version 1.4, 2009/10/28 19:21:59 |
version 1.113, 2018/12/18 22:00:02 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2008, 2009 Kristaps Dzonsons <kristaps@kth.se> |
* Copyright (c) 2008-2011, 2014 Kristaps Dzonsons <kristaps@bsd.lv> |
|
* Copyright (c) 2011-2015, 2017, 2018 Ingo Schwarze <schwarze@openbsd.org> |
* |
* |
* Permission to use, copy, modify, and distribute this software for any |
* Permission to use, copy, modify, and distribute this software for any |
* purpose with or without fee is hereby granted, provided that the above |
* purpose with or without fee is hereby granted, provided that the above |
* copyright notice and this permission notice appear in all copies. |
* copyright notice and this permission notice appear in all copies. |
* |
* |
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES |
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHORS DISCLAIM ALL WARRANTIES |
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF |
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF |
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR |
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR |
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES |
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES |
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN |
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN |
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF |
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF |
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. |
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. |
*/ |
*/ |
|
#include "config.h" |
|
|
#include <sys/types.h> |
#include <sys/types.h> |
|
|
#include <assert.h> |
#include <assert.h> |
#include <ctype.h> |
#include <ctype.h> |
|
#include <errno.h> |
|
#include <limits.h> |
#include <stdlib.h> |
#include <stdlib.h> |
#include <stdio.h> |
#include <stdio.h> |
#include <string.h> |
#include <string.h> |
|
#include <time.h> |
|
|
|
#include "mandoc_aux.h" |
|
#include "mandoc.h" |
|
#include "roff.h" |
#include "libmandoc.h" |
#include "libmandoc.h" |
|
|
int |
static int a2time(time_t *, const char *, const char *); |
mandoc_special(const char *p) |
static char *time2a(time_t); |
|
|
|
|
|
enum mandoc_esc |
|
mandoc_font(const char *cp, int sz) |
{ |
{ |
int c; |
switch (sz) { |
|
case 0: |
if ('\\' != *p++) |
return ESCAPE_FONTPREV; |
return(0); |
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; |
|
} |
|
} |
|
|
switch (*p) { |
enum mandoc_esc |
case ('\\'): |
mandoc_escape(const char **end, const char **start, int *sz) |
/* FALLTHROUGH */ |
{ |
case ('\''): |
const char *local_start; |
/* FALLTHROUGH */ |
int local_sz, c, i; |
case ('`'): |
char term; |
/* FALLTHROUGH */ |
enum mandoc_esc gly; |
case ('q'): |
|
/* FALLTHROUGH */ |
/* |
case ('-'): |
* When the caller doesn't provide return storage, |
/* FALLTHROUGH */ |
* use local storage. |
case ('~'): |
*/ |
/* FALLTHROUGH */ |
|
case ('^'): |
if (NULL == start) |
/* FALLTHROUGH */ |
start = &local_start; |
case ('%'): |
if (NULL == sz) |
/* FALLTHROUGH */ |
sz = &local_sz; |
case ('0'): |
|
/* FALLTHROUGH */ |
/* |
case (' '): |
* Treat "\E" just like "\"; |
/* FALLTHROUGH */ |
* it only makes a difference in copy mode. |
case ('|'): |
*/ |
/* FALLTHROUGH */ |
|
case ('&'): |
if (**end == 'E') |
/* FALLTHROUGH */ |
++*end; |
case ('.'): |
|
/* FALLTHROUGH */ |
/* |
case (':'): |
* Beyond the backslash, at least one input character |
/* FALLTHROUGH */ |
* is part of the escape sequence. With one exception |
case ('c'): |
* (see below), that character won't be returned. |
return(2); |
*/ |
case ('e'): |
|
return(2); |
gly = ESCAPE_ERROR; |
case ('f'): |
*start = ++*end; |
if (0 == *++p || ! isgraph((u_char)*p)) |
*sz = 0; |
return(0); |
term = '\0'; |
return(3); |
|
case ('*'): |
switch ((*start)[-1]) { |
if (0 == *++p || ! isgraph((u_char)*p)) |
/* |
return(0); |
* First the glyphs. There are several different forms of |
switch (*p) { |
* these, but each eventually returns a substring of the glyph |
case ('('): |
* name. |
if (0 == *++p || ! isgraph((u_char)*p)) |
*/ |
return(0); |
case '(': |
return(4); |
gly = ESCAPE_SPECIAL; |
case ('['): |
*sz = 2; |
for (c = 3, p++; *p && ']' != *p; p++, c++) |
break; |
if ( ! isgraph((u_char)*p)) |
case '[': |
|
if (**start == ' ') { |
|
++*end; |
|
return ESCAPE_ERROR; |
|
} |
|
gly = ESCAPE_SPECIAL; |
|
term = ']'; |
|
break; |
|
case 'C': |
|
if ('\'' != **start) |
|
return ESCAPE_ERROR; |
|
*start = ++*end; |
|
gly = ESCAPE_SPECIAL; |
|
term = '\''; |
|
break; |
|
|
|
/* |
|
* Escapes taking no arguments at all. |
|
*/ |
|
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; |
|
|
|
/* |
|
* 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. |
|
*/ |
|
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 '[': |
|
if ((*start)[-1] == 'O') |
|
gly = (*start)[1] == '5' ? |
|
ESCAPE_UNSUPP : ESCAPE_ERROR; |
|
*start = ++*end; |
|
term = ']'; |
|
break; |
|
default: |
|
if ((*start)[-1] == 'O') { |
|
switch (**start) { |
|
case '0': |
|
gly = ESCAPE_UNSUPP; |
break; |
break; |
return(*p == ']' ? c : 0); |
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': |
|
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; |
|
break; |
|
|
|
/* |
|
* These escapes are of the form \X'N', where 'X' is the trigger |
|
* and 'N' resolves to a numerical expression. |
|
*/ |
|
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: |
default: |
|
gly = ESCAPE_IGNORE; |
break; |
break; |
} |
} |
return(3); |
term = **start; |
case ('('): |
*start = ++*end; |
if (0 == *++p || ! isgraph((u_char)*p)) |
|
return(0); |
|
if (0 == *++p || ! isgraph((u_char)*p)) |
|
return(0); |
|
return(4); |
|
case ('['): |
|
break; |
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; |
|
|
|
/* See +/- counts as a sign. */ |
|
if ('+' == **end || '-' == **end || ASCII_HYPH == **end) |
|
*start = ++*end; |
|
|
|
switch (**end) { |
|
case '(': |
|
*start = ++*end; |
|
*sz = 2; |
|
break; |
|
case '[': |
|
*start = ++*end; |
|
term = ']'; |
|
break; |
|
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; |
|
} |
|
|
|
break; |
|
|
|
/* |
|
* Several special characters can be encoded as |
|
* one-byte escape sequences without using \[]. |
|
*/ |
|
case ' ': |
|
case '\'': |
|
case '-': |
|
case '.': |
|
case '0': |
|
case ':': |
|
case '_': |
|
case '`': |
|
case 'e': |
|
case '~': |
|
gly = ESCAPE_SPECIAL; |
|
/* FALLTHROUGH */ |
default: |
default: |
return(0); |
if (gly == ESCAPE_ERROR) |
|
gly = ESCAPE_UNDEF; |
|
*start = --*end; |
|
*sz = 1; |
|
break; |
} |
} |
|
|
for (c = 3, p++; *p && ']' != *p; p++, c++) |
/* |
if ( ! isgraph((u_char)*p)) |
* Read up to the terminating character, |
|
* paying attention to nested escapes. |
|
*/ |
|
|
|
if ('\0' != term) { |
|
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; |
|
|
|
/* |
|
* 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; |
|
} |
|
|
|
/* Run post-processors. */ |
|
|
|
switch (gly) { |
|
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; |
break; |
|
} |
|
|
return(*p == ']' ? c : 0); |
/* |
|
* 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; |
} |
} |
|
|
|
static int |
void * |
a2time(time_t *t, const char *fmt, const char *p) |
mandoc_calloc(size_t num, size_t size) |
|
{ |
{ |
void *ptr; |
struct tm tm; |
|
char *pp; |
|
|
ptr = calloc(num, size); |
memset(&tm, 0, sizeof(struct tm)); |
if (NULL == ptr) { |
|
fprintf(stderr, "memory exhausted\n"); |
pp = NULL; |
exit(EXIT_FAILURE); |
#if HAVE_STRPTIME |
|
pp = strptime(p, fmt, &tm); |
|
#endif |
|
if (NULL != pp && '\0' == *pp) { |
|
*t = mktime(&tm); |
|
return 1; |
} |
} |
|
|
return(ptr); |
return 0; |
} |
} |
|
|
|
static char * |
|
time2a(time_t t) |
|
{ |
|
struct tm *tm; |
|
char *buf, *p; |
|
size_t ssz; |
|
int isz; |
|
|
void * |
tm = localtime(&t); |
mandoc_malloc(size_t size) |
if (tm == NULL) |
|
return NULL; |
|
|
|
/* |
|
* Reserve space: |
|
* up to 9 characters for the month (September) + blank |
|
* 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 ((ssz = strftime(p, 10 + 1, "%B ", tm)) == 0) |
|
goto fail; |
|
p += (int)ssz; |
|
|
|
/* |
|
* 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 (strftime(p, 4 + 1, "%Y", tm) == 0) |
|
goto fail; |
|
return buf; |
|
|
|
fail: |
|
free(buf); |
|
return NULL; |
|
} |
|
|
|
char * |
|
mandoc_normdate(struct roff_man *man, char *in, int ln, int pos) |
{ |
{ |
void *ptr; |
char *cp; |
|
time_t t; |
|
|
ptr = malloc(size); |
/* No date specified: use today's date. */ |
if (NULL == ptr) { |
|
fprintf(stderr, "memory exhausted\n"); |
if (in == NULL || *in == '\0' || strcmp(in, "$" "Mdocdate$") == 0) { |
exit(EXIT_FAILURE); |
mandoc_msg(MANDOCERR_DATE_MISSING, ln, pos, NULL); |
|
return time2a(time(NULL)); |
} |
} |
|
|
return(ptr); |
/* 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; |
|
} |
|
|
void * |
/* In man(7), do not warn about the legacy format. */ |
mandoc_realloc(void *ptr, size_t size) |
|
|
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) |
{ |
{ |
|
const char *q; |
|
int enclosed, found; |
|
|
ptr = realloc(ptr, size); |
if (0 == sz) |
if (NULL == ptr) { |
return 0; |
fprintf(stderr, "memory exhausted\n"); |
|
exit(EXIT_FAILURE); |
/* |
|
* End-of-sentence recognition must include situations where |
|
* some symbols, such as `)', allow prior EOS punctuation to |
|
* propagate outward. |
|
*/ |
|
|
|
enclosed = found = 0; |
|
for (q = p + (int)sz - 1; q >= p; q--) { |
|
switch (*q) { |
|
case '\"': |
|
case '\'': |
|
case ']': |
|
case ')': |
|
if (0 == found) |
|
enclosed = 1; |
|
break; |
|
case '.': |
|
case '!': |
|
case '?': |
|
found = 1; |
|
break; |
|
default: |
|
return found && |
|
(!enclosed || isalnum((unsigned char)*q)); |
|
} |
} |
} |
|
|
return(ptr); |
return found && !enclosed; |
} |
} |
|
|
|
/* |
void * |
* Convert a string to a long that may not be <0. |
mandoc_reallocf(void *old_ptr, size_t size) /* FIXME: remove (not used) */ |
* If the string is invalid, or is less than 0, return -1. |
|
*/ |
|
int |
|
mandoc_strntoi(const char *p, size_t sz, int base) |
{ |
{ |
void *ptr; |
char buf[32]; |
|
char *ep; |
|
long v; |
|
|
ptr = realloc(old_ptr, size); |
if (sz > 31) |
if (NULL == ptr) |
return -1; |
free(old_ptr); |
|
|
|
return(ptr); |
memcpy(buf, p, sz); |
} |
buf[(int)sz] = '\0'; |
|
|
|
errno = 0; |
|
v = strtol(buf, &ep, base); |
|
|
char * |
if (buf[0] == '\0' || *ep != '\0') |
mandoc_strdup(const char *ptr) |
return -1; |
{ |
|
char *p; |
|
|
|
p = strdup(ptr); |
if (v > INT_MAX) |
if (NULL == p) { |
v = INT_MAX; |
fprintf(stderr, "memory exhausted\n"); |
if (v < INT_MIN) |
exit(EXIT_FAILURE); |
v = INT_MIN; |
} |
|
|
|
return(p); |
return (int)v; |
} |
} |