def warn():
    print("  Note: Must be run in Terminal")
    print("  e.g. python md5_IX_v01o1.py -r filename hashTotal")
#def end
    
import sys
import hashlib

#by D@CC
#on 2023ISep25
progName="md5_IX_v01o1.py"
print("progName:",progName)
warn()
#Issue: The subjectFile must NOT begin with more than 1 "#########_"+"MD5_IX " records
#  Result: the hashed file (without Record 1) will begin with a bad "###..." record

#Hash Source: https://stackoverflow.com/questions/22058048/hashing-a-file-in-python
# compare to:
# $ md5-console -f bigfile
# $ shasum bigfile

#Snap Source:https://snapcraft.io/install/md5-console/raspbian
# $ sudo apt update
# $ sudo apt install snapd
# then reboot
# $ sudo snap install core
# $ sudo snap install snapcraft --classic
# $ sudo snap install md5-console
#  the last step took several minutes
prefixMD5='#########'+'_MD5_IX '
print('try grep "'+prefixMD5+'" fileName(s)')
import time; now=int(time.time());print ("UnixEpochTime:",now)

# BUF_SIZE is totally arbitrary, change for your app!
BUF_SIZE = 65536  # lets read stuff in 64kb chunks!

subjectFile=sys.argv[2]
print("subjectFile:",subjectFile)

md5 = hashlib.md5()
md5woR1 = hashlib.md5()
#sha1 = hashlib.sha1()
controlString=sys.argv[1]
controlString=controlString[1:2]
print("controlString:",controlString)

if "aefhru".find(controlString) >-1:
    print("controlString is valid")
else:
    print("Error 01: Invalid Control String:",controlString)
    exit
#if end
if controlString=="r":
    md5old=sys.argv[3]
    print(" ",md5old,":md5 (parm3)")
    #get first record only

    with open(subjectFile, 'r') as t:
        rec=t.readline().strip()
        lenPrefix=17
        prefix=rec[0:17]
        if prefix==prefixMD5:
            suffix=rec[17:len(rec)]
            #print("prefix:"+prefix+":")
            #print("suffix:"+suffix+":")
            r1h=suffix  #get real MD5 from rec 1
            isMD5inRec1=True
        else:
            r1h="missing rec1"
            isMD5inRec1=False
        #if end
        #print("line 64 r1h",r1h,":",rec," r1h")
        print(" ",r1h,":r1h")
    #with end
    t.close()
    

    # chop off rec1, write out file as "temp.txt"
    lenSubjectFile=len(subjectFile)
    tempStr=subjectFile[0:lenSubjectFile-4]
    #print("tempStr:",tempStr)
    tempName=tempStr+"_woR1"+subjectFile[-4:lenSubjectFile]
    #print("at 85 tempName:",tempName)
    temp=open(tempName, 'w')
    n=1
    with open(subjectFile, 'r') as t:
        if isMD5inRec1 :
            # skip record 1
            rec=t.readline()
            n+=1
            isMD5inRec1=False
        #if end
        while True:
            n+=1
            rec=t.readline()
            #print(n,rec)
            if rec=="": break
            temp.write(rec)
        #while end
        #print("eof")
    #with end
    temp.close()
    t.close()
    #print("temp written:",n," records")
    #print("at 107 tempName:",tempName)
    #print("a {0} :MD5".format(md5.hexdigest()))
    #print("hexdigest",md5.hexdigest()) 
    with open(tempName, 'rb') as f:             
        #with open(sys.argv[2], 'rb') as f:
        while True:
            data = f.read(BUF_SIZE)
            #print("data:",data,":")
            if not data:
                break
            md5.update(data)
            #sha1.update(data)
    # with end
    f.close()

    print("  {0} :MD5".format(md5.hexdigest()))
    #print("hexdigest",md5.hexdigest())    
    if md5old==md5.hexdigest() and md5old==r1h:
        print("This is a valid md5_IX file. The 3 md5 agree.")
    else:
        print("Bad md5 hashes exist.")
    #if end
    print("Name of hashed file (any MD5_IX record 1 was excluded):")
    print("  ",tempName)
    #print("SHA1: {0}".format(sha1.hexdigest()))
#if end r
if controlString=="h":
    print()
    print("md5_IX help information")
    warn()
    print("invoke with 3 parameters:")
    print(" controlString")
    print(" fileName")
    print(" md5-hash-total (expected) or 0")
    print("valid controlStrings are: -r, -h")
    print("File actually hashed is named before program exits")
    print('Use grep "'+prefixMD5+'" fileName(s)')
    print(" which will list hash totals for all files previously processed by md5_IX")
    print("Users should insert a hash_MD5_IX record as rec1 of each file")
    print(' rec1 format is "'+prefixMD5+'md5-hash-total"')
    print('Source: http://www.ePhotoCaption.com/a/206/206.html ')
#if end