summaryrefslogtreecommitdiff
path: root/core/fpdfapi/parser
diff options
context:
space:
mode:
authorart-snake <art-snake@yandex-team.ru>2016-11-09 15:20:59 -0800
committerCommit bot <commit-bot@chromium.org>2016-11-09 15:20:59 -0800
commitc0a47773d6dadeb8a39a6ced4ebbb1795e2e411f (patch)
tree79efdd2dd00f19294a44a3b4fe5e851221ea5dc0 /core/fpdfapi/parser
parent335cf093231c984a23cb9ea113148ea1f19621ba (diff)
downloadpdfium-c0a47773d6dadeb8a39a6ced4ebbb1795e2e411f.tar.xz
Fix receiving page, if it have not obj num.
In some PDF's the page may not have the obj num. For example: testing\corpus\fx\other\jetman_std.pdf in pdfium repository. And CPDF_Document::GetPage failed on second call for this page. Restart the traversing of pages, to fix this Also added test. Review-Url: https://codereview.chromium.org/2491583002
Diffstat (limited to 'core/fpdfapi/parser')
-rw-r--r--core/fpdfapi/parser/cpdf_document.cpp11
-rw-r--r--core/fpdfapi/parser/cpdf_document_unittest.cpp33
2 files changed, 43 insertions, 1 deletions
diff --git a/core/fpdfapi/parser/cpdf_document.cpp b/core/fpdfapi/parser/cpdf_document.cpp
index 1c73ce1015..6788394118 100644
--- a/core/fpdfapi/parser/cpdf_document.cpp
+++ b/core/fpdfapi/parser/cpdf_document.cpp
@@ -492,9 +492,18 @@ CPDF_Dictionary* CPDF_Document::GetPage(int iPage) {
if (!pPages)
return nullptr;
+ if (iPage - m_iNextPageToTraverse + 1 <= 0) {
+ // This can happen when the page does not have an object number. On repeated
+ // calls to this function for the same page index, this condition causes
+ // TraversePDFPages() to incorrectly return nullptr.
+ // Example "testing/corpus/fx/other/jetman_std.pdf"
+ // We should restart traversing in this case.
+ // TODO(art-snake): optimize this.
+ ResetTraversal();
+ }
+ int nPagesToGo = iPage - m_iNextPageToTraverse + 1;
if (m_pTreeTraversal.empty())
m_pTreeTraversal.push_back(std::make_pair(pPages, 0));
- int nPagesToGo = iPage - m_iNextPageToTraverse + 1;
CPDF_Dictionary* pPage = TraversePDFPages(iPage, &nPagesToGo, 0);
m_iNextPageToTraverse = iPage + 1;
return pPage;
diff --git a/core/fpdfapi/parser/cpdf_document_unittest.cpp b/core/fpdfapi/parser/cpdf_document_unittest.cpp
index 7b5ab43b5c..f27e7403f6 100644
--- a/core/fpdfapi/parser/cpdf_document_unittest.cpp
+++ b/core/fpdfapi/parser/cpdf_document_unittest.cpp
@@ -76,6 +76,27 @@ class CPDF_TestDocumentForPages : public CPDF_Document {
std::unique_ptr<CPDF_Dictionary> m_pOwnedRootDict;
};
+class CPDF_TestDocumentWithPageWithoutPageNum : public CPDF_Document {
+ public:
+ CPDF_TestDocumentWithPageWithoutPageNum() : CPDF_Document(nullptr) {
+ // Set up test
+ CPDF_Array* allPages = new CPDF_Array();
+ allPages->AddReference(this, AddIndirectObject(CreateNumberedPage(0)));
+ allPages->AddReference(this, AddIndirectObject(CreateNumberedPage(1)));
+ // Page without pageNum.
+ allPages->Add(CreateNumberedPage(2));
+ CPDF_Dictionary* pagesDict = CreatePageTreeNode(allPages, this, 3);
+
+ m_pOwnedRootDict.reset(new CPDF_Dictionary());
+ m_pOwnedRootDict->SetReferenceFor("Pages", this, pagesDict->GetObjNum());
+ m_pRootDict = m_pOwnedRootDict.get();
+ m_PageList.SetSize(3);
+ }
+
+ private:
+ std::unique_ptr<CPDF_Dictionary> m_pOwnedRootDict;
+};
+
class TestLinearized : public CPDF_LinearizedHeader {
public:
explicit TestLinearized(CPDF_Dictionary* dict)
@@ -105,6 +126,18 @@ TEST_F(cpdf_document_test, GetPages) {
EXPECT_FALSE(page);
}
+TEST_F(cpdf_document_test, GetPageWithoutObjNumTwice) {
+ std::unique_ptr<CPDF_TestDocumentWithPageWithoutPageNum> document =
+ pdfium::MakeUnique<CPDF_TestDocumentWithPageWithoutPageNum>();
+ const CPDF_Dictionary* page = document->GetPage(2);
+ ASSERT_TRUE(page);
+ // This is page without obj num.
+ ASSERT_EQ(0ul, page->GetObjNum());
+ const CPDF_Dictionary* second_call_page = document->GetPage(2);
+ EXPECT_TRUE(second_call_page);
+ EXPECT_EQ(page, second_call_page);
+}
+
TEST_F(cpdf_document_test, GetPagesReverseOrder) {
std::unique_ptr<CPDF_TestDocumentForPages> document =
pdfium::MakeUnique<CPDF_TestDocumentForPages>();