Eliminate flattenScalarReferences

3 files changed, 113 insertions, 160 deletions

diff --git a/libqpdf/QPDF.cc b/libqpdf/QPDF.cc
index 777fb837..fac79796 100644
--- a/libqpdf/QPDF.cc
+++ b/libqpdf/QPDF.cc
@@ -1860,28 +1860,6 @@ QPDF::swapObjects(int objid1, int generation1, int objid2, int generation2)
     this->obj_cache[og2] = t;
 }
 
-void
-QPDF::trimTrailerForWrite()
-{
-    // Note that removing the encryption dictionary does not interfere
-    // with reading encrypted files.  QPDF loads all the information
-    // it needs from the encryption dictionary at the beginning and
-    // never looks at it again.
-    this->trailer.removeKey("/ID");
-    this->trailer.removeKey("/Encrypt");
-    this->trailer.removeKey("/Prev");
-
-    // Remove all trailer keys that potentially come from a
-    // cross-reference stream
-    this->trailer.removeKey("/Index");
-    this->trailer.removeKey("/W");
-    this->trailer.removeKey("/Length");
-    this->trailer.removeKey("/Filter");
-    this->trailer.removeKey("/DecodeParms");
-    this->trailer.removeKey("/Type");
-    this->trailer.removeKey("/XRefStm");
-}
-
 std::string
 QPDF::getFilename() const
 {
@@ -2067,20 +2045,3 @@ QPDF::pipeStreamData(int objid, int generation,
     }
     pipeline->finish();
 }
-
-void
-QPDF::decodeStreams()
-{
-    for (std::map<ObjGen, QPDFXRefEntry>::iterator iter =
-	     this->xref_table.begin();
-	 iter != this->xref_table.end(); ++iter)
-    {
-	ObjGen const& og = (*iter).first;
-	QPDFObjectHandle obj = getObjectByID(og.obj, og.gen);
-	if (obj.isStream())
-	{
-	    Pl_Discard pl;
-	    obj.pipeStreamData(&pl, true, false, false);
-	}
-    }
-}
diff --git a/libqpdf/QPDFWriter.cc b/libqpdf/QPDFWriter.cc
index c1e4e1dd..05b5a9a9 100644
--- a/libqpdf/QPDFWriter.cc
+++ b/libqpdf/QPDFWriter.cc
@@ -834,16 +834,6 @@ QPDFWriter::enqueueObject(QPDFObjectHandle object)
 	{
 	    // This is a place-holder object for an object stream
 	}
-	else if (object.isScalar())
-	{
-	    // flattenScalarReferences is supposed to have removed all
-	    // indirect scalars.
-	    throw std::logic_error(
-		"INTERNAL ERROR: QPDFWriter::enqueueObject: indirect scalar: " +
-		std::string(this->filename) + " " +
-		QUtil::int_to_string(object.getObjectID()) + " " +
-		QUtil::int_to_string(object.getGeneration()));
-	}
 	int objid = object.getObjectID();
 
 	if (obj_renumber.count(objid) == 0)
@@ -916,15 +906,6 @@ QPDFWriter::unparseChild(QPDFObjectHandle child, int level, int flags)
     }
     if (child.isIndirect())
     {
-	if (child.isScalar())
-	{
-	    // flattenScalarReferences is supposed to have removed all
-	    // indirect scalars.
-	    throw std::logic_error(
-		"INTERNAL ERROR: QPDFWriter::unparseChild: indirect scalar: " +
-		QUtil::int_to_string(child.getObjectID()) + " " +
-		QUtil::int_to_string(child.getGeneration()));
-	}
 	int old_id = child.getObjectID();
 	int new_id = obj_renumber[old_id];
 	writeString(QUtil::int_to_string(new_id));
@@ -1648,6 +1629,117 @@ QPDFWriter::generateObjectStreams()
 }
 
 void
+QPDFWriter::prepareFileForWrite()
+{
+    // Remove keys from the trailer that necessarily have to be
+    // replaced when writing the file.
+
+    QPDFObjectHandle trailer = pdf.getTrailer();
+
+    // Note that removing the encryption dictionary does not interfere
+    // with reading encrypted files.  QPDF loads all the information
+    // it needs from the encryption dictionary at the beginning and
+    // never looks at it again.
+    trailer.removeKey("/ID");
+    trailer.removeKey("/Encrypt");
+    trailer.removeKey("/Prev");
+
+    // Remove all trailer keys that potentially come from a
+    // cross-reference stream
+    trailer.removeKey("/Index");
+    trailer.removeKey("/W");
+    trailer.removeKey("/Length");
+    trailer.removeKey("/Filter");
+    trailer.removeKey("/DecodeParms");
+    trailer.removeKey("/Type");
+    trailer.removeKey("/XRefStm");
+
+    // Do a traversal of the entire PDF file structure replacing all
+    // indirect objects that QPDFWriter wants to be direct.  This
+    // includes stream lengths, stream filtering parameters, and
+    // document extension level information.  Also replace all
+    // indirect null references with direct nulls.  This way, the only
+    // indirect nulls queued for output will be object stream place
+    // holders.
+
+    std::list<QPDFObjectHandle> queue;
+    queue.push_back(pdf.getTrailer());
+    std::set<int> visited;
+
+    while (! queue.empty())
+    {
+	QPDFObjectHandle node = queue.front();
+	queue.pop_front();
+	if (node.isIndirect())
+	{
+	    if (visited.count(node.getObjectID()) > 0)
+	    {
+		continue;
+	    }
+	    visited.insert(node.getObjectID());
+	}
+
+	if (node.isArray())
+	{
+	    int nitems = node.getArrayNItems();
+	    for (int i = 0; i < nitems; ++i)
+	    {
+		QPDFObjectHandle oh = node.getArrayItem(i);
+                if (oh.isIndirect() && oh.isNull())
+                {
+                    QTC::TC("qpdf", "QPDFWriter flatten array null");
+                    oh.makeDirect();
+                    node.setArrayItem(i, oh);
+                }
+		else if (! oh.isScalar())
+		{
+		    queue.push_back(oh);
+		}
+	    }
+	}
+	else if (node.isDictionary() || node.isStream())
+	{
+            bool is_stream = false;
+	    QPDFObjectHandle dict = node;
+	    if (node.isStream())
+	    {
+                is_stream = true;
+		dict = node.getDict();
+	    }
+
+	    std::set<std::string> keys = dict.getKeys();
+	    for (std::set<std::string>::iterator iter = keys.begin();
+		 iter != keys.end(); ++iter)
+	    {
+		std::string const& key = *iter;
+		QPDFObjectHandle oh = dict.getKey(key);
+                bool add_to_queue = true;
+                if (oh.isIndirect())
+                {
+                    if (is_stream)
+                    {
+                        if ((key == "/Length") ||
+                            (key == "/Filter") ||
+                            (key == "/DecodeParms"))
+                        {
+                            QTC::TC("qpdf", "QPDF make stream key direct");
+                            add_to_queue = false;
+                            oh.makeDirect();
+                            dict.replaceKey(key, oh);
+                        }
+                    }
+                }
+
+                if (add_to_queue)
+                {
+                    queue.push_back(oh);
+		}
+	    }
+	}
+    }
+}
+
+void
 QPDFWriter::write()
 {
     // Do preliminary setup
@@ -1785,8 +1877,7 @@ QPDFWriter::write()
 
     generateID();
 
-    pdf.trimTrailerForWrite();
-    pdf.flattenScalarReferences();
+    prepareFileForWrite();
 
     if (this->linearized)
     {
diff --git a/libqpdf/QPDF_optimization.cc b/libqpdf/QPDF_optimization.cc
index 67f147f3..f832a883 100644
--- a/libqpdf/QPDF_optimization.cc
+++ b/libqpdf/QPDF_optimization.cc
@@ -59,103 +59,6 @@ QPDF::ObjUser::operator<(ObjUser const& rhs) const
 }
 
 void
-QPDF::flattenScalarReferences()
-{
-    // Do a traversal of the entire PDF file structure replacing all
-    // indirect objects that are not arrays, streams, or dictionaries
-    // with direct objects.
-
-    std::list<QPDFObjectHandle> queue;
-    queue.push_back(this->trailer);
-    std::set<ObjGen> visited;
-
-    // Add every object in the xref table to the queue.  This ensures
-    // that we flatten scalar references in unreferenced objects.
-    // This becomes important if we are preserving object streams in a
-    // file that has unreferenced objects in its object streams.  (See
-    // QPDF bug 2974522 at SourceForge.)
-    for (std::map<ObjGen, QPDFXRefEntry>::iterator iter =
-	     this->xref_table.begin();
-	 iter != this->xref_table.end(); ++iter)
-    {
-	ObjGen const& og = (*iter).first;
-	queue.push_back(getObjectByID(og.obj, og.gen));
-    }
-
-    while (! queue.empty())
-    {
-	QPDFObjectHandle node = queue.front();
-	queue.pop_front();
-	if (node.isIndirect())
-	{
-	    ObjGen og(node.getObjectID(), node.getGeneration());
-	    if (visited.count(og) > 0)
-	    {
-		continue;
-	    }
-	    visited.insert(og);
-	}
-
-	if (node.isArray())
-	{
-	    int nitems = node.getArrayNItems();
-	    for (int i = 0; i < nitems; ++i)
-	    {
-		QPDFObjectHandle oh = node.getArrayItem(i);
-		if (oh.isScalar())
-		{
-		    if (oh.isIndirect())
-		    {
-			QTC::TC("qpdf", "QPDF opt flatten array scalar");
-			oh.makeDirect();
-			node.setArrayItem(i, oh);
-		    }
-		}
-		else
-		{
-		    queue.push_back(oh);
-		}
-	    }
-	}
-	else if (node.isDictionary() || node.isStream())
-	{
-	    QPDFObjectHandle dict = node;
-	    if (node.isStream())
-	    {
-		dict = node.getDict();
-	    }
-	    std::set<std::string> keys = dict.getKeys();
-	    for (std::set<std::string>::iterator iter = keys.begin();
-		 iter != keys.end(); ++iter)
-	    {
-		std::string const& key = *iter;
-		QPDFObjectHandle oh = dict.getKey(key);
-		if (oh.isNull())
-		{
-		    // QPDF_Dictionary.getKeys() never returns null
-		    // keys.
-		    throw std::logic_error(
-			"INTERNAL ERROR: dictionary with null key found");
-		}
-		else if (oh.isScalar())
-		{
-		    if (oh.isIndirect())
-		    {
-			QTC::TC("qpdf", "QPDF opt flatten dict scalar");
-			oh.makeDirect();
-			dict.replaceKey(key, oh);
-		    }
-		}
-		else
-		{
-		    queue.push_back(oh);
-		}
-	    }
-	}
-    }
-}
-
-void
 QPDF::optimize(std::map<int, int> const& object_stream_data,
 	       bool allow_changes)
 {
@@ -304,9 +207,7 @@ QPDF::pushInheritedAttributesToPageInternal(
 		    }
 		    else
 		    {
-			// Don't defeat flattenScalarReferences which
-			// would have already been called by this
-			// time.
+			// It's okay to copy scalars.
 			QTC::TC("qpdf", "QPDF opt inherited scalar");
 		    }
 		}