version 1.48, 2011/04/19 16:38:48 |
version 1.64, 2012/05/31 22:34:06 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2008, 2009, 2010 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2011 Ingo Schwarze <schwarze@openbsd.org> |
* Copyright (c) 2011, 2012 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 |
|
|
|
|
#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> |
|
|
|
|
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); |
static int numescape(const char *); |
|
|
|
/* |
|
* Pass over recursive numerical expressions. This context of this |
|
* function is important: it's only called within character-terminating |
|
* escapes (e.g., \s[xxxyyy]), so all we need to do is handle initial |
|
* recursion: we don't care about what's in these blocks. |
|
* This returns the number of characters skipped or -1 if an error |
|
* occurs (the caller should bail). |
|
*/ |
|
static int |
|
numescape(const char *start) |
|
{ |
|
int i; |
|
size_t sz; |
|
const char *cp; |
|
|
|
i = 0; |
|
|
|
/* The expression consists of a subexpression. */ |
|
|
|
if ('\\' == start[i]) { |
|
cp = &start[++i]; |
|
/* |
|
* Read past the end of the subexpression. |
|
* Bail immediately on errors. |
|
*/ |
|
if (ESCAPE_ERROR == mandoc_escape(&cp, NULL, NULL)) |
|
return(-1); |
|
return(i + cp - &start[i]); |
|
} |
|
|
|
if ('(' != start[i++]) |
|
return(0); |
|
|
|
/* |
|
* A parenthesised subexpression. Read until the closing |
|
* parenthesis, making sure to handle any nested subexpressions |
|
* that might ruin our parse. |
|
*/ |
|
|
|
while (')' != start[i]) { |
|
sz = strcspn(&start[i], ")\\"); |
|
i += (int)sz; |
|
|
|
if ('\0' == start[i]) |
|
return(-1); |
|
else if ('\\' != start[i]) |
|
continue; |
|
|
|
cp = &start[++i]; |
|
if (ESCAPE_ERROR == mandoc_escape(&cp, NULL, NULL)) |
|
return(-1); |
|
i += cp - &start[i]; |
|
} |
|
|
|
/* Read past the terminating ')'. */ |
|
return(++i); |
|
} |
|
|
|
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) |
{ |
{ |
char c, term, numeric; |
char c, term; |
int i, lim, ssz, rlim; |
int i, rlim; |
const char *cp, *rstart; |
const char *cp, *rstart; |
enum mandoc_esc gly; |
enum mandoc_esc gly; |
|
|
Line 107 mandoc_escape(const char **end, const char **start, in |
|
Line 51 mandoc_escape(const char **end, const char **start, in |
|
rstart = cp; |
rstart = cp; |
if (start) |
if (start) |
*start = rstart; |
*start = rstart; |
i = lim = 0; |
i = rlim = 0; |
gly = ESCAPE_ERROR; |
gly = ESCAPE_ERROR; |
term = numeric = '\0'; |
term = '\0'; |
|
|
switch ((c = cp[i++])) { |
switch ((c = cp[i++])) { |
/* |
/* |
Line 119 mandoc_escape(const char **end, const char **start, in |
|
Line 63 mandoc_escape(const char **end, const char **start, in |
|
*/ |
*/ |
case ('('): |
case ('('): |
gly = ESCAPE_SPECIAL; |
gly = ESCAPE_SPECIAL; |
lim = 2; |
rlim = 2; |
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 133 mandoc_escape(const char **end, const char **start, in |
|
Line 85 mandoc_escape(const char **end, const char **start, in |
|
break; |
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'): |
|
(*end)++; |
|
return(ESCAPE_SKIPCHAR); |
|
|
|
/* |
* Handle all triggers matching \X(xy, \Xx, and \X[xxxx], where |
* Handle all triggers matching \X(xy, \Xx, and \X[xxxx], where |
* 'X' is the trigger. These have opaque sub-strings. |
* 'X' is the trigger. These have opaque sub-strings. |
*/ |
*/ |
Line 151 mandoc_escape(const char **end, const char **start, in |
|
Line 113 mandoc_escape(const char **end, const char **start, in |
|
case ('V'): |
case ('V'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('Y'): |
case ('Y'): |
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; |
Line 168 mandoc_escape(const char **end, const char **start, in |
|
Line 125 mandoc_escape(const char **end, const char **start, in |
|
|
|
switch (cp[i++]) { |
switch (cp[i++]) { |
case ('('): |
case ('('): |
lim = 2; |
rlim = 2; |
break; |
break; |
case ('['): |
case ('['): |
term = ']'; |
term = ']'; |
break; |
break; |
default: |
default: |
lim = 1; |
rlim = 1; |
i--; |
i--; |
break; |
break; |
} |
} |
Line 216 mandoc_escape(const char **end, const char **start, in |
|
Line 173 mandoc_escape(const char **end, const char **start, in |
|
case ('L'): |
case ('L'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('l'): |
case ('l'): |
|
gly = ESCAPE_NUMBERED; |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('N'): |
|
if (ESCAPE_ERROR == gly) |
|
gly = ESCAPE_NUMBERED; |
|
/* FALLTHROUGH */ |
|
case ('S'): |
case ('S'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('v'): |
case ('v'): |
Line 232 mandoc_escape(const char **end, const char **start, in |
|
Line 186 mandoc_escape(const char **end, const char **start, in |
|
gly = ESCAPE_IGNORE; |
gly = ESCAPE_IGNORE; |
if ('\'' != cp[i++]) |
if ('\'' != cp[i++]) |
return(ESCAPE_ERROR); |
return(ESCAPE_ERROR); |
term = numeric = '\''; |
term = '\''; |
break; |
break; |
|
|
|
/* |
|
* Special handling for the numbered character escape. |
|
* XXX Do any other escapes need similar handling? |
|
*/ |
|
case ('N'): |
|
if ('\0' == cp[i]) |
|
return(ESCAPE_ERROR); |
|
*end = &cp[++i]; |
|
if (isdigit((unsigned char)cp[i-1])) |
|
return(ESCAPE_IGNORE); |
|
while (isdigit((unsigned char)**end)) |
|
(*end)++; |
|
if (start) |
|
*start = &cp[i]; |
|
if (sz) |
|
*sz = *end - &cp[i]; |
|
if ('\0' != **end) |
|
(*end)++; |
|
return(ESCAPE_NUMBERED); |
|
|
/* |
/* |
* Sizes get a special category of their own. |
* Sizes get a special category of their own. |
*/ |
*/ |
Line 252 mandoc_escape(const char **end, const char **start, in |
|
Line 226 mandoc_escape(const char **end, const char **start, in |
|
|
|
switch (cp[i++]) { |
switch (cp[i++]) { |
case ('('): |
case ('('): |
lim = 2; |
rlim = 2; |
break; |
break; |
case ('['): |
case ('['): |
term = numeric = ']'; |
term = ']'; |
break; |
break; |
case ('\''): |
case ('\''): |
term = numeric = '\''; |
term = '\''; |
break; |
break; |
default: |
default: |
lim = 1; |
rlim = 1; |
i--; |
i--; |
break; |
break; |
} |
} |
Line 278 mandoc_escape(const char **end, const char **start, in |
|
Line 252 mandoc_escape(const char **end, const char **start, in |
|
*/ |
*/ |
default: |
default: |
gly = ESCAPE_SPECIAL; |
gly = ESCAPE_SPECIAL; |
lim = 1; |
rlim = 1; |
i--; |
i--; |
break; |
break; |
} |
} |
|
|
assert(ESCAPE_ERROR != gly); |
assert(ESCAPE_ERROR != gly); |
|
|
rstart = &cp[i]; |
*end = rstart = &cp[i]; |
if (start) |
if (start) |
*start = rstart; |
*start = rstart; |
|
|
/* |
/* |
* If a terminating block has been specified, we need to |
* Read up to the terminating character, |
* handle the case of recursion, which could have their |
* paying attention to nested escapes. |
* own terminating blocks that mess up our parse. This, by the |
|
* way, means that the "start" and "size" values will be |
|
* effectively meaningless. |
|
*/ |
*/ |
|
|
ssz = 0; |
|
if (numeric && -1 == (ssz = numescape(&cp[i]))) |
|
return(ESCAPE_ERROR); |
|
|
|
i += ssz; |
|
rlim = -1; |
|
|
|
/* |
|
* We have a character terminator. Try to read up to that |
|
* character. If we can't (i.e., we hit the nil), then return |
|
* an error; if we can, calculate our length, read past the |
|
* terminating character, and exit. |
|
*/ |
|
|
|
if ('\0' != term) { |
if ('\0' != term) { |
*end = strchr(&cp[i], term); |
while (**end != term) { |
if ('\0' == *end) |
switch (**end) { |
|
case ('\0'): |
|
return(ESCAPE_ERROR); |
|
case ('\\'): |
|
(*end)++; |
|
if (ESCAPE_ERROR == |
|
mandoc_escape(end, NULL, NULL)) |
|
return(ESCAPE_ERROR); |
|
break; |
|
default: |
|
(*end)++; |
|
break; |
|
} |
|
} |
|
rlim = (*end)++ - rstart; |
|
} else { |
|
assert(rlim > 0); |
|
if ((size_t)rlim > strlen(rstart)) |
return(ESCAPE_ERROR); |
return(ESCAPE_ERROR); |
|
*end += rlim; |
rlim = *end - &cp[i]; |
|
if (sz) |
|
*sz = rlim; |
|
(*end)++; |
|
goto out; |
|
} |
} |
|
|
assert(lim > 0); |
|
|
|
/* |
|
* We have a numeric limit. If the string is shorter than that, |
|
* stop and return an error. Else adjust our endpoint, length, |
|
* and return the current glyph. |
|
*/ |
|
|
|
if ((size_t)lim > strlen(&cp[i])) |
|
return(ESCAPE_ERROR); |
|
|
|
rlim = lim; |
|
if (sz) |
if (sz) |
*sz = rlim; |
*sz = rlim; |
|
|
*end = &cp[i] + lim; |
|
|
|
out: |
|
assert(rlim >= 0 && rstart); |
|
|
|
/* Run post-processors. */ |
/* Run post-processors. */ |
|
|
switch (gly) { |
switch (gly) { |
case (ESCAPE_FONT): |
case (ESCAPE_FONT): |
if (1 != rlim) |
/* |
|
* Pretend that the constant-width font modes are the |
|
* same as the regular font modes. |
|
*/ |
|
if (2 == rlim && 'C' == *rstart) |
|
rstart++; |
|
else if (1 != rlim) |
break; |
break; |
|
|
switch (*rstart) { |
switch (*rstart) { |
case ('3'): |
case ('3'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
Line 426 mandoc_realloc(void *ptr, size_t size) |
|
Line 384 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 526 a2time(time_t *t, const char *fmt, const char *p) |
|
Line 494 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 538 a2time(time_t *t, const char *fmt, const char *p) |
|
Line 509 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 553 time2a(time_t t) |
|
Line 524 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 581 mandoc_normdate(struct mparse *parse, char *in, int ln |
|
Line 552 mandoc_normdate(struct mparse *parse, char *in, int ln |
|
mandoc_msg(MANDOCERR_NODATE, parse, ln, pos, NULL); |
mandoc_msg(MANDOCERR_NODATE, parse, ln, pos, NULL); |
time(&t); |
time(&t); |
} |
} |
|
else if (a2time(&t, "%Y-%m-%d", in)) |
|
t = 0; |
else if (!a2time(&t, "$" "Mdocdate: %b %d %Y $", in) && |
else if (!a2time(&t, "$" "Mdocdate: %b %d %Y $", in) && |
!a2time(&t, "%b %d, %Y", in) && |
!a2time(&t, "%b %d, %Y", in)) { |
!a2time(&t, "%Y-%m-%d", in)) { |
|
mandoc_msg(MANDOCERR_BADDATE, parse, ln, pos, NULL); |
mandoc_msg(MANDOCERR_BADDATE, parse, ln, pos, NULL); |
t = 0; |
t = 0; |
} |
} |
Line 603 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
Line 575 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 634 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
Line 606 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
return(found && !enclosed); |
return(found && !enclosed); |
} |
} |
|
|
int |
|
mandoc_hyph(const char *start, const char *c) |
|
{ |
|
|
|
/* |
|
* Choose whether to break at a hyphenated character. We only |
|
* do this if it's free-standing within a word. |
|
*/ |
|
|
|
/* Skip first/last character of buffer. */ |
|
if (c == start || '\0' == *(c + 1)) |
|
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); |
|
} |
|
|
|
/* |
/* |
* Find out whether a line is a macro line or not. If it is, adjust the |
* Find out whether a line is a macro line or not. If it is, adjust the |
* current position and return one; if it isn't, return zero and don't |
* current position and return one; if it isn't, return zero and don't |
Line 685 mandoc_getcontrol(const char *cp, int *ppos) |
|
Line 630 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); |
} |
} |