download.py 8.77 KB
Newer Older
1 2
##############################################################################
#
icemac's avatar
icemac committed
3
# Copyright (c) 2009 Zope Foundation and Contributors.
4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
# All Rights Reserved.
#
# This software is subject to the provisions of the Zope Public License,
# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
# FOR A PARTICULAR PURPOSE.
#
##############################################################################
"""Buildout download infrastructure"""

try:
    from hashlib import md5
except ImportError:
    from md5 import new as md5
from zc.buildout.easy_install import realpath
import logging
import os
import os.path
24
import re
25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47
import shutil
import tempfile
import urllib
import urlparse
import zc.buildout


class URLOpener(urllib.FancyURLopener):
    http_error_default = urllib.URLopener.http_error_default


class ChecksumError(zc.buildout.UserError):
    pass


url_opener = URLOpener()


class Download(object):
    """Configurable download utility.

    Handles the download cache and offline mode.

48 49
    Download(options=None, cache=None, namespace=None,
             offline=False, fallback=False, hash_name=False, logger=None)
50 51 52 53

    options: mapping of buildout options (e.g. a ``buildout`` config section)
    cache: path to the download cache (excluding namespaces)
    namespace: namespace directory to use inside the cache
54 55
    offline: whether to operate in offline mode
    fallback: whether to use the cache as a fallback (try downloading first)
56 57 58 59 60 61 62
    hash_name: whether to use a hash of the URL as cache file name
    logger: an optional logger to receive download-related log messages

    """

    def __init__(self, options={}, cache=-1, namespace=None,
                 offline=-1, fallback=False, hash_name=False, logger=None):
63
        self.directory = options.get('directory', '')
64 65 66 67 68 69 70 71 72 73 74 75 76
        self.cache = cache
        if cache == -1:
            self.cache = options.get('download-cache')
        self.namespace = namespace
        self.offline = offline
        if offline == -1:
            self.offline = (options.get('offline') == 'true'
                            or options.get('install-from-cache') == 'true')
        self.fallback = fallback
        self.hash_name = hash_name
        self.logger = logger or logging.getLogger('zc.buildout')

    @property
77
    def download_cache(self):
78
        if self.cache is not None:
79 80 81 82 83 84
            return realpath(os.path.join(self.directory, self.cache))

    @property
    def cache_dir(self):
        if self.download_cache is not None:
            return os.path.join(self.download_cache, self.namespace or '')
85 86 87 88 89 90 91 92 93 94 95 96

    def __call__(self, url, md5sum=None, path=None):
        """Download a file according to the utility's configuration.

        url: URL to download
        md5sum: MD5 checksum to match
        path: where to place the downloaded file

        Returns the path to the downloaded file.

        """
        if self.cache:
97
            local_path, is_temp = self.download_cached(url, md5sum)
98
        else:
99
            local_path, is_temp = self.download(url, md5sum, path)
100

101
        return locate_at(local_path, path), is_temp
102 103 104 105 106 107 108 109 110

    def download_cached(self, url, md5sum=None):
        """Download a file from a URL using the cache.

        This method assumes that the cache has been configured. Optionally, it
        raises a ChecksumError if a cached copy of a file has an MD5 mismatch,
        but will not remove the copy in that case.

        """
111 112 113 114 115 116
        if not os.path.exists(self.download_cache):
            raise zc.buildout.UserError(
                'The directory:\n'
                '%r\n'
                "to be used as a download cache doesn't exist.\n"
                % self.download_cache)
117 118
        cache_dir = self.cache_dir
        if not os.path.exists(cache_dir):
119
            os.mkdir(cache_dir)
120 121 122 123
        cache_key = self.filename(url)
        cached_path = os.path.join(cache_dir, cache_key)

        self.logger.debug('Searching cache at %s' % cache_dir)
124
        if os.path.exists(cached_path):
125
            is_temp = False
126 127
            if self.fallback:
                try:
128
                    _, is_temp = self.download(url, md5sum, cached_path)
129 130 131 132 133 134
                except ChecksumError:
                    raise
                except Exception:
                    pass

            if not check_md5sum(cached_path, md5sum):
135 136 137 138 139 140 141 142
                try:
                    _, is_temp = self.download(url, md5sum, cached_path)
                except ChecksumError:
                    raise ChecksumError(
                        'MD5 checksum mismatch for cached download '
                        'from %r at %r' % (url, cached_path))
                except Exception:
                    pass
143 144 145 146
            self.logger.debug('Using cache file %s' % cached_path)
        else:
            self.logger.debug('Cache miss; will cache %s as %s' %
                              (url, cached_path))
147
            _, is_temp = self.download(url, md5sum, cached_path)
148

149
        return cached_path, is_temp
150 151 152 153 154 155 156

    def download(self, url, md5sum=None, path=None):
        """Download a file from a URL to a given or temporary path.

        An online resource is always downloaded to a temporary file and moved
        to the specified path only after the download is complete and the
        checksum (if given) matches. If path is None, the temporary file is
157
        returned and the client code is responsible for cleaning it up.
158 159

        """
160 161
        # Make sure the drive letter in windows-style file paths isn't
        # interpreted as a URL scheme.
162 163
        if re.match(r"^[A-Za-z]:\\", url):
            url = 'file:' + url
164

165
        parsed_url = urlparse.urlparse(url, 'file')
tlotze's avatar
tlotze committed
166 167
        url_scheme, _, url_path = parsed_url[:3]
        if url_scheme == 'file':
168
            self.logger.debug('Using local resource %s' % url)
tlotze's avatar
tlotze committed
169
            if not check_md5sum(url_path, md5sum):
170 171
                raise ChecksumError(
                    'MD5 checksum mismatch for local resource at %r.' %
tlotze's avatar
tlotze committed
172
                    url_path)
173
            return locate_at(url_path, path), False
174 175 176 177 178 179 180 181

        if self.offline:
            raise zc.buildout.UserError(
                "Couldn't download %r in offline mode." % url)

        self.logger.info('Downloading %s' % url)
        urllib._urlopener = url_opener
        handle, tmp_path = tempfile.mkstemp(prefix='buildout-')
182
        try:
alex_plugaru's avatar
alex_plugaru committed
183 184 185 186 187 188 189 190 191
            tmp_path, headers = urllib.urlretrieve(url, tmp_path)
            if not check_md5sum(tmp_path, md5sum):
                raise ChecksumError(
                    'MD5 checksum mismatch downloading %r' % url)
        except IOError, e:
            os.remove(tmp_path)
            raise zc.buildout.UserError("Error downloading extends for URL "
                              "%s: %r" % (url, e[1:3]))
        except Exception, e:
192 193
            os.remove(tmp_path)
            raise
alex_plugaru's avatar
alex_plugaru committed
194 195
        finally:
            os.close(handle)
196 197 198

        if path:
            shutil.move(tmp_path, path)
199
            return path, False
200
        else:
201
            return tmp_path, True
202 203 204 205 206 207 208 209

    def filename(self, url):
        """Determine a file name from a URL according to the configuration.

        """
        if self.hash_name:
            return md5(url).hexdigest()
        else:
210 211 212
            if re.match(r"^[A-Za-z]:\\", url):
                url = 'file:' + url
            parsed = urlparse.urlparse(url, 'file')
tlotze's avatar
tlotze committed
213
            url_path = parsed[2]
214 215 216 217 218 219 220 221

            if parsed[0] == 'file':
                while True:
                    url_path, name = os.path.split(url_path)
                    if name:
                        return name
                    if not url_path:
                        break
222
            else:
223 224 225 226 227 228
                for name in reversed(url_path.split('/')):
                    if name:
                        return name

            url_host, url_port = parsed[-2:]
            return '%s:%s' % (url_host, url_port)
229 230 231 232 233 234 235 236 237 238 239


def check_md5sum(path, md5sum):
    """Tell whether the MD5 checksum of the file at path matches.

    No checksum being given is considered a match.

    """
    if md5sum is None:
        return True

240
    f = open(path, 'rb')
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260
    checksum = md5()
    try:
        chunk = f.read(2**16)
        while chunk:
            checksum.update(chunk)
            chunk = f.read(2**16)
        return checksum.hexdigest() == md5sum
    finally:
        f.close()


def remove(path):
    if os.path.exists(path):
        os.remove(path)


def locate_at(source, dest):
    if dest is None or realpath(dest) == realpath(source):
        return source

261 262 263 264 265 266 267
    if os.path.isdir(source):
        shutil.copytree(source, dest)
    else:
        try:
            os.link(source, dest)
        except (AttributeError, OSError):
            shutil.copyfile(source, dest)
268
    return dest