Merge pull request #336 from gittip/simplify_encoding_parsing

Simplify the encoding parsing routine
AspenWeb · May 1, 2014 · 2c08c44 · 2c08c44
2 parents 17254ce + 22c7ff3
commit 2c08c44
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 16 deletions.
diff --git a/aspen/resources/__init__.py b/aspen/resources/__init__.py
@@ -79,31 +79,25 @@ def get_declaration(line):
             return match.group(1)
         return None
 
-    encoding = b'ascii'
+    encoding = None
     fulltext = b''
     sio = StringIO(raw)
-    first = sio.readline()
-    second = sio.readline()
-    for i, line in enumerate([first, second]):
+    for line in (sio.readline(), sio.readline()):
         potential = get_declaration(line)
-        if potential is not None:
+        if encoding is not None:
+            # If we found a match in the first line, skip the second. This
+            # matches Python's observed behavior.
+            pass
+        elif potential is not None:
             encoding = potential
-
             # Munge the encoding line. We want to preserve the line numbering,
             # but when we exec down the line Python will complain if we have a
             # coding: line in a unicode.
-            fulltext += line.split(b'#')[0] + b'# encoding set to {0}\n'.format(encoding)
-
-            # If we find a match in the first line, we want to skip the second.
-            # This matches Python's observed behavior.
-            if i == 0:
-                fulltext += second
-                break
-        else:
-            fulltext += line
+            line = line.split(b'#')[0] + b'# encoding set to {0}\n'.format(encoding)
+        fulltext += line
     fulltext += sio.read()
     sio.close()
-    return fulltext.decode(encoding)
+    return fulltext.decode(encoding or b'ascii')
 
 
 # Core loaders

diff --git a/tests/test_unicode.py b/tests/test_unicode.py
@@ -122,6 +122,7 @@ def test_decode_raw_cant_take_encoding_from_bad_line_formats():
               , b'  coding : utf8'
               , b'encoding : utf8'
               , b'  flubcoding =utf8'
+              , b'coding: '
                ]
     for fmt in formats:
         def test():