Handle page tree node with no /Type

Original reported here:
https://bugs.launchpad.net/ubuntu/+source/qpdf/+bug/1397413

The PDF specification says that the /Type key for nodes in the pages
dictionary (both /Page and /Pages) is required, but some PDF files
omit them. Use the presence of other keys to determine the type of
pages tree node this is if the type key is not found.

5 files changed, 112 insertions, 2 deletions

diff --git a/ChangeLog b/ChangeLog
index 77ab74b9..72cef333 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,11 @@
+2014-12-01  Jay Berkenbilt  <ejb@ql.org>
+
+	* Some broken PDF files lack the required /Type key for /Page and
+	/Pages nodes in the page dictionary. QPDF now uses other methods
+	to figure out what kind of node it is looking at so that it can
+	handle those files. Original reported at
+	https://bugs.launchpad.net/ubuntu/+source/qpdf/+bug/1397413
+
 2014-11-14  Jay Berkenbilt  <ejb@ql.org>
 
 	* Bug fix: QPDFObjectHandle::getPageContents() no longer throws an
diff --git a/libqpdf/QPDF_pages.cc b/libqpdf/QPDF_pages.cc
index e8d107b3..44db064c 100644
--- a/libqpdf/QPDF_pages.cc
+++ b/libqpdf/QPDF_pages.cc
@@ -56,7 +56,20 @@ void
 QPDF::getAllPagesInternal(QPDFObjectHandle cur_pages,
 			  std::vector<QPDFObjectHandle>& result)
 {
-    std::string type = cur_pages.getKey("/Type").getName();
+    std::string type;
+    QPDFObjectHandle type_key = cur_pages.getKey("/Type");
+    if (type_key.isName())
+    {
+        type = type_key.getName();
+    }
+    else if (cur_pages.hasKey("/Kids"))
+    {
+        type = "/Pages";
+    }
+    else
+    {
+        type = "/Page";
+    }
     if (type == "/Pages")
     {
 	QPDFObjectHandle kids = cur_pages.getKey("/Kids");
diff --git a/qpdf/qtest/qpdf.test b/qpdf/qtest/qpdf.test
index b2bf06a7..3bd1a2fa 100644
--- a/qpdf/qtest/qpdf.test
+++ b/qpdf/qtest/qpdf.test
@@ -199,7 +199,7 @@ $td->runtest("remove page we don't have",
 show_ntests();
 # ----------
 $td->notify("--- Miscellaneous Tests ---");
-$n_tests += 73;
+$n_tests += 74;
 
 $td->runtest("qpdf version",
 	     {$td->COMMAND => "qpdf --version"},
@@ -558,6 +558,10 @@ $td->runtest("handle page no with contents",
              {$td->COMMAND => "qpdf --show-pages page-no-content.pdf"},
              {$td->FILE => "page-no-content.out", $td->EXIT_STATUS => 0},
              $td->NORMALIZE_NEWLINES);
+$td->runtest("no type key for page nodes",
+             {$td->COMMAND => "qpdf --check no-pages-types.pdf"},
+             {$td->FILE => "no-pages-types.out", $td->EXIT_STATUS => 0},
+             $td->NORMALIZE_NEWLINES);
 
 show_ntests();
 # ----------
diff --git a/qpdf/qtest/qpdf/no-pages-types.out b/qpdf/qtest/qpdf/no-pages-types.out
new file mode 100644
index 00000000..0d5eb23b
--- /dev/null
+++ b/qpdf/qtest/qpdf/no-pages-types.out
@@ -0,0 +1,6 @@
+checking no-pages-types.pdf
+PDF Version: 1.3
+File is not encrypted
+File is not linearized
+No syntax or stream encoding errors found; the file may still contain
+errors that qpdf cannot detect
diff --git a/qpdf/qtest/qpdf/no-pages-types.pdf b/qpdf/qtest/qpdf/no-pages-types.pdf
new file mode 100644
index 00000000..9bef0bbb
--- /dev/null
+++ b/qpdf/qtest/qpdf/no-pages-types.pdf
@@ -0,0 +1,79 @@
+%PDF-1.3
+1 0 obj
+<<
+  /Type /Catalog
+  /Pages 2 0 R
+>>
+endobj
+
+2 0 obj
+<<
+  /Zype /Pages
+  /Kids [
+    3 0 R
+  ]
+  /Count 1
+>>
+endobj
+
+3 0 obj
+<<
+  /Zype /Page
+  /Parent 2 0 R
+  /MediaBox [0 0 612 792]
+  /Contents 4 0 R
+  /Resources <<
+    /ProcSet 5 0 R
+    /Font <<
+      /F1 6 0 R
+    >>
+  >>
+>>
+endobj
+
+4 0 obj
+<<
+  /Length 44
+>>
+stream
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Potato) Tj
+ET
+endstream
+endobj
+
+5 0 obj
+[
+  /PDF
+  /Text
+]
+endobj
+
+6 0 obj
+<<
+  /Type /Font
+  /Subtype /Type1
+  /Name /F1
+  /BaseFont /Helvetica
+  /Encoding /WinAnsiEncoding
+>>
+endobj
+
+xref
+0 7
+0000000000 65535 f 
+0000000009 00000 n 
+0000000063 00000 n 
+0000000135 00000 n 
+0000000307 00000 n 
+0000000403 00000 n 
+0000000438 00000 n 
+trailer <<
+  /Size 7
+  /Root 1 0 R
+>>
+startxref
+556
+%%EOF