Test for direct, rather than resolved nulls in parser

Just because we know an indirect reference is null, doesn't mean we shouldn't keep it indirect.

Test for direct, rather than resolved nulls in parser
Just because we know an indirect reference is null, doesn't mean we shouldn't keep it indirect.
Jay Berkenbilt
1 parent 3f3dbe22
Showing 8 changed files with 259 additions and 10 deletions
ChangeLog
include/qpdf/QPDFObjectHandle.hh
libqpdf/QPDFObjectHandle.cc
libqpdf/SparseOHArray.cc
qpdf/qtest/qpdf.test
qpdf/qtest/qpdf/good21.out
qpdf/qtest/qpdf/good21.pdf
qpdf/qtest/qpdf/good21.qdf
 2019-08-22  Jay Berkenbilt  <ejb@ql.org>
+	* Add QPDFObjectHandle::isDirectNull() -- a const method that
+	allows determining whether an object is a literal null without
+	attempting to resolve it.
+
 	* Stop replacing indirect references to null with literal null in
 	arrays when writing output with QPDFWriter.
@@ -281,13 +281,12 @@ class QPDFObjectHandle
     QPDF_DLL
     bool isReserved();
-    // True for objects that are direct nulls or have previously been
-    // resolved to be nulls. Does not attempt to resolve objects. This
-    // is intended for internal use, but it can be used as an
-    // efficient way to check for nulls if you don't mind unresolved
-    // indirect nulls being false negatives.
+    // True for objects that are direct nulls. Does not attempt to
+    // resolve objects. This is intended for internal use, but it can
+    // be used as an efficient way to check for nulls that are not
+    // indirect objects.
     QPDF_DLL
-    bool isResolvedNull() const;
+    bool isDirectNull() const;
     // This returns true in addition to the query for the specific
     // type for indirect objects.
@@ -263,9 +263,10 @@ QPDFObjectHandle::isBool()
 }
 bool
-QPDFObjectHandle::isResolvedNull() const
+QPDFObjectHandle::isDirectNull() const
 {
-    return QPDFObjectTypeAccessor<QPDF_Null>::check(m->obj.getPointer());
+    return (this->m->initialized && (this->m->objid == 0) &&
+            QPDFObjectTypeAccessor<QPDF_Null>::check(m->obj.getPointer()));
 }
 bool
@@ -15,7 +15,7 @@ SparseOHArray::size() const
 void
 SparseOHArray::append(QPDFObjectHandle oh)
 {
-    if (! oh.isResolvedNull())
+    if (! oh.isDirectNull())
     {
         this->elements[this->n_elements] = oh;
     }
@@ -73,7 +73,7 @@ SparseOHArray::setAt(size_t idx, QPDFObjectHandle oh)
     {
 	throw std::logic_error("bounds error setting item in SparseOHArray");
     }
-    if (oh.isResolvedNull())
+    if (oh.isDirectNull())
     {
         this->elements.erase(idx);
     }
@@ -2456,6 +2456,7 @@ my @goodfiles = (&quot;implicit null&quot;,			# 1
 		 "hybrid xref old mode",		# 18
 		 "xref with prev",			# 19
 		 "lots of compressible objects",	# 20
+                 "array with indirect nulls",           # 21
 		 );
 $n_tests += (3 * @goodfiles) + 6;
+/QTest is indirect and has type array (8)
+/QTest is an array with 6 items
+  item 0 is direct
+  item 1 is direct
+  item 2 is direct
+  item 3 is indirect
+  item 4 is direct
+  item 5 is indirect
+unparse: 9 0 R
+unparseResolved: [ /literal null /indirect 8 0 R /undefined 10 0 R ]
+test 1 done
+%PDF-1.3
+%¿÷¢þ
+%QDF-1.0
+
+1 0 obj
+<<
+  /Pages 2 0 R
+  /Type /Catalog
+>>
+endobj
+
+2 0 obj
+<<
+  /Count 1
+  /Kids [
+    3 0 R
+  ]
+  /Type /Pages
+>>
+endobj
+
+%% Page 1
+3 0 obj
+<<
+  /Contents 4 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 6 0 R
+    >>
+    /ProcSet 7 0 R
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Contents for page 1
+4 0 obj
+<<
+  /Length 5 0 R
+>>
+stream
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Potato) Tj
+ET
+endstream
+endobj
+
+5 0 obj
+44
+endobj
+
+6 0 obj
+<<
+  /BaseFont /Helvetica
+  /Encoding /WinAnsiEncoding
+  /Name /F1
+  /Subtype /Type1
+  /Type /Font
+>>
+endobj
+
+7 0 obj
+[
+  /PDF
+  /Text
+]
+endobj
+
+8 0 obj
+null
+endobj
+
+9 0 obj
+[ /literal null /indirect 8 0 R /undefined 10 0 R ]
+endobj
+
+xref
+0 10
+0000000000 65535 f 
+0000000025 00000 n 
+0000000079 00000 n 
+0000000161 00000 n 
+0000000376 00000 n 
+0000000475 00000 n 
+0000000494 00000 n 
+0000000612 00000 n 
+0000000647 00000 n 
+0000000668 00000 n 
+trailer <<
+  /Root 1 0 R
+  /Size 10
+  /QTest 9 0 R
+  /ID [<06c2c8fc54c5f9cc9246898e1e1a7146><06c2c8fc54c5f9cc9246898e1e1a7146>]
+>>
+startxref
+736
+%%EOF
+%PDF-1.3
+%¿÷¢þ
+%QDF-1.0
+
+%% Original object ID: 1 0
+1 0 obj
+<<
+  /Pages 3 0 R
+  /Type /Catalog
+>>
+endobj
+
+%% Original object ID: 9 0
+2 0 obj
+[
+  /literal
+  null
+  /indirect
+  4 0 R
+  /undefined
+  5 0 R
+]
+endobj
+
+%% Original object ID: 2 0
+3 0 obj
+<<
+  /Count 1
+  /Kids [
+    6 0 R
+  ]
+  /Type /Pages
+>>
+endobj
+
+%% Original object ID: 8 0
+4 0 obj
+null
+endobj
+
+%% Original object ID: 10 0
+5 0 obj
+null
+endobj
+
+%% Page 1
+%% Original object ID: 3 0
+6 0 obj
+<<
+  /Contents 7 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 3 0 R
+  /Resources <<
+    /Font <<
+      /F1 9 0 R
+    >>
+    /ProcSet 10 0 R
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Contents for page 1
+%% Original object ID: 4 0
+7 0 obj
+<<
+  /Length 8 0 R
+>>
+stream
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Potato) Tj
+ET
+endstream
+endobj
+
+8 0 obj
+44
+endobj
+
+%% Original object ID: 6 0
+9 0 obj
+<<
+  /BaseFont /Helvetica
+  /Encoding /WinAnsiEncoding
+  /Name /F1
+  /Subtype /Type1
+  /Type /Font
+>>
+endobj
+
+%% Original object ID: 7 0
+10 0 obj
+[
+  /PDF
+  /Text
+]
+endobj
+
+xref
+0 11
+0000000000 65535 f 
+0000000052 00000 n 
+0000000133 00000 n 
+0000000239 00000 n 
+0000000338 00000 n 
+0000000387 00000 n 
+0000000445 00000 n 
+0000000688 00000 n 
+0000000787 00000 n 
+0000000833 00000 n 
+0000000978 00000 n 
+trailer <<
+  /QTest 2 0 R
+  /Root 1 0 R
+  /Size 11
+  /ID [<06c2c8fc54c5f9cc9246898e1e1a7146><31415926535897932384626433832795>]
+>>
+startxref
+1014
+%%EOF