aboutsummaryrefslogtreecommitdiff
path: root/wqflask/wqflask/metadata_edits.py
blob: 31d056b48b3992dced4c14881539de129ca8b851 (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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
import MySQLdb
import os
import json
import datetime
import difflib
import redis

from collections import namedtuple
from flask import (Blueprint, current_app, redirect,
                   flash, g, render_template, request, Response)
from itertools import groupby

from wqflask.decorators import edit_access_required
from wqflask.decorators import login_required

from gn3.db import diff_from_dict
from gn3.db import fetchall
from gn3.db import fetchone
from gn3.db import insert
from gn3.db import update
from gn3.db.metadata_audit import MetadataAudit
from gn3.db.phenotypes import Phenotype
from gn3.db.phenotypes import Probeset
from gn3.db.phenotypes import Publication
from gn3.db.phenotypes import PublishXRef
from gn3.db.phenotypes import probeset_mapping
from gn3.commands import run_cmd
from gn3.db.traits import get_trait_csv_sample_data
from gn3.db.traits import update_sample_data


metadata_edit = Blueprint('metadata_edit', __name__)


def edit_phenotype(conn, name, dataset_id):
    publish_xref = fetchone(
        conn=conn,
        table="PublishXRef",
        where=PublishXRef(id_=name,
                          inbred_set_id=dataset_id))
    phenotype_ = fetchone(
        conn=conn,
        table="Phenotype",
        where=Phenotype(id_=publish_xref.phenotype_id))
    publication_ = fetchone(
        conn=conn,
        table="Publication",
        where=Publication(id_=publish_xref.publication_id))
    json_data = fetchall(
        conn,
        "metadata_audit",
        where=MetadataAudit(dataset_id=publish_xref.id_))
    Edit = namedtuple("Edit", ["field", "old", "new", "diff"])
    Diff = namedtuple("Diff", ["author", "diff", "timestamp"])
    diff_data = []
    for data in json_data:
        json_ = json.loads(data.json_data)
        timestamp = json_.get("timestamp")
        author = json_.get("author")
        for key, value in json_.items():
            if isinstance(value, dict):
                for field, data_ in value.items():
                    diff_data.append(
                        Diff(author=author,
                             diff=Edit(field,
                                       data_.get("old"),
                                       data_.get("new"),
                                       "\n".join(difflib.ndiff(
                                           [data_.get("old")],
                                           [data_.get("new")]))),
                             timestamp=timestamp))
    diff_data_ = None
    if len(diff_data) > 0:
        diff_data_ = groupby(diff_data, lambda x: x.timestamp)
    return {
        "diff": diff_data_,
        "publish_xref": publish_xref,
        "phenotype": phenotype_,
        "publication": publication_,
    }


def edit_probeset(conn, name):
    probeset_ = fetchone(conn=conn,
                         table="ProbeSet",
                         columns=list(probeset_mapping.values()),
                         where=Probeset(name=name))
    json_data = fetchall(
        conn,
        "metadata_audit",
        where=MetadataAudit(dataset_id=probeset_.id_))
    Edit = namedtuple("Edit", ["field", "old", "new", "diff"])
    Diff = namedtuple("Diff", ["author", "diff", "timestamp"])
    diff_data = []
    for data in json_data:
        json_ = json.loads(data.json_data)
        timestamp = json_.get("timestamp")
        author = json_.get("author")
        for key, value in json_.items():
            if isinstance(value, dict):
                for field, data_ in value.items():
                    diff_data.append(
                        Diff(author=author,
                             diff=Edit(field,
                                       data_.get("old"),
                                       data_.get("new"),
                                       "\n".join(difflib.ndiff(
                                           [data_.get("old")],
                                           [data_.get("new")]))),
                             timestamp=timestamp))
    diff_data_ = None
    if len(diff_data) > 0:
        diff_data_ = groupby(diff_data, lambda x: x.timestamp)
    return {
        "diff": diff_data_,
        "probeset": probeset_,
    }


@metadata_edit.route("/<dataset_id>/traits/<name>")
@edit_access_required
@login_required
def display_phenotype_metadata(dataset_id: str, name: str):
    conn = MySQLdb.Connect(db=current_app.config.get("DB_NAME"),
                           user=current_app.config.get("DB_USER"),
                           passwd=current_app.config.get("DB_PASS"),
                           host=current_app.config.get("DB_HOST"))
    _d = edit_phenotype(conn=conn, name=name, dataset_id=dataset_id)
    return render_template(
        "edit_phenotype.html",
        diff=_d.get("diff"),
        publish_xref=_d.get("publish_xref"),
        phenotype=_d.get("phenotype"),
        publication=_d.get("publication"),
        dataset_id=dataset_id,
        resource_id=request.args.get("resource-id"),
        version=os.environ.get("GN_VERSION"),
    )


@metadata_edit.route("/traits/<name>")
@edit_access_required
@login_required
def display_probeset_metadata(name: str):
    conn = MySQLdb.Connect(db=current_app.config.get("DB_NAME"),
                           user=current_app.config.get("DB_USER"),
                           passwd=current_app.config.get("DB_PASS"),
                           host=current_app.config.get("DB_HOST"))
    _d = edit_probeset(conn=conn, name=name)
    return render_template(
        "edit_probeset.html",
        diff=_d.get("diff"),
        probeset=_d.get("probeset"),
        name=name,
        resource_id=request.args.get("resource-id"),
        version=os.environ.get("GN_VERSION"),
    )


@metadata_edit.route("/<dataset_id>/traits/<name>", methods=("POST",))
@edit_access_required
@login_required
def update_phenotype(dataset_id: str, name: str):
    conn = MySQLdb.Connect(db=current_app.config.get("DB_NAME"),
                           user=current_app.config.get("DB_USER"),
                           passwd=current_app.config.get("DB_PASS"),
                           host=current_app.config.get("DB_HOST"))
    data_ = request.form.to_dict()
    TMPDIR = current_app.config.get("TMPDIR")
    author = ((g.user_session.record.get(b"user_id") or b"").decode("utf-8")
               or g.user_session.record.get("user_id") or "")
    phenotype_id = str(data_.get('phenotype-id'))
    if not (file_ := request.files.get("file")):
        flash("No sample-data has been uploaded", "warning")
    else:
        if not os.path.exists(SAMPLE_DATADIR := os.path.join(TMPDIR, "sample-data")):
            os.makedirs(SAMPLE_DATADIR)
        if not os.path.exists(os.path.join(SAMPLE_DATADIR,
                                           "diffs")):
            os.makedirs(os.path.join(SAMPLE_DATADIR,
                                     "diffs"))
        if not os.path.exists(os.path.join(SAMPLE_DATADIR,
                                           "updated")):
            os.makedirs(os.path.join(SAMPLE_DATADIR,
                                     "updated"))
        current_time = str(datetime.datetime.now().isoformat())
        _file_name = (f"{request.args.get('resource-id')}."
                      f"{current_time}.csv")
        new_file_name = (os.path.join(TMPDIR,
                                      f"sample-data/updated/{_file_name}.csv"))
        uploaded_file_name = (os.path.join(
            TMPDIR, "sample-data/updated/updated.",
            f"{_file_name}.csv"))
        file_.save(new_file_name)
        publishdata_id = ""
        lines = []
        with open(new_file_name, "r") as f:
            lines = f.read()
            first_line = lines.split('\n', 1)[0]
            publishdata_id = first_line.split("Id:")[-1].strip()
        with open(new_file_name, "w") as f:
            f.write(lines.split("\n\n")[-1])
        csv_ = get_trait_csv_sample_data(conn=conn,
                                         trait_name=str(name),
                                         phenotype_id=str(phenotype_id))
        with open(uploaded_file_name, "w") as f_:
            f_.write(csv_.split("\n\n")[-1])
        r = run_cmd(cmd=("csvdiff "
                         f"'{uploaded_file_name}' '{new_file_name}' "
                         "--format json"))
        diff_output = (f"{TMPDIR}/sample-data/diffs/"
                       f"{_file_name}.json")
        with open(diff_output, "w") as f:
            dict_ = json.loads(r.get("output"))
            dict_.update({
                "author": author,
                "publishdata_id": publishdata_id,
                "dataset_id": data_.get("dataset-name"),
                "timestamp": datetime.datetime.now().strftime(
                    "%Y-%m-%d %H:%M:%S")
            })
            f.write(json.dumps(dict_))
        flash("Sample-data has been successfully uploaded", "success")
    # Run updates:
    phenotype_ = {
        "pre_pub_description": data_.get("pre-pub-desc"),
        "post_pub_description": data_.get("post-pub-desc"),
        "original_description": data_.get("orig-desc"),
        "units": data_.get("units"),
        "pre_pub_abbreviation": data_.get("pre-pub-abbrev"),
        "post_pub_abbreviation": data_.get("post-pub-abbrev"),
        "lab_code": data_.get("labcode"),
        "submitter": data_.get("submitter"),
        "owner": data_.get("owner"),
        "authorized_users": data_.get("authorized-users"),
    }
    updated_phenotypes = update(
        conn, "Phenotype",
        data=Phenotype(**phenotype_),
        where=Phenotype(id_=data_.get("phenotype-id")))
    diff_data = {}
    if updated_phenotypes:
        diff_data.update({"Phenotype": diff_from_dict(old={
            k: data_.get(f"old_{k}") for k, v in phenotype_.items()
            if v is not None}, new=phenotype_)})
    publication_ = {
        "abstract": data_.get("abstract"),
        "authors": data_.get("authors"),
        "title": data_.get("title"),
        "journal": data_.get("journal"),
        "volume": data_.get("volume"),
        "pages": data_.get("pages"),
        "month": data_.get("month"),
        "year": data_.get("year")
    }
    updated_publications = update(
        conn, "Publication",
        data=Publication(**publication_),
        where=Publication(id_=data_.get("pubmed-id",
                                        data_.get("old_id_"))))
    if updated_publications:
        diff_data.update({"Publication": diff_from_dict(old={
            k: data_.get(f"old_{k}") for k, v in publication_.items()
            if v is not None}, new=publication_)})
    if diff_data:
        diff_data.update({"dataset_id": name})
        diff_data.update({"resource_id": request.args.get('resource-id')})
        diff_data.update({"author": author})
        diff_data.update({"timestamp": datetime.datetime.now().strftime(
            "%Y-%m-%d %H:%M:%S")})
        insert(conn,
               table="metadata_audit",
               data=MetadataAudit(dataset_id=name,
                                  editor=author,
                                  json_data=json.dumps(diff_data)))
        flash(f"Diff-data: \n{diff_data}\nhas been uploaded", "success")
    return redirect(f"/datasets/{dataset_id}/traits/{name}"
                    f"?resource-id={request.args.get('resource-id')}")


@metadata_edit.route("/traits/<name>", methods=("POST",))
@edit_access_required
@login_required
def update_probeset(name: str):
    conn = MySQLdb.Connect(db=current_app.config.get("DB_NAME"),
                           user=current_app.config.get("DB_USER"),
                           passwd=current_app.config.get("DB_PASS"),
                           host=current_app.config.get("DB_HOST"))
    data_ = request.form.to_dict()
    probeset_ = {
        "id_": data_.get("id"),
        "symbol": data_.get("symbol"),
        "description": data_.get("description"),
        "probe_target_description": data_.get("probe_target_description"),
        "chr_": data_.get("chr"),
        "mb": data_.get("mb"),
        "alias": data_.get("alias"),
        "geneid": data_.get("geneid"),
        "homologeneid": data_.get("homologeneid"),
        "unigeneid": data_.get("unigeneid"),
        "omim": data_.get("OMIM"),
        "refseq_transcriptid": data_.get("refseq_transcriptid"),
        "blatseq": data_.get("blatseq"),
        "targetseq": data_.get("targetseq"),
        "strand_probe": data_.get("Strand_Probe"),
        "probe_set_target_region": data_.get("probe_set_target_region"),
        "probe_set_specificity": data_.get("probe_set_specificity"),
        "probe_set_blat_score": data_.get("probe_set_blat_score"),
        "probe_set_blat_mb_start": data_.get("probe_set_blat_mb_start"),
        "probe_set_blat_mb_end": data_.get("probe_set_blat_mb_end"),
        "probe_set_strand": data_.get("probe_set_strand"),
        "probe_set_note_by_rw": data_.get("probe_set_note_by_rw"),
        "flag": data_.get("flag")
    }
    diff_data = {}
    author = ((g.user_session.record.get(b"user_id") or b"").decode("utf-8")
               or g.user_session.record.get("user_id") or "")
    if (updated_probeset := update(
            conn, "ProbeSet",
            data=Probeset(**probeset_),
            where=Probeset(id_=data_.get("id")))):
        diff_data.update({"Probeset": diff_from_dict(old={
            k: data_.get(f"old_{k}") for k, v in probeset_.items()
            if v is not None}, new=probeset_)})
    if diff_data:
        diff_data.update({"probeset_name": data_.get("probeset_name")})
        diff_data.update({"author": author})
        diff_data.update({"resource_id": request.args.get('resource-id')})
        diff_data.update({"timestamp": datetime.datetime.now().strftime(
            "%Y-%m-%d %H:%M:%S")})
        insert(conn,
               table="metadata_audit",
               data=MetadataAudit(dataset_id=data_.get("id"),
                                  editor=author,
                                  json_data=json.dumps(diff_data)))
    return redirect(f"/datasets/traits/{name}"
                    f"?resource-id={request.args.get('resource-id')}")


@metadata_edit.route("/<dataset_id>/traits/<phenotype_id>/csv")
@login_required
def get_sample_data_as_csv(dataset_id: str, phenotype_id:     int):
    return Response(
        get_trait_csv_sample_data(
            conn=MySQLdb.Connect(db=current_app.config.get("DB_NAME"),
                                 user=current_app.config.get("DB_USER"),
                                 passwd=current_app.config.get("DB_PASS"),
                                 host=current_app.config.get("DB_HOST")),
            trait_name=str(dataset_id),
            phenotype_id=str(phenotype_id)),
        mimetype="text/csv",
        headers={"Content-disposition":
                 "attachment; filename=myplot.csv"}
    )


# @metadata_edit.route("/diffs")
# @login_required
# def display_diffs_admin():
#     TMPDIR = current_app.config.get("TMPDIR")
#     DIFF_DIR = f"{TMPDIR}/sample-data/diffs"
#     approved_files, rejected_files, files = {}, {}, {}
#     user_id = ((g.user_session.record.get(b"user_id") or
#                         b"").decode("utf-8")
#                or g.user_session.record.get("user_id") or "")
#     redis_conn = redis.from_url(current_app.config["REDIS_URL"],
#                                     decode_responses=True)
#     if os.path.exists(DIFF_DIR):
#         for name in os.listdir(DIFF_DIR):
#             if name.endswith(".approved"):
                
#                 approved_file.update{
                    
#                 }
#                 approved_files.add(name)
#             elif name.endswith(".rejected"):
#                 approved_files.add(name)
#             else:
#                 files.append(name)
#     return render_template("display_files_admin.html",
#                            files=files)
# http://localhost:5004/datasets/diffs/admin