Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CSW harvester OutputSchema config support #258 #259

Open
wants to merge 9 commits into
base: master
Choose a base branch
from
Open

CSW harvester OutputSchema config support #258 #259

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
e2349d9
CSW harvester OutputSchema config support #258
ccancellieri Oct 22, 2021
33d9b70
fix special character formatting
ccancellieri Oct 22, 2021
855ab7d
preload config to read namespace if necessary. Generalize metadata na…
ccancellieri Oct 22, 2021
bf2d1d6
lets reload config at each run (the config can be different for each …
ccancellieri Oct 22, 2021
fbd5d1c
improve checks and comments
ccancellieri Oct 23, 2021
9d36378
namespace from getcapabilities also for getrecords
ccancellieri Oct 23, 2021
4fb17cc
documentation, pep8 and improve are requested
ccancellieri Oct 28, 2021
f91f516
fallback to default schema
ccancellieri Oct 28, 2021
b82eb89
fallback to default schema
ccancellieri Oct 28, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions ckanext/spatial/harvesters/csw.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,10 +159,14 @@ def fetch_stage(self,harvest_object):
self._save_object_error('Error contacting the CSW server: %s' % e,
harvest_object)
return False


# load config
self._set_source_config(harvest_object.source.config)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you document the new output_schema option and its default value in here so others are aware of it?

https://github.com/ckan/ckanext-spatial/blob/master/doc/harvesters.rst

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

added fallback to default in case the server is not supporting iso19139 -> 19115 transformation
the fallback will log and switch back to default asking for iso19139 -> iso19139.

# get output_schema from config
namespace = self.source_config.get('output_schema',self.output_schema())
identifier = harvest_object.guid
try:
record = self.csw.getrecordbyid([identifier], outputschema=self.output_schema())
record = self.csw.getrecordbyid([identifier], outputschema=namespace)
except Exception as e:
self._save_object_error('Error getting the CSW record with GUID %s' % identifier, harvest_object)
return False
Expand Down
59 changes: 47 additions & 12 deletions ckanext/spatial/lib/csw_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,14 +70,36 @@ class CswService(OwsService):
def __init__(self, endpoint=None):
super(CswService, self).__init__(endpoint)
self.sortby = SortBy([SortProperty('dc:identifier')])
# check capabilities
_cap = self.getcapabilities(endpoint)['response']
self.capabilities=etree.ElementTree(etree.fromstring(_cap))
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please try to follow PEP8 guidelines, specially spacing between = and , :)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sorry, I can't validate the whole project and my code editor is not helping me, good catch, I'll try to fix my bad.


def _get_output_schemas(self, operation):
_cap_ns = self.capabilities.getroot().nsmap
_ows_ns = _cap_ns.get('ows')
if not _ows_ns:
raise CswError('Bad getcapabilities response: OWS namespace not found '+str(_cap_ns))
_op=self.capabilities.find("//{{{}}}Operation[@name='{}']".format(_ows_ns,operation))
_schemas=_op.find("{{{}}}Parameter[@name='outputSchema']".format(_ows_ns))
_values = map(lambda v: v.text, _schemas.findall("{{{}}}Value".format(_ows_ns)))
output_schemas={}
for key, value in _schemas.nsmap.items():
if value in _values:
output_schemas.update({key:value})
return output_schemas

def getrecords(self, qtype=None, keywords=[],
typenames="csw:Record", esn="brief",
skip=0, count=10, outputschema="gmd", **kw):
from owslib.csw import namespaces

constraints = []
csw = self._ows(**kw)

# fetch target csw server capabilities for requested output schema
output_schemas=self._get_output_schemas('GetRecords')
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we move this call to the __init__() method to avoid duplication and multiple calls to GetCapabilities?
Something like:

def __init__(self, endpoint=None):
    _cap = self.getcapabilities(endpoint)['response']
    self.capabilities = etree.ElementTree(etree.fromstring(_cap))
    self.output_schemas = {
        'GetRecords': self._get_output_schemas('GetRecords'),
        'GetRecordById': self._get_output_schemas('GetRecordById'),
    }

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

if not output_schemas.get(outputschema):
raise CswError('Output schema \'{}\' not supported by target server: '.format(output_schemas))

if qtype is not None:
constraints.append(PropertyIsEqualTo("dc:type", qtype))

Expand All @@ -87,7 +109,7 @@ def getrecords(self, qtype=None, keywords=[],
"esn": esn,
"startposition": skip,
"maxrecords": count,
"outputschema": namespaces[outputschema],
"outputschema": output_schemas[outputschema],
"sortby": self.sortby
}
log.info('Making CSW request: getrecords2 %r', kwa)
Expand All @@ -102,10 +124,15 @@ def getrecords(self, qtype=None, keywords=[],
def getidentifiers(self, qtype=None, typenames="csw:Record", esn="brief",
keywords=[], limit=None, page=10, outputschema="gmd",
startposition=0, cql=None, **kw):
from owslib.csw import namespaces

constraints = []
csw = self._ows(**kw)

# fetch target csw server capabilities for requested output schema
output_schemas=self._get_output_schemas('GetRecords')
if not output_schemas.get(outputschema):
raise CswError('Output schema \'{}\' not supported by target server: '.format(output_schemas))

if qtype is not None:
constraints.append(PropertyIsEqualTo("dc:type", qtype))

Expand All @@ -115,7 +142,7 @@ def getidentifiers(self, qtype=None, typenames="csw:Record", esn="brief",
"esn": esn,
"startposition": startposition,
"maxrecords": page,
"outputschema": namespaces[outputschema],
"outputschema": output_schemas[outputschema],
"cql": cql,
"sortby": self.sortby
}
Expand All @@ -129,7 +156,6 @@ def getidentifiers(self, qtype=None, typenames="csw:Record", esn="brief",
err = 'Error getting identifiers: %r' % \
csw.exceptionreport.exceptions
#log.error(err)
raise CswError(err)

if matches == 0:
matches = csw.results['matches']
Expand All @@ -154,11 +180,17 @@ def getidentifiers(self, qtype=None, typenames="csw:Record", esn="brief",
kwa["startposition"] = startposition

def getrecordbyid(self, ids=[], esn="full", outputschema="gmd", **kw):
from owslib.csw import namespaces

csw = self._ows(**kw)

# fetch target csw server capabilities for requested output schema
output_schemas=self._get_output_schemas('GetRecordById')
if not output_schemas.get(outputschema):
raise CswError('Output schema \'{}\' not supported by target server: '.format(output_schemas))
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Probably here I should be more tolerant Logging ERROR and returning.


kwa = {
"esn": esn,
"outputschema": namespaces[outputschema],
"outputschema": output_schemas[outputschema],
}
# Ordinary Python version's don't support the metadata argument
log.info('Making CSW request: getrecordbyid %r %r', ids, kwa)
Expand All @@ -168,14 +200,17 @@ def getrecordbyid(self, ids=[], esn="full", outputschema="gmd", **kw):
csw.exceptionreport.exceptions
#log.error(err)
raise CswError(err)
if not csw.records:
elif csw.records:
record = self._xmd(list(csw.records.values())[0])
elif csw.response:
record = self._xmd(etree.fromstring(csw.response))
else:
return
record = self._xmd(list(csw.records.values())[0])

## strip off the enclosing results container, we only want the metadata
#md = csw._exml.find("/gmd:MD_Metadata")#, namespaces=namespaces)
# Ordinary Python version's don't support the metadata argument
md = csw._exml.find("/{http://www.isotc211.org/2005/gmd}MD_Metadata")
# '/{schema}*' expression should be safe enough and is able to match the
# desired schema followed by both MD_Metadata or MI_Metadata (iso19115[-2])
md = csw._exml.find("/{{{schema}}}*".format(schema=output_schemas[outputschema]))
mdtree = etree.ElementTree(md)
try:
record["xml"] = etree.tostring(mdtree, pretty_print=True, encoding=str)
Expand Down