From caab1b0e1642bc6ee0194c7ab4c4a4de2ab22f2c Mon Sep 17 00:00:00 2001
From: Jay Berkenbilt <ejb@ql.org>
Date: Fri, 14 Nov 2014 13:43:34 -0500
Subject: [PATCH] Handle pages with no /Contents from getPageContents()

The spec allows /Contents to be omitted for pages that are blank, but
QPDFObjectHandle::getPageContents() was throwing an exception in this
case.
---
 ChangeLog                           |   8 ++++++++
 libqpdf/QPDFObjectHandle.cc         |   2 +-
 qpdf/qtest/qpdf.test                |   7 ++++++-
 qpdf/qtest/qpdf/page-no-content.out |   8 ++++++++
 qpdf/qtest/qpdf/page-no-content.pdf | Bin 0 -> 1362 bytes
 5 files changed, 23 insertions(+), 2 deletions(-)
 create mode 100644 qpdf/qtest/qpdf/page-no-content.out
 create mode 100644 qpdf/qtest/qpdf/page-no-content.pdf

diff --git a/ChangeLog b/ChangeLog
index 8816d6cf..77ab74b9 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,11 @@
+2014-11-14  Jay Berkenbilt  <ejb@ql.org>
+
+	* Bug fix: QPDFObjectHandle::getPageContents() no longer throws an
+	exception when called on a page that has no /Contents key in its
+	dictionary. This is allowed by the spec, and some software
+	packages generate files like this for pages that are blank in the
+	original.
+
 2014-06-07  Jay Berkenbilt  <ejb@ql.org>
 
 	* 5.1.2: release
diff --git a/libqpdf/QPDFObjectHandle.cc b/libqpdf/QPDFObjectHandle.cc
index ef92e3ac..eec4fae3 100644
--- a/libqpdf/QPDFObjectHandle.cc
+++ b/libqpdf/QPDFObjectHandle.cc
@@ -633,7 +633,7 @@ QPDFObjectHandle::getPageContents()
     {
 	result.push_back(contents);
     }
-    else
+    else if (! contents.isNull())
     {
 	throw std::runtime_error("unknown object type inspecting /Contents "
 				 "key in page dictionary");
diff --git a/qpdf/qtest/qpdf.test b/qpdf/qtest/qpdf.test
index 8e697844..b2bf06a7 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 += 72;
+$n_tests += 73;
 
 $td->runtest("qpdf version",
 	     {$td->COMMAND => "qpdf --version"},
@@ -554,6 +554,11 @@ $td->runtest("check file",
              {$td->FILE => "a.pdf"},
              {$td->FILE => "indirect-decode-parms-out.pdf"});
 
+$td->runtest("handle page no with contents",
+             {$td->COMMAND => "qpdf --show-pages page-no-content.pdf"},
+             {$td->FILE => "page-no-content.out", $td->EXIT_STATUS => 0},
+             $td->NORMALIZE_NEWLINES);
+
 show_ntests();
 # ----------
 $td->notify("--- Numeric range parsing tests ---");
diff --git a/qpdf/qtest/qpdf/page-no-content.out b/qpdf/qtest/qpdf/page-no-content.out
new file mode 100644
index 00000000..15df72db
--- /dev/null
+++ b/qpdf/qtest/qpdf/page-no-content.out
@@ -0,0 +1,8 @@
+page 1: 3 0 R
+  content:
+    6 0 R
+page 2: 4 0 R
+  content:
+page 3: 5 0 R
+  content:
+    9 0 R
diff --git a/qpdf/qtest/qpdf/page-no-content.pdf b/qpdf/qtest/qpdf/page-no-content.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..77b7832a36bf834bb13ccaa52548c08622103200
GIT binary patch
literal 1362
zcmcgsOODe(5alDJ!4h{UB(ekA-Tt&KMHWml5fQ(TL}C$T(Xl(hC}ShL1A!G6;0CNX
z0vBML5kg`G>){gY5Y?S=3`y7lwq&=ft6sgTdhJH9-MK+;I#%Pu_jf-m3O3}Er&hBG
zq$g&w1csJAkm1W`5=cuZG0$fZMV8DG?Wnh_fL6Z96gWWcrb!7ST<K8PJU#OqS3qm*
z8b-U;Fqx8>D#14~<i1Q&ahNX=(Z<`S40y-@v3jCF$BJTKmieNHk+Wvs$#KUlC~yN5
zMHo@!@jxmFHkNf^n$Is)Y0ed$-;?Zh*Tq%tEzE1!hbF~eU{7_`ePmbDr+Q9n(_TWl
za}}X`GMlL<;0D-}bgpE9@3~O2E#o{fMVG3O;@DcgEv?gj@AC_1XtPHL-HY!(y?MR5
zb@ke%)t7@6>0UqiIy^Y}R$Mu~aPH&z%PUmCS>%}(bepTJhoY2b1mupKKbI<v1(2f*
zQ>NJr$m2A-ot0^Acp#2ZUmXf$u$U+#HeDHhuM0F-wO;i6bgB{dq}@R$xl}N&M5$X}
z5&3`Rn>kf!|8f0B0Do@4vXE2D2FfgZbAj)9jt5iN*eL2&Uy#){AEm!#qZqYqV;m>2
z<>#<nKbNC;xBR?dH`Wh#WBDGuz{Nks7GCJ#X{c<f5a}E>u1|hH&lRjs3K^uYB=!SH
zw+*9a?AR=^U5AG5bSmvQraa)>^@NjfTur0q#E+AZI&tDLCc|J7*o?=NN}fyt*G`;h
VtbZ4!5`{9&4g+R28b=R1)=x>Gd!YaT

literal 0
HcmV?d00001