Allow numeric range to be omitted qpdf --pages

Detect a missing page range and assume 1-z.

Allow numeric range to be omitted qpdf --pages
Detect a missing page range and assume 1-z.
Jay Berkenbilt
1 parent 88bacb64
Showing 6 changed files with 714 additions and 8 deletions
ChangeLog
manual/qpdf-manual.xml
qpdf/qpdf.cc
qpdf/qpdf.testcov
qpdf/qtest/qpdf.test
qpdf/qtest/qpdf/merge-implicit-ranges.pdf
+2013-07-07  Jay Berkenbilt  <ejb@ql.org>
+
+	* qpdf: allow omission of range in --pages.  If range is omitted
+	such that an argument that is supposed to be a range is an invalid
+	range and a valid file name, the range of 1-z is assumed.  This
+	makes it possible to merge a bunch of files with something like
+	qpdf --empty out.pdf --pages *.pdf --
+
 2013-06-15  Jay Berkenbilt  <ejb@ql.org>
 	* Handle some additional broken files with missing /ID in trailer
@@ -614,7 +614,7 @@ make
     file is given as the primary input file is used as the starting
     point, but its pages are replaced with pages as specified.
-    <programlisting><option>--pages <replaceable>input-file</replaceable> [ <replaceable>--password=password</replaceable> ] <replaceable>page-range</replaceable> [ ... ] --</option>
+    <programlisting><option>--pages <replaceable>input-file</replaceable> [ <replaceable>--password=password</replaceable> ] [ <replaceable>page-range</replaceable> ] [ ... ] --</option>
 </programlisting>
     Multiple input files may be specified.  Each one is given as the
     name of the input file, an optional password (if required to open
@@ -636,6 +636,15 @@ make
     primary input.
    </para>
    <para>
+    Starting with qpdf 4.2.0, it is possible to omit the page range.
+    If qpdf sees a value in the place where it expects a page range
+    and that value is not a valid range but is a valid file name, qpdf
+    will implicitly use the range <literal>1-z</literal>, meaning that
+    it will include all pages in the file.  This makes it possible to
+    easily combine all pages in a set of files with a command like
+    <command>qpdf --empty out.pdf --pages *.pdf --</command>.
+   </para>
+   <para>
     It is not presently possible to specify the same page from the
     same file directly more than once, but you can make this work by
     specifying two different paths to the same file (such as by
@@ -163,7 +163,7 @@ These options allow pages to be selected from one or more PDF files.\n\
 Whatever file is given as the primary input file is used as the\n\
 starting point, but its pages are replaced with pages as specified.\n\
 \n\
---pages file [ --password=password ] page-range ... --\n\
+--pages file [ --password=password ] [ page-range ] ... --\n\
 \n\
 For each file that pages should be taken from, specify the file, a\n\
 password needed to open the file (if any), and a page range.  The\n\
@@ -183,6 +183,10 @@ pages to appear in reverse.  Repeating a number will cause an error, but\n\
 the manual discusses a workaround should you really want to include the\n\
 same page twice.\n\
 \n\
+If the page range is omitted, the range of 1-z is assumed.  qpdf decides\n\
+that the page range is omitted if the range argument is either -- or a\n\
+valid file name and not a valid range.\n\
+\n\
 See the manual for examples and a discussion of additional subtleties.\n\
 \n\
 \n\
@@ -354,7 +358,8 @@ static void show_encryption(QPDF&amp; pdf)
     }
 }
-static std::vector<int> parse_numrange(char const* range, int max)
+static std::vector<int> parse_numrange(char const* range, int max,
+                                       bool throw_error = false)
 {
     std::vector<int> result;
     char const* p = range;
@@ -436,7 +441,9 @@ static std::vector&lt;int&gt; parse_numrange(char const* range, int max)
         for (size_t i = 0; i < work.size(); i += 2)
         {
             int num = work[i];
-            if ((num < 1) || (num > max))
+            // max == 0 means we don't know the max and are just
+            // testing for valid syntax.
+            if ((max > 0) && ((num < 1) || (num > max)))
             {
                 throw std::runtime_error(
                     "number " + QUtil::int_to_string(num) + " out of range");
@@ -480,6 +487,10 @@ static std::vector&lt;int&gt; parse_numrange(char const* range, int max)
     }
     catch (std::runtime_error e)
     {
+        if (throw_error)
+        {
+            throw e;
+        }
         if (p)
         {
             usage("error at * in numeric range " +
@@ -839,9 +850,9 @@ parse_pages_options(
         {
             usage("insufficient arguments to --pages");
         }
-        char* file = argv[cur_arg++];
-        char* password = 0;
-        char* range = argv[cur_arg++];
+        char const* file = argv[cur_arg++];
+        char const* password = 0;
+        char const* range = argv[cur_arg++];
         if (strncmp(range, "--password=", 11) == 0)
         {
             // Oh, that's the password, not the range
@@ -853,6 +864,44 @@ parse_pages_options(
             range = argv[cur_arg++];
         }
+        // See if the user omitted the range entirely, in which case
+        // we assume "1-z".
+        bool range_omitted = false;
+        if (strcmp(range, "--") == 0)
+        {
+            // The filename or password was the last argument
+            QTC::TC("qpdf", "qpdf pages range omitted at end");
+            range_omitted = true;
+        }
+        else
+        {
+            try
+            {
+                parse_numrange(range, 0, true);
+            }
+            catch (std::runtime_error& e1)
+            {
+                // The range is invalid.  Let's see if it's a file.
+                try
+                {
+                    fclose(QUtil::safe_fopen(range, "rb"));
+                    // Yup, it's a file.
+                    QTC::TC("qpdf", "qpdf pages range omitted in middle");
+                    range_omitted = true;
+                }
+                catch (std::runtime_error& e2)
+                {
+                    // Ignore.  The range is invalid and not a file.
+                    // We'll get an error message later.
+                }
+            }
+        }
+        if (range_omitted)
+        {
+            --cur_arg;
+            range = "1-z";
+        }
+
         result.push_back(PageSpec(file, password, range));
     }
     return result;
@@ -265,3 +265,5 @@ QPDF not caching overridden objstm object 0
 QPDFWriter original obj non-zero gen 0
 QPDF_optimization indirect outlines 0
 QPDF xref space 2
+qpdf pages range omitted at end 0
+qpdf pages range omitted in middle 0
@@ -567,7 +567,7 @@ foreach my $d (@nrange_tests)
 show_ntests();
 # ----------
 $td->notify("--- Merging and Splitting ---");
-$n_tests += 6;
+$n_tests += 8;
 # Select pages from the same file multiple times including selecting
 # twice from an encrypted file and specifying the password only the
@@ -612,6 +612,16 @@ $td-&gt;runtest(&quot;avoid respecification of password&quot;,
 $td->runtest("check output",
              {$td->FILE => "a.pdf"},
              {$td->FILE => "pages-copy-encryption.pdf"});
+$td->runtest("merge with implicit ranges",
+             {$td->COMMAND =>
+                  "qpdf --empty a.pdf" .
+                  " --pages minimal.pdf 20-pages.pdf --password=user" .
+                  " page-labels-and-outlines.pdf --" .
+                  " --static-id"},
+             {$td->STRING => "", $td->EXIT_STATUS => 0});
+$td->runtest("check output",
+             {$td->FILE => "a.pdf"},
+             {$td->FILE => "merge-implicit-ranges.pdf"});
 show_ntests();
 # ----------
 $td->notify("--- PDF From Scratch ---");