diff options
author | hbono@chromium.org <hbono@chromium.org@0039d316-1c4b-4281-b951-d872f2087c98> | 2009-02-26 10:02:52 +0000 |
---|---|---|
committer | hbono@chromium.org <hbono@chromium.org@0039d316-1c4b-4281-b951-d872f2087c98> | 2009-02-26 10:02:52 +0000 |
commit | 0676a96af598e97e3b6016cd3675e2f424dc8407 (patch) | |
tree | 5ff6d221bdbbc1bba12a5b41f160fd68e2ef453a /base/string_util.cc | |
parent | 503683f23ea6fe3eb728f2d09f81f2603ffc7d6f (diff) | |
download | chromium_src-0676a96af598e97e3b6016cd3675e2f424dc8407.zip chromium_src-0676a96af598e97e3b6016cd3675e2f424dc8407.tar.gz chromium_src-0676a96af598e97e3b6016cd3675e2f424dc8407.tar.bz2 |
Fixes Issue 7377: Regression: Omnibox trims URL ending with 0x85
To fix this issue, this change adds a new function TrimWhitespaceUTF8(), which trims space characters (including non-printable characters and broken UTF-8 characters) from either end of a UTF-8 string.
Please feel free to give me your comments since I'm not sure this implimentation is correct. (Maybe this implementation trims too aggressively.)
BUG=7377
Review URL: http://codereview.chromium.org/20219
git-svn-id: svn://svn.chromium.org/chrome/trunk/src@10456 0039d316-1c4b-4281-b951-d872f2087c98
Diffstat (limited to 'base/string_util.cc')
-rw-r--r-- | base/string_util.cc | 26 |
1 files changed, 23 insertions, 3 deletions
diff --git a/base/string_util.cc b/base/string_util.cc index 4ba8c4b..55be9df 100644 --- a/base/string_util.cc +++ b/base/string_util.cc @@ -337,8 +337,6 @@ const char kWhitespaceASCII[] = { 0x0C, 0x0D, 0x20, // Space - '\x85', // <control-0085> - '\xa0', // No-Break Space 0 }; const char* const kCodepageUTF8 = "UTF-8"; @@ -393,10 +391,32 @@ TrimPositions TrimWhitespace(const std::wstring& input, return TrimStringT(input, kWhitespaceWide, positions, output); } +TrimPositions TrimWhitespaceASCII(const std::string& input, + TrimPositions positions, + std::string* output) { + return TrimStringT(input, kWhitespaceASCII, positions, output); +} + +TrimPositions TrimWhitespaceUTF8(const std::string& input, + TrimPositions positions, + std::string* output) { + // This implementation is not so fast since it converts the text encoding + // twice. Please feel free to file a bug if this function hurts the + // performance of Chrome. + DCHECK(IsStringUTF8(input)); + std::wstring input_wide = UTF8ToWide(input); + std::wstring output_wide; + TrimPositions result = TrimWhitespace(input_wide, positions, &output_wide); + *output = WideToUTF8(output_wide); + return result; +} + +// This function is only for backward-compatibility. +// To be removed when all callers are updated. TrimPositions TrimWhitespace(const std::string& input, TrimPositions positions, std::string* output) { - return TrimStringT(input, kWhitespaceASCII, positions, output); + return TrimWhitespaceASCII(input, positions, output); } std::wstring CollapseWhitespace(const std::wstring& text, |