def archiveFile_escape(s):
m = re.match('\[(.*?) TO (.*?)\]$', s)
if m is None:
return solr_escape(s)
else:
archiveFile_from = solr_escape(m.groups()[0])
archiveFile_to = solr_escape(m.groups()[1])
return '["{archiveFile_from}" TO "{archiveFile_to}"]'.format(
archiveFile_from=archiveFile_from,
archiveFile_to=archiveFile_to)
def cast_scan_as_archivefile(context, scandata):
"""'extracts' the archive file information from a scan, suitable for solr indexing
scan is a dictionary represting a scan"""
# todo: cleanup code so we don't need to import here
q = 'archive_id:{archive_id} AND archiveFile:{archiveFile}'.format(
archive_id=solr_escape(scandata['archive_id']),
archiveFile=solr_escape(scandata['archiveFile']),
)
documents = context.solr_archivefile.search(q=q).documents
from restrepo.db.archivefile import ArchiveFile
archivefile = ArchiveFile()
if documents:
for k in documents[0]:
setattr(archivefile, k, documents[0][k])
else:
archivefile.archive_id = scandata['archive_id']
archivefile.archiveFile = scandata['archiveFile']
return archivefile
def update_archivefile(request):
"""
update information about this archivefile
parameters:
* **status:** a boolean
a status: a value among :ref:`status_values` (except 0)
* **user**: a string that identifies the user responsible for the udpate
"""
""
_data_changed = False
archivefile = request._dbentity['archivefile']
# find a database record
qry = request.db.query(ArchiveFile)
qry = qry.filter(ArchiveFile.archive_id == archivefile['archive_id'])
qry = qry.filter(ArchiveFile.archiveFile == archivefile['archiveFile'])
try:
archivefile_db = qry.one()
except sqlalchemy.orm.exc.NoResultFound:
# if we do not find this archivefile in the database
# we create a new db record
archivefile_db = ArchiveFile()
for key in archivefile:
setattr(archivefile_db, key, archivefile[key])
request.db.add(archivefile_db)
_data_changed = True
data = request.validated
for k in data:
if k in request.POST and k not in ['user']: # only update with data that is explicitly given
if data[k] != getattr(archivefile_db, k):
setattr(archivefile_db, k, data[k])
# also update the object that we are about to return
archivefile[k] = data[k]
_data_changed = True
if _data_changed:
request.db.flush()
# update the index
request.solr_archivefile.update([archivefile_db.get_solr_data(request)])
# request.solr_archivefile.update([archivefile])
if data:
q = 'archive_id:{archive_id} AND archiveFile:{archiveFile}'.format(
archive_id=solr_escape(archivefile['archive_id']),
archiveFile=solr_escape(archivefile['archiveFile']),
)
documents = request.solr_eadcomponent.search(q=q).documents
if documents:
for document in documents:
document['status'] = data['status']
request.solr_eadcomponent.update(documents)
user = get_user(request)
log_events(request.db, user, [{
'message': 'update', 'object_id': archivefile['id'], 'object_type': 'archivefile'
}])
for ead_id in archivefile_db.ead_ids:
if archivefile_db.status == STATUS_PUBLISHED:
pagebrowser.update.refresh_book(request, ead_id=ead_id, archivefile_id=archivefile_db.id)
else:
pagebrowser.update.delete_book(request, ead_id=ead_id, archivefile_id=archivefile_db.id)
return archivefile
def search_archivefiles(context, **kwargs):
"""
possible arguments:
start
limit
date_from
date_to
archive
archive_id
archiveFile
country
contains_text
ead_id
findingaid
institution
is_archiveFile
is_component
parent
show_in_tree
language
xpath
with_facets : return the argument with facets, default is True
"""
start = kwargs.get('start', 0)
limit = kwargs.get('limit', 1000)
conditions = []
query_used = {}
with_facets = kwargs.get('with_facets', True)
if with_facets:
query = {
'facet': 'true',
'facet.field': ['country', 'language'],
'start': start,
'rows': limit,
}
else:
query = {}
date_from = kwargs.get('date_from')
date_to = kwargs.get('date_to')
if date_from:
date_from = datetime_to_string_zulu(date_from)
if date_to:
date_to = datetime_to_string_zulu(date_to)
if date_from or date_to:
date_from = date_from or '*'
date_to = date_to or '*'
conditions.append('date_from:[* TO %(date_to)s]' % locals())
conditions.append('date_to:[%(date_from)s TO *]' % locals())
for k in [
'archive',
'archive_id',
'archiveFile',
'country',
'contains_text',
'ead_id',
'findingaid',
'institution',
'is_component',
'language',
'parent',
'show_in_tree',
'xpath',
]:
value = kwargs.get(k, None)
if k == 'is_component' and not value:
value = None
if value is not None:
query_used[k] = value
value = solr_escape(value)
value = '"%s"' % value.strip('"')
if k == 'contains_text':
value = value.lower()
conditions.append('search_source:%s' % value)
# cf. http://wiki.apache.org/solr/HighlightingParameters
query['hl'] = True
query['hl.fl'] = 'search_source'
query['hl.q'] = 'search_source:%s' % value
else:
conditions.append('%s:%s' % (k, value))
query['q'] = ' AND '.join(conditions) if conditions else '*:*'
response = context.solr_archivefile.search(**query)
results = response.documents
for result in results:
if 'breadcrumbs' in result:
result['breadcrumbs'] = json.loads(result['breadcrumbs'])
else:
result['breadcrumbs'] = []
total_results = response.total_results
start = response.start
end = start + len(results)
if query.get('hl'):
# incluce highlighted phrases in the results
for component in results:
component_id = 'archivefile=%s' % component['id']
component['snippet'] = response.highlighting[component_id].get(
'search_source', '')
return {
'results': results,
'query_used': query_used,
'total_results': total_results,
'start': start,
'end': end,
'facets': with_facets and response.facets['facet_fields'] or {},
}
def get_archivefiles(
context,
ead_id=None,
archive_id=None,
archivefile_id=None,
archiveFile=None,
archiveFiles=[],
has_scans=None,
status=None,
start=0,
limit=10000,
sort='sort_field asc',
):
q = ['*:*']
if ead_id:
q.append('ead_ids:%s' % solr_escape(ead_id))
if archive_id:
archive_id = int(archive_id)
q.append('archive_id:%s' % solr_escape(archive_id))
if archivefile_id:
q.append('archivefile_id:%s' % solr_escape(archivefile_id))
def archiveFile_escape(s):
m = re.match('\[(.*?) TO (.*?)\]$', s)
if m is None:
return solr_escape(s)
else:
archiveFile_from = solr_escape(m.groups()[0])
archiveFile_to = solr_escape(m.groups()[1])
return '["{archiveFile_from}" TO "{archiveFile_to}"]'.format(
archiveFile_from=archiveFile_from,
archiveFile_to=archiveFile_to)
if archiveFile:
q.append('archiveFile:%s' % archiveFile_escape(archiveFile))
if archiveFiles:
q.append('archiveFile:(%s)' %
' OR '.join(archiveFile_escape(s) for s in archiveFiles))
if status is not None:
q.append('status:%s' % status)
if has_scans is not None:
if has_scans:
q.append('number_of_scans:[1 TO *]')
else:
q.append('number_of_scans:0')
q = ' AND '.join(q)
response = context.solr_archivefile.search(q=q,
rows=limit,
start=start,
sort=sort)
results = response.documents
results = [archivefile_solr_to_json(context, x) for x in results]
total_results = response.total_results
return total_results, results