diff options
author | Bryan Newbold <bnewbold@robocracy.org> | 2019-06-13 14:24:16 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@robocracy.org> | 2019-06-13 14:24:16 -0700 |
commit | 404f6ff6d542dc6dc61395cdb25646e3a69eb061 (patch) | |
tree | c70a5421be53f935674f64f0d519a31e32fba4d4 /python/fatcat_web/entity_helpers.py | |
parent | 95286700bbe06c8c0676e08acc0b6dc4a8f8504d (diff) | |
download | fatcat-404f6ff6d542dc6dc61395cdb25646e3a69eb061.tar.gz fatcat-404f6ff6d542dc6dc61395cdb25646e3a69eb061.zip |
implement major refactor for other entity types
Diffstat (limited to 'python/fatcat_web/entity_helpers.py')
-rw-r--r-- | python/fatcat_web/entity_helpers.py | 135 |
1 files changed, 121 insertions, 14 deletions
diff --git a/python/fatcat_web/entity_helpers.py b/python/fatcat_web/entity_helpers.py index 8a28deb3..b3cda67f 100644 --- a/python/fatcat_web/entity_helpers.py +++ b/python/fatcat_web/entity_helpers.py @@ -2,16 +2,105 @@ from flask import abort from fatcat_client.rest import ApiException from fatcat_tools.transforms import * -from fatcat_web import api +from fatcat_web import app, api +from fatcat_web.search import get_elastic_container_stats +from fatcat_web.hacks import strip_extlink_xml, wayback_suffix +def enrich_container_entity(entity): + if entity.state in ('redirect', 'deleted'): + return entity + if entity.state == "active": + entity._es = container_to_elasticsearch(entity, force_bool=False) + entity._stats = None + if entity.issnl: + try: + entity._stats = get_elastic_container_stats(entity.issnl) + except Exception as e: + app.log.error(e) + pass + return entity + +def enrich_creator_entity(entity): + if entity.state in ('redirect', 'deleted'): + return entity + entity._releases = None + if entity.state in ('active', 'wip'): + entity._releases = api.get_creator_releases(entity.ident) + return entity + +def enrich_file_entity(entity): + return entity + +def enrich_fileset_entity(entity): + if entity.state in ('redirect', 'deleted'): + return entity + entity._total_size = None + if entity.manifest != None: + entity._total_size = sum([f.size for f in entity.manifest]) or 0 + return entity + +def enrich_webcapture_entity(entity): + if entity.state in ('redirect', 'deleted'): + return entity + entity.wayback_suffix = wayback_suffix(entity) + return entity + +def enrich_release_entity(entity): + if entity.state in ('redirect', 'deleted'): + return entity + if entity.state == "active": + entity._es = release_to_elasticsearch(entity, force_bool=False) + if entity.container and entity.container.state == "active": + entity.container._es = container_to_elasticsearch(entity.container, force_bool=False) + if entity.filesets: + for fs in entity.filesets: + fs._total_size = sum([f.size for f in fs.manifest]) + if entity.webcaptures: + for wc in entity.webcaptures: + wc._wayback_suffix = wayback_suffix(wc) + for ref in entity.refs: + # this is a UI hack to get rid of XML crud in unstructured refs like: + # LOCKSS (2014) Available: <ext-link + # xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" + # xlink:href="http://lockss.org/" + # xlink:type="simple">http://lockss.org/</ext-link>. Accessed: 2014 + # November 1. + if ref.extra and ref.extra.get('unstructured'): + ref.extra['unstructured'] = strip_extlink_xml(ref.extra['unstructured']) + # author list to display; ensure it's sorted by index (any othors with + # index=None go to end of list) + authors = [c for c in entity.contribs if c.role in ('author', None)] + entity._authors = sorted(authors, key=lambda c: (c.index == None and 99999999) or c.index) + # hack to show plain text instead of latex abstracts + if entity.abstracts: + if 'latex' in entity.abstracts[0].mimetype: + entity.abstracts.reverse() + return entity + +def enrich_work_entity(entity): + if entity.state in ('redirect', 'deleted'): + return entity + entity._releases = None + if entity.state in ('active', 'wip'): + entity._releases = api.get_work_releases(entity.ident) + return entity def generic_get_entity(entity_type, ident): try: if entity_type == 'container': - entity = api.get_container(ident) - if entity.state == "active": - entity.es = container_to_elasticsearch(entity, force_bool=False) - return entity + return enrich_container_entity(api.get_container(ident)) + elif entity_type == 'creator': + return enrich_creator_entity(api.get_creator(ident)) + elif entity_type == 'file': + return enrich_file_entity(api.get_file(ident, expand="releases")) + elif entity_type == 'fileset': + return enrich_fileset_entity(api.get_fileset(ident, expand="releases")) + elif entity_type == 'webcapture': + return enrich_webcapture_entity(api.get_webcapture(ident, expand="releases")) + elif entity_type == 'release': + return enrich_release_entity(api.get_release(ident, expand="container,files,filesets,webcaptures")) + elif entity_type == 'work': + return api.get_work(ident) else: raise NotImplementedError except ApiException as ae: @@ -20,8 +109,19 @@ def generic_get_entity(entity_type, ident): def generic_get_entity_revision(entity_type, revision_id): try: if entity_type == 'container': - entity = api.get_container_revision(revision_id) - return entity + return enrich_container_entity(api.get_container_revision(revision_id)) + elif entity_type == 'creator': + return enrich_creator_entity(api.get_creator_revision(revision_id)) + elif entity_type == 'file': + return enrich_file_entity(api.get_file_revision(revision_id, expand="releases")) + elif entity_type == 'fileset': + return enrich_fileset_entity(api.get_fileset_revision(revision_id, expand="releases")) + elif entity_type == 'webcapture': + return enrich_webcapture_entity(api.get_webcapture_revision(revision_id, expand="releases")) + elif entity_type == 'release': + return enrich_release_entity(api.get_release_revision(revision_id, expand="container")) + elif entity_type == 'work': + return enrich_work_entity(api.get_work_revision(revision_id)) else: raise NotImplementedError except ApiException as ae: @@ -30,6 +130,18 @@ def generic_get_entity_revision(entity_type, revision_id): def generic_get_editgroup_entity(editgroup, entity_type, ident): if entity_type == 'container': edits = editgroup.edits.containers + elif entity_type == 'creator': + edits = editgroup.edits.creators + elif entity_type == 'file': + edits = editgroup.edits.files + elif entity_type == 'fileset': + edits = editgroup.edits.filesets + elif entity_type == 'webcapture': + edits = editgroup.edits.webcaptures + elif entity_type == 'release': + edits = editgroup.edits.releases + elif entity_type == 'work': + edits = editgroup.edits.works else: raise NotImplementedError revision_id = None @@ -41,12 +153,7 @@ def generic_get_editgroup_entity(editgroup, entity_type, ident): if not revision_id: # couldn't find relevent edit in this editgroup abort(404) - try: - if entity_type == 'container': - entity = api.get_container_revision(revision_id) - else: - raise NotImplementedError - except ApiException as ae: - abort(ae.status) + + entity = generic_get_entity_revision(entity_type, revision_id) entity.ident = ident return entity, edit |