#!/usr/bin/env python3
#
# wut-ia-sha1 --- Verify downloaded files checksums
#
# XXX uses both ET and xml.parsers.expat

import argparse
import os
from xml.parsers.expat import ParserCreate, ExpatError, errors
from pathlib import Path
import hashlib
import xml.etree.ElementTree as ET

dl_dir=Path('/srv/dl')

def convertxml(xmlfile, xml_attribs=True):
    with open(xmlfile, "rb") as f:
        d = xmltodict.parse(f, xml_attribs=xml_attribs, process_namespaces=False)
        return d

def parse_args():
    parser = argparse.ArgumentParser(description='sha1 check Internet Archive downloads')
    parser.add_argument('observations',
			type=str,
			help='Observation set. Example: 006050001-006060000')
    args = parser.parse_args()
    obs_set = 'satnogs-observations-' + args.observations
    obs_dir = Path(dl_dir, obs_set)
    filename_xml = obs_set + '_files.xml'
    print('filename XML:', filename_xml)
    xmlfile = Path(obs_dir, filename_xml)
    p = ParserCreate()
    try:
        p.ParseFile(open(xmlfile, 'rb'))
    except:
        print('No XML file to process')
        exit()

    return(xmlfile, obs_dir)

def get_sha1(filename):
    sha1 = hashlib.sha1()
    try:
        with open(filename, 'rb') as f:
            while True:
                data = f.read(1048576)
                if not data:
                    break
                sha1.update(data)
        return sha1.hexdigest()

    except:
         status='EXCEPTION'

def process_set(xmlfile, obs_dir):
    root_node = ET.parse(xmlfile).getroot()
    for tag in root_node.findall('file'):
        name = tag.get('name')
        for file_sha1 in tag.iter('sha1'):
            filename = Path(obs_dir, name)
            sha1_hash=get_sha1(filename)
            if sha1_hash == file_sha1.text:
                print('OK ', end='')
            else:
                print('FAIL ', end='')
            print(name)

def main():
    xmlfile, obs_dir = parse_args()
    process_set(xmlfile, obs_dir)

if __name__ == "__main__":
    main();