QPDFPageObjectHelper::getPageImages: support form XObjects

4 files changed, 73 insertions, 60 deletions

diff --git a/include/qpdf/QPDFPageObjectHelper.hh b/include/qpdf/QPDFPageObjectHelper.hh
index 9f1addd2..e6f9f76d 100644
--- a/include/qpdf/QPDFPageObjectHelper.hh
+++ b/include/qpdf/QPDFPageObjectHelper.hh
@@ -32,6 +32,10 @@
 
 class QPDFPageObjectHelper: public QPDFObjectHelper
 {
+    // This is a helper class for page objects, but as of qpdf 10.1,
+    // many of the methods also work for form XObjects. When this is
+    // the case, it is noted in the comment.
+
   public:
     QPDF_DLL
     QPDFPageObjectHelper(QPDFObjectHandle);
@@ -40,14 +44,15 @@ class QPDFPageObjectHelper: public QPDFObjectHelper
     {
     }
 
-    // Return the effective value of this attribute for the page. If
-    // the requested attribute is not present on the page but is
+    // Works with pages and form XObjects. Return the effective value
+    // of this attribute for the page/form XObject. For pages, if the
+    // requested attribute is not present on the page but is
     // inheritable, look up through the page's ancestors in the page
     // tree. If copy_if_shared is true, then this method will replace
     // the attribute with a shallow copy if it is in indirect or
     // inherited and return the copy. You should do this if you are
     // going to modify the returned object and want the modifications
-    // to apply to the current page only.
+    // to apply to the current page/form XObject only.
     QPDF_DLL
     QPDFObjectHandle
     getAttribute(std::string const& name, bool copy_if_shared);
@@ -70,7 +75,8 @@ class QPDFPageObjectHelper: public QPDFObjectHelper
     // Returns an empty map if there are no images or no resources.
     // Prior to qpdf 8.4.0, this function did not support inherited
     // resources, but it does now. Return value is a map from XObject
-    // name to the image object, which is always a stream.
+    // name to the image object, which is always a stream. Works with
+    // form XObjects as well as pages.
     QPDF_DLL
     std::map<std::string, QPDFObjectHandle> getPageImages();
 
diff --git a/libqpdf/QPDFObjectHandle.cc b/libqpdf/QPDFObjectHandle.cc
index 181793f4..d5d199d9 100644
--- a/libqpdf/QPDFObjectHandle.cc
+++ b/libqpdf/QPDFObjectHandle.cc
@@ -1320,35 +1320,7 @@ QPDFObjectHandle::getGeneration() const
 std::map<std::string, QPDFObjectHandle>
 QPDFObjectHandle::getPageImages()
 {
-    std::map<std::string, QPDFObjectHandle> result;
-    QPDFObjectHandle resources =
-        QPDFPageObjectHelper(*this).getAttribute("/Resources", false);
-    if (resources.isDictionary())
-    {
-	if (resources.hasKey("/XObject"))
-	{
-	    QPDFObjectHandle xobject = resources.getKey("/XObject");
-	    std::set<std::string> keys = xobject.getKeys();
-	    for (std::set<std::string>::iterator iter = keys.begin();
-		 iter != keys.end(); ++iter)
-	    {
-		std::string key = (*iter);
-		QPDFObjectHandle value = xobject.getKey(key);
-		if (value.isStream())
-		{
-		    QPDFObjectHandle dict = value.getDict();
-		    if (dict.hasKey("/Subtype") &&
-			(dict.getKey("/Subtype").getName() == "/Image") &&
-			(! dict.hasKey("/ImageMask")))
-		    {
-			result[key] = value;
-		    }
-		}
-	    }
-	}
-    }
-
-    return result;
+    return QPDFPageObjectHelper(*this).getPageImages();
 }
 
 std::vector<QPDFObjectHandle>
diff --git a/libqpdf/QPDFPageObjectHelper.cc b/libqpdf/QPDFPageObjectHelper.cc
index a80ab641..0e9792a6 100644
--- a/libqpdf/QPDFPageObjectHelper.cc
+++ b/libqpdf/QPDFPageObjectHelper.cc
@@ -314,33 +314,46 @@ QPDFObjectHandle
 QPDFPageObjectHelper::getAttribute(std::string const& name,
                                    bool copy_if_shared)
 {
-    bool inheritable = ((name == "/MediaBox") || (name == "/CropBox") ||
-                        (name == "/Resources") || (name == "/Rotate"));
-
-    QPDFObjectHandle node = this->oh;
-    QPDFObjectHandle result(node.getKey(name));
-    std::set<QPDFObjGen> seen;
+    QPDFObjectHandle result;
+    QPDFObjectHandle dict;
+    bool is_form_xobject = this->oh.isFormXObject();
     bool inherited = false;
-    while (inheritable && result.isNull() && node.hasKey("/Parent"))
+    if (is_form_xobject)
     {
-        seen.insert(node.getObjGen());
-        node = node.getKey("/Parent");
-        if (seen.count(node.getObjGen()))
-        {
-            break;
-        }
+        dict = this->oh.getDict();
+        result = dict.getKey(name);
+    }
+    else
+    {
+        dict = this->oh;
+        bool inheritable = ((name == "/MediaBox") || (name == "/CropBox") ||
+                            (name == "/Resources") || (name == "/Rotate"));
+
+        QPDFObjectHandle node = dict;
         result = node.getKey(name);
-        if (! result.isNull())
+        std::set<QPDFObjGen> seen;
+        while (inheritable && result.isNull() && node.hasKey("/Parent"))
         {
-            QTC::TC("qpdf", "QPDFPageObjectHelper non-trivial inheritance");
-            inherited = true;
+            seen.insert(node.getObjGen());
+            node = node.getKey("/Parent");
+            if (seen.count(node.getObjGen()))
+            {
+                break;
+            }
+            result = node.getKey(name);
+            if (! result.isNull())
+            {
+                QTC::TC("qpdf", "QPDFPageObjectHelper non-trivial inheritance");
+                inherited = true;
+            }
         }
     }
     if (copy_if_shared && (inherited || result.isIndirect()))
     {
-        QTC::TC("qpdf", "QPDFPageObjectHelper copy shared attribute");
+        QTC::TC("qpdf", "QPDFPageObjectHelper copy shared attribute",
+                is_form_xobject ? 0 : 1);
         result = result.shallowCopy();
-        this->oh.replaceKey(name, result);
+        dict.replaceKey(name, result);
     }
     return result;
 }
@@ -376,7 +389,34 @@ QPDFPageObjectHelper::getMediaBox(bool copy_if_shared)
 std::map<std::string, QPDFObjectHandle>
 QPDFPageObjectHelper::getPageImages()
 {
-    return this->oh.getPageImages();
+    std::map<std::string, QPDFObjectHandle> result;
+    QPDFObjectHandle resources = getAttribute("/Resources", false);
+    if (resources.isDictionary())
+    {
+	if (resources.hasKey("/XObject"))
+	{
+	    QPDFObjectHandle xobject = resources.getKey("/XObject");
+	    std::set<std::string> keys = xobject.getKeys();
+	    for (std::set<std::string>::iterator iter = keys.begin();
+		 iter != keys.end(); ++iter)
+	    {
+		std::string key = (*iter);
+		QPDFObjectHandle value = xobject.getKey(key);
+		if (value.isStream())
+		{
+		    QPDFObjectHandle dict = value.getDict();
+		    if (dict.hasKey("/Subtype") &&
+			(dict.getKey("/Subtype").getName() == "/Image") &&
+			(! dict.hasKey("/ImageMask")))
+		    {
+			result[key] = value;
+		    }
+		}
+	    }
+	}
+    }
+
+    return result;
 }
 
 void
@@ -571,13 +611,8 @@ QPDFPageObjectHelper::removeUnreferencedResourcesHelper(
                 removeUnreferencedResourcesHelper(
                     resource.getDict(), seen,
                     [&resource]() {
-                        auto result = resource.getDict().getKey("/Resources");
-                        if (result.isDictionary())
-                        {
-                            result = result.shallowCopy();
-                            resource.getDict().replaceKey("/Resources", result);
-                        }
-                        return result;
+                        return QPDFPageObjectHelper(resource)
+                            .getAttribute("/Resources", true);
                     },
                     [&resource](QPDFObjectHandle::TokenFilter* f) {
                         resource.filterAsContents(f);
diff --git a/qpdf/qpdf.testcov b/qpdf/qpdf.testcov
index 04e3e044..2fddc87c 100644
--- a/qpdf/qpdf.testcov
+++ b/qpdf/qpdf.testcov
@@ -422,7 +422,7 @@ QPDFFormFieldObjectHelper create AP from scratch 0
 QPDFFormFieldObjectHelper replaced BMC at EOF 0
 QPDFFormFieldObjectHelper fallback Tf 0
 QPDFPageObjectHelper non-trivial inheritance 0
-QPDFPageObjectHelper copy shared attribute 0
+QPDFPageObjectHelper copy shared attribute 1
 qpdf from_nr from repeat_nr 0
 QPDF resolve duplicated page object 0
 QPDF handle direct page object 0