p4ul · November 6, 2013 07:12 · Nov 6, 2013
diff --git a/avg_line_length.py b/avg_line_length.py
@@ -0,0 +1,77 @@
+#!/usr/bin/python
+
+import texttable as tt
+import fnmatch
+import os
+import operator
+from collections import Counter
+import mimetypes
+
+def file_len(fname):
+  linecount = 0
+  linelength = 0
+  i = 0
+  with open(fname) as f:
+    for i, l in enumerate(f):
+      # print len(l)
+      linelength += len(l)
+      pass
+  linecount = i + 1
+  return linelength / linecount
+
+
+
+matches = []
+for root, dirnames, filenames in os.walk('sites'):
+# ignore .git and .svn
+  if root.find('.'):
+    pass
+
+for filename in fnmatch.filter(filenames, '*.*'):
+  mimetype = str(mimetypes.guess_type(filename)[0])
+
+  # ignore images
+  if mimetype.find('image') >= 0 :
+    continue
+
+  # ignore minified files
+  if filename.find('.min.') >= 0 :
+    continue
+
+# print filename + " " + mimetype
+fileName, fileExtension = os.path.splitext(filename)
+line_length = file_len(os.path.join(os.getcwd(), root,filename))
+
+#ignore crazy long lines
+if line_length > 120:
+  continue
+matches.append((fileExtension,line_length))
+
+filecounts = {}
+linecounts = {}
+
+for lang, linelength in matches:
+
+  if lang in filecounts :
+    filecounts[lang] = filecounts[lang] + 1
+    linecounts[lang] = linecounts[lang] + linelength
+  else :
+    filecounts[lang] = 1
+    linecounts[lang] = linelength
+
+
+tabledata = []
+
+for i in linecounts:
+  tabledata.append((i, filecounts[i], linecounts[i]/filecounts[i]))
+
+
+# sort by avg line length descending
+tabledata = sorted(tabledata, key=operator.itemgetter(2), reverse=True)
+
+
+tab = tt.Texttable()
+tab.add_rows(tabledata)
+tab.set_cols_align(['r','r', 'r'])
+tab.header(['extension', 'number of files', 'avg line length'])
+print tab.draw()