Add new CLI option --remove-structure

... to remove the /Root /StructTreeRoot and /MarkInfo entries.

Add new CLI option --remove-structure
... to remove the /Root /StructTreeRoot and /MarkInfo entries.
m-holger
1 parent 314bd3eb
Showing 16 changed files with 293 additions and 21 deletions
include/qpdf/QPDFJob.hh
include/qpdf/auto_job_c_main.hh
job.sums
job.yml
libqpdf/QPDFJob.cc
libqpdf/QPDFJob_config.cc
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/merge-and-split.test
qpdf/qtest/qpdf/remove-structure.out.pdf
qpdf/qtest/qpdf/remove-structure.pdf
@@ -696,6 +696,7 @@ class QPDFJob
         bool remove_info{false};
         bool remove_metadata{false};
         bool remove_page_labels{false};
+        bool remove_structure{false};
         size_t oi_min_width{DEFAULT_OI_MIN_WIDTH};
         size_t oi_min_height{DEFAULT_OI_MIN_HEIGHT};
         size_t oi_min_area{DEFAULT_OI_MIN_AREA};
@@ -35,6 +35,7 @@ QPDF_DLL Config* recompressFlate();
 QPDF_DLL Config* removeInfo();
 QPDF_DLL Config* removeMetadata();
 QPDF_DLL Config* removePageLabels();
+QPDF_DLL Config* removeStructure();
 QPDF_DLL Config* reportMemoryUsage();
 QPDF_DLL Config* requiresPassword();
 QPDF_DLL Config* removeRestrictions();
@@ -4,17 +4,17 @@ generate_auto_job f64733b79dcee5a0e3e8ccc6976448e8ddf0e8b6529987a66a7d3ab2ebc10a
 include/qpdf/auto_job_c_att.hh 4c2b171ea00531db54720bf49a43f8b34481586ae7fb6cbf225099ee42bc5bb4
 include/qpdf/auto_job_c_copy_att.hh 50609012bff14fd82f0649185940d617d05d530cdc522185c7f3920a561ccb42
 include/qpdf/auto_job_c_enc.hh 28446f3c32153a52afa239ea40503e6cc8ac2c026813526a349e0cd4ae17ddd5
-include/qpdf/auto_job_c_main.hh 84f463237235b2c095b747a4f5dd00f109ee596a1c207b944efb296c0c568cae
+include/qpdf/auto_job_c_main.hh 48e8ea475e8a8f4c96de86bdad10dff83a263deccc3798c8bed7f5e0e070a037
 include/qpdf/auto_job_c_pages.hh 09ca15649cc94fdaf6d9bdae28a20723f2a66616bf15aa86d83df31051d82506
 include/qpdf/auto_job_c_uo.hh 9c2f98a355858dd54d0bba444b73177a59c9e56833e02fa6406f429c07f39e62
-job.yml 2c424c7be0c02545191969e849e1d8f7fdb4ab65bbf799b9a190e21343899751
+job.yml ba9f24920c2221883b1d6d8e42f7ac7c78988063a0ca9181dc08abe9cde6f760
 libqpdf/qpdf/auto_job_decl.hh 34ba07d3891c3e5cdd8712f991e508a0652c9db314c5d5bcdf4421b76e6f6e01
-libqpdf/qpdf/auto_job_help.hh a36476d0c823033b2af0e4170651e1fa31173887c310f2f208e9ed7e6e36a2ce
-libqpdf/qpdf/auto_job_init.hh f89e7f9950a185372732d2ff7f113161f275f45ee7937dd7fd37e38013bf22e7
+libqpdf/qpdf/auto_job_help.hh 03bdaab05f84b16bfb15ad7993a4655b7dc14af070fa97fe3035943726d4b258
+libqpdf/qpdf/auto_job_init.hh 029d929f930f60b4055796c8c4ce2ed625f861316ac738ab638579eca46b2472
 libqpdf/qpdf/auto_job_json_decl.hh 843892c8e8652a86b7eb573893ef24050b7f36fe313f7251874be5cd4cdbe3fd
-libqpdf/qpdf/auto_job_json_init.hh 344c2fb473f88fe829c93b1efe6c70a0e4796537b8eb35e421d955fff481ba7d
-libqpdf/qpdf/auto_job_schema.hh 6d3eef5137b8828eaa301a1b3cf75cb7bb812aa6e2d8301de865b42d238d7a7c
+libqpdf/qpdf/auto_job_json_init.hh b883f3768c8367327ea1f17e8ca503178be62a9cede316bf7ad96c0fafee5513
+libqpdf/qpdf/auto_job_schema.hh 6d28db327dd19e0a7da375c681ecea7965513fa4b5d2349a80089b057f8c02d8
 manual/_ext/qpdf.py 6add6321666031d55ed4aedf7c00e5662bba856dfcd66ccb526563bffefbb580
-manual/cli.rst 67357688f9a52fafa9a4f231fe4ce74c3cd8977130da7501efe54439a1ee22d4
-manual/qpdf.1 dbcc567623f1fa080743ae9bc32b6264a3b6bd3074c81c438e52ca328e94ecd7
+manual/cli.rst 1094662a10db21528fd151739a9779a4504ebac75b483a11a53d42ab0430ee42
+manual/qpdf.1 eb45321c598f23f0724cb963a17aef972ef5b817dc44cf787882a4621c6e1c8e
 manual/qpdf.1.in 436ecc85d45c4c9e2dbd1725fb7f0177fb627179469f114561adf3cb6cbb677b
@@ -134,6 +134,7 @@ options:
       - remove-info
       - remove-metadata
       - remove-page-labels
+      - remove-structure
       - replace-input
       - report-memory-usage
       - requires-password
@@ -446,6 +447,7 @@ json:
   remove-info:
   remove-metadata:
   remove-page-labels:
+  remove-structure:
   report-memory-usage:
   rotate:
   set-page-labels:
@@ -490,6 +490,10 @@ QPDFJob::createQPDF()
     if (m->remove_metadata) {
         pdf.getRoot().removeKey("/Metadata");
     }
+    if (m->remove_structure) {
+        pdf.getRoot().removeKey("/StructTreeRoot");
+        pdf.getRoot().removeKey("/MarkInfo");
+    }
     for (auto& foreign: page_heap) {
         if (foreign->anyWarnings()) {
@@ -532,6 +532,13 @@ QPDFJob::Config::removePageLabels()
 }
 QPDFJob::Config*
+QPDFJob::Config::removeStructure()
+{
+    o.m->remove_structure = true;
+    return this;
+}
+
+QPDFJob::Config*
 QPDFJob::Config::reportMemoryUsage()
 {
     o.m->report_mem_usage = true;
@@ -428,6 +428,8 @@ ap.addOptionHelp(&quot;--remove-metadata&quot;, &quot;modification&quot;, &quot;remove metadata&quot;, R&quot;(Excl
 )");
 ap.addOptionHelp("--remove-page-labels", "modification", "remove explicit page numbers", R"(Exclude page labels (explicit page numbers) from the output file.
 )");
+ap.addOptionHelp("--remove-structure", "modification", "remove metadata", R"(Exclude the structure tree from the output file.
+)");
 ap.addOptionHelp("--set-page-labels", "modification", "number pages for the entire document", R"(--set-page-labels label-spec ... --
 Set page labels (explicit page numbers) for the entire file.
@@ -643,12 +645,12 @@ reasons. Use 256-bit encryption instead.
 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.
 )");
-ap.addOptionHelp("--force-V4", "encryption", "force V=4 in encryption dictionary", R"(This option is for testing and is never needed in practice since
-qpdf does this automatically when needed.
-)");
 }
 static void add_help_6(QPDFArgParser& ap)
 {
+ap.addOptionHelp("--force-V4", "encryption", "force V=4 in encryption dictionary", R"(This option is for testing and is never needed in practice since
+qpdf does this automatically when needed.
+)");
 ap.addOptionHelp("--force-R5", "encryption", "use unsupported R=5 encryption", R"(Use an undocumented, unsupported, deprecated encryption
 algorithm that existed only in Acrobat version IX. This option
 should not be used except for compatibility testing.
@@ -828,13 +830,13 @@ ap.addOptionHelp(&quot;--description&quot;, &quot;add-attachment&quot;, &quot;set attachment&#39;s descriptio
 Supply descriptive text for the attachment, displayed by some
 PDF viewers.
 )");
+}
+static void add_help_7(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--replace", "add-attachment", "replace attachment with same key", R"(Indicate that any existing attachment with the same key should
 be replaced by the new attachment. Otherwise, qpdf gives an
 error if an attachment with that key is already present.
 )");
-}
-static void add_help_7(QPDFArgParser& ap)
-{
 ap.addHelpTopic("copy-attachments", "copy attachments from another file", R"(The options listed below appear between --copy-attachments-from and
 its terminating "--".
@@ -920,14 +922,14 @@ 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.
 )");
+}
+static void add_help_8(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--show-attachment", "inspection", "export an embedded file", R"(--show-attachment=key
 Write the contents of the specified attachment to standard
 output as binary data. Get the key with --list-attachments.
 )");
-}
-static void add_help_8(QPDFArgParser& ap)
-{
 ap.addHelpTopic("json", "JSON output for PDF information", R"(Show information about the PDF file in JSON format. Please see the
 JSON chapter in the qpdf manual for details.
 )");
@@ -72,6 +72,7 @@ this-&gt;ap.addBare(&quot;recompress-flate&quot;, [this](){c_main-&gt;recompressFlate();});
 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();});
+this->ap.addBare("remove-structure", [this](){c_main->removeStructure();});
 this->ap.addBare("replace-input", b(&ArgParser::argReplaceInput));
 this->ap.addBare("report-memory-usage", [this](){c_main->reportMemoryUsage();});
 this->ap.addBare("requires-password", [this](){c_main->requiresPassword();});
@@ -421,6 +421,9 @@ popHandler(); // key: removeMetadata
 pushKey("removePageLabels");
 addBare([this]() { c_main->removePageLabels(); });
 popHandler(); // key: removePageLabels
+pushKey("removeStructure");
+addBare([this]() { c_main->removeStructure(); });
+popHandler(); // key: removeStructure
 pushKey("reportMemoryUsage");
 addBare([this]() { c_main->reportMemoryUsage(); });
 popHandler(); // key: reportMemoryUsage
@@ -148,6 +148,7 @@ static constexpr char const* JOB_SCHEMA_DATA = R&quot;({
   "removeInfo": "remove file information",
   "removeMetadata": "remove metadata",
   "removePageLabels": "remove explicit page numbers",
+  "removeStructure": "remove metadata",
   "reportMemoryUsage": "best effort report of memory usage",
   "rotate": "rotate pages",
   "setPageLabels": [
@@ -1799,7 +1799,7 @@ Related Options
    Exclude file information (except modification date) from the output file by
    omitting all entries (except ``/ModDate``) from the ``/Info`` dictionary in
    the document trailer.
-   See also :qpdf:ref:`--remove-metadata`.
+   See also :qpdf:ref:`--remove-metadata`, :qpdf:ref:`--remove-structure`.
 .. qpdf:option:: --remove-metadata
@@ -1809,7 +1809,7 @@ Related Options
    Exclude metadata from the output file by omitting the ``/Metadata``
    dictionary in the document catalog.
-   See also :qpdf:ref:`--remove-info`.
+   See also :qpdf:ref:`--remove-info`, :qpdf:ref:`--remove-structure`.
 .. qpdf:option:: --remove-page-labels
@@ -1821,6 +1821,19 @@ Related Options
    omitting the ``/PageLabels`` dictionary in the document catalog.
    See also :qpdf:ref:`--set-page-labels`.
+.. qpdf:option:: --remove-structure
+
+   .. help: remove metadata
+
+      Exclude the structure tree from the output file.
+
+   Exclude the structure tree from the output file by omitting the
+   ``/StructTreeRoot`` and ``/MarkInfo`` dictionaries in the document
+   catalog.
+   See also :qpdf:ref:`--remove-info`, :qpdf:ref:`--remove-metadata`.
+
+
+
 .. qpdf:option:: --set-page-labels label-spec ... --
    .. help: number pages for the entire document
@@ -545,6 +545,9 @@ Exclude metadata from the output file.
 .B --remove-page-labels \-\- remove explicit page numbers
 Exclude page labels (explicit page numbers) from the output file.
 .TP
+.B --remove-structure \-\- remove metadata
+Exclude the structure tree from the output file.
+.TP
 .B --set-page-labels \-\- number pages for the entire document
 --set-page-labels label-spec ... --
@@ -13,7 +13,7 @@ more detail.
 .. x.y.z: not yet released
-12.0.1: not yet released
+12.1.0: not yet released
   - Bug fixes
     - In ``QPDF::isLinearized`` return false if the first object in the file is
@@ -29,6 +29,11 @@ more detail.
     - Fix two object stream error/warning messages that reported the wrong
       object id.
+  - CLI Enhancements
+
+    - New :qpdf:ref:`--remove-structure` option to exclude the document
+      structure tree from the output PDF.
+
   - Other enhancements
     - There have been further enhancements to how files with damaged xref
@@ -14,7 +14,7 @@ cleanup();
 my $td = new TestDriver('merge-and-split');
-my $n_tests = 34;
+my $n_tests = 36;
 # Select pages from the same file multiple times including selecting
 # twice from an encrypted file and specifying the password only the
@@ -136,6 +136,15 @@ $td-&gt;runtest(&quot;check output&quot;,
              {$td->FILE => "a.pdf"},
              {$td->FILE => "remove-info-no-moddate.pdf"});
+$td->runtest("remove structure tree",
+             {$td->COMMAND =>
+                  "qpdf remove-structure.pdf a.pdf" .
+                  " --qdf --remove-structure --static-id"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "remove-structure.out.pdf"});
+
 $td->runtest("split with shared resources",
              {$td->COMMAND =>
                   "qpdf --qdf --static-id" .
+%PDF-1.3
+%¿÷¢þ
+%QDF-1.0
+
+%% Original object ID: 1 0
+1 0 obj
+<<
+  /Pages 2 0 R
+  /Type /Catalog
+>>
+endobj
+
+%% Original object ID: 3 0
+2 0 obj
+<<
+  /Count 1
+  /Kids [
+    3 0 R
+  ]
+  /Type /Pages
+>>
+endobj
+
+%% Page 1
+%% Original object ID: 5 0
+3 0 obj
+<<
+  /Contents 4 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 6 0 R
+    >>
+    /ProcSet 7 0 R
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Contents for page 1
+%% Original object ID: 6 0
+4 0 obj
+<<
+  /Length 5 0 R
+>>
+stream
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Potato) Tj
+ET
+endstream
+endobj
+
+5 0 obj
+44
+endobj
+
+%% Original object ID: 8 0
+6 0 obj
+<<
+  /BaseFont /Helvetica
+  /Encoding /WinAnsiEncoding
+  /Name /F1
+  /Subtype /Type1
+  /Type /Font
+>>
+endobj
+
+%% Original object ID: 9 0
+7 0 obj
+[
+  /PDF
+  /Text
+]
+endobj
+
+xref
+0 8
+0000000000 65535 f 
+0000000052 00000 n 
+0000000133 00000 n 
+0000000242 00000 n 
+0000000484 00000 n 
+0000000583 00000 n 
+0000000629 00000 n 
+0000000774 00000 n 
+trailer <<
+  /Root 1 0 R
+  /Size 8
+  /ID [<e8147af54e2f4232c87179e90799f037><31415926535897932384626433832795>]
+>>
+startxref
+809
+%%EOF
+%PDF-1.3
+%¿÷¢þ
+%QDF-1.0
+
+%% Original object ID: 1 0
+1 0 obj
+<<
+  /MarkInfo 2 0 R
+  /Pages 3 0 R
+  /StructTreeRoot 4 0 R
+  /Type /Catalog
+>>
+endobj
+
+%% Original object ID: 8 0
+2 0 obj
+<<
+  /Marked /False
+>>
+endobj
+
+%% Original object ID: 2 0
+3 0 obj
+<<
+  /Count 1
+  /Kids [
+    5 0 R
+  ]
+  /Type /Pages
+>>
+endobj
+
+%% Original object ID: 7 0
+4 0 obj
+<<
+  /Type /StructTreeRoot
+>>
+endobj
+
+%% Page 1
+%% Original object ID: 3 0
+5 0 obj
+<<
+  /Contents 6 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 3 0 R
+  /Resources <<
+    /Font <<
+      /F1 8 0 R
+    >>
+    /ProcSet 9 0 R
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Contents for page 1
+%% Original object ID: 4 0
+6 0 obj
+<<
+  /Length 7 0 R
+>>
+stream
+BT
+  /F1 24 Tf
+  72 720 Td
+  (Potato) Tj
+ET
+endstream
+endobj
+
+7 0 obj
+44
+endobj
+
+%% Original object ID: 6 0
+8 0 obj
+<<
+  /BaseFont /Helvetica
+  /Encoding /WinAnsiEncoding
+  /Name /F1
+  /Subtype /Type1
+  /Type /Font
+>>
+endobj
+
+%% Original object ID: 5 0
+9 0 obj
+[
+  /PDF
+  /Text
+]
+endobj
+
+xref
+0 10
+0000000000 65535 f 
+0000000052 00000 n 
+0000000175 00000 n 
+0000000241 00000 n 
+0000000340 00000 n 
+0000000423 00000 n 
+0000000665 00000 n 
+0000000764 00000 n 
+0000000810 00000 n 
+0000000955 00000 n 
+trailer <<
+  /Root 1 0 R
+  /Size 10
+  /ID [<e8147af54e2f4232c87179e90799f037><e8147af54e2f4232c87179e90799f037>]
+>>
+startxref
+990
+%%EOF