def records_by_author (context, author):
cursor = context.get_cursor()
queued_records = []
source_catalog = context.get_source_catalog()
complete_mapping = source_catalog.get_complete_mapping()
term_list = complete_mapping['author']
term_clause = ' OR '.join(['queued_record_metadata.term_id=%s' % term.uid for term in term_list])
try:
select_clause = """
SELECT queued_records.uid
FROM queued_records, queued_record_metadata, studies
WHERE queued_records.uid = queued_record_metadata.queued_record_id
AND queued_records.uid = studies.record_id
AND queued_records.status = 2
AND studies.article_type >= 2
AND studies.article_type < 8
AND (%s)
""" % term_clause
cursor.execute(select_clause + """
AND value LIKE %s
""", str(author) + '%'
)
rows = cursor.fetchall()
for row in rows:
queued_record = QueuedRecord(context, row[0])
queued_records.append(queued_record)
except Exception, e:
context.logger.error('Records by author: %s', e)
def records_by_author_index (context):
cursor = context.get_cursor()
results = []
source_catalog = context.get_source_catalog()
complete_mapping = source_catalog.get_complete_mapping()
term_list = complete_mapping['author']
term_clause = ' OR '.join(['term_id=%s' % term.uid for term in term_list])
select_clause = """
SELECT COUNT(*) AS the_count, value
FROM queued_record_metadata, queued_records, studies
WHERE queued_record_metadata.queued_record_id = queued_records.uid
AND queued_records.uid = studies.record_id
AND queued_records.status = 2
AND studies.article_type >= 2
AND studies.article_type < 8
AND (%s)
GROUP BY value
ORDER BY value
""" % term_clause
cursor.execute(select_clause)
rows = cursor.fetchall()
results.extend([(r[0], r[1]) for r in rows])
return results
dest='field',
default='all',
help='field to search')
parser.add_option('-l',
'--locations',
dest='locations',
action='store_true',
default=False,
help='report location data only?')
(options, args) = parser.parse_args()
config = canary.context.CanaryConfig()
config.read_file(options.config)
context = canary.context.Context(config)
source_catalog = context.get_source_catalog()
ctm = source_catalog.get_complete_mapping()
if not args:
print usage
sys.exit(0)
query_str = options.boolean.join(
[' "%s" [%s] ' % (term, options.field) for term in args])
#print query_str.strip()
search_index = SearchIndex(context)
hit_list = []
hits, searcher = search_index.search(query_str)
for i, doc in hits:
hit_list.append(doc.get('uid'))
dest='canary_id', default=0,
help='specific canary id to fetch')
parser.add_option('-c', '--config',
dest='config', default='conf/canary_config.py',
help='path to configuration file')
parser.add_option('-u', '--update',
action='store_true', dest='update', default=False,
help='save updated data to the database')
(options, args) = parser.parse_args()
context = canary.context.Context()
cursor = context.get_cursor()
# get a complete mapping
source_catalog = context.get_source_catalog()
complete_mapping = source_catalog.get_complete_mapping()
# pubmed-medline is source 13
pubmed_source = source_catalog.get_source(13)
pubmed_search = PubmedSearch()
if options.canary_id:
rows = [[options.canary_id,],]
else:
# get all active queuedrecord ids
cursor.execute("""
SELECT uid
FROM queued_records
""")
rows = cursor.fetchall()
