#!/usr/bin/python
import csv,sys,os,shutil,ast,json,hashlib,pprint

reference_rows = []
referenceSequences = './'


with open('sequences.csv') as csv_reference:
    reference = csv.reader(csv_reference, delimiter=',')
    reference_header = next(reference)
    for row in reference: 
        reference_rows.append(row)

    # get total number of rows 
    print("Total no. of rows: %d"%(reference.line_num)) 
    for j in range(reference.line_num-1):
        sequence = reference_rows[j][0]
        # read sequence file
        sequencefile1 = sequence + '.json'
        sequencefile = referenceSequences + reference_rows[j][2] + '/' + sequencefile1
        # do some plausibility checks
        filename = reference_rows[j][2] + '/' + reference_rows[j][6]
        if os.path.isfile(filename):
            datasize = os.path.getsize(filename)
        if reference_rows[j][16] == "8":
            bit = 8
        else:
            bit = 16
        bytesize = int((int(reference_rows[j][29]) * int(reference_rows[j][10]) * int(reference_rows[j][11]) * 1.5 * bit)/8)
        if (bytesize == datasize):
            print((bytesize == datasize), j, reference.line_num, sequence, datasize, reference_rows[j][3], float(reference_rows[j][29])/float(reference_rows[j][17]))
        else:
            print((bytesize == datasize), j, reference.line_num, sequence, datasize, bytesize, reference_rows[j][29], int(8*datasize/(int(reference_rows[j][10]) * int(reference_rows[j][11]) * 1.5 * bit)))
        
        # writing
        if os.path.isfile(sequencefile):
            with open(sequencefile) as json_file:
                data = json.load(json_file)
        data["Sequence"]["Name"] = reference_rows[j][0]
        data["Sequence"]["TR26.955"] = reference_rows[j][1]
        data["Properties"]["duration"] = float(reference_rows[j][3])
        data["Sequence"]["Background"] = reference_rows[j][4]
        data["Sequence"]["Scenario"] = reference_rows[j][5]
        data["Sequence"]["URI"] = reference_rows[j][6]
        if (reference_rows[j][7] == ''):
            md5_hash = hashlib.md5()
            with open(filename,"rb") as f:
                # Read and update hash in chunks of 4K
                for byte_block in iter(lambda: f.read(4096),b""):
                    md5_hash.update(byte_block)
                data["Sequence"]["md5"] = md5_hash.hexdigest()
                print(data["Sequence"]["md5"])
        else:
            data["Sequence"]["md5"] = reference_rows[j][7]
        data["Sequence"]["size"] = datasize
        data["Sequence"]["thumbnail"] = reference_rows[j][8]
        data["Sequence"]["preview"] = reference_rows[j][9]
        data["Properties"]["width"] = int(reference_rows[j][10])
        data["Properties"]["height"] = int(reference_rows[j][11])
        data["Properties"]["format"] = reference_rows[j][12]
        data["Properties"]["packing"] = reference_rows[j][13]
        data["Properties"]["scan"] = reference_rows[j][14]
        data["Properties"]["subsampling"] = reference_rows[j][15]
        data["Properties"]["bitDepth"] = int(reference_rows[j][16])
        data["Properties"]["frameRate"] = float(reference_rows[j][17])
        data["Properties"]["colourPrimaries"] = reference_rows[j][18]
        data["Properties"]["transferCharacteristics"] = reference_rows[j][19]
        data["Properties"]["matrixCoefficients"] = reference_rows[j][20]
        data["Properties"]["videoFullRangeFlag"] = reference_rows[j][21]
        data["Properties"]["chromaSampleLocType"] = reference_rows[j][22]
        data["Properties"]["sampleAspectRatio"] = reference_rows[j][23]
        if int(reference_rows[j][24]) == 1:
            data["Properties"]["HDRmasterDisplay"] = reference_rows[j][25]
            data["Properties"]["HDRmaxCLL"] = reference_rows[j][26]
            data["Properties"]["HDRmaxFALL"] = reference_rows[j][27]
        data["Properties"]["startFrame"] = int(reference_rows[j][28])
        data["Properties"]["frameCount"] = int(reference_rows[j][29])
        data["copyRight"] = reference_rows[j][30]
        data["Contact"]["Name"] = reference_rows[j][31]
        data["Contact"]["Company"] = reference_rows[j][32]
        data["Contact"]["e-mail"] = reference_rows[j][33]
        data["Contact"]["generation"] = reference_rows[j][34]
        with open(sequencefile, 'w') as outfile:
            json.dump(data, outfile, sort_keys=False, indent=4)