def validateStream(aFile, firstOccurrenceOnly=0, contentType=None, base=""):
loggedEvents = []
if contentType:
(mediaType, charset) = mediaTypes.checkValid(contentType, loggedEvents)
else:
(mediaType, charset) = (None, None)
rawdata = aFile.read(MAXDATALENGTH)
if aFile.read(1):
raise ValidationFailure(
logging.ValidatorLimit(
{'limit': 'feed length > ' + str(MAXDATALENGTH) + ' bytes'}))
encoding, rawdata = xmlEncoding.decode(mediaType,
charset,
rawdata,
loggedEvents,
fallback='utf-8')
validator = _validate(rawdata,
firstOccurrenceOnly,
loggedEvents,
base,
encoding,
mediaType=mediaType)
if mediaType and validator.feedType:
mediaTypes.checkAgainstFeedType(mediaType, validator.feedType,
validator.loggedEvents)
return {
"feedType": validator.feedType,
"loggedEvents": validator.loggedEvents
}
def validateString(aString, firstOccurrenceOnly=0, fallback=None, base=""):
loggedEvents = []
if type(aString) != unicode:
encoding, aString = xmlEncoding.decode("", None, aString, loggedEvents, fallback)
else:
encoding = "utf-8" # setting a sane (?) default
if aString is not None:
validator = _validate(aString, firstOccurrenceOnly, loggedEvents, base, encoding)
return {"feedType":validator.feedType, "loggedEvents":validator.loggedEvents}
else:
return {"loggedEvents": loggedEvents}
def validateStream(aFile, firstOccurrenceOnly=0, contentType=None, base=""):
loggedEvents = []
if contentType:
(mediaType, charset) = mediaTypes.checkValid(contentType, loggedEvents)
else:
(mediaType, charset) = (None, None)
rawdata = aFile.read(MAXDATALENGTH)
if aFile.read(1):
raise ValidationFailure(logging.ValidatorLimit({'limit': 'feed length > ' + str(MAXDATALENGTH) + ' bytes'}))
encoding, rawdata = xmlEncoding.decode(mediaType, charset, rawdata, loggedEvents, fallback='utf-8')
validator = _validate(rawdata, firstOccurrenceOnly, loggedEvents, base, encoding)
if mediaType and validator.feedType:
mediaTypes.checkAgainstFeedType(mediaType, validator.feedType, validator.loggedEvents)
return {"feedType":validator.feedType, "loggedEvents":validator.loggedEvents}
# Get baseURI from content-location and/or redirect information
if usock.headers.get('content-location', None):
from urlparse import urljoin
baseURI=urljoin(baseURI,usock.headers.get('content-location', ""))
elif usock.headers.get('location', None):
from urlparse import urljoin
baseURI=urljoin(baseURI,usock.headers.get('location', ""))
if not baseURI in selfURIs: selfURIs.append(baseURI)
usock.close()
usock = None
mediaTypes.contentSniffing(mediaType, rawdata, loggedEvents)
encoding, rawdata = xmlEncoding.decode(mediaType, charset, rawdata, loggedEvents, fallback='utf-8')
if rawdata is None:
return {'loggedEvents': loggedEvents}
rawdata = rawdata.replace('\r\n', '\n').replace('\r', '\n') # normalize EOL
validator = _validate(rawdata, firstOccurrenceOnly, loggedEvents, baseURI, encoding, selfURIs)
# Warn about mismatches between media type and feed version
if mediaType and validator.feedType:
mediaTypes.checkAgainstFeedType(mediaType, validator.feedType, validator.loggedEvents)
params = {"feedType":validator.feedType, "loggedEvents":validator.loggedEvents}
if wantRawData:
params['rawdata'] = rawdata
return params
