Skip to content

Commit 8d965c5

Browse files
Pawel Zembrzuskidrjova
Pawel Zembrzuski
authored and
drjova
committed
setup: remove invenio-files
 *INSPIR-3105
1 parent 2d81d9f commit 8d965c5

File tree

6 files changed

+20
-464
lines changed

6 files changed

+20
-464
lines changed

‎backend/inspirehep/alembic/7be4c8b5c5e8_inspirehep_new_migrations.py‎

Lines changed: 3 additions & 302 deletions
Original file line numberDiff line numberDiff line change
@@ -8,9 +8,6 @@
88
"""Inspirehep initial revision of migrations
99
which makes db identical like in inspire-next"""
1010

11-
import sqlalchemy as sa
12-
from alembic import op
13-
from sqlalchemy.dialects import postgresql
1411

1512
# revision identifiers, used by Alembic.
1613
revision = "7be4c8b5c5e8"
@@ -19,312 +16,16 @@
1916

2017
"""Migrations which are required and inspirehep is depending on:
2118
07fb52561c5c - invenio-records,
22-
1ba76da94103 - invenio-records-files
23-
f741aa746a7d - invenio-files-rest
2419
e12419831262 - invenio-accounts
2520
"""
26-
depends_on = "07fb52561c5c", "1ba76da94103", "f741aa746a7d", "e12419831262"
21+
depends_on = "07fb52561c5c", "e12419831262"
2722

2823

2924
def upgrade():
3025
# """Upgrade database."""
31-
op.create_table(
32-
"workflows_workflow",
33-
sa.Column("uuid", postgresql.UUID(), autoincrement=False, nullable=False),
34-
sa.Column("name", sa.VARCHAR(length=255), autoincrement=False, nullable=False),
35-
sa.Column(
36-
"created", postgresql.TIMESTAMP(), autoincrement=False, nullable=False
37-
),
38-
sa.Column(
39-
"modified", postgresql.TIMESTAMP(), autoincrement=False, nullable=False
40-
),
41-
sa.Column("id_user", sa.INTEGER(), autoincrement=False, nullable=False),
42-
sa.Column(
43-
"extra_data",
44-
postgresql.JSON(astext_type=sa.Text()),
45-
autoincrement=False,
46-
nullable=False,
47-
),
48-
sa.Column("status", sa.INTEGER(), autoincrement=False, nullable=False),
49-
sa.PrimaryKeyConstraint("uuid", name="pk_workflows_workflow"),
50-
)
51-
op.create_table(
52-
"workflows_object",
53-
sa.Column(
54-
"id",
55-
sa.INTEGER(),
56-
server_default=sa.text("nextval('workflows_object_id_seq'::regclass)"),
57-
autoincrement=True,
58-
nullable=False,
59-
),
60-
sa.Column(
61-
"data",
62-
postgresql.JSON(astext_type=sa.Text()),
63-
autoincrement=False,
64-
nullable=False,
65-
),
66-
sa.Column(
67-
"extra_data",
68-
postgresql.JSON(astext_type=sa.Text()),
69-
autoincrement=False,
70-
nullable=False,
71-
),
72-
sa.Column("id_workflow", postgresql.UUID(), autoincrement=False, nullable=True),
73-
sa.Column("status", sa.INTEGER(), autoincrement=False, nullable=False),
74-
sa.Column("id_parent", sa.INTEGER(), autoincrement=False, nullable=True),
75-
sa.Column("id_user", sa.INTEGER(), autoincrement=False, nullable=False),
76-
sa.Column(
77-
"created", postgresql.TIMESTAMP(), autoincrement=False, nullable=False
78-
),
79-
sa.Column(
80-
"modified", postgresql.TIMESTAMP(), autoincrement=False, nullable=False
81-
),
82-
sa.Column(
83-
"data_type", sa.VARCHAR(length=150), autoincrement=False, nullable=True
84-
),
85-
sa.Column(
86-
"callback_pos",
87-
postgresql.JSON(astext_type=sa.Text()),
88-
autoincrement=False,
89-
nullable=True,
90-
),
91-
sa.ForeignKeyConstraint(
92-
["id_parent"],
93-
["workflows_object.id"],
94-
name="fk_workflows_object_id_parent_workflows_object",
95-
ondelete="CASCADE",
96-
),
97-
sa.ForeignKeyConstraint(
98-
["id_workflow"],
99-
["workflows_workflow.uuid"],
100-
name="fk_workflows_object_id_workflow_workflows_workflow",
101-
ondelete="CASCADE",
102-
),
103-
sa.PrimaryKeyConstraint("id", name="pk_workflows_object"),
104-
postgresql_ignore_search_path=False,
105-
)
106-
op.create_index(
107-
"ix_workflows_object_status", "workflows_object", ["status"], unique=False
108-
)
109-
op.create_index(
110-
"ix_workflows_object_id_workflow",
111-
"workflows_object",
112-
["id_workflow"],
113-
unique=False,
114-
)
115-
op.create_index(
116-
"ix_workflows_object_id_parent", "workflows_object", ["id_parent"], unique=False
117-
)
118-
op.create_index(
119-
"ix_workflows_object_data_type", "workflows_object", ["data_type"], unique=False
120-
)
121-
op.create_table(
122-
"workflows_buckets",
123-
sa.Column(
124-
"workflow_object_id", sa.INTEGER(), autoincrement=False, nullable=False
125-
),
126-
sa.Column("bucket_id", postgresql.UUID(), autoincrement=False, nullable=False),
127-
sa.ForeignKeyConstraint(
128-
["bucket_id"],
129-
["files_bucket.id"],
130-
name="fk_workflows_buckets_bucket_id_files_bucket",
131-
onupdate="CASCADE",
132-
ondelete="CASCADE",
133-
),
134-
sa.ForeignKeyConstraint(
135-
["workflow_object_id"],
136-
["workflows_object.id"],
137-
name="fk_workflows_buckets_workflow_object_id_workflows_object",
138-
onupdate="CASCADE",
139-
ondelete="CASCADE",
140-
),
141-
sa.PrimaryKeyConstraint(
142-
"workflow_object_id", "bucket_id", name="pk_workflows_buckets"
143-
),
144-
)
145-
op.create_table(
146-
"workflows_audit_logging",
147-
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
148-
sa.Column("user_id", sa.INTEGER(), autoincrement=False, nullable=True),
149-
sa.Column(
150-
"score",
151-
postgresql.DOUBLE_PRECISION(precision=53),
152-
autoincrement=False,
153-
nullable=False,
154-
),
155-
sa.Column("user_action", sa.TEXT(), autoincrement=False, nullable=False),
156-
sa.Column("decision", sa.TEXT(), autoincrement=False, nullable=False),
157-
sa.Column("source", sa.TEXT(), autoincrement=False, nullable=False),
158-
sa.Column("action", sa.TEXT(), autoincrement=False, nullable=False),
159-
sa.Column(
160-
"created", postgresql.TIMESTAMP(), autoincrement=False, nullable=False
161-
),
162-
sa.Column("object_id", sa.INTEGER(), autoincrement=False, nullable=False),
163-
sa.ForeignKeyConstraint(
164-
["object_id"],
165-
["workflows_object.id"],
166-
name="fk_workflows_audit_logging_object_id_workflows_object",
167-
ondelete="CASCADE",
168-
),
169-
sa.ForeignKeyConstraint(
170-
["user_id"],
171-
["accounts_user.id"],
172-
name="fk_workflows_audit_logging_user_id_accounts_user",
173-
ondelete="CASCADE",
174-
),
175-
sa.PrimaryKeyConstraint("id", name="pk_workflows_audit_logging"),
176-
)
177-
op.create_index(
178-
"ix_workflows_audit_logging_user_id",
179-
"workflows_audit_logging",
180-
["user_id"],
181-
unique=False,
182-
)
183-
op.create_index(
184-
"ix_workflows_audit_logging_object_id",
185-
"workflows_audit_logging",
186-
["object_id"],
187-
unique=False,
188-
)
189-
op.create_table(
190-
"crawler_job",
191-
sa.Column("id", sa.INTEGER(), autoincrement=True, nullable=False),
192-
sa.Column("job_id", postgresql.UUID(), autoincrement=False, nullable=True),
193-
sa.Column("spider", sa.VARCHAR(length=255), autoincrement=False, nullable=True),
194-
sa.Column(
195-
"workflow", sa.VARCHAR(length=255), autoincrement=False, nullable=True
196-
),
197-
sa.Column("results", sa.TEXT(), autoincrement=False, nullable=True),
198-
sa.Column("status", sa.VARCHAR(length=10), autoincrement=False, nullable=False),
199-
sa.Column("logs", sa.TEXT(), autoincrement=False, nullable=True),
200-
sa.Column(
201-
"scheduled", postgresql.TIMESTAMP(), autoincrement=False, nullable=False
202-
),
203-
sa.PrimaryKeyConstraint("id", name="pk_crawler_job"),
204-
)
205-
op.create_index(
206-
"ix_crawler_job_workflow", "crawler_job", ["workflow"], unique=False
207-
)
208-
op.create_index("ix_crawler_job_spider", "crawler_job", ["spider"], unique=False)
209-
op.create_index(
210-
"ix_crawler_job_scheduled", "crawler_job", ["scheduled"], unique=False
211-
)
212-
op.create_index("ix_crawler_job_job_id", "crawler_job", ["job_id"], unique=False)
213-
op.create_table(
214-
"crawler_workflows_object",
215-
sa.Column("job_id", postgresql.UUID(), autoincrement=False, nullable=False),
216-
sa.Column("object_id", sa.INTEGER(), autoincrement=False, nullable=False),
217-
sa.ForeignKeyConstraint(
218-
["object_id"],
219-
["workflows_object.id"],
220-
name="fk_crawler_workflows_object_object_id_workflows_object",
221-
onupdate="CASCADE",
222-
ondelete="CASCADE",
223-
),
224-
sa.PrimaryKeyConstraint(
225-
"job_id", "object_id", name="pk_crawler_workflows_object"
226-
),
227-
)
228-
op.create_table(
229-
"workflows_pending_record",
230-
sa.Column("workflow_id", sa.INTEGER(), autoincrement=False, nullable=False),
231-
sa.Column("record_id", sa.INTEGER(), autoincrement=False, nullable=False),
232-
sa.ForeignKeyConstraint(
233-
["workflow_id"],
234-
["workflows_object.id"],
235-
name="fk_workflows_pending_record_workflow_id_workflows_object",
236-
ondelete="CASCADE",
237-
),
238-
sa.PrimaryKeyConstraint("workflow_id", name="pk_workflows_pending_record"),
239-
)
240-
op.create_table(
241-
"workflows_record_sources",
242-
sa.Column(
243-
"source",
244-
postgresql.ENUM("arxiv", "submitter", "publisher", name="source_enum"),
245-
autoincrement=False,
246-
nullable=False,
247-
),
248-
sa.Column(
249-
"record_uuid", postgresql.UUID(), autoincrement=False, nullable=False
250-
),
251-
sa.Column(
252-
"json",
253-
postgresql.JSONB(astext_type=sa.Text()),
254-
autoincrement=False,
255-
nullable=True,
256-
),
257-
sa.Column(
258-
"created", postgresql.TIMESTAMP(), autoincrement=False, nullable=True
259-
),
260-
sa.Column(
261-
"updated", postgresql.TIMESTAMP(), autoincrement=False, nullable=True
262-
),
263-
sa.ForeignKeyConstraint(
264-
["record_uuid"],
265-
["records_metadata.id"],
266-
name="fk_workflows_record_sources_record_uuid_records_metadata",
267-
ondelete="CASCADE",
268-
),
269-
sa.PrimaryKeyConstraint(
270-
"record_uuid", "source", name="pk_workflows_record_sources"
271-
),
272-
)
273-
op.execute(
274-
"""
275-
CREATE OR REPLACE FUNCTION referenced_records(json jsonb) RETURNS TEXT[] AS $$
276-
DECLARE
277-
reference_arr jsonb;
278-
text_val text;
279-
text_arr_val text[];
280-
ret_val text[];
281-
BEGIN
282-
FOR reference_arr IN (SELECT jsonb_array_elements(json->'references')) LOOP
283-
text_val := split_part(reference_arr->'record'->>'$ref',E'api/',2);
284-
IF text_val != '' THEN
285-
text_arr_val := regexp_split_to_array(text_val, E'/');
286-
ret_val:=array_append(ret_val, text_arr_val[2]||substring(text_arr_val[1] for 3));
287-
END IF;
288-
END LOOP;
289-
RETURN ret_val;
290-
END;
291-
$$ LANGUAGE plpgsql IMMUTABLE;
292-
"""
293-
)
294-
295-
op.execute(
296-
"""
297-
CREATE INDEX ix_records_metadata_json_referenced_records_2_0
298-
ON records_metadata
299-
USING gin(referenced_records(json))
300-
"""
301-
)
26+
pass
30227

30328

30429
def downgrade():
30530
# """Downgrade database."""
306-
op.execute("drop index if exists ix_records_metadata_json_referenced_records_2_0")
307-
op.execute("drop function if exists referenced_records(json jsonb)")
308-
op.drop_table("workflows_record_sources")
309-
op.drop_table("workflows_pending_record")
310-
op.drop_table("crawler_workflows_object")
311-
op.drop_index("ix_crawler_job_job_id", table_name="crawler_job")
312-
op.drop_index("ix_crawler_job_scheduled", table_name="crawler_job")
313-
op.drop_index("ix_crawler_job_spider", table_name="crawler_job")
314-
op.drop_index("ix_crawler_job_workflow", table_name="crawler_job")
315-
op.drop_table("crawler_job")
316-
op.drop_index(
317-
"ix_workflows_audit_logging_object_id", table_name="workflows_audit_logging"
318-
)
319-
op.drop_index(
320-
"ix_workflows_audit_logging_user_id", table_name="workflows_audit_logging"
321-
)
322-
op.drop_table("workflows_audit_logging")
323-
op.drop_table("workflows_buckets")
324-
op.drop_index("ix_workflows_object_data_type", table_name="workflows_object")
325-
op.drop_index("ix_workflows_object_id_parent", table_name="workflows_object")
326-
op.drop_index("ix_workflows_object_id_workflow", table_name="workflows_object")
327-
op.drop_index("ix_workflows_object_status", table_name="workflows_object")
328-
op.drop_table("workflows_object")
329-
op.drop_table("workflows_workflow")
330-
op.execute("DROP TYPE IF EXISTS source_enum")
31+
pass

‎backend/inspirehep/alembic/e5e43ad8f861_add_index_for_objectversion_key.py‎

Lines changed: 2 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,6 @@
77

88
"""Add index for ObjectVersion.key"""
99

10-
from alembic import op
1110

1211
# revision identifiers, used by Alembic.
1312
revision = "e5e43ad8f861"
@@ -18,11 +17,9 @@
1817

1918
def upgrade():
2019
"""Upgrade database."""
21-
op.create_index(
22-
"ix_files_object_key_head", "files_object", ["key", "is_head"], unique=False
23-
)
20+
pass
2421

2522

2623
def downgrade():
2724
"""Downgrade database."""
28-
op.drop_index("ix_files_object_key_head", table_name="files_object")
25+
pass

‎backend/inspirehep/config.py‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -194,6 +194,15 @@ def annotate(self, task):
194194
"alembic_version",
195195
"crawler_job",
196196
"crawler_workflows_object",
197+
"files_bucket",
198+
"files_buckettags",
199+
"files_files",
200+
"files_location",
201+
"files_multipartobject",
202+
"files_multipartobject_part",
203+
"files_object",
204+
"files_objecttags",
205+
"records_buckets",
197206
"oaiharvester_configs",
198207
"transaction",
199208
"workflows_audit_logging",

0 commit comments

Comments
 (0)