| Index: base/utf_offset_string_conversions.h
|
| diff --git a/base/utf_offset_string_conversions.h b/base/utf_offset_string_conversions.h
|
| index 97b641edda8b49a9a9797ec4cd08966f2400c277..a63d6a46d02e761f3c99cbe67c0cc087bb65e14c 100644
|
| --- a/base/utf_offset_string_conversions.h
|
| +++ b/base/utf_offset_string_conversions.h
|
| @@ -1,4 +1,4 @@
|
| -// Copyright (c) 2011 The Chromium Authors. All rights reserved.
|
| +// Copyright (c) 2012 The Chromium Authors. All rights reserved.
|
| // Use of this source code is governed by a BSD-style license that can be
|
| // found in the LICENSE file.
|
|
|
| @@ -13,6 +13,36 @@
|
| #include "base/string16.h"
|
| #include "base/string_piece.h"
|
|
|
| +// Returns false if s[index-1] is a high surrogate and s[index] is a low
|
| +// surrogate, true otherwise.
|
| +BASE_EXPORT bool IsValidCodePointIndex(const string16& s, size_t index);
|
| +
|
| +// |Utf16IndexToOffset| returns the number of code points between |base| and
|
| +// |pos| in the given string. |Utf16OffsetToIndex| returns the index that is
|
| +// |offset| code points away from the given |base| index. These functions are
|
| +// named after glib's |g_utf8_pointer_to_offset| and |g_utf8_offset_to_pointer|,
|
| +// which perform the same function for UTF-8.
|
| +// Unpaired surrogates in the string are counted as BMP characters. If an
|
| +// argument index points to the middle of a surrogate pair, it is treated as
|
| +// though it pointed to the end of that pair (in other words, the first word of
|
| +// any surrogate pair is the one that is counted). The index returned by
|
| +// |Utf16OffsetToIndex| never points to the middle of a surrogate pair.
|
| +// The following identities hold:
|
| +// If |s| contains no surrogate pairs, then
|
| +// Utf16IndexToOffset(s, base, pos) == pos - base
|
| +// Utf16OffsetToIndex(s, base, offset) == base + offset
|
| +// If |pos| does not point to the middle of a surrogate pair, then
|
| +// Utf16OffsetToIndex(s, base, Utf16IndexToOffset(s, base, pos)) == pos
|
| +// Always,
|
| +// Utf16IndexToOffset(s, base, Utf16OffsetToIndex(s, base, ofs)) == ofs
|
| +// Utf16IndexToOffset(s, i, j) == -Utf16IndexToOffset(s, j, i)
|
| +BASE_EXPORT ptrdiff_t Utf16IndexToOffset(const string16& s,
|
| + size_t base,
|
| + size_t pos);
|
| +BASE_EXPORT size_t Utf16OffsetToIndex(const string16& s,
|
| + size_t base,
|
| + ptrdiff_t offset);
|
| +
|
| // 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.
|
|
|