Counting lines in files

Here’s silly (and long) Python script I wrote a while back to count the number of lines in files recursively through a dir. (I guess I was fed up with ‘find ../ -iname “*cpp” | xargs wc -l” or just utterly bored or using Windows…)

#!/usr/bin/python
#
# Usage:
#   ./count_lines.py [path_to_dir_or_file]

__author__ = "Rui Barbosa Martins (ruibmartins@gmail.com)"

import optparse
import os.path
import sys

def getNumberOfLines(filePath):
  fp = file(filePath, "r");
  numberOfLines = len(fp.readlines())
  fp.close()
  return numberOfLines

def visit((fileTypesIncluded, files), dirname, names):
  for f in names:    
    filePath = os.path.join(dirname, f)
    if (fileTypesIncluded == ["*"] or 
        filter(lambda fe: f.endswith(fe), fileTypesIncluded)) and
        os.path.isfile(filePath):
      files[filePath] = getNumberOfLines(filePath)

def main(startPath, fileTypesIncluded):
  if not os.path.exists(startPath):
    print "Error: Path [%s] does not exist." % (startPath)
    sys.exit(-1)
  elif os.path.isfile(startPath):
    files = {startPath: getNumberOfLines(startPath)}
  else:
    fileTypes = "|".join(fileTypesIncluded)
    absPath = os.path.abspath(startPath)
    print "Searching for extensions '%s' in '%s'." % (fileTypes, absPath)    
    files = {}
    os.path.walk(startPath, visit, (fileTypesIncluded, files))

  keys = files.keys()
  keys.sort()
  total = 0
  longestLength = 0
  groups = {}

  for key in keys:
    if longestLength < len(key):
      longestLength = len(key)      

  for key in keys:
    spaces = " " * (longestLength - len(key))
    print "%s%s %d" % (key, spaces , files[key])
    total = total + files[key]

  if len(keys) > 1:
    print "Total lines of code: %d" % (total)

def parseArgs():
  usage = "Usage: %prog [Options] FILE_OR_DIRECTORY"
  parser = optparse.OptionParser(usage=usage)
  parser.add_option("-f", "--file_extensions", dest="file_extensions",
                    help="File extensions to count in. (comma separated)", 
                    metavar="FILE_TYPES",
                    default=[".*"])
  (options, args) = parser.parse_args()
  fe = options.file_extensions
  if not args:
    path = "."
  elif len(args) == 1:
    path = args[0]
  else:
    parser.print_help()
    print "Error: Too many paths provided. Only one expected."
    sys.exit(0)

  if type(fe) == str:
    fe = map(lambda s: s.strip(), fe.split(","))
  if not fe or filter(lambda s: "*" in s, fe):
    fe = ["*"]
  return path, fe

if __name__ == "__main__":
  main(*parseArgs())

Advertisements
This entry was posted in Programming, Software. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s