Add coalesce contents capability

Jay Berkenbilt
1 parent 25988e8d
Showing 9 changed files with 566 additions and 21 deletions
ChangeLog
include/qpdf/QPDFObjectHandle.hh
libqpdf/QPDFObjectHandle.cc
qpdf/qpdf.cc
qpdf/qpdf.testcov
qpdf/qtest/qpdf.test
qpdf/qtest/qpdf/coalesce-out.pdf
qpdf/qtest/qpdf/coalesce-out.qdf
qpdf/qtest/qpdf/coalesce.pdf
@@ -78,6 +78,35 @@
 	production use. Even if it did, it would be very unusual for a PDF
 	file to actually be adversely affected by this issue.
+	* Add support for coalescing a page's contents into a single
+	stream if they are represented as an array of streams. This can be
+	performed from the command line using the --coalesce-contents
+	option. Coalescing content streams can simplify things for
+	software that wants to operate on a page's content streams without
+	having to handle weird edge cases like content streams split in
+	the middle of tokens. Note that
+	QPDFObjectHandle::parsePageContents and
+	QPDFObjectHandle::parseContentStream already handled split content
+	streams. This is mainly to set the stage for new methods of
+	operating on page contents. The new method
+	QPDFObjectHandle::pipeContentStreams will pipe all of a page's
+	content streams though a single pipeline. The new method
+	QPDFObjectHandle.coalesceContentStreams, when called on a page
+	object, will do nothing if the page's contents are a single
+	stream, but if they are an array of streams, it will replace the
+	page's contents with a single stream whose contents are the
+	concatenation of the original streams.
+
+	* A few library routines throw exceptions if called on non-page
+	objects. These constraints have been relaxed somewhat to make qpdf
+	more tolerant of files whose page dictionaries are not properly
+	marked as such. Mostly exceptions about page operations being
+	called on non page objects will only be thrown in cases where the
+	operation had no chance of succeeding anyway. This change has no
+	impact on any default mode operations, but it could allow
+	applications that use page-level APIs in QPDFObjectHandle to be
+	more tolerant of certain types of damaged files.
+
 2018-02-04  Jay Berkenbilt  <ejb@ql.org>
 	* Add QPDFWriter::setLinearizationPass1Filename method and
@@ -200,6 +200,20 @@ class QPDFObjectHandle
     QPDF_DLL
     void pipePageContents(Pipeline* p);
+    // When called on a stream or stream array that is some page's
+    // content streams, do the same as pipePageContents. This method
+    // is a lower level way to do what pipePageContents does, but it
+    // allows you to perform this operation on a contents object that
+    // is disconnected from a page object. The description argument
+    // should describe the containing page and is used in error
+    // messages. The all_description argument is initialized to
+    // something that could be used to describe the result of the
+    // pipeline. It is the description amended with the identifiers of
+    // the underlying objects.
+    QPDF_DLL
+    void pipeContentStreams(Pipeline* p, std::string const& description,
+                            std::string& all_description);
+
     // Older method: stream_or_array should be the value of /Contents
     // from a page object. It's more convenient to just call
     // parsePageContents on the page object, and error messages will
@@ -556,30 +570,30 @@ class QPDFObjectHandle
     // Convenience routines for commonly performed functions
-    // Throws an exception if this is not a Page object.  Returns an
-    // empty map if there are no images or no resources.  This
-    // function does not presently support inherited resources.  If
-    // this is a significant concern, call
+    // Returns an empty map if there are no images or no resources.
+    // This function does not presently support inherited resources.
+    // If this is a significant concern, call
     // pushInheritedAttributesToPage() on the QPDF object that owns
-    // this page.  See comment in the source for details.  Return
-    // value is a map from XObject name to the image object, which is
-    // always a stream.
+    // this page. See comment in the source for details. Return value
+    // is a map from XObject name to the image object, which is always
+    // a stream.
     QPDF_DLL
     std::map<std::string, QPDFObjectHandle> getPageImages();
     // Returns a vector of stream objects representing the content
     // streams for the given page.  This routine allows the caller to
     // not care whether there are one or more than one content streams
-    // for a page.  Throws an exception if this is not a Page object.
+    // for a page.
     QPDF_DLL
     std::vector<QPDFObjectHandle> getPageContents();
-    // Add the given object as a new content stream for this page.  If
-    // parameter 'first' is true, add to the beginning.  Otherwise,
-    // add to the end.  This routine automatically converts the page
+    // Add the given object as a new content stream for this page. If
+    // parameter 'first' is true, add to the beginning. Otherwise, add
+    // to the end. This routine automatically converts the page
     // contents to an array if it is a scalar, allowing the caller not
-    // to care what the initial structure is.  Throws an exception if
-    // this is not a Page object.
+    // to care what the initial structure is. You can call
+    // coalesceContentStreams() afterwards if you want to force it to
+    // be a single stream.
     QPDF_DLL
     void addPageContents(QPDFObjectHandle contents, bool first);
@@ -590,6 +604,16 @@ class QPDFObjectHandle
     QPDF_DLL
     void rotatePage(int angle, bool relative);
+    // Coalesce a page's content streams. A page's content may be a
+    // stream or an array of streams. If this page's content is an
+    // array, concatenate the streams into a single stream. This can
+    // be useful when working with files that split content streams in
+    // arbitary spots, such as in the middle of a token, as that can
+    // confuse some software. You could also call this after calling
+    // addPageContents.
+    QPDF_DLL
+    void coalesceContentStreams();
+
     // Initializers for objects.  This Factory class gives the QPDF
     // class specific permission to call factory methods without
     // making it a friend of the whole QPDFObjectHandle class.
@@ -724,8 +748,6 @@ class QPDFObjectHandle
         ParserCallbacks* callbacks);
     std::vector<QPDFObjectHandle> arrayOrStreamToStreamArray(
         std::string const& description, std::string& all_description);
-    void pipeContentStreams(Pipeline* p, std::string const& description,
-                            std::string& all_description);
     static void warn(QPDF*, QPDFExc const&);
     bool initialized;
@@ -14,6 +14,7 @@
 #include <qpdf/QPDF_Stream.hh>
 #include <qpdf/QPDF_Reserved.hh>
 #include <qpdf/Pl_Buffer.hh>
+#include <qpdf/Pl_Concatenate.hh>
 #include <qpdf/BufferInputSource.hh>
 #include <qpdf/QPDFExc.hh>
@@ -28,6 +29,39 @@ class TerminateParsing
 {
 };
+class CoalesceProvider: public QPDFObjectHandle::StreamDataProvider
+{
+  public:
+    CoalesceProvider(QPDFObjectHandle containing_page,
+                     QPDFObjectHandle old_contents) :
+        containing_page(containing_page),
+        old_contents(old_contents)
+    {
+    }
+    virtual ~CoalesceProvider()
+    {
+    }
+    virtual void provideStreamData(int objid, int generation,
+                                   Pipeline* pipeline);
+
+  private:
+    QPDFObjectHandle containing_page;
+    QPDFObjectHandle old_contents;
+};
+
+void
+CoalesceProvider::provideStreamData(int, int, Pipeline* p)
+{
+    QTC::TC("qpdf", "QPDFObjectHandle coalesce provide stream data");
+    Pl_Concatenate concat("concatenate", p);
+    std::string description = "page object " +
+        QUtil::int_to_string(containing_page.getObjectID()) + " " +
+        QUtil::int_to_string(containing_page.getGeneration());
+    std::string all_description;
+    old_contents.pipeContentStreams(&concat, description, all_description);
+    concat.manualFinish();
+}
+
 void
 QPDFObjectHandle::ParserCallbacks::terminateParsing()
 {
@@ -691,7 +725,6 @@ QPDFObjectHandle::arrayOrStreamToStreamArray(
 std::vector<QPDFObjectHandle>
 QPDFObjectHandle::getPageContents()
 {
-    assertPageObject();
     std::string description = "page object " +
         QUtil::int_to_string(this->objid) + " " +
         QUtil::int_to_string(this->generation);
@@ -703,7 +736,6 @@ QPDFObjectHandle::getPageContents()
 void
 QPDFObjectHandle::addPageContents(QPDFObjectHandle new_contents, bool first)
 {
-    assertPageObject();
     new_contents.assertStream();
     std::vector<QPDFObjectHandle> orig_contents = getPageContents();
@@ -785,6 +817,33 @@ QPDFObjectHandle::rotatePage(int angle, bool relative)
     replaceKey("/Rotate", QPDFObjectHandle::newInteger(new_angle));
 }
+void
+QPDFObjectHandle::coalesceContentStreams()
+{
+    assertPageObject();
+    QPDFObjectHandle contents = this->getKey("/Contents");
+    if (contents.isStream())
+    {
+        QTC::TC("qpdf", "QPDFObjectHandle coalesce called on stream");
+        return;
+    }
+    QPDF* qpdf = getOwningQPDF();
+    if (qpdf == 0)
+    {
+        // Should not be possible for a page object to not have an
+        // owning PDF unless it was manually constructed in some
+        // incorrect way.
+        throw std::logic_error("coalesceContentStreams called on object"
+                               " with no associated PDF file");
+    }
+    QPDFObjectHandle new_contents = newStream(qpdf);
+    this->replaceKey("/Contents", new_contents);
+
+    PointerHolder<StreamDataProvider> provider =
+        new CoalesceProvider(*this, contents);
+    new_contents.replaceStreamData(provider, newNull(), newNull());
+}
+
 std::string
 QPDFObjectHandle::unparse()
 {
@@ -842,6 +901,7 @@ QPDFObjectHandle::parse(std::string const&amp; object_str,
 void
 QPDFObjectHandle::pipePageContents(Pipeline* p)
 {
+    assertPageObject();
     std::string description = "page object " +
         QUtil::int_to_string(this->objid) + " " +
         QUtil::int_to_string(this->generation);
@@ -879,6 +939,7 @@ QPDFObjectHandle::pipeContentStreams(
 void
 QPDFObjectHandle::parsePageContents(ParserCallbacks* callbacks)
 {
+    assertPageObject();
     std::string description = "page object " +
         QUtil::int_to_string(this->objid) + " " +
         QUtil::int_to_string(this->generation);
@@ -1728,15 +1789,15 @@ QPDFObjectHandle::assertNumber()
 bool
 QPDFObjectHandle::isPageObject()
 {
-    return (this->isDictionary() && this->hasKey("/Type") &&
-            (this->getKey("/Type").getName() == "/Page"));
+    // Some PDF files have /Type broken on pages.
+    return (this->isDictionary() && this->hasKey("/Contents"));
 }
 bool
 QPDFObjectHandle::isPagesObject()
 {
-    return (this->isDictionary() && this->hasKey("/Type") &&
-            (this->getKey("/Type").getName() == "/Pages"));
+    // Some PDF files have /Type broken on pages.
+    return (this->isDictionary() && this->hasKey("/Kids"));
 }
 void
@@ -90,6 +90,7 @@ struct Options
         qdf_mode(false),
         preserve_unreferenced_objects(false),
         newline_before_endstream(false),
+        coalesce_contents(false),
         show_npages(false),
         deterministic_id(false),
         static_id(false),
@@ -154,6 +155,7 @@ struct Options
     bool preserve_unreferenced_objects;
     bool newline_before_endstream;
     std::string linearize_pass1;
+    bool coalesce_contents;
     std::string min_version;
     std::string force_version;
     bool show_npages;
@@ -391,6 +393,7 @@ familiar with the PDF file format or who are PDF developers.\n\
 --object-streams=mode     controls handing of object streams\n\
 --preserve-unreferenced   preserve unreferenced objects\n\
 --newline-before-endstream  always put a newline before endstream\n\
+--coalesce-contents       force all pages' content to be a single stream\n\
 --qdf                     turns on \"QDF mode\" (below)\n\
 --linearize-pass1=file    write intermediate pass of linearized file\n\
                           for debugging\n\
@@ -1543,6 +1546,10 @@ static void parse_options(int argc, char* argv[], Options&amp; o)
                 }
                 o.linearize_pass1 = parameter;
             }
+            else if (strcmp(arg, "coalesce-contents") == 0)
+            {
+                o.coalesce_contents = true;
+            }
             else if (strcmp(arg, "min-version") == 0)
             {
                 if (parameter == 0)
@@ -1960,6 +1967,19 @@ static void do_inspection(QPDF&amp; pdf, Options&amp; o)
     }
 }
+static void handle_transformations(QPDF& pdf, Options& o)
+{
+    if (o.coalesce_contents)
+    {
+        std::vector<QPDFObjectHandle> pages = pdf.getAllPages();
+        for (std::vector<QPDFObjectHandle>::iterator iter = pages.begin();
+             iter != pages.end(); ++iter)
+        {
+            (*iter).coalesceContentStreams();
+        }
+    }
+}
+
 static void handle_page_specs(QPDF& pdf, Options& o,
                               std::vector<PointerHolder<QPDF> >& page_heap)
 {
@@ -2382,6 +2402,7 @@ int main(int argc, char* argv[])
             pdf.processFile(o.infilename, o.password);
         }
+        handle_transformations(pdf, o);
         std::vector<PointerHolder<QPDF> > page_heap;
         if (! o.page_specs.empty())
         {
@@ -304,3 +304,5 @@ QPDFTokenizer EOF when not allowed 0
 QPDFTokenizer inline image at EOF 0
 Pl_QPDFTokenizer found ID 0
 QPDFObjectHandle non-stream in stream array 0
+QPDFObjectHandle coalesce called on stream 0
+QPDFObjectHandle coalesce provide stream data 0
@@ -736,6 +736,28 @@ $td-&gt;runtest(&quot;stream with tiff predictor&quot;,
 show_ntests();
 # ----------
+$td->notify("--- Coalesce contents ---");
+$n_tests += 4;
+
+$td->runtest("coalesce contents with qdf",
+             {$td->COMMAND =>
+                  "qpdf --qdf --static-id" .
+                  " --coalesce-contents coalesce.pdf a.pdf"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "coalesce-out.qdf"});
+$td->runtest("coalesce contents without qdf",
+             {$td->COMMAND =>
+                  "qpdf --static-id" .
+                  " --coalesce-contents coalesce.pdf a.pdf"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "coalesce-out.pdf"});
+
+show_ntests();
+# ----------
 $td->notify("--- Newline before endstream ---");
 $n_tests += 10;