version 1.38, 2011/03/15 03:03:54 |
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 |
* Copyright (c) 2011 Ingo Schwarze <schwarze@openbsd.org> |
* 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 |
|
|
* 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" |
|
|
#define DATESIZE 32 |
|
|
|
static int a2time(time_t *, const char *, const char *); |
static int a2time(time_t *, const char *, const char *); |
static char *time2a(time_t); |
static char *time2a(time_t); |
|
|
int |
|
mandoc_special(char *p) |
|
{ |
|
int len, i; |
|
char term; |
|
char *sv; |
|
|
|
len = 0; |
|
term = '\0'; |
|
sv = p; |
|
|
|
assert('\\' == *p); |
enum mandoc_esc |
p++; |
mandoc_font(const char *cp, int sz) |
|
{ |
switch (*p++) { |
switch (sz) { |
#if 0 |
case 0: |
case ('Z'): |
return ESCAPE_FONTPREV; |
/* FALLTHROUGH */ |
case 1: |
case ('X'): |
switch (cp[0]) { |
/* FALLTHROUGH */ |
case 'B': |
case ('x'): |
case '3': |
/* FALLTHROUGH */ |
return ESCAPE_FONTBOLD; |
case ('S'): |
case 'I': |
/* FALLTHROUGH */ |
case '2': |
case ('R'): |
return ESCAPE_FONTITALIC; |
/* FALLTHROUGH */ |
case 'P': |
case ('N'): |
return ESCAPE_FONTPREV; |
/* FALLTHROUGH */ |
case 'R': |
case ('l'): |
case '1': |
/* FALLTHROUGH */ |
return ESCAPE_FONTROMAN; |
case ('L'): |
case '4': |
/* FALLTHROUGH */ |
return ESCAPE_FONTBI; |
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 ('o'): |
|
/* FALLTHROUGH */ |
|
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); |
|
} |
} |
|
|
|
|
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_strdup(const char *ptr) |
|
{ |
|
char *p; |
|
|
|
p = strdup(ptr); |
|
if (NULL == p) { |
|
perror(NULL); |
|
exit((int)MANDOCLEVEL_SYSERR); |
|
} |
|
|
|
return(p); |
|
} |
|
|
|
/* |
|
* Parse a quoted or unquoted roff-style request or macro argument. |
|
* Return a pointer to the parsed argument, which is either the original |
|
* pointer or advanced by one byte in case the argument is quoted. |
|
* Null-terminate the argument in place. |
|
* Collapse pairs of quotes inside quoted arguments. |
|
* Advance the argument pointer to the next argument, |
|
* or to the null byte terminating the argument line. |
|
*/ |
|
char * |
|
mandoc_getarg(char **cpp, mandocmsg msg, void *data, int ln, int *pos) |
|
{ |
|
char *start, *cp; |
|
int quoted, pairs, white; |
|
|
|
/* Quoting can only start with a new word. */ |
|
start = *cpp; |
|
if ('"' == *start) { |
|
quoted = 1; |
|
start++; |
|
} else |
|
quoted = 0; |
|
|
|
pairs = 0; |
|
white = 0; |
|
for (cp = start; '\0' != *cp; cp++) { |
|
/* Move left after quoted quotes and escaped backslashes. */ |
|
if (pairs) |
|
cp[-pairs] = cp[0]; |
|
if ('\\' == cp[0]) { |
|
if ('\\' == cp[1]) { |
|
/* Poor man's copy mode. */ |
|
pairs++; |
|
cp++; |
|
} else if (0 == quoted && ' ' == cp[1]) |
|
/* Skip escaped blanks. */ |
|
cp++; |
|
} else if (0 == quoted) { |
|
if (' ' == cp[0]) { |
|
/* Unescaped blanks end unquoted args. */ |
|
white = 1; |
|
break; |
|
} |
|
} else if ('"' == cp[0]) { |
|
if ('"' == cp[1]) { |
|
/* Quoted quotes collapse. */ |
|
pairs++; |
|
cp++; |
|
} else { |
|
/* Unquoted quotes end quoted args. */ |
|
quoted = 2; |
|
break; |
|
} |
|
} |
|
} |
|
|
|
/* Quoted argument without a closing quote. */ |
|
if (1 == quoted && msg) |
|
(*msg)(MANDOCERR_BADQUOTE, data, ln, *pos, NULL); |
|
|
|
/* Null-terminate this argument and move to the next one. */ |
|
if (pairs) |
|
cp[-pairs] = '\0'; |
|
if ('\0' != *cp) { |
|
*cp++ = '\0'; |
|
while (' ' == *cp) |
|
cp++; |
|
} |
|
*pos += (cp - start) + (quoted ? 1 : 0); |
|
*cpp = cp; |
|
|
|
if ('\0' == *cp && msg && (white || ' ' == cp[-1])) |
|
(*msg)(MANDOCERR_EOLNSPACE, data, ln, *pos, NULL); |
|
|
|
return(start); |
|
} |
|
|
|
|
|
static int |
static int |
a2time(time_t *t, const char *fmt, const char *p) |
a2time(time_t *t, const char *fmt, const char *p) |
{ |
{ |
Line 372 a2time(time_t *t, const char *fmt, const char *p) |
|
Line 105 a2time(time_t *t, const char *fmt, const char *p) |
|
|
|
memset(&tm, 0, sizeof(struct tm)); |
memset(&tm, 0, sizeof(struct tm)); |
|
|
|
pp = NULL; |
|
#if HAVE_STRPTIME |
pp = strptime(p, fmt, &tm); |
pp = strptime(p, fmt, &tm); |
|
#endif |
if (NULL != pp && '\0' == *pp) { |
if (NULL != pp && '\0' == *pp) { |
*t = mktime(&tm); |
*t = mktime(&tm); |
return(1); |
return 1; |
} |
} |
|
|
return(0); |
return 0; |
} |
} |
|
|
|
|
static char * |
static char * |
time2a(time_t t) |
time2a(time_t t) |
{ |
{ |
struct tm tm; |
struct tm *tm; |
char *buf, *p; |
char *buf, *p; |
size_t ssz; |
size_t ssz; |
int isz; |
int isz; |
|
|
localtime_r(&t, &tm); |
buf = NULL; |
|
tm = localtime(&t); |
|
if (tm == NULL) |
|
goto fail; |
|
|
/* |
/* |
* Reserve space: |
* Reserve space: |
Line 398 time2a(time_t t) |
|
Line 136 time2a(time_t t) |
|
* up to 2 characters for the day + comma + blank |
* up to 2 characters for the day + comma + blank |
* 4 characters for the year and a terminating '\0' |
* 4 characters for the year and a terminating '\0' |
*/ |
*/ |
|
|
p = buf = mandoc_malloc(10 + 4 + 4 + 1); |
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; |
goto fail; |
p += (int)ssz; |
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. |
|
*/ |
|
|
|
isz = snprintf(p, 4 + 1, "%d, ", tm->tm_mday); |
|
if (isz < 0 || isz > 4) |
goto fail; |
goto fail; |
p += isz; |
p += isz; |
|
|
if (0 == strftime(p, 4 + 1, "%Y", &tm)) |
if (strftime(p, 4 + 1, "%Y", tm) == 0) |
goto fail; |
goto fail; |
return(buf); |
return buf; |
|
|
fail: |
fail: |
free(buf); |
free(buf); |
return(NULL); |
return mandoc_strdup(""); |
} |
} |
|
|
|
|
char * |
char * |
mandoc_normdate(char *in, mandocmsg msg, void *data, int ln, int pos) |
mandoc_normdate(struct roff_node *nch, struct roff_node *nbl) |
{ |
{ |
char *out; |
char *cp; |
time_t t; |
time_t t; |
|
|
if (NULL == in || '\0' == *in || |
/* No date specified. */ |
0 == strcmp(in, "$" "Mdocdate$")) { |
|
(*msg)(MANDOCERR_NODATE, data, ln, pos, NULL); |
if (nch == NULL) { |
time(&t); |
if (nbl == NULL) |
|
mandoc_msg(MANDOCERR_DATE_MISSING, 0, 0, NULL); |
|
else |
|
mandoc_msg(MANDOCERR_DATE_MISSING, nbl->line, |
|
nbl->pos, "%s", roff_name[nbl->tok]); |
|
return mandoc_strdup(""); |
} |
} |
else if (!a2time(&t, "$" "Mdocdate: %b %d %Y $", in) && |
if (*nch->string == '\0') { |
!a2time(&t, "%b %d, %Y", in) && |
mandoc_msg(MANDOCERR_DATE_MISSING, nch->line, |
!a2time(&t, "%Y-%m-%d", in)) { |
nch->pos, "%s", roff_name[nbl->tok]); |
(*msg)(MANDOCERR_BADDATE, data, ln, pos, NULL); |
return mandoc_strdup(""); |
t = 0; |
|
} |
} |
out = t ? time2a(t) : NULL; |
if (strcmp(nch->string, "$" "Mdocdate$") == 0) |
return(out ? out : mandoc_strdup(in)); |
return time2a(time(NULL)); |
} |
|
|
|
|
/* Valid mdoc(7) date format. */ |
|
|
|
if (a2time(&t, "$" "Mdocdate: %b %d %Y $", nch->string) || |
|
a2time(&t, "%b %d, %Y", nch->string)) { |
|
cp = time2a(t); |
|
if (t > time(NULL) + 86400) |
|
mandoc_msg(MANDOCERR_DATE_FUTURE, nch->line, |
|
nch->pos, "%s %s", roff_name[nbl->tok], cp); |
|
else if (*nch->string != '$' && |
|
strcmp(nch->string, cp) != 0) |
|
mandoc_msg(MANDOCERR_DATE_NORM, nch->line, |
|
nch->pos, "%s %s", roff_name[nbl->tok], cp); |
|
return cp; |
|
} |
|
|
|
/* In man(7), do not warn about the legacy format. */ |
|
|
|
if (a2time(&t, "%Y-%m-%d", nch->string) == 0) |
|
mandoc_msg(MANDOCERR_DATE_BAD, nch->line, nch->pos, |
|
"%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); |
|
|
|
/* Use any non-mdoc(7) date verbatim. */ |
|
|
|
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; |
} |
} |