-/* $Id: mandoc.c,v 1.86 2014/08/18 09:11:47 kristaps Exp $ */
+/* $Id: mandoc.c,v 1.102 2017/06/14 01:31:26 schwarze Exp $ */
/*
- * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
- * Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze <schwarze@openbsd.org>
+ * Copyright (c) 2008-2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv>
+ * Copyright (c) 2011-2015, 2017 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
#include <string.h>
#include <time.h>
-#include "mandoc.h"
#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);
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 ('\'' != **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 ',':
+ case '/':
+ return ESCAPE_IGNORE;
+ case 'p':
+ return ESCAPE_BREAK;
/*
* The \z escape is supposed to output the following
* let us just skip the next character.
*/
case 'z':
- return(ESCAPE_SKIPCHAR);
+ 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':
gly = ESCAPE_IGNORE;
/* FALLTHROUGH */
* 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 ('\0' == **start)
- return(ESCAPE_ERROR);
gly = ESCAPE_IGNORE;
+ /* FALLTHROUGH */
+ case 'o':
+ if (**start == '\0')
+ return ESCAPE_ERROR;
+ if (gly == ESCAPE_ERROR)
+ gly = ESCAPE_OVERSTRIKE;
term = **start;
*start = ++*end;
break;
* and 'N' resolves to a numerical expression.
*/
case 'h':
- /* FALLTHROUGH */
case 'H':
- /* FALLTHROUGH */
case 'L':
- /* FALLTHROUGH */
case 'l':
- /* FALLTHROUGH */
case 'S':
- /* FALLTHROUGH */
case 'v':
- /* FALLTHROUGH */
case 'x':
if (strchr(" %&()*+-./0123456789:<=>", **start)) {
if ('\0' != **start)
++*end;
- return(ESCAPE_ERROR);
+ return ESCAPE_ERROR;
+ }
+ switch ((*start)[-1]) {
+ case 'h':
+ gly = ESCAPE_HORIZ;
+ break;
+ case 'l':
+ gly = ESCAPE_HLINE;
+ break;
+ default:
+ gly = ESCAPE_IGNORE;
+ break;
}
- gly = ESCAPE_IGNORE;
term = **start;
*start = ++*end;
break;
*/
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.
/* See +/- counts as a sign. */
if ('+' == **end || '-' == **end || ASCII_HYPH == **end)
- (*end)++;
+ *start = ++*end;
switch (**end) {
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;
while (**end != term) {
switch (**end) {
case '\0':
- return(ESCAPE_ERROR);
+ 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;
}
switch (**start) {
case '3':
- /* FALLTHROUGH */
case 'B':
gly = ESCAPE_FONTBOLD;
break;
case '2':
- /* FALLTHROUGH */
case 'I':
gly = ESCAPE_FONTITALIC;
break;
gly = ESCAPE_FONTPREV;
break;
case '1':
- /* FALLTHROUGH */
case 'R':
gly = ESCAPE_FONTROMAN;
break;
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);
+ return gly;
}
/*
if ('\0' == *cp && (white || ' ' == cp[-1]))
mandoc_msg(MANDOCERR_SPACE_EOL, parse, ln, *pos, NULL);
- return(start);
+ return start;
}
static int
#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:
* 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;
time_t t;
- if (NULL == in || '\0' == *in ||
- 0 == strcmp(in, "$" "Mdocdate$")) {
- 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 $", in) &&
- !a2time(&t, "%b %d, %Y", in)) {
- mandoc_msg(MANDOCERR_DATE_BAD, parse, ln, pos, in);
- t = 0;
+ /* No date specified: use today's date. */
+
+ if (in == NULL || *in == '\0' || strcmp(in, "$" "Mdocdate$") == 0) {
+ mandoc_msg(MANDOCERR_DATE_MISSING, man->parse, ln, pos, NULL);
+ return time2a(time(NULL));
}
- out = t ? time2a(t) : NULL;
- return(out ? out : mandoc_strdup(in));
+
+ /* Valid mdoc(7) date format. */
+
+ if (a2time(&t, "$" "Mdocdate: %b %d %Y $", in) ||
+ a2time(&t, "%b %d, %Y", in))
+ return time2a(t);
+
+ /* In man(7), do not warn about the legacy format. */
+
+ if (a2time(&t, "%Y-%m-%d", in) == 0)
+ mandoc_msg(MANDOCERR_DATE_BAD, man->parse, ln, pos, in);
+ else if (man->macroset == MACROSET_MDOC)
+ mandoc_vmsg(MANDOCERR_DATE_LEGACY, man->parse,
+ ln, pos, "Dd %s", in);
+
+ /* Use any non-mdoc(7) date verbatim. */
+
+ return mandoc_strdup(in);
}
int
int enclosed, found;
if (0 == sz)
- return(0);
+ return 0;
/*
* End-of-sentence recognition must include situations where
for (q = p + (int)sz - 1; q >= p; q--) {
switch (*q) {
case '\"':
- /* FALLTHROUGH */
case '\'':
- /* FALLTHROUGH */
case ']':
- /* FALLTHROUGH */
case ')':
if (0 == found)
enclosed = 1;
break;
case '.':
- /* FALLTHROUGH */
case '!':
- /* FALLTHROUGH */
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