version 1.45, 2011/04/09 15:29:40 |
version 1.57, 2011/07/27 07:06:29 |
|
|
|
|
#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> |
Line 95 numescape(const char *start) |
|
Line 97 numescape(const char *start) |
|
return(++i); |
return(++i); |
} |
} |
|
|
/* |
|
* Handle an escaped sequeence. This should be called with any |
|
* string subsequent a `\'. Pass a pointer to this substring as "end"; |
|
* it will be set to the supremum of the parsed escape sequence. If |
|
* this returns ESCAPE_ERROR, the string is bogus and should be thrown |
|
* away. If not ESCAPE_ERROR or ESCAPE_IGNORE, "start" is set to the |
|
* first relevant character of the substring (font, glyph, whatever) of |
|
* length sz. Both "start" and "sz" may be NULL. |
|
*/ |
|
enum mandoc_esc |
enum mandoc_esc |
mandoc_escape(const char **end, const char **start, int *sz) |
mandoc_escape(const char **end, const char **start, int *sz) |
{ |
{ |
Line 116 mandoc_escape(const char **end, const char **start, in |
|
Line 109 mandoc_escape(const char **end, const char **start, in |
|
rstart = cp; |
rstart = cp; |
if (start) |
if (start) |
*start = rstart; |
*start = rstart; |
i = 0; |
i = lim = 0; |
gly = ESCAPE_ERROR; |
gly = ESCAPE_ERROR; |
term = '\0'; |
term = numeric = '\0'; |
numeric = 0; |
|
|
|
switch ((c = cp[i++])) { |
switch ((c = cp[i++])) { |
/* |
/* |
Line 133 mandoc_escape(const char **end, const char **start, in |
|
Line 125 mandoc_escape(const char **end, const char **start, in |
|
break; |
break; |
case ('['): |
case ('['): |
gly = ESCAPE_SPECIAL; |
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' == cp[i] && ']' != cp[i + 1]) |
|
gly = ESCAPE_UNICODE; |
term = ']'; |
term = ']'; |
break; |
break; |
case ('C'): |
case ('C'): |
Line 164 mandoc_escape(const char **end, const char **start, in |
|
Line 164 mandoc_escape(const char **end, const char **start, in |
|
if (ESCAPE_ERROR == gly) |
if (ESCAPE_ERROR == gly) |
gly = ESCAPE_IGNORE; |
gly = ESCAPE_IGNORE; |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('*'): |
|
if (ESCAPE_ERROR == gly) |
|
gly = ESCAPE_PREDEF; |
|
/* FALLTHROUGH */ |
|
case ('f'): |
case ('f'): |
if (ESCAPE_ERROR == gly) |
if (ESCAPE_ERROR == gly) |
gly = ESCAPE_FONT; |
gly = ESCAPE_FONT; |
|
|
gly = ESCAPE_FONTROMAN; |
gly = ESCAPE_FONTROMAN; |
break; |
break; |
} |
} |
|
break; |
case (ESCAPE_SPECIAL): |
case (ESCAPE_SPECIAL): |
if (1 != rlim) |
if (1 != rlim) |
break; |
break; |
Line 435 mandoc_realloc(void *ptr, size_t size) |
|
Line 432 mandoc_realloc(void *ptr, size_t size) |
|
return(ptr); |
return(ptr); |
} |
} |
|
|
|
char * |
|
mandoc_strndup(const char *ptr, size_t sz) |
|
{ |
|
char *p; |
|
|
|
p = mandoc_malloc(sz + 1); |
|
memcpy(p, ptr, sz); |
|
p[(int)sz] = '\0'; |
|
return(p); |
|
} |
|
|
char * |
char * |
mandoc_strdup(const char *ptr) |
mandoc_strdup(const char *ptr) |
{ |
{ |
Line 467 mandoc_getarg(struct mparse *parse, char **cpp, int ln |
|
Line 474 mandoc_getarg(struct mparse *parse, char **cpp, int ln |
|
|
|
/* Quoting can only start with a new word. */ |
/* Quoting can only start with a new word. */ |
start = *cpp; |
start = *cpp; |
|
quoted = 0; |
if ('"' == *start) { |
if ('"' == *start) { |
quoted = 1; |
quoted = 1; |
start++; |
start++; |
} else |
} |
quoted = 0; |
|
|
|
pairs = 0; |
pairs = 0; |
white = 0; |
white = 0; |
Line 535 a2time(time_t *t, const char *fmt, const char *p) |
|
Line 542 a2time(time_t *t, const char *fmt, const char *p) |
|
|
|
memset(&tm, 0, sizeof(struct tm)); |
memset(&tm, 0, sizeof(struct tm)); |
|
|
|
pp = NULL; |
|
#ifdef 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); |
Line 547 a2time(time_t *t, const char *fmt, const char *p) |
|
Line 557 a2time(time_t *t, const char *fmt, const char *p) |
|
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); |
tm = localtime(&t); |
|
|
/* |
/* |
* Reserve space: |
* Reserve space: |
Line 562 time2a(time_t t) |
|
Line 572 time2a(time_t t) |
|
*/ |
*/ |
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 (0 == (ssz = strftime(p, 10 + 1, "%B ", tm))) |
goto fail; |
goto fail; |
p += (int)ssz; |
p += (int)ssz; |
|
|
if (-1 == (isz = snprintf(p, 4 + 1, "%d, ", tm.tm_mday))) |
if (-1 == (isz = snprintf(p, 4 + 1, "%d, ", tm->tm_mday))) |
goto fail; |
goto fail; |
p += isz; |
p += isz; |
|
|
if (0 == strftime(p, 4 + 1, "%Y", &tm)) |
if (0 == strftime(p, 4 + 1, "%Y", tm)) |
goto fail; |
goto fail; |
return(buf); |
return(buf); |
|
|
Line 612 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
Line 622 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
/* |
/* |
* 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; |
found = 0; |
Line 643 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
Line 653 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
return(found && !enclosed); |
return(found && !enclosed); |
} |
} |
|
|
|
/* |
|
* Choose whether to break at a hyphenated character (identified by the |
|
* ASCII_HYPH value in the input string). |
|
*/ |
int |
int |
mandoc_hyph(const char *start, const char *c) |
mandoc_hyph(const char *start, const char *c) |
{ |
{ |
|
char l, r; |
|
|
/* |
l = *(c - 1); |
* Choose whether to break at a hyphenated character. We only |
r = *(c + 1); |
* do this if it's free-standing within a word. |
|
*/ |
|
|
|
/* Skip first/last character of buffer. */ |
/* Skip first/last character of buffer. */ |
if (c == start || '\0' == *(c + 1)) |
if (c == start || '\0' == r) |
return(0); |
return(0); |
|
|
|
/* Skip a number on either side of the hyphen. */ |
|
if (isdigit((unsigned char)r) || isdigit((unsigned char)l)) |
|
return(0); |
|
|
/* Skip first/last character of word. */ |
/* Skip first/last character of word. */ |
if ('\t' == *(c + 1) || '\t' == *(c - 1)) |
if ('\t' == r || '\t' == l) |
return(0); |
return(0); |
if (' ' == *(c + 1) || ' ' == *(c - 1)) |
|
|
if (' ' == r || ' ' == l) |
return(0); |
return(0); |
|
|
/* Skip double invocations. */ |
/* Skip double invocations. */ |
if ('-' == *(c + 1) || '-' == *(c - 1)) |
if ('-' == r || '-' == l) |
return(0); |
return(0); |
|
|
/* Skip escapes. */ |
/* Skip escapes. */ |
if ('\\' == *(c - 1)) |
if ('\\' == l) |
return(0); |
return(0); |
|
|
return(1); |
return(1); |
Line 694 mandoc_getcontrol(const char *cp, int *ppos) |
|
Line 715 mandoc_getcontrol(const char *cp, int *ppos) |
|
|
|
*ppos = pos; |
*ppos = pos; |
return(1); |
return(1); |
|
} |
|
|
|
/* |
|
* Convert a string to a long that may not be <0. |
|
* If the string is invalid, or is less than 0, return -1. |
|
*/ |
|
int |
|
mandoc_strntoi(const char *p, size_t sz, int base) |
|
{ |
|
char buf[32]; |
|
char *ep; |
|
long v; |
|
|
|
if (sz > 31) |
|
return(-1); |
|
|
|
memcpy(buf, p, sz); |
|
buf[(int)sz] = '\0'; |
|
|
|
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); |
} |
} |