| Index: base/utf_offset_string_conversions.cc
|
| ===================================================================
|
| --- base/utf_offset_string_conversions.cc (revision 82762)
|
| +++ base/utf_offset_string_conversions.cc (working copy)
|
| @@ -14,21 +14,18 @@
|
| using base::ReadUnicodeCharacter;
|
| using base::WriteUnicodeCharacter;
|
|
|
| -// Generalized Unicode converter -----------------------------------------------
|
| -
|
| // Converts the given source Unicode character type to the given destination
|
| // Unicode character type as a STL string. The given input buffer and size
|
| // determine the source, and the given output STL string will be replaced by
|
| // the result.
|
| -template<typename SRC_CHAR>
|
| -bool ConvertUnicode(const SRC_CHAR* src,
|
| +bool ConvertUnicode(const char* src,
|
| size_t src_len,
|
| - std::wstring* output,
|
| + string16* output,
|
| std::vector<size_t>* offsets_for_adjustment) {
|
| if (offsets_for_adjustment) {
|
| std::for_each(offsets_for_adjustment->begin(),
|
| offsets_for_adjustment->end(),
|
| - LimitOffset<std::wstring>(src_len));
|
| + LimitOffset<string16>(src_len));
|
| }
|
|
|
| // ICU requires 32-bit numbers.
|
| @@ -65,152 +62,50 @@
|
| return success;
|
| }
|
|
|
| -// UTF-8 <-> Wide --------------------------------------------------------------
|
| -
|
| -bool UTF8ToWideAndAdjustOffset(const char* src,
|
| - size_t src_len,
|
| - std::wstring* output,
|
| - size_t* offset_for_adjustment) {
|
| - std::vector<size_t> offsets;
|
| - if (offset_for_adjustment)
|
| - offsets.push_back(*offset_for_adjustment);
|
| - PrepareForUTF16Or32Output(src, src_len, output);
|
| - bool ret = ConvertUnicode(src, src_len, output, &offsets);
|
| - if (offset_for_adjustment)
|
| - *offset_for_adjustment = offsets[0];
|
| - return ret;
|
| -}
|
| -
|
| -bool UTF8ToWideAndAdjustOffsets(const char* src,
|
| +bool UTF8ToUTF16AndAdjustOffset(const char* src,
|
| size_t src_len,
|
| - std::wstring* output,
|
| - std::vector<size_t>* offsets_for_adjustment) {
|
| - PrepareForUTF16Or32Output(src, src_len, output);
|
| - return ConvertUnicode(src, src_len, output, offsets_for_adjustment);
|
| -}
|
| -
|
| -std::wstring UTF8ToWideAndAdjustOffset(const base::StringPiece& utf8,
|
| - size_t* offset_for_adjustment) {
|
| - std::vector<size_t> offsets;
|
| - if (offset_for_adjustment)
|
| - offsets.push_back(*offset_for_adjustment);
|
| - std::wstring result;
|
| - UTF8ToWideAndAdjustOffsets(utf8.data(), utf8.length(), &result,
|
| - &offsets);
|
| - if (offset_for_adjustment)
|
| - *offset_for_adjustment = offsets[0];
|
| - return result;
|
| -}
|
| -
|
| -std::wstring UTF8ToWideAndAdjustOffsets(const base::StringPiece& utf8,
|
| - std::vector<size_t>*
|
| - offsets_for_adjustment) {
|
| - std::wstring result;
|
| - UTF8ToWideAndAdjustOffsets(utf8.data(), utf8.length(), &result,
|
| - offsets_for_adjustment);
|
| - return result;
|
| -}
|
| -
|
| -// UTF-16 <-> Wide -------------------------------------------------------------
|
| -
|
| -#if defined(WCHAR_T_IS_UTF16)
|
| -
|
| -// When wide == UTF-16, then conversions are a NOP.
|
| -bool UTF16ToWideAndAdjustOffset(const char16* src,
|
| - size_t src_len,
|
| - std::wstring* output,
|
| + string16* output,
|
| size_t* offset_for_adjustment) {
|
| - output->assign(src, src_len);
|
| - if (offset_for_adjustment && (*offset_for_adjustment >= src_len))
|
| - *offset_for_adjustment = std::wstring::npos;
|
| - return true;
|
| -}
|
| -
|
| -bool UTF16ToWideAndAdjustOffsets(const char16* src,
|
| - size_t src_len,
|
| - std::wstring* output,
|
| - std::vector<size_t>* offsets_for_adjustment) {
|
| - output->assign(src, src_len);
|
| - if (offsets_for_adjustment) {
|
| - std::for_each(offsets_for_adjustment->begin(),
|
| - offsets_for_adjustment->end(),
|
| - LimitOffset<std::wstring>(src_len));
|
| - }
|
| - return true;
|
| -}
|
| -
|
| -std::wstring UTF16ToWideAndAdjustOffset(const string16& utf16,
|
| - size_t* offset_for_adjustment) {
|
| - if (offset_for_adjustment && (*offset_for_adjustment >= utf16.length()))
|
| - *offset_for_adjustment = std::wstring::npos;
|
| - return utf16;
|
| -}
|
| -
|
| -std::wstring UTF16ToWideAndAdjustOffsets(
|
| - const string16& utf16,
|
| - std::vector<size_t>* offsets_for_adjustment) {
|
| - if (offsets_for_adjustment) {
|
| - std::for_each(offsets_for_adjustment->begin(),
|
| - offsets_for_adjustment->end(),
|
| - LimitOffset<std::wstring>(utf16.length()));
|
| - }
|
| - return utf16;
|
| -}
|
| -
|
| -#elif defined(WCHAR_T_IS_UTF32)
|
| -
|
| -bool UTF16ToWideAndAdjustOffset(const char16* src,
|
| - size_t src_len,
|
| - std::wstring* output,
|
| - size_t* offset_for_adjustment) {
|
| std::vector<size_t> offsets;
|
| if (offset_for_adjustment)
|
| offsets.push_back(*offset_for_adjustment);
|
| - output->clear();
|
| - // Assume that normally we won't have any non-BMP characters so the counts
|
| - // will be the same.
|
| - output->reserve(src_len);
|
| + PrepareForUTF16Or32Output(src, src_len, output);
|
| bool ret = ConvertUnicode(src, src_len, output, &offsets);
|
| if (offset_for_adjustment)
|
| *offset_for_adjustment = offsets[0];
|
| return ret;
|
| }
|
|
|
| -bool UTF16ToWideAndAdjustOffsets(const char16* src,
|
| +bool UTF8ToUTF16AndAdjustOffsets(const char* src,
|
| size_t src_len,
|
| - std::wstring* output,
|
| + string16* output,
|
| std::vector<size_t>* offsets_for_adjustment) {
|
| - output->clear();
|
| - // Assume that normally we won't have any non-BMP characters so the counts
|
| - // will be the same.
|
| - output->reserve(src_len);
|
| + PrepareForUTF16Or32Output(src, src_len, output);
|
| return ConvertUnicode(src, src_len, output, offsets_for_adjustment);
|
| }
|
|
|
| -std::wstring UTF16ToWideAndAdjustOffset(const string16& utf16,
|
| +string16 UTF8ToUTF16AndAdjustOffset(const base::StringPiece& utf8,
|
| size_t* offset_for_adjustment) {
|
| std::vector<size_t> offsets;
|
| if (offset_for_adjustment)
|
| offsets.push_back(*offset_for_adjustment);
|
| - std::wstring result;
|
| - UTF16ToWideAndAdjustOffsets(utf16.data(), utf16.length(), &result,
|
| + string16 result;
|
| + UTF8ToUTF16AndAdjustOffsets(utf8.data(), utf8.length(), &result,
|
| &offsets);
|
| if (offset_for_adjustment)
|
| *offset_for_adjustment = offsets[0];
|
| return result;
|
| }
|
|
|
| -std::wstring UTF16ToWideAndAdjustOffsets(
|
| - const string16& utf16,
|
| +string16 UTF8ToUTF16AndAdjustOffsets(
|
| + const base::StringPiece& utf8,
|
| std::vector<size_t>* offsets_for_adjustment) {
|
| - std::wstring result;
|
| - UTF16ToWideAndAdjustOffsets(utf16.data(), utf16.length(), &result,
|
| + string16 result;
|
| + UTF8ToUTF16AndAdjustOffsets(utf8.data(), utf8.length(), &result,
|
| offsets_for_adjustment);
|
| return result;
|
| }
|
|
|
| -#endif // defined(WCHAR_T_IS_UTF32)
|
| -
|
| AdjustOffset::Adjustment::Adjustment(size_t location,
|
| size_t old_length,
|
| size_t new_length)
|
| @@ -222,20 +117,20 @@
|
| : adjustments_(adjustments) {}
|
|
|
| void AdjustOffset::operator()(size_t& offset) {
|
| - if (offset == std::wstring::npos)
|
| + if (offset == string16::npos)
|
| return;
|
| size_t adjustment = 0;
|
| for (Adjustments::const_iterator i = adjustments_.begin();
|
| i != adjustments_.end(); ++i) {
|
| size_t location = i->location;
|
| if (offset == location && i->new_length == 0) {
|
| - offset = std::wstring::npos;
|
| + offset = string16::npos;
|
| return;
|
| }
|
| if (offset <= location)
|
| break;
|
| if (offset < (location + i->old_length)) {
|
| - offset = std::wstring::npos;
|
| + offset = string16::npos;
|
| return;
|
| }
|
| adjustment += (i->old_length - i->new_length);
|
|
|