|
@@ -17,6 +17,14 @@
|
|
from shutil import copyfileobj
|
|
from shutil import copyfileobj
|
|
from urllib.error import HTTPError
|
|
from urllib.error import HTTPError
|
|
|
|
|
|
|
|
+class AssetError(Exception):
|
|
|
|
+ def __init__(self, asset, msg, transient=False):
|
|
|
|
+ self.url = asset.url
|
|
|
|
+ self.msg = msg
|
|
|
|
+ self.transient = transient
|
|
|
|
+
|
|
|
|
+ def __str__(self):
|
|
|
|
+ return "%s: %s" % (self.url, self.msg)
|
|
|
|
|
|
# Instances of this class must be declared as class level variables
|
|
# Instances of this class must be declared as class level variables
|
|
# starting with a name "ASSET_". This enables the pre-caching logic
|
|
# starting with a name "ASSET_". This enables the pre-caching logic
|
|
@@ -51,7 +59,7 @@ def _check(self, cache_file):
|
|
elif len(self.hash) == 128:
|
|
elif len(self.hash) == 128:
|
|
hl = hashlib.sha512()
|
|
hl = hashlib.sha512()
|
|
else:
|
|
else:
|
|
- raise Exception("unknown hash type")
|
|
|
|
|
|
+ raise AssetError(self, "unknown hash type")
|
|
|
|
|
|
# Calculate the hash of the file:
|
|
# Calculate the hash of the file:
|
|
with open(cache_file, 'rb') as file:
|
|
with open(cache_file, 'rb') as file:
|
|
@@ -111,7 +119,8 @@ def fetch(self):
|
|
return str(self.cache_file)
|
|
return str(self.cache_file)
|
|
|
|
|
|
if not self.fetchable():
|
|
if not self.fetchable():
|
|
- raise Exception("Asset cache is invalid and downloads disabled")
|
|
|
|
|
|
+ raise AssetError(self,
|
|
|
|
+ "Asset cache is invalid and downloads disabled")
|
|
|
|
|
|
self.log.info("Downloading %s to %s...", self.url, self.cache_file)
|
|
self.log.info("Downloading %s to %s...", self.url, self.cache_file)
|
|
tmp_cache_file = self.cache_file.with_suffix(".download")
|
|
tmp_cache_file = self.cache_file.with_suffix(".download")
|
|
@@ -121,6 +130,20 @@ def fetch(self):
|
|
with tmp_cache_file.open("xb") as dst:
|
|
with tmp_cache_file.open("xb") as dst:
|
|
with urllib.request.urlopen(self.url) as resp:
|
|
with urllib.request.urlopen(self.url) as resp:
|
|
copyfileobj(resp, dst)
|
|
copyfileobj(resp, dst)
|
|
|
|
+ length_hdr = resp.getheader("Content-Length")
|
|
|
|
+
|
|
|
|
+ # Verify downloaded file size against length metadata, if
|
|
|
|
+ # available.
|
|
|
|
+ if length_hdr is not None:
|
|
|
|
+ length = int(length_hdr)
|
|
|
|
+ fsize = tmp_cache_file.stat().st_size
|
|
|
|
+ if fsize != length:
|
|
|
|
+ self.log.error("Unable to download %s: "
|
|
|
|
+ "connection closed before "
|
|
|
|
+ "transfer complete (%d/%d)",
|
|
|
|
+ self.url, fsize, length)
|
|
|
|
+ tmp_cache_file.unlink()
|
|
|
|
+ continue
|
|
break
|
|
break
|
|
except FileExistsError:
|
|
except FileExistsError:
|
|
self.log.debug("%s already exists, "
|
|
self.log.debug("%s already exists, "
|
|
@@ -133,10 +156,23 @@ def fetch(self):
|
|
tmp_cache_file)
|
|
tmp_cache_file)
|
|
tmp_cache_file.unlink()
|
|
tmp_cache_file.unlink()
|
|
continue
|
|
continue
|
|
|
|
+ except HTTPError as e:
|
|
|
|
+ tmp_cache_file.unlink()
|
|
|
|
+ self.log.error("Unable to download %s: HTTP error %d",
|
|
|
|
+ self.url, e.code)
|
|
|
|
+ # Treat 404 as fatal, since it is highly likely to
|
|
|
|
+ # indicate a broken test rather than a transient
|
|
|
|
+ # server or networking problem
|
|
|
|
+ if e.code == 404:
|
|
|
|
+ raise AssetError(self, "Unable to download: "
|
|
|
|
+ "HTTP error %d" % e.code)
|
|
|
|
+ continue
|
|
except Exception as e:
|
|
except Exception as e:
|
|
- self.log.error("Unable to download %s: %s", self.url, e)
|
|
|
|
tmp_cache_file.unlink()
|
|
tmp_cache_file.unlink()
|
|
- raise
|
|
|
|
|
|
+ raise AssetError(self, "Unable to download: " % e)
|
|
|
|
+
|
|
|
|
+ if not os.path.exists(tmp_cache_file):
|
|
|
|
+ raise AssetError(self, "Download retries exceeded", transient=True)
|
|
|
|
|
|
try:
|
|
try:
|
|
# Set these just for informational purposes
|
|
# Set these just for informational purposes
|
|
@@ -150,8 +186,7 @@ def fetch(self):
|
|
|
|
|
|
if not self._check(tmp_cache_file):
|
|
if not self._check(tmp_cache_file):
|
|
tmp_cache_file.unlink()
|
|
tmp_cache_file.unlink()
|
|
- raise Exception("Hash of %s does not match %s" %
|
|
|
|
- (self.url, self.hash))
|
|
|
|
|
|
+ raise AssetError(self, "Hash does not match %s" % self.hash)
|
|
tmp_cache_file.replace(self.cache_file)
|
|
tmp_cache_file.replace(self.cache_file)
|
|
# Remove write perms to stop tests accidentally modifying them
|
|
# Remove write perms to stop tests accidentally modifying them
|
|
os.chmod(self.cache_file, stat.S_IRUSR | stat.S_IRGRP)
|
|
os.chmod(self.cache_file, stat.S_IRUSR | stat.S_IRGRP)
|
|
@@ -173,15 +208,10 @@ def precache_test(test):
|
|
log.info("Attempting to cache '%s'" % asset)
|
|
log.info("Attempting to cache '%s'" % asset)
|
|
try:
|
|
try:
|
|
asset.fetch()
|
|
asset.fetch()
|
|
- except HTTPError as e:
|
|
|
|
- # Treat 404 as fatal, since it is highly likely to
|
|
|
|
- # indicate a broken test rather than a transient
|
|
|
|
- # server or networking problem
|
|
|
|
- if e.code == 404:
|
|
|
|
|
|
+ except AssetError as e:
|
|
|
|
+ if not e.transient:
|
|
raise
|
|
raise
|
|
-
|
|
|
|
- log.debug(f"HTTP error {e.code} from {asset.url} " +
|
|
|
|
- "skipping asset precache")
|
|
|
|
|
|
+ log.error("%s: skipping asset precache" % e)
|
|
|
|
|
|
log.removeHandler(handler)
|
|
log.removeHandler(handler)
|
|
|
|
|