Thanks to visit codestin.com
Credit goes to github.com

Skip to content

resmgr: support zip archives and non-folder archive contents #967

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kba merged 2 commits into from
Dec 13, 2022
Merged

resmgr: support zip archives and non-folder archive contents #967

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e3a06c4
resmgr: support zip archives and non-folder archive contents
kba Dec 9, 2022
fbfe14c
merge master, remove unused imports
kba Dec 13, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 19 additions & 11 deletions ocrd/ocrd/resource_manager.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,16 @@
from pathlib import Path
from os.path import join
from os import environ, listdir, getcwd, path, unlink
from shutil import copytree, rmtree
from json import loads
from os import environ, listdir, getcwd, path
from shutil import copytree, rmtree, copy
from fnmatch import filter as apply_glob
from datetime import datetime
from tarfile import open as open_tarfile
from urllib.parse import urlparse, unquote
from subprocess import run, PIPE
from zipfile import ZipFile

import requests
from yaml import safe_load, safe_dump
import magic

# https://github.com/OCR-D/core/issues/867
# https://stackoverflow.com/questions/50900727/skip-converting-entities-while-loading-a-yaml-string-using-pyyaml
Expand Down Expand Up @@ -310,18 +309,27 @@ def download(
else:
self._copy_impl(url, fpath, progress_cb)
elif resource_type == 'archive':
archive_fname = 'download.tar.xx'
with pushd_popd(tempdir=True) as tempdir:
if is_url:
self._download_impl(url, 'download.tar.xx', progress_cb)
self._download_impl(url, archive_fname, progress_cb)
else:
self._copy_impl(url, 'download.tar.xx', progress_cb)
self._copy_impl(url, archive_fname, progress_cb)
Path('out').mkdir()
with pushd_popd('out'):
log.info("Extracting archive to %s/out" % tempdir)
with open_tarfile('../download.tar.xx', 'r:*') as tar:
tar.extractall()
log.info("Copying '%s' from tarball to %s" % (path_in_archive, fpath))
copytree(path_in_archive, str(fpath))
mimetype = magic.from_file(f'../{archive_fname}', mime=True)
log.info("Extracting %s archive to %s/out" % (mimetype, tempdir))
if mimetype == 'application/zip':
with ZipFile(f'../{archive_fname}', 'r') as zipf:
zipf.extractall()
else:
with open_tarfile(f'../{archive_fname}', 'r:*') as tar:
tar.extractall()
log.info("Copying '%s' from archive to %s" % (path_in_archive, fpath))
if Path(path_in_archive).is_dir():
copytree(path_in_archive, str(fpath))
else:
copy(path_in_archive, str(fpath))
return fpath

def _dedup_database(self, database=None, dedup_key='name'):
Expand Down
1 change: 1 addition & 0 deletions ocrd/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,3 +10,4 @@ pyyaml
Deprecated == 1.2.0
memory-profiler >= 0.58.0
sparklines >= 0.4.2
python-magic