incorporated some patches by Andre Auzi

git-svn-id: https://pdfminerr.googlecode.com/svn/trunk/pdfminer@180 1aa58f4a-7d42-0410-adbc-911cccaed67c

pdfminer/converter.py

@@ -52,8 +52,14 @@ class PDFPageAggregator(PDFTextDevice):
 
     def render_image(self, name, stream):
         assert isinstance(self.cur_item, LTFigure)
-        item = LTImage(name, stream.get('Filter'),
-                       (stream['Width'], stream['Height']),
+        ismask = stream.get_any(('IM', 'ImageMask'))
+        bits = stream.get_any(('BPC', 'BitsPerCompoment'), 1)
+        csp = stream.get_any(('CS', 'ColorSpace'))
+        if not isinstance(csp, list):
+            csp = [csp]
+        item = LTImage(name, stream.get_any(('F', 'Filter')),
+                       (stream.get_any(('W', 'Width')),
+                        stream.get_any(('H', 'Height'))),
                        (self.cur_item.x0, self.cur_item.y0,
                         self.cur_item.x1, self.cur_item.y1),
                        stream.get_rawdata())

pdfminer/pdffont.py

@@ -338,8 +338,10 @@ class PDFFont(object):
         self.fontname = descriptor.get('FontName', 'unknown')
         if isinstance(self.fontname, PSLiteral):
             self.fontname = literal_name(self.fontname)
+        self.flags = int_value(descriptor.get('Flags', 0))
         self.ascent = num_value(descriptor.get('Ascent', 0))
         self.descent = num_value(descriptor.get('Descent', 0))
+        self.italic_angle = num_value(descriptor.get('ItalicAngle', 0))
         self.default_width = default_width or descriptor.get('MissingWidth', 0)
         self.leading = num_value(descriptor.get('Leading', 0))
         self.bbox = list_value(descriptor.get('FontBBox', (0,0,0,0)))

pdfminer/pdftypes.py

@@ -173,6 +173,11 @@ class PDFStream(PDFObject):
         return self.attrs[name]
     def get(self, name, default=None):
         return self.attrs.get(name, default)
+    def get_any(self, names, default=None):
+        for name in names:
+            if name in self.attrs:
+                return self.attrs[name]
+        return default
 
     def decomp(self,data):
         buf = data
@@ -193,9 +198,8 @@ class PDFStream(PDFObject):
         if self.decipher:
             # Handle encryption
             data = self.decipher(self.objid, self.genno, data)
-        try:
-            filters = self['Filter']
-        except KeyError:
+        filters = self.get_any(('F', 'Filter'))
+        if not filters:
             self.rawdata = self.data = data
             return
         if not isinstance(filters, list):
@@ -218,18 +222,13 @@ class PDFStream(PDFObject):
             else:
                 raise PDFNotImplementedError('Unsupported filter: %r' % f)
             # apply predictors
-            try:
-                params = self['DP']
-            except KeyError:
-                params = self.get('DecodeParms', {})
-            if 'Predictor' in params:
+            params = self.get_any(('DP', 'DecodeParms', 'FDecodeParms'), {})
+            if 'Predictor' in params and 'Columns' in params:
                 pred = int_value(params['Predictor'])
+                columns = int_value(params['Columns'])
                 if pred:
                     if pred != 12:
                         raise PDFNotImplementedError('Unsupported predictor: %r' % pred)
-                    if 'Columns' not in params:
-                        raise PDFValueError('Columns undefined for predictor=12')
-                    columns = int_value(params['Columns'])
                     buf = ''
                     ent0 = '\x00' * columns
                     for i in xrange(0, len(data), columns+1):