version 1.33, 2010/08/24 13:56:51 |
version 1.121, 2022/05/19 15:37:47 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2010, 2011, 2015, 2017, 2018, 2019, 2020, 2021 |
|
* Ingo Schwarze <schwarze@openbsd.org> |
|
* Copyright (c) 2009, 2010 Kristaps Dzonsons <kristaps@bsd.lv> |
* |
* |
* 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. |
|
* |
|
* Utility functions to handle end of sentence punctuation |
|
* and dates and times, for use by mdoc(7) and man(7) parsers. |
|
* Utility functions to handle fonts and numbers, |
|
* for use by mandoc(1) parsers and formatters. |
*/ |
*/ |
#ifdef HAVE_CONFIG_H |
|
#include "config.h" |
#include "config.h" |
#endif |
|
|
|
#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 <time.h> |
|
|
|
#include "mandoc_aux.h" |
#include "mandoc.h" |
#include "mandoc.h" |
|
#include "roff.h" |
#include "libmandoc.h" |
#include "libmandoc.h" |
|
#include "roff_int.h" |
|
|
static int a2time(time_t *, const char *, const char *); |
static int a2time(time_t *, const char *, const char *); |
|
static char *time2a(time_t); |
|
|
|
|
int |
enum mandoc_esc |
mandoc_special(char *p) |
mandoc_font(const char *cp, int sz) |
{ |
{ |
int len, i; |
switch (sz) { |
char term; |
case 0: |
char *sv; |
return ESCAPE_FONTPREV; |
|
case 1: |
len = 0; |
switch (cp[0]) { |
term = '\0'; |
case 'B': |
sv = p; |
case '3': |
|
return ESCAPE_FONTBOLD; |
assert('\\' == *p); |
case 'I': |
p++; |
case '2': |
|
return ESCAPE_FONTITALIC; |
switch (*p++) { |
case 'P': |
#if 0 |
return ESCAPE_FONTPREV; |
case ('Z'): |
case 'R': |
/* FALLTHROUGH */ |
case '1': |
case ('X'): |
return ESCAPE_FONTROMAN; |
/* FALLTHROUGH */ |
case '4': |
case ('x'): |
return ESCAPE_FONTBI; |
/* FALLTHROUGH */ |
|
case ('S'): |
|
/* FALLTHROUGH */ |
|
case ('R'): |
|
/* FALLTHROUGH */ |
|
case ('o'): |
|
/* FALLTHROUGH */ |
|
case ('N'): |
|
/* FALLTHROUGH */ |
|
case ('l'): |
|
/* FALLTHROUGH */ |
|
case ('L'): |
|
/* FALLTHROUGH */ |
|
case ('H'): |
|
/* FALLTHROUGH */ |
|
case ('h'): |
|
/* FALLTHROUGH */ |
|
case ('D'): |
|
/* FALLTHROUGH */ |
|
case ('C'): |
|
/* FALLTHROUGH */ |
|
case ('b'): |
|
/* FALLTHROUGH */ |
|
case ('B'): |
|
/* FALLTHROUGH */ |
|
case ('a'): |
|
/* FALLTHROUGH */ |
|
case ('A'): |
|
if (*p++ != '\'') |
|
return(0); |
|
term = '\''; |
|
break; |
|
#endif |
|
case ('h'): |
|
/* FALLTHROUGH */ |
|
case ('v'): |
|
/* FALLTHROUGH */ |
|
case ('s'): |
|
if (ASCII_HYPH == *p) |
|
*p = '-'; |
|
|
|
i = 0; |
|
if ('+' == *p || '-' == *p) { |
|
p++; |
|
i = 1; |
|
} |
|
|
|
switch (*p++) { |
|
case ('('): |
|
len = 2; |
|
break; |
|
case ('['): |
|
term = ']'; |
|
break; |
|
case ('\''): |
|
term = '\''; |
|
break; |
|
case ('0'): |
|
i = 1; |
|
/* FALLTHROUGH */ |
|
default: |
default: |
len = 1; |
return ESCAPE_ERROR; |
p--; |
|
break; |
|
} |
} |
|
case 2: |
if (ASCII_HYPH == *p) |
switch (cp[0]) { |
*p = '-'; |
case 'B': |
if ('+' == *p || '-' == *p) { |
switch (cp[1]) { |
if (i) |
case 'I': |
return(0); |
return ESCAPE_FONTBI; |
p++; |
default: |
} |
return ESCAPE_ERROR; |
|
} |
/* Handle embedded numerical subexp or escape. */ |
case 'C': |
|
switch (cp[1]) { |
if ('(' == *p) { |
case 'B': |
while (*p && ')' != *p) |
return ESCAPE_FONTCB; |
if ('\\' == *p++) { |
case 'I': |
i = mandoc_special(--p); |
return ESCAPE_FONTCI; |
if (0 == i) |
case 'R': |
return(0); |
case 'W': |
p += i; |
return ESCAPE_FONTCR; |
} |
default: |
|
return ESCAPE_ERROR; |
if (')' == *p++) |
} |
break; |
|
|
|
return(0); |
|
} else if ('\\' == *p) { |
|
if (0 == (i = mandoc_special(p))) |
|
return(0); |
|
p += i; |
|
} |
|
|
|
break; |
|
#if 0 |
|
case ('Y'): |
|
/* FALLTHROUGH */ |
|
case ('V'): |
|
/* FALLTHROUGH */ |
|
case ('$'): |
|
/* FALLTHROUGH */ |
|
case ('n'): |
|
/* FALLTHROUGH */ |
|
#endif |
|
case ('k'): |
|
/* FALLTHROUGH */ |
|
case ('M'): |
|
/* FALLTHROUGH */ |
|
case ('m'): |
|
/* FALLTHROUGH */ |
|
case ('f'): |
|
/* FALLTHROUGH */ |
|
case ('F'): |
|
/* FALLTHROUGH */ |
|
case ('*'): |
|
switch (*p++) { |
|
case ('('): |
|
len = 2; |
|
break; |
|
case ('['): |
|
term = ']'; |
|
break; |
|
default: |
default: |
len = 1; |
return ESCAPE_ERROR; |
p--; |
|
break; |
|
} |
} |
break; |
|
case ('('): |
|
len = 2; |
|
break; |
|
case ('['): |
|
term = ']'; |
|
break; |
|
case ('z'): |
|
len = 1; |
|
if ('\\' == *p) { |
|
if (0 == (i = mandoc_special(p))) |
|
return(0); |
|
p += i; |
|
return(*p ? (int)(p - sv) : 0); |
|
} |
|
break; |
|
case ('w'): |
|
if ('\'' == *p++) { |
|
term = '\''; |
|
break; |
|
} |
|
/* FALLTHROUGH */ |
|
default: |
default: |
len = 1; |
return ESCAPE_ERROR; |
p--; |
|
break; |
|
} |
} |
|
|
if (term) { |
|
for ( ; *p && term != *p; p++) |
|
if (ASCII_HYPH == *p) |
|
*p = '-'; |
|
return(*p ? (int)(p - sv) : 0); |
|
} |
|
|
|
for (i = 0; *p && i < len; i++, p++) |
|
if (ASCII_HYPH == *p) |
|
*p = '-'; |
|
return(i == len ? (int)(p - sv) : 0); |
|
} |
} |
|
|
|
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) { |
|
perror(NULL); |
pp = NULL; |
exit(MANDOCLEVEL_SYSERR); |
#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 * |
void * |
time2a(time_t t) |
mandoc_malloc(size_t size) |
|
{ |
{ |
void *ptr; |
struct tm *tm; |
|
char *buf, *p; |
|
size_t ssz; |
|
int isz; |
|
|
ptr = malloc(size); |
buf = NULL; |
if (NULL == ptr) { |
tm = localtime(&t); |
perror(NULL); |
if (tm == NULL) |
exit(MANDOCLEVEL_SYSERR); |
goto fail; |
} |
|
|
|
return(ptr); |
/* |
} |
* 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); |
|
|
void * |
if ((ssz = strftime(p, 10 + 1, "%B ", tm)) == 0) |
mandoc_realloc(void *ptr, size_t size) |
goto fail; |
{ |
p += (int)ssz; |
|
|
ptr = realloc(ptr, size); |
/* |
if (NULL == ptr) { |
* The output format is just "%d" here, not "%2d" or "%02d". |
perror(NULL); |
* That's also the reason why we can't just format the |
exit(MANDOCLEVEL_SYSERR); |
* 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. |
|
*/ |
|
|
return(ptr); |
isz = snprintf(p, 4 + 1, "%d, ", tm->tm_mday); |
} |
if (isz < 0 || isz > 4) |
|
goto fail; |
|
p += isz; |
|
|
|
if (strftime(p, 4 + 1, "%Y", tm) == 0) |
|
goto fail; |
|
return buf; |
|
|
char * |
fail: |
mandoc_strdup(const char *ptr) |
free(buf); |
{ |
return mandoc_strdup(""); |
char *p; |
|
|
|
p = strdup(ptr); |
|
if (NULL == p) { |
|
perror(NULL); |
|
exit(MANDOCLEVEL_SYSERR); |
|
} |
|
|
|
return(p); |
|
} |
} |
|
|
|
char * |
static int |
mandoc_normdate(struct roff_node *nch, struct roff_node *nbl) |
a2time(time_t *t, const char *fmt, const char *p) |
|
{ |
{ |
struct tm tm; |
char *cp; |
char *pp; |
time_t t; |
|
|
memset(&tm, 0, sizeof(struct tm)); |
/* No date specified. */ |
|
|
pp = strptime(p, fmt, &tm); |
if (nch == NULL) { |
if (NULL != pp && '\0' == *pp) { |
if (nbl == NULL) |
*t = mktime(&tm); |
mandoc_msg(MANDOCERR_DATE_MISSING, 0, 0, NULL); |
return(1); |
else |
|
mandoc_msg(MANDOCERR_DATE_MISSING, nbl->line, |
|
nbl->pos, "%s", roff_name[nbl->tok]); |
|
return mandoc_strdup(""); |
} |
} |
|
if (*nch->string == '\0') { |
|
mandoc_msg(MANDOCERR_DATE_MISSING, nch->line, |
|
nch->pos, "%s", roff_name[nbl->tok]); |
|
return mandoc_strdup(""); |
|
} |
|
if (strcmp(nch->string, "$" "Mdocdate$") == 0) |
|
return time2a(time(NULL)); |
|
|
return(0); |
/* Valid mdoc(7) date format. */ |
} |
|
|
|
|
if (a2time(&t, "$" "Mdocdate: %b %d %Y $", nch->string) || |
/* |
a2time(&t, "%b %d, %Y", nch->string)) { |
* Convert from a manual date string (see mdoc(7) and man(7)) into a |
cp = time2a(t); |
* date according to the stipulated date type. |
if (t > time(NULL) + 86400) |
*/ |
mandoc_msg(MANDOCERR_DATE_FUTURE, nch->line, |
time_t |
nch->pos, "%s %s", roff_name[nbl->tok], cp); |
mandoc_a2time(int flags, const char *p) |
else if (*nch->string != '$' && |
{ |
strcmp(nch->string, cp) != 0) |
time_t t; |
mandoc_msg(MANDOCERR_DATE_NORM, nch->line, |
|
nch->pos, "%s %s", roff_name[nbl->tok], cp); |
if (MTIME_MDOCDATE & flags) { |
return cp; |
if (0 == strcmp(p, "$" "Mdocdate$")) |
|
return(time(NULL)); |
|
if (a2time(&t, "$" "Mdocdate: %b %d %Y $", p)) |
|
return(t); |
|
} |
} |
|
|
if (MTIME_CANONICAL & flags || MTIME_REDUCED & flags) |
/* In man(7), do not warn about the legacy format. */ |
if (a2time(&t, "%b %d, %Y", p)) |
|
return(t); |
|
|
|
if (MTIME_ISO_8601 & flags) |
if (a2time(&t, "%Y-%m-%d", nch->string) == 0) |
if (a2time(&t, "%Y-%m-%d", p)) |
mandoc_msg(MANDOCERR_DATE_BAD, nch->line, nch->pos, |
return(t); |
"%s %s", roff_name[nbl->tok], nch->string); |
|
else if (t > time(NULL) + 86400) |
|
mandoc_msg(MANDOCERR_DATE_FUTURE, nch->line, nch->pos, |
|
"%s %s", roff_name[nbl->tok], nch->string); |
|
else if (nbl->tok == MDOC_Dd) |
|
mandoc_msg(MANDOCERR_DATE_LEGACY, nch->line, nch->pos, |
|
"Dd %s", nch->string); |
|
|
if (MTIME_REDUCED & flags) { |
/* Use any non-mdoc(7) date verbatim. */ |
if (a2time(&t, "%d, %Y", p)) |
|
return(t); |
|
if (a2time(&t, "%Y", p)) |
|
return(t); |
|
} |
|
|
|
return(0); |
return mandoc_strdup(nch->string); |
} |
} |
|
|
|
|
int |
int |
mandoc_eos(const char *p, size_t sz, int enclosed) |
mandoc_eos(const char *p, size_t sz) |
{ |
{ |
const char *q; |
const char *q; |
int found; |
int enclosed, found; |
|
|
if (0 == sz) |
if (0 == sz) |
return(0); |
return 0; |
|
|
/* |
/* |
* End-of-sentence recognition must include situations where |
* End-of-sentence recognition must include situations where |
* some symbols, such as `)', allow prior EOS punctuation to |
* some symbols, such as `)', allow prior EOS punctuation to |
* propogate outward. |
* propagate outward. |
*/ |
*/ |
|
|
found = 0; |
enclosed = found = 0; |
for (q = p + (int)sz - 1; q >= p; q--) { |
for (q = p + (int)sz - 1; q >= p; q--) { |
switch (*q) { |
switch (*q) { |
case ('\"'): |
case '\"': |
/* FALLTHROUGH */ |
case '\'': |
case ('\''): |
case ']': |
/* FALLTHROUGH */ |
case ')': |
case (']'): |
|
/* FALLTHROUGH */ |
|
case (')'): |
|
if (0 == found) |
if (0 == found) |
enclosed = 1; |
enclosed = 1; |
break; |
break; |
case ('.'): |
case '.': |
/* FALLTHROUGH */ |
case '!': |
case ('!'): |
case '?': |
/* FALLTHROUGH */ |
|
case ('?'): |
|
found = 1; |
found = 1; |
break; |
break; |
default: |
default: |
return(found && (!enclosed || isalnum((unsigned char)*q))); |
return found && |
|
(!enclosed || isalnum((unsigned char)*q)); |
} |
} |
} |
} |
|
|
return(found && !enclosed); |
return found && !enclosed; |
} |
} |
|
|
|
/* |
|
* Convert a string to a long that may not be <0. |
|
* If the string is invalid, or is less than 0, return -1. |
|
*/ |
int |
int |
mandoc_hyph(const char *start, const char *c) |
mandoc_strntoi(const char *p, size_t sz, int base) |
{ |
{ |
|
char buf[32]; |
|
char *ep; |
|
long v; |
|
|
/* |
if (sz > 31) |
* Choose whether to break at a hyphenated character. We only |
return -1; |
* do this if it's free-standing within a word. |
|
*/ |
|
|
|
/* Skip first/last character of buffer. */ |
memcpy(buf, p, sz); |
if (c == start || '\0' == *(c + 1)) |
buf[(int)sz] = '\0'; |
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); |
errno = 0; |
|
v = strtol(buf, &ep, base); |
|
|
|
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; |
} |
} |