diff options
Diffstat (limited to 'gpr/source/lib/xmp_core/UnicodeInlines.incl_cpp')
| -rw-r--r-- | gpr/source/lib/xmp_core/UnicodeInlines.incl_cpp | 129 |
1 files changed, 129 insertions, 0 deletions
diff --git a/gpr/source/lib/xmp_core/UnicodeInlines.incl_cpp b/gpr/source/lib/xmp_core/UnicodeInlines.incl_cpp new file mode 100644 index 0000000..d96d370 --- /dev/null +++ b/gpr/source/lib/xmp_core/UnicodeInlines.incl_cpp @@ -0,0 +1,129 @@ +#ifndef __UnicodeInlines_incl_cpp__ +#define __UnicodeInlines_incl_cpp__ + +// ================================================================================================= +// Copyright 2004 Adobe Systems Incorporated +// All Rights Reserved. +// +// NOTICE: Adobe permits you to use, modify, and distribute this file in accordance with the terms +// of the Adobe license agreement accompanying it. +// ================================================================================================= + +#include "UnicodeConversions.hpp" + +// ================================================================================================= +// Inner loop utilities that need to be inlined. +// ================================================================================================= + +static inline XMP_Uns32 GetCodePoint ( const XMP_Uns8 ** utf8Str_io ) +{ + const XMP_Uns8 * u8Ptr = *utf8Str_io; + XMP_Uns32 cp; + size_t u8Len; + CodePoint_from_UTF8 ( u8Ptr, 4, &cp, &u8Len ); // Throws an exception for errors. + *utf8Str_io = u8Ptr + u8Len; + return cp; +} + +// ================================================================================================= + +static inline bool IsStartChar_ASCII ( XMP_Uns32 cp ) +{ + // ASCII starting characters for an XML name. + if ( (('a' <= cp) && (cp <= 'z')) || (('A' <= cp) && (cp <= 'Z')) || (cp == '_') ) return true; + return false; +} + +// ------------------------------------------------------------------------------------------------- + +static inline bool IsStartChar_NonASCII ( XMP_Uns32 cp ) +{ + // Non-ASCII starting characters for an XML name. + + if ( ((0xC0 <= cp) && (cp <= 0xD6)) || ((0xD8 <= cp) && (cp <= 0xF6)) ) return true; + if ( ((0xF8 <= cp) && (cp <= 0x2FF)) || ((0x370 <= cp) && (cp <= 0x37D)) ) return true; + + if ( ((0x37F <= cp) && (cp <= 0x1FFF)) || ((0x200C <= cp) && (cp <= 0x200D)) ) return true; + if ( ((0x2070 <= cp) && (cp <= 0x218F)) || ((0x2C00 <= cp) && (cp <= 0x2FEF)) ) return true; + if ( ((0x3001 <= cp) && (cp <= 0xD7FF)) || ((0xF900 <= cp) && (cp <= 0xFDCF)) ) return true; + if ( ((0xFDF0 <= cp) && (cp <= 0xFFFD)) || ((0x10000 <= cp) && (cp <= 0xEFFFF)) ) return true; + + return false; + +} + +// ------------------------------------------------------------------------------------------------- + +static inline bool IsOtherChar_ASCII ( XMP_Uns32 cp ) +{ + // ASCII following characters for an XML name. + if ( (('0' <= cp) && (cp <= '9')) || (cp == '-') || (cp == '.') ) return true; + return false; +} + +// ------------------------------------------------------------------------------------------------- + +static inline bool IsOtherChar_NonASCII ( XMP_Uns32 cp ) +{ + // Non-ASCII following characters for an XML name. + if ( (cp == 0xB7) || ((0x300 <= cp) && (cp <= 0x36F)) || ((0x203F <= cp) && (cp <= 0x2040)) ) return true; + return false; +} + +// ------------------------------------------------------------------------------------------------- + +static inline void VerifyUTF8 ( XMP_StringPtr str ) +{ + const XMP_Uns8 * utf8Str = (XMP_Uns8*)str; + while ( *utf8Str != 0 ) { + while ( (*utf8Str != 0) && (*utf8Str < 0x80) ) ++utf8Str; + if ( *utf8Str >= 0x80 ) (void) GetCodePoint ( &utf8Str ); // Throws for bad UTF-8. + } +} + +// ------------------------------------------------------------------------------------------------- + +static inline void VerifySimpleXMLName ( XMP_StringPtr _nameStart, XMP_StringPtr _nameEnd ) +{ + + const XMP_Uns8 * nameStart = (const XMP_Uns8 *) _nameStart; + const XMP_Uns8 * nameEnd = (const XMP_Uns8 *) _nameEnd; + const XMP_Uns8 * namePos = nameStart; + XMP_Uns32 cp; + + // The first character is more restricted. + + if ( nameStart >= nameEnd ) XMP_Throw ( "Empty XML name", kXMPErr_BadXPath ); + + cp = *namePos; + if ( cp < 0x80 ) { + ++namePos; + if ( ! IsStartChar_ASCII(cp) ) goto NameError; + } else { + cp = GetCodePoint ( &namePos ); + if ( ! IsStartChar_NonASCII(cp) ) goto NameError; + } + + // Check the rest of the name. + + while ( namePos < nameEnd ) { + cp = *namePos; + if ( cp < 0x80 ) { + ++namePos; + if ( (! IsStartChar_ASCII(cp)) && (! IsOtherChar_ASCII(cp)) ) goto NameError; + } else { + cp = GetCodePoint ( &namePos ); + if ( (! IsStartChar_NonASCII(cp)) && (! IsOtherChar_NonASCII(cp)) ) goto NameError; + } + } + + return; + +NameError: + XMP_Throw ( "Bad XML name", kXMPErr_BadXPath ); + +} // VerifySimpleXMLName + +// ================================================================================================= + +#endif // __UnicodeInlines_incl_cpp__ |