| OLD | NEW |
| 1 /* | 1 /* |
| 2 * Copyright (C) 2013 Google Inc. All rights reserved. | 2 * Copyright (C) 2013 Google Inc. All rights reserved. |
| 3 * | 3 * |
| 4 * Redistribution and use in source and binary forms, with or without | 4 * Redistribution and use in source and binary forms, with or without |
| 5 * modification, are permitted provided that the following conditions are | 5 * modification, are permitted provided that the following conditions are |
| 6 * met: | 6 * met: |
| 7 * | 7 * |
| 8 * * Redistributions of source code must retain the above copyright | 8 * * Redistributions of source code must retain the above copyright |
| 9 * notice, this list of conditions and the following disclaimer. | 9 * notice, this list of conditions and the following disclaimer. |
| 10 * * Redistributions in binary form must reproduce the above | 10 * * Redistributions in binary form must reproduce the above |
| (...skipping 24 matching lines...) Expand all Loading... |
| 35 #include "wtf/text/TextEncoding.h" | 35 #include "wtf/text/TextEncoding.h" |
| 36 #include "wtf/text/WTFString.h" | 36 #include "wtf/text/WTFString.h" |
| 37 | 37 |
| 38 namespace WTF { | 38 namespace WTF { |
| 39 | 39 |
| 40 // This class lets you get UTF-8 data out of a String without mallocing a | 40 // This class lets you get UTF-8 data out of a String without mallocing a |
| 41 // separate buffer to hold the data if the String happens to be 8 bit and | 41 // separate buffer to hold the data if the String happens to be 8 bit and |
| 42 // contain only ASCII characters. | 42 // contain only ASCII characters. |
| 43 class StringUTF8Adaptor { | 43 class StringUTF8Adaptor { |
| 44 public: | 44 public: |
| 45 enum ShouldNormalize { | 45 explicit StringUTF8Adaptor(const String& string) |
| 46 DoNotNormalize, | |
| 47 Normalize | |
| 48 }; | |
| 49 | |
| 50 explicit StringUTF8Adaptor(const String& string, ShouldNormalize normalize =
DoNotNormalize, UnencodableHandling handling = EntitiesForUnencodables) | |
| 51 : m_data(0) | 46 : m_data(0) |
| 52 , m_length(0) | 47 , m_length(0) |
| 53 { | 48 { |
| 54 if (string.isEmpty()) | 49 if (string.isEmpty()) |
| 55 return; | 50 return; |
| 56 // Unfortunately, 8 bit WTFStrings are encoded in Latin-1 and GURL uses
UTF-8 | 51 // Unfortunately, 8 bit WTFStrings are encoded in Latin-1 and GURL uses
UTF-8 |
| 57 // when processing 8 bit strings. If |relative| is entirely ASCII, we lu
ck out | 52 // when processing 8 bit strings. If |relative| is entirely ASCII, we lu
ck out |
| 58 // and can avoid mallocing a new buffer to hold the UTF-8 data because U
TF-8 | 53 // and can avoid mallocing a new buffer to hold the UTF-8 data because U
TF-8 |
| 59 // and Latin-1 use the same code units for ASCII code points. | 54 // and Latin-1 use the same code units for ASCII code points. |
| 60 if (string.is8Bit() && string.containsOnlyASCII()) { | 55 if (string.is8Bit() && string.containsOnlyASCII()) { |
| 61 m_data = reinterpret_cast<const char*>(string.characters8()); | 56 m_data = reinterpret_cast<const char*>(string.characters8()); |
| 62 m_length = string.length(); | 57 m_length = string.length(); |
| 63 } else { | 58 } else { |
| 64 if (normalize == Normalize) | 59 m_utf8Buffer = string.utf8(); |
| 65 m_utf8Buffer = UTF8Encoding().normalizeAndEncode(string, handlin
g); | |
| 66 else | |
| 67 m_utf8Buffer = string.utf8(); | |
| 68 m_data = m_utf8Buffer.data(); | 60 m_data = m_utf8Buffer.data(); |
| 69 m_length = m_utf8Buffer.length(); | 61 m_length = m_utf8Buffer.length(); |
| 70 } | 62 } |
| 71 } | 63 } |
| 72 | 64 |
| 73 const char* data() const { return m_data; } | 65 const char* data() const { return m_data; } |
| 74 size_t length() const { return m_length; } | 66 size_t length() const { return m_length; } |
| 75 | 67 |
| 76 private: | 68 private: |
| 77 CString m_utf8Buffer; | 69 CString m_utf8Buffer; |
| 78 const char* m_data; | 70 const char* m_data; |
| 79 size_t m_length; | 71 size_t m_length; |
| 80 }; | 72 }; |
| 81 | 73 |
| 82 } // namespace WTF | 74 } // namespace WTF |
| 83 | 75 |
| 84 using WTF::StringUTF8Adaptor; | 76 using WTF::StringUTF8Adaptor; |
| 85 | 77 |
| 86 #endif // StringUTF8Adaptor_h | 78 #endif // StringUTF8Adaptor_h |
| OLD | NEW |