Remove the HTMLSourceTracker

This class was previously only (really) used in HTMLViewSourceParser,
so this CL folds it into that class.

This CL should not change any functionality.

Bug: 901056
Change-Id: Ia47e5da05b586c542c4ff93a94dafdb439f22dd0
Reviewed-on: https://chromium-review.googlesource.com/c/chromium/src/+/2225124
Commit-Queue: Mason Freed <masonfreed@chromium.org>
Reviewed-by: Richard Townsend <richard.townsend@arm.com>
Cr-Commit-Position: refs/heads/master@{#773785}

third_party/blink/renderer/core/html/parser/BUILD.gn

@@ -47,8 +47,6 @@ blink_core_sources("parser") {
     "html_preload_scanner.h",
     "html_resource_preloader.cc",
     "html_resource_preloader.h",
-    "html_source_tracker.cc",
-    "html_source_tracker.h",
     "html_srcset_parser.cc",
     "html_srcset_parser.h",
     "html_stack_item.h",

third_party/blink/renderer/core/html/parser/background_html_parser.h

@@ -37,7 +37,6 @@
 #include "third_party/blink/renderer/core/html/parser/compact_html_token.h"
 #include "third_party/blink/renderer/core/html/parser/html_parser_options.h"
 #include "third_party/blink/renderer/core/html/parser/html_preload_scanner.h"
-#include "third_party/blink/renderer/core/html/parser/html_source_tracker.h"
 #include "third_party/blink/renderer/core/html/parser/html_tree_builder_simulator.h"
 #include "third_party/blink/renderer/core/html/parser/text_resource_decoder.h"
 #include "third_party/blink/renderer/core/page/viewport_description.h"
@@ -108,7 +107,6 @@ class BackgroundHTMLParser {
   void UpdateDocument(const String& decoded_data);
 
   BackgroundHTMLInputStream input_;
-  HTMLSourceTracker source_tracker_;
   std::unique_ptr<HTMLToken> token_;
   std::unique_ptr<HTMLTokenizer> tokenizer_;
   HTMLTreeBuilderSimulator tree_builder_simulator_;

third_party/blink/renderer/core/html/parser/html_source_tracker.cc

-/*
- * Copyright (C) 2010 Adam Barth. All Rights Reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
- * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
- * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
- * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include "third_party/blink/renderer/core/html/parser/html_source_tracker.h"
-
-#include "third_party/blink/renderer/core/html/parser/html_tokenizer.h"
-#include "third_party/blink/renderer/platform/wtf/text/string_builder.h"
-
-namespace blink {
-
-HTMLSourceTracker::HTMLSourceTracker() : is_started_(false) {}
-
-void HTMLSourceTracker::Start(SegmentedString& current_input,
-                              HTMLTokenizer* tokenizer,
-                              HTMLToken& token) {
-  if (token.GetType() == HTMLToken::kUninitialized && !is_started_) {
-    previous_source_.Clear();
-    if (NeedToCheckTokenizerBuffer(tokenizer) &&
-        tokenizer->NumberOfBufferedCharacters())
-      previous_source_ = tokenizer->BufferedCharacters();
-  } else {
-    previous_source_.Append(current_source_);
-  }
-
-  is_started_ = true;
-  current_source_ = current_input;
-  token.SetBaseOffset(current_source_.NumberOfCharactersConsumed() -
-                      previous_source_.length());
-}
-
-void HTMLSourceTracker::end(SegmentedString& current_input,
-                            HTMLTokenizer* tokenizer,
-                            HTMLToken& token) {
-  is_started_ = false;
-
-  cached_source_for_token_ = String();
-
-  // FIXME: This work should really be done by the HTMLTokenizer.
-  wtf_size_t number_of_buffered_characters = 0u;
-  if (NeedToCheckTokenizerBuffer(tokenizer)) {
-    number_of_buffered_characters = tokenizer->NumberOfBufferedCharacters();
-  }
-  token.end(current_input.NumberOfCharactersConsumed() -
-            number_of_buffered_characters);
-}
-
-String HTMLSourceTracker::SourceForToken(const HTMLToken& token) {
-  if (!cached_source_for_token_.IsEmpty())
-    return cached_source_for_token_;
-
-  wtf_size_t length;
-  if (token.GetType() == HTMLToken::kEndOfFile) {
-    // Consume the remainder of the input, omitting the null character we use to
-    // mark the end of the file.
-    length = previous_source_.length() + current_source_.length() - 1;
-  } else {
-    DCHECK(!token.StartIndex());
-    length = static_cast<wtf_size_t>(token.EndIndex() - token.StartIndex());
-  }
-
-  StringBuilder source;
-  source.ReserveCapacity(length);
-
-  size_t i = 0;
-  for (; i < length && !previous_source_.IsEmpty(); ++i) {
-    source.Append(previous_source_.CurrentChar());
-    previous_source_.Advance();
-  }
-  for (; i < length; ++i) {
-    DCHECK(!current_source_.IsEmpty());
-    source.Append(current_source_.CurrentChar());
-    current_source_.Advance();
-  }
-
-  cached_source_for_token_ = source.ToString();
-  return cached_source_for_token_;
-}
-
-bool HTMLSourceTracker::NeedToCheckTokenizerBuffer(HTMLTokenizer* tokenizer) {
-  HTMLTokenizer::State state = tokenizer->GetState();
-  // The temporary buffer must not be used unconditionally, because in some
-  // states (e.g. ScriptDataDoubleEscapedStartState), data is appended to
-  // both the temporary buffer and the token itself.
-  return state == HTMLTokenizer::kDataState ||
-         HTMLTokenizer::IsEndTagBufferingState(state);
-}
-
-}  // namespace blink

third_party/blink/renderer/core/html/parser/html_source_tracker.h

-/*
- * Copyright (C) 2010 Adam Barth. All Rights Reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
- * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
- * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
- * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
- * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
- * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
- * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
- * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef THIRD_PARTY_BLINK_RENDERER_CORE_HTML_PARSER_HTML_SOURCE_TRACKER_H_
-#define THIRD_PARTY_BLINK_RENDERER_CORE_HTML_PARSER_HTML_SOURCE_TRACKER_H_
-
-#include "base/macros.h"
-#include "third_party/blink/renderer/core/html/parser/html_token.h"
-#include "third_party/blink/renderer/platform/text/segmented_string.h"
-#include "third_party/blink/renderer/platform/wtf/allocator/allocator.h"
-
-namespace blink {
-
-class HTMLTokenizer;
-
-class HTMLSourceTracker {
-  DISALLOW_NEW();
-
- public:
-  HTMLSourceTracker();
-
-  // FIXME: Once we move "end" into HTMLTokenizer, rename "start" to
-  // something that makes it obvious that this method can be called multiple
-  // times.
-  void Start(SegmentedString&, HTMLTokenizer*, HTMLToken&);
-  void end(SegmentedString&, HTMLTokenizer*, HTMLToken&);
-
-  String SourceForToken(const HTMLToken&);
-
- private:
-  bool NeedToCheckTokenizerBuffer(HTMLTokenizer*);
-
-  SegmentedString previous_source_;
-  SegmentedString current_source_;
-
-  String cached_source_for_token_;
-
-  bool is_started_;
-
-  DISALLOW_COPY_AND_ASSIGN(HTMLSourceTracker);
-};
-
-}  // namespace blink
-
-#endif

third_party/blink/renderer/core/html/parser/html_view_source_parser.cc

@@ -44,12 +44,12 @@ HTMLViewSourceParser::HTMLViewSourceParser(HTMLViewSourceDocument& document,
 
 void HTMLViewSourceParser::PumpTokenizer() {
   while (true) {
-    source_tracker_.Start(input_.Current(), tokenizer_.get(), token_);
+    StartTracker(input_.Current(), tokenizer_.get(), token_);
     if (!tokenizer_->NextToken(input_.Current(), token_))
       return;
-    source_tracker_.end(input_.Current(), tokenizer_.get(), token_);
+    EndTracker(input_.Current(), tokenizer_.get(), token_);
 
-    GetDocument()->AddSource(source_tracker_.SourceForToken(token_), token_);
+    GetDocument()->AddSource(SourceForToken(token_), token_);
 
     // FIXME: The tokenizer should do this work for us.
     if (token_.GetType() == HTMLToken::kStartTag)
@@ -75,4 +75,80 @@ void HTMLViewSourceParser::Finish() {
   }
 }
 
+void HTMLViewSourceParser::StartTracker(SegmentedString& current_input,
+                                        HTMLTokenizer* tokenizer,
+                                        HTMLToken& token) {
+  if (token.GetType() == HTMLToken::kUninitialized && !tracker_is_started_) {
+    previous_source_.Clear();
+    if (NeedToCheckTokenizerBuffer(tokenizer) &&
+        tokenizer->NumberOfBufferedCharacters())
+      previous_source_ = tokenizer->BufferedCharacters();
+  } else {
+    previous_source_.Append(current_source_);
+  }
+
+  tracker_is_started_ = true;
+  current_source_ = current_input;
+  token.SetBaseOffset(current_source_.NumberOfCharactersConsumed() -
+                      previous_source_.length());
+}
+
+void HTMLViewSourceParser::EndTracker(SegmentedString& current_input,
+                                      HTMLTokenizer* tokenizer,
+                                      HTMLToken& token) {
+  tracker_is_started_ = false;
+
+  cached_source_for_token_ = String();
+
+  // FIXME: This work should really be done by the HTMLTokenizer.
+  wtf_size_t number_of_buffered_characters = 0u;
+  if (NeedToCheckTokenizerBuffer(tokenizer)) {
+    number_of_buffered_characters = tokenizer->NumberOfBufferedCharacters();
+  }
+  token.end(current_input.NumberOfCharactersConsumed() -
+            number_of_buffered_characters);
+}
+
+String HTMLViewSourceParser::SourceForToken(const HTMLToken& token) {
+  if (!cached_source_for_token_.IsEmpty())
+    return cached_source_for_token_;
+
+  wtf_size_t length;
+  if (token.GetType() == HTMLToken::kEndOfFile) {
+    // Consume the remainder of the input, omitting the null character we use to
+    // mark the end of the file.
+    length = previous_source_.length() + current_source_.length() - 1;
+  } else {
+    DCHECK(!token.StartIndex());
+    length = static_cast<wtf_size_t>(token.EndIndex() - token.StartIndex());
+  }
+
+  StringBuilder source;
+  source.ReserveCapacity(length);
+
+  size_t i = 0;
+  for (; i < length && !previous_source_.IsEmpty(); ++i) {
+    source.Append(previous_source_.CurrentChar());
+    previous_source_.Advance();
+  }
+  for (; i < length; ++i) {
+    DCHECK(!current_source_.IsEmpty());
+    source.Append(current_source_.CurrentChar());
+    current_source_.Advance();
+  }
+
+  cached_source_for_token_ = source.ToString();
+  return cached_source_for_token_;
+}
+
+bool HTMLViewSourceParser::NeedToCheckTokenizerBuffer(
+    HTMLTokenizer* tokenizer) {
+  HTMLTokenizer::State state = tokenizer->GetState();
+  // The temporary buffer must not be used unconditionally, because in some
+  // states (e.g. ScriptDataDoubleEscapedStartState), data is appended to
+  // both the temporary buffer and the token itself.
+  return state == HTMLTokenizer::kDataState ||
+         HTMLTokenizer::IsEndTagBufferingState(state);
+}
+
 }  // namespace blink

third_party/blink/renderer/core/html/parser/html_view_source_parser.h

@@ -31,7 +31,6 @@
 #include "third_party/blink/renderer/core/dom/decoded_data_document_parser.h"
 #include "third_party/blink/renderer/core/html/html_view_source_document.h"
 #include "third_party/blink/renderer/core/html/parser/html_input_stream.h"
-#include "third_party/blink/renderer/core/html/parser/html_source_tracker.h"
 #include "third_party/blink/renderer/core/html/parser/html_tokenizer.h"
 
 namespace blink {
@@ -56,10 +55,20 @@ class CORE_EXPORT HTMLViewSourceParser final
   void PumpTokenizer();
   void UpdateTokenizerState();
 
+  void StartTracker(SegmentedString&, HTMLTokenizer*, HTMLToken&);
+  void EndTracker(SegmentedString&, HTMLTokenizer*, HTMLToken&);
+  String SourceForToken(const HTMLToken&);
+  bool NeedToCheckTokenizerBuffer(HTMLTokenizer*);
+
   HTMLInputStream input_;
   HTMLToken token_;
-  HTMLSourceTracker source_tracker_;
   std::unique_ptr<HTMLTokenizer> tokenizer_;
+  bool tracker_is_started_;
+
+  SegmentedString previous_source_;
+  SegmentedString current_source_;
+
+  String cached_source_for_token_;
 };
 
 }  // namespace blink