/usr/lib/python2.7/dist-packages/drslib/thredds.py is in python-drslib 0.3.0a3-5build1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 | """
Check metadata in a THREDDS catalog is consistent with the DRS.
Things to check:
1. All DRS components set as properties and validate with drslib
2. drs_id is consistent with properties
3. version is a date
4. dataset urlPath is consistent with the DRS directory structure.
5. Checksums are present and the right format (NOT 'MD5:...')
6. tracking_id is present
7. Check product assignement is right.
Currently implemented: 1-3
"""
import sys
import os
import re
from lxml import etree as ET
from drslib.drs import DRS
from drslib.cmip5 import make_translator
from optparse import OptionParser
try:
from urllib.parse import urlparse
except ImportError:
# Python 2
from urlparse import urlparse
import logging
log = logging.getLogger(__name__)
THREDDS_NS = 'http://www.unidata.ucar.edu/namespaces/thredds/InvCatalog/v1.0'
XLINK_NS = 'http://www.w3.org/1999/xlink'
usage = """%prog [options] thredds ...
thredds:
A thredds url or file path of a dataset published by esgpublish.\
"""
trans = make_translator('')
drs_prop_map = {'dataset_version': 'version',
'project': 'activity',
'experiment': 'experiment',
'product': 'product',
'model': 'model',
'time_frequency': 'frequency',
'realm': 'realm',
'cmor_table': 'table',
'ensemble': 'ensemble',
'institute': 'institute'
}
class InvalidThreddsException(Exception):
"""
An exception raised to indicate failure of a ThreddsCheck
"""
pass
class CheckNotPossible(Exception):
"""
Raised to indicate a check doesn't have enough information to continue.
"""
pass
class ThreddsCheck(object):
"""
Base class of all checks, defining the interface.
"""
def __init__(self, environ=None):
"""
environ is a dictionary shared accross all checks allowing
checks to share information.
"""
self.environ = environ
def check(self, etree):
"""
Check the THREDDS catalogue represented by an ElementTree object.
"""
pass
def run_checks(etree, checks, environ=None):
"""
Run a sequence of checks on a THREDDS catalogue as an ElementTree.
InvalidThreddsExceptions are converted to log messages.
"""
if environ is None:
environ = {}
for CheckClass in checks:
check = CheckClass(environ)
try:
check.check(etree)
except InvalidThreddsException as e:
log.error(e)
except CheckNotPossible:
log.warn('Check %s aborted' % CheckClass.__name__)
else:
log.info('Check %s succeeded' % CheckClass.__name__)
return environ
class DRSIdCheck(ThreddsCheck):
"""
Check drs_id is present and consistent with dataset_id.
"""
def check(self, etree):
dataset = get_dataset(etree)
drs_id = get_property(dataset, 'drs_id')
dataset_id = get_property(dataset, 'dataset_id')
# Check 2 ids are consistent
if drs_id != dataset_id:
raise InvalidThreddsException("dataset_id != drs_id for dataset %s" %
dataset.get('ID'))
self.environ['dataset_id'] = dataset_id
self.environ['drs_id'] = drs_id
class DRSPropCheck(ThreddsCheck):
"""
Check all drs components are defined as properties.
Creates a drs attribute in the environment if successful.
"""
def check(self, etree):
dataset = get_dataset(etree)
props = {}
for prop_name in drs_prop_map:
prop = get_property(dataset, prop_name)
if prop_name is 'dataset_version':
prop = int(prop)
elif prop_name is 'ensemble':
#!TODO: refactor this to share code with drslib.translate
mo = re.match(r'(?:r(\d+))?(?:i(\d+))?(?:p(\d+))?', prop)
if not mo:
raise InvalidThreddsException('Unrecognised ensemble syntax %s' % prop)
(r, i, p) = mo.groups()
prop = tuple(x and int(x) for x in (r, i, p))
props[drs_prop_map[prop_name]] = prop
drs = DRS(**props)
# If present in environ check against drs_id
if 'drs_id' in self.environ:
if drs.to_dataset_id() != self.environ['drs_id']:
raise InvalidThreddsException("drs properties inconsistent with drs_id for dataset %s" %
dataset.get('ID'))
self.environ['drs'] = drs
class ValidDRSCheck(ThreddsCheck):
"""
Check the drs object in the environment is valid.
"""
def check(self, etree):
if 'drs' not in self.environ:
raise CheckNotPossible
drs = self.environ['drs']
try:
path = trans.drs_to_path(drs)
except:
raise InvalidThreddsException("drs %s fails to validate" % drs)
class ValidDateCheck(ThreddsCheck):
"""
Check date versioning.
"""
def check(self, etree):
if not 'drs' in self.environ:
raise CheckNotPossible
drs = self.environ['drs']
if not drs.version > 20100101:
raise InvalidThreddsException("The version of dataset doesn't look like a date: %s" %
drs)
#
# Utility functions
#
def get_dataset(etree):
# There should be only 1 top-level dataset element
datasets = etree.findall('{%s}dataset' % THREDDS_NS)
if len(datasets) != 1:
raise InvalidThreddsException("More than one top-level dataset")
return datasets[0]
def get_property(dataset, name):
prop = dataset.find('{%s}property[@name="%s"]' %
(THREDDS_NS, name))
if prop is None:
raise InvalidThreddsException("Property %s not found in dataset %s" %
(name, dataset.get('ID')))
return prop.get('value')
def read_master_catalog(catalog_url):
"""
Read master catalogue and generate dataset catalogue ElementTree objects.
"""
cat_etree = ET.parse(catalog_url)
scheme, netloc, path, query, fragment = urlparse.urlsplit(catalog_url)
base_url = urlparse.urlunsplit((scheme, netloc, os.path.dirname(path)+'/', None, None))
for catalog_ref in cat_etree.findall('{%s}catalogRef' % THREDDS_NS):
ds_url = catalog_ref.get('{%s}href' % XLINK_NS)
abs_ds_url = urlparse.urljoin(base_url, ds_url)
yield abs_ds_url
def main(argv=sys.argv):
logging.basicConfig(level=logging.ERROR)
checks = [DRSIdCheck, DRSPropCheck, ValidDRSCheck, ValidDateCheck]
op = OptionParser(usage)
op.add_option('-c', '--catalog', action='store',
help="Scan root THREDDS catalog CATALOG for catalogRef "
"elements and check each referenced catalog")
opts, args = op.parse_args(argv[1:])
xmls = args
if opts.catalog:
log.info('Discovering catalogs from master catalog %s' % opts.catalog)
xmls += list(read_master_catalog(opts.catalog))
if not xmls:
op.print_help()
for xml in xmls:
log.info('Checking %s' % xml)
etree = ET.parse(xml)
run_checks(etree, checks)
if __name__ == '__main__':
main()
|