aboutsummaryrefslogtreecommitdiff
path: root/gn_auth/auth/authorisation/resources/groups/data.py
blob: ad0dfbaef461fa8d251f0656ab9872650ebf639a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
"""Handles the resource objects' data."""
from gn_libs import mysqldb as gn3db
from MySQLdb.cursors import DictCursor

from gn_auth.auth.db import sqlite3 as authdb

from gn_auth.auth.errors import NotFoundError
from gn_auth.auth.authorisation.checks import authorised_p
from gn_auth.auth.authorisation.resources.groups import Group

def __fetch_mrna_data_by_ids__(
        conn: gn3db.Connection, dataset_ids: tuple[str, ...]) -> tuple[
            dict, ...]:
    """Fetch mRNA Assay data by ID."""
    with conn.cursor(DictCursor) as cursor:
        paramstr = ", ".join(["%s"] * len(dataset_ids))
        cursor.execute(
            "SELECT psf.Id, psf.Name AS dataset_name, "
            "psf.FullName AS dataset_fullname, "
            "ifiles.GN_AccesionId AS accession_id FROM ProbeSetFreeze AS psf "
            "INNER JOIN InfoFiles AS ifiles ON psf.Name=ifiles.InfoPageName "
            f"WHERE psf.Id IN ({paramstr})",
            dataset_ids)
        res = cursor.fetchall()
        if res:
            return tuple(dict(row) for row in res)
        raise NotFoundError("Could not find mRNA Assay data with the given ID.")

def __fetch_geno_data_by_ids__(
        conn: gn3db.Connection, dataset_ids: tuple[str, ...]) -> tuple[
            dict, ...]:
    """Fetch genotype data by ID."""
    with conn.cursor(DictCursor) as cursor:
        paramstr = ", ".join(["%s"] * len(dataset_ids))
        cursor.execute(
            "SELECT gf.Id, gf.Name AS dataset_name, "
            "gf.FullName AS dataset_fullname, "
            "ifiles.GN_AccesionId AS accession_id FROM GenoFreeze AS gf "
            "INNER JOIN InfoFiles AS ifiles ON gf.Name=ifiles.InfoPageName "
            f"WHERE gf.Id IN ({paramstr})",
            dataset_ids)
        res = cursor.fetchall()
        if res:
            return tuple(dict(row) for row in res)
        raise NotFoundError("Could not find Genotype data with the given ID.")

def __fetch_pheno_data_by_ids__(
        conn: gn3db.Connection, dataset_ids: tuple[str, ...]) -> tuple[
            dict, ...]:
    """Fetch phenotype data by ID."""
    with conn.cursor(DictCursor) as cursor:
        paramstr = ", ".join(["%s"] * len(dataset_ids))
        cursor.execute(
            "SELECT pxf.Id, iset.InbredSetName, pf.Id AS dataset_id, "
            "pf.Name AS dataset_name, pf.FullName AS dataset_fullname, "
            "ifiles.GN_AccesionId AS accession_id "
            "FROM PublishXRef AS pxf "
            "INNER JOIN InbredSet AS iset ON pxf.InbredSetId=iset.InbredSetId "
            "INNER JOIN PublishFreeze AS pf ON iset.InbredSetId=pf.InbredSetId "
            "INNER JOIN InfoFiles AS ifiles ON pf.Name=ifiles.InfoPageName "
            f"WHERE pxf.Id IN ({paramstr})",
            dataset_ids)
        res = cursor.fetchall()
        if res:
            return tuple(dict(row) for row in res)
        raise NotFoundError(
            "Could not find Phenotype/Publish data with the given IDs.")

def __fetch_data_by_id(
        conn: gn3db.Connection, dataset_type: str,
        dataset_ids: tuple[str, ...]) -> tuple[dict, ...]:
    """Fetch data from MySQL by IDs."""
    fetch_fns = {
        "mrna": __fetch_mrna_data_by_ids__,
        "genotype": __fetch_geno_data_by_ids__,
        "phenotype": __fetch_pheno_data_by_ids__
    }
    return fetch_fns[dataset_type](conn, dataset_ids)

@authorised_p(("system:data:link-to-group",),
              error_description=(
                  "You do not have sufficient privileges to link data to (a) "
                  "group(s)."),
              oauth2_scope="profile group resource")
def link_data_to_group(
        authconn: authdb.DbConnection, gn3conn: gn3db.Connection,
        dataset_type: str, dataset_ids: tuple[str, ...], group: Group) -> tuple[
            dict, ...]:
    """Link the given data to the specified group."""
    the_data = __fetch_data_by_id(gn3conn, dataset_type, dataset_ids)
    with authdb.cursor(authconn) as cursor:
        params = tuple({
            "group_id": str(group.group_id), "dataset_type": {
                "mrna": "mRNA", "genotype": "Genotype",
                "phenotype": "Phenotype"
            }[dataset_type],
            "dataset_or_trait_id": item["Id"],
            "dataset_name": item["dataset_name"],
            "dataset_fullname": item["dataset_fullname"],
            "accession_id": item["accession_id"]
        } for item in the_data)
        cursor.executemany(
            "INSERT INTO linked_group_data VALUES"
            "(:group_id, :dataset_type, :dataset_or_trait_id, :dataset_name, "
            ":dataset_fullname, :accession_id)",
            params)
        return params