From 352ce9b22ba32fa50e22258f7d61557ae0d53cc5 Mon Sep 17 00:00:00 2001
From: Jay Berkenbilt <ejb@ql.org>
Date: Tue, 18 Dec 2018 14:59:14 -0500
Subject: [PATCH] Preserve page labels (numbers) when splitting and merging

---
 ChangeLog                                 |   6 +
 manual/qpdf-manual.xml                    |  38 +--
 qpdf/qpdf.cc                              |  52 +++-
 qpdf/qpdf.testcov                         |   1 +
 qpdf/qtest/qpdf.test                      |  29 +-
 qpdf/qtest/qpdf/11-pages-with-labels.pdf  | Bin 0 -> 4215 bytes
 qpdf/qtest/qpdf/labels-split-01-06.pdf    | 324 ++++++++++++++++++++++
 qpdf/qtest/qpdf/labels-split-07-11.pdf    | 280 +++++++++++++++++++
 qpdf/qtest/qpdf/merge-implicit-ranges.pdf | 220 +++++++--------
 qpdf/qtest/qpdf/merge-multiple-labels.pdf | Bin 0 -> 3452 bytes
 qpdf/qtest/qpdf/merge-three-files-1.pdf   | Bin 8495 -> 8396 bytes
 qpdf/qtest/qpdf/merge-three-files-2.pdf   | Bin 6036 -> 6196 bytes
 12 files changed, 806 insertions(+), 144 deletions(-)
 create mode 100644 qpdf/qtest/qpdf/11-pages-with-labels.pdf
 create mode 100644 qpdf/qtest/qpdf/labels-split-01-06.pdf
 create mode 100644 qpdf/qtest/qpdf/labels-split-07-11.pdf
 create mode 100644 qpdf/qtest/qpdf/merge-multiple-labels.pdf

diff --git a/ChangeLog b/ChangeLog
index 75fad549..5f44bb05 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,11 @@
 2018-12-18  Jay Berkenbilt  <ejb@ql.org>
 
+	* Preserve page labels when merging and splitting files. Prior
+	versions of qpdf simply preserved the page label information from
+	the first file, which usually wouldn't make any sense in the
+	merged file. Now any page that had a page number in any original
+	file will have the same page number after merging or splitting.
+
 	* Add QPDFPageLabelDocumentHelper class. This is a document helper
 	class that provides useful methods for dealing with page labels.
 	It abstracts the fact that they are stored as number trees and
diff --git a/manual/qpdf-manual.xml b/manual/qpdf-manual.xml
index 8185b848..e327eb95 100644
--- a/manual/qpdf-manual.xml
+++ b/manual/qpdf-manual.xml
@@ -911,23 +911,23 @@ make
     </itemizedlist>
    </para>
    <para>
-    Note that qpdf doesn't presently do anything special about other
-    constructs in a PDF file that may know about pages, so semantics
-    of splitting and merging vary across features.  For example, the
-    document's outlines (bookmarks) point to actual page objects, so
-    if you select some pages and not others, bookmarks that point to
-    pages that are in the output file will work, and remaining
-    bookmarks will not work.  On the other hand, page labels (page
-    numbers specified in the file) are just sequential, so page labels
-    will be messed up in the output file.  A future version of
-    <command>qpdf</command> may do a better job at handling these
-    issues.  (Note that the qpdf library already contains all of the
-    APIs required in order to implement this in your own application
-    if you need it.)  In the mean time, you can always use
-    <option>--empty</option> as the primary input file to avoid
-    copying all of that from the first file.  For example, to take
-    pages 1 through 5 from a <filename>infile.pdf</filename> while
-    preserving all metadata associated with that file, you could use
+    Starting in qpdf version 8.3, when you split and merge files, any
+    page labels (page numbers) are preserved in the final file. It is
+    expected that more document features will be preserved by
+    splitting and merging. In the mean time, semantics of splitting
+    and merging vary across features. For example, the document's
+    outlines (bookmarks) point to actual page objects, so if you
+    select some pages and not others, bookmarks that point to pages
+    that are in the output file will work, and remaining bookmarks
+    will not work. A future version of <command>qpdf</command> may do
+    a better job at handling these issues. (Note that the qpdf library
+    already contains all of the APIs required in order to implement
+    this in your own application if you need it.) In the mean time,
+    you can always use <option>--empty</option> as the primary input
+    file to avoid copying all of that from the first file. For
+    example, to take pages 1 through 5 from a
+    <filename>infile.pdf</filename> while preserving all metadata
+    associated with that file, you could use
 
     <programlisting><command>qpdf</command> <option>infile.pdf --pages infile.pdf 1-5 -- outfile.pdf</option>
 </programlisting>
@@ -946,8 +946,8 @@ make
     If, for some reason, you wanted to take the first page of an
     encrypted file called <filename>encrypted.pdf</filename> with
     password <literal>pass</literal> and repeat it twice in an output
-    file, and if you wanted to drop metadata (like page numbers and
-    outlines) but preserve encryption, you would use
+    file, and if you wanted to drop document-level metadata but
+    preserve encryption, you would use
 
     <programlisting><command>qpdf</command> <option>--empty --copy-encryption=encrypted.pdf --encryption-file-password=pass
 --pages encrypted.pdf --password=pass 1 ./encrypted.pdf --password=pass 1 --
diff --git a/qpdf/qpdf.cc b/qpdf/qpdf.cc
index 19d46acc..b6762aab 100644
--- a/qpdf/qpdf.cc
+++ b/qpdf/qpdf.cc
@@ -16,6 +16,7 @@
 #include <qpdf/QPDF.hh>
 #include <qpdf/QPDFPageDocumentHelper.hh>
 #include <qpdf/QPDFPageObjectHelper.hh>
+#include <qpdf/QPDFPageLabelDocumentHelper.hh>
 #include <qpdf/QPDFExc.hh>
 
 #include <qpdf/QPDFWriter.hh>
@@ -2296,11 +2297,25 @@ static void handle_page_specs(QPDF& pdf, Options& o,
     // Keep track of any pages from the original file that we are
     // selecting.
     std::set<int> selected_from_orig;
+    std::vector<QPDFObjectHandle> new_labels;
+    bool any_page_labels = false;
+    int out_pageno = 0;
     for (std::vector<QPDFPageData>::iterator iter =
              parsed_specs.begin();
          iter != parsed_specs.end(); ++iter)
     {
         QPDFPageData& page_data = *iter;
+        ClosedFileInputSource* cis = 0;
+        if (page_spec_cfis.count(page_data.filename))
+        {
+            cis = page_spec_cfis[page_data.filename];
+            cis->stayOpen(true);
+        }
+        QPDFPageLabelDocumentHelper pldh(*page_data.qpdf);
+        if (pldh.hasPageLabels())
+        {
+            any_page_labels = true;
+        }
         if (o.verbose)
         {
             std::cout << whoami << ": adding pages from "
@@ -2309,22 +2324,14 @@ static void handle_page_specs(QPDF& pdf, Options& o,
         for (std::vector<int>::iterator pageno_iter =
                  page_data.selected_pages.begin();
              pageno_iter != page_data.selected_pages.end();
-             ++pageno_iter)
+             ++pageno_iter, ++out_pageno)
         {
             // Pages are specified from 1 but numbered from 0 in the
             // vector
             int pageno = *pageno_iter - 1;
-            ClosedFileInputSource* cis = 0;
-            if (page_spec_cfis.count(page_data.filename))
-            {
-                cis = page_spec_cfis[page_data.filename];
-                cis->stayOpen(true);
-            }
+            pldh.getLabelsForPageRange(pageno, pageno, out_pageno,
+                                       new_labels);
             dh.addPage(page_data.orig_pages.at(pageno), false);
-            if (cis)
-            {
-                cis->stayOpen(false);
-            }
             if (page_data.qpdf == &pdf)
             {
                 // This is a page from the original file. Keep track
@@ -2332,6 +2339,18 @@ static void handle_page_specs(QPDF& pdf, Options& o,
                 selected_from_orig.insert(pageno);
             }
         }
+        if (cis)
+        {
+            cis->stayOpen(false);
+        }
+    }
+    if (any_page_labels)
+    {
+        QPDFObjectHandle page_labels =
+            QPDFObjectHandle::newDictionary();
+        page_labels.replaceKey(
+            "/Nums", QPDFObjectHandle::newArray(new_labels));
+        pdf.getRoot().replaceKey("/PageLabels", page_labels);
     }
 
     // Delete page objects for unused page in primary. This prevents
@@ -2574,6 +2593,7 @@ static void write_outfile(QPDF& pdf, Options& o)
             dh.pushInheritedAttributesToPage();
             dh.removeUnreferencedResources();
         }
+        QPDFPageLabelDocumentHelper pldh(pdf);
         std::vector<QPDFObjectHandle> const& pages = pdf.getAllPages();
         int pageno_len = QUtil::int_to_string(pages.size()).length();
         unsigned int num_pages = pages.size();
@@ -2592,6 +2612,16 @@ static void write_outfile(QPDF& pdf, Options& o)
                 QPDFObjectHandle page = pages.at(pageno - 1);
                 outpdf.addPage(page, false);
             }
+            if (pldh.hasPageLabels())
+            {
+                std::vector<QPDFObjectHandle> labels;
+                pldh.getLabelsForPageRange(first - 1, last - 1, 0, labels);
+                QPDFObjectHandle page_labels =
+                    QPDFObjectHandle::newDictionary();
+                page_labels.replaceKey(
+                    "/Nums", QPDFObjectHandle::newArray(labels));
+                outpdf.getRoot().replaceKey("/PageLabels", page_labels);
+            }
             std::string page_range = QUtil::int_to_string(first, pageno_len);
             if (o.split_pages > 1)
             {
diff --git a/qpdf/qpdf.testcov b/qpdf/qpdf.testcov
index 6f06ab05..71858eec 100644
--- a/qpdf/qpdf.testcov
+++ b/qpdf/qpdf.testcov
@@ -360,3 +360,4 @@ qpdf disable keep files open 0
 qpdf keep files open n 0
 qpdf keep files open y 0
 qpdf don't disable keep files open 0
+QPDFPageLabelDocumentHelper skip first 0
diff --git a/qpdf/qtest/qpdf.test b/qpdf/qtest/qpdf.test
index aba78938..cf5b2ab5 100644
--- a/qpdf/qtest/qpdf.test
+++ b/qpdf/qtest/qpdf.test
@@ -1137,7 +1137,7 @@ my @sp_cases = (
     [11, 'pdf extension', '', 'split-out.Pdf'],
     [4, 'fallback', '--pages 11-pages.pdf 1-3 minimal.pdf --', 'split-out'],
     );
-$n_tests += 9;
+$n_tests += 12;
 for (@sp_cases)
 {
     $n_tests += 1 + $_->[0];
@@ -1171,6 +1171,17 @@ foreach my $i (qw(01-04 05-08 09-10))
                  {$td->FILE => "shared-split-$i.pdf"});
 }
 
+$td->runtest("split page with labels",
+             {$td->COMMAND => "qpdf --qdf --static-id --split-pages=6".
+                  " 11-pages-with-labels.pdf split-out-labels.pdf"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+foreach my $i (qw(01-06 07-11))
+{
+    $td->runtest("check output ($i)",
+                 {$td->FILE => "split-out-labels-$i.pdf"},
+                 {$td->FILE => "labels-split-$i.pdf"});
+}
+
 foreach my $d (@sp_cases)
 {
     my ($n, $description, $xargs, $out) = @$d;
@@ -1335,7 +1346,7 @@ foreach my $d (@nrange_tests)
 show_ntests();
 # ----------
 $td->notify("--- Merging and Splitting ---");
-$n_tests += 16;
+$n_tests += 18;
 
 # Select pages from the same file multiple times including selecting
 # twice from an encrypted file and specifying the password only the
@@ -1368,8 +1379,7 @@ $td->runtest("merge three files",
                   " $pages_options --static-id"},
              {$td->STRING => "", $td->EXIT_STATUS => 0});
 # Manually verified about this file: it has the same pages but does
-# not contain outlines, page labels, or other things from the original
-# file.
+# not contain outlines or other things from the original file.
 $td->runtest("check output",
              {$td->FILE => "a.pdf"},
              {$td->FILE => "merge-three-files-2.pdf"});
@@ -1392,6 +1402,17 @@ $td->runtest("merge with implicit ranges",
 $td->runtest("check output",
              {$td->FILE => "a.pdf"},
              {$td->FILE => "merge-implicit-ranges.pdf"});
+$td->runtest("merge with multiple labels",
+             {$td->COMMAND =>
+                  "qpdf --empty a.pdf" .
+                  " --pages 11-pages-with-labels.pdf 8-11" .
+                  " minimal.pdf " .
+                  " page-labels-and-outlines.pdf 17-19 --" .
+                  " --static-id"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "merge-multiple-labels.pdf"});
 
 $td->runtest("split with shared resources",
              {$td->COMMAND =>
diff --git a/qpdf/qtest/qpdf/11-pages-with-labels.pdf b/qpdf/qtest/qpdf/11-pages-with-labels.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..962b1b0e57954e198a3d78385952ec1a104d4698
GIT binary patch
literal 4215
zcmd5=&uiR96fOydpsFR%(q3|SxEO4Rt(lQVKU!l*c4G*M({$Hu4yg~b+F4g+Eg4Bm
zw>buU&mYiJ{*FQ~Ip&aC|B*m%ZQhJ5OV;ElP<0q-pGNb2@6*ipG`sb5e7H;ZJZtN(
ze_sD<Q6P}bezo@Z!Fei9<zq3E%L3HTC#$mpp5uLe54O*9xw``g2jJ<*6r3EKX^B5E
z7S=JLW7Jo{6V>Qp3vh9u2{^~UpG$B?q7=*Q6mMHHohy9S;xWplD3dH5i&Db&_*+IO
zBLTyPFdFROh<P?&#WIKOd*^Zun9;L5DP^wM)dMQLI<Zl<N=u*=oJYxA<>YBHT(`b%
z1KozYjdV*%by5mVfGUD`s?wm<04H@mO1Yv1u5LHrX(`jP09xTWM{=Hs``KD+OTfpW
zgNUJ6s8o(UYpEu($X0ob1FIKsnBg6LK>^iOWVE<>7Efh~V>u`T@{#NEQuj(~MXkk5
zaWI)x*$>N1<zzCe-pH`blsYD}YL*PkOsQiqW7WhRmYGt=WLB-EVVUW5ZBnb&_rTQJ
zZal&TuYH4ETIZm?q5aQPt@6QvRl9EWwQBzdx7BsRRIRe_fmLf)g2ysFEq?*-Vx38r
zSV{4`#OgbiaW>cGqbRW`pIPfa3hRe=zq!Z6`|;MpDG6?D-n@AA<;G|Ky?*=t?VoS%
zT)ceq{&-__bn)u$#^1O1KKbf%`!1IF%f~N^y{=!iEcZnrb#Zf!lQUWDPO>wRg7Y9n
z=p;P_=UI~8ON*olOjol~e@3VZhef?Abb5@Y{?oQ=_nqH2O@3e7yJmiEU+x<_Zm_}L
zGqKyw+c)+X4fc-h7}&b<)bF)#>}i9|Y+_=!y|Zs@x556-rY3g#>$Pv}qQM^9%*1ZH
zU*FiDHrPkDYht&*bNj}A)L{Q)dnWeB{LAahziwWEZ-V`^3Euu#trPDJym8OX9s9%p
zU*~dR5nzEut`6`ycR4KJDyDWD>VWhrMmesLPK>!YcRMkcqjz><9CuIMnD3hyAw~b`
zJR1c#N3X{yWd;Uip@Bg?7p3kz%OkU2;F<j*V)SE#8~qp!@r(I724f$Ic?9QsrypnN
z^_`f{4NX}Pn79$XozAl^VFrdvJp;pKfq~(=QA^V@7s(O}x!N*5Ocxm_kHQW3B+GCs
zTwPC-7ZT?Yb{NC+eMwv<!Y~d*6bAE|9}5@%43HcT;>U4(urC%d7Yn-Z=OmiXxQHSi
hM~wI+^!*@=q64+zw~A8arJkfNXUy8#dhq?B^#MH_qWJ&-

literal 0
HcmV?d00001

diff --git a/qpdf/qtest/qpdf/labels-split-01-06.pdf b/qpdf/qtest/qpdf/labels-split-01-06.pdf
new file mode 100644
index 00000000..1058eba1
--- /dev/null
+++ b/qpdf/qtest/qpdf/labels-split-01-06.pdf
@@ -0,0 +1,324 @@
+%PDF-1.3
+%¿÷¢þ
+%QDF-1.0
+
+%% Original object ID: 1 0
+1 0 obj
+<<
+  /PageLabels <<
+    /Nums [
+      0
+      <<
+        /P (pre-)
+        /St 1
+      >>
+      4
+      <<
+        /S /r
+        /St 4
+      >>
+    ]
+  >>
+  /Pages 2 0 R
+  /Type /Catalog
+>>
+endobj
+
+%% Original object ID: 2 0
+2 0 obj
+<<
+  /Count 6
+  /Kids [
+    3 0 R
+    4 0 R
+    5 0 R
+    6 0 R
+    7 0 R
+    8 0 R
+  ]
+  /Type /Pages
+>>
+endobj
+
+%% Page 1
+%% Original object ID: 3 0
+3 0 obj
+<<
+  /Contents 9 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 11 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 2
+%% Original object ID: 6 0
+4 0 obj
+<<
+  /Contents 12 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 11 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 3
+%% Original object ID: 8 0
+5 0 obj
+<<
+  /Contents 14 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 11 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 4
+%% Original object ID: 10 0
+6 0 obj
+<<
+  /Contents 16 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 11 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 5
+%% Original object ID: 12 0
+7 0 obj
+<<
+  /Contents 18 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 11 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 6
+%% Original object ID: 14 0
+8 0 obj
+<<
+  /Contents 20 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 11 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Contents for page 1
+%% Original object ID: 4 0
+9 0 obj
+<<
+  /Length 10 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 1) Tj ET
+endstream
+endobj
+
+10 0 obj
+47
+endobj
+
+%% Original object ID: 5 0
+11 0 obj
+<<
+  /BaseFont /Times-Roman
+  /Encoding /WinAnsiEncoding
+  /Subtype /Type1
+  /Type /Font
+>>
+endobj
+
+%% Contents for page 2
+%% Original object ID: 7 0
+12 0 obj
+<<
+  /Length 13 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 2) Tj ET
+endstream
+endobj
+
+13 0 obj
+47
+endobj
+
+%% Contents for page 3
+%% Original object ID: 9 0
+14 0 obj
+<<
+  /Length 15 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 3) Tj ET
+endstream
+endobj
+
+15 0 obj
+47
+endobj
+
+%% Contents for page 4
+%% Original object ID: 11 0
+16 0 obj
+<<
+  /Length 17 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 4) Tj ET
+endstream
+endobj
+
+17 0 obj
+47
+endobj
+
+%% Contents for page 5
+%% Original object ID: 13 0
+18 0 obj
+<<
+  /Length 19 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 5) Tj ET
+endstream
+endobj
+
+19 0 obj
+47
+endobj
+
+%% Contents for page 6
+%% Original object ID: 15 0
+20 0 obj
+<<
+  /Length 21 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 6) Tj ET
+endstream
+endobj
+
+21 0 obj
+47
+endobj
+
+xref
+0 22
+0000000000 65535 f 
+0000000052 00000 n 
+0000000285 00000 n 
+0000000444 00000 n 
+0000000699 00000 n 
+0000000955 00000 n 
+0000001212 00000 n 
+0000001469 00000 n 
+0000001726 00000 n 
+0000001995 00000 n 
+0000002098 00000 n 
+0000002145 00000 n 
+0000002304 00000 n 
+0000002408 00000 n 
+0000002478 00000 n 
+0000002582 00000 n 
+0000002653 00000 n 
+0000002757 00000 n 
+0000002828 00000 n 
+0000002932 00000 n 
+0000003003 00000 n 
+0000003107 00000 n 
+trailer <<
+  /Root 1 0 R
+  /Size 22
+  /ID [<31415926535897932384626433832795><31415926535897932384626433832795>]
+>>
+startxref
+3127
+%%EOF
diff --git a/qpdf/qtest/qpdf/labels-split-07-11.pdf b/qpdf/qtest/qpdf/labels-split-07-11.pdf
new file mode 100644
index 00000000..42120fed
--- /dev/null
+++ b/qpdf/qtest/qpdf/labels-split-07-11.pdf
@@ -0,0 +1,280 @@
+%PDF-1.3
+%¿÷¢þ
+%QDF-1.0
+
+%% Original object ID: 1 0
+1 0 obj
+<<
+  /PageLabels <<
+    /Nums [
+      0
+      <<
+        /S /r
+        /St 6
+      >>
+      2
+      <<
+        /S /a
+        /St 16
+      >>
+    ]
+  >>
+  /Pages 2 0 R
+  /Type /Catalog
+>>
+endobj
+
+%% Original object ID: 2 0
+2 0 obj
+<<
+  /Count 5
+  /Kids [
+    3 0 R
+    4 0 R
+    5 0 R
+    6 0 R
+    7 0 R
+  ]
+  /Type /Pages
+>>
+endobj
+
+%% Page 1
+%% Original object ID: 3 0
+3 0 obj
+<<
+  /Contents 8 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 10 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 2
+%% Original object ID: 6 0
+4 0 obj
+<<
+  /Contents 11 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 10 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 3
+%% Original object ID: 8 0
+5 0 obj
+<<
+  /Contents 13 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 10 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 4
+%% Original object ID: 10 0
+6 0 obj
+<<
+  /Contents 15 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 10 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Page 5
+%% Original object ID: 12 0
+7 0 obj
+<<
+  /Contents 17 0 R
+  /MediaBox [
+    0
+    0
+    612
+    792
+  ]
+  /Parent 2 0 R
+  /Resources <<
+    /Font <<
+      /F1 10 0 R
+    >>
+    /ProcSet [
+      /PDF
+      /Text
+    ]
+  >>
+  /Type /Page
+>>
+endobj
+
+%% Contents for page 1
+%% Original object ID: 4 0
+8 0 obj
+<<
+  /Length 9 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 7) Tj ET
+endstream
+endobj
+
+9 0 obj
+47
+endobj
+
+%% Original object ID: 5 0
+10 0 obj
+<<
+  /BaseFont /Times-Roman
+  /Encoding /WinAnsiEncoding
+  /Subtype /Type1
+  /Type /Font
+>>
+endobj
+
+%% Contents for page 2
+%% Original object ID: 7 0
+11 0 obj
+<<
+  /Length 12 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 8) Tj ET
+endstream
+endobj
+
+12 0 obj
+47
+endobj
+
+%% Contents for page 3
+%% Original object ID: 9 0
+13 0 obj
+<<
+  /Length 14 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 9) Tj ET
+endstream
+endobj
+
+14 0 obj
+47
+endobj
+
+%% Contents for page 4
+%% Original object ID: 11 0
+15 0 obj
+<<
+  /Length 16 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 10) Tj ET
+endstream
+endobj
+
+16 0 obj
+48
+endobj
+
+%% Contents for page 5
+%% Original object ID: 13 0
+17 0 obj
+<<
+  /Length 18 0 R
+>>
+stream
+BT /F1 15 Tf 72 720 Td (Original page 11) Tj ET
+endstream
+endobj
+
+18 0 obj
+48
+endobj
+
+xref
+0 19
+0000000000 65535 f 
+0000000052 00000 n 
+0000000282 00000 n 
+0000000431 00000 n 
+0000000686 00000 n 
+0000000942 00000 n 
+0000001199 00000 n 
+0000001456 00000 n 
+0000001725 00000 n 
+0000001827 00000 n 
+0000001873 00000 n 
+0000002032 00000 n 
+0000002136 00000 n 
+0000002206 00000 n 
+0000002310 00000 n 
+0000002381 00000 n 
+0000002486 00000 n 
+0000002557 00000 n 
+0000002662 00000 n 
+trailer <<
+  /Root 1 0 R
+  /Size 19
+  /ID [<31415926535897932384626433832795><31415926535897932384626433832795>]
+>>
+startxref
+2682
+%%EOF
diff --git a/qpdf/qtest/qpdf/merge-implicit-ranges.pdf b/qpdf/qtest/qpdf/merge-implicit-ranges.pdf
index da523cad..be17bf46 100644
--- a/qpdf/qtest/qpdf/merge-implicit-ranges.pdf
+++ b/qpdf/qtest/qpdf/merge-implicit-ranges.pdf
@@ -1,7 +1,7 @@
 %PDF-1.3
 %¿÷¢þ
 1 0 obj
-<< /Pages 2 0 R /Type /Catalog >>
+<< /PageLabels << /Nums [ 0 << /St 1 >> 21 << /P () /St 1 >> 23 << /S /r /St 1 >> 28 << /P () /St 1 >> 30 << /S /r /St 6 >> 32 << /P () /St 1 >> 33 << /S /D /St 2 >> 36 << /S /D /St 6 >> 40 << /P () /St 1 >> 41 << /S /D /St 12 >> 43 << /S /D /St 16059 >> 44 << /S /r /St 50 >> 50 << /S /r /St 54 >> ] >> /Pages 2 0 R /Type /Catalog >>
 endobj
 2 0 obj
 << /Count 51 /Kids [ 3 0 R 4 0 R 5 0 R 6 0 R 7 0 R 8 0 R 9 0 R 10 0 R 11 0 R 12 0 R 13 0 R 14 0 R 15 0 R 16 0 R 17 0 R 18 0 R 19 0 R 20 0 R 21 0 R 22 0 R 23 0 R 24 0 R 25 0 R 26 0 R 27 0 R 28 0 R 29 0 R 30 0 R 31 0 R 32 0 R 33 0 R 34 0 R 35 0 R 36 0 R 37 0 R 38 0 R 39 0 R 40 0 R 41 0 R 42 0 R 43 0 R 44 0 R 45 0 R 46 0 R 47 0 R 48 0 R 49 0 R 50 0 R 51 0 R 52 0 R 53 0 R ] /Type /Pages >>
@@ -514,115 +514,115 @@ xref
 0 110
 0000000000 65535 f 
 0000000015 00000 n 
-0000000064 00000 n 
-0000000468 00000 n 
-0000000614 00000 n 
-0000000768 00000 n 
-0000000922 00000 n 
-0000001076 00000 n 
-0000001230 00000 n 
-0000001384 00000 n 
-0000001538 00000 n 
-0000001693 00000 n 
-0000001848 00000 n 
-0000002003 00000 n 
-0000002158 00000 n 
-0000002313 00000 n 
-0000002468 00000 n 
-0000002623 00000 n 
-0000002778 00000 n 
-0000002933 00000 n 
-0000003088 00000 n 
-0000003243 00000 n 
-0000003398 00000 n 
-0000003553 00000 n 
-0000003708 00000 n 
-0000003855 00000 n 
-0000004002 00000 n 
-0000004149 00000 n 
-0000004296 00000 n 
-0000004443 00000 n 
-0000004590 00000 n 
-0000004737 00000 n 
-0000004884 00000 n 
-0000005031 00000 n 
-0000005178 00000 n 
-0000005325 00000 n 
-0000005472 00000 n 
-0000005619 00000 n 
-0000005766 00000 n 
-0000005913 00000 n 
-0000006060 00000 n 
-0000006207 00000 n 
-0000006354 00000 n 
-0000006501 00000 n 
-0000006648 00000 n 
-0000006796 00000 n 
-0000006944 00000 n 
-0000007092 00000 n 
-0000007240 00000 n 
-0000007388 00000 n 
-0000007536 00000 n 
-0000007684 00000 n 
-0000007832 00000 n 
-0000007980 00000 n 
-0000008128 00000 n 
-0000008247 00000 n 
-0000008355 00000 n 
-0000008386 00000 n 
-0000008510 00000 n 
-0000008610 00000 n 
-0000008734 00000 n 
-0000008858 00000 n 
-0000008982 00000 n 
-0000009106 00000 n 
-0000009230 00000 n 
-0000009354 00000 n 
-0000009478 00000 n 
-0000009602 00000 n 
-0000009726 00000 n 
-0000009851 00000 n 
-0000009976 00000 n 
-0000010101 00000 n 
-0000010226 00000 n 
-0000010351 00000 n 
-0000010475 00000 n 
-0000010600 00000 n 
-0000010725 00000 n 
-0000010850 00000 n 
-0000010975 00000 n 
-0000011096 00000 n 
-0000011204 00000 n 
-0000011235 00000 n 
-0000011356 00000 n 
-0000011477 00000 n 
-0000011598 00000 n 
-0000011719 00000 n 
-0000011840 00000 n 
-0000011961 00000 n 
-0000012082 00000 n 
-0000012203 00000 n 
-0000012324 00000 n 
-0000012446 00000 n 
-0000012568 00000 n 
-0000012690 00000 n 
-0000012812 00000 n 
-0000012934 00000 n 
-0000013056 00000 n 
-0000013178 00000 n 
-0000013300 00000 n 
-0000013422 00000 n 
-0000013544 00000 n 
-0000013667 00000 n 
-0000013790 00000 n 
-0000013913 00000 n 
-0000014036 00000 n 
-0000014158 00000 n 
-0000014281 00000 n 
-0000014404 00000 n 
-0000014527 00000 n 
-0000014650 00000 n 
+0000000365 00000 n 
+0000000769 00000 n 
+0000000915 00000 n 
+0000001069 00000 n 
+0000001223 00000 n 
+0000001377 00000 n 
+0000001531 00000 n 
+0000001685 00000 n 
+0000001839 00000 n 
+0000001994 00000 n 
+0000002149 00000 n 
+0000002304 00000 n 
+0000002459 00000 n 
+0000002614 00000 n 
+0000002769 00000 n 
+0000002924 00000 n 
+0000003079 00000 n 
+0000003234 00000 n 
+0000003389 00000 n 
+0000003544 00000 n 
+0000003699 00000 n 
+0000003854 00000 n 
+0000004009 00000 n 
+0000004156 00000 n 
+0000004303 00000 n 
+0000004450 00000 n 
+0000004597 00000 n 
+0000004744 00000 n 
+0000004891 00000 n 
+0000005038 00000 n 
+0000005185 00000 n 
+0000005332 00000 n 
+0000005479 00000 n 
+0000005626 00000 n 
+0000005773 00000 n 
+0000005920 00000 n 
+0000006067 00000 n 
+0000006214 00000 n 
+0000006361 00000 n 
+0000006508 00000 n 
+0000006655 00000 n 
+0000006802 00000 n 
+0000006949 00000 n 
+0000007097 00000 n 
+0000007245 00000 n 
+0000007393 00000 n 
+0000007541 00000 n 
+0000007689 00000 n 
+0000007837 00000 n 
+0000007985 00000 n 
+0000008133 00000 n 
+0000008281 00000 n 
+0000008429 00000 n 
+0000008548 00000 n 
+0000008656 00000 n 
+0000008687 00000 n 
+0000008811 00000 n 
+0000008911 00000 n 
+0000009035 00000 n 
+0000009159 00000 n 
+0000009283 00000 n 
+0000009407 00000 n 
+0000009531 00000 n 
+0000009655 00000 n 
+0000009779 00000 n 
+0000009903 00000 n 
+0000010027 00000 n 
+0000010152 00000 n 
+0000010277 00000 n 
+0000010402 00000 n 
+0000010527 00000 n 
+0000010652 00000 n 
+0000010776 00000 n 
+0000010901 00000 n 
+0000011026 00000 n 
+0000011151 00000 n 
+0000011276 00000 n 
+0000011397 00000 n 
+0000011505 00000 n 
+0000011536 00000 n 
+0000011657 00000 n 
+0000011778 00000 n 
+0000011899 00000 n 
+0000012020 00000 n 
+0000012141 00000 n 
+0000012262 00000 n 
+0000012383 00000 n 
+0000012504 00000 n 
+0000012625 00000 n 
+0000012747 00000 n 
+0000012869 00000 n 
+0000012991 00000 n 
+0000013113 00000 n 
+0000013235 00000 n 
+0000013357 00000 n 
+0000013479 00000 n 
+0000013601 00000 n 
+0000013723 00000 n 
+0000013845 00000 n 
+0000013968 00000 n 
+0000014091 00000 n 
+0000014214 00000 n 
+0000014337 00000 n 
+0000014459 00000 n 
+0000014582 00000 n 
+0000014705 00000 n 
+0000014828 00000 n 
+0000014951 00000 n 
 trailer << /Root 1 0 R /Size 110 /ID [<31415926535897932384626433832795><31415926535897932384626433832795>] >>
 startxref
-14773
+15074
 %%EOF
diff --git a/qpdf/qtest/qpdf/merge-multiple-labels.pdf b/qpdf/qtest/qpdf/merge-multiple-labels.pdf
new file mode 100644
index 0000000000000000000000000000000000000000..d767e760b4140eb379068c9858dfdd205467a9e6
GIT binary patch
literal 3452
zcmc&%OHUL*5LO5Yj*xgTo;<Wf4ko}%_dGWtM0so^yq4Wn4#;7E2FL8qn3-NgFB%h$
zCj0<T`~>6C#0v+An2?yr8BhEG5^rjC53@6DgAZ849(s4GyQ{vc`ReQ5?!s`s7x(E(
z_s8!WKNO5K6wE(S`umYuaF^-0J5MVS;*XQHYJ_HCo<Ee38p6nsjRpn~PHe8QVT&7$
z*vOE{pUh;*aJp@dPlzxPBH*}))bjJE6sbclb1T6zOe@r1<aqdWf@>(K`3yNo9rG4B
zB3*1X#Au4q5~D3fM~pc!VoiL_C2@F$Q6>ualt%Fx^;v{4uL(e#po^Y67_5pKXvo3@
z**Sv1S-}lqWs*XXMnNrH0LQ#g`2c3b4~$?3_au@IgM|`h;7f%U0C?ys16O=1E&+#@
zLB_L_k;R!`EHYkk8Cm=`E*2SQfs8C>$i*V#%#@MEtZfFenE6?r;kXS><rklp5yf58
z1VkimyeuLTx7DeLcx(v~Ig*L<_u?543H6X6HLVHH0x7H4d9T7KsB*sIGCE8bf<=(h
zaq2I#$H>&Vm_#h3ZdF-*8!6Mf&-AipJZK*+X?9Cj>)QJDw$7g$JBK?THgB%I-aIU~
zU7c84?`hk+)_3W~M28MSe6;;Yl7*Tj<rs7$Dx^*=dsQ0s7K5tmBXz_F6rR6~)EUpe
z=SN;@DAnef5PPn7IFUW!Bb9xeRpe&pH<sr2u)~n^%WCd#V;lco+o9Ha@GjKxNDiKr
z)usm@N`v3&n3IENmGg)|2AsDi;W*B!{bE7zicGhUw!ZuP=GE5STesV`zP4|vqdnVu
z<@W7wVds9!rB9cyY{_A>vX~O;KCP@!<}JY8B4v+6r%AU8Y|jIc{*G9Q;2l4Jlj{b~
zs!!5F;QPE4n9+<c^&%Wpl_{wRLImWl`Y%Ng63k<rTm&Ju36$m*A!WkBic*k^kZt>>
zMt;AWmj9(PEk#}p>5`%$VklbugDlh3O|*pSHVoa#Kgh4!um$XGun`Mr)L=6R<kny_
zZF#S)gS0oSa~vry*5q{<%l@z~$Hj&X$MW$Q*vx_KHQ1~ZY!1IsG_1=RQf@@Eq;&*4
zQoe-bq}+&3K!}dVAO;9gqs=tsb>;~%Y%TLXSm=5cI4=3!ych%w{=|rDe#v`5;r%0Z
zbQsO{>)3#j5DN(4<m?<&(J?Gy8M^N1#Lk%me_p|F^>FgKArs^xj*gY??vbgy@(Ztz
B%ai~B

literal 0
HcmV?d00001

diff --git a/qpdf/qtest/qpdf/merge-three-files-1.pdf b/qpdf/qtest/qpdf/merge-three-files-1.pdf
index 709f21eddac3ddabec4b24df17c871db89f2f882..d90b97d77f544248e0aba16c7d4e59005edd927c 100644
GIT binary patch
delta 1178
zcmZuwyGjH>5X5wU!DNyHP2B0}$IQTSprDbUaIt|uaKW*dPHZOlAs6@?ew4GjC;O<I
zU|4FZx|-_V)5Gum*K=w2og=r~)oZ(T?cTM=dY`ed#JK0_5>x3x8^O-Sq132*bvL(D
zE#iL;4U)H>+5X&JeO{Mf?0kRR!8OB&_sjyAWCP4%04#aLvZOVSd>%Z?+?axRAaVj@
zQii6<5^57G)XRC!tN!%_5+DYytqreJGC>r1M#zgAL7NGZVP6c0T)SC|nJoimg1l(Z
zAg2gvarUFO%;qjWfLKT%ehJvLaDo|&VlraOkqr4uT!MY-k_=*%oS;D^G|_+ytgMir
zN-DIDRn4PG3@A<)unU`B%Rz$X(|PP=S}qH?Ty?~-G^QDL#-c!jmho4Ne(up7-@i}p
OqoJ(LX7l*+)cgT;OXWrY

delta 1266
zcmZuwJ5Iwu5bb>hnr$LMm6@H-?n+T45Ku(|iH4R7P(%@}uYd&iK-_=>a46PmLTo>_
zu<YkI^TuzUzb`+oUU&U=8)DdO!ulbs_w{-R94eL?b|20!hNm)T_<%9bDE!yux^;<-
zW5>b~91F*8WADc*Pjgc3Gz_)q$4*w-3pvuqag7?f7|}kz-p_jR7-%@*IdtuYNJRj%
zVt}Q@fE5CaNz;<YT$)Bd6=snFM9m<~E-*BwgtbL<*)LL_@~VD4F)9+JOo=1U40(x=
zm(7>LLNyMp%gJfs-jOH__KSLk;-tvS4g*R_;Fc1Nwf$u8$`Oh+D%h`rL#t-ku{t`V
zX}*%?zvekOxTK|Kd104Ph5;?2hzSPR)WAWrT)%%Qk_bg|#NvXO|C4lQ0|%Y+@7nuQ
o7+f%1ZVI7sFOV6}3Iis>Uor7i<FJ2v+l7}d7VTE6o4ecY2aX>1QUCw|

diff --git a/qpdf/qtest/qpdf/merge-three-files-2.pdf b/qpdf/qtest/qpdf/merge-three-files-2.pdf
index c8b717e6b2561de3070102b71b3ed35d26d0f8d7..2d472ac691a6f14de9cad23fa0739e24e8e679ee 100644
GIT binary patch
delta 935
zcmZXSyGjH>5JfRDm~;^l11nk3XsWBa`T@&k8i@)Uih+WWkHB5yN&Em|{gDO#%pY*3
z$Hkew9SqZ#Q+4anU-dVCo-~*D50B4Fn$4)bdVg8cEpfTr(CHb~ixoMV&)ZK2EU13_
z*JP||$Jtmj--)3YR}@RCKJG97@zy}MkSj5FExI}SnKUAvxI6SpRrz7oq@bB(&_XoO
zk~q+Eh`X9|u6Q&<V<!eC&iCMmvydQR6e!xI2%NAExu?>yxP+i8bSFOZuCWA<T+9Mo
zUT+R24dZ;24QO?7SZ1kGCBv@NJ8)Oiu<NeDN{6F)Ys5usLd`S7c-pl<fnIu(;jX-<
rVRNm2d%Q8c2p{l;`Dkd8BF1Laj5AEZWRKVThaZ)wRnzJD^+ojy6lS<|

delta 793
zcmZuvv2g=24C}vjkuu-74oOg=G(gg36R)7g1NhFFA-(V1XQJ$okL*JKcvd<bD1adE
z^7VFkz5V<inq;5lzvk0C^@oTV2t%%fB~66otb`Q_!fNUoZ4_3iB%<~pu6QnG`=O>x
zrZtp#B}U$&zm$m)(KKi}17s^~UYM6*#0wt8O5?b!RBDFk=(?MRf>sAhWCn=5H3P4Y
zf!nZmWZpYs2P;l#p{`=>23?*agNB=}hU@t|oDRgD56)Ai6g-rB%MMmSDJ1dh_se;b
MNYnB7{`oQe0p@U-F8}}l