version 1.1.1.1, 2012/02/21 23:50:25
|
version 1.1.1.2, 2013/07/22 08:25:55
|
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) 1997-2012 University of Cambridge | Copyright (c) 1997-2013 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 69 PCRE_UTF16_ERR0 No error
|
Line 69 PCRE_UTF16_ERR0 No error
|
PCRE_UTF16_ERR1 Missing low surrogate at the end of the string |
PCRE_UTF16_ERR1 Missing low surrogate at the end of the string |
PCRE_UTF16_ERR2 Invalid low surrogate |
PCRE_UTF16_ERR2 Invalid low surrogate |
PCRE_UTF16_ERR3 Isolated low surrogate |
PCRE_UTF16_ERR3 Isolated low surrogate |
PCRE_UTF16_ERR4 Not allowed character | PCRE_UTF16_ERR4 Unused (was non-character) |
|
|
Arguments: |
Arguments: |
string points to the string |
string points to the string |
Line 85 PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *e
|
Line 85 PRIV(valid_utf)(PCRE_PUCHAR string, int length, int *e
|
{ |
{ |
#ifdef SUPPORT_UTF |
#ifdef SUPPORT_UTF |
register PCRE_PUCHAR p; |
register PCRE_PUCHAR p; |
register pcre_uchar c; | register pcre_uint32 c; |
|
|
if (length < 0) |
if (length < 0) |
{ |
{ |
Line 100 for (p = string; length-- > 0; p++)
|
Line 100 for (p = string; length-- > 0; p++)
|
if ((c & 0xf800) != 0xd800) |
if ((c & 0xf800) != 0xd800) |
{ |
{ |
/* Normal UTF-16 code point. Neither high nor low surrogate. */ |
/* Normal UTF-16 code point. Neither high nor low surrogate. */ |
|
|
/* This is probably a BOM from a different byte-order. |
|
Regardless, the string is rejected. */ |
|
if (c == 0xfffe) |
|
{ |
|
*erroroffset = p - string; |
|
return PCRE_UTF16_ERR4; |
|
} |
|
} |
} |
else if ((c & 0x0400) == 0) |
else if ((c & 0x0400) == 0) |
{ |
{ |
/* High surrogate. */ | /* High surrogate. Must be a followed by a low surrogate. */ |
| |
/* Must be a followed by a low surrogate. */ | |
if (length == 0) |
if (length == 0) |
{ |
{ |
*erroroffset = p - string; |
*erroroffset = p - string; |
Line 138 for (p = string; length-- > 0; p++)
|
Line 128 for (p = string; length-- > 0; p++)
|
#else /* SUPPORT_UTF */ |
#else /* SUPPORT_UTF */ |
(void)(string); /* Keep picky compilers happy */ |
(void)(string); /* Keep picky compilers happy */ |
(void)(length); |
(void)(length); |
|
(void)(erroroffset); |
#endif /* SUPPORT_UTF */ |
#endif /* SUPPORT_UTF */ |
|
|
return PCRE_UTF16_ERR0; /* This indicates success */ |
return PCRE_UTF16_ERR0; /* This indicates success */ |