from urllib import request
from io import TextIOWrapper
from itertools import groupby
import re
import json
from meta_release import SourceMetaRelease, MetaRelease
import pdb


#RELEASE_WORD_MATCHER = r'(^\Origin\:\s|Label:\s|Suite:\s|Version:\s|Codename:\s|Date:\s|Architecture:\s|Components:\s|Description:\s|MD5Sum:\s|SHA256:\s|Aquire\-By\-Hash:\s)'

class Release:
    def __init__(self, distro_codename):
        # example url:http://old-releases.ubuntu.com/ubuntu/dists/hoary/Release
		# example distro_codename = 'hoary'
        self.distro_codename = distro_codename
        self.meta_release = self.changelog_release_file()

    def changelog_release_file(self):
        meta_release = SourceMetaRelease().meta_release_parse()
        return meta_release

    def distro_release_file_urls(self):
        meta_release_objects = []

        for d in self.meta_release:
            meta_release_obj = MetaRelease(d)
            dist_and_release_file_url = { meta_release_obj.dist: meta_release_obj.release_file }
            meta_release_objects.append(dist_and_release_file_url)

        return meta_release_objects

    def line_format(self, line):
        """ Use this method for cleaning the line, especially the one with the md5
        and shasums in them. """
        try:
            data = {}
            #cleaned_line = re.split(RELEASE_WORD_MATCHER, line)
            split_line_arr = line.split(':')
            split_line_arr_len = len(split_line_arr)

            if split_line_arr_len == 1:
                # example: [' 26f7612b4526f7b97b6b2f7abbdd59e5f83f879a0dbdcce799b7b91bc36387de            36973 universe/debian-installer/binary-sparc/Packages\n'] 

                l = split_line_arr[0]
                checksum_size_and_filepath = l.strip().split(' ')

                while ('' in checksum_size_and_filepath):
                    checksum_size_and_filepath.remove('')

                data['checksum'] = checksum_size_and_filepath[0]
                data['filesize'] = checksum_size_and_filepath[1]
                data['filepath'] = checksum_size_and_filepath[2]
                
            elif split_line_arr_len >= 2:
                k = split_line_arr[0].strip()
                v = split_line_arr[1]
                data[k] = v

            return data 
        except Exception as e:
            print('failed to clean')
            print(line)
            print(e)

    def validate_parse(self):
        """ Use this method for validating the entire returned dictionary. make
        sure it has the expected keys we want/expect. """
        return 

    def md5_from_line(line):
        return 

    def sha256_from_line(line):
        return

    def release_file_parse(self, release_file_url):
        """ Returns the parsed_release_file parsed as a list of dicts """
        with request.urlopen(f'{release_file_url}') as response:
            index_counter = 0
            lines = TextIOWrapper(response, encoding='utf-8')

            cleaned_lines = []

            for l in lines:
                cleaned_line = self.line_format(l)
                cleaned_lines.append(cleaned_line)
                #print(cleaned_line)

            return cleaned_lines
            #return parsed_release_file

"""
            stripped_lines = [
                    re.split(RELEASE_WORD_MATCHER, l.strip()[::1]) for l in
                    lines ]
            print(stripped_lines)
            grouped_lines = [list(group) for key, group in
                    groupby(stripped_lines, lambda x: x == []) if not key]
            list_of_dicts = []

            for group in grouped_lines:
                d = {}
                # list of each group
                for arr in group:
                    arr_per_group = len(group)
                    k = arr[0].lower().replace(":", "").strip()
                    v = arr[1].strip()

                    # this builds up our dict by adding one k,v pair per key
                    d[f"{k}"] = v

                    list_of_dicts.append(d) if arr_per_group == len(d.keys()) else None 

            return list_of_dicts
"""

if __name__ == '__main__':
    # testing

    r = Release('focal')
    release_file_urls = r.distro_release_file_urls()

    for meta_release_dict in release_file_urls:
        keys = meta_release_dict.keys()
        for distro in keys:
            url = meta_release_dict[distro]
            try:
                results = r.release_file_parse(url)
                print(type(results))
                print(len(results))
                for d in results:
                    print(type(d))
                    print(d)
            except Exception as e:
                print(e.__doc__)
                print(e.message)