Linting...

Author: asherpasha

api/Archive/analyze_efp_schemas.py

@@ -20,9 +20,21 @@
 
 # Extra columns that some databases have (we want to know which ones)
 EXTRA_COLUMNS = {
-    "channel", "data_call", "data_num", "data_p_val", "data_p_value",
-    "genome", "genome_id", "log", "orthogroup", "p_val", "project_id",
-    "qvalue", "sample_file_name", "sample_tissue", "version",
+    "channel",
+    "data_call",
+    "data_num",
+    "data_p_val",
+    "data_p_value",
+    "genome",
+    "genome_id",
+    "log",
+    "orthogroup",
+    "p_val",
+    "project_id",
+    "qvalue",
+    "sample_file_name",
+    "sample_tissue",
+    "version",
 }
 
 
@@ -94,7 +106,9 @@ def main():
 
     # ---- 2. Group databases by their 3-column signature ----
     print("\n" + "=" * 80)
-    print("GROUPING BY SIGNATURE (probeset_type, probeset_nullable, signal_nullable, signal_default, bot_type, bot_nullable)")
+    print(
+        "GROUPING BY SIGNATURE (probeset_type, probeset_nullable, signal_nullable, signal_default, bot_type, bot_nullable)"
+    )
     print("=" * 80)
 
     sig_groups = defaultdict(list)
@@ -103,7 +117,9 @@ def main():
         sig_groups[sig].append(db)
 
     for sig, dbs in sorted(sig_groups.items(), key=lambda x: -len(x[1])):
-        print(f"\n  Signature: probeset={sig[0]}(nullable={sig[1]}) signal(nullable={sig[2]}, default={sig[3]}) bot={sig[4]}(nullable={sig[5]})")
+        print(
+            f"\n  Signature: probeset={sig[0]}(nullable={sig[1]}) signal(nullable={sig[2]}, default={sig[3]}) bot={sig[4]}(nullable={sig[5]})"
+        )
         print(f"  Count: {len(dbs)}")
         print(f"  DBs: {', '.join(dbs[:10])}{'...' if len(dbs) > 10 else ''}")
 
@@ -135,15 +151,17 @@ def main():
         # Determine extra columns this DB needs
         extras = set(cols.keys()) - NEEDED_COLUMNS - {"proj_id", "sample_id"}
 
-        compact_entries.append({
-            "db": db,
-            "probeset_len": probeset_len,  # None = tinytext
-            "probeset_type": probeset_type,
-            "bot_len": bot_len,  # None = tinytext
-            "bot_type": bot_type,
-            "signal_nullable": signal_nullable,
-            "extras": extras,
-        })
+        compact_entries.append(
+            {
+                "db": db,
+                "probeset_len": probeset_len,  # None = tinytext
+                "probeset_type": probeset_type,
+                "bot_len": bot_len,  # None = tinytext
+                "bot_type": bot_type,
+                "signal_nullable": signal_nullable,
+                "extras": extras,
+            }
+        )
 
     # ---- 4. Show the most compact table-driven representation ----
     print("\n" + "=" * 80)
@@ -180,9 +198,7 @@ def main():
     for e in compact_entries:
         # Filter out databases that ONLY have unneeded extras
         # (sample_file_name, data_call, data_p_val etc. are not needed)
-        has_important_extras = e["extras"] - {
-            "sample_file_name", "data_call", "data_p_val", "data_p_value", "data_num"
-        }
+        has_important_extras = e["extras"] - {"sample_file_name", "data_call", "data_p_val", "data_p_value", "data_num"}
         if has_important_extras:
             complex_dbs.append(e)
         else:
@@ -217,11 +233,13 @@ def main():
         with open(SAMPLE_DATA_CSV, newline="") as f:
             reader = csv.DictReader(f)
             for row in reader:
-                db_samples[row["source_database"]].append({
-                    "data_bot_id": row["data_bot_id"],
-                    "data_probeset_id": row["data_probeset_id"],
-                    "data_signal": row["data_signal"],
-                })
+                db_samples[row["source_database"]].append(
+                    {
+                        "data_bot_id": row["data_bot_id"],
+                        "data_probeset_id": row["data_probeset_id"],
+                        "data_signal": row["data_signal"],
+                    }
+                )
 
         print(f"Total databases with sample data: {len(db_samples)}")
         print(f"Total sample rows: {sum(len(v) for v in db_samples.values())}")

api/__init__.py

@@ -42,6 +42,7 @@ def create_app():
         mysql_efp_base = bar_app.config.get("MYSQL_EFP_BASE_URI")
         if mysql_efp_base:
             from api.models.efp_schemas import SIMPLE_EFP_DATABASE_SCHEMAS
+
             binds = bar_app.config.get("SQLALCHEMY_BINDS") or {}
             base = mysql_efp_base.rstrip("/")
             for db_name in SIMPLE_EFP_DATABASE_SCHEMAS:
@@ -70,9 +71,9 @@ def create_app():
         # On BAR, MySQL binds come from the server config — never build SQLite mirrors there.
         # For CI and local dev, determine whether to build SQLite mirrors.
         needs_sqlite_mirrors = (
-            is_ci                                               # always build on CI
-            or bar_app.config.get("TESTING")                   # config requests test mode
-            or "pytest" in os.sys.modules                      # running under pytest
+            is_ci  # always build on CI
+            or bar_app.config.get("TESTING")  # config requests test mode
+            or "pytest" in os.sys.modules  # running under pytest
             or os.environ.get("BAR_API_AUTO_SQLITE_MIRRORS") == "1"  # explicit override
         )
 

api/models/bar_utils.py

@@ -1,4 +1,4 @@
 # Bridge file to maintain backward compatibility with imports
 from api.utils.bar_utils import BARUtils
 
-__all__ = ['BARUtils']
+__all__ = ["BARUtils"]

api/resources/fastpheno.py

@@ -13,7 +13,6 @@
 from api.utils.bar_utils import BARUtils
 from markupsafe import escape
 
-
 fastpheno = Namespace("FastPheno", description="FastPheno API service", path="/fastpheno")
 
 
@@ -240,9 +239,7 @@ def get(self, tree_site_id, band):
 class FastPhenoSites(Resource):
     def get(self):
         """Returns all sites with coordinates, for initializing the map view."""
-        rows = db.session.execute(
-            db.select(Sites).order_by(Sites.site_name)
-        ).scalars().all()
+        rows = db.session.execute(db.select(Sites).order_by(Sites.site_name)).scalars().all()
 
         res = [
             {
@@ -266,11 +263,11 @@ def get(self, sites_pk):
         if not BARUtils.is_integer(str(sites_pk)):
             return BARUtils.error_exit("Invalid sites_pk"), 400
 
-        rows = db.session.execute(
-            db.select(Flights)
-            .where(Flights.sites_pk == sites_pk)
-            .order_by(Flights.flight_date)
-        ).scalars().all()
+        rows = (
+            db.session.execute(db.select(Flights).where(Flights.sites_pk == sites_pk).order_by(Flights.flight_date))
+            .scalars()
+            .all()
+        )
 
         if len(rows) == 0:
             return BARUtils.error_exit("No flights found for the given site"), 400
@@ -297,12 +294,16 @@ def get(self, flights_pk):
         if not BARUtils.is_integer(str(flights_pk)):
             return BARUtils.error_exit("Invalid flights_pk"), 400
 
-        rows = db.session.execute(
-            db.select(Bands.band)
-            .where(Bands.flights_pk == flights_pk)
-            .distinct()
-            .order_by(db.func.cast(db.func.regexp_replace(Bands.band, "[^0-9]", ""), db.Integer))
-        ).scalars().all()
+        rows = (
+            db.session.execute(
+                db.select(Bands.band)
+                .where(Bands.flights_pk == flights_pk)
+                .distinct()
+                .order_by(db.func.cast(db.func.regexp_replace(Bands.band, "[^0-9]", ""), db.Integer))
+            )
+            .scalars()
+            .all()
+        )
 
         if len(rows) == 0:
             return BARUtils.error_exit("No bands found for the given flight"), 400

api/resources/gene_expression.py

@@ -14,16 +14,14 @@
 )
 
 gene_expression = Namespace(
-    'Gene Expression',
-    description='Gene expression data from BAR eFP databases',
-    path='/gene_expression',
+    "Gene Expression",
+    description="Gene expression data from BAR eFP databases",
+    path="/gene_expression",
 )
 
 
 @gene_expression.route("/expression/<string:database>/<string:gene_id>")
-@gene_expression.doc(
-    description="Retrieve gene expression values from a specified eFP database."
-)
+@gene_expression.doc(description="Retrieve gene expression values from a specified eFP database.")
 @gene_expression.param(
     "gene_id",
     "Gene ID (e.g. AT1G01010 for Arabidopsis, or a probeset like 261585_at)",
@@ -76,4 +74,4 @@ def get(self, database, gene_id):
         return BARUtils.error_exit(result["error"]), result.get("error_code", 500)
 
 
-gene_expression.add_resource(GeneExpression, '/expression/<string:database>/<string:gene_id>')
+gene_expression.add_resource(GeneExpression, "/expression/<string:database>/<string:gene_id>")

api/resources/gene_information.py

@@ -15,7 +15,6 @@
 from api import db
 from sqlalchemy import func
 
-
 gene_information = Namespace("Gene Information", description="Information about Genes", path="/gene_information")
 
 parser = gene_information.parser()
@@ -91,9 +90,9 @@ def post(self):
 
         # Query must be run individually for each species
         lowered_genes = [gene.lower() for gene in genes]
-        rows = db.session.execute(
-            db.select(database).where(func.lower(database.agi).in_(lowered_genes))
-        ).scalars().all()
+        rows = (
+            db.session.execute(db.select(database).where(func.lower(database.agi).in_(lowered_genes))).scalars().all()
+        )
 
         # If there are any isoforms found, return data
         data = []
@@ -286,9 +285,9 @@ def post(self):
         gene_ids = []
         gene_fail = []
         for one_term in terms:
-            query = db.select(alias_database.agi).where(
-                func.lower(alias_database.agi).contains(one_term.lower())
-            ).limit(1)
+            query = (
+                db.select(alias_database.agi).where(func.lower(alias_database.agi).contains(one_term.lower())).limit(1)
+            )
             result = db.session.execute(query).fetchone()
             if result is not None:
                 gene_ids.append(result[0])

api/resources/interactions.py

@@ -474,7 +474,7 @@ def get(self, tag=""):
                         "image_url": ex.image_url,
                         "grn_title": ex.grn_title,
                         "cyjs_layout": _normalize_cyjs_layout(ex.cyjs_layout),
-                        "tag": "|".join(_sort_tag_strings(src_tag_match[ex.source_id]))
+                        "tag": "|".join(_sort_tag_strings(src_tag_match[ex.source_id])),
                     }
                     result.append(one_source[source_id])
 
@@ -544,7 +544,7 @@ def get(self, number=""):
                         "url": row.url,
                         "image_url": row.image_url,
                         "grn_title": row.grn_title,
-                        "cyjs_layout": _normalize_cyjs_layout(row.cyjs_layout)
+                        "cyjs_layout": _normalize_cyjs_layout(row.cyjs_layout),
                     }
                 )
 
@@ -607,20 +607,14 @@ def get(self, stringAGI=""):
                         "source_name": row.source_name,
                         "comments": row.comments,
                         "cyjs_layout": _normalize_cyjs_layout(row.cyjs_layout),
-                        "tags": []
+                        "tags": [],
                     }
 
                 tag_entry = f"{row.tag_name}:{row.tag_group}"
                 if tag_entry not in result_dict[source_id]["tags"]:  # DISTINCT
                     result_dict[source_id]["tags"].append(tag_entry)
 
-            result = [
-                {
-                    **data,
-                    "tags": "|".join(_sort_tag_strings(data["tags"]))
-                }
-                for data in result_dict.values()
-            ]
+            result = [{**data, "tags": "|".join(_sort_tag_strings(data["tags"]))} for data in result_dict.values()]
             result.sort(key=lambda item: (item["grn_title"] or ""))
 
             if len(result) == 0:
@@ -681,18 +675,15 @@ def get(self, AGI_1="", AGI_2=""):
                         "source_name": row.source_name,
                         "comments": row.comments,
                         "cyjs_layout": _normalize_cyjs_layout(row.cyjs_layout),
-                        "tags": []
+                        "tags": [],
                     }
 
                 tag_entry = f"{row.tag_name}:{row.tag_group}"
                 if tag_entry not in result_dict[source_id]["tags"]:
                     result_dict[source_id]["tags"].append(tag_entry)
 
             result = [
-                {
-                    **data,
-                    "tags": "|".join(_sort_tag_strings_natural_case_sensitive(data["tags"]))
-                }
+                {**data, "tags": "|".join(_sort_tag_strings_natural_case_sensitive(data["tags"]))}
                 for data in result_dict.values()
             ]
             result.sort(key=lambda item: item["source_id"])
@@ -746,7 +737,7 @@ def get(self):
                         "image_url": ex.image_url,
                         "grn_title": ex.grn_title,
                         "cyjs_layout": _normalize_cyjs_layout(ex.cyjs_layout),
-                        "tag": "|".join(_sort_tag_strings(src_tag_match[ex.source_id]))
+                        "tag": "|".join(_sort_tag_strings(src_tag_match[ex.source_id])),
                     }
                     result.append(one_source[source_id])
 

api/resources/llama3.py

@@ -10,7 +10,6 @@
 from api import db
 from api.models.llama3 import Summaries
 
-
 llama3 = Namespace("LLaMA", description="Endpoint for retreiving LLaMA3 results", path="/LLaMA")