Last active
June 12, 2019 18:53
-
-
Save helrond/50fabbf59e92dde1c77e5a76021f5582 to your computer and use it in GitHub Desktop.
A script to build bags which validate against the BagIt spec and a BagIt Profile.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
""" | |
A script to build bags which validate against the BagIt spec and a BagIt Profile. | |
Usage: build_bags.py [-h] [-t TARGET_DIR] [-b BAG_COUNT] profile_url source_dir | |
""" | |
import argparse | |
import bagit | |
from datetime import datetime | |
from os import makedirs, listdir | |
from os.path import basename, isdir, join, normpath | |
from random import choice, randint | |
import requests | |
from shutil import copyfile, make_archive | |
import string | |
import tarfile | |
import time | |
from uuid import uuid4 | |
import zipfile | |
class BagBuilderException(Exception): pass | |
class BagBuilder: | |
""" | |
Builds a bag from a random selection of files in a directory. | |
The following arguments are required: | |
profile_url: a HTTP-addressable URL at which a JSON representation of a | |
BagIt Profile is available. Used to construct valid metadata. | |
source_dir: a directory containing files, which will be randomly selected | |
and added to bags. | |
The following arguments are optional: | |
target_dir: a location in which bags should be created. Defaults to the | |
current directory if argument is omitted. | |
bag_count: the number of bags to create. Defaults to 10 if the argument | |
is omitted. | |
""" | |
def __init__(self, profile_url, source_dir, target_dir=None, bag_count=None): | |
self.profile_url = profile_url | |
self.bag_count = int(bag_count) if bag_count else 10 | |
self.source_dir = source_dir | |
self.target_dir = target_dir | |
try: | |
self.profile = requests.get(profile_url).json() | |
except Exception as e: | |
raise BagBuilderException("Error fetching BagIt Profile: {}".format(e)) | |
if not isdir(self.source_dir): | |
raise BagBuilderException("Source directory does not exist") | |
if (self.target_dir and not isdir(self.target_dir)): | |
makedirs(self.target_dir) | |
def run(self): | |
for i in range(self.bag_count): | |
self.bag_dir = self.make_dir() | |
self.add_files() | |
metadata = self.create_metadata(self.profile) | |
bagit.make_bag(self.bag_dir, metadata) | |
self.create_serialized() | |
def make_dir(self): | |
dir = str(uuid4())[:8] | |
if not isdir(join(self.target_dir, dir)): | |
makedirs(join(self.target_dir, dir)) | |
return join(self.target_dir, dir) | |
else: | |
self.make_dir() | |
def add_files(self): | |
num_files = randint(1, len(listdir(self.source_dir))) | |
files = listdir(self.source_dir) | |
for i in range(num_files): | |
f = choice(files) | |
copyfile(join(self.source_dir, f), join(self.bag_dir, f)) | |
def create_metadata(self, profile): | |
metadata = {} | |
for field in profile.get('Bag-Info'): | |
if profile['Bag-Info'][field].get('values'): | |
metadata[field] = choice(profile['Bag-Info'][field]['values']) | |
elif 'Date' in field: | |
metadata[field] = self.random_date() | |
elif 'Language' in field: | |
metadata[field] = self.random_language() | |
elif field == 'Bag-Count': | |
metadata[field] = self.random_string(randint(5,9)) | |
else: | |
metadata[field] = self.random_string(randint(5,20)) | |
metadata['BagIt-Profile-Identifier'] = self.profile_url | |
return metadata | |
def create_serialized(self): | |
with tarfile.open("{}.tar".format(self.bag_dir), 'w') as tar: | |
tar.add(self.bag_dir, arcname=basename(self.bag_dir)) | |
with tarfile.open("{}.tar.gz".format(self.bag_dir), 'w:gz') as targz: | |
targz.add(self.bag_dir, arcname=basename(self.bag_dir)) | |
make_archive(self.bag_dir, 'zip', self.target_dir, basename(normpath(self.bag_dir))) | |
def random_string(self, length=10): | |
letters = string.ascii_lowercase | |
return ''.join(choice(letters) for i in range(length)) | |
def random_date(self): | |
d = randint(1, int(time.time())) | |
return datetime.fromtimestamp(d).strftime('%Y-%m-%d') | |
def random_language(self): | |
languages = ["aar", "abk", "ace", "ach", "ada", "ady", "afa", "afh", "afr", "ain", "aka", "akk", "alb", "ale", "alg", "alt", "amh", "ang", "anp", "apa", "ara", "arc", "arg", "arm", "arn", "arp", "art", "arw", "asm", "ast", "ath", "aus", "ava", "ave", "awa", "aym", "aze", "bad", "bai", "bak", "bal", "bam", "ban", "baq", "bas", "bat", "bej", "bel", "bem", "ben", "ber", "bho", "bih", "bik", "bin", "bis", "bla", "bnt", "bos", "bra", "bre", "btk", "bua", "bug", "bul", "bur", "byn", "cad", "cai", "car", "cat", "cau", "ceb", "cel", "cha", "chb", "che", "chg", "chi", "chk", "chm", "chn", "cho", "chp", "chr", "chu", "chv", "chy", "cmc", "cop", "cor", "cos", "cpe", "cpf", "cpp", "cre", "crh", "crp", "csb", "cus", "cze", "dak", "dan", "dar", "day", "del", "den", "dgr", "din", "div", "doi", "dra", "dsb", "dua", "dum", "dut", "dyu", "dzo", "efi", "egy", "eka", "elx", "eng", "enm", "epo", "est", "ewe", "ewo", "fan", "fao", "fat", "fij", "fil", "fin", "fiu", "fon", "fre", "frm", "fro", "frr", "frs", "fry", "ful", "fur", "gaa", "gay", "gba", "gem", "geo", "ger", "gez", "gil", "gla", "gle", "glg", "glv", "gmh", "goh", "gon", "gor", "got", "grb", "grc", "gre", "grn", "gsw", "guj", "gwi", "hai", "hat", "hau", "haw", "heb", "her", "hil", "him", "hin", "hit", "hmn", "hmo", "hrv", "hsb", "hun", "hup", "iba", "ibo", "ice", "ido", "iii", "ijo", "iku", "ile", "ilo", "ina", "inc", "ind", "ine", "inh", "ipk", "ira", "iro", "ita", "jav", "jbo", "jpn", "jpr", "jrb", "kaa", "kab", "kac", "kal", "kam", "kan", "kar", "kas", "kau", "kaw", "kaz", "kbd", "kha", "khi", "khm", "kho", "kik", "kin", "kir", "kmb", "kok", "kom", "kon", "kor", "kos", "kpe", "krc", "krl", "kro", "kru", "kua", "kum", "kur", "kut", "lad", "lah", "lam", "lao", "lat", "lav", "lez", "lim", "lin", "lit", "lol", "loz", "ltz", "lua", "lub", "lug", "lui", "lun", "luo", "lus", "mac", "mad", "mag", "mah", "mai", "mak", "mal", "man", "mao", "map", "mar", "mas", "may", "mdf", "mdr", "men", "mga", "mic", "min", "mis", "mkh", "mlg", "mlt", "mnc", "mni", "mno", "moh", "mon", "mos", "mul", "mun", "mus", "mwl", "mwr", "myn", "myv", "nah", "nai", "nap", "nau", "nav", "nbl", "nde", "ndo", "nds", "nep", "new", "nia", "nic", "niu", "nno", "nob", "nog", "non", "nor", "nqo", "nso", "nub", "nwc", "nya", "nym", "nyn", "nyo", "nzi", "oci", "oji", "ori", "orm", "osa", "oss", "ota", "oto", "paa", "pag", "pal", "pam", "pan", "pap", "pau", "peo", "per", "phi", "phn", "pli", "pol", "pon", "por", "pra", "pro", "pus", "qaa-qtz", "que", "raj", "rap", "rar", "roa", "roh", "rom", "rum", "run", "rup", "rus", "sad", "sag", "sah", "sai", "sal", "sam", "san", "sas", "sat", "scn", "sco", "sel", "sem", "sga", "sgn", "shn", "sid", "sin", "sio", "sit", "sla", "slo", "slv", "sma", "sme", "smi", "smj", "smn", "smo", "sms", "sna", "snd", "snk", "sog", "som", "son", "sot", "spa", "srd", "srn", "srp", "srr", "ssa", "ssw", "suk", "sun", "sus", "sux", "swa", "swe", "syc", "syr", "tah", "tai", "tam", "tat", "tel", "tem", "ter", "tet", "tgk", "tgl", "tha", "tib", "tig", "tir", "tiv", "tkl", "tlh", "tli", "tmh", "tog", "ton", "tpi", "tsi", "tsn", "tso", "tuk", "tum", "tup", "tur", "tut", "tvl", "twi", "tyv", "udm", "uga", "uig", "ukr", "umb", "und", "urd", "uzb", "vai", "ven", "vie", "vol", "vot", "wak", "wal", "war", "was", "wel", "wen", "wln", "wol", "xal", "xho", "yao", "yap", "yid", "yor", "ypk", "zap", "zbl", "zen", "zha", "znd", "zul", "zun", "zxx", "zza"] | |
num = randint(0, len(languages)) | |
return languages[num] | |
parser = argparse.ArgumentParser(description='Builds bags which validate against the BagIt spec and a BagIt Profile.') | |
parser.add_argument('profile_url', help='URL for a BagIt Profile.') | |
parser.add_argument('source_dir', help='A directory containing files which will be randomly added to bags.') | |
parser.add_argument('-t', '--target_dir', help='Target directory in which bags will be created. Defaults to current directory.') | |
parser.add_argument('-b', '--bag_count', help='The number of bags to generate. Defaults to 10') | |
args = parser.parse_args() | |
BagBuilder(args.profile_url, args.source_dir, args.target_dir, args.bag_count).run() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment