version 1.1.1.1, 2012/02/21 23:05:51
|
version 1.1.1.4, 2014/06/15 19:46:04
|
Line 6
|
Line 6
|
and semantics are as close as possible to those of the Perl 5 language. |
and semantics are as close as possible to those of the Perl 5 language. |
|
|
Written by Philip Hazel |
Written by Philip Hazel |
Copyright (c) 1997-2008 University of Cambridge | Copyright (c) 1997-2012 University of Cambridge |
|
|
----------------------------------------------------------------------------- |
----------------------------------------------------------------------------- |
Redistribution and use in source and binary forms, with or without |
Redistribution and use in source and binary forms, with or without |
Line 59 compilation of dftables.c, in which case the macro DFT
|
Line 59 compilation of dftables.c, in which case the macro DFT
|
/* This function builds a set of character tables for use by PCRE and returns |
/* This function builds a set of character tables for use by PCRE and returns |
a pointer to them. They are build using the ctype functions, and consequently |
a pointer to them. They are build using the ctype functions, and consequently |
their contents will depend upon the current locale setting. When compiled as |
their contents will depend upon the current locale setting. When compiled as |
part of the library, the store is obtained via pcre_malloc(), but when compiled | part of the library, the store is obtained via PUBL(malloc)(), but when |
inside dftables, use malloc(). | compiled inside dftables, use malloc(). |
|
|
Arguments: none |
Arguments: none |
Returns: pointer to the contiguous block of data |
Returns: pointer to the contiguous block of data |
*/ |
*/ |
|
|
|
#if defined COMPILE_PCRE8 |
const unsigned char * |
const unsigned char * |
pcre_maketables(void) |
pcre_maketables(void) |
|
#elif defined COMPILE_PCRE16 |
|
const unsigned char * |
|
pcre16_maketables(void) |
|
#elif defined COMPILE_PCRE32 |
|
const unsigned char * |
|
pcre32_maketables(void) |
|
#endif |
{ |
{ |
unsigned char *yield, *p; |
unsigned char *yield, *p; |
int i; |
int i; |
|
|
#ifndef DFTABLES |
#ifndef DFTABLES |
yield = (unsigned char*)(pcre_malloc)(tables_length); | yield = (unsigned char*)(PUBL(malloc))(tables_length); |
#else |
#else |
yield = (unsigned char*)malloc(tables_length); |
yield = (unsigned char*)malloc(tables_length); |
#endif |
#endif |
Line 90 for (i = 0; i < 256; i++) *p++ = tolower(i);
|
Line 98 for (i = 0; i < 256; i++) *p++ = tolower(i);
|
for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); |
for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); |
|
|
/* Then the character class tables. Don't try to be clever and save effort on |
/* Then the character class tables. Don't try to be clever and save effort on |
exclusive ones - in some locales things may be different. Note that the table | exclusive ones - in some locales things may be different. |
for "space" includes everything "isspace" gives, including VT in the default | |
locale. This makes it work for the POSIX class [:space:]. Note also that it is | |
possible for a character to be alnum or alpha without being lower or upper, | |
such as "male and female ordinals" (\xAA and \xBA) in the fr_FR locale (at | |
least under Debian Linux's locales as of 12/2005). So we must test for alnum | |
specially. */ | |
|
|
|
Note that the table for "space" includes everything "isspace" gives, including |
|
VT in the default locale. This makes it work for the POSIX class [:space:]. |
|
From release 8.34 is is also correct for Perl space, because Perl added VT at |
|
release 5.18. |
|
|
|
Note also that it is possible for a character to be alnum or alpha without |
|
being lower or upper, such as "male and female ordinals" (\xAA and \xBA) in the |
|
fr_FR locale (at least under Debian Linux's locales as of 12/2005). So we must |
|
test for alnum specially. */ |
|
|
memset(p, 0, cbit_length); |
memset(p, 0, cbit_length); |
for (i = 0; i < 256; i++) |
for (i = 0; i < 256; i++) |
{ |
{ |
Line 115 for (i = 0; i < 256; i++)
|
Line 127 for (i = 0; i < 256; i++)
|
} |
} |
p += cbit_length; |
p += cbit_length; |
|
|
/* Finally, the character type table. In this, we exclude VT from the white | /* Finally, the character type table. In this, we used to exclude VT from the |
space chars, because Perl doesn't recognize it as such for \s and for comments | white space chars, because Perl didn't recognize it as such for \s and for |
within regexes. */ | comments within regexes. However, Perl changed at release 5.18, so PCRE changed |
| at release 8.34. */ |
|
|
for (i = 0; i < 256; i++) |
for (i = 0; i < 256; i++) |
{ |
{ |
int x = 0; |
int x = 0; |
if (i != 0x0b && isspace(i)) x += ctype_space; | if (isspace(i)) x += ctype_space; |
if (isalpha(i)) x += ctype_letter; |
if (isalpha(i)) x += ctype_letter; |
if (isdigit(i)) x += ctype_digit; |
if (isdigit(i)) x += ctype_digit; |
if (isxdigit(i)) x += ctype_xdigit; |
if (isxdigit(i)) x += ctype_xdigit; |