size_t sz; - const char *cp; + const char *local_start; + int local_sz; + char term; + enum mandoc_esc gly; - i = 0; + /* + * When the caller doesn't provide return storage, + * use local storage. + */ - /* The expression consists of a subexpression. */ + if (NULL == start) + start = &local_start; + if (NULL == sz) + sz = &local_sz; - 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. + * Beyond the backslash, at least one input character + * is part of the escape sequence. With one exception + * (see below), that character won't be returned. */ - 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; - const char *cp, *rstart; - enum mandoc_esc gly; - - cp = *end; - rstart = cp; - if (start) - *start = rstart; - i = lim = 0; gly = ESCAPE_ERROR; - term = numeric = '\0'; + *start = ++*end; + *sz = 0; + term = '\0'; - switch ((c = cp[i++])) { + switch ((*start)[-1]) { /* * First the glyphs. There are several different forms of * these, but each eventually returns a substring of the glyph @@ -119,20 +76,38 @@ mandoc_escape(const char **end, const char **start, in */ case ('('): gly = ESCAPE_SPECIAL; - lim = 2; + *sz = 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' == (*start)[0] && ']' != (*start)[1]) + gly = ESCAPE_UNICODE; term = ']'; break; case ('C'): - if ('\'' != cp[i]) + if ('\'' != **start) return(ESCAPE_ERROR); gly = ESCAPE_SPECIAL; + *start = ++*end; term = '\''; 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'): + return(ESCAPE_SKIPCHAR); + + /* * Handle all triggers matching \X(xy, \Xx, and \X[xxxx], where * 'X' is the trigger. These have opaque sub-strings. */ @@ -151,31 +126,22 @@ 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; - - rstart= &cp[i]; - if (start) - *start = rstart; - - switch (cp[i++]) { + switch (**start) { case ('('): - lim = 2; + *start = ++*end; + *sz = 2; break; case ('['): + *start = ++*end; term = ']'; break; default: - lim = 1; - i--; + *sz = 1; break; } break; @@ -197,9 +163,10 @@ mandoc_escape(const char **end, const char **start, in case ('X'): /* FALLTHROUGH */ case ('Z'): - if ('\'' != cp[i++]) + if ('\'' != **start) return(ESCAPE_ERROR); gly = ESCAPE_IGNORE; + *start = ++*end; term = '\''; break; @@ -216,11 +183,8 @@ 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'): @@ -228,128 +192,121 @@ mandoc_escape(const char **end, const char **start, in case ('w'): /* FALLTHROUGH */ case ('x'): + if ('\'' != **start) + return(ESCAPE_ERROR); if (ESCAPE_ERROR == gly) gly = ESCAPE_IGNORE; - if ('\'' != cp[i++]) - return(ESCAPE_ERROR); - term = numeric = '\''; + *start = ++*end; + term = '\''; break; + /* + * Special handling for the numbered character escape. + * XXX Do any other escapes need similar handling? + */ + case ('N'): + if ('\0' == **start) + return(ESCAPE_ERROR); + (*end)++; + if (isdigit((unsigned char)**start)) { + *sz = 1; + return(ESCAPE_IGNORE); + } + (*start)++; + while (isdigit((unsigned char)**end)) + (*end)++; + *sz = *end - *start; + if ('\0' != **end) + (*end)++; + return(ESCAPE_NUMBERED); + /* * Sizes get a special category of their own. */ case ('s'): gly = ESCAPE_IGNORE; - rstart = &cp[i]; - if (start) - *start = rstart; - /* See +/- counts as a sign. */ - c = cp[i]; - if ('+' == c || '-' == c || ASCII_HYPH == c) - ++i; + if ('+' == **end || '-' == **end || ASCII_HYPH == **end) + (*end)++; - switch (cp[i++]) { + switch (**end) { case ('('): - lim = 2; + *start = ++*end; + *sz = 2; break; case ('['): - term = numeric = ']'; + *start = ++*end; + term = ']'; break; case ('\''): - term = numeric = '\''; + *start = ++*end; + term = '\''; break; default: - lim = 1; - i--; + *sz = 1; break; } - /* See +/- counts as a sign. */ - c = cp[i]; - if ('+' == c || '-' == c || ASCII_HYPH == c) - ++i; - break; /* * Anything else is assumed to be a glyph. + * In this case, pass back the character after the backslash. */ default: gly = ESCAPE_SPECIAL; - lim = 1; - i--; + *start = --*end; + *sz = 1; break; } assert(ESCAPE_ERROR != gly); - 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; + } + } + *sz = (*end)++ - *start; + } else { + assert(*sz > 0); + if ((size_t)*sz > strlen(*start)) return(ESCAPE_ERROR); - - rlim = *end - &cp[i]; - if (sz) - *sz = rlim; - (*end)++; - goto out; + *end += *sz; } - 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 == *sz && 'C' == **start) { + (*start)++; + (*sz)--; + } else if (1 != *sz) break; - switch (*rstart) { + + switch (**start) { case ('3'): /* FALLTHROUGH */ case ('B'): @@ -371,9 +328,7 @@ out: } break; case (ESCAPE_SPECIAL): - if (1 != rlim) - break; - if ('c' == *rstart) + if (1 == *sz && 'c' == **start) gly = ESCAPE_NOSPACE; break; default: @@ -426,7 +381,17 @@ 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) { @@ -526,7 +491,10 @@ 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); @@ -538,12 +506,12 @@ 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: @@ -553,15 +521,15 @@ 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); @@ -581,9 +549,10 @@ 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; } @@ -634,33 +603,6 @@ 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 @@ -685,4 +627,35 @@ mandoc_getcontrol(const char *cp, int *ppos) *ppos = pos; return(1); +} + +/* + * Convert a string to a long that may not be <0. + * If the string is invalid, or is less than 0, return -1. + */ +int +mandoc_strntoi(const char *p, size_t sz, int base) +{ + char buf[32]; + char *ep; + long v; + + if (sz > 31) + return(-1); + + memcpy(buf, p, sz); + buf[(int)sz] = '\0'; + + errno = 0; + v = strtol(buf, &ep, base); + + if (buf[0] == '\0' || *ep != '\0') + return(-1); + + if (v > INT_MAX) + v = INT_MAX; + if (v < INT_MIN) + v = INT_MIN; + + return((int)v); }