Ignore objects with offset 0

ChangeLog

@@ -1,3 +1,9 @@
+2012-11-20  Jay Berkenbilt  <ejb@ql.org>
+
+	* Ignore (with warning) non-freed objects in the xref table whose
+	offset is 0.  Some PDF producers (incorrectly) do this.  See
+	https://bugs.linuxfoundation.org/show_bug.cgi?id=1081.
+
 2012-09-23  Jay Berkenbilt  <ejb@ql.org>
 
 	* Add public methods QPDF::processInputSource and

TODO

@@ -1,12 +1,31 @@
 General
 =======
 
- * See if I can support the encryption format used with /R 5 /V 5,
-   even though a qpdf-announce subscriber with an adobe.com email
-   address mentioned that this is deprecated.  There is also a new
-   encryption format coming in a future release, which may be better
-   to support.  As of the qpdf 3.0 release, the specification was not
-   publicly available yet.
+ * See if I can support the encryption format used with /R 5 /V 5
+   (AESV3), even though a qpdf-announce subscriber with an adobe.com
+   email address mentioned that this is deprecated.  There is also a
+   new encryption format coming in a future release (PDF 2.0), which
+   may be better to support.  As of the qpdf 3.0 release, the
+   specification was not publicly available yet.
+
+   AESV3 encryption is supported with PDF 1.7 extension level 3 and is
+   being deprecated, but there are plenty of files out there.  The
+   encryption format is decribed in adobe_supplement_iso32000.pdf.
+   Such a file must specify that it uses these extensions in its
+   document catalog:
+
+   <<
+     /Type /Catalog
+     /Extensions <<
+       /ADBE <<
+         /BaseVersion /1.7
+         /ExtensionLevel 3
+       >>
+     >>
+   >>
+
+   Possible sha256 implementations: http://sol-biotech.com/code/sha2/,
+   http://hashlib2plus.sourceforge.net/
 
  * Consider the possibility of doing something locale-aware to support
    non-ASCII passwords.  Update documentation if this is done.

libqpdf/QPDF.cc

@@ -1253,6 +1253,21 @@ QPDF::readObjectAtOffset(bool try_recovery,
 			 int& objid, int& generation)
 {
     setLastObjectDescription(description, exp_objid, exp_generation);
+
+    // Special case: if offset is 0, just return null.  Some PDF
+    // writers, in particuar "Mac OS X 10.7.5 Quartz PDFContext", may
+    // store deleted objects in the xref table as "0000000000 00000
+    // n", which is not correct, but it won't hurt anything for to
+    // ignore these.
+    if (offset == 0)
+    {
+        QTC::TC("qpdf", "QPDF bogus 0 offset", 0);
+	warn(QPDFExc(qpdf_e_damaged_pdf, this->file->getName(),
+		     this->last_object_description, 0,
+		     "object has offset 0"));
+        return QPDFObjectHandle::newNull();
+    }
+
     this->file->seek(offset, SEEK_SET);
 
     QPDFTokenizer::Token tobjid = readToken(this->file);

qpdf/qpdf.testcov

@@ -242,3 +242,4 @@ QPDF_Tokenizer EOF reading token 0
 QPDF_Tokenizer EOF reading appendable token 0
 QPDFWriter extra header text no newline 0
 QPDFWriter extra header text add newline 0
+QPDF bogus 0 offset 0

qpdf/qtest/qpdf.test

@@ -149,7 +149,7 @@ $td->runtest("remove page we don't have",
 	     $td->NORMALIZE_NEWLINES);
 # ----------
 $td->notify("--- Miscellaneous Tests ---");
-$n_tests += 55;
+$n_tests += 56;
 
 $td->runtest("qpdf version",
 	     {$td->COMMAND => "qpdf --version"},
@@ -410,6 +410,10 @@ $td->runtest("output to custom pipeline",
 $td->runtest("check output",
              {$td->FILE => "a.pdf"},
              {$td->FILE => "custom-pipeline.pdf"});
+$td->runtest("object with zero offset",
+             {$td->COMMAND => "qpdf --check zero-offset.pdf"},
+             {$td->FILE => "zero-offset.out", $td->EXIT_STATUS => 3},
+             $td->NORMALIZE_NEWLINES);
 
 show_ntests();
 # ----------

qpdf/qtest/qpdf/zero-offset.out

@@ -0,0 +1,5 @@
+checking zero-offset.pdf
+PDF Version: 1.3
+File is not encrypted
+File is not linearized
+WARNING: zero-offset.pdf (object 27 0): object has offset 0