CodeCounter.py for Python

#!/usr/bin/env python
	
# Count code lines, comment lines, blank lines ( show percentage of each )
# Count imports, classes, functions, try statements, print statements,
#       if statements, variables, variable assignments
# Reports count/percentage of each item on the console

# This program cannot handle Doc Strings as of yet, and multiple
# variables on a single line confuses it a bit (so it ignores them).
# I am working on fixing these and other issues.
#---------------------------------------------------------------------

#(c) Copyright by Christopher J. Welborn, 2012, cjwelborn@gmail.com 

# Permission to use, copy, modify, and distribute this software and 
# its documentation without fee and for any purpose, except direct 
# commerial advantage, is hereby granted, provided that the above 
# copyright notice appear in all copies and that both that copyright
# notice and this permission notice appear in supporting documentation.
#
# THE AUTHOR CHRISTOPHER J. WELBORN DISCLAIMS ALL WARRANTIES WITH REGARD TO
# THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
# FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL,
# INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING
# FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
# NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION
# WITH THE USE OR PERFORMANCE OF THIS SOFTWARE!

# -Christopher J. Welborn

# 7-17-2012


# Note to developers:
# I realize that there are probably better ways to do what I am
# doing here, I have only been writing Python for a couple weeks now
# and I am just getting used to it. If you can do this better, or plan
# on taking this script and modifying it, please drop a line in the 
# comments that says "inspired by Christopher Welborn's codecount.py"
# or something like that. If you have any pointers for me I welcome
# them, just send me an email and I'll try to implement your idea.
# 

# Imports
import sys          # for argument parsing
from os import path # for file stuff
import re           # for trimming spaces from strings

# Set App Name
sAppName = "Code Counter"
# Set Version
sVersion = "1.0"
# Get script file name
sAppExe = sys.argv[0]
# Set spacing for reports
sSpacing = "        "
# Trim ./ from script file name
if sAppExe[:2] == "./": 
	sAppExe = sAppExe[2:] 

sUsage = "Usage: ./" + sAppExe + " [-hdvi] script_to_analyze.py"


# No command-line arguments?
if len(sys.argv) < 2:
	print sAppName + " v." + sVersion + " - Not enough arguments, expecting:"
	print sUsage
	exit()
# Too many command-line arguments?
if len(sys.argv) > 3:
	print sAppName + " v. " + sVersion + " - Too many arguments, expecting:"
	print sUsage
	exit()
	
# Get count of arguments
iArgs = len(sys.argv)
# Get last argument (File to analyze)
sFile = sys.argv[iArgs - 1]

# Initialize Count: Counters
iTotal = 0          # Total Lines
iBlanks = 0         # Blank Lines
iCode = 0           # Actual Code
iCommentLine = 0    # Full Comment Line
iComments = 0       # Comments
iFunction = 0       # Function Definitions
iClass = 0          # Class Definitions
iIf = 0             # If/ElseIf Statements
iTry = 0            # Try/Catch Blocks
iPrint = 0          # Print Statements
iAssignments = 0    # Assignment Statements
iCodePer = 0        # Percent of Code
iBlankPer = 0       # Percent of Blank Lines
iCommPer = 0        # Percent of Comments
lVariables = list() # Variables
lImports = list()   # Imports

# Initialize Count: Length of code
iLongest = 0
iLongestComment = 0
# For calculating the shortest we have to start high
# The only way this wouldn't work is if ALL lines were greater than 999 chars.
iShortest = 999 
iShortestComment = 999

			
# DO WORK (analyze)
def doWork():	
	global iTotal, iBlanks, iCode, iCommentLine, iComments
	global iFunction, iClass, iIf, iTry, iPrint, iAssignments
	global iLongest, iLongestComment, iShortest, iShortestComment
	global iCodePer, iCommPer, iBlankPer
	global lVariables, lImports
	
	try:
		# Open script file for reading
		fFile = open(sFile, 'r')
	except exMsg:
		# Caught Error
		print sAppName + " Error Opening File: " + sFile
		print exMsg
		exit()
		
	# Cycle thru lines in file
	for sLine in fFile:
		# Increment Total Line Counter
		iTotal += 1

		# Strip all tabs
		sLine = sLine.strip("\t")
		
		# Replace Spaces With Nothing (Trim Spaces)
		sTrim = re.sub(r' ', '', sLine)
		# Trim NewLine Chars
		sTrim = re.sub(r'\n', '', sTrim)
		# Trim TabSpace Chars
		sTrim = re.sub(r'\t', '', sTrim)
	

		# Empty Line?
		if len(sTrim) == 0:
			# Increment Blank Line Counter
			iBlanks += 1
		# Not Empty:
		else:
		

			# Just a regular comment?:
			if sTrim[:1] == "#" and sTrim[:2] != "#!":
				# Increment Comment Count
				iCommentLine += 1
				# Longest Comment Yet?
				if len(sTrim) > iLongestComment:
					iLongestComment = len(sLine)
				# Shortest Comment Yet?
				if len(sTrim) < iShortestComment:
					iShortestComment = len(sLine)
			# Actual Code?:
			else:
				# Increment Code Line Counter
				iCode += 1
				# Longest Line Yet?
				if len(sTrim) > iLongest:
					iLongest = len(sLine)
				# Shortest Line Yet?
				if len(sTrim) < iShortest:
					if len(sTrim) > 0:
						iShortest = len(sLine)
				# Function?
				if sTrim[:3] == "def":
					iFunction += 1
				# Class?
				if sTrim[:5] == "class":
					iClass += 1
				# If/ElseIf?
				if sTrim[:2] == "if" or sTrim[:4] == "elif":
					iIf += 1
				# Try?
				if sTrim[:3] == "try":
					iTry += 1
				# Import?
				if sTrim[:6] == "import" or ((sTrim[:4] == "from") and ("import" in sTrim)):
					# Initialize String
					sImport = ""
					# Grab import name using "import [module]"
					if sTrim[:6] == "import":
						sImport = sLine[7:]
						sSplit = sImport.split(" ")
						sImport = sSplit[0].strip("#").strip("\t")
					# Grab import name using "from [module] import"
					else:
						sImport = sLine[5:]
						sSplit = sImport.split(" ")
						sImport = sSplit[0] + "." + sSplit[2]
					# Add to list of imports
					if not sImport in lImports:
						lImports.append(sImport)
					 
				# Print?
				if sTrim[:5] == "print":
					iPrint += 1
				# Inline Comments
				if "#" in sTrim and (not '"' in sTrim):
					iComments += 1
				# Inline Comments vs. # Characters in "string"
				elif "#" in sTrim and '"' in sTrim:
					# Split string by " Character
					sSplit = sTrim.split('"') # strings with "
								
					# Simple Inline Comment?
					if len(sSplit) == 1:
						iComments += 1
					# Tricky Inline Comment?: (# in "string" or outside?)
					else:
						# Get index for last section of string
						iLast = len(sSplit) - 1
					
						# Get last section of string
						sLast = sSplit[iLast]
					
						# Comment in last section?
						if "#" in sLast:
							iComments += 1
				# Inline Comments vs. # Characters in 'string'
				elif "#" in sTrim and "'" in sTrim:
					# Split string by ' Character
					sSplit = sTrim.split("'") # strings with '
				
					# Simple Inline Comment?
					if len(sSplit) == 1:
						iComments += 1
					# Tricky Inline Comment?: (# in 'string' or outside?)
					else:
						# Get index for last section of string
						iLast = len(sSplit) - 1
					
						# Get last section of string
						sLast = sSplit[iLast]
					
						# Comment in last section?
						if "#" in sLast:
							iComments += 1
				# Assignment Statements 
				if "=" in sLine:
					# We Found the = sign, now we have to weed out the non-assignment stuff
					sTrimA = sLine
					if "==" in sTrimA: 
						sTrimA = re.sub('==','', sTrimA)
					if "<=" in sTrimA: 
						sTrimA = re.sub('<=','', sTrimA)
					if ">=" in sTrimA: 
						sTrimA = re.sub('>=','', sTrimA)
					if "!=" in sTrimA: 
						sTrimA = re.sub('!=','', sTrimA)
					# Do we still have a = sign after that?
					if "=" in sTrimA:
						# Increment assigment count (because we found some kind of assignment)
						iAssignments += 1

						# Grab Variable Name, so we can count all the variables when we're done.
					
						# Get everything left of = character
						sLeft = sTrimA[:sTrimA.index("=")]
						# Split by spaces
						sSplit = sLeft.split(" ")
						

						# Get index of last string section (to get variable name)
						iLast = len(sSplit) - 1
						# If last item is blank or ",',+,-,*,\,\\ char, use the next to last item
						if sSplit[iLast] == "" or sSplit[iLast] == '"' or sSplit[iLast] == '+': 
							iLast -= 1
						if sSplit[iLast] == "-" or sSplit[iLast] == '*' or sSplit[iLast] == "/": 
							iLast -= 1
						if sSplit[iLast] == "'" or sSplit[iLast] == "//":
							iLast -= 1
							
						# "=" is definately inside string if " or ' is first or last char
						# ...so it doesn't count as a variable. (it's just a "#1 String")
						if (not '"' in sSplit[iLast]) and (not "'" in sSplit[iLast]) and (sSplit[0] != "print") and (sSplit[0] != "if"):
							# functions like "def myfunc(self, data=None)" don't count...
							if (not sSplit[0] == "def"):
								
								# Get Variable Name
								sVariable = sSplit[iLast].strip('\t')
									
								# Add Variable to list (If Not Already There)
								if (not sVariable in lVariables):
				
									# Catch split variable assignments?
									if ")" in sVariable:
										# Remove )'s
										sVariable = sVariable.strip(")")
										if ("(" in sSplit[iLast -1]) and ("," in sSplit[iLast - 1]):
											sExtraVar = sSplit[iLast - 1]
											sExtraVar = sExtraVar.strip(",")
											sExtraVar = sExtraVar.strip("(")
											# add our extra variable we caught, if not already there
											if (not sExtraVar in lVariables): 
												lVariables.append(sExtraVar)
									
									# variable passed all of our tests, append it
									lVariables.append(sVariable)
									
												
									
			
	# Close File
	fFile.close()


	# Find Percentage of Code Lines vs. Total
	iCodePer = (iCode / float(iTotal)) * 100
	# Find Percentage of Comment Lines vs. Total
	iCommPer = (iCommentLine / float(iTotal)) * 100
	# Find Percentage of Blank Lines vs. Total
	iBlankPer = (iBlanks / float(iTotal)) * 100

# REPORT
def printReport():
	# Report Information
	print "                        "
	print "    Finished analyzing: " + sFile + "..."
	print "                        "
	print "           Total Lines: " + str(iTotal)
	print "                        "
	print "            Code Lines: " + str(iCode) + " (" + str(iCodePer)[:7] + "%)"
	print "           Blank Lines: " + str(iBlanks) + " (" + str(iBlankPer)[:7] + "%)"
	print "                        "
	print "         Comment Lines: " + str(iCommentLine) + " (" + str(iCommPer)[:7] + "%)"
	print "       Inline Comments: " + str(iComments)
	print "        Total Comments: " + str(iCommentLine + iComments)
	print "                        "
	print "     Longest Code Line: " + str(iLongest)
	print "    Shortest Code Line: " + str(iShortest)
	print "                        "
	print "       Longest Comment: " + str(iLongestComment)
	print "      Shortest Comment: " + str(iShortestComment)
	print "                        "
	print "               Imports: " + str(len(lImports))
	print "             Functions: " + str(iFunction)
	print "               Classes: " + str(iClass)
	print "         If Statements: " + str(iIf)
	print "        Try Statements: " + str(iTry)
	print "      Print Statements: " + str(iPrint)
	print "           Assignments: " + str(iAssignments)
	print "             Variables: " + str(len(lVariables))

# IMPORTS
def printImports():
	global lImports
	
	# Print Header
	print sAppName + ":"
	if len(lImports) > 0:
		# sort imports?
		if not "d" in sys.argv[1]:
			lImports = sorted(lImports)
		# print imports
		print " " + str(len(lImports)) + " imports found in " + sFile + ":"
		for sImp in lImports:
			print sSpacing + sImp
			
	# No Imports Found!
	else:
		print " No Imports Found In " + sFile + "!"
		
# VARIABLES
def printVariables():
	global lVariables
	
	# Print header, if printImports() didn't already...
	if (not "i" in sys.argv[1]):
		print sAppName + ":"
	# Print Variables	
	if len(lVariables) > 0:
		# sort variables?
		if not "d" in sys.argv[1]:
			lVariables = sorted(lVariables)
		# print variables
		print " " + str(len(lVariables)) + " variables (" + str(iAssignments) + " assignments) found in " + sFile + ":"
		for sVar in lVariables:
			print sSpacing + sVar
	# No Variables Found!
	else:
		print " No Variables Found In " + sFile + "!"

# HELP		
def printHelp():
	print " "
	print sAppName +  " Help:"
	print sUsage
	print " "
	print " h : Show this help message"
	print " v : Print all variables found"
	print " i : Print all imports found"
	print " d : Sorts variable/import lists in the order they were discovered,"
	print "      ...default is alphabetically."
	print " "
	print "Note:"
	print "      As of right now the variable finder is not %100 accurate,"
	print "      ...it works for simple variable assignments but if it finds"
	print "      ...a line like this: (variable1, variable2) = myFunc(args)"
	print "      ...it will grab variable2, but not always variable1."
	print "      This program does not handle doc strings yet, they"
	print "     ...will be counted as code."
	exit()
		
# ! --- Start Of Script --- ! #

# -- Script Shelled not Imported, so do some work
if __name__ == "__main__":
		
	# Show Help? (Do this before we waste our doWork on nothing)
	if ("-h" in sys.argv[1]):
		printHelp()
		exit()

	# Is valid file? (Don't waste our time on bad filenames)
	if path.isfile(sFile) == False:
		print sUsage
		print "Expecting valid filename!"
		exit()

	# Do All Analyzing
	doWork()
	
	# Extra arguments?
	if len(sys.argv) > 2:
		# Is Import List?
		if "i" in sys.argv[1]:
			printImports()
	
		# Is variable list?
		if "v" in sys.argv[1]:
			printVariables()
		
		# only -d flag passed? why would you do that?
		if ("-" in sys.argv[1]) and ("d" in sys.argv[1]) and (not "i" in sys.argv[1]) and (not "v" in sys.argv[1]):
			print sUsage
			print "'d' flag doesn't do anything without the 'v' or 'i'!"
		# Don't go to report since argument options passed
		exit()
	# No flags passed? Print Regular Report
	printReport()
	# EXIT SCRIPT
	exit()