def matches(id, other_id):
collection = get_db_collection(id)
other = get_db_collection(other_id)
parser = QueryParser(request.args, request.authz, limit=10)
q = Match.find_by_collection(collection.id, other.id)
result = DatabaseQueryResult(request, q, parser=parser, schema=MatchSchema)
return jsonify(result)
def matches(collection_id, other_id):
collection = get_db_collection(collection_id)
other = get_db_collection(other_id)
parser = QueryParser(request.args, request.authz)
q = Match.find_by_collection(collection.id, other.id)
result = DatabaseQueryResult(request, q, parser=parser)
return MatchSerializer.jsonify_result(result)
def matches(id, other_id):
collection = obj_or_404(Collection.by_id(id))
require(request.authz.can_read(collection.id))
require(request.authz.can_read(other_id))
parser = QueryParser(request.args, request.authz, limit=10)
q = Match.find_by_collection(collection.id, other_id)
result = MatchQueryResult(request, q, parser=parser, schema=MatchSchema)
return jsonify(result)
def matches(id, other_id):
collection = get_db_collection(id)
record_audit(Audit.ACT_COLLECTION, id=collection.id)
other = get_db_collection(other_id)
record_audit(Audit.ACT_COLLECTION, id=other.id)
parser = QueryParser(request.args, request.authz)
q = Match.find_by_collection(collection.id, other.id)
result = DatabaseQueryResult(request, q, parser=parser, schema=MatchSchema)
return jsonify(result)
def matches(collection_id, other_id):
collection = get_db_collection(collection_id)
record_audit(Audit.ACT_COLLECTION, id=collection.id)
other = get_db_collection(other_id)
record_audit(Audit.ACT_COLLECTION, id=other.id)
parser = QueryParser(request.args, request.authz)
q = Match.find_by_collection(collection.id, other.id)
result = DatabaseQueryResult(request, q, parser=parser)
return MatchSerializer.jsonify_result(result)
def matches(collection_id, other_id):
"""
---
get:
summary: Fetch cross-reference matches between collections
description: >-
Fetch cross-reference matches between 2 collections with ids
`collection_id` and `other_id`
parameters:
- in: path
name: collection_id
required: true
schema:
type: integer
- in: path
name: other_id
required: true
schema:
type: integer
responses:
'200':
description: OK
content:
application/json:
schema:
type: object
allOf:
- $ref: '#/components/schemas/QueryResponse'
properties:
results:
type: array
items:
$ref: '#/components/schemas/XrefMatch'
tags:
- Xref
- Collection
"""
collection = get_db_collection(collection_id)
other = get_db_collection(other_id)
parser = QueryParser(request.args, request.authz)
q = Match.find_by_collection(collection.id, other.id)
result = DatabaseQueryResult(request, q, parser=parser)
return MatchSerializer.jsonify_result(result)
def generate_matches_sheet(workbook,
sheet,
collection,
match_collection,
authz,
links=True,
one_sheet=False,
offset=0,
limit=1000):
from aleph.views.serializers import MatchSchema
if one_sheet:
sheet_label = "All matches (top %s per collection)" % limit
else:
sheet_label = "%s (top %s)" % (match_collection.label, limit)
sheet.set_zoom(125)
parser = QueryParser({}, authz, limit=limit)
q_match = Match.find_by_collection(collection.id, match_collection.id)
matches = MatchQueryResult({}, q_match, parser=parser, schema=MatchSchema)
if offset < 3:
sheet.write(0, 0, '', workbook.header_format)
sheet.write(1, 0, 'Score', workbook.header_format)
sheet.merge_range(0, 1, 0, 4, collection.label, workbook.header_format)
sheet.write(1, 1, 'Name', workbook.header_format)
sheet.write(1, 2, 'Type', workbook.header_format)
sheet.write(1, 3, 'Country', workbook.header_format)
sheet.write(1, 4, 'Source URL', workbook.header_format)
sheet.merge_range(0, 5, 0, 8, sheet_label, workbook.header_format)
sheet.write(1, 5, 'Name', workbook.header_format)
sheet.write(1, 6, 'Type', workbook.header_format)
sheet.write(1, 7, 'Country', workbook.header_format)
if one_sheet:
sheet.write(1, 8, 'Collection', workbook.header_format)
sheet.freeze_panes(2, 0)
sheet.autofilter(1, 1, 2 + len(matches.results), 8)
widths = {}
for row, result in enumerate(matches.results, offset):
sheet.write_number(row, 0, int(result.score))
name = result.entity.get('name')
widths[1] = max(widths.get(1, 0), len(name))
if links:
url = entity_url(result.entity_id)
sheet.write_url(row, 1, url, workbook.link_format, name)
else:
sheet.write_string(row, 1, name)
schema = model.get(result.entity['schema'])
sheet.write_string(row, 2, schema.label)
countries = ', '.join(sorted(result.entity.get('countries', [])))
sheet.write_string(row, 3, countries.upper())
ent_props = result.entity.get('properties', {})
if (ent_props.get('sourceUrl') is not None):
source_url = ', '.join(ent_props.get('sourceUrl'))
else:
source_url = ''
sheet.write_string(row, 4, source_url)
name = result.match.get('name')
widths[5] = max(widths.get(5, 0), len(name))
if links:
url = entity_url(result.match_id)
sheet.write_url(row, 5, url, workbook.link_format, name)
else:
sheet.write_string(row, 5, name)
schema = model.get(result.match['schema'])
sheet.write_string(row, 6, schema.label)
countries = ', '.join(sorted(result.match.get('countries', [])))
sheet.write_string(row, 7, countries.upper())
if one_sheet:
sheet.write_string(row, 8, match_collection.label)
for idx, max_len in widths.items():
max_len = min(70, max(7, max_len + 1))
sheet.set_column(idx, idx, float(max_len))
return sheet
