Merge pull request #74 from Oceans-1876/release-1.0.0

Release 1.0.0

.github/workflows/ci.yml

@@ -15,7 +15,7 @@ jobs:
     steps:
       # Checkout source code
       - name: Check out source code
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       # Calculate some variables that are used later
       - name: Version information
@@ -29,7 +29,7 @@ jobs:
           fi
           echo "GITHUB_BRANCH=${BRANCH}" >> $GITHUB_ENV
           if [ "$BRANCH" == "main" ]; then
-            version=$(cat package.json | grep \"version\" | head -1 | awk -F= "{ print $2 }" | sed 's/[version:,",]//g' | tr -d '[[:space:]]')
+            version=$(awk -F= '/^version/ { print $2}' pyproject.toml | sed 's/[ "]//g')
             tags="latest"
             oldversion=""
             while [ "${oldversion}" != "${version}" ]; do
@@ -52,6 +52,7 @@ jobs:
         uses: elgohr/[email protected]
         env:
           BRANCH: ${{ env.GITHUB_BRANCH }}
+          VERSION: ${{ env.VERSION }}
           BUILDNUMBER: ${{ github.run_number }}
           GITSHA1: ${{ github.sha }}
         with:
@@ -60,7 +61,7 @@ jobs:
           password: ${{ secrets.GITHUB_TOKEN }}
           registry: ghcr.io
           tags: "${{ env.TAGS }}"
-          buildargs: BRANCH,BUILDNUMBER,GITSHA1
+          buildargs: BRANCH,VERSION,BUILDNUMBER,GITSHA1
           dockerfile: docker/Dockerfile
 
       - name: Deploy to prod server

.github/workflows/lint.yml

@@ -3,18 +3,18 @@ name: Perform Type and Formatting checks on a new/edited pull requests.
 on:
   workflow_dispatch:
   pull_request:
-    types: [opened, edited]
+    types: [opened, edited, synchronize]
 
 jobs:
-  perfrom-type-and-formatting-check:
-    runs-on: ubuntu-latest
+  perform-type-and-formatting-check:
+    runs-on: ubuntu-20.04
 
     steps:
       - name: Check out repo
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
 
       - name: Setup Python 3.10
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: "3.10"
 

.github/workflows/pytest.yml

@@ -3,7 +3,7 @@ name: Run unit test
 on:
   workflow_dispatch:
   pull_request:
-    types: [ opened, edited ]
+    types: [opened, edited, synchronize]
 
 jobs:
   pytest:
@@ -37,7 +37,7 @@ jobs:
 
     steps:
       - name: Check out repo
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
         with:
           submodules: true
 
@@ -68,3 +68,4 @@ jobs:
           POSTGRES_DB: challenger_expedition
           FIRST_SUPERUSER: [email protected]
           FIRST_SUPERUSER_PASSWORD: secret_password
+          SECRET_KEY: pytest_secret_key

.pre-commit-config.yaml

@@ -1,13 +1,13 @@
 repos:
     - repo: https://github.com/PyCQA/isort
-      rev: 5.10.1
+      rev: 5.12.0
       hooks:
         - id: isort
     - repo: https://github.com/python/black
       rev: 22.6.0
       hooks:
         - id: black
-    - repo: https://gitlab.com/pycqa/flake8
+    - repo: https://github.com/pycqa/flake8
       rev: 5.0.4
       hooks:
         - id: flake8

CHANGELOG.md

@@ -0,0 +1,27 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.0.0] - 2023-12-04
+
+### Added
+
+- Added Roboto Bold font (in `fonts` submodule).
+
+### Fixed
+
+- Optimized station search.
+- Fixed pytest workflow failure.
+
+### Changed
+
+- Added temporary binomial name filter at species endpoints.
+- Replaced string similarity function for fuzzy search.
+- Minor changes to several API endpoints.
+
+## [0.1.0] - 2022-12-21
+
+- The initial release of the Challenger-API.

CONTRIBUTORS.md

@@ -0,0 +1,8 @@
+# Contributors
+
+- Chris Navarro
+- Kaveh Karimi-Asli
+- Rashmil Panchani
+- Michael Wieck-Sosa
+- Olajide Jegede
+- Wenqi He

app/api/v1/endpoints/species.py

@@ -1,11 +1,14 @@
-from typing import Any, List, Optional, Union
+from typing import Any, List, Optional, Type, Union
 
 from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy import Table
 from sqlalchemy.orm import Session
 
 from app import crud, schemas
 from app.api import deps
-from app.models import SpeciesCommonNames, SpeciesSynonyms
+from app.db.base_class import Base
+from app.models import SpeciesCommonNames, SpeciesSynonyms, stations_species_table
+from app.utils.species import binomial_only
 
 router = APIRouter()
 
@@ -28,7 +31,7 @@ def read_all_species(
 ) -> Any:
     """Retrieve all species."""
     species = crud.species.get_all(db, order_by=order_by)
-    return species
+    return binomial_only(species)
 
 
 @router.post("/search/", response_model=List[schemas.SpeciesSummary])
@@ -45,14 +48,15 @@ def read_species_by_search(
         order_by=order_by,
         limit=limit,
     )
-    return species
+    return binomial_only(species)
 
 
 @router.get("/fuzzymatch/", response_model=List[schemas.SpeciesSummary])
 def read_fuzzy_species_by_search(
     query_str: str,
+    station: Optional[str] = Query(None),
     db: Session = Depends(deps.get_db),
-    min_string_similarity_score: float = 0.2,
+    min_string_similarity_score: float = 0.5,
     limit: int = 0,
     order_by: Optional[List[str]] = Query(None),
 ) -> Any:
@@ -91,17 +95,33 @@ def read_fuzzy_species_by_search(
         ],
     }
 
+    relations: List[Union[Type[Base], Table]] = [SpeciesCommonNames, SpeciesSynonyms]
+
+    if station:
+        expressions_dict = {
+            "join": "AND",
+            "expressions": [
+                expressions_dict,
+                {
+                    "column_name": "station_id",
+                    "search_term": station,
+                    "operator": "eq",
+                },
+            ],
+        }
+        relations.append(stations_species_table)
+
     expressions = schemas.ExpressionGroup(**expressions_dict)
 
     """Retrieves the species based on the given search expressions."""
     species = crud.species.search(
         db,
         expressions=expressions,
-        relations=[SpeciesCommonNames, SpeciesSynonyms],
+        relations=relations,
         order_by=order_by,
         limit=limit,
     )
-    return species
+    return binomial_only(species)
 
 
 @router.get(

app/api/v1/endpoints/stations.py

@@ -1,10 +1,12 @@
-from typing import Any, List, Optional, Union
+from typing import Any, List, Optional, Type, Union
 
 from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy import Table
 from sqlalchemy.orm import Session
 
 from app import crud, schemas
 from app.api import deps
+from app.db.base_class import Base
 from app.models import stations_species_table
 
 router = APIRouter()
@@ -40,10 +42,13 @@ def read_stations_by_search(
     order_by: Optional[List[str]] = Query(None),
 ) -> Any:
     """Retrieves the stations based on the given search expressions."""
+    relations: Optional[List[Union[Type[Base], Table]]] = (
+        [stations_species_table] if expressions.uses_column("species_id") else None
+    )
     stations = crud.station.search(
         db,
         expressions=expressions,
-        relations=[stations_species_table],
+        relations=relations,
         order_by=order_by,
         limit=limit,
     )

app/core/config.py

@@ -106,7 +106,7 @@ def get_emails_enabled(cls, v: bool, values: Dict[str, Any]) -> bool:
             and values.get("EMAILS_FROM_EMAIL")
         )
 
-    EMAIL_TEST_USER: EmailStr = "test@example.com"  # type: ignore
+    EMAIL_TEST_USER: EmailStr = "test2@example.com"  # type: ignore
     FIRST_SUPERUSER: Optional[EmailStr] = None
     FIRST_SUPERUSER_PASSWORD: Optional[str] = None
 
@@ -122,6 +122,12 @@ def get_superuser_password(cls, v: Optional[str]) -> Optional[str]:
             return "test"
         return v
 
+    @validator("ENABLE_AUTH", pre=True)
+    def get_auth_enable(cls, v: Optional[bool]) -> Optional[bool]:
+        if os.environ.get("PYTHON_TEST"):
+            return True
+        return v
+
     USERS_OPEN_REGISTRATION: bool = False
 
     class Config:

app/crud/base.py

@@ -168,9 +168,9 @@ def create_search_expressions(
                 raise ValueError(f"Invalid column name: {expression.column_name}")
 
             if column.type.python_type == str and expression.fuzzy:  # type: ignore
-                similarity_func = func.similarity(column, expression.search_term)
-                # TODO: find a better searching function in database.
-                # similarity_func = func.levenshtein(column, expression.search_term)
+
+                similarity_func = func.word_similarity(expression.search_term, column)
+
                 search_expressions["clauses"].append(
                     cast(
                         BinaryExpression,

app/crud/crud_station.py

@@ -1,17 +1,23 @@
-from typing import Any, Optional
+from typing import Any, Optional, cast
 
 from sqlalchemy.orm import Session
 
 from app.crud.base import CRUDBase
 from app.models import Station
 from app.schemas import StationCreate, StationSummaryPagination, StationUpdate
+from app.utils.species import binomial_only
 
 
 class CRUDStation(
     CRUDBase[Station, StationCreate, StationUpdate, StationSummaryPagination]
 ):
     def get(self, db: Session, id: Any) -> Optional[Station]:
-        return db.query(self.model).filter(self.model.name == id).first()
+        station = cast(
+            Station, db.query(self.model).filter(self.model.name == id).first()
+        )
+        if station:
+            station.species = binomial_only(station.species)
+        return station
 
 
 station = CRUDStation(Station)

app/schemas/search.py

@@ -27,6 +27,9 @@ class Expression(BaseModel):
     fuzzy: bool = False
     min_string_similarity: Optional[float] = Field(default=0.1)
 
+    def uses_column(self, name: str) -> bool:
+        return self.column_name == name
+
 
 class ExpressionGroup(BaseModel):
     join: Optional[Join]
@@ -46,5 +49,11 @@ def expressions_validator(
             raise ValueError("a join operator is not needed for one expression")
         return v
 
+    def uses_column(self, name: str) -> bool:
+        for expression in self.expressions:
+            if expression.uses_column(name):
+                return True
+        return False
+
 
 ExpressionGroup.update_forward_refs()

app/schemas/station.py

@@ -15,6 +15,10 @@ class StationBase(BaseModel):
     name: str
     date: date
     coordinates: List[float] = Field(min_items=2, max_items=2)
+    fao_area: int
+    location: str
+    gear: Optional[str]
+    sediment_sample: Optional[str]
 
     @validator("coordinates", pre=True)
     def to_point(cls, value: WKBElement) -> List[float]:

app/utils/species.py

@@ -0,0 +1,17 @@
+from typing import List
+
+from app.models import Species
+
+
+def binomial_only(species: List[Species]) -> List[Species]:
+    """
+    TODO: This is a temporary fix. In the future, we could consider filtering out genera
+    when loading data into the database or as part of the OCR workflow.
+    """
+    # Unlike `current_name`, `current_canonical_full_name` doesn't include
+    # author(s) and year of publication, so for a genus, there won't be any spaces.
+    return [
+        sp
+        for sp in species
+        if sp.current_canonical_simple_name and " " in sp.current_canonical_simple_name
+    ]