Add QPDFObjectHandle::parse for strings with context

5 files changed, 40 insertions, 1 deletions

diff --git a/ChangeLog b/ChangeLog
index 7b1db1f2..2009162c 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,9 @@
+2021-02-15  Jay Berkenbilt  <ejb@ql.org>
+
+	* Add a version of QPDFObjectHandle::parse that takes a QPDF* as
+	context so that it can parse strings containing indirect object
+	references.
+
 2021-02-14  Jay Berkenbilt  <ejb@ql.org>
 
 	* Add new versions of QPDFObjectHandle::replaceStreamData that
diff --git a/include/qpdf/QPDFObjectHandle.hh b/include/qpdf/QPDFObjectHandle.hh
index cb4c5be6..efcd653a 100644
--- a/include/qpdf/QPDFObjectHandle.hh
+++ b/include/qpdf/QPDFObjectHandle.hh
@@ -379,6 +379,20 @@ class QPDFObjectHandle
     static QPDFObjectHandle parse(std::string const& object_str,
                                   std::string const& object_description = "");
 
+    // Construct an object of any type from a string representation of
+    // the object. Indirect object syntax (obj gen R) is allowed and
+    // will create indirect references within the passed-in context.
+    // If object_description is provided, it will appear in the
+    // message of any QPDFExc exception thrown for invalid syntax.
+    // Note that you can't parse an indirect object reference all by
+    // itself as parse will stop at the end of the first complete
+    // object, which will just be the first number and will report
+    // that there is trailing data at the end of the string.
+    QPDF_DLL
+    static QPDFObjectHandle parse(QPDF* context,
+                                  std::string const& object_str,
+                                  std::string const& object_description = "");
+
     // Construct an object as above by reading from the given
     // InputSource at its current position and using the tokenizer you
     // supply.  Indirect objects and encrypted strings are permitted.
diff --git a/libqpdf/QPDFObjectHandle.cc b/libqpdf/QPDFObjectHandle.cc
index d4796498..8f7399f2 100644
--- a/libqpdf/QPDFObjectHandle.cc
+++ b/libqpdf/QPDFObjectHandle.cc
@@ -1693,12 +1693,20 @@ QPDFObjectHandle
 QPDFObjectHandle::parse(std::string const& object_str,
                         std::string const& object_description)
 {
+    return parse(nullptr, object_str, object_description);
+}
+
+QPDFObjectHandle
+QPDFObjectHandle::parse(QPDF* context,
+                        std::string const& object_str,
+                        std::string const& object_description)
+{
     PointerHolder<InputSource> input =
         new BufferInputSource("parsed object", object_str);
     QPDFTokenizer tokenizer;
     bool empty = false;
     QPDFObjectHandle result =
-        parse(input, object_description, tokenizer, empty, 0, 0);
+        parse(input, object_description, tokenizer, empty, 0, context);
     size_t offset = QIntC::to_size(input->tell());
     while (offset < object_str.length())
     {
diff --git a/manual/qpdf-manual.xml b/manual/qpdf-manual.xml
index ae085d6e..508e0ec9 100644
--- a/manual/qpdf-manual.xml
+++ b/manual/qpdf-manual.xml
@@ -5196,6 +5196,14 @@ print "\n";
         </listitem>
         <listitem>
          <para>
+          Add a version of
+          <function>QPDFObjectHandle::parse</function> that takes a
+          <classname>QPDF</classname> pointer as context so that it
+          can parse strings containing indirect object references.
+         </para>
+        </listitem>
+        <listitem>
+         <para>
           Re-implement <classname>QPDFNameTreeObjectHelper</classname>
           and <classname>QPDFNumberTreeObjectHelper</classname> to be
           more efficient, add an iterator-based API, give them the
diff --git a/qpdf/test_driver.cc b/qpdf/test_driver.cc
index d7c9a352..2ad5bd62 100644
--- a/qpdf/test_driver.cc
+++ b/qpdf/test_driver.cc
@@ -1319,6 +1319,9 @@ void runtest(int n, char const* filename1, char const* arg2)
             std::cout << "trailing data: " << e.what()
                       << std::endl;
         }
+        assert(QPDFObjectHandle::parse(
+                   &pdf, "[1 0 R]", "indirect test").unparse() ==
+               "[ 1 0 R ]");
     }
     else if (n == 32)
     {