Add QPDFObjectHandle::setFilterOnWrite

Jay Berkenbilt
1 parent 3f9191a3
Showing 11 changed files with 131 additions and 5 deletions
ChangeLog
include/qpdf/QPDFObjectHandle.hh
libqpdf/QPDFObjectHandle.cc
libqpdf/QPDFWriter.cc
libqpdf/QPDF_Stream.cc
libqpdf/qpdf/QPDF_Stream.hh
qpdf/qpdf.testcov
qpdf/qtest/qpdf.test
qpdf/qtest/qpdf/filter-on-write-out.pdf
qpdf/qtest/qpdf/filter-on-write.pdf
qpdf/test_driver.cc
 2020-12-26  Jay Berkenbilt  <ejb@ql.org>
+	* Add QPDFObjectHandle::setFilterOnWrite, which can be used to
+	tell QPDFWriter not to filter a stream on output even if it can.
+	You can use this to prevent QPDFWriter from touching a stream
+	(either uncompressing or compressing) that you have optimized or
+	otherwise ensured looks exactly the way you want it, even if
+	decode level or stream compression would otherwise cause
+	QPDFWriter to modify the stream.
+
 	* Add ostream << for QPDFObjGen. (Don't ask why it took 7.5 years
 	for me to decide to do this.)
@@ -786,6 +786,22 @@ class QPDFObjectHandle
     QPDF_DLL
     QPDFObjectHandle getDict();
+    // By default, or if true passed, QPDFWriter will attempt to
+    // filter a stream based on decode level, whether compression is
+    // enabled, and its ability to filter. Passing false will prevent
+    // QPDFWriter from attempting to filter the stream even if it can.
+    // This includes both decoding and compressing. This makes it
+    // possible for you to prevent QPDFWriter from uncompressing and
+    // recompressing a stream that it knows how to operate on for any
+    // application-specific reason, such as that you have already
+    // optimized its filtering. Note that this doesn't affect any
+    // other ways to get the stream's data, such as pipeStreamData or
+    // getStreamData.
+    QPDF_DLL
+    void setFilterOnWrite(bool);
+    QPDF_DLL
+    bool getFilterOnWrite();
+
     // If addTokenFilter has been called for this stream, then the
     // original data should be considered to be modified. This means we
     // should avoid optimizations such as not filtering a stream that
@@ -1176,6 +1176,20 @@ QPDFObjectHandle::getDict()
     return dynamic_cast<QPDF_Stream*>(obj.getPointer())->getDict();
 }
+void
+QPDFObjectHandle::setFilterOnWrite(bool val)
+{
+    assertStream();
+    dynamic_cast<QPDF_Stream*>(obj.getPointer())->setFilterOnWrite(val);
+}
+
+bool
+QPDFObjectHandle::getFilterOnWrite()
+{
+    assertStream();
+    return dynamic_cast<QPDF_Stream*>(obj.getPointer())->getFilterOnWrite();
+}
+
 bool
 QPDFObjectHandle::isDataModified()
 {
@@ -1470,6 +1470,7 @@ QPDFWriter::willFilterStream(QPDFObjectHandle stream,
 {
     compress_stream = false;
     is_metadata = false;
+
     QPDFObjGen old_og = stream.getObjGen();
     QPDFObjectHandle stream_dict = stream.getDict();
@@ -1481,7 +1482,13 @@ QPDFWriter::willFilterStream(QPDFObjectHandle stream,
     bool filter = (stream.isDataModified() ||
                    this->m->compress_streams ||
                    this->m->stream_decode_level);
-    if (this->m->compress_streams)
+    bool filter_on_write = stream.getFilterOnWrite();
+    if (! filter_on_write)
+    {
+        QTC::TC("qpdf", "QPDFWriter getFilterOnWrite false");
+        filter = false;
+    }
+    if (filter_on_write && this->m->compress_streams)
     {
         // Don't filter if the stream is already compressed with
         // FlateDecode. This way we don't make it worse if the
@@ -1502,7 +1509,7 @@ QPDFWriter::willFilterStream(QPDFObjectHandle stream,
     }
     bool normalize = false;
     bool uncompress = false;
-    if (is_metadata &&
+    if (filter_on_write && is_metadata &&
         ((! this->m->encrypted) || (this->m->encrypt_metadata == false)))
     {
         QTC::TC("qpdf", "QPDFWriter not compressing metadata");
@@ -1510,13 +1517,13 @@ QPDFWriter::willFilterStream(QPDFObjectHandle stream,
         compress_stream = false;
         uncompress = true;
     }
-    else if (this->m->normalize_content &&
+    else if (filter_on_write && this->m->normalize_content &&
              this->m->normalized_streams.count(old_og))
     {
         normalize = true;
         filter = true;
     }
-    else if (filter && this->m->compress_streams)
+    else if (filter_on_write && filter && this->m->compress_streams)
     {
         compress_stream = true;
         QTC::TC("qpdf", "QPDFWriter compressing uncompressed stream");
@@ -90,6 +90,7 @@ QPDF_Stream::QPDF_Stream(QPDF* qpdf, int objid, int generation,
     qpdf(qpdf),
     objid(objid),
     generation(generation),
+    filter_on_write(true),
     stream_dict(stream_dict),
     offset(offset),
     length(length)
@@ -116,6 +117,18 @@ QPDF_Stream::registerStreamFilter(
 }
 void
+QPDF_Stream::setFilterOnWrite(bool val)
+{
+    this->filter_on_write = val;
+}
+
+bool
+QPDF_Stream::getFilterOnWrite() const
+{
+    return this->filter_on_write;
+}
+
+void
 QPDF_Stream::releaseResolved()
 {
     this->stream_provider = 0;
@@ -27,6 +27,8 @@ class QPDF_Stream: public QPDFObject
     virtual void setDescription(QPDF*, std::string const&);
     QPDFObjectHandle getDict() const;
     bool isDataModified() const;
+    void setFilterOnWrite(bool);
+    bool getFilterOnWrite() const;
     // Methods to help QPDF copy foreign streams
     qpdf_offset_t getOffset() const;
@@ -83,6 +85,7 @@ class QPDF_Stream: public QPDFObject
     QPDF* qpdf;
     int objid;
     int generation;
+    bool filter_on_write;
     QPDFObjectHandle stream_dict;
     qpdf_offset_t offset;
     size_t length;
@@ -520,3 +520,4 @@ qpdf-c called qpdf_oh_get_generation 0
 qpdf-c called qpdf_oh_unparse 0
 qpdf-c called qpdf_oh_unparse_resolved 0
 qpdf-c called qpdf_oh_unparse_binary 0
+QPDFWriter getFilterOnWrite false 0
@@ -1181,6 +1181,19 @@ $td-&gt;runtest(&quot;check output&quot;,
 show_ntests();
 # ----------
+$td->notify("--- Disable filter on write ---");
+$n_tests += 2;
+
+$td->runtest("no filter on write",
+	     {$td->COMMAND => "test_driver 70 filter-on-write.pdf"},
+	     {$td->STRING => "test 70 done\n", $td->EXIT_STATUS => 0},
+	     $td->NORMALIZE_NEWLINES);
+$td->runtest("check output",
+	     {$td->FILE => "a.pdf"},
+	     {$td->FILE => "filter-on-write-out.pdf"});
+
+show_ntests();
+# ----------
 $td->notify("--- Invalid objects ---");
 $n_tests += 2;
@@ -1197,7 +1210,7 @@ $td-&gt;runtest(&quot;object with zero offset&quot;,
 show_ntests();
 # ----------
-$td->notify("--- Error/output rediction ---");
+$td->notify("--- Error/output redirection ---");
 $n_tests += 2;
 $td->runtest("error/output redirection to null",
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Pages 2 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 0 /Kids [ ] /Type /Pages >>
+endobj
+3 0 obj
+<< /Filter /RunLengthDecode /Length 5 >>
+stream
+w¹w€endstream
+endobj
+4 0 obj
+<< /Length 6 >>
+stream
+potatoendstream
+endobj
+5 0 obj
+<< /Filter /RunLengthDecode /Length 5 >>
+stream
+w¹w€endstream
+endobj
+6 0 obj
+<< /Length 5 >>
+stream
+saladendstream
+endobj
+xref
+0 7
+0000000000 65535 f 
+0000000015 00000 n 
+0000000064 00000 n 
+0000000117 00000 n 
+0000000195 00000 n 
+0000000249 00000 n 
+0000000327 00000 n 
+trailer << /Root 1 0 R /Size 7 /ID [<5ab7a0329a828e2f46377e16247bc367><5ab7a0329a828e2f46377e16247bc367>] /S1 3 0 R /S2 4 0 R /S3 5 0 R /S4 6 0 R >>
+startxref
+380
+%%EOF
@@ -2219,6 +2219,16 @@ void runtest(int n, char const* filename1, char const* arg2)
             w.write();
         }
     }
+    else if (n == 70)
+    {
+        auto trailer = pdf.getTrailer();
+        trailer.getKey("/S1").setFilterOnWrite(false);
+        trailer.getKey("/S2").setFilterOnWrite(false);
+        QPDFWriter w(pdf, "a.pdf");
+        w.setStaticID(true);
+        w.setDecodeLevel(qpdf_dl_specialized);
+        w.write();
+    }
     else
     {
 	throw std::runtime_error(std::string("invalid test ") +