use string.punctuation and unicodedata

cooperhewitt · Aug 10, 2012 · 7558ff8 · 7558ff8
1 parent 384c83d
commit 7558ff8
Showing 1 changed file with 21 additions and 16 deletions.
diff --git a/bin/utils.py b/bin/utils.py
@@ -1,5 +1,7 @@
-import os.path
 import pprint
+import os.path
+import string
+import unicodedata
 
 def dumper(data):
     print pprint.pformat(data)
@@ -18,23 +20,26 @@ def id2path(id):
 
     return os.path.join(*parts)
 
-def clean_meta_name(name):
+def clean_meta_name(name, allow_punctuation=[]):
-
-    # sudo make me better
 
     name = name.strip()
-    name = name.replace(" ", "-")
-    name = name.replace("?", "")
-    name = name.replace("&", "")
-    name = name.replace(":", "")
-    name = name.replace("/", "-")
-    name = name.replace(",", "-")
-    name = name.replace("'", "-")
-    name = name.replace("(", "-")
-    name = name.replace(")", "")
-    name = name.replace("`", "")
-    name = name.replace("--", "-")
-    name = name.replace("..", ".")
     name = name.lower()
+
+    name = remove_accents(name)
+
+    for c in string.punctuation:
 
+        if c in allow_punctuation:
+            continue
+
+        name = name.replace(c, "")
+
+    name = name.replace(" ", "-")
+    name = name.replace("--", "-")
+
     return name
+
+def remove_accents(input_str):
+    nkfd_form = unicodedata.normalize('NFKD', unicode(input_str))
+    only_ascii = nkfd_form.encode('ASCII', 'ignore')
+    return only_ascii