When splitting files, remove unreferenced objects (fixes #203)

2 files changed, 19 insertions, 0 deletions

diff --git a/include/qpdf/QPDFPageDocumentHelper.hh b/include/qpdf/QPDFPageDocumentHelper.hh
index d7d4a026..5847e078 100644
--- a/include/qpdf/QPDFPageDocumentHelper.hh
+++ b/include/qpdf/QPDFPageDocumentHelper.hh
@@ -52,6 +52,12 @@ class QPDFPageDocumentHelper: public QPDFDocumentHelper
     QPDF_DLL
     void pushInheritedAttributesToPage();
 
+    // This calls QPDFPageObjectHelper::removeUnreferencedResources
+    // for every page in the document. See comments in
+    // QPDFPageObjectHelper.hh for details.
+    QPDF_DLL
+    void removeUnreferencedResources();
+
     // Add new page at the beginning or the end of the current pdf.
     // The newpage parameter may be either a direct object, an
     // indirect object from this QPDF, or an indirect object from
diff --git a/include/qpdf/QPDFPageObjectHelper.hh b/include/qpdf/QPDFPageObjectHelper.hh
index 9226a748..570e81b4 100644
--- a/include/qpdf/QPDFPageObjectHelper.hh
+++ b/include/qpdf/QPDFPageObjectHelper.hh
@@ -122,6 +122,19 @@ class QPDFPageObjectHelper: public QPDFObjectHelper
     void addContentTokenFilter(
         PointerHolder<QPDFObjectHandle::TokenFilter> token_filter);
 
+    // A page's resources dictionary maps names to objects elsewhere
+    // in the file. This method walks through a page's contents and
+    // keeps tracks of which resources are referenced somewhere in the
+    // contents. Then it removes from the resources dictionary any
+    // object that is not referenced in the contents. This operation
+    // is most useful after calling
+    // QPDFPageDocumentHelper::pushInheritedAttributesToPage(). This
+    // method is used by page splitting code to avoid copying unused
+    // objects in files that used shared resource dictionaries across
+    // multiple pages.
+    QPDF_DLL
+    void removeUnreferencedResources();
+
   private:
     class Members
     {