PaddleRS/paddlers/models/ppgan/utils/download.py

#   Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import sys
import time
import shutil
import hashlib
import tarfile
import zipfile
import requests
import os.path as osp
from tqdm import tqdm

from .logger import get_logger

PPGAN_HOME = os.path.expanduser(os.path.join('~', '.cache', 'ppgan'))

DOWNLOAD_RETRY_LIMIT = 3


def is_url(path):
    """
    Whether path is URL.
    Args:
        path (string): URL string or not.
    """
    return path.startswith('http://') or path.startswith('https://')


def _map_path(url, root_dir):
    # parse path after download under root_dir
    fname = osp.split(url)[-1]
    fpath = fname
    return osp.join(root_dir, fpath)


def get_path_from_url(url, md5sum=None, check_exist=True):
    """ Download from given url to root_dir.
    if file or directory specified by url is exists under
    root_dir, return the path directly, otherwise download
    from url and decompress it, return the path.

    Args:
        url (str): download url
        md5sum (str): md5 sum of download package

    Returns:
        str: a local path to save downloaded models & weights & datasets.
    """

    from paddle.distributed import ParallelEnv

    assert is_url(url), "downloading from {} not a url".format(url)
    root_dir = PPGAN_HOME
    # parse path after download to decompress under root_dir
    fullpath = _map_path(url, root_dir)

    if osp.exists(fullpath) and check_exist and _md5check(fullpath, md5sum):
        logger = get_logger('ppgan')
        logger.info("Found {}".format(fullpath))
    else:
        if ParallelEnv().local_rank == 0:
            fullpath = _download(url, root_dir, md5sum)
        else:
            while not os.path.exists(fullpath):
                time.sleep(1)

    if ParallelEnv().local_rank == 0:
        if tarfile.is_tarfile(fullpath) or zipfile.is_zipfile(fullpath):
            fullpath = _decompress(fullpath)

    return fullpath


def _download(url, path, md5sum=None):
    """
    Download from url, save to path.

    url (str): download url
    path (str): download to given path
    """
    if not osp.exists(path):
        os.makedirs(path)

    fname = osp.split(url)[-1]
    fullname = osp.join(path, fname)
    retry_cnt = 0

    while not (osp.exists(fullname) and _md5check(fullname, md5sum)):
        if retry_cnt < DOWNLOAD_RETRY_LIMIT:
            retry_cnt += 1
        else:
            raise RuntimeError("Download from {} failed. "
                               "Retry limit reached".format(url))

        logger = get_logger('ppgan')
        logger.info("Downloading {} from {} to {}".format(fname, url, fullname))

        req = requests.get(url, stream=True)
        if req.status_code != 200:
            raise RuntimeError("Downloading from {} failed with code "
                               "{}!".format(url, req.status_code))

        # For protecting download interupted, download to
        # tmp_fullname firstly, move tmp_fullname to fullname
        # after download finished
        tmp_fullname = fullname + "_tmp"
        total_size = req.headers.get('content-length')
        with open(tmp_fullname, 'wb') as f:
            if total_size:
                with tqdm(total=(int(total_size) + 1023) // 1024) as pbar:
                    for chunk in req.iter_content(chunk_size=1024):
                        f.write(chunk)
                        pbar.update(1)
            else:
                for chunk in req.iter_content(chunk_size=1024):
                    if chunk:
                        f.write(chunk)
        shutil.move(tmp_fullname, fullname)
    return fullname


def _md5check(fullname, md5sum=None):
    if md5sum is None:
        return True

    logger = get_logger('ppgan')
    logger.info("File {} md5 checking...".format(fullname))
    md5 = hashlib.md5()
    with open(fullname, 'rb') as f:
        for chunk in iter(lambda: f.read(4096), b""):
            md5.update(chunk)
    calc_md5sum = md5.hexdigest()

    if calc_md5sum != md5sum:
        logger.info("File {} md5 check failed, {}(calc) != "
                    "{}(base)".format(fullname, calc_md5sum, md5sum))
        return False
    return True


def _decompress(fname):
    """
    Decompress for zip and tar file
    """
    logger = get_logger('ppgan')

    logger.info("Decompressing {}...".format(fname))

    # For protecting decompressing interupted,
    # decompress to fpath_tmp directory firstly, if decompress
    # successed, move decompress files to fpath and delete
    # fpath_tmp and remove download compress file.

    if tarfile.is_tarfile(fname):
        uncompressed_path = _uncompress_file_tar(fname)
    elif zipfile.is_zipfile(fname):
        uncompressed_path = _uncompress_file_zip(fname)
    else:
        raise TypeError("Unsupport compress file type {}".format(fname))

    return uncompressed_path


def _uncompress_file_zip(filepath):
    files = zipfile.ZipFile(filepath, 'r')
    file_list = files.namelist()

    file_dir = os.path.dirname(filepath)

    if _is_a_single_file(file_list):
        rootpath = file_list[0]
        uncompressed_path = os.path.join(file_dir, rootpath)

        for item in file_list:
            files.extract(item, file_dir)

    elif _is_a_single_dir(file_list):
        rootpath = os.path.splitext(file_list[0])[0].strip(os.sep).split(
            os.sep)[-1]
        uncompressed_path = os.path.join(file_dir, rootpath)

        for item in file_list:
            files.extract(item, file_dir)

    else:
        rootpath = os.path.splitext(filepath)[0].split(os.sep)[-1]
        uncompressed_path = os.path.join(file_dir, rootpath)
        if not os.path.exists(uncompressed_path):
            os.makedirs(uncompressed_path)
        for item in file_list:
            files.extract(item, os.path.join(file_dir, rootpath))

    files.close()

    return uncompressed_path


def _uncompress_file_tar(filepath, mode="r:*"):
    files = tarfile.open(filepath, mode)
    file_list = files.getnames()

    file_dir = os.path.dirname(filepath)

    if _is_a_single_file(file_list):
        rootpath = file_list[0]
        uncompressed_path = os.path.join(file_dir, rootpath)
        for item in file_list:
            files.extract(item, file_dir)
    elif _is_a_single_dir(file_list):
        rootpath = os.path.splitext(file_list[0])[0].split(os.sep)[-1]
        uncompressed_path = os.path.join(file_dir, rootpath)
        for item in file_list:
            files.extract(item, file_dir)
    else:
        rootpath = os.path.splitext(filepath)[0].split(os.sep)[-1]
        uncompressed_path = os.path.join(file_dir, rootpath)
        if not os.path.exists(uncompressed_path):
            os.makedirs(uncompressed_path)

        for item in file_list:
            files.extract(item, os.path.join(file_dir, rootpath))

    files.close()

    return uncompressed_path


def _is_a_single_file(file_list):
    if len(file_list) == 1 and file_list[0].find('/') < -1:
        return True
    return False


def _is_a_single_dir(file_list):
    file_name = file_list[0].split('/')[0]
    for i in range(1, len(file_list)):
        if file_name != file_list[i].split('/')[0]:
            return False
    return True