Implement QPDFObjectHandle::parse

Move object parsing code from QPDF to QPDFObjectHandle and
parameterize the parts of it that are specific to a QPDF object.
Provide a version that can't handle indirect objects and that can be
called on an arbitrary string.

A side effect of this change is that the offset used when reporting
invalid stream length has changed, but since the new value seems like
a better value than the old one, the test suite has been updated
rather than making the code backward compatible.  This only effects
the offset reported for invalid streams that lack /Length or have an
invalid /Length key.

Updated some test code and exmaples to use QPDFObjectHandle::parse.

Supporting changes include adding a BufferInputSource constructor that
takes a string.

3 files changed, 74 insertions, 5 deletions

diff --git a/include/qpdf/BufferInputSource.hh b/include/qpdf/BufferInputSource.hh
index 63c14def..48f6e3ac 100644
--- a/include/qpdf/BufferInputSource.hh
+++ b/include/qpdf/BufferInputSource.hh
@@ -9,6 +9,8 @@ class BufferInputSource: public InputSource
   public:
     BufferInputSource(std::string const& description, Buffer* buf,
                       bool own_memory = false);
+    BufferInputSource(std::string const& description,
+                      std::string const& contents);
     virtual ~BufferInputSource();
     virtual qpdf_offset_t findAndSkipNextEOL();
     virtual std::string const& getName() const;
diff --git a/include/qpdf/QPDF.hh b/include/qpdf/QPDF.hh
index e6ff75b4..dc6e9090 100644
--- a/include/qpdf/QPDF.hh
+++ b/include/qpdf/QPDF.hh
@@ -531,6 +531,23 @@ class QPDF
         std::map<ObjGen, QPDFObjectHandle> foreign_streams;
     };
 
+    class StringDecrypter: public QPDFObjectHandle::StringDecrypter
+    {
+        friend class QPDF;
+
+      public:
+        StringDecrypter(QPDF* qpdf, int objid, int gen);
+        virtual ~StringDecrypter()
+        {
+        }
+        virtual void decryptString(std::string& val);
+
+      private:
+        QPDF* qpdf;
+        int objid;
+        int gen;
+    };
+
     void parse(char const* password);
     void warn(QPDFExc const& e);
     void setTrailer(QPDFObjectHandle obj);
@@ -547,10 +564,6 @@ class QPDF
     QPDFObjectHandle readObject(
 	PointerHolder<InputSource>, std::string const& description,
 	int objid, int generation, bool in_object_stream);
-    QPDFObjectHandle readObjectInternal(
-	PointerHolder<InputSource> input, int objid, int generation,
-	bool in_object_stream,
-	bool in_array, bool in_dictionary);
     size_t recoverStreamLength(
 	PointerHolder<InputSource> input, int objid, int generation,
 	qpdf_offset_t stream_offset);
diff --git a/include/qpdf/QPDFObjectHandle.hh b/include/qpdf/QPDFObjectHandle.hh
index 22ded37e..a1819d99 100644
--- a/include/qpdf/QPDFObjectHandle.hh
+++ b/include/qpdf/QPDFObjectHandle.hh
@@ -18,6 +18,7 @@
 
 #include <qpdf/PointerHolder.hh>
 #include <qpdf/Buffer.hh>
+#include <qpdf/InputSource.hh>
 
 #include <qpdf/QPDFObject.hh>
 
@@ -25,6 +26,7 @@ class Pipeline;
 class QPDF;
 class QPDF_Dictionary;
 class QPDF_Array;
+class QPDFTokenizer;
 
 class QPDFObjectHandle
 {
@@ -57,6 +59,18 @@ class QPDFObjectHandle
 				       Pipeline* pipeline) = 0;
     };
 
+    // This class is used by parse to decrypt strings when reading an
+    // object that contains encrypted strings.
+    class StringDecrypter
+    {
+      public:
+        QPDF_DLL
+        virtual ~StringDecrypter()
+        {
+        }
+        virtual void decryptString(std::string& val) = 0;
+    };
+
     QPDF_DLL
     QPDFObjectHandle();
     QPDF_DLL
@@ -95,6 +109,30 @@ class QPDFObjectHandle
 
     // Public factory methods
 
+    // Construct an object of any type from a string representation of
+    // the object.  Throws QPDFExc with an empty filename and an
+    // offset into the string if there is an error.  Any indirect
+    // object syntax (obj gen R) will cause a logic_error exception to
+    // be thrown.  If object_description is provided, it will appear
+    // in the message of any QPDFExc exception thrown for invalid
+    // syntax.
+    QPDF_DLL
+    static QPDFObjectHandle parse(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.
+    // This method is intended to be called by QPDF for parsing
+    // objects that are ready from the object's input stream.
+    QPDF_DLL
+    static QPDFObjectHandle parse(PointerHolder<InputSource> input,
+                                  std::string const& object_description,
+                                  QPDFTokenizer&, bool& empty,
+                                  StringDecrypter* decrypter,
+                                  QPDF* context);
+
+    // Type-specific factories
     QPDF_DLL
     static QPDFObjectHandle newNull();
     QPDF_DLL
@@ -124,7 +162,8 @@ class QPDFObjectHandle
     // object.  A subsequent call must be made to replaceStreamData()
     // to provide data for the stream.  The stream's dictionary may be
     // retrieved by calling getDict(), and the resulting dictionary
-    // may be modified.
+    // may be modified.  Alternatively, you can create a new
+    // dictionary and call replaceDict to install it.
     QPDF_DLL
     static QPDFObjectHandle newStream(QPDF* qpdf);
 
@@ -303,6 +342,15 @@ class QPDFObjectHandle
     bool pipeStreamData(Pipeline*, bool filter,
 			bool normalize, bool compress);
 
+    // Replace a stream's dictionary.  The new dictionary must be
+    // consistent with the stream's data.  This is most appropriately
+    // used when creating streams from scratch that will use a stream
+    // data provider and therefore start with an empty dictionary.  It
+    // may be more convenient in this case than calling getDict and
+    // modifying it for each key.  The pdf-create example does this.
+    QPDF_DLL
+    void replaceDict(QPDFObjectHandle);
+
     // Replace this stream's stream data with the given data buffer,
     // and replace the /Filter and /DecodeParms keys in the stream
     // dictionary with the given values.  (If either value is empty,
@@ -489,6 +537,12 @@ class QPDFObjectHandle
     void dereference();
     void makeDirectInternal(std::set<int>& visited);
     void releaseResolved();
+    static QPDFObjectHandle parseInternal(
+        PointerHolder<InputSource> input,
+        std::string const& object_description,
+        QPDFTokenizer& tokenizer, bool& empty,
+        StringDecrypter* decrypter, QPDF* context,
+        bool in_array, bool in_dictionary);
 
     bool initialized;