Adding PDFFormatter and kernel side handling of PDF display data.

IPython/core/display.py

@@ -271,6 +271,24 b' def display_javascript(*objs, **kwargs):'
     """
     _display_mimetype('application/javascript', objs, **kwargs)
 
+
+def display_pdf(*objs, **kwargs):
+    """Display the PDF representation of an object.
+
+    Parameters
+    ----------
+    objs : tuple of objects
+        The Python objects to display, or if raw=True raw javascript data to
+        display.
+    raw : bool
+        Are the data objects raw data or Python objects that need to be
+        formatted before display? [default: False]
+    metadata : dict (optional)
+        Metadata to be associated with the specific mimetype output.
+    """
+    _display_mimetype('application/pdf', objs, **kwargs)
+
+
 #-----------------------------------------------------------------------------
 # Smart classes
 #-----------------------------------------------------------------------------

IPython/core/formatters.py

@@ -93,6 +93,7 b' class DisplayFormatter(Configurable):'
             HTMLFormatter,
             SVGFormatter,
             PNGFormatter,
+            PDFFormatter,
             JPEGFormatter,
             LatexFormatter,
             JSONFormatter,
@@ -116,6 +117,7 b' class DisplayFormatter(Configurable):'
         * text/latex
         * application/json
         * application/javascript
+        * application/pdf
         * image/png
         * image/jpeg
         * image/svg+xml
@@ -766,11 +768,29 b' class JavascriptFormatter(BaseFormatter):'
 
     print_method = ObjectName('_repr_javascript_')
 
+
+class PDFFormatter(BaseFormatter):
+    """A PDF formatter.
+
+    To defined the callables that compute to PDF representation of your
+    objects, define a :meth:`_repr_pdf_` method or use the :meth:`for_type`
+    or :meth:`for_type_by_name` methods to register functions that handle
+    this.
+
+    The return value of this formatter should be raw PDF data, *not*
+    base64 encoded.
+    """
+    format_type = Unicode('application/pdf')
+
+    print_method = ObjectName('_repr_pdf_')
+
+
 FormatterABC.register(BaseFormatter)
 FormatterABC.register(PlainTextFormatter)
 FormatterABC.register(HTMLFormatter)
 FormatterABC.register(SVGFormatter)
 FormatterABC.register(PNGFormatter)
+FormatterABC.register(PDFFormatter)
 FormatterABC.register(JPEGFormatter)
 FormatterABC.register(LatexFormatter)
 FormatterABC.register(JSONFormatter)
@@ -789,6 +809,7 b' def format_display_data(obj, include=None, exclude=None):'
     * text/latex
     * application/json
     * application/javascript
+    * application/pdf
     * image/png
     * image/jpeg
     * image/svg+xml

IPython/core/tests/test_formatters.py

@@ -8,7 +8,9 b' except:'
     numpy = None
 import nose.tools as nt
 
-from IPython.core.formatters import PlainTextFormatter, HTMLFormatter, _mod_name_key
+from IPython.core.formatters import (
+    PlainTextFormatter, HTMLFormatter, PDFFormatter, _mod_name_key
+)
 from IPython.utils.io import capture_output
 
 class A(object):
@@ -279,4 +281,11 b' def test_warn_error_pretty_method():'
     nt.assert_in("text/plain", captured.stderr)
     nt.assert_in("argument", captured.stderr)
 
+class MakePDF(object):
+    def _repr_pdf_(self):
+        return 'PDF'
 
+def test_pdf_formatter():
+    pdf = MakePDF()
+    f = PDFFormatter()
+    nt.assert_equal(f(pdf), 'PDF')

IPython/utils/jsonutil.py

@@ -119,6 +119,8 b" PNG64 = b'iVBORw0KG'"
 JPEG = b'\xff\xd8'
 # front of JPEG base64-encoded
 JPEG64 = b'/9'
+# front of PDF base64-encoded
+PDF64 = b'JVBER'
 
 def encode_images(format_dict):
     """b64-encodes images in a displaypub format dict
@@ -136,7 +138,7 b' def encode_images(format_dict):'
 
     format_dict : dict
         A copy of the same dictionary,
-        but binary image data ('image/png' or 'image/jpeg')
+        but binary image data ('image/png', 'image/jpeg' or 'application/pdf')
         is base64-encoded.
 
     """
@@ -156,6 +158,13 b' def encode_images(format_dict):'
             jpegdata = encodebytes(jpegdata)
         encoded['image/jpeg'] = jpegdata.decode('ascii')
 
+    pdfdata = format_dict.get('application/pdf')
+    if isinstance(pdfdata, bytes):
+        # make sure we don't double-encode
+        if not pdfdata.startswith(PDF64):
+            pdfdata = encodebytes(pdfdata)
+        encoded['application/pdf'] = pdfdata.decode('ascii')
+
     return encoded
 
 

IPython/utils/tests/test_jsonutil.py

@@ -69,10 +69,12 b' def test_encode_images():'
     # invalid data, but the header and footer are from real files
     pngdata = b'\x89PNG\r\n\x1a\nblahblahnotactuallyvalidIEND\xaeB`\x82'
     jpegdata = b'\xff\xd8\xff\xe0\x00\x10JFIFblahblahjpeg(\xa0\x0f\xff\xd9'
+    pdfdata = b'%PDF-1.\ntrailer<</Root<</Pages<</Kids[<</MediaBox[0 0 3 3]>>]>>>>>>'
     
     fmt = {
         'image/png'  : pngdata,
         'image/jpeg' : jpegdata,
+        'application/pdf' : pdfdata
     }
     encoded = encode_images(fmt)
     for key, value in iteritems(fmt):