From 900f421e29daf2ab62de3ae8dc821f031bc7bdb3 Mon Sep 17 00:00:00 2001 From: npm Date: Fri, 28 Oct 2016 14:30:44 -0700 Subject: Revert of Traverse PDF page tree only once in CPDF_Document Try 2 (patchset #3 id:40001 of https://codereview.chromium.org/2442403002/ ) Reason for revert: Not quite right yet. Original issue's description: > Traverse PDF page tree only once in CPDF_Document > > Try 2: main fix was recursively popping elements from the stack. Since > the Traverse method can be called on non-root nodes from GetPage(), we > have to make sure to properly update the parents. > > Try 1 at https://codereview.chromium.org/2414423002/ > > In our current implementation of CPDF_Document::GetPage, we traverse > the PDF page tree until we find the index we are looking for. This is > slow when we do calls GetPage(0), GetPage(1), ... since in this case > the page tree will be traversed n times if there are n pages. This CL > makes sure the page tree is only traversed once. > > Time to load the PDF from the bug below in chrome official build: > Before this CL: around 1 minute 25 seconds > After this CL: around 4 seconds > > BUG=chromium:638513 > > Committed: https://pdfium.googlesource.com/pdfium/+/d3a2009d75eac3cda442f545ef0865afae7b35cf TBR=tsepez@chromium.org,weili@chromium.org,thestig@chromium.org # Not skipping CQ checks because original CL landed more than 1 days ago. BUG=chromium:638513 Review-Url: https://codereview.chromium.org/2461063003 --- core/fpdfapi/parser/cpdf_document.h | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) (limited to 'core/fpdfapi/parser/cpdf_document.h') diff --git a/core/fpdfapi/parser/cpdf_document.h b/core/fpdfapi/parser/cpdf_document.h index ef9f663c3b..ea7bd328aa 100644 --- a/core/fpdfapi/parser/cpdf_document.h +++ b/core/fpdfapi/parser/cpdf_document.h @@ -9,7 +9,6 @@ #include #include -#include #include "core/fpdfapi/parser/cpdf_indirect_object_holder.h" #include "core/fpdfapi/parser/cpdf_object.h" @@ -106,7 +105,10 @@ class CPDF_Document : public CPDF_IndirectObjectHolder { protected: // Retrieve page count information by getting count value from the tree nodes int RetrievePageCount() const; - CPDF_Dictionary* TraversePDFPages(int iPage, int nPagesToGo); + CPDF_Dictionary* FindPDFPage(CPDF_Dictionary* pPages, + int iPage, + int nPagesToGo, + int level); int FindPageIndex(CPDF_Dictionary* pNode, uint32_t& skip_count, uint32_t objnum, @@ -122,23 +124,10 @@ class CPDF_Document : public CPDF_IndirectObjectHolder { FX_BOOL bVert, CFX_ByteString basefont, std::function Insert); - int InsertDeletePDFPage(CPDF_Dictionary* pPages, - int nPagesToGo, - CPDF_Dictionary* pPage, - FX_BOOL bInsert, - std::set* pVisited); - int InsertNewPage(int iPage, - CPDF_Dictionary* pPageDict, - CFX_ArrayTemplate& pageList); - void PopAndPropagate(); + std::unique_ptr m_pParser; CPDF_Dictionary* m_pRootDict; CPDF_Dictionary* m_pInfoDict; - // Stack of page nodes to know current position in page tree. Int is the index - // of last processed child. - std::stack> m_pTreeTraversal; - // Index of last page (leaf) processed from page tree. - int m_iLastPageTraversed; bool m_bLinearized; int m_iFirstPageNo; uint32_t m_dwFirstPageObjNum; -- cgit v1.2.3