Add new commands --remove-metadata and --remove-info

m-holger
1 parent 0b3debaf
Showing 18 changed files with 138 additions and 21 deletions
ChangeLog
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
qpdf/qtest/merge-and-split.test
qpdf/qtest/qpdf/remove-info-no-moddate.pdf
qpdf/qtest/qpdf/remove-info.pdf
qpdf/qtest/qpdf/remove-metadata-no-moddate.pdf
qpdf/qtest/qpdf/remove-metadata.pdf
+2024-08-25  M Holger  <m.holger@qpdf.org>
+
+	* Add new command-line arguments --remove-metadata and --remove-info
+	to exclude document metadata and information from the output PDF
+	file. Patially fixes #1145.
+
 2024-08-06  M Holger  <m.holger@qpdf.org>
 	* Bug fix: when writing real numbers as JSON ensure that they don't
@@ -692,6 +692,8 @@ class QPDFJob
         bool optimize_images{false};
         bool externalize_inline_images{false};
         bool keep_inline_images{false};
+        bool remove_info{false};
+        bool remove_metadata{false};
         bool remove_page_labels{false};
         size_t oi_min_width{DEFAULT_OI_MIN_WIDTH};
         size_t oi_min_height{DEFAULT_OI_MIN_HEIGHT};
@@ -32,6 +32,8 @@ QPDF_DLL Config* progress();
 QPDF_DLL Config* qdf();
 QPDF_DLL Config* rawStreamData();
 QPDF_DLL Config* recompressFlate();
+QPDF_DLL Config* removeInfo();
+QPDF_DLL Config* removeMetadata();
 QPDF_DLL Config* removePageLabels();
 QPDF_DLL Config* reportMemoryUsage();
 QPDF_DLL Config* requiresPassword();
@@ -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 dbfc221d1533120d1aa9c361d8d2483dea5fcb1c0fd95144d98d305e64ed32a6
+include/qpdf/auto_job_c_main.hh 84f463237235b2c095b747a4f5dd00f109ee596a1c207b944efb296c0c568cae
 include/qpdf/auto_job_c_pages.hh 09ca15649cc94fdaf6d9bdae28a20723f2a66616bf15aa86d83df31051d82506
 include/qpdf/auto_job_c_uo.hh 9c2f98a355858dd54d0bba444b73177a59c9e56833e02fa6406f429c07f39e62
-job.yml 53cad86659db6722e8f415aacb19fc51ab81bb1589c3cb8f65ec893bb4bf5566
+job.yml 31935064eca625af7657b23f2f12c614d14751ec0b12702482b1768a04905d22
 libqpdf/qpdf/auto_job_decl.hh 20d6affe1e260f5a1af4f1d82a820b933835440ff03020e877382da2e8dac6c6
-libqpdf/qpdf/auto_job_help.hh 74b2982771720927ce7be8f1690720ec65cb9989620493a0c154f50ba2c254e4
-libqpdf/qpdf/auto_job_init.hh 19d1da7c4c0c635bd1c5db8d5f17df8edad3442f8eba006adb075cec295fa158
+libqpdf/qpdf/auto_job_help.hh 1e9181f4729a22ff91ab54e2b4a82e6af0c57a8327efb222a4196adb609c1ade
+libqpdf/qpdf/auto_job_init.hh e2a6bb87870c5522a01b15461c9fe909e360f5c7fed06e41acf13a125bd1d03e
 libqpdf/qpdf/auto_job_json_decl.hh 843892c8e8652a86b7eb573893ef24050b7f36fe313f7251874be5cd4cdbe3fd
-libqpdf/qpdf/auto_job_json_init.hh a87256c082427ec0318223762472970b2eced535c0c8b0288d45c8cdaaf62f74
-libqpdf/qpdf/auto_job_schema.hh 5dac568dff39614e161a0af59a0f328f1e28edf69b96f08bb76fd592d51bb053
+libqpdf/qpdf/auto_job_json_init.hh 344c2fb473f88fe829c93b1efe6c70a0e4796537b8eb35e421d955fff481ba7d
+libqpdf/qpdf/auto_job_schema.hh 6d3eef5137b8828eaa301a1b3cf75cb7bb812aa6e2d8301de865b42d238d7a7c
 manual/_ext/qpdf.py 6add6321666031d55ed4aedf7c00e5662bba856dfcd66ccb526563bffefbb580
-manual/cli.rst 94057baba9ecffb4ce19ae61c8fa507ef07209c280fccae97b283c3dfce834e0
-manual/qpdf.1 0ec05f1392c160165cdf6adada4de84c0de75bd2fb5762caff4e1372aacada4c
+manual/cli.rst b7f37995f13346518ae7b2ea84836fba13b4da4e1f55be5f2a861f20dea0ccdb
+manual/qpdf.1 59c26635017cba5d142ec3fcc4aebcb91e0cf1355d51365db84f48b21585ad8d
 manual/qpdf.1.in 436ecc85d45c4c9e2dbd1725fb7f0177fb627179469f114561adf3cb6cbb677b
@@ -130,6 +130,8 @@ options:
       - qdf
       - raw-stream-data
       - recompress-flate
+      - remove-info
+      - remove-metadata
       - remove-page-labels
       - replace-input
       - report-memory-usage
@@ -440,6 +442,8 @@ json:
     - Pages.file:
       Pages.password:
       range:
+  remove-info:
+  remove-metadata:
   remove-page-labels:
   report-memory-usage:
   rotate:
@@ -471,6 +471,21 @@ QPDFJob::createQPDF()
     }
     handleUnderOverlay(pdf);
     handleTransformations(pdf);
+    if (m->remove_info) {
+        auto trailer = pdf.getTrailer();
+        auto mod_date = trailer.getKey("/Info").getKeyIfDict("/ModDate");
+        if (mod_date.isNull()) {
+            trailer.removeKey("/Info");
+        } else {
+            auto info = trailer.replaceKeyAndGetNew(
+                "/Info", pdf.makeIndirectObject(QPDFObjectHandle::newDictionary()));
+            info.replaceKey("/ModDate", mod_date);
+        }
+        pdf.getRoot().removeKey("/Metadata");
+    }
+    if (m->remove_metadata) {
+        pdf.getRoot().removeKey("/Metadata");
+    }
     for (auto& foreign: page_heap) {
         if (foreign->anyWarnings()) {
@@ -511,6 +511,20 @@ QPDFJob::Config::removeAttachment(std::string const&amp; parameter)
 }
 QPDFJob::Config*
+QPDFJob::Config::removeInfo()
+{
+    o.m->remove_info = true;
+    return this;
+}
+
+QPDFJob::Config*
+QPDFJob::Config::removeMetadata()
+{
+    o.m->remove_metadata = true;
+    return this;
+}
+
+QPDFJob::Config*
 QPDFJob::Config::removePageLabels()
 {
     o.m->remove_page_labels = true;
@@ -414,6 +414,13 @@ Don&#39;t optimize images whose area in pixels is below the specified value.
 )");
 ap.addOptionHelp("--keep-inline-images", "modification", "exclude inline images from optimization", R"(Prevent inline images from being considered by --optimize-images.
 )");
+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.
+)");
+}
+static void add_help_5(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--remove-page-labels", "modification", "remove explicit page numbers", R"(Exclude page labels (explicit page numbers) from the output file.
 )");
 ap.addOptionHelp("--set-page-labels", "modification", "number pages for the entire document", R"(--set-page-labels label-spec ... --
@@ -460,9 +467,6 @@ iv, then the remaining pages with Arabic numerals starting with
 1 and continuing sequentially until the end of the document. For
 additional examples, please consult the manual.
 )");
-}
-static void add_help_5(QPDFArgParser& ap)
-{
 ap.addHelpTopic("encryption", "create encrypted files", R"(Create encrypted files. Usage:
 --encrypt \
@@ -641,6 +645,9 @@ ap.addOptionHelp(&quot;--force-R5&quot;, &quot;encryption&quot;, &quot;use unsupported R=5 encryption&quot;, R
 algorithm that existed only in Acrobat version IX. This option
 should not be used except for compatibility testing.
 )");
+}
+static void add_help_6(QPDFArgParser& ap)
+{
 ap.addHelpTopic("page-selection", "select pages from one or more files", R"(Use the --pages option to select pages from multiple files. Usage:
 qpdf in.pdf --pages --file=input-file \
@@ -725,9 +732,6 @@ appearance: first underlays, then the original page, then overlays.
 Run qpdf --help=page-ranges for help with page ranges.
 )");
-}
-static void add_help_6(QPDFArgParser& ap)
-{
 ap.addOptionHelp("--to", "overlay-underlay", "destination pages for underlay/overlay", R"(--to=page-range
 Specify the range of pages in the primary output to apply
@@ -829,6 +833,9 @@ its terminating &quot;--&quot;.
 To copy attachments from a password-protected file, use
 the --password option after the file name.
 )");
+}
+static void add_help_7(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--prefix", "copy-attachments", "key prefix for copying attachments", R"(--prefix=prefix
 Prepend a prefix to each key; may be needed if there are
@@ -839,9 +846,6 @@ ap.addHelpTopic(&quot;inspection&quot;, &quot;inspect PDF files&quot;, R&quot;(These options provide tool
 the options in this section are specified, no output file may be
 given.
 )");
-}
-static void add_help_7(QPDFArgParser& ap)
-{
 ap.addOptionHelp("--is-encrypted", "inspection", "silently test whether a file is encrypted", R"(Silently exit with a code indicating the file's encryption status:
 0: the file is encrypted
@@ -919,6 +923,9 @@ output as binary data. Get the key with --list-attachments.
 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.
 )");
+}
+static void add_help_8(QPDFArgParser& ap)
+{
 ap.addOptionHelp("--json", "json", "show file in JSON format", R"(--json[=version]
 Generate a JSON representation of the file. This is described in
@@ -932,9 +939,6 @@ Describe the format of the JSON output by writing to standard
 output a JSON object with the same keys and with values
 containing descriptive text.
 )");
-}
-static void add_help_8(QPDFArgParser& ap)
-{
 ap.addOptionHelp("--json-key", "json", "limit which keys are in JSON output", R"(--json-key=key
 This option is repeatable. If given, only the specified
@@ -68,6 +68,8 @@ 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-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("replace-input", b(&ArgParser::argReplaceInput));
 this->ap.addBare("report-memory-usage", [this](){c_main->reportMemoryUsage();});
@@ -412,6 +412,12 @@ addParameter([this](std::string const&amp; p) { c_pages-&gt;range(p); });
 popHandler(); // key: range
 popHandler(); // array: .pages[]
 popHandler(); // key: pages
+pushKey("removeInfo");
+addBare([this]() { c_main->removeInfo(); });
+popHandler(); // key: removeInfo
+pushKey("removeMetadata");
+addBare([this]() { c_main->removeMetadata(); });
+popHandler(); // key: removeMetadata
 pushKey("removePageLabels");
 addBare([this]() { c_main->removePageLabels(); });
 popHandler(); // key: removePageLabels
@@ -145,6 +145,8 @@ static constexpr char const* JOB_SCHEMA_DATA = R&quot;({
       "range": "page range"
     }
   ],
+  "removeInfo": "remove file information",
+  "removeMetadata": "remove metadata",
   "removePageLabels": "remove explicit page numbers",
   "reportMemoryUsage": "best effort report of memory usage",
   "rotate": "rotate pages",
@@ -1773,6 +1773,27 @@ Related Options
    Prevent inline images from being included in image optimization
    done by :qpdf:ref:`--optimize-images`.
+.. qpdf:option:: --remove-info
+
+   .. help: remove file information
+
+      Exclude file information (except modification date) from the output file.
+
+   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`.
+
+.. qpdf:option:: --remove-metadata
+
+   .. help: remove metadata
+
+      Exclude metadata from the output file.
+
+   Exclude metadata from the output file by omitting the ``/Metadata``
+   dictionary in the document catalog.
+   See also :qpdf:ref:`--remove-info`.
+
 .. qpdf:option:: --remove-page-labels
    .. help: remove explicit page numbers
@@ -530,6 +530,12 @@ 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-info \-\- remove file information
+Exclude file information (except modification date) from the output file.
+.TP
+.B --remove-metadata \-\- remove metadata
+Exclude metadata from the output file.
+.TP
 .B --remove-page-labels \-\- remove explicit page numbers
 Exclude page labels (explicit page numbers) from the output file.
 .TP
@@ -14,7 +14,7 @@ cleanup();
 my $td = new TestDriver('merge-and-split');
-my $n_tests = 28;
+my $n_tests = 34;
 # Select pages from the same file multiple times including selecting
 # twice from an encrypted file and specifying the password only the
@@ -103,6 +103,39 @@ $td-&gt;runtest(&quot;check output&quot;,
              {$td->COMMAND => "qpdf-test-compare a.pdf remove-labels.pdf"},
              {$td->FILE => "remove-labels.pdf", $td->EXIT_STATUS => 0});
+$td->runtest("remove metadata",
+             {$td->COMMAND =>
+                  "qpdf metadata-crypt-filter.pdf a.pdf" .
+                  " --remove-metadata" .
+                  " --decrypt" .
+                  " --static-id"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "remove-metadata.pdf"});
+
+$td->runtest("remove info (with moddate)",
+             {$td->COMMAND =>
+                  "qpdf remove-metadata.pdf a.pdf" .
+                  " --remove-info" .
+                  " --decrypt" .
+                  " --static-id"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "remove-info.pdf"});
+
+$td->runtest("remove info (without moddate)",
+             {$td->COMMAND =>
+                  "qpdf remove-metadata-no-moddate.pdf a.pdf" .
+                  " --remove-info" .
+                  " --decrypt" .
+                  " --static-id"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "remove-info-no-moddate.pdf"});
+
 $td->runtest("split with shared resources",
              {$td->COMMAND =>
                   "qpdf --qdf --static-id" .