diff options
Diffstat (limited to 'uploader/phenotypes')
| -rw-r--r-- | uploader/phenotypes/misc.py | 26 | ||||
| -rw-r--r-- | uploader/phenotypes/views.py | 52 |
2 files changed, 57 insertions, 21 deletions
diff --git a/uploader/phenotypes/misc.py b/uploader/phenotypes/misc.py new file mode 100644 index 0000000..cbe3b7f --- /dev/null +++ b/uploader/phenotypes/misc.py @@ -0,0 +1,26 @@ +"""Miscellaneous functions handling phenotypes and phenotypes data.""" +import logging + +logger = logging.getLogger(__name__) + + +def phenotypes_data_differences( + filedata: tuple[dict, ...], dbdata: tuple[dict, ...] +) -> tuple[dict, ...]: + """Compute differences between file data and db data""" + diff = tuple() + for filerow, dbrow in zip( + sorted(filedata, key=lambda item: (item["phenotype_id"], item["xref_id"])), + sorted(dbdata, key=lambda item: (item["PhenotypeId"], item["xref_id"]))): + for samplename, value in filerow["data"].items(): + if value != dbrow["data"].get(samplename, {}).get("value"): + diff = diff + ({ + "PhenotypeId": filerow["phenotype_id"], + "xref_id": filerow["xref_id"], + "DataId": dbrow["DataId"], + "StrainId": dbrow["data"].get(samplename, {}).get("StrainId"), + "StrainName": samplename, + "value": value + },) + + return diff diff --git a/uploader/phenotypes/views.py b/uploader/phenotypes/views.py index 9c737fc..a18c44d 100644 --- a/uploader/phenotypes/views.py +++ b/uploader/phenotypes/views.py @@ -868,6 +868,17 @@ def process_phenotype_data_for_download(pheno: dict) -> dict: } +BULK_EDIT_COMMON_FIELDNAMES = [ + "UniqueIdentifier", + "Post_publication_description", + "Pre_publication_abbreviation", + "Pre_publication_description", + "Original_description", + "Post_publication_abbreviation", + "PubMed_ID" +] + + @phenotypesbp.route( "<int:species_id>/populations/<int:population_id>/phenotypes/datasets" "/<int:dataset_id>/edit-download", @@ -915,15 +926,9 @@ def edit_download_phenotype_data(# pylint: disable=[unused-argument] "comment line. This line, and all the lines above it, are " "all comment lines. Comment lines will be ignored.\n") writer = csv.DictWriter(outfile, - fieldnames=[ - "UniqueIdentifier", - "Post_publication_description", - "Pre_publication_abbreviation", - "Pre_publication_description", - "Original_description", - "Post_publication_abbreviation", - "PubMed_ID" - ] + samples_list, + fieldnames= ( + BULK_EDIT_COMMON_FIELDNAMES + + samples_list), dialect="excel-tab") writer.writeheader() writer.writerows(data) @@ -967,23 +972,28 @@ def edit_upload_phenotype_data(# pylint: disable=[unused-argument] jobs_db = app.config["ASYNCHRONOUS_JOBS_SQLITE_DB"] with sqlite3.connection(jobs_db) as conn: job_id = uuid.uuid4() + job_cmd = [ + sys.executable, "-u", + "-m", "scripts.phenotypes_bulk_edit", + app.config["SQL_URI"], + jobs_db, + str(job_id), + "--log-level", + logging.getLevelName( + app.logger.getEffectiveLevel() + ).lower() + ] + app.logger.debug("Phenotype-edit, bulk-upload command: %s", job_cmd) _job = gnlibs_jobs.launch_job( gnlibs_jobs.initialise_job(conn, job_id, - [ - sys.executable, "-u", - "-m", "scripts.phenotypes_bulk_edit", - app.config["SQL_URI"], - jobs_db, - str(job_id), - "--log-level", - logging.getLevelName( - app.logger.getEffectiveLevel() - ).lower() - ], + job_cmd, "phenotype-bulk-edit", extra_meta = { - "edit-file": str(edit_file) + "edit-file": str(edit_file), + "species-id": species["SpeciesId"], + "population-id": population["Id"], + "dataset-id": dataset["Id"] }), jobs_db, f"{app.config['UPLOAD_FOLDER']}/job_errors", |