Julianna Kissane Lab Compression

text_codecs/alphanumeric.py

@@ -1,10 +1,29 @@
 import string
 import codecs
-from custom_codecs.register import register_codec
+#from text_codecs.register import register_codec
 from easybits import Bits
 
 allowed_characters = string.ascii_letters + string.digits
 
+import codecs
+
+def register_codec(encode, decode, name):
+    """Registers a codec so that it can later be used to encode
+    or decode strings and bytes.
+    """
+    def encode_wrapper(text):
+        return encode(text), len(text)
+
+    def decode_wrapper(data):
+        return decode(data), len(data)
+
+    def search_for_codec(query):
+        if query == name:
+            return codecs.CodecInfo(encode_wrapper, decode_wrapper, name=name)
+
+    codecs.register(search_for_codec)
+
+
 def encode(text):
     """A (very) lossy encoder which only saves ASCII letters, numbers, and spaces.
     Everything else is discarded. All whitespace (e.g. tabs) is converted into spaces.

text_codecs/ascii7.py

@@ -1,6 +1,25 @@
-from custom_codecs.register import register_codec
+#from text_codecs.register import register_codec
 from easybits import Bits
 
+import codecs
+
+def register_codec(encode, decode, name):
+    """Registers a codec so that it can later be used to encode
+    or decode strings and bytes.
+    """
+    def encode_wrapper(text):
+        return encode(text), len(text)
+
+    def decode_wrapper(data):
+        return decode(data), len(data)
+
+    def search_for_codec(query):
+        if query == name:
+            return codecs.CodecInfo(encode_wrapper, decode_wrapper, name=name)
+
+    codecs.register(search_for_codec)
+
+
 def encode(text):
     """An encoder which only handles ASCII: non-ASCII characters
     are replaced with '?'. Once all the characters are ASCII, this encoder

text_codecs/mycodec.py

@@ -0,0 +1,12 @@
+"This simple codec converts all text to Lowercase."
+
+def encode(text):
+    text = text.lower()
+    return text.encode("utf-8")
+
+def decode(data):
+    return bytes(data).decode("utf-8").lower()
+
+from register import register_codec
+register_codec(encode, decode, "mycodec")
+