Merge pull request #1617 from m-holger/i1403

Add `--remove-acroform` option to exclude AcroForm dictionary

Merge pull request #1617 from m-holger/i1403
Add `--remove-acroform` option to exclude AcroForm dictionary
m-holger · GitHub
2 parents 96e3677c f3109f67
Showing 15 changed files with 2512 additions and 21 deletions
include/qpdf/auto_job_c_main.hh
job.sums
job.yml
libqpdf/QPDFJob.cc
libqpdf/QPDFJob_config.cc
libqpdf/qpdf/QPDFJob_private.hh
libqpdf/qpdf/auto_job_help.hh
libqpdf/qpdf/auto_job_init.hh
libqpdf/qpdf/auto_job_json_init.hh
libqpdf/qpdf/auto_job_schema.hh
manual/cli.rst
manual/qpdf.1
manual/release-notes.rst
qpdf/qtest/interactive-form.test
qpdf/qtest/qpdf/remove-acroform-out.pdf
@@ -32,6 +32,7 @@ QPDF_DLL Config* progress();
 QPDF_DLL Config* qdf();
 QPDF_DLL Config* rawStreamData();
 QPDF_DLL Config* recompressFlate();
+QPDF_DLL Config* removeAcroform();
 QPDF_DLL Config* removeInfo();
 QPDF_DLL Config* removeMetadata();
 QPDF_DLL Config* removePageLabels();
@@ -5,17 +5,17 @@ include/qpdf/auto_job_c_att.hh 4c2b171ea00531db54720bf49a43f8b34481586ae7fb6cbf2
 include/qpdf/auto_job_c_copy_att.hh 50609012bff14fd82f0649185940d617d05d530cdc522185c7f3920a561ccb42
 include/qpdf/auto_job_c_enc.hh 28446f3c32153a52afa239ea40503e6cc8ac2c026813526a349e0cd4ae17ddd5
 include/qpdf/auto_job_c_global.hh 7df0ff87d18d7fa6d57437960377509420b6b6eb9527b534996f86d3bd7a0ddc
-include/qpdf/auto_job_c_main.hh b865eb827356554763bb8349eadfcbc5cb260f80e025a5e229467c525007356d
+include/qpdf/auto_job_c_main.hh 7a7cc311e194b778ea7568ece2335c00c9bdd8162431c264af2f6105548efc5f
 include/qpdf/auto_job_c_pages.hh 09ca15649cc94fdaf6d9bdae28a20723f2a66616bf15aa86d83df31051d82506
 include/qpdf/auto_job_c_uo.hh 9c2f98a355858dd54d0bba444b73177a59c9e56833e02fa6406f429c07f39e62
-job.yml fa98c8444c8a22a89aeeb76670aa5919aa7a86ebfac2eb45018602fbc7e45b79
+job.yml 442ef5e7fb8027a0f3cd4816b614d59abb327b359e861d87426b706db142d2bc
 libqpdf/qpdf/auto_job_decl.hh d612a02839e4f20a80e1c6a3ba09c17187fccddc3581ec7ebb1e3919ffd6801d
-libqpdf/qpdf/auto_job_help.hh 7503b1083c952ace12976857c8ece4e1af67788af9f827fb4248bd22329f93cd
-libqpdf/qpdf/auto_job_init.hh 10a697528d4cae1ac566ee7612f62e611190b3c10c0021862a77fa7e4f330570
+libqpdf/qpdf/auto_job_help.hh 43d0c1f4477949d1a4facc6984e9e341758201f4884e8d0d82ffc8dd795b2d38
+libqpdf/qpdf/auto_job_init.hh 2bb9d1524817e7150da55790ba0ac5ed8042ff4ff9688d70a927ee95903849a4
 libqpdf/qpdf/auto_job_json_decl.hh 7dbb83ddadcea39bfd1faa4ca061e1e3c3134d693b8ae634b463e7e19dc8bd0a
-libqpdf/qpdf/auto_job_json_init.hh e9cacbcb78ca250a962c226a935067ef9b76f5485bae7e5302eea0a1a8e2ff65
-libqpdf/qpdf/auto_job_schema.hh 2b974a436c5b4d03fb38258d6213f993cfa9f673834cebe754b4c7ad657481c9
+libqpdf/qpdf/auto_job_json_init.hh 33934c23235c760a1fc1375c74f4fd52c8f5accf655c510fa3dd9a2be293b61d
+libqpdf/qpdf/auto_job_schema.hh 81b8d57f05f5125a722912b6ee5e10fc6b02ae68e040108b75f32fc6527c02b1
 manual/_ext/qpdf.py 6add6321666031d55ed4aedf7c00e5662bba856dfcd66ccb526563bffefbb580
-manual/cli.rst be2b9366e953fce743c115db00eeedc7894e547a9222133395e929f535fa9836
-manual/qpdf.1 c1d6e58e37aed1b8d434b37edd1837b7261c9933b09d64bf3915dc3f35d6cccb
+manual/cli.rst efbce4b34fefbe1f46fca9c9693af245a7f7e2b63c0853c464569087aa49cb18
+manual/qpdf.1 0567419e4f6a2b8facd03b9febaf65a384dd68e0e327fc058e77c21121a6cf17
 manual/qpdf.1.in 436ecc85d45c4c9e2dbd1725fb7f0177fb627179469f114561adf3cb6cbb677b
@@ -145,6 +145,7 @@ options:
       - qdf
       - raw-stream-data
       - recompress-flate
+      - remove-acroform
       - remove-info
       - remove-metadata
       - remove-page-labels
@@ -468,6 +469,7 @@ json:
     - Pages.file:
       Pages.password:
       range:
+  remove-acroform:
   remove-info:
   remove-metadata:
   remove-page-labels:
@@ -438,6 +438,9 @@ QPDFJob::createQPDF()
     m->warnings |= m->inputs.clear();
  
     auto root = pdf.getRoot();
+    if (m->remove_acroform) {
+        root.erase("/AcroForm");
+    }
     if (m->remove_info) {
         auto trailer = pdf.getTrailer();
         auto mod_date = trailer["/Info"]["/ModDate"];
@@ -563,6 +563,13 @@ QPDFJob::Config::removeAttachment(std::string const&amp; parameter)
 }
  
 QPDFJob::Config*
+QPDFJob::Config::removeAcroform()
+{
+    o.m->remove_acroform = true;
+    return this;
+}
+
+QPDFJob::Config*
 QPDFJob::Config::removeInfo()
 {
     o.m->remove_info = true;
@@ -250,6 +250,7 @@ class QPDFJob::Members
     bool optimize_images{false};
     bool externalize_inline_images{false};
     bool keep_inline_images{false};
+    bool remove_acroform{false};
     bool remove_info{false};
     bool remove_metadata{false};
     bool remove_page_labels{false};
@@ -430,6 +430,11 @@ ap.addOptionHelp(&quot;--keep-inline-images&quot;, &quot;modification&quot;, &quot;exclude inline images 
 }
 static void add_help_5(QPDFArgParser& ap)
 {
+ap.addOptionHelp("--remove-acroform", "modification", "remove the interactive form dictionary", R"(Exclude the interactive form dictionary from the output file. This
+option only removes the interactive form dictionary from the
+document catalog. It does not remove form field dictionaries or
+widget annotations. See the manual for more detail.
+)");
 ap.addOptionHelp("--remove-info", "modification", "remove file information", R"(Exclude file information (except modification date) from the output file.
 )");
 ap.addOptionHelp("--remove-metadata", "modification", "remove metadata", R"(Exclude metadata from the output file.
@@ -642,6 +647,9 @@ ap.addOptionHelp(&quot;--cleartext-metadata&quot;, &quot;encryption&quot;, &quot;don&#39;t encrypt metadata&quot;,
 encrypting the rest of the document. This option is not
 available with 40-bit encryption.
 )");
+}
+static void add_help_6(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--use-aes", "encryption", "use AES with 128-bit encryption", R"(--use-aes=[y|n]
  
 Enables/disables use of the more secure AES encryption with
@@ -650,9 +658,6 @@ version to be at least 1.6. This option is only available with
 128-bit encryption. The default is "n" for compatibility
 reasons. Use 256-bit encryption instead.
 )");
-}
-static void add_help_6(QPDFArgParser& ap)
-{
 ap.addOptionHelp("--allow-insecure", "encryption", "allow empty owner passwords", R"(Allow creation of PDF files with empty owner passwords and
 non-empty user passwords when using 256-bit encryption.
 )");
@@ -828,14 +833,14 @@ Specify the attachment&#39;s modification date in PDF format;
 defaults to the current time. Run qpdf --help=pdf-dates for
 information about the date format.
 )");
+}
+static void add_help_7(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--mimetype", "add-attachment", "attachment mime type, e.g. application/pdf", R"(--mimetype=type/subtype
  
 Specify the mime type for the attachment, such as text/plain,
 application/pdf, image/png, etc.
 )");
-}
-static void add_help_7(QPDFArgParser& ap)
-{
 ap.addOptionHelp("--description", "add-attachment", "set attachment's description", R"(--description="text"
  
 Supply descriptive text for the attachment, displayed by some
@@ -924,12 +929,12 @@ Useful for scripts.
 ap.addOptionHelp("--show-pages", "inspection", "display page dictionary information", R"(Show the object and generation number for each page dictionary
 object and for each content stream associated with the page.
 )");
-ap.addOptionHelp("--with-images", "inspection", "include image details with --show-pages", R"(When used with --show-pages, also shows the object and
-generation numbers for the image objects on each page.
-)");
 }
 static void add_help_8(QPDFArgParser& ap)
 {
+ap.addOptionHelp("--with-images", "inspection", "include image details with --show-pages", R"(When used with --show-pages, also shows the object and
+generation numbers for the image objects on each page.
+)");
 ap.addOptionHelp("--list-attachments", "inspection", "list embedded files", R"(Show the key and stream number for each embedded file. Combine
 with --verbose for more detailed information.
 )");
@@ -1033,6 +1038,9 @@ parsing. The limit applies when the PDF document&#39;s xref table is undamaged
 and the object itself can be parsed without errors. The default limit
 is 4,294,967,295. See also --parser-max-container-size-damaged.
 )");
+}
+static void add_help_9(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--parser-max-container-size-damaged", "global", "set the maximum container size while parsing damaged files", R"(--parser-max-container-size-damaged=n
  
 Set the maximum number of top-level objects allowed in a container while
@@ -1041,9 +1049,6 @@ or the object itself is damaged. The limit also applies when parsing
 xref streams. The default limit is 5,000.
 See also --parser-max-container-size.
 )");
-}
-static void add_help_9(QPDFArgParser& ap)
-{
 ap.addOptionHelp("--max-stream-filters", "global", "set the maximum number of filters allowed when filtering streams", R"(--max-stream-filters=n
  
 An excessive number of stream filters is usually a sign that a file
@@ -77,6 +77,7 @@ this-&gt;ap.addBare(&quot;progress&quot;, [this](){c_main-&gt;progress();});
 this->ap.addBare("qdf", [this](){c_main->qdf();});
 this->ap.addBare("raw-stream-data", [this](){c_main->rawStreamData();});
 this->ap.addBare("recompress-flate", [this](){c_main->recompressFlate();});
+this->ap.addBare("remove-acroform", [this](){c_main->removeAcroform();});
 this->ap.addBare("remove-info", [this](){c_main->removeInfo();});
 this->ap.addBare("remove-metadata", [this](){c_main->removeMetadata();});
 this->ap.addBare("remove-page-labels", [this](){c_main->removePageLabels();});
@@ -436,6 +436,9 @@ addParameter([this](std::string const&amp; p) { c_pages-&gt;range(p); });
 popHandler(); // key: range
 popHandler(); // array: .pages[]
 popHandler(); // key: pages
+pushKey("removeAcroform");
+addBare([this]() { c_main->removeAcroform(); });
+popHandler(); // key: removeAcroform
 pushKey("removeInfo");
 addBare([this]() { c_main->removeInfo(); });
 popHandler(); // key: removeInfo
@@ -154,6 +154,7 @@ static constexpr char const* JOB_SCHEMA_DATA = R&quot;({
       "range": "page range"
     }
   ],
+  "removeAcroform": "remove the interactive form dictionary",
   "removeInfo": "remove file information",
   "removeMetadata": "remove metadata",
   "removePageLabels": "remove explicit page numbers",
@@ -1641,6 +1641,14 @@ Related Options
    appearances with some limitations. See the
    :qpdf:ref:`--generate-appearances` option for details.
  
+   In some damaged files with interactive form fields the form fields
+   in the document's AcroForm structure may be out-of-sync with the
+   corresponding widget annotations on the page. In this case, some
+   viewers may after flattening show some field values twice with
+   a slight offset. In this situation it may help to remove the
+   AcroForm entry in the document catalog using the
+   :qpdf:ref:`--remove-acroform` option after flattening.
+
 .. qpdf:option:: --rotate=[+|-]angle[:page-range]
  
    .. help: rotate pages
@@ -1810,6 +1818,30 @@ Related Options
    Prevent inline images from being included in image optimization
    done by :qpdf:ref:`--optimize-images`.
  
+.. qpdf:option:: --remove-acroform
+
+   .. help: remove the interactive form dictionary
+
+      Exclude the interactive form dictionary from the output file. This
+      option only removes the interactive form dictionary from the
+      document catalog. It does not remove form field dictionaries or
+      widget annotations. See the manual for more detail.
+
+Exclude the interactive form dictionary from the output file. This
+option only removes the interactive form dictionary from the
+document catalog. It does not remove form field dictionaries or the
+associated widget annotations.
+
+In some damaged files with interactive form fields the form fields
+in the document's AcroForm structure may be out-of-sync with the
+corresponding widget annotations on the page. In this case,
+different viewers may display different field values, and after flattening
+annotations with the :qpdf:ref:`--flatten-annotations` option,
+some viewers may show some field values twice with
+a slight offset. In this situation it may help to remove the
+AcroForm entry in the document catalog using this option. **Users should
+check the output file carefully after using this option**.
+
 .. qpdf:option:: --remove-info
  
    .. help: remove file information
@@ -545,6 +545,12 @@ Don&#39;t optimize images whose area in pixels is below the specified value.
 .B --keep-inline-images \-\- exclude inline images from optimization
 Prevent inline images from being considered by --optimize-images.
 .TP
+.B --remove-acroform \-\- remove the interactive form dictionary
+Exclude the interactive form dictionary from the output file. This
+option only removes the interactive form dictionary from the
+document catalog. It does not remove form field dictionaries or
+widget annotations. See the manual for more detail.
+.TP
 .B --remove-info \-\- remove file information
 Exclude file information (except modification date) from the output file.
 .TP
@@ -98,6 +98,11 @@ more detail.
       into the environment during completion and to correctly handle
       ``bashcompinit`` for zsh users.
  
+    - Add new :qpdf:ref:`--remove-acroform` option to exclude the AcroForm
+      dictionary from the output PDF. This option can be useful particularly
+      when the :qpdf:ref:`--flatten-annotations` option is used on damaged
+      PDF files.
+
   - Other enhancements
  
     - Add new ``inspection mode`` to help with the inspection and manual repair
@@ -26,7 +26,7 @@ my @form_tests = (
     'form-document-defaults',
     );
  
-my $n_tests = scalar(@form_tests) + 6;
+my $n_tests = scalar(@form_tests) + 8;
  
 # Many of the form*.pdf files were created by converting the
 # LibreOffice document storage/form.odt to PDF and then manually
@@ -70,5 +70,13 @@ $td-&gt;runtest(&quot;compare files&quot;,
              {$td->FILE => "a.pdf"},
              {$td->FILE => "button-set-broken-out.pdf"});
  
+$td->runtest("remove-acroform",
+             {$td->COMMAND => "qpdf form-filled-with-atril.pdf --qdf --static-id --remove-acroform a.pdf"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0},
+             $td->NORMALIZE_NEWLINES);
+$td->runtest("compare files",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "remove-acroform-out.pdf"});
+
 cleanup();
 $td->report($n_tests);