Refactor QPDFPageObjectHelper::removeUnreferencedResources()

Refactor removeUnreferencedResources to prepare for filtering form
XObjects.

ChangeLog

@@ -1,5 +1,9 @@
 2020-03-31  Jay Berkenbilt  <[email protected]>
 
+	* Add QPDFObjectHandle::filterAsContents, which filters a stream's
+	data as if it were page contents. This can be useful to filter
+	form XObjects the same way we would filter page contents.
+
 	* If QPDF_EXECUTABLE is set, use it as the path to qpdf for
 	purposes of completion. This variable is only read during the
 	executation of `qpdf --completion-zsh` and `qpdf

include/qpdf/QPDFObjectHandle.hh

@@ -400,6 +400,12 @@ class QPDFObjectHandle
     void addContentTokenFilter(PointerHolder<TokenFilter> token_filter);
     // End legacy content stream helpers
 
+    // Called on a stream to filter the stream as if it were page
+    // contents. This can be used to apply a TokenFilter to a form
+    // XObject, whose data is in the same format as a content stream.
+    QPDF_DLL
+    void filterAsContents(TokenFilter* filter, Pipeline* next = 0);
+
     // Type-specific factories
     QPDF_DLL
     static QPDFObjectHandle newNull();

include/qpdf/QPDFPageObjectHelper.hh

@@ -28,6 +28,7 @@
 #include <qpdf/DLL.h>
 
 #include <qpdf/QPDFObjectHandle.hh>
+#include <functional>
 
 class QPDFPageObjectHelper: public QPDFObjectHelper
 {
@@ -231,6 +232,12 @@ class QPDFPageObjectHelper: public QPDFObjectHelper
         bool invert_transformations = true);
 
   private:
+    static void
+    removeUnreferencedResourcesHelper(
+        QPDFObjectHandle oh, std::set<QPDFObjGen>& seen,
+        std::function<QPDFObjectHandle()> get_resource,
+        std::function<void(QPDFObjectHandle::TokenFilter*)> filter_content);
+
     class Members
     {
         friend class QPDFPageObjectHelper;

libqpdf/QPDFObjectHandle.cc

@@ -1629,6 +1629,16 @@ QPDFObjectHandle::filterPageContents(TokenFilter* filter, Pipeline* next)
     this->pipePageContents(&token_pipeline);
 }
 
+void
+QPDFObjectHandle::filterAsContents(TokenFilter* filter, Pipeline* next)
+{
+    std::string description = "token filter for object " +
+        QUtil::int_to_string(this->m->objid) + " " +
+        QUtil::int_to_string(this->m->generation);
+    Pl_QPDFTokenizer token_pipeline(description.c_str(), filter, next);
+    this->pipeStreamData(&token_pipeline, 0, qpdf_dl_specialized);
+}
+
 void
 QPDFObjectHandle::parseContentStream(QPDFObjectHandle stream_or_array,
                                      ParserCallbacks* callbacks)

libqpdf/QPDFPageObjectHelper.cc

@@ -511,24 +511,32 @@ NameWatcher::handleToken(QPDFTokenizer::Token const& token)
 }
 
 void
-QPDFPageObjectHelper::removeUnreferencedResources()
+QPDFPageObjectHelper::removeUnreferencedResourcesHelper(
+    QPDFObjectHandle oh, std::set<QPDFObjGen>& seen,
+    std::function<QPDFObjectHandle()> get_resource,
+    std::function<void(QPDFObjectHandle::TokenFilter*)> filter_content)
 {
+    if (seen.count(oh.getObjGen()))
+    {
+        return;
+    }
+    seen.insert(oh.getObjGen());
     NameWatcher nw;
     try
     {
-        filterPageContents(&nw);
+        filter_content(&nw);
     }
     catch (std::exception& e)
     {
-        this->oh.warnIfPossible(
+        oh.warnIfPossible(
             std::string("Unable to parse content stream: ") + e.what() +
             "; not attempting to remove unreferenced objects from this page");
         return;
     }
     if (nw.saw_bad)
     {
         QTC::TC("qpdf", "QPDFPageObjectHelper bad token finding names");
-        this->oh.warnIfPossible(
+        oh.warnIfPossible(
             "Bad token found while scanning content stream; "
             "not attempting to remove unreferenced objects from this page");
         return;
@@ -541,7 +549,7 @@ QPDFPageObjectHelper::removeUnreferencedResources()
     std::vector<std::string> to_filter;
     to_filter.push_back("/Font");
     to_filter.push_back("/XObject");
-    QPDFObjectHandle resources = getAttribute("/Resources", true);
+    QPDFObjectHandle resources = get_resource();
     for (std::vector<std::string>::iterator d_iter = to_filter.begin();
          d_iter != to_filter.end(); ++d_iter)
     {
@@ -564,6 +572,18 @@ QPDFPageObjectHelper::removeUnreferencedResources()
     }
 }
 
+void
+QPDFPageObjectHelper::removeUnreferencedResources()
+{
+    std::set<QPDFObjGen> seen;
+    removeUnreferencedResourcesHelper(
+        this->oh, seen,
+        [this]() { return this->getAttribute("/Resources", true); },
+        [this](QPDFObjectHandle::TokenFilter* f) {
+            this->filterPageContents(f);
+        });
+}
+
 QPDFPageObjectHelper
 QPDFPageObjectHelper::shallowCopyPage()
 {