version 1.40, 2011/03/17 09:16:38 |
version 1.53, 2011/05/24 21:31:23 |
|
|
|
|
#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 *); |
|
|
int |
/* |
mandoc_special(char *p) |
* 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 len, i; |
int i; |
char term; |
size_t sz; |
char *sv; |
const char *cp; |
|
|
len = 0; |
|
term = '\0'; |
|
sv = p; |
|
|
|
assert('\\' == *p); |
i = 0; |
p++; |
|
|
|
switch (*p++) { |
/* The expression consists of a subexpression. */ |
#if 0 |
|
case ('Z'): |
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 |
|
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; |
|
term = numeric = '\0'; |
|
|
|
switch ((c = cp[i++])) { |
|
/* |
|
* First the glyphs. There are several different forms of |
|
* these, but each eventually returns a substring of the glyph |
|
* name. |
|
*/ |
|
case ('('): |
|
gly = ESCAPE_SPECIAL; |
|
lim = 2; |
|
break; |
|
case ('['): |
|
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 = ']'; |
|
break; |
|
case ('C'): |
|
if ('\'' != cp[i]) |
|
return(ESCAPE_ERROR); |
|
gly = ESCAPE_SPECIAL; |
|
term = '\''; |
|
break; |
|
|
|
/* |
|
* Handle all triggers matching \X(xy, \Xx, and \X[xxxx], where |
|
* 'X' is the trigger. These have opaque sub-strings. |
|
*/ |
|
case ('F'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('X'): |
case ('g'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('x'): |
case ('k'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('S'): |
case ('M'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('R'): |
case ('m'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('N'): |
case ('n'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('l'): |
case ('V'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('L'): |
case ('Y'): |
|
if (ESCAPE_ERROR == gly) |
|
gly = ESCAPE_IGNORE; |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('H'): |
case ('f'): |
|
if (ESCAPE_ERROR == gly) |
|
gly = ESCAPE_FONT; |
|
|
|
rstart= &cp[i]; |
|
if (start) |
|
*start = rstart; |
|
|
|
switch (cp[i++]) { |
|
case ('('): |
|
lim = 2; |
|
break; |
|
case ('['): |
|
term = ']'; |
|
break; |
|
default: |
|
lim = 1; |
|
i--; |
|
break; |
|
} |
|
break; |
|
|
|
/* |
|
* These escapes are of the form \X'Y', where 'X' is the trigger |
|
* and 'Y' is any string. These have opaque sub-strings. |
|
*/ |
|
case ('A'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('h'): |
case ('b'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('D'): |
case ('D'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('C'): |
case ('o'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('b'): |
case ('R'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('B'): |
case ('X'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case ('a'): |
case ('Z'): |
/* FALLTHROUGH */ |
if ('\'' != cp[i++]) |
case ('A'): |
return(ESCAPE_ERROR); |
if (*p++ != '\'') |
gly = ESCAPE_IGNORE; |
return(0); |
|
term = '\''; |
term = '\''; |
break; |
break; |
#endif |
|
|
/* |
|
* These escapes are of the form \X'N', where 'X' is the trigger |
|
* and 'N' resolves to a numerical expression. |
|
*/ |
|
case ('B'): |
|
/* FALLTHROUGH */ |
case ('h'): |
case ('h'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
|
case ('H'): |
|
/* FALLTHROUGH */ |
|
case ('L'): |
|
/* FALLTHROUGH */ |
|
case ('l'): |
|
/* FALLTHROUGH */ |
|
case ('N'): |
|
if (ESCAPE_ERROR == gly) |
|
gly = ESCAPE_NUMBERED; |
|
/* FALLTHROUGH */ |
|
case ('S'): |
|
/* FALLTHROUGH */ |
case ('v'): |
case ('v'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
|
case ('w'): |
|
/* FALLTHROUGH */ |
|
case ('x'): |
|
if (ESCAPE_ERROR == gly) |
|
gly = ESCAPE_IGNORE; |
|
if ('\'' != cp[i++]) |
|
return(ESCAPE_ERROR); |
|
term = numeric = '\''; |
|
break; |
|
|
|
/* |
|
* Sizes get a special category of their own. |
|
*/ |
case ('s'): |
case ('s'): |
if (ASCII_HYPH == *p) |
gly = ESCAPE_IGNORE; |
*p = '-'; |
|
|
|
i = 0; |
rstart = &cp[i]; |
if ('+' == *p || '-' == *p) { |
if (start) |
p++; |
*start = rstart; |
i = 1; |
|
} |
|
|
|
switch (*p++) { |
/* See +/- counts as a sign. */ |
|
c = cp[i]; |
|
if ('+' == c || '-' == c || ASCII_HYPH == c) |
|
++i; |
|
|
|
switch (cp[i++]) { |
case ('('): |
case ('('): |
len = 2; |
lim = 2; |
break; |
break; |
case ('['): |
case ('['): |
term = ']'; |
term = numeric = ']'; |
break; |
break; |
case ('\''): |
case ('\''): |
term = '\''; |
term = numeric = '\''; |
break; |
break; |
case ('0'): |
|
i = 1; |
|
/* FALLTHROUGH */ |
|
default: |
default: |
len = 1; |
lim = 1; |
p--; |
i--; |
break; |
break; |
} |
} |
|
|
if (ASCII_HYPH == *p) |
/* See +/- counts as a sign. */ |
*p = '-'; |
c = cp[i]; |
if ('+' == *p || '-' == *p) { |
if ('+' == c || '-' == c || ASCII_HYPH == c) |
if (i) |
++i; |
return(0); |
|
p++; |
|
} |
|
|
|
/* Handle embedded numerical subexp or escape. */ |
|
|
|
if ('(' == *p) { |
break; |
while (*p && ')' != *p) |
|
if ('\\' == *p++) { |
|
i = mandoc_special(--p); |
|
if (0 == i) |
|
return(0); |
|
p += i; |
|
} |
|
|
|
if (')' == *p++) |
/* |
break; |
* Anything else is assumed to be a glyph. |
|
*/ |
|
default: |
|
gly = ESCAPE_SPECIAL; |
|
lim = 1; |
|
i--; |
|
break; |
|
} |
|
|
return(0); |
assert(ESCAPE_ERROR != gly); |
} else if ('\\' == *p) { |
|
if (0 == (i = mandoc_special(p))) |
|
return(0); |
|
p += i; |
|
} |
|
|
|
break; |
rstart = &cp[i]; |
#if 0 |
if (start) |
case ('Y'): |
*start = rstart; |
/* FALLTHROUGH */ |
|
case ('V'): |
/* |
/* FALLTHROUGH */ |
* If a terminating block has been specified, we need to |
case ('$'): |
* handle the case of recursion, which could have their |
/* FALLTHROUGH */ |
* own terminating blocks that mess up our parse. This, by the |
case ('n'): |
* way, means that the "start" and "size" values will be |
/* FALLTHROUGH */ |
* effectively meaningless. |
#endif |
*/ |
case ('k'): |
|
/* FALLTHROUGH */ |
ssz = 0; |
case ('M'): |
if (numeric && -1 == (ssz = numescape(&cp[i]))) |
/* FALLTHROUGH */ |
return(ESCAPE_ERROR); |
case ('m'): |
|
/* FALLTHROUGH */ |
i += ssz; |
case ('f'): |
rlim = -1; |
/* FALLTHROUGH */ |
|
case ('F'): |
/* |
/* FALLTHROUGH */ |
* We have a character terminator. Try to read up to that |
case ('*'): |
* character. If we can't (i.e., we hit the nil), then return |
switch (*p++) { |
* an error; if we can, calculate our length, read past the |
case ('('): |
* terminating character, and exit. |
len = 2; |
*/ |
|
|
|
if ('\0' != term) { |
|
*end = strchr(&cp[i], term); |
|
if ('\0' == *end) |
|
return(ESCAPE_ERROR); |
|
|
|
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. */ |
|
|
|
switch (gly) { |
|
case (ESCAPE_FONT): |
|
if (1 != rlim) |
break; |
break; |
case ('['): |
switch (*rstart) { |
term = ']'; |
case ('3'): |
|
/* FALLTHROUGH */ |
|
case ('B'): |
|
gly = ESCAPE_FONTBOLD; |
break; |
break; |
default: |
case ('2'): |
len = 1; |
/* FALLTHROUGH */ |
p--; |
case ('I'): |
|
gly = ESCAPE_FONTITALIC; |
break; |
break; |
|
case ('P'): |
|
gly = ESCAPE_FONTPREV; |
|
break; |
|
case ('1'): |
|
/* FALLTHROUGH */ |
|
case ('R'): |
|
gly = ESCAPE_FONTROMAN; |
|
break; |
} |
} |
break; |
break; |
case ('('): |
case (ESCAPE_SPECIAL): |
len = 2; |
if (1 != rlim) |
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; |
break; |
} |
if ('c' == *rstart) |
/* FALLTHROUGH */ |
gly = ESCAPE_NOSPACE; |
|
break; |
default: |
default: |
len = 1; |
|
p--; |
|
break; |
break; |
} |
} |
|
|
if (term) { |
return(gly); |
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 * |
void * |
mandoc_calloc(size_t num, size_t size) |
mandoc_calloc(size_t num, size_t size) |
{ |
{ |
Line 296 mandoc_strdup(const char *ptr) |
|
Line 457 mandoc_strdup(const char *ptr) |
|
* or to the null byte terminating the argument line. |
* or to the null byte terminating the argument line. |
*/ |
*/ |
char * |
char * |
mandoc_getarg(char **cpp, mandocmsg msg, void *data, int ln, int *pos) |
mandoc_getarg(struct mparse *parse, char **cpp, int ln, int *pos) |
{ |
{ |
char *start, *cp; |
char *start, *cp; |
int quoted, pairs, white; |
int quoted, pairs, white; |
|
|
/* 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 343 mandoc_getarg(char **cpp, mandocmsg msg, void *data, i |
|
Line 504 mandoc_getarg(char **cpp, mandocmsg msg, void *data, i |
|
} |
} |
|
|
/* Quoted argument without a closing quote. */ |
/* Quoted argument without a closing quote. */ |
if (1 == quoted && msg) |
if (1 == quoted) |
(*msg)(MANDOCERR_BADQUOTE, data, ln, *pos, NULL); |
mandoc_msg(MANDOCERR_BADQUOTE, parse, ln, *pos, NULL); |
|
|
/* Null-terminate this argument and move to the next one. */ |
/* Null-terminate this argument and move to the next one. */ |
if (pairs) |
if (pairs) |
Line 357 mandoc_getarg(char **cpp, mandocmsg msg, void *data, i |
|
Line 518 mandoc_getarg(char **cpp, mandocmsg msg, void *data, i |
|
*pos += (int)(cp - start) + (quoted ? 1 : 0); |
*pos += (int)(cp - start) + (quoted ? 1 : 0); |
*cpp = cp; |
*cpp = cp; |
|
|
if ('\0' == *cp && msg && (white || ' ' == cp[-1])) |
if ('\0' == *cp && (white || ' ' == cp[-1])) |
(*msg)(MANDOCERR_EOLNSPACE, data, ln, *pos, NULL); |
mandoc_msg(MANDOCERR_EOLNSPACE, parse, ln, *pos, NULL); |
|
|
return(start); |
return(start); |
} |
} |
|
|
} |
} |
|
|
char * |
char * |
mandoc_normdate(char *in, mandocmsg msg, void *data, int ln, int pos) |
mandoc_normdate(struct mparse *parse, char *in, int ln, int pos) |
{ |
{ |
char *out; |
char *out; |
time_t t; |
time_t t; |
|
|
if (NULL == in || '\0' == *in || |
if (NULL == in || '\0' == *in || |
0 == strcmp(in, "$" "Mdocdate$")) { |
0 == strcmp(in, "$" "Mdocdate$")) { |
(*msg)(MANDOCERR_NODATE, data, ln, pos, NULL); |
mandoc_msg(MANDOCERR_NODATE, parse, ln, pos, NULL); |
time(&t); |
time(&t); |
} |
} |
else if (!a2time(&t, "$" "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)) { |
!a2time(&t, "%Y-%m-%d", in)) { |
(*msg)(MANDOCERR_BADDATE, data, ln, pos, NULL); |
mandoc_msg(MANDOCERR_BADDATE, parse, ln, pos, NULL); |
t = 0; |
t = 0; |
} |
} |
out = t ? time2a(t) : NULL; |
out = t ? time2a(t) : NULL; |
Line 448 mandoc_eos(const char *p, size_t sz, int enclosed) |
|
Line 609 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 507 mandoc_hyph(const char *start, const char *c) |
|
Line 668 mandoc_hyph(const char *start, const char *c) |
|
} |
} |
|
|
/* |
/* |
* Check if a string is a punctuation delimiter. This only applies to |
* Find out whether a line is a macro line or not. If it is, adjust the |
* mdoc(7) documents, but as it's used in both front-ends and back-ends, |
* current position and return one; if it isn't, return zero and don't |
* it needs to go here (instead of, say, in libmdoc.h). |
* change the current position. |
*/ |
*/ |
enum mdelim |
int |
mandoc_isdelim(const char *p) |
mandoc_getcontrol(const char *cp, int *ppos) |
{ |
{ |
|
int pos; |
|
|
if ('\0' == p[0]) |
pos = *ppos; |
return(DELIM_NONE); |
|
|
|
if ('\0' == p[1]) |
if ('\\' == cp[pos] && '.' == cp[pos + 1]) |
switch (p[0]) { |
pos += 2; |
case('('): |
else if ('.' == cp[pos] || '\'' == cp[pos]) |
/* FALLTHROUGH */ |
pos++; |
case('['): |
else |
return(DELIM_OPEN); |
return(0); |
case('|'): |
|
return(DELIM_MIDDLE); |
|
case('.'): |
|
/* FALLTHROUGH */ |
|
case(','): |
|
/* FALLTHROUGH */ |
|
case(';'): |
|
/* FALLTHROUGH */ |
|
case(':'): |
|
/* FALLTHROUGH */ |
|
case('?'): |
|
/* FALLTHROUGH */ |
|
case('!'): |
|
/* FALLTHROUGH */ |
|
case(')'): |
|
/* FALLTHROUGH */ |
|
case(']'): |
|
return(DELIM_CLOSE); |
|
default: |
|
return(DELIM_NONE); |
|
} |
|
|
|
if ('\\' != p[0]) |
while (' ' == cp[pos] || '\t' == cp[pos]) |
return(DELIM_NONE); |
pos++; |
|
|
if (0 == strcmp(p, "\\.")) |
*ppos = pos; |
return(DELIM_CLOSE); |
return(1); |
if (0 == strcmp(p, "\\*(Ba")) |
} |
return(DELIM_MIDDLE); |
|
|
|
return(DELIM_NONE); |
/* |
|
* 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_strntou(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 ((errno == ERANGE && |
|
(v == LONG_MAX || v == LONG_MIN)) || |
|
(v > INT_MAX || v < 0)) |
|
return(-1); |
|
|
|
return((int)v); |
} |
} |
|
|