download: support more hash algorithms, not just md5sum

TODO: see XXX comments in the doctest

This changes to use hashlib directly, the module was introduced in python2.5
we don't need to support older versions.

src/zc/buildout/download.py

@@ -66,6 +66,7 @@ except ImportError:
 
 
 from zc.buildout.easy_install import realpath
+import hashlib
 import logging
 import os
 import os.path
@@ -122,7 +123,7 @@ class Download(object):
         if self.download_cache is not None:
             return os.path.join(self.download_cache, self.namespace or '')
 
-    def __call__(self, url, md5sum=None, path=None):
+    def __call__(self, url, md5sum=None, path=None, hashes=None):
         """Download a file according to the utility's configuration.
 
         url: URL to download
@@ -133,13 +134,13 @@ class Download(object):
 
         """
         if self.cache:
-            local_path, is_temp = self.download_cached(url, md5sum)
+            local_path, is_temp = self.download_cached(url, md5sum, hashes)
         else:
-            local_path, is_temp = self.download(url, md5sum, path)
+            local_path, is_temp = self.download(url, md5sum, path, hashes)
 
         return locate_at(local_path, path), is_temp
 
-    def download_cached(self, url, md5sum=None):
+    def download_cached(self, url, md5sum=None, hashes=None):
         """Download a file from a URL using the cache.
 
         This method assumes that the cache has been configured. Optionally, it
@@ -164,7 +165,7 @@ class Download(object):
             is_temp = False
             if self.fallback:
                 try:
-                    _, is_temp = self.download(url, md5sum, cached_path)
+                    _, is_temp = self.download(url, md5sum, cached_path, hashes)
                 except ChecksumError:
                     raise
                 except Exception:
@@ -174,15 +175,19 @@ class Download(object):
                 raise ChecksumError(
                     'MD5 checksum mismatch for cached download '
                     'from %r at %r' % (url, cached_path))
+            if not check_integrity(cached_path, hashes):
+                raise ChecksumError(
+                    'Checksum mismatch for cached download '
+                    'from %r at %r' % (url, cached_path))
             self.logger.debug('Using cache file %s' % cached_path)
         else:
             self.logger.debug('Cache miss; will cache %s as %s' %
                               (url, cached_path))
-            _, is_temp = self.download(url, md5sum, cached_path)
+            _, is_temp = self.download(url, md5sum, cached_path, hashes)
 
         return cached_path, is_temp
 
-    def download(self, url, md5sum=None, path=None):
+    def download(self, url, md5sum=None, path=None, hashes=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
@@ -204,6 +209,10 @@ class Download(object):
                 raise ChecksumError(
                     'MD5 checksum mismatch for local resource at %r.' %
                     url_path)
+            if not check_integrity(url_path, hashes):
+                raise ChecksumError(
+                    'Checksum mismatch for local resource at %r.' %
+                    url_path)
             return locate_at(url_path, path), False
 
         if self.offline:
@@ -225,6 +234,10 @@ class Download(object):
                 if not check_md5sum(tmp_path, md5sum):
                     raise ChecksumError(
                         'MD5 checksum mismatch downloading %r' % url)
+                if not check_integrity(tmp_path, hashes):
+                    raise ChecksumError(
+                        'Checksum mismatch downloading %r' % url)
+
                 # Upload the file to network cache.
                 if nc.get('upload-cache-url') and nc.get('upload-dir-url'):
                     upload_network_cached(
@@ -280,25 +293,46 @@ class Download(object):
             return '%s:%s' % (url_host, url_port)
 
 
-def check_md5sum(path, md5sum):
-    """Tell whether the MD5 checksum of the file at path matches.
+def check_integrity(path, hashes):
+    """Tell wether the checksum of the file at path matches any of the hashes.
 
-    No checksum being given is considered a match.
+    The hashes is string following format `algorithm:hash`, or None.
+
+    Multiple hashes can be specified, by separating them by spaces. In that
+    case, having one hash matching is enough.
+
+    hashes being None is considered a match.
 
     """
-    if md5sum is None:
+    if hashes is None:
         return True
 
+    for algorithm_and_expected_hash in hashes.split():
+        algorithm, expected_hash = algorithm_and_expected_hash.split(':', 1)
         f = open(path, 'rb')
-    checksum = md5()
+        checksum = hashlib.new(algorithm)
         try:
             chunk = f.read(2**16)
             while chunk:
                 checksum.update(chunk)
                 chunk = f.read(2**16)
-        return checksum.hexdigest() == md5sum
+            if checksum.hexdigest() == expected_hash:
+                return True
         finally:
             f.close()
+    return False
+
+
+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
+
+    return check_integrity(path, 'md5:' + md5sum)
 
 
 def remove(path):

src/zc/buildout/download.txt

@@ -69,19 +69,56 @@ the local file itself:
 >>> download(join(server_data, 'foo.txt'))
 ('/sample_files/foo.txt', False)
 
-We can also have the downloaded file's MD5 sum checked:
+We can also have the downloaded file's integrity checked:
+
+>>> import hashlib
+>>> path, is_temp = download(server_url+'foo.txt',
+...                          hashes='sha256:%s' % hashlib.sha256('This is a foo text.'.encode()).hexdigest())
+>>> is_temp
+True
+>>> remove(path)
+
+>>> download(server_url+'foo.txt',
+...          hashes='sha256:%s' % hashlib.sha256('The wrong text.'.encode()).hexdigest())
+Traceback (most recent call last):
+ChecksumError: Checksum mismatch downloading 'http://localhost/foo.txt'
+
+We can specify multiple hashes, as long as one match, the download is satisfied.
+
+XXX not sure it makes sense to expose this here ...
+XXX but then hashe*s* is a bad name - maybe integrity ?
+
+>>> path, is_temp = download(
+...    server_url+'foo.txt',
+...    hashes='sha512:1234567-wrong-hash sha256:%s' % hashlib.sha256('This is a foo text.'.encode()).hexdigest())
+>>> is_temp
+True
+>>> remove(path)
+
+
+The error message in the event of an checksum mismatch for a local file
+reads somewhat differently:
+
+>>> download(join(server_data, 'foo.txt'),
+...          hashes='sha256:%s' % hashlib.sha256('This is a foo text.'.encode()).hexdigest())
+('/sample_files/foo.txt', False)
+
+>>> download(join(server_data, 'foo.txt'),
+...          hashes='sha256:%s' % hashlib.sha256('The wrong text.'.encode()).hexdigest())
+Traceback (most recent call last):
+ChecksumError: Checksum mismatch for local resource at '/sample_files/foo.txt'.
 
->>> try: from hashlib import md5
-... except ImportError: from md5 import new as md5
+
+This also support MD5 sum for legacy:
 
 >>> path, is_temp = download(server_url+'foo.txt',
-...                          md5('This is a foo text.'.encode()).hexdigest())
+...                          hashlib.md5('This is a foo text.'.encode()).hexdigest())
 >>> is_temp
 True
 >>> remove(path)
 
 >>> download(server_url+'foo.txt',
-...          md5('The wrong text.'.encode()).hexdigest())
+...          hashlib.md5('The wrong text.'.encode()).hexdigest())
 Traceback (most recent call last):
 ChecksumError: MD5 checksum mismatch downloading 'http://localhost/foo.txt'
 
@@ -89,11 +126,11 @@ The error message in the event of an MD5 checksum mismatch for a local file
 reads somewhat differently:
 
 >>> download(join(server_data, 'foo.txt'),
-...               md5('This is a foo text.'.encode()).hexdigest())
+...               hashlib.md5('This is a foo text.'.encode()).hexdigest())
 ('/sample_files/foo.txt', False)
 
 >>> download(join(server_data, 'foo.txt'),
-...          md5('The wrong text.'.encode()).hexdigest())
+...          hashlib.md5('The wrong text.'.encode()).hexdigest())
 Traceback (most recent call last):
 ChecksumError: MD5 checksum mismatch for local resource at '/sample_files/foo.txt'.
 
@@ -165,10 +202,17 @@ the file on the server to see this:
 >>> cat(path)
 This is a foo text.
 
-If we specify an MD5 checksum for a file that is already in the cache, the
+If we specify hashes for a file that is already in the cache, the
 cached copy's checksum will be verified:
 
->>> download(server_url+'foo.txt', md5('The wrong text.'.encode()).hexdigest())
+>>> download(server_url+'foo.txt', hashes='sha256:%s' % hashlib.sha256('The wrong text.'.encode()).hexdigest())
+Traceback (most recent call last):
+ChecksumError: Checksum mismatch for cached download
+               from 'http://localhost/foo.txt' at '/download-cache/foo.txt'
+
+Same for legacy MD5 checksums:
+
+>>> download(server_url+'foo.txt', hashlib.md5('The wrong text.'.encode()).hexdigest())
 Traceback (most recent call last):
 ChecksumError: MD5 checksum mismatch for cached download
                from 'http://localhost/foo.txt' at '/download-cache/foo.txt'
@@ -247,7 +291,14 @@ This is a foo text.
 
 However, resources with checksum mismatches will not be copied to the cache:
 
->>> download(server_url+'foo.txt', md5('The wrong text.'.encode()).hexdigest())
+>>> download(server_url+'foo.txt', hashes='sha256:%s' % hashlib.sha256('The wrong text.'.encode()).hexdigest())
+Traceback (most recent call last):
+ChecksumError: Checksum mismatch downloading 'http://localhost/foo.txt'
+>>> ls(cache)
+
+Same for legay MD5 checksum:
+
+>>> download(server_url+'foo.txt', hashlib.md5('The wrong text.'.encode()).hexdigest())
 Traceback (most recent call last):
 ChecksumError: MD5 checksum mismatch downloading 'http://localhost/foo.txt'
 >>> ls(cache)
@@ -347,7 +398,7 @@ the test is run, so we don't actually know the full URL of the file. Let's
 check that the checksum actually belongs to the particular URL used:
 
 >>> (path.lower() ==
-...  join(cache, md5((server_url+'foo.txt').encode()).hexdigest()).lower())
+...  join(cache, hashlib.md5((server_url+'foo.txt').encode()).hexdigest()).lower())
 True
 
 The cached copy is used when downloading the file again:
@@ -370,7 +421,7 @@ cache under a different name:
 >>> path == path2
 False
 >>> (path2.lower() ==
-...  join(cache, md5((server_url+'other/foo.txt').encode()).hexdigest()
+...  join(cache, hashlib.md5((server_url+'other/foo.txt').encode()).hexdigest()
 ...       ).lower())
 True
 >>> cat(path)
@@ -451,12 +502,19 @@ When trying to download a resource whose checksum does not match, the cached
 copy will neither be used nor overwritten:
 
 >>> write(server_data, 'foo.txt', 'This is a foo text.')
->>> download(server_url+'foo.txt', md5('The wrong text.'.encode()).hexdigest())
+>>> download(server_url+'foo.txt', hashes='sha256:%s' % hashlib.sha256('The wrong text.'.encode()).hexdigest())
 Traceback (most recent call last):
-ChecksumError: MD5 checksum mismatch downloading 'http://localhost/foo.txt'
+ChecksumError: Checksum mismatch downloading 'http://localhost/foo.txt'
 >>> cat(cache, 'foo.txt')
 The wrong text.
 
+This is also the case with legacy MD5
+
+>>> download(server_url+'foo.txt', hashlib.md5('The wrong text.'.encode()).hexdigest())
+Traceback (most recent call last):
+ChecksumError: MD5 checksum mismatch downloading 'http://localhost/foo.txt'
+>>> cat(cache, 'foo.txt')
+The wrong text.
 
 Configuring the download utility from buildout options
 ------------------------------------------------------
@@ -538,7 +596,7 @@ True
 Regressions
 -----------
 
-MD5 checksum calculation needs to be reliable on all supported systems, which
+Checksum calculation needs to be reliable on all supported systems, which
 requires text files to be treated as binary to avoid implicit line-ending
 conversions:
 
@@ -547,7 +605,10 @@ conversions:
 >>> _ = f.write(text.encode())
 >>> f.close()
 >>> path, is_temp = Download()(server_url+'foo.txt',
-...                            md5(text.encode()).hexdigest())
+...                            hashlib.md5(text.encode()).hexdigest())
+>>> remove(path)
+>>> path, is_temp = Download()(server_url+'foo.txt',
+...                            hashes='sha512:%s' % hashlib.sha512(text.encode()).hexdigest())
 >>> remove(path)
 
 When "downloading" a directory given by file-system path or ``file:`` URL and