feat: snapshot tests

Makefile

@@ -13,16 +13,24 @@ setup-git-hooks:
 
 lint:
 	ruff check soil_id
+	ruff format soil_id --diff
 
 format:
+	ruff check soil_id --fix
 	ruff format soil_id
 
 lock:
 	CUSTOM_COMPILE_COMMAND="make lock" uv pip compile --upgrade --generate-hashes requirements/base.in -o requirements.txt
 
+lock-package:
+	CUSTOM_COMPILE_COMMAND="make lock" uv pip compile --upgrade-package $(PACKAGE) --generate-hashes --emit-build-options requirements/base.in requirements/deploy.in -o requirements.txt
+
 lock-dev:
 	CUSTOM_COMPILE_COMMAND="make lock-dev" uv pip compile --upgrade --generate-hashes requirements/dev.in -o requirements-dev.txt
 
+lock-dev-package:
+	CUSTOM_COMPILE_COMMAND="make lock-dev" uv pip compile --upgrade-package $(PACKAGE) --generate-hashes requirements/dev.in -o requirements-dev.txt
+
 build:
 	echo "Building TK..."
 
@@ -35,9 +43,16 @@ clean:
 
 test: clean check_rebuild
 	if [ -z "$(PATTERN)" ]; then \
-		$(DC_RUN_CMD) pytest soil_id; \
+		$(DC_RUN_CMD) pytest soil_id -vv; \
+	else \
+		$(DC_RUN_CMD) pytest soil_id -vv -k $(PATTERN); \
+	fi
+
+test_update_snapshots: clean check_rebuild
+	if [ -z "$(PATTERN)" ]; then \
+		$(DC_RUN_CMD) pytest soil_id --snapshot-update; \
 	else \
-		$(DC_RUN_CMD) pytest soil_id -k $(PATTERN); \
+		$(DC_RUN_CMD) pytest soil_id --snapshot-update -k $(PATTERN); \
 	fi
 
 test-verbose:

requirements-dev.txt

@@ -161,6 +161,7 @@ pytest==8.4.2 \
     # via
     #   -r requirements/dev.in
     #   pytest-profiling
+    #   syrupy
 pytest-profiling==1.8.1 \
     --hash=sha256:3dd8713a96298b42d83de8f5951df3ada3e61b3e5d2a06956684175529e17aea \
     --hash=sha256:3f171fa69d5c82fa9aab76d66abd5f59da69135c37d6ae5bf7557f1b154cb08d
@@ -253,6 +254,10 @@ soupsieve==2.8 \
     --hash=sha256:0cc76456a30e20f5d7f2e14a98a4ae2ee4e5abdc7c5ea0aafe795f344bc7984c \
     --hash=sha256:e2dd4a40a628cb5f28f6d4b0db8800b8f581b65bb380b97de22ba5ca8d72572f
     # via beautifulsoup4
+syrupy==4.9.1 \
+    --hash=sha256:b7d0fcadad80a7d2f6c4c71917918e8ebe2483e8c703dfc8d49cdbb01081f9a4 \
+    --hash=sha256:b94cc12ed0e5e75b448255430af642516842a2374a46936dd2650cfb6dd20eda
+    # via -r requirements/dev.in
 tqdm==4.67.1 \
     --hash=sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2 \
     --hash=sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2

requirements/dev.in

@@ -4,3 +4,4 @@ ruff
 pre-commit
 pytest
 pytest-profiling
+syrupy

soil_id/config.py

@@ -15,12 +15,17 @@
 import os
 import tempfile
 
+from dotenv import load_dotenv
 from platformdirs import user_cache_dir
 
+# Load environment variables from .env file
+load_dotenv()
+
+
 DATA_PATH = os.environ.get("DATA_PATH", "Data")
 
 # Numpy seeding
-RANDOM_SEED = os.environ.get("RANDOM_SEED", 19)
+RANDOM_SEED = int(os.environ.get("RANDOM_SEED", 19))
 
 # Output
 APP_NAME = os.environ.get("APP_NAME", "org.terraso.soilid")
@@ -41,5 +46,6 @@
 # Database
 DB_NAME = os.environ.get("DB_NAME", "terraso_backend")
 DB_HOST = os.environ.get("DB_HOST")
+DB_PORT = int(os.environ.get("DB_PORT", 5432))
 DB_USERNAME = os.environ.get("DB_USERNAME")
 DB_PASSWORD = os.environ.get("DB_PASSWORD")

soil_id/db.py

@@ -39,6 +39,7 @@ def get_datastore_connection():
             user=soil_id.config.DB_USERNAME,
             password=soil_id.config.DB_PASSWORD,
             dbname=soil_id.config.DB_NAME,
+            port=soil_id.config.DB_PORT,
         )
         return conn
     except Exception as err:
@@ -185,6 +186,7 @@ def get_hwsd2_profile_data(connection, hwsd2_mu_select):
                        ph_water, elec_cond, fao90_name
                 FROM hwsd2_data
                 WHERE hwsd2_smu_id IN ({placeholders})
+                ORDER BY hwsd2_smu_id, compid, sequence, layer
             """
             cur.execute(sql_query, tuple(hwsd2_mu_select))
             results = cur.fetchall()
@@ -352,7 +354,8 @@ def extract_hwsd2_data(connection, lon, lat, buffer_dist, table_name):
                 BOOL_OR(ST_Intersects(shape, {point})) AS pt_intersect
             FROM hwsd2_segment
             WHERE ST_DWithin(shape, {point}, {buffer_dist})
-            GROUP BY hwsd2_id;
+            GROUP BY hwsd2_id
+            ORDER BY hwsd2_id;
         """
 
         # Use GeoPandas to execute the main query and load results into a GeoDataFrame.
@@ -398,7 +401,8 @@ def get_WRB_descriptions(connection, WRB_Comp_List):
             sql = f"""SELECT WRB_tax, Description_en, Management_en, Description_es, Management_es,
                              Description_ks, Management_ks, Description_fr, Management_fr
                       FROM wrb_fao90_desc
-                      WHERE WRB_tax IN ({placeholders})"""
+                      WHERE WRB_tax IN ({placeholders})
+                      ORDER BY WRB_tax"""
 
             # Execute the query with the parameters
             cur.execute(sql, tuple(WRB_Comp_List))
@@ -455,6 +459,7 @@ def execute_query(query, params):
             SELECT lu.WRB_1984_Full
             FROM wrb2006_to_fao90 AS lu
             WHERE lu.WRB_2006_Full = ANY(%s)
+            ORDER BY lu.WRB_1984_Full
         """
         names = execute_query(sql1, ([WRB_Comp_List],))
 
@@ -491,6 +496,7 @@ def execute_query(query, params):
                    Management_fr
             FROM wrb_fao90_desc
             WHERE WRB_tax = ANY(%s)
+            ORDER BY WRB_tax
         """
         results = execute_query(sql2, ([WRB_Comp_List_mapped],))