handle files with object 0 as a real object

git-svn-id: svn+q:///qpdf/trunk@1049 71b93d88-0707-0410-a8cf-f5a4172ac649

ChangeLog

@@ -1,3 +1,16 @@
+2011-01-31  Jay Berkenbilt  <ejb@ql.org>
+
+	* libqpdf/QPDF.cc (readObjectAtOffset): use -1 rather than 0 when
+	reading an object at a given to indicate that no object number is
+	expected.  This allows xref recovery to proceed even if a file
+	uses the invalid object number 0 as a regular object.
+
+	* libqpdf/QPDF_linearization.cc (isLinearized): use -1 rather than
+	0 as a sentintel for not having found the first object in the
+	file.  Since -1 can never match the regular expression, this
+	prevents an infinite loop when checking a file that starts with
+	(erroneous) 0 0 obj.  (Fixes qpdf-Bugs-3159950.)
+
 2010-10-04  Jay Berkenbilt  <ejb@ql.org>
 
 	* 2.2.2: release

libqpdf/QPDF.cc

@@ -782,7 +782,7 @@ QPDF::read_xrefStream(off_t xref_offset)
 	try
 	{
 	    xref_obj = readObjectAtOffset(
-		false, xref_offset, "xref stream", 0, 0, xobj, xgen);
+		false, xref_offset, "xref stream", -1, 0, xobj, xgen);
 	}
 	catch (QPDFExc& e)
 	{
@@ -1580,7 +1580,7 @@ QPDF::readObjectAtOffset(bool try_recovery,
 	objid = atoi(tobjid.getValue().c_str());
 	generation = atoi(tgen.getValue().c_str());
 
-	if (exp_objid &&
+	if ((exp_objid >= 0) &&
 	    (! ((objid == exp_objid) && (generation == exp_generation))))
 	{
 	    QTC::TC("qpdf", "QPDF err wrong objid/generation");
@@ -1593,7 +1593,7 @@ QPDF::readObjectAtOffset(bool try_recovery,
     }
     catch (QPDFExc& e)
     {
-	if (exp_objid && try_recovery && this->attempt_recovery)
+	if ((exp_objid >= 0) && try_recovery && this->attempt_recovery)
 	{
 	    // Try again after reconstructing xref table
 	    reconstruct_xref(e);

libqpdf/QPDF_linearization.cc

@@ -95,9 +95,9 @@ QPDF::isLinearized()
     static PCRE lindict_re("(?s:(\\d+)\\s+0\\s+obj\\s*<<)");
 
     off_t offset = -1;
-    int lindict_obj = 0;
+    int lindict_obj = -1;
     char* p = buf;
-    while (lindict_obj == 0)
+    while (lindict_obj == -1)
     {
 	PCRE::Match m(lindict_re.match(p));
 	if (m)
@@ -312,7 +312,7 @@ QPDF::readHintStream(Pipeline& pl, off_t offset, size_t length)
     int obj;
     int gen;
     QPDFObjectHandle H = readObjectAtOffset(
-	false, offset, "linearization hint stream", 0, 0, obj, gen);
+	false, offset, "linearization hint stream", -1, 0, obj, gen);
     ObjCache& oc = this->obj_cache[ObjGen(obj, gen)];
     off_t min_end_offset = oc.end_before_space;
     off_t max_end_offset = oc.end_after_space;

qpdf/qtest/qpdf.test

@@ -111,7 +111,7 @@ $td->runtest("new stream",
 show_ntests();
 # ----------
 $td->notify("--- Miscellaneous Tests ---");
-$n_tests += 28;
+$n_tests += 29;
 
 $td->runtest("qpdf version",
 	     {$td->COMMAND => "qpdf --version"},
@@ -191,6 +191,14 @@ foreach my $file (qw(short-id long-id))
 		 $td->NORMALIZE_NEWLINES);
 }
 
+# Handle file with invalid xref table and object 0 as a regular object
+# (bug 3159950).
+$td->runtest("check obj0.pdf",
+	     {$td->COMMAND => "qpdf --check obj0.pdf"},
+	     {$td->FILE => "obj0-check.out",
+	      $td->EXIT_STATUS => 3},
+	     $td->NORMALIZE_NEWLINES);
+
 # Min/Force version
 $td->runtest("set min version",
 	     {$td->COMMAND => "qpdf --min-version=1.6 good1.pdf a.pdf"},

qpdf/qtest/qpdf/obj0-check.out

@@ -0,0 +1,7 @@
+checking obj0.pdf
+PDF Version: 1.3
+File is not encrypted
+File is not linearized
+WARNING: obj0.pdf: file is damaged
+WARNING: obj0.pdf (object 1 0, file position 77): expected n n obj
+WARNING: obj0.pdf: Attempting to reconstruct cross-reference table