-/* $Id: mandoc.c,v 1.78 2014/04/08 01:37:27 schwarze Exp $ */
+/* $Id: mandoc.c,v 1.87 2014/10/13 17:17:45 schwarze Exp $ */
/*
* Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
* Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze <schwarze@openbsd.org>
* 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>
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);
*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'):
+ case 'd':
/* FALLTHROUGH */
- case ('u'):
+ case 'u':
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'):
+ 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'):
+ case 'F':
/* FALLTHROUGH */
- case ('g'):
+ case 'g':
/* FALLTHROUGH */
- case ('k'):
+ case 'k':
/* FALLTHROUGH */
- case ('M'):
+ case 'M':
/* FALLTHROUGH */
- case ('m'):
+ case 'm':
/* FALLTHROUGH */
- case ('n'):
+ case 'n':
/* FALLTHROUGH */
- case ('V'):
+ case 'V':
/* FALLTHROUGH */
- case ('Y'):
+ 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;
* and 'Y' is any string. These have opaque sub-strings.
* The \B and \w escapes are handled in roff.c, roff_res().
*/
- case ('A'):
+ case 'A':
/* FALLTHROUGH */
- case ('b'):
+ case 'b':
/* FALLTHROUGH */
- case ('D'):
+ case 'D':
/* FALLTHROUGH */
- case ('o'):
+ case 'o':
/* FALLTHROUGH */
- case ('R'):
+ case 'R':
/* FALLTHROUGH */
- case ('X'):
+ case 'X':
/* FALLTHROUGH */
- case ('Z'):
+ case 'Z':
if ('\0' == **start)
return(ESCAPE_ERROR);
gly = ESCAPE_IGNORE;
* These escapes are of the form \X'N', where 'X' is the trigger
* and 'N' resolves to a numerical expression.
*/
- case ('h'):
+ case 'h':
/* FALLTHROUGH */
- case ('H'):
+ case 'H':
/* FALLTHROUGH */
- case ('L'):
+ case 'L':
/* FALLTHROUGH */
- case ('l'):
+ case 'l':
/* FALLTHROUGH */
- case ('S'):
+ case 'S':
/* FALLTHROUGH */
- case ('v'):
+ case 'v':
/* FALLTHROUGH */
- case ('x'):
- if (strchr("\0 %&()*+-./0123456789:<=>", **start))
+ case 'x':
+ if (strchr(" %&()*+-./0123456789:<=>", **start)) {
+ if ('\0' != **start)
+ ++*end;
return(ESCAPE_ERROR);
+ }
gly = ESCAPE_IGNORE;
term = **start;
*start = ++*end;
* 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);
(*end)++;
(*end)++;
return(ESCAPE_NUMBERED);
- /*
+ /*
* Sizes get a special category of their own.
*/
- case ('s'):
+ case 's':
gly = ESCAPE_IGNORE;
/* See +/- counts as a sign. */
(*end)++;
switch (**end) {
- case ('('):
+ case '(':
*start = ++*end;
*sz = 2;
break;
- case ('['):
+ case '[':
*start = ++*end;
term = ']';
break;
- case ('\''):
+ case '\'':
*start = ++*end;
term = '\'';
break;
if ('\0' != term) {
while (**end != term) {
switch (**end) {
- case ('\0'):
+ case '\0':
return(ESCAPE_ERROR);
- case ('\\'):
+ case '\\':
(*end)++;
if (ESCAPE_ERROR ==
mandoc_escape(end, NULL, NULL))
/* Run post-processors. */
switch (gly) {
- case (ESCAPE_FONT):
+ case ESCAPE_FONT:
if (2 == *sz) {
if ('C' == **start) {
/*
break;
switch (**start) {
- case ('3'):
+ case '3':
/* FALLTHROUGH */
- case ('B'):
+ case 'B':
gly = ESCAPE_FONTBOLD;
break;
- case ('2'):
+ case '2':
/* FALLTHROUGH */
- case ('I'):
+ case 'I':
gly = ESCAPE_FONTITALIC;
break;
- case ('P'):
+ case 'P':
gly = ESCAPE_FONTPREV;
break;
- case ('1'):
+ case '1':
/* FALLTHROUGH */
- case ('R'):
+ 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 \[uXXXX]
+ * to \[u10FFFF], where the contained value must be
+ * a valid Unicode codepoint. Here, however, only
+ * check the length and the validity of all digits.
+ */
+ else if (*sz > 4 && *sz < 8 && **start == 'u' &&
+ (int)strspn(*start + 1, "0123456789ABCDEFabcdef")
+ + 1 == *sz)
+ gly = ESCAPE_UNICODE;
break;
default:
break;
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);
}
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) {
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;
enclosed = found = 0;
for (q = p + (int)sz - 1; q >= p; q--) {
switch (*q) {
- case ('\"'):
+ case '\"':
/* FALLTHROUGH */
- case ('\''):
+ case '\'':
/* FALLTHROUGH */
- case (']'):
+ case ']':
/* FALLTHROUGH */
- case (')'):
+ case ')':
if (0 == found)
enclosed = 1;
break;
- case ('.'):
+ case '.':
/* FALLTHROUGH */
- case ('!'):
+ case '!':
/* FALLTHROUGH */
- case ('?'):
+ case '?':
found = 1;
break;
default: