version 1.63, 2012/05/31 22:29:13 |
version 1.69, 2013/10/05 20:30:05 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2011, 2012 Ingo Schwarze <schwarze@openbsd.org> |
* Copyright (c) 2011, 2012, 2013 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 |
|
|
|
|
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 |
enum mandoc_esc |
* function is important: it's only called within character-terminating |
mandoc_escape(const char const **end, const char const **start, int *sz) |
* 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; |
const char *local_start; |
size_t sz; |
int local_sz; |
const char *cp; |
char term; |
|
enum mandoc_esc gly; |
|
|
i = 0; |
/* |
|
* When the caller doesn't provide return storage, |
|
* use local storage. |
|
*/ |
|
|
/* The expression consists of a subexpression. */ |
if (NULL == start) |
|
start = &local_start; |
|
if (NULL == sz) |
|
sz = &local_sz; |
|
|
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 |
* Beyond the backslash, at least one input character |
* parenthesis, making sure to handle any nested subexpressions |
* is part of the escape sequence. With one exception |
* that might ruin our parse. |
* (see below), that character won't be returned. |
*/ |
*/ |
|
|
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 |
|
mandoc_escape(const char **end, const char **start, int *sz) |
|
{ |
|
char c, term, numeric; |
|
int i, lim, ssz, rlim; |
|
const char *cp, *rstart; |
|
enum mandoc_esc gly; |
|
|
|
cp = *end; |
|
rstart = cp; |
|
if (start) |
|
*start = rstart; |
|
i = lim = 0; |
|
gly = ESCAPE_ERROR; |
gly = ESCAPE_ERROR; |
term = numeric = '\0'; |
*start = ++*end; |
|
*sz = 0; |
|
term = '\0'; |
|
|
switch ((c = cp[i++])) { |
switch ((*start)[-1]) { |
/* |
/* |
* First the glyphs. There are several different forms of |
* First the glyphs. There are several different forms of |
* these, but each eventually returns a substring of the glyph |
* these, but each eventually returns a substring of the glyph |
Line 121 mandoc_escape(const char **end, const char **start, in |
|
Line 76 mandoc_escape(const char **end, const char **start, in |
|
*/ |
*/ |
case ('('): |
case ('('): |
gly = ESCAPE_SPECIAL; |
gly = ESCAPE_SPECIAL; |
lim = 2; |
*sz = 2; |
break; |
break; |
case ('['): |
case ('['): |
gly = ESCAPE_SPECIAL; |
gly = ESCAPE_SPECIAL; |
Line 131 mandoc_escape(const char **end, const char **start, in |
|
Line 86 mandoc_escape(const char **end, const char **start, in |
|
* Unicode codepoint. Here, however, only check whether |
* Unicode codepoint. Here, however, only check whether |
* it's not a zero-width escape. |
* it's not a zero-width escape. |
*/ |
*/ |
if ('u' == cp[i] && ']' != cp[i + 1]) |
if ('u' == (*start)[0] && ']' != (*start)[1]) |
gly = ESCAPE_UNICODE; |
gly = ESCAPE_UNICODE; |
term = ']'; |
term = ']'; |
break; |
break; |
case ('C'): |
case ('C'): |
if ('\'' != cp[i]) |
if ('\'' != **start) |
return(ESCAPE_ERROR); |
return(ESCAPE_ERROR); |
gly = ESCAPE_SPECIAL; |
gly = ESCAPE_SPECIAL; |
|
*start = ++*end; |
term = '\''; |
term = '\''; |
break; |
break; |
|
|
Line 149 mandoc_escape(const char **end, const char **start, in |
|
Line 105 mandoc_escape(const char **end, const char **start, in |
|
* let us just skip the next character. |
* let us just skip the next character. |
*/ |
*/ |
case ('z'): |
case ('z'): |
(*end)++; |
|
return(ESCAPE_SKIPCHAR); |
return(ESCAPE_SKIPCHAR); |
|
|
/* |
/* |
Line 176 mandoc_escape(const char **end, const char **start, in |
|
Line 131 mandoc_escape(const char **end, const char **start, in |
|
case ('f'): |
case ('f'): |
if (ESCAPE_ERROR == gly) |
if (ESCAPE_ERROR == gly) |
gly = ESCAPE_FONT; |
gly = ESCAPE_FONT; |
|
switch (**start) { |
rstart= &cp[i]; |
|
if (start) |
|
*start = rstart; |
|
|
|
switch (cp[i++]) { |
|
case ('('): |
case ('('): |
lim = 2; |
*start = ++*end; |
|
*sz = 2; |
break; |
break; |
case ('['): |
case ('['): |
|
*start = ++*end; |
term = ']'; |
term = ']'; |
break; |
break; |
default: |
default: |
lim = 1; |
*sz = 1; |
i--; |
|
break; |
break; |
} |
} |
break; |
break; |
Line 212 mandoc_escape(const char **end, const char **start, in |
|
Line 163 mandoc_escape(const char **end, const char **start, in |
|
case ('X'): |
case ('X'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('Z'): |
case ('Z'): |
if ('\'' != cp[i++]) |
if ('\'' != **start) |
return(ESCAPE_ERROR); |
return(ESCAPE_ERROR); |
gly = ESCAPE_IGNORE; |
gly = ESCAPE_IGNORE; |
|
*start = ++*end; |
term = '\''; |
term = '\''; |
break; |
break; |
|
|
Line 240 mandoc_escape(const char **end, const char **start, in |
|
Line 192 mandoc_escape(const char **end, const char **start, in |
|
case ('w'): |
case ('w'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('x'): |
case ('x'): |
|
if ('\'' != **start) |
|
return(ESCAPE_ERROR); |
if (ESCAPE_ERROR == gly) |
if (ESCAPE_ERROR == gly) |
gly = ESCAPE_IGNORE; |
gly = ESCAPE_IGNORE; |
if ('\'' != cp[i++]) |
*start = ++*end; |
return(ESCAPE_ERROR); |
term = '\''; |
term = numeric = '\''; |
|
break; |
break; |
|
|
/* |
/* |
Line 252 mandoc_escape(const char **end, const char **start, in |
|
Line 205 mandoc_escape(const char **end, const char **start, in |
|
* XXX Do any other escapes need similar handling? |
* XXX Do any other escapes need similar handling? |
*/ |
*/ |
case ('N'): |
case ('N'): |
if ('\0' == cp[i]) |
if ('\0' == **start) |
return(ESCAPE_ERROR); |
return(ESCAPE_ERROR); |
*end = &cp[++i]; |
(*end)++; |
if (isdigit((unsigned char)cp[i-1])) |
if (isdigit((unsigned char)**start)) { |
|
*sz = 1; |
return(ESCAPE_IGNORE); |
return(ESCAPE_IGNORE); |
|
} |
|
(*start)++; |
while (isdigit((unsigned char)**end)) |
while (isdigit((unsigned char)**end)) |
(*end)++; |
(*end)++; |
if (start) |
*sz = *end - *start; |
*start = &cp[i]; |
|
if (sz) |
|
*sz = *end - &cp[i]; |
|
if ('\0' != **end) |
if ('\0' != **end) |
(*end)++; |
(*end)++; |
return(ESCAPE_NUMBERED); |
return(ESCAPE_NUMBERED); |
Line 273 mandoc_escape(const char **end, const char **start, in |
|
Line 226 mandoc_escape(const char **end, const char **start, in |
|
case ('s'): |
case ('s'): |
gly = ESCAPE_IGNORE; |
gly = ESCAPE_IGNORE; |
|
|
rstart = &cp[i]; |
|
if (start) |
|
*start = rstart; |
|
|
|
/* See +/- counts as a sign. */ |
/* See +/- counts as a sign. */ |
c = cp[i]; |
if ('+' == **end || '-' == **end || ASCII_HYPH == **end) |
if ('+' == c || '-' == c || ASCII_HYPH == c) |
(*end)++; |
++i; |
|
|
|
switch (cp[i++]) { |
switch (**end) { |
case ('('): |
case ('('): |
lim = 2; |
*start = ++*end; |
|
*sz = 2; |
break; |
break; |
case ('['): |
case ('['): |
term = numeric = ']'; |
*start = ++*end; |
|
term = ']'; |
break; |
break; |
case ('\''): |
case ('\''): |
term = numeric = '\''; |
*start = ++*end; |
|
term = '\''; |
break; |
break; |
default: |
default: |
lim = 1; |
*sz = 1; |
i--; |
|
break; |
break; |
} |
} |
|
|
/* See +/- counts as a sign. */ |
|
c = cp[i]; |
|
if ('+' == c || '-' == c || ASCII_HYPH == c) |
|
++i; |
|
|
|
break; |
break; |
|
|
/* |
/* |
* Anything else is assumed to be a glyph. |
* Anything else is assumed to be a glyph. |
|
* In this case, pass back the character after the backslash. |
*/ |
*/ |
default: |
default: |
gly = ESCAPE_SPECIAL; |
gly = ESCAPE_SPECIAL; |
lim = 1; |
*start = --*end; |
i--; |
*sz = 1; |
break; |
break; |
} |
} |
|
|
assert(ESCAPE_ERROR != gly); |
assert(ESCAPE_ERROR != gly); |
|
|
rstart = &cp[i]; |
|
if (start) |
|
*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; |
|
} |
|
} |
|
*sz = (*end)++ - *start; |
|
} else { |
|
assert(*sz > 0); |
|
if ((size_t)*sz > strlen(*start)) |
return(ESCAPE_ERROR); |
return(ESCAPE_ERROR); |
|
*end += *sz; |
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) |
|
*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 (2 == *sz) { |
* Pretend that the constant-width font modes are the |
if ('C' == **start) { |
* same as the regular font modes. |
/* |
*/ |
* Treat constant-width font modes |
if (2 == rlim && 'C' == *rstart) |
* just like regular font modes. |
rstart++; |
*/ |
else if (1 != rlim) |
(*start)++; |
|
(*sz)--; |
|
} else { |
|
if ('B' == (*start)[0] && 'I' == (*start)[1]) |
|
gly = ESCAPE_FONTBI; |
|
break; |
|
} |
|
} else if (1 != *sz) |
break; |
break; |
|
|
switch (*rstart) { |
switch (**start) { |
case ('3'): |
case ('3'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('B'): |
case ('B'): |
|
|
} |
} |
break; |
break; |
case (ESCAPE_SPECIAL): |
case (ESCAPE_SPECIAL): |
if (1 != rlim) |
if (1 == *sz && 'c' == **start) |
break; |
|
if ('c' == *rstart) |
|
gly = ESCAPE_NOSPACE; |
gly = ESCAPE_NOSPACE; |
break; |
break; |
default: |
default: |
Line 516 mandoc_getarg(struct mparse *parse, char **cpp, int ln |
|
Line 438 mandoc_getarg(struct mparse *parse, char **cpp, int ln |
|
pairs = 0; |
pairs = 0; |
white = 0; |
white = 0; |
for (cp = start; '\0' != *cp; cp++) { |
for (cp = start; '\0' != *cp; cp++) { |
/* Move left after quoted quotes and escaped backslashes. */ |
|
|
/* |
|
* Move the following text left |
|
* after quoted quotes and after "\\" and "\t". |
|
*/ |
if (pairs) |
if (pairs) |
cp[-pairs] = cp[0]; |
cp[-pairs] = cp[0]; |
|
|
if ('\\' == cp[0]) { |
if ('\\' == cp[0]) { |
if ('\\' == cp[1]) { |
/* |
/* Poor man's copy mode. */ |
* In copy mode, translate double to single |
|
* backslashes and backslash-t to literal tabs. |
|
*/ |
|
switch (cp[1]) { |
|
case ('t'): |
|
cp[0] = '\t'; |
|
/* FALLTHROUGH */ |
|
case ('\\'): |
pairs++; |
pairs++; |
cp++; |
cp++; |
} else if (0 == quoted && ' ' == cp[1]) |
break; |
|
case (' '): |
/* Skip escaped blanks. */ |
/* Skip escaped blanks. */ |
cp++; |
if (0 == quoted) |
|
cp++; |
|
break; |
|
default: |
|
break; |
|
} |
} else if (0 == quoted) { |
} else if (0 == quoted) { |
if (' ' == cp[0]) { |
if (' ' == cp[0]) { |
/* Unescaped blanks end unquoted args. */ |
/* Unescaped blanks end unquoted args. */ |
Line 685 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
Line 625 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
} |
} |
|
|
return(found && !enclosed); |
return(found && !enclosed); |
} |
|
|
|
/* |
|
* 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 |
|
* change the current position. |
|
*/ |
|
int |
|
mandoc_getcontrol(const char *cp, int *ppos) |
|
{ |
|
int pos; |
|
|
|
pos = *ppos; |
|
|
|
if ('\\' == cp[pos] && '.' == cp[pos + 1]) |
|
pos += 2; |
|
else if ('.' == cp[pos] || '\'' == cp[pos]) |
|
pos++; |
|
else |
|
return(0); |
|
|
|
while (' ' == cp[pos] || '\t' == cp[pos]) |
|
pos++; |
|
|
|
*ppos = pos; |
|
return(1); |
|
} |
} |
|
|
/* |
/* |