Store page no for distilled pages undergoing distillation.

components/dom_distiller/core/distiller.h

 // Copyright 2013 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.
 
 #ifndef COMPONENTS_DOM_DISTILLER_CORE_DISTILLER_H_
 #define COMPONENTS_DOM_DISTILLER_CORE_DISTILLER_H_
 
 #include <string>
 
 #include "base/callback.h"
@@ skipping 50 matching lines @@
       const DistillerURLFetcherFactory& distiller_url_fetcher_factory);
   virtual ~DistillerImpl();
 
   // Creates an execution context. This must be called once before any calls are
   // made to distill the page.
   virtual void Init();
 
   virtual void DistillPage(const GURL& url,
                            const DistillerCallback& callback) OVERRIDE;
 
+  void SetMaxNumPagesInArticle(size_t max_num_pages);
+
  private:
-  void OnFetchImageDone(DistilledPageProto* distilled_page_proto,
+  // In case of multiple pages, the Distiller maintains state of multiple pages
+  // as relative page numbers. E.g. if distillation starts at page 2 for a 3

[cjhopman, 2014/02/15 02:44:15]

nit: relative to what? Might not be needed since it can be determined from the
example, but maybe just say "as page numbers relative to the page where
distillation started".

[shashi, 2014/02/15 03:15:36]

Done.

+  // page article. The relative page numbers assigned to pages will be [-1,0,1].
+
+  // Class representing the state of a page under distillation.
+  struct DistilledPageData {
+    DistilledPageData();
+    virtual ~DistilledPageData();
+    // Relative page number of the page.
+    int page_num;
+    std::string title;
+    ScopedVector<DistillerURLFetcher> image_fetchers_;
+    scoped_ptr<DistilledPageProto> proto;
+
+   private:
+    DISALLOW_COPY_AND_ASSIGN(DistilledPageData);
+  };
+
+  void OnFetchImageDone(int page_num,
                         DistillerURLFetcher* url_fetcher,
                         const std::string& id,
                         const std::string& response);
 
-  void OnPageDistillationFinished(const GURL& page_url,
+  void OnPageDistillationFinished(int page_num,
+                                  const GURL& page_url,
                                   scoped_ptr<DistilledPageInfo> distilled_page,
                                   bool distillation_successful);
 
-  virtual void FetchImage(DistilledPageProto* distilled_page_proto,
+  virtual void FetchImage(int page_num,
                           const std::string& image_id,
                           const std::string& item);
 
-  // Distills the page and adds the new page to |article_proto|.
-  void DistillPage(const GURL& url);
+  // Distills the next page.
+  void DistillNextPage();
+
+  // Adds the |url| to |pages_to_be_distilled| if |page_num| is a valid relative
+  // page number and |url| is valid. Ignores duplicate pages and urls.
+  void AddToDistillationQueue(int page_num, const GURL& url);
+
+  // Check if |page_num| is a valid relative page number, i.e. page with
+  // |page_num| is either under distillation or has already completed
+  // distillation.
+  bool IsPageNumberInUse(int page_num) const;
+
+  bool AreAllPagesFinished() const;
+
+  // Total number of pages in the article that the distiller knows of, this
+  // includes pages that are pending distillation.
+  size_t TotalPageCount() const;
 
   // Runs |distillation_cb_| if all distillation callbacks and image fetches are
   // complete.
   void RunDistillerCallbackIfDone();
 
+  // Checks if page |distilled_page_data| has finished distillation, including
+  // all image fetches.
+  void AddPageIfDone(int page_num);
+
+  DistilledPageData* GetPageAtIndex(size_t index) const;
+
   const DistillerURLFetcherFactory& distiller_url_fetcher_factory_;
   scoped_ptr<PageDistiller> page_distiller_;
   DistillerCallback distillation_cb_;
 
-  ScopedVector<DistillerURLFetcher> image_fetchers_;
-  scoped_ptr<DistilledArticleProto> article_proto_;
-  bool distillation_in_progress_;
-  // Set to keep track of which urls are already seen by the distiller.
-  base::hash_set<std::string> processed_urls_;
+  // Set of pages that are under distillation or have finished distillation.
+  // |started_pages_index_| and |finished_pages_index_| maintains the mapping
+  // from page number to the indices in |pages_|.
+  ScopedVector<DistilledPageData> pages_;
+
+  // Maps page numbers of finished pages to the indices in |pages_|.
+  std::map<int, size_t> finished_pages_index_;
+
+  // The list of pages that are still waiting for distillation to start.

[cjhopman, 2014/02/15 02:44:15]

Nit: The order of declaration here should be finished/started/waiting (or the
reverse of that).

[shashi, 2014/02/15 03:15:36]

Done.

[shashi, 2014/02/15 03:15:36]

Done.

+  // This is a map, to make distiller prefer distilling lower page numbers
+  // first.
+  std::map<int, GURL> waiting_pages_;
+
+  // Maps page numbers of pages under distillation to the indices in |pages_|.
+  // If a page is |started_pages_| that means it is still waiting for an action
+  // (distillation or image fetch) to finish.
+  base::hash_map<int, size_t> started_pages_index_;
+
+  // Set to keep track of which urls are already seen by the distiller. Used to
+  // prevent distiller from distilling the same url twice.
+  base::hash_set<std::string> seen_urls_;
+
+  size_t max_pages_in_article_;
 
   DISALLOW_COPY_AND_ASSIGN(DistillerImpl);
 };
 
 }  // namespace dom_distiller
 
 #endif  // COMPONENTS_DOM_DISTILLER_CORE_DISTILLER_H_