def __init__(self):
print "\nreading NEW standards"
self.new_AsnStandards = StdDocument(new_asnpath)
self.new_asn_ids = self.new_AsnStandards.keys()
print "\nreading OLD standards"
self.old_AsnStandards = StdDocument(old_asnpath)
self.old_asn_ids = self.old_AsnStandards.keys()
def __init__(self, url):
self.url = url
XmlRecord.__init__(self, xml=self.getUrl(url))
self.mapped_ids = self._getMappedIds()
print "\nreading NEW standards"
self.new_AsnStandards = StdDocument(new_asnpath)
self.new_asn_ids = self.new_AsnStandards.keys()
print "\nreading OLD standards"
self.old_AsnStandards = StdDocument(old_asnpath)
self.old_asn_ids = self.old_AsnStandards.keys()
class NSESStandardsSetup(UserDict):
def __init__(self, path):
UserDict.__init__(self)
self.NSES = StdDocument(NSESpath)
self.groups = SubjectGroupMap()
self._init_pool()
# for i in range(10):
# std = self.pool[i]
# # print "%s: %s" % (getBand(std), std.description)
# print self._get_std_domain (std)
def add(self, item):
self[item.id] = item
self.groups.add(item)
def _init_pool(self):
for asnStd in self.NSES.values():
if asnStd.level == 3:
std_domain = self._get_std_domain(asnStd)
if std_domain:
self.add(NSESStandard(asnStd, std_domain))
def _get_std_domain(self, std):
# print "getBand(): " + std.description
domains = nses_std_domains.keys()
node = std
while node and node.description not in domains:
node = self.NSES[node.parent]
if node and node.description in domains:
return nses_std_domains[node.description]
def __repr__(self):
s = []
add = s.append
add("NSES_stds_pool = {")
for group_name in domain_groups_keys:
add('\t"%s": {' % group_name)
group = self.groups[group_name]
for band_name in group.keys():
add('\t\t"%s" : [' % band_name)
band = group[band_name]
for std in band:
add('\t\t\t"%s",' % std.numId)
add('\t\t],')
add('\t},')
add('}')
return string.join(s, "\n")
class AsnCompare:
def __init__(self):
print "\nreading NEW standards"
self.new_AsnStandards = StdDocument(new_asnpath)
self.new_asn_ids = self.new_AsnStandards.keys()
print "\nreading OLD standards"
self.old_AsnStandards = StdDocument(old_asnpath)
self.old_asn_ids = self.old_AsnStandards.keys()
def set_diff(self, set1, set2):
ids = []
add = ids.append
for id in set1:
if id not in set2:
add(id)
return ids
def new_asn_not_in_old_asn(self):
ids = self.set_diff(self.new_asn_ids, self.old_asn_ids)
return self.filter_ids_by_level(ids, self.new_AsnStandards)
def old_asn_not_in_new_asn(self):
ids = self.set_diff(self.old_asn_ids, self.new_asn_ids)
return self.filter_ids_by_level(ids, self.old_AsnStandards)
def report_asn_diff(self):
ids = self.new_asn_not_in_old_asn()
if 1:
print "\nNEW ASN stds not in OLD ASN stds (%d)" % len(ids)
for id in ids:
std = self.new_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
ids = self.old_asn_not_in_new_asn()
if 1:
print "\nOLD ASN stds not in NEW ASN stds (%d)" % len(ids)
for id in ids:
std = self.old_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
def filter_ids_by_level(self, ids, standardsDoc, threshold=None):
"""
1 - sort the ids as strings (just to put them in some consistent order)
2 - filter out the standards for level less than threshold (if provided)
3 - sort by level (in standards hierarchy)
"""
filtered = []
ids.sort()
for id in ids:
level = standardsDoc[id].level + 1
if threshold:
if level > threshold:
filtered.append(id)
else:
filtered.append(id)
return self.sort_by_level(filtered, standardsDoc)
def sort_by_level(self, ids, standardsDoc):
bins = {}
for id in ids:
level = standardsDoc[id].level + 1
if not bins.has_key(level):
bins[level] = []
items = bins[level]
items.append(id)
bins[level] = items
sorted_ids = []
add = sorted_ids.append
for level in bins.keys():
items = bins[level]
for id in items:
add(id)
return sorted_ids
def report(self):
self.report_asn_diff()
def __init__(self, dir):
self.data_dir = dir
NSESDocPath = os.path.join(self.asnDocDir, self.nsesDoc)
self.NSES = StdDocument(NSESDocPath)
class Validator(XmlRecord):
def __init__(self, url):
self.url = url
XmlRecord.__init__(self, xml=self.getUrl(url))
self.mapped_ids = self._getMappedIds()
print "\nreading NEW standards"
self.new_AsnStandards = StdDocument(new_asnpath)
self.new_asn_ids = self.new_AsnStandards.keys()
print "\nreading OLD standards"
self.old_AsnStandards = StdDocument(old_asnpath)
self.old_asn_ids = self.old_AsnStandards.keys()
def _getMappedIds(self):
mappings = self.selectNodes(self.dom, "Adn-to-Asn-mappings:mapping")
print "%d mappings found" % len(mappings)
ids = map(lambda a: a.getAttribute("asnIdentifier"), mappings)
## for id in ids:
## print "\t", id
ids.sort()
return ids
def set_diff(self, set1, set2):
ids = []
add = ids.append
for id in set1:
if id not in set2:
add(id)
return ids
def new_asn_not_in_old_asn(self):
ids = self.set_diff(self.new_asn_ids, self.old_asn_ids)
return self.filter_ids_by_level(ids, self.new_AsnStandards)
def old_asn_not_in_new_asn(self):
ids = self.set_diff(self.old_asn_ids, self.new_asn_ids)
return self.filter_ids_by_level(ids, self.old_AsnStandards)
# filter threshold for mapping files is 2, since mapping contains only levels 3 and 4
def mapping_not_in_new_asn(self):
ids = self.set_diff(self.mapped_ids, self.new_asn_ids)
return self.filter_ids_by_level(ids, self.old_AsnStandards, 2)
# filter threshold for mapping files is 2, since mapping contains only levels 3 and 4
def mapping_not_in_old_asn(self):
ids = self.set_diff(self.mapped_ids, self.old_asn_ids)
return self.filter_ids_by_level(ids, self.old_AsnStandards, 2)
# filter threshold for mapping files is 2, since mapping contains only levels 3 and 4
def new_asn_not_in_mapping(self):
ids = self.set_diff(self.new_asn_ids, self.mapped_ids)
return self.filter_ids_by_level(ids, self.new_AsnStandards, 2)
# filter threshold for mapping files is 2, since mapping contains only levels 3 and 4
def old_asn_not_in_mapping(self):
ids = self.set_diff(self.old_asn_ids, self.mapped_ids)
return self.filter_ids_by_level(ids, self.old_AsnStandards, 2)
def report_new(self):
ids = self.mapping_not_in_new_asn()
if ids:
print "\nIds in Mapping but not in NEW ASN doc (%d)" % len(ids)
for id in ids:
std = self.old_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
else:
print "\nAll Ids in mapping are present in NEW ASN doc"
ids = self.new_asn_not_in_mapping()
if ids:
print "\nIds in NEW ASN but not in Mapping (%d)" % len(ids)
for id in ids:
std = self.new_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
else:
print "\nAll NEW ASN Ids are present in mapping doc"
def report_old(self):
ids = self.mapping_not_in_old_asn()
if ids and 0:
print "\nIds in Mapping but not in OLD ASN doc (%d)" % len(ids)
for id in ids:
std = self.old_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
ids = self.old_asn_not_in_mapping()
if ids:
print "\nIds in OLD ASN but not in Mapping (%d)" % len(ids)
for id in ids:
std = self.old_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
def report_asn_diff(self):
ids = self.new_asn_not_in_old_asn()
if 1:
print "\nNEW ASN stds not in OLD ASN stds (%d)" % len(ids)
for id in ids:
std = self.new_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
ids = self.old_asn_not_in_new_asn()
if 1:
print "\nOLD ASN stds not in NEW ASN stds (%d)" % len(ids)
for id in ids:
std = self.old_AsnStandards[id]
print "\t%s level: %d" % (getNumId(id), std.level + 1)
def filter_ids_by_level(self, ids, standardsDoc, threshold=None):
"""
1 - sort the ids as strings (just to put them in some consistent order)
2 - filter out the standards for level less than threshold (if provided)
3 - sort by level (in standards hierarchy)
"""
filtered = []
ids.sort()
for id in ids:
level = standardsDoc[id].level + 1
if threshold:
if level > threshold:
filtered.append(id)
else:
filtered.append(id)
return self.sort_by_level(filtered, standardsDoc)
def sort_by_level(self, ids, standardsDoc):
bins = {}
for id in ids:
level = standardsDoc[id].level + 1
if not bins.has_key(level):
bins[level] = []
items = bins[level]
items.append(id)
bins[level] = items
sorted_ids = []
add = sorted_ids.append
for level in bins.keys():
items = bins[level]
for id in items:
add(id)
return sorted_ids
def report(self):
self.report_new()
self.report_old()
self.report_asn_diff()
def getUrl(self, url):
try:
data = urllib.urlopen(url) # open file by url
return data.read()
except IOError, error_code: # catch the error
if error_code[0] == "http error":
print "error: ", error_code[1]
def __init__(self, path):
UserDict.__init__(self)
self.NSES = StdDocument(NSESpath)
self.groups = SubjectGroupMap()
self._init_pool()