📄 regex.c
字号:
putchar (']');
p += 1 + *p;
}
break;
case begline:
printf ("/begline");
break;
case endline:
printf ("/endline");
break;
case on_failure_jump:
extract_number_and_incr (&mcnt, &p);
printf ("/on_failure_jump to %d", p + mcnt - start);
break;
case on_failure_keep_string_jump:
extract_number_and_incr (&mcnt, &p);
printf ("/on_failure_keep_string_jump to %d", p + mcnt - start);
break;
case dummy_failure_jump:
extract_number_and_incr (&mcnt, &p);
printf ("/dummy_failure_jump to %d", p + mcnt - start);
break;
case push_dummy_failure:
printf ("/push_dummy_failure");
break;
case maybe_pop_jump:
extract_number_and_incr (&mcnt, &p);
printf ("/maybe_pop_jump to %d", p + mcnt - start);
break;
case pop_failure_jump:
extract_number_and_incr (&mcnt, &p);
printf ("/pop_failure_jump to %d", p + mcnt - start);
break;
case jump_past_alt:
extract_number_and_incr (&mcnt, &p);
printf ("/jump_past_alt to %d", p + mcnt - start);
break;
case jump:
extract_number_and_incr (&mcnt, &p);
printf ("/jump to %d", p + mcnt - start);
break;
case succeed_n:
extract_number_and_incr (&mcnt, &p);
p1 = p + mcnt;
extract_number_and_incr (&mcnt2, &p);
printf ("/succeed_n to %d, %d times", p1 - start, mcnt2);
break;
case jump_n:
extract_number_and_incr (&mcnt, &p);
p1 = p + mcnt;
extract_number_and_incr (&mcnt2, &p);
printf ("/jump_n to %d, %d times", p1 - start, mcnt2);
break;
case set_number_at:
extract_number_and_incr (&mcnt, &p);
p1 = p + mcnt;
extract_number_and_incr (&mcnt2, &p);
printf ("/set_number_at location %d to %d", p1 - start, mcnt2);
break;
case wordbound:
printf ("/wordbound");
break;
case notwordbound:
printf ("/notwordbound");
break;
case wordbeg:
printf ("/wordbeg");
break;
case wordend:
printf ("/wordend");
# ifdef emacs
case before_dot:
printf ("/before_dot");
break;
case at_dot:
printf ("/at_dot");
break;
case after_dot:
printf ("/after_dot");
break;
case syntaxspec:
printf ("/syntaxspec");
mcnt = *p++;
printf ("/%d", mcnt);
break;
case notsyntaxspec:
printf ("/notsyntaxspec");
mcnt = *p++;
printf ("/%d", mcnt);
break;
# endif /* emacs */
case wordchar:
printf ("/wordchar");
break;
case notwordchar:
printf ("/notwordchar");
break;
case begbuf:
printf ("/begbuf");
break;
case endbuf:
printf ("/endbuf");
break;
default:
printf ("?%d", *(p-1));
}
putchar ('\n');
}
printf ("%d:\tend of pattern.\n", p - start);
}
void
print_compiled_pattern (bufp)
struct re_pattern_buffer *bufp;
{
unsigned char *buffer = bufp->buffer;
print_partial_compiled_pattern (buffer, buffer + bufp->used);
printf ("%ld bytes used/%ld bytes allocated.\n",
bufp->used, bufp->allocated);
if (bufp->fastmap_accurate && bufp->fastmap)
{
printf ("fastmap: ");
print_fastmap (bufp->fastmap);
}
printf ("re_nsub: %d\t", bufp->re_nsub);
printf ("regs_alloc: %d\t", bufp->regs_allocated);
printf ("can_be_null: %d\t", bufp->can_be_null);
printf ("newline_anchor: %d\n", bufp->newline_anchor);
printf ("no_sub: %d\t", bufp->no_sub);
printf ("not_bol: %d\t", bufp->not_bol);
printf ("not_eol: %d\t", bufp->not_eol);
printf ("syntax: %lx\n", bufp->syntax);
/* Perhaps we should print the translate table? */
}
void
print_double_string (where, string1, size1, string2, size2)
const char *where;
const char *string1;
const char *string2;
int size1;
int size2;
{
int this_char;
if (where == NULL)
printf ("(null)");
else
{
if (FIRST_STRING_P (where))
{
for (this_char = where - string1; this_char < size1; this_char++)
putchar (string1[this_char]);
where = string2;
}
for (this_char = where - string2; this_char < size2; this_char++)
putchar (string2[this_char]);
}
}
void
printchar (c)
int c;
{
putc (c, stderr);
}
#else /* not DEBUG */
# undef assert
# define assert(e)
# define DEBUG_STATEMENT(e)
# define DEBUG_PRINT1(x)
# define DEBUG_PRINT2(x1, x2)
# define DEBUG_PRINT3(x1, x2, x3)
# define DEBUG_PRINT4(x1, x2, x3, x4)
# define DEBUG_PRINT_COMPILED_PATTERN(p, s, e)
# define DEBUG_PRINT_DOUBLE_STRING(w, s1, sz1, s2, sz2)
#endif /* not DEBUG */
#if JS
reg_syntax_t re_syntax_options = RE_SYNTAX_GNU_AWK;
#else /* not JS */
/* Set by `re_set_syntax' to the current regexp syntax to recognize. Can
also be assigned to arbitrarily: each pattern buffer stores its own
syntax, so it can be changed between regex compilations. */
/* This has no initializer because initialized variables in Emacs
become read-only after dumping. */
reg_syntax_t re_syntax_options;
#endif /* not JS */
/* Specify the precise syntax of regexps for compilation. This provides
for compatibility for various utilities which historically have
different, incompatible syntaxes.
The argument SYNTAX is a bit mask comprised of the various bits
defined in regex.h. We return the old syntax. */
reg_syntax_t
re_set_syntax (syntax)
reg_syntax_t syntax;
{
reg_syntax_t ret = re_syntax_options;
re_syntax_options = syntax;
#ifdef DEBUG
if (syntax & RE_DEBUG)
debug = 1;
else if (debug) /* was on but now is not */
debug = 0;
#endif /* DEBUG */
return ret;
}
#ifdef _LIBC
weak_alias (__re_set_syntax, re_set_syntax)
#endif
/* This table gives an error message for each of the error codes listed
in regex.h. Obviously the order here has to be same as there.
POSIX doesn't require that we do anything for REG_NOERROR,
but why not be nice? */
static const char *re_error_msgid[] =
{
gettext_noop ("Success"), /* REG_NOERROR */
gettext_noop ("No match"), /* REG_NOMATCH */
gettext_noop ("Invalid regular expression"), /* REG_BADPAT */
gettext_noop ("Invalid collation character"), /* REG_ECOLLATE */
gettext_noop ("Invalid character class name"), /* REG_ECTYPE */
gettext_noop ("Trailing backslash"), /* REG_EESCAPE */
gettext_noop ("Invalid back reference"), /* REG_ESUBREG */
gettext_noop ("Unmatched [ or [^"), /* REG_EBRACK */
gettext_noop ("Unmatched ( or \\("), /* REG_EPAREN */
gettext_noop ("Unmatched \\{"), /* REG_EBRACE */
gettext_noop ("Invalid content of \\{\\}"), /* REG_BADBR */
gettext_noop ("Invalid range end"), /* REG_ERANGE */
gettext_noop ("Memory exhausted"), /* REG_ESPACE */
gettext_noop ("Invalid preceding regular expression"), /* REG_BADRPT */
gettext_noop ("Premature end of regular expression"), /* REG_EEND */
gettext_noop ("Regular expression too big"), /* REG_ESIZE */
gettext_noop ("Unmatched ) or \\)"), /* REG_ERPAREN */
};
/* Avoiding alloca during matching, to placate r_alloc. */
/* Define MATCH_MAY_ALLOCATE unless we need to make sure that the
searching and matching functions should not call alloca. On some
systems, alloca is implemented in terms of malloc, and if we're
using the relocating allocator routines, then malloc could cause a
relocation, which might (if the strings being searched are in the
ralloc heap) shift the data out from underneath the regexp
routines.
Here's another reason to avoid allocation: Emacs
processes input from X in a signal handler; processing X input may
call malloc; if input arrives while a matching routine is calling
malloc, then we're scrod. But Emacs can't just block input while
calling matching routines; then we don't notice interrupts when
they come in. So, Emacs blocks input around all regexp calls
except the matching calls, which it leaves unprotected, in the
faith that they will not malloc. */
/* Normally, this is fine. */
#define MATCH_MAY_ALLOCATE
/* When using GNU C, we are not REALLY using the C alloca, no matter
what config.h may say. So don't take precautions for it. */
#ifdef __GNUC__
# undef C_ALLOCA
#endif
/* The match routines may not allocate if (1) they would do it with malloc
and (2) it's not safe for them to use malloc.
Note that if REL_ALLOC is defined, matching would not use malloc for the
failure stack, but we would still use it for the register vectors;
so REL_ALLOC should not affect this. */
#if (defined C_ALLOCA || defined REGEX_MALLOC) && defined emacs
# undef MATCH_MAY_ALLOCATE
#endif
/* Failure stack declarations and macros; both re_compile_fastmap and
re_match_2 use a failure stack. These have to be macros because of
REGEX_ALLOCATE_STACK. */
/* Number of failure points for which to initially allocate space
when matching. If this number is exceeded, we allocate more
space, so it is not a hard limit. */
#ifndef INIT_FAILURE_ALLOC
# define INIT_FAILURE_ALLOC 5
#endif
/* Roughly the maximum number of failure points on the stack. Would be
exactly that if always used MAX_FAILURE_ITEMS items each time we failed.
This is a variable only so users of regex can assign to it; we never
change it ourselves. */
#ifdef INT_IS_16BIT
# if defined MATCH_MAY_ALLOCATE
/* 4400 was enough to cause a crash on Alpha OSF/1,
whose default stack limit is 2mb. */
long int re_max_failures = 4000;
# else
long int re_max_failures = 2000;
# endif
union fail_stack_elt
{
unsigned char *pointer;
long int integer;
};
typedef union fail_stack_elt fail_stack_elt_t;
typedef struct
{
fail_stack_elt_t *stack;
unsigned long int size;
unsigned long int avail; /* Offset of next open position. */
} fail_stack_type;
#else /* not INT_IS_16BIT */
# if defined MATCH_MAY_ALLOCATE
/* 4400 was enough to cause a crash on Alpha OSF/1,
whose default stack limit is 2mb. */
int re_max_failures = 20000;
# else
int re_max_failures = 2000;
# endif
union fail_stack_elt
{
unsigned char *pointer;
int integer;
};
typedef union fail_stack_elt fail_stack_elt_t;
typedef struct
{
fail_stack_elt_t *stack;
unsigned size;
unsigned avail; /* Offset of next open position. */
} fail_stack_type;
#endif /* INT_IS_16BIT */
#define FAIL_STACK_EMPTY() (fail_stack.avail == 0)
#define FAIL_STACK_PTR_EMPTY() (fail_stack_ptr->avail == 0)
#define FAIL_STACK_FULL() (fail_stack.avail == fail_stack.size)
/* Define macros to initialize and free the failure stack.
Do `return -2' if the alloc fails. */
#ifdef MATCH_MAY_ALLOCATE
# define INIT_FAIL_STACK() \
do { \
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -