=================================================================== RCS file: /cvs/mandoc/mandoc.c,v retrieving revision 1.49 retrieving revision 1.113 diff -u -p -r1.49 -r1.113 --- mandoc/mandoc.c 2011/04/30 10:18:24 1.49 +++ mandoc/mandoc.c 2018/12/18 22:00:02 1.113 @@ -1,7 +1,7 @@ -/* $Id: mandoc.c,v 1.49 2011/04/30 10:18:24 kristaps Exp $ */ +/* $Id: mandoc.c,v 1.113 2018/12/18 22:00:02 schwarze Exp $ */ /* - * Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons - * Copyright (c) 2011 Ingo Schwarze + * Copyright (c) 2008-2011, 2014 Kristaps Dzonsons + * Copyright (c) 2011-2015, 2017, 2018 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 @@ -15,509 +15,456 @@ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#ifdef HAVE_CONFIG_H #include "config.h" -#endif #include #include #include +#include +#include #include #include #include #include +#include "mandoc_aux.h" #include "mandoc.h" +#include "roff.h" #include "libmandoc.h" -#define DATESIZE 32 - 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_font(const char *cp, int sz) { - int i; - size_t sz; - const char *cp; + switch (sz) { + case 0: + return ESCAPE_FONTPREV; + case 1: + switch (cp[0]) { + case 'B': + case '3': + return ESCAPE_FONTBOLD; + case 'I': + case '2': + return ESCAPE_FONTITALIC; + case 'P': + return ESCAPE_FONTPREV; + case 'R': + case '1': + return ESCAPE_FONTROMAN; + case '4': + return ESCAPE_FONTBI; + default: + return ESCAPE_ERROR; + } + case 2: + switch (cp[0]) { + case 'B': + switch (cp[1]) { + case 'I': + return ESCAPE_FONTBI; + default: + return ESCAPE_ERROR; + } + case 'C': + switch (cp[1]) { + case 'B': + return ESCAPE_FONTBOLD; + case 'I': + return ESCAPE_FONTITALIC; + case 'R': + case 'W': + return ESCAPE_FONTCW; + default: + return ESCAPE_ERROR; + } + default: + return ESCAPE_ERROR; + } + default: + return ESCAPE_ERROR; + } +} - i = 0; +enum mandoc_esc +mandoc_escape(const char **end, const char **start, int *sz) +{ + const char *local_start; + int local_sz, c, i; + char term; + enum mandoc_esc gly; - /* The expression consists of a subexpression. */ + /* + * When the caller doesn't provide return storage, + * use local storage. + */ - 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 (NULL == start) + start = &local_start; + if (NULL == sz) + sz = &local_sz; - 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. + * Treat "\E" just like "\"; + * it only makes a difference in copy mode. */ - while (')' != start[i]) { - sz = strcspn(&start[i], ")\\"); - i += (int)sz; + if (**end == 'E') + ++*end; - if ('\0' == start[i]) - return(-1); - else if ('\\' != start[i]) - continue; + /* + * 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. + */ - 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 * name. */ - case ('('): + case '(': gly = ESCAPE_SPECIAL; - lim = 2; + *sz = 2; break; - case ('['): + case '[': + if (**start == ' ') { + ++*end; + return ESCAPE_ERROR; + } gly = ESCAPE_SPECIAL; term = ']'; break; - case ('C'): - if ('\'' != cp[i]) - return(ESCAPE_ERROR); + case 'C': + if ('\'' != **start) + return ESCAPE_ERROR; + *start = ++*end; gly = ESCAPE_SPECIAL; term = '\''; break; /* - * Handle all triggers matching \X(xy, \Xx, and \X[xxxx], where - * 'X' is the trigger. These have opaque sub-strings. + * Escapes taking no arguments at all. */ - case ('F'): - /* FALLTHROUGH */ - case ('g'): - /* FALLTHROUGH */ - case ('k'): - /* FALLTHROUGH */ - case ('M'): - /* FALLTHROUGH */ - case ('m'): - /* FALLTHROUGH */ - case ('n'): - /* FALLTHROUGH */ - case ('V'): - /* FALLTHROUGH */ - case ('Y'): - if (ESCAPE_ERROR == gly) - gly = ESCAPE_IGNORE; - /* FALLTHROUGH */ - case ('*'): - if (ESCAPE_ERROR == gly) - gly = ESCAPE_PREDEF; - /* FALLTHROUGH */ - case ('f'): - if (ESCAPE_ERROR == gly) - gly = ESCAPE_FONT; + case '!': + case '?': + return ESCAPE_UNSUPP; + case '%': + case '&': + case ')': + case ',': + case '/': + case '^': + case 'a': + case 'd': + case 'r': + case 't': + case 'u': + case '{': + case '|': + case '}': + return ESCAPE_IGNORE; + case 'c': + return ESCAPE_NOSPACE; + case 'p': + return ESCAPE_BREAK; - rstart= &cp[i]; - if (start) - *start = rstart; + /* + * 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; - switch (cp[i++]) { - case ('('): - lim = 2; + /* + * Handle all triggers matching \X(xy, \Xx, and \X[xxxx], where + * 'X' is the trigger. These have opaque sub-strings. + */ + case 'F': + case 'f': + case 'g': + case 'k': + case 'M': + case 'm': + case 'n': + case 'O': + case 'V': + case 'Y': + gly = (*start)[-1] == 'f' ? ESCAPE_FONT : ESCAPE_IGNORE; + switch (**start) { + case '(': + if ((*start)[-1] == 'O') + gly = ESCAPE_ERROR; + *start = ++*end; + *sz = 2; break; - case ('['): + case '[': + if ((*start)[-1] == 'O') + gly = (*start)[1] == '5' ? + ESCAPE_UNSUPP : ESCAPE_ERROR; + *start = ++*end; term = ']'; break; default: - lim = 1; - i--; + if ((*start)[-1] == 'O') { + switch (**start) { + case '0': + gly = ESCAPE_UNSUPP; + break; + case '1': + case '2': + case '3': + case '4': + break; + default: + gly = ESCAPE_ERROR; + break; + } + } + *sz = 1; break; } break; + case '*': + if (strncmp(*start, "(.T", 3) != 0) + abort(); + gly = ESCAPE_DEVICE; + *start = ++*end; + *sz = 2; + break; /* * These escapes are of the form \X'Y', where 'X' is the trigger * and 'Y' is any string. These have opaque sub-strings. + * The \B and \w escapes are handled in roff.c, roff_res(). */ - case ('A'): - /* FALLTHROUGH */ - case ('b'): - /* FALLTHROUGH */ - case ('D'): - /* FALLTHROUGH */ - case ('o'): - /* FALLTHROUGH */ - case ('R'): - /* FALLTHROUGH */ - case ('X'): - /* FALLTHROUGH */ - case ('Z'): - if ('\'' != cp[i++]) - return(ESCAPE_ERROR); + case 'A': + case 'b': + case 'D': + case 'R': + case 'X': + case 'Z': gly = ESCAPE_IGNORE; - term = '\''; + /* FALLTHROUGH */ + case 'o': + if (**start == '\0') + return ESCAPE_ERROR; + if (gly == ESCAPE_ERROR) + gly = ESCAPE_OVERSTRIKE; + term = **start; + *start = ++*end; break; /* * These escapes are of the form \X'N', where 'X' is the trigger * and 'N' resolves to a numerical expression. */ - case ('B'): - /* FALLTHROUGH */ - case ('h'): - /* FALLTHROUGH */ - case ('H'): - /* FALLTHROUGH */ - case ('L'): - /* FALLTHROUGH */ - case ('l'): - /* FALLTHROUGH */ - case ('N'): - if (ESCAPE_ERROR == gly) - gly = ESCAPE_NUMBERED; - /* FALLTHROUGH */ - case ('S'): - /* FALLTHROUGH */ - case ('v'): - /* FALLTHROUGH */ - case ('w'): - /* FALLTHROUGH */ - case ('x'): - if (ESCAPE_ERROR == gly) + case 'h': + case 'H': + case 'L': + case 'l': + case 'S': + case 'v': + case 'x': + if (strchr(" %&()*+-./0123456789:<=>", **start)) { + if ('\0' != **start) + ++*end; + return ESCAPE_ERROR; + } + switch ((*start)[-1]) { + case 'h': + gly = ESCAPE_HORIZ; + break; + case 'l': + gly = ESCAPE_HLINE; + break; + default: gly = ESCAPE_IGNORE; - if ('\'' != cp[i++]) - return(ESCAPE_ERROR); - term = numeric = '\''; + break; + } + term = **start; + *start = ++*end; 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'): + 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) + *start = ++*end; - switch (cp[i++]) { - case ('('): - lim = 2; + switch (**end) { + case '(': + *start = ++*end; + *sz = 2; break; - case ('['): - term = numeric = ']'; + case '[': + *start = ++*end; + term = ']'; break; - case ('\''): - term = numeric = '\''; + case '\'': + *start = ++*end; + term = '\''; break; + case '3': + case '2': + case '1': + *sz = (*end)[-1] == 's' && + isdigit((unsigned char)(*end)[1]) ? 2 : 1; + 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. + * Several special characters can be encoded as + * one-byte escape sequences without using \[]. */ - default: + case ' ': + case '\'': + case '-': + case '.': + case '0': + case ':': + case '_': + case '`': + case 'e': + case '~': gly = ESCAPE_SPECIAL; - lim = 1; - i--; + /* FALLTHROUGH */ + default: + if (gly == ESCAPE_ERROR) + gly = ESCAPE_UNDEF; + *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) - return(ESCAPE_ERROR); + 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; - rlim = *end - &cp[i]; - if (sz) - *sz = rlim; - (*end)++; - goto out; + /* + * The file chars.c only provides one common list + * of character names, but \[-] == \- is the only + * one of the characters with one-byte names that + * allows enclosing the name in brackets. + */ + if (gly == ESCAPE_SPECIAL && *sz == 1 && **start != '-') + return ESCAPE_ERROR; + } else { + assert(*sz > 0); + if ((size_t)*sz > strlen(*start)) + return ESCAPE_ERROR; + *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) + case ESCAPE_FONT: + gly = mandoc_font(*start, *sz); + break; + case ESCAPE_SPECIAL: + if (**start == 'c') { + if (*sz < 6 || *sz > 7 || + strncmp(*start, "char", 4) != 0 || + (int)strspn(*start + 4, "0123456789") + 4 < *sz) + break; + c = 0; + for (i = 4; i < *sz; i++) + c = 10 * c + ((*start)[i] - '0'); + if (c < 0x21 || (c > 0x7e && c < 0xa0) || c > 0xff) + break; + *start += 4; + *sz -= 4; + gly = ESCAPE_NUMBERED; break; - switch (*rstart) { - case ('3'): - /* FALLTHROUGH */ - case ('B'): - gly = ESCAPE_FONTBOLD; + } + + /* + * Unicode escapes are defined in groff as \[u0000] + * to \[u10FFFF], where the contained value must be + * a valid Unicode codepoint. Here, however, only + * check the length and range. + */ + if (**start != 'u' || *sz < 5 || *sz > 7) break; - case ('2'): - /* FALLTHROUGH */ - case ('I'): - gly = ESCAPE_FONTITALIC; + if (*sz == 7 && ((*start)[1] != '1' || (*start)[2] != '0')) break; - case ('P'): - gly = ESCAPE_FONTPREV; + if (*sz == 6 && (*start)[1] == '0') break; - case ('1'): - /* FALLTHROUGH */ - case ('R'): - gly = ESCAPE_FONTROMAN; + if (*sz == 5 && (*start)[1] == 'D' && + strchr("89ABCDEF", (*start)[2]) != NULL) break; - } + if ((int)strspn(*start + 1, "0123456789ABCDEFabcdef") + + 1 == *sz) + gly = ESCAPE_UNICODE; break; - case (ESCAPE_SPECIAL): - if (1 != rlim) - break; - if ('c' == *rstart) - gly = ESCAPE_NOSPACE; - break; default: break; } - return(gly); + return gly; } -void * -mandoc_calloc(size_t num, size_t size) -{ - void *ptr; - - ptr = calloc(num, size); - if (NULL == ptr) { - perror(NULL); - exit((int)MANDOCLEVEL_SYSERR); - } - - return(ptr); -} - - -void * -mandoc_malloc(size_t size) -{ - void *ptr; - - ptr = malloc(size); - if (NULL == ptr) { - perror(NULL); - exit((int)MANDOCLEVEL_SYSERR); - } - - return(ptr); -} - - -void * -mandoc_realloc(void *ptr, size_t size) -{ - - ptr = realloc(ptr, size); - if (NULL == ptr) { - perror(NULL); - exit((int)MANDOCLEVEL_SYSERR); - } - - return(ptr); -} - - -char * -mandoc_strdup(const char *ptr) -{ - char *p; - - p = strdup(ptr); - if (NULL == p) { - perror(NULL); - exit((int)MANDOCLEVEL_SYSERR); - } - - return(p); -} - -/* - * Parse a quoted or unquoted roff-style request or macro argument. - * Return a pointer to the parsed argument, which is either the original - * pointer or advanced by one byte in case the argument is quoted. - * Null-terminate the argument in place. - * Collapse pairs of quotes inside quoted arguments. - * Advance the argument pointer to the next argument, - * or to the null byte terminating the argument line. - */ -char * -mandoc_getarg(struct mparse *parse, char **cpp, int ln, int *pos) -{ - char *start, *cp; - int quoted, pairs, white; - - /* Quoting can only start with a new word. */ - start = *cpp; - quoted = 0; - if ('"' == *start) { - quoted = 1; - start++; - } - - pairs = 0; - white = 0; - for (cp = start; '\0' != *cp; cp++) { - /* Move left after quoted quotes and escaped backslashes. */ - if (pairs) - cp[-pairs] = cp[0]; - if ('\\' == cp[0]) { - if ('\\' == cp[1]) { - /* Poor man's copy mode. */ - pairs++; - cp++; - } else if (0 == quoted && ' ' == cp[1]) - /* Skip escaped blanks. */ - cp++; - } else if (0 == quoted) { - if (' ' == cp[0]) { - /* Unescaped blanks end unquoted args. */ - white = 1; - break; - } - } else if ('"' == cp[0]) { - if ('"' == cp[1]) { - /* Quoted quotes collapse. */ - pairs++; - cp++; - } else { - /* Unquoted quotes end quoted args. */ - quoted = 2; - break; - } - } - } - - /* Quoted argument without a closing quote. */ - if (1 == quoted) - mandoc_msg(MANDOCERR_BADQUOTE, parse, ln, *pos, NULL); - - /* Null-terminate this argument and move to the next one. */ - if (pairs) - cp[-pairs] = '\0'; - if ('\0' != *cp) { - *cp++ = '\0'; - while (' ' == *cp) - cp++; - } - *pos += (int)(cp - start) + (quoted ? 1 : 0); - *cpp = cp; - - if ('\0' == *cp && (white || ' ' == cp[-1])) - mandoc_msg(MANDOCERR_EOLNSPACE, parse, ln, *pos, NULL); - - return(start); -} - static int a2time(time_t *t, const char *fmt, const char *p) { @@ -526,24 +473,29 @@ a2time(time_t *t, const char *fmt, const char *p) memset(&tm, 0, sizeof(struct tm)); + pp = NULL; +#if HAVE_STRPTIME pp = strptime(p, fmt, &tm); +#endif if (NULL != pp && '\0' == *pp) { *t = mktime(&tm); - return(1); + return 1; } - return(0); + return 0; } 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); + if (tm == NULL) + return NULL; /* * Reserve space: @@ -551,54 +503,82 @@ time2a(time_t t) * up to 2 characters for the day + comma + blank * 4 characters for the year and a terminating '\0' */ + p = buf = mandoc_malloc(10 + 4 + 4 + 1); - if (0 == (ssz = strftime(p, 10 + 1, "%B ", &tm))) + if ((ssz = strftime(p, 10 + 1, "%B ", tm)) == 0) goto fail; p += (int)ssz; - if (-1 == (isz = snprintf(p, 4 + 1, "%d, ", tm.tm_mday))) + /* + * The output format is just "%d" here, not "%2d" or "%02d". + * That's also the reason why we can't just format the + * date as a whole with "%B %e, %Y" or "%B %d, %Y". + * Besides, the present approach is less prone to buffer + * overflows, in case anybody should ever introduce the bug + * of looking at LC_TIME. + */ + + if ((isz = snprintf(p, 4 + 1, "%d, ", tm->tm_mday)) == -1) goto fail; p += isz; - if (0 == strftime(p, 4 + 1, "%Y", &tm)) + if (strftime(p, 4 + 1, "%Y", tm) == 0) goto fail; - return(buf); + return buf; fail: free(buf); - return(NULL); + return NULL; } char * -mandoc_normdate(struct mparse *parse, char *in, int ln, int pos) +mandoc_normdate(struct roff_man *man, char *in, int ln, int pos) { - char *out; + char *cp; time_t t; - if (NULL == in || '\0' == *in || - 0 == strcmp(in, "$" "Mdocdate$")) { - mandoc_msg(MANDOCERR_NODATE, parse, ln, pos, NULL); - time(&t); + /* No date specified: use today's date. */ + + if (in == NULL || *in == '\0' || strcmp(in, "$" "Mdocdate$") == 0) { + mandoc_msg(MANDOCERR_DATE_MISSING, ln, pos, NULL); + return time2a(time(NULL)); } - else if (!a2time(&t, "$" "Mdocdate: %b %d %Y $", in) && - !a2time(&t, "%b %d, %Y", in) && - !a2time(&t, "%Y-%m-%d", in)) { - mandoc_msg(MANDOCERR_BADDATE, parse, ln, pos, NULL); - t = 0; + + /* Valid mdoc(7) date format. */ + + if (a2time(&t, "$" "Mdocdate: %b %d %Y $", in) || + a2time(&t, "%b %d, %Y", in)) { + cp = time2a(t); + if (t > time(NULL) + 86400) + mandoc_msg(MANDOCERR_DATE_FUTURE, ln, pos, "%s", cp); + else if (*in != '$' && strcmp(in, cp) != 0) + mandoc_msg(MANDOCERR_DATE_NORM, ln, pos, "%s", cp); + return cp; } - out = t ? time2a(t) : NULL; - return(out ? out : mandoc_strdup(in)); + + /* In man(7), do not warn about the legacy format. */ + + if (a2time(&t, "%Y-%m-%d", in) == 0) + mandoc_msg(MANDOCERR_DATE_BAD, ln, pos, "%s", in); + else if (t > time(NULL) + 86400) + mandoc_msg(MANDOCERR_DATE_FUTURE, ln, pos, "%s", in); + else if (man->macroset == MACROSET_MDOC) + mandoc_msg(MANDOCERR_DATE_LEGACY, ln, pos, "Dd %s", in); + + /* Use any non-mdoc(7) date verbatim. */ + + return mandoc_strdup(in); } int -mandoc_eos(const char *p, size_t sz, int enclosed) +mandoc_eos(const char *p, size_t sz) { - const char *q; - int found; + const char *q; + int enclosed, found; if (0 == sz) - return(0); + return 0; /* * End-of-sentence recognition must include situations where @@ -606,83 +586,57 @@ mandoc_eos(const char *p, size_t sz, int enclosed) * propagate outward. */ - found = 0; + enclosed = found = 0; for (q = p + (int)sz - 1; q >= p; q--) { switch (*q) { - case ('\"'): - /* FALLTHROUGH */ - case ('\''): - /* FALLTHROUGH */ - case (']'): - /* FALLTHROUGH */ - case (')'): + case '\"': + case '\'': + case ']': + case ')': if (0 == found) enclosed = 1; break; - case ('.'): - /* FALLTHROUGH */ - case ('!'): - /* FALLTHROUGH */ - case ('?'): + case '.': + case '!': + case '?': found = 1; break; default: - return(found && (!enclosed || isalnum((unsigned char)*q))); + return found && + (!enclosed || isalnum((unsigned char)*q)); } } - return(found && !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 - * change the current position. + * 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_getcontrol(const char *cp, int *ppos) +mandoc_strntoi(const char *p, size_t sz, int base) { - int pos; + char buf[32]; + char *ep; + long v; - pos = *ppos; + if (sz > 31) + return -1; - if ('\\' == cp[pos] && '.' == cp[pos + 1]) - pos += 2; - else if ('.' == cp[pos] || '\'' == cp[pos]) - pos++; - else - return(0); + memcpy(buf, p, sz); + buf[(int)sz] = '\0'; - while (' ' == cp[pos] || '\t' == cp[pos]) - pos++; + errno = 0; + v = strtol(buf, &ep, base); - *ppos = pos; - return(1); + 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; }