-/* $Id: mandoc.c,v 1.72 2013/12/25 22:45:33 schwarze Exp $ */
+/* $Id: mandoc.c,v 1.97 2015/10/15 23:35:55 schwarze Exp $ */
/*
- * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
- * Copyright (c) 2011, 2012, 2013 Ingo Schwarze <schwarze@openbsd.org>
+ * Copyright (c) 2008-2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
+ * Copyright (c) 2011-2015 Ingo Schwarze <schwarze@openbsd.org>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* 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 <sys/types.h>
#include <time.h>
#include "mandoc.h"
+#include "mandoc_aux.h"
#include "libmandoc.h"
-#define DATESIZE 32
-
static int a2time(time_t *, const char *, const char *);
static char *time2a(time_t);
enum mandoc_esc
-mandoc_escape(const char const **end, const char const **start, int *sz)
+mandoc_escape(const char **end, const char **start, int *sz)
{
const char *local_start;
int local_sz;
char term;
- enum mandoc_esc gly;
+ enum mandoc_esc gly;
/*
* When the caller doesn't provide return storage,
* these, but each eventually returns a substring of the glyph
* name.
*/
- case ('('):
+ case '(':
gly = ESCAPE_SPECIAL;
*sz = 2;
break;
- case ('['):
+ 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'):
+ case 'C':
if ('\'' != **start)
- return(ESCAPE_ERROR);
+ return ESCAPE_ERROR;
*start = ++*end;
- if ('u' == (*start)[0] && '\'' != (*start)[1])
- gly = ESCAPE_UNICODE;
- else
- gly = ESCAPE_SPECIAL;
+ gly = ESCAPE_SPECIAL;
term = '\'';
break;
/*
* Escapes taking no arguments at all.
*/
- case ('d'):
- /* FALLTHROUGH */
- case ('u'):
- return(ESCAPE_IGNORE);
+ case 'd':
+ case 'u':
+ case ',':
+ case '/':
+ return ESCAPE_IGNORE;
/*
* The \z escape is supposed to output the following
- * character without advancing the cursor position.
+ * 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);
+ 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.
*/
- case ('F'):
- /* FALLTHROUGH */
- case ('g'):
- /* FALLTHROUGH */
- case ('k'):
- /* FALLTHROUGH */
- case ('M'):
- /* FALLTHROUGH */
- case ('m'):
- /* FALLTHROUGH */
- case ('n'):
- /* FALLTHROUGH */
- case ('V'):
- /* FALLTHROUGH */
- case ('Y'):
+ case 'F':
+ case 'g':
+ case 'k':
+ case 'M':
+ case 'm':
+ case 'n':
+ case 'V':
+ case 'Y':
gly = ESCAPE_IGNORE;
/* FALLTHROUGH */
- case ('f'):
+ case 'f':
if (ESCAPE_ERROR == gly)
gly = ESCAPE_FONT;
switch (**start) {
- case ('('):
+ case '(':
*start = ++*end;
*sz = 2;
break;
- case ('['):
+ case '[':
*start = ++*end;
term = ']';
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 ('\'' != **start)
- return(ESCAPE_ERROR);
+ case 'A':
+ case 'b':
+ case 'D':
+ case 'R':
+ case 'X':
+ case 'Z':
gly = ESCAPE_IGNORE;
+ /* FALLTHROUGH */
+ case 'o':
+ if (**start == '\0')
+ return ESCAPE_ERROR;
+ if (gly == ESCAPE_ERROR)
+ gly = ESCAPE_OVERSTRIKE;
+ term = **start;
*start = ++*end;
- term = '\'';
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'):
- gly = ESCAPE_NUMBERED;
- /* FALLTHROUGH */
- case ('S'):
- /* FALLTHROUGH */
- case ('v'):
- /* FALLTHROUGH */
- case ('w'):
- /* FALLTHROUGH */
- case ('x'):
- if ('\'' != **start)
- return(ESCAPE_ERROR);
- if (ESCAPE_ERROR == gly)
- gly = ESCAPE_IGNORE;
+ 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;
+ }
+ gly = ESCAPE_IGNORE;
+ term = **start;
*start = ++*end;
- term = '\'';
break;
/*
* Special handling for the numbered character escape.
* XXX Do any other escapes need similar handling?
*/
- case ('N'):
+ case 'N':
if ('\0' == **start)
- return(ESCAPE_ERROR);
+ return ESCAPE_ERROR;
(*end)++;
if (isdigit((unsigned char)**start)) {
*sz = 1;
- return(ESCAPE_IGNORE);
+ return ESCAPE_IGNORE;
}
(*start)++;
while (isdigit((unsigned char)**end))
*sz = *end - *start;
if ('\0' != **end)
(*end)++;
- return(ESCAPE_NUMBERED);
+ return ESCAPE_NUMBERED;
- /*
+ /*
* Sizes get a special category of their own.
*/
- case ('s'):
+ case 's':
gly = ESCAPE_IGNORE;
/* See +/- counts as a sign. */
if ('+' == **end || '-' == **end || ASCII_HYPH == **end)
- (*end)++;
+ *start = ++*end;
switch (**end) {
- case ('('):
+ case '(':
*start = ++*end;
*sz = 2;
break;
- case ('['):
+ case '[':
*start = ++*end;
term = ']';
break;
- case ('\''):
+ case '\'':
*start = ++*end;
term = '\'';
break;
+ case '3':
+ case '2':
+ case '1':
+ *sz = (*end)[-1] == 's' &&
+ isdigit((unsigned char)(*end)[1]) ? 2 : 1;
+ break;
default:
*sz = 1;
break;
if ('\0' != term) {
while (**end != term) {
switch (**end) {
- case ('\0'):
- return(ESCAPE_ERROR);
- case ('\\'):
+ case '\0':
+ return ESCAPE_ERROR;
+ case '\\':
(*end)++;
if (ESCAPE_ERROR ==
mandoc_escape(end, NULL, NULL))
- return(ESCAPE_ERROR);
+ return ESCAPE_ERROR;
break;
default:
(*end)++;
} else {
assert(*sz > 0);
if ((size_t)*sz > strlen(*start))
- return(ESCAPE_ERROR);
+ return ESCAPE_ERROR;
*end += *sz;
}
/* Run post-processors. */
switch (gly) {
- case (ESCAPE_FONT):
+ case ESCAPE_FONT:
if (2 == *sz) {
if ('C' == **start) {
/*
break;
switch (**start) {
- case ('3'):
- /* FALLTHROUGH */
- case ('B'):
+ case '3':
+ case 'B':
gly = ESCAPE_FONTBOLD;
break;
- case ('2'):
- /* FALLTHROUGH */
- case ('I'):
+ case '2':
+ case 'I':
gly = ESCAPE_FONTITALIC;
break;
- case ('P'):
+ case 'P':
gly = ESCAPE_FONTPREV;
break;
- case ('1'):
- /* FALLTHROUGH */
- case ('R'):
+ case '1':
+ case 'R':
gly = ESCAPE_FONTROMAN;
break;
}
break;
- case (ESCAPE_SPECIAL):
+ case ESCAPE_SPECIAL:
if (1 == *sz && 'c' == **start)
gly = ESCAPE_NOSPACE;
+ /*
+ * 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;
+ if (*sz == 7 && ((*start)[1] != '1' || (*start)[2] != '0'))
+ break;
+ if (*sz == 6 && (*start)[1] == '0')
+ break;
+ if (*sz == 5 && (*start)[1] == 'D' &&
+ strchr("89ABCDEF", (*start)[2]) != NULL)
+ break;
+ if ((int)strspn(*start + 1, "0123456789ABCDEFabcdef")
+ + 1 == *sz)
+ gly = ESCAPE_UNICODE;
break;
default:
break;
}
- 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_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)
-{
- char *p;
-
- p = strdup(ptr);
- if (NULL == p) {
- perror(NULL);
- exit((int)MANDOCLEVEL_SYSERR);
- }
-
- return(p);
+ return gly;
}
/*
if ('"' == *start) {
quoted = 1;
start++;
- }
+ }
pairs = 0;
white = 0;
* backslashes and backslash-t to literal tabs.
*/
switch (cp[1]) {
- case ('t'):
+ case 't':
cp[0] = '\t';
/* FALLTHROUGH */
- case ('\\'):
+ case '\\':
pairs++;
cp++;
break;
- case (' '):
+ case ' ':
/* Skip escaped blanks. */
if (0 == quoted)
cp++;
/* Quoted argument without a closing quote. */
if (1 == quoted)
- mandoc_msg(MANDOCERR_BADQUOTE, parse, ln, *pos, NULL);
+ mandoc_msg(MANDOCERR_ARG_QUOTE, parse, ln, *pos, NULL);
/* NUL-terminate this argument and move to the next one. */
if (pairs)
*cpp = cp;
if ('\0' == *cp && (white || ' ' == cp[-1]))
- mandoc_msg(MANDOCERR_EOLNSPACE, parse, ln, *pos, NULL);
+ mandoc_msg(MANDOCERR_SPACE_EOL, parse, ln, *pos, NULL);
- return(start);
+ return start;
}
static int
memset(&tm, 0, sizeof(struct tm));
pp = NULL;
-#ifdef HAVE_STRPTIME
+#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 *
int isz;
tm = localtime(&t);
+ if (tm == NULL)
+ return NULL;
/*
* Reserve space:
if (0 == strftime(p, 4 + 1, "%Y", tm))
goto fail;
- return(buf);
+ return buf;
fail:
free(buf);
- return(NULL);
+ return NULL;
}
char *
if (NULL == in || '\0' == *in ||
0 == strcmp(in, "$" "Mdocdate$")) {
- mandoc_msg(MANDOCERR_NODATE, parse, ln, pos, NULL);
+ mandoc_msg(MANDOCERR_DATE_MISSING, 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)) {
- mandoc_msg(MANDOCERR_BADDATE, parse, ln, pos, NULL);
+ mandoc_msg(MANDOCERR_DATE_BAD, parse, ln, pos, in);
t = 0;
}
out = t ? time2a(t) : NULL;
- return(out ? out : mandoc_strdup(in));
+ return out ? out : 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
* 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;
}
/*
long v;
if (sz > 31)
- return(-1);
+ return -1;
memcpy(buf, p, sz);
buf[(int)sz] = '\0';
v = strtol(buf, &ep, base);
if (buf[0] == '\0' || *ep != '\0')
- return(-1);
+ return -1;
if (v > INT_MAX)
v = INT_MAX;
if (v < INT_MIN)
v = INT_MIN;
- return((int)v);
+ return (int)v;
}
git.ckatri.com / mandoc.git / blobdiff