diff options
author | mrossetti@chromium.org <mrossetti@chromium.org@0039d316-1c4b-4281-b951-d872f2087c98> | 2011-04-13 00:45:39 +0000 |
---|---|---|
committer | mrossetti@chromium.org <mrossetti@chromium.org@0039d316-1c4b-4281-b951-d872f2087c98> | 2011-04-13 00:45:39 +0000 |
commit | a47f8eadd67f75d3b663fdcc898caabb335bad0b (patch) | |
tree | fdf872770d4cd58ee753f219475850490a008f6d /base/utf_offset_string_conversions.h | |
parent | 2e0e8253a232fa499d22e47753c5bbadaebd69e7 (diff) | |
download | chromium_src-a47f8eadd67f75d3b663fdcc898caabb335bad0b.zip chromium_src-a47f8eadd67f75d3b663fdcc898caabb335bad0b.tar.gz chromium_src-a47f8eadd67f75d3b663fdcc898caabb335bad0b.tar.bz2 |
Add multiple-offset versions of the various URL reformatting functions. Fixed a couple of erroneous unit tests of offsets into username/password.
Note: This does not complete the work required for 78153 -- tis but the first 2/3rds.
BUG=78153
TEST=Many unit tests updated and added.
Review URL: http://codereview.chromium.org/6822038
git-svn-id: svn://svn.chromium.org/chrome/trunk/src@81343 0039d316-1c4b-4281-b951-d872f2087c98
Diffstat (limited to 'base/utf_offset_string_conversions.h')
-rw-r--r-- | base/utf_offset_string_conversions.h | 66 |
1 files changed, 61 insertions, 5 deletions
diff --git a/base/utf_offset_string_conversions.h b/base/utf_offset_string_conversions.h index 13df1b4..19b312a 100644 --- a/base/utf_offset_string_conversions.h +++ b/base/utf_offset_string_conversions.h @@ -7,6 +7,7 @@ #pragma once #include <string> +#include <vector> #include "base/base_api.h" #include "base/string16.h" @@ -15,23 +16,78 @@ namespace base { class StringPiece; } -// Like the conversions in utf_string_conversions.h, but also take offsets into -// the source strings, which will be adjusted to point at the same logical place -// in the result strings. If this isn't possible because the offsets point past -// the end of the source strings or into the middle of multibyte sequences, they -// will be set to std::wstring::npos. |offset_for_adjustment| may be NULL. +// Like the conversions in utf_string_conversions.h, but also takes one or more +// offsets (|offset[s]_for_adjustment|) into the source strings, each offset +// will be adjusted to point at the same logical place in the result strings. +// If this isn't possible because an offset points past the end of the source +// strings or into the middle of a multibyte sequence, the offending offset will +// be set to std::wstring::npos. |offset[s]_for_adjustment| may be NULL. BASE_API bool UTF8ToWideAndAdjustOffset(const char* src, size_t src_len, std::wstring* output, size_t* offset_for_adjustment); +BASE_API bool UTF8ToWideAndAdjustOffsets( + const char* src, + size_t src_len, + std::wstring* output, + std::vector<size_t>* offsets_for_adjustment); + BASE_API std::wstring UTF8ToWideAndAdjustOffset(const base::StringPiece& utf8, size_t* offset_for_adjustment); +BASE_API std::wstring UTF8ToWideAndAdjustOffsets( + const base::StringPiece& utf8, + std::vector<size_t>* offsets_for_adjustment); BASE_API bool UTF16ToWideAndAdjustOffset(const char16* src, size_t src_len, std::wstring* output, size_t* offset_for_adjustment); +BASE_API bool UTF16ToWideAndAdjustOffsets( + const char16* src, + size_t src_len, + std::wstring* output, + std::vector<size_t>* offsets_for_adjustment); + BASE_API std::wstring UTF16ToWideAndAdjustOffset(const string16& utf16, size_t* offset_for_adjustment); +BASE_API std::wstring UTF16ToWideAndAdjustOffsets( + const string16& utf16, + std::vector<size_t>* offsets_for_adjustment); + +// Limiting function callable by std::for_each which will replace any value +// which is equal to or greater than |limit| with npos. +template <typename T> +struct LimitOffset { + explicit LimitOffset(size_t limit); + void operator()(size_t& offset); + + size_t limit_; +}; + +// Adjustment function called by std::transform which will adjust any offset +// that occurs after one or more modified substrings. To use, create any +// number of AdjustOffset::Adjustments, drop them into a vector, then call +// std::transform with the transform function being something similar to +// AdjustOffset(adjustments). Each Adjustment gives the original |location| +// of the encoded section and the |old_length| and |new_length| of the section +// before and after decoding. +struct AdjustOffset { + // Helper structure which indicates where an encoded character occurred + // and how long that encoding was. + struct Adjustment { + Adjustment(size_t location, size_t old_length, size_t new_length); + + size_t location; + size_t old_length; + size_t new_length; + }; + + typedef std::vector<Adjustment> Adjustments; + + explicit AdjustOffset(const Adjustments& adjustments); + void operator()(size_t& offset); + + const Adjustments& adjustments_; +}; #endif // BASE_UTF_OFFSET_STRING_CONVERSIONS_H_ |