#!/usr/bin/python
###This Program is used to rename image files with its content

##SETUP
try:
	from PIL import Image
except ImportError:
	import Image
import pytesseract
import os
import string
import hashlib

namearray = []
indexnow = 0

print("OS name:", os.name)
if os.name == "nt": #U are using windows?
	pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files (x86)\Tesseract-OCR\tesseract" #absolute path to out tesseract instalation
	PATHSEPARATOR = "\\"
else: #No? NICE
	pytesseract.pytesseract.tesseract_cmd = r"/usr/bin/tesseract" #absolute path to teseract instalation
	PATHSEPARATOR = "/"

# Define the input and output directories
BASEPATHINPUT = "."+PATHSEPARATOR+"ImagesToConvert"
print("BASEPATHINPUT = "+BASEPATHINPUT)
BASEPATHOUTPUT = "."+PATHSEPARATOR+"ImagesOutput"
print("BASEPATHOUTPUT = "+BASEPATHOUTPUT)

# Getting the absolute path to the before named directories
ABSOLUTEPATHINPUT = os.path.abspath(BASEPATHINPUT)
print("ABSOLUTEPATHINPUT = "+ABSOLUTEPATHINPUT)
ABSOLUTEPATHOUTPUT = os.path.abspath(BASEPATHOUTPUT)
print("ABSOLUTEPATHOUTPUT = "+ABSOLUTEPATHOUTPUT)

##FUNCTIONS
def ocr(filename):
	newname = pytesseract.image_to_string(Image.open(ABSOLUTEPATHINPUT+PATHSEPARATOR+filename))  # Use pillow to open an image for pytesseract image2string to use
	return newname

def getHashedOut(filename):
	return hashlib.md5(Image.open(ABSOLUTEPATHINPUT+PATHSEPARATOR+filename).tobytes())

def namecleaner(filename):
	print("filenameis "+filename)
	filename = "-".join(filename.split()) # Get rid of line braks and spaces
	filename = filename.replace(" ","") # Get rid of spaces(For recursion)
	filename = filename.replace("\n","") # Get rid of line braks(For recursion)
	#Get rid of forbiden characters(NTFS)
	filename = filename.replace("<","")
	filename = filename.replace(">","")
	filename = filename.replace(":","")
	filename = filename.replace("\"","")
	filename = filename.replace("/","")
	filename = filename.replace("\\","")
	filename = filename.replace("|","")
	filename = filename.replace("?","")
	filename = filename.replace("*","")
	##################################
	filename = filename.replace(".","") # Get rid of extra dots
	while filename.count("--") != 0:
		filename = filename.replace("--","-") # Cleaning duplicated '-'s
	print("outputnameis "+filename)
	return filename

##CORECODE
# List all files in a directory using scandir()
with os.scandir(ABSOLUTEPATHINPUT) as entries:
	for entry in entries:
		if entry.is_file():
			# Fill an array with the list
			namearray.append(entry.name)

# Get array length for the loop
arraylength = len(namearray)
print("arraylength = "+str(arraylength))

while indexnow < arraylength:
	# Get file name from the array
	basename = namearray[indexnow]
	print("basename = "+basename)
	# Call ocr
	newname = ocr(basename)
	print("newname = "+newname)
	# Call "namecleaner" to get rid of forbiden characters, line breaks and spaces.
	cleanname = namecleaner(newname)
	print("cleanname = "+cleanname)
	if cleanname != "":
		if len(cleanname) > 200:
			cleanname = cleanname[0:200]
		cleanname = cleanname + "." + basename.split(".")[-1]
		os.rename(ABSOLUTEPATHINPUT+PATHSEPARATOR+basename, ABSOLUTEPATHOUTPUT+PATHSEPARATOR+cleanname)
		print(basename+" is now renamed as "+cleanname)
	else:
		imgHash = getHashedOut(basename).hexdigest()
		cleanname = imgHash + "." + basename.split(".")[-1]
		os.rename(ABSOLUTEPATHINPUT+PATHSEPARATOR+basename, ABSOLUTEPATHOUTPUT+PATHSEPARATOR+cleanname)
		print(basename+" is now "+cleanname)

	indexnow += 1


print("All images are given a name")