Revert 81343 - 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=78153TEST=Many unit tests updated and added.Review URL: http://codereview.chromium.org/6822038

TBR=mrossetti@chromium.org
Review URL: http://codereview.chromium.org/6833011

git-svn-id: svn://svn.chromium.org/chrome/trunk/src@81348 0039d316-1c4b-4281-b951-d872f2087c98

1 files changed, 23 insertions, 156 deletions

diff --git a/base/utf_offset_string_conversions.cc b/base/utf_offset_string_conversions.cc
index f091cb4..4c47ef8 100644
--- a/base/utf_offset_string_conversions.cc
+++ b/base/utf_offset_string_conversions.cc
@@ -1,12 +1,9 @@
-// Copyright (c) 2011 The Chromium Authors. All rights reserved.
+// Copyright (c) 2009 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.
 
 #include "base/utf_offset_string_conversions.h"
 
-#include <algorithm>
-
-#include "base/scoped_ptr.h"
 #include "base/string_piece.h"
 #include "base/utf_string_conversion_utils.h"
 
@@ -24,16 +21,13 @@ template<typename SRC_CHAR>
 bool ConvertUnicode(const SRC_CHAR* src,
                     size_t src_len,
                     std::wstring* 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));
-  }
+                    size_t* offset_for_adjustment) {
+  size_t output_offset =
+      (offset_for_adjustment && *offset_for_adjustment < src_len) ?
+          *offset_for_adjustment : std::wstring::npos;
 
   // ICU requires 32-bit numbers.
   bool success = true;
-  AdjustOffset::Adjustments adjustments;
   int32 src_len32 = static_cast<int32>(src_len);
   for (int32 i = 0; i < src_len32; i++) {
     uint32 code_point;
@@ -45,23 +39,21 @@ bool ConvertUnicode(const SRC_CHAR* src,
       chars_written = WriteUnicodeCharacter(0xFFFD, output);
       success = false;
     }
-    if (offsets_for_adjustment) {
+    if ((output_offset != std::wstring::npos) &&
+        (*offset_for_adjustment > original_i)) {
       // NOTE: ReadUnicodeCharacter() adjusts |i| to point _at_ the last
       // character read, not after it (so that incrementing it in the loop
       // increment will place it at the right location), so we need to account
       // for that in determining the amount that was read.
-      adjustments.push_back(AdjustOffset::Adjustment(
-          original_i, i - original_i + 1, chars_written));
+      if (*offset_for_adjustment <= static_cast<size_t>(i))
+        output_offset = std::wstring::npos;
+      else
+        output_offset += chars_written - (i - original_i + 1);
     }
   }
 
-  // Make offset adjustment.
-  if (offsets_for_adjustment && !adjustments.empty()) {
-    std::for_each(offsets_for_adjustment->begin(),
-                  offsets_for_adjustment->end(),
-                  AdjustOffset(adjustments));
-  }
-
+  if (offset_for_adjustment)
+    *offset_for_adjustment = output_offset;
   return success;
 }
 
@@ -71,44 +63,16 @@ 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,
-                                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);
+  return ConvertUnicode(src, src_len, output, offset_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;
+  std::wstring ret;
+  UTF8ToWideAndAdjustOffset(utf8.data(), utf8.length(), &ret,
+                            offset_for_adjustment);
+  return ret;
 }
 
 // UTF-16 <-> Wide -------------------------------------------------------------
@@ -126,19 +90,6 @@ bool UTF16ToWideAndAdjustOffset(const char16* src,
   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()))
@@ -146,109 +97,25 @@ std::wstring UTF16ToWideAndAdjustOffset(const string16& utf16,
   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);
-  bool ret = ConvertUnicode(src, src_len, output, &offsets);
-  if (offset_for_adjustment)
-    *offset_for_adjustment = offsets[0];
-  return ret;
-}
-
-bool UTF16ToWideAndAdjustOffsets(const char16* src,
-                                 size_t src_len,
-                                 std::wstring* 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);
-  return ConvertUnicode(src, src_len, output, offsets_for_adjustment);
+  return ConvertUnicode(src, src_len, output, offset_for_adjustment);
 }
 
 std::wstring UTF16ToWideAndAdjustOffset(const string16& utf16,
                                         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,
-                              &offsets);
-  if (offset_for_adjustment)
-    *offset_for_adjustment = offsets[0];
-  return result;
-}
-
-std::wstring UTF16ToWideAndAdjustOffsets(
-    const string16& utf16,
-    std::vector<size_t>* offsets_for_adjustment) {
-  std::wstring result;
-  UTF16ToWideAndAdjustOffsets(utf16.data(), utf16.length(), &result,
-                              offsets_for_adjustment);
-  return result;
+  std::wstring ret;
+  UTF16ToWideAndAdjustOffset(utf16.data(), utf16.length(), &ret,
+                             offset_for_adjustment);
+  return ret;
 }
 
 #endif  // defined(WCHAR_T_IS_UTF32)
-
-template <typename T>
-LimitOffset<T>::LimitOffset(size_t limit)
-  : limit_(limit) {}
-
-template <typename T>
-void LimitOffset<T>::operator()(size_t& offset) {
-  if (offset >= limit_)
-    offset = T::npos;
-}
-
-AdjustOffset::Adjustment::Adjustment(size_t location,
-                                     size_t old_length,
-                                     size_t new_length)
-  : location(location),
-    old_length(old_length),
-    new_length(new_length) {}
-
-AdjustOffset::AdjustOffset(const Adjustments& adjustments)
-    : adjustments_(adjustments) {}
-
-void AdjustOffset::operator()(size_t& offset) {
-  if (offset == std::wstring::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;
-      return;
-    }
-    if (offset <= location)
-      break;
-    if (offset < (location + i->old_length)) {
-      offset = std::wstring::npos;
-      return;
-    }
-    adjustment += (i->old_length - i->new_length);
-  }
-  offset -= adjustment;
-}