Add --remove-page-labels option (fixes #317)

5 files changed, 43 insertions, 4 deletions

diff --git a/ChangeLog b/ChangeLog
index 944d80b4..6ab197fc 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,12 @@
 2019-04-20  Jay Berkenbilt  <ejb@ql.org>
 
+	* Add parameter --remove-page-labels to remove page labels from
+	output. In qpdf 8.3.0, the behavior changed so that page labels
+	were preserved when merging and splitting files. Some users were
+	relying on the fact that if you ran qpdf --empty --pages ... all
+	page labels were dropped. This option makes it possible to get
+	that behavior if it is explicitly desired. Fixes #317.
+
 	* Add parameter --keep-files-open-threshold to override the
 	maximum number of files that qpdf will allow to be kept open at
 	once. Fixes #288.
diff --git a/manual/qpdf-manual.xml b/manual/qpdf-manual.xml
index 669fd42e..dac5f00d 100644
--- a/manual/qpdf-manual.xml
+++ b/manual/qpdf-manual.xml
@@ -1797,9 +1797,6 @@ outfile.pdf</option>
        </para>
       </listitem>
      </varlistentry>
-
-
-
      <varlistentry>
       <term><option>--externalize-inline-images</option></term>
       <listitem>
@@ -1835,6 +1832,14 @@ outfile.pdf</option>
       </listitem>
      </varlistentry>
      <varlistentry>
+      <term><option>--remove-page-labels</option></term>
+      <listitem>
+       <para>
+        Remove page labels from the output file.
+       </para>
+      </listitem>
+     </varlistentry>
+     <varlistentry>
       <term><option>--qdf</option></term>
       <listitem>
        <para>
diff --git a/qpdf/qpdf.cc b/qpdf/qpdf.cc
index 3d80abac..495816c3 100644
--- a/qpdf/qpdf.cc
+++ b/qpdf/qpdf.cc
@@ -164,6 +164,7 @@ struct Options
         optimize_images(false),
         externalize_inline_images(false),
         keep_inline_images(false),
+        remove_page_labels(false),
         oi_min_width(128),      // Default values for these
         oi_min_height(128),     // oi flags are in --help
         oi_min_area(16384),     // and in the manual.
@@ -261,6 +262,7 @@ struct Options
     bool optimize_images;
     bool externalize_inline_images;
     bool keep_inline_images;
+    bool remove_page_labels;
     size_t oi_min_width;
     size_t oi_min_height;
     size_t oi_min_area;
@@ -670,6 +672,7 @@ class ArgParser
     void argOptimizeImages();
     void argExternalizeInlineImages();
     void argKeepInlineImages();
+    void argRemovePageLabels();
     void argOiMinWidth(char* parameter);
     void argOiMinHeight(char* parameter);
     void argOiMinArea(char* parameter);
@@ -911,6 +914,7 @@ ArgParser::initOptionTable()
     (*t)["externalize-inline-images"] =
         oe_bare(&ArgParser::argExternalizeInlineImages);
     (*t)["keep-inline-images"] = oe_bare(&ArgParser::argKeepInlineImages);
+    (*t)["remove-page-labels"] = oe_bare(&ArgParser::argRemovePageLabels);
     (*t)["oi-min-width"] = oe_requiredParameter(
         &ArgParser::argOiMinWidth, "minimum-width");
     (*t)["oi-min-height"] = oe_requiredParameter(
@@ -1335,6 +1339,7 @@ ArgParser::argHelp()
         << "--ii-min-bytes=bytes      specify minimum size of inline images to be\n"
         << "                          converted to regular images\n"
         << "--keep-inline-images      exclude inline images from image optimization\n"
+        << "--remove-page-labels      remove any page labels present in the output file\n"
         << "--qdf                     turns on \"QDF mode\" (below)\n"
         << "--linearize-pass1=file    write intermediate pass of linearized file\n"
         << "                          for debugging\n"
@@ -2013,6 +2018,12 @@ ArgParser::argKeepInlineImages()
 }
 
 void
+ArgParser::argRemovePageLabels()
+{
+    o.remove_page_labels = true;
+}
+
+void
 ArgParser::argOiMinWidth(char* parameter)
 {
     o.oi_min_width = QUtil::string_to_int(parameter);
@@ -4335,6 +4346,10 @@ static void handle_transformations(QPDF& pdf, Options& o)
             (*iter).coalesceContentStreams();
         }
     }
+    if (o.remove_page_labels)
+    {
+        pdf.getRoot().removeKey("/PageLabels");
+    }
 }
 
 static void handle_page_specs(QPDF& pdf, Options& o)
diff --git a/qpdf/qtest/qpdf.test b/qpdf/qtest/qpdf.test
index d01ac3af..6ee0ecfe 100644
--- a/qpdf/qtest/qpdf.test
+++ b/qpdf/qtest/qpdf.test
@@ -1877,7 +1877,7 @@ foreach my $f (qw(page_api_2 direct-pages))
 show_ntests();
 # ----------
 $td->notify("--- Merging and Splitting ---");
-$n_tests += 22;
+$n_tests += 24;
 
 # Select pages from the same file multiple times including selecting
 # twice from an encrypted file and specifying the password only the
@@ -1944,6 +1944,18 @@ $td->runtest("merge with multiple labels",
 $td->runtest("check output",
              {$td->FILE => "a.pdf"},
              {$td->FILE => "merge-multiple-labels.pdf"});
+$td->runtest("remove labels",
+             {$td->COMMAND =>
+                  "qpdf --empty a.pdf" .
+                  " --remove-page-labels" .
+                  " --pages 11-pages-with-labels.pdf 8-11" .
+                  " minimal.pdf " .
+                  " page-labels-and-outlines.pdf 17-19 --" .
+                  " --static-id"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "remove-labels.pdf"});
 
 $td->runtest("split with shared resources",
              {$td->COMMAND =>
diff --git a/qpdf/qtest/qpdf/remove-labels.pdf b/qpdf/qtest/qpdf/remove-labels.pdf
new file mode 100644
index 00000000..838f4cbb
--- /dev/null
+++ b/qpdf/qtest/qpdf/remove-labels.pdf