Support batch validation

.pre-commit-config.yaml

@@ -11,7 +11,6 @@ repos:
 #    pass_filenames: false
 #    # types: [python]
 
-
   - id: black
     name: black
     language: system
@@ -39,24 +38,25 @@ repos:
       # Tell ruff to fix sorting of imports
       - "--fix"
       - "--format=github"
-      - "--target-version=py37"
+      - "--target-version=py311"
       - "."
     # types: [python]
     pass_filenames: false
 
  # https://jaredkhan.com/blog/mypy-pre-commit
   - id: mypy
     name: mypy
+    # entry: python -c "import sys; print(sys.argv)"
     entry: mypy
+    args: ["--check-untyped-defs"]
     language: python
-    # use your preferred Python version
-    # language_version: python3.7
-    # additional_dependencies: ["mypy==0.790"]
-    types: [python]
-    # use require_serial so that script
-    # is only called once per commit
+    language_version: python3.13
     require_serial: true
-    exclude: shape.py|compareshape.py
+    # To be able to exclude properly
+    pass_filenames: true
+    types: [python]
+    # args: ["--config-file=pyproject.toml"]
+    exclude: .*(shape|compareshape)\.py$
     # Print the number of files as a sanity-check
     # verbose: true
 

README.md

@@ -1,15 +1,14 @@
-# [Entityshape](https://www.wikidata.org/wiki/Q119899931)
-A python library to compare a wikidata entity 
-(item or lexeme) with a 
-[Wikibase Entity Schema](https://www.wikidata.org/wiki/Wikidata:WikiProject_Schemas).
+# [EntityValidator](https://www.wikidata.org/wiki/Q119899931)
+A python library and FastAPI backend to compare a wikidata entity 
+(item or lexeme) with a [Wikibase Entity Schema](https://www.wikidata.org/wiki/Wikidata:WikiProject_Schemas).
 
 Based on https://github.com/Teester/entityshape by Mark Tully 
 and https://github.com/dpriskorn/PyEntityshape by Dennis Priskorn
 
 # Features
 * compare a given wikidata item with an entityschema and dig into missing properties, too many statement, etc.
 * determine whether an item is valid according to a certain schema or not
-* support for any Wikibase
+* the backend currently only support Wikidata, but the library has support for any Wikibase
 
 # Limitations
 The shape and compareshape classes currently only support:
@@ -22,41 +21,36 @@ It is still a bit unclear if and how the qualifier validation works.
 Validation of lexemes is still considered experimental. 
 Feel free to open an issue with a working or non-working example.
 
-# Installation
+~~# Installation
 Get it from pypi
 
-`$ pip install pyentityshape`
+`$ pip install entityvalidator`~~
 
 # Usage
 
-## Jupyter Notebooks
+~~## Jupyter Notebooks
 Example notebooks with code for validation of multiple items: 
 [hiking paths](https://public-paws.wmcloud.org/User:So9q/Validating%20a%20group%20of%20items-all-hiking-paths-in-sweden.ipynb) 
 [campsites](https://public-paws.wmcloud.org/User:So9q/Validating%20a%20group%20of%20items-all-campsites-in-sweden.ipynb) 
-[shelters](https://public-paws.wmcloud.org/User:So9q/Validating%20a%20group%20of%20items-all-shelters-in-sweden.ipynb)
+[shelters](https://public-paws.wmcloud.org/User:So9q/Validating%20a%20group%20of%20items-all-shelters-in-sweden.ipynb)~~
 
 ## CLI
 Example:
 ```
-# Note that we default to English so the lang parameter here is optional. 
+import pprint
 # Note that we default to Wikidata so the mediawiki_api_url and wikibase_url parameters here are optional. 
-e = EntityShape(eid="E1", 
+e = EntityValidator(eid="E1", 
                 entity_id="Q1", 
                 lang="en", 
                 # mediawiki_api_url='http://localhost/api.php', 
                 # wikibase_url='http://wikibase.svc'
                 )
-result = e.validate_and_get_result()
-# Get human readable result
-print(result)
-"Valid: False\nProperties_without_enough_correct_statements: instance of (P31)"
-# Access the data
-print(result.properties_without_enough_correct_statements)
-"{'P31'}"
+# Machine readable json result
+pprint(e.get_result)
 ```
 
 ## Validation
-The is_valid method on the Result object mimics all red warnings displayed by https://www.wikidata.org/wiki/User:Teester/EntityShape.js 
+The is_valid method on the Result object mimics all red warnings displayed by https://www.wikidata.org/wiki/User:Teester/entityvalidator.js 
 
 It currently checks these five conditions that all have to be false for the item to be valid:
 1.  properties with too many statements found
@@ -115,7 +109,8 @@ advice and help with Ruff to make this better.
 GPLv3+
 
 # What I learned
-* Forking other peoples undocumented spaghetti code is not much fun.
+* Forking other peoples undocumented code is not much fun.
 * I want to find a more reliable validator that support somevalue and novalue
 * Pydantic is wonderful yet again it makes working with OOP easy peasy :)
-* Ruff is crazy fast and very nice!
+* Ruff is crazy fast and very nice!
+* FastAPI is super nice

api.py

@@ -0,0 +1,109 @@
+import logging
+from typing import Any
+
+from fastapi import APIRouter, FastAPI, HTTPException, Query
+from starlette.responses import RedirectResponse
+
+import config
+from entityvalidator import (
+    ApiError,
+    EidError,
+    EntityIdError,
+    EntityValidator,
+    WikibaseEntitySchemaDownloadError,
+)
+from entityvalidator.exceptions import (
+    MissingInformationError,
+    NoEntitySchemaDataError,
+    WikibasePropertiesDownloadError,
+)
+
+app = FastAPI()
+logging.basicConfig(level=config.loglevel)
+logger = logging.getLogger(__name__)
+router = APIRouter()
+
+
+@app.get("/", include_in_schema=False)
+def root_redirect():
+    return RedirectResponse(url="/docs")
+
+
+@router.get("/validate")
+def validate_entities(
+    # mandatory
+    eid: str = Query(..., description="EntitySchema ID, ex. E100"),
+    entity_ids: str = Query(
+        ..., description="Comma-separated list of entity IDs, e.g. Q42,Q43"
+    ),
+    # We only support Wikidata for now
+    # wikibase_url: str = Query(default="http://www.wikidata.org"),
+    # mediawiki_api_url: str = Query(default="https://www.wikidata.org/w/api.php")
+) -> dict[str, Any]:
+    """
+    Validate a list of entity IDs against a specific Wikibase entity schema.
+
+    Args:
+        eid (str): The EntitySchema ID to validate against (e.g., "E100").
+        entity_ids (str): A comma-separated list of entity IDs to validate (max 100 IDs).
+
+    Returns:
+        dict: A dictionary containing the validation results:
+            - results (list): Details of the validation.
+
+    Raises:
+        HTTPException: Raised in case of validation failure, missing data, API errors,
+                       or unexpected exceptions.
+    """
+    # Split by comma and strip whitespace
+    entity_list = [e.strip() for e in entity_ids.split(",") if e.strip()]
+
+    # Validate at least 1 entity
+    if not entity_list:
+        raise HTTPException(
+            status_code=400, detail="At least one entity ID must be provided."
+        )
+
+    # Optional: validate max length
+    if len(entity_list) > 100:
+        raise HTTPException(status_code=400, detail="Maximum 100 entity IDs allowed.")
+    try:
+        entity_validator = EntityValidator(
+            entity_ids=entity_list,
+            eid=eid,
+        )
+        entity_validator.__download_and_validate__()
+
+        return {
+            "results": entity_validator.get_results,
+        }
+
+    except (EntityIdError, EidError) as e:
+        raise HTTPException(
+            status_code=422,
+            detail={"error": "Invalid entity id", "message": str(e)},
+        ) from e
+    except ApiError as e:
+        raise HTTPException(
+            status_code=502,
+            detail={"error": "Upstream API failed", "message": str(e)},
+        ) from e
+    except (WikibaseEntitySchemaDownloadError, WikibasePropertiesDownloadError) as e:
+        raise HTTPException(
+            status_code=502,
+            detail={"error": "Wikibase download failed", "message": str(e)},
+        ) from e
+    except (NoEntitySchemaDataError, MissingInformationError) as e:
+        raise HTTPException(
+            status_code=422,
+            detail={"error": "Missing data", "message": str(e)},
+        ) from e
+    except Exception as e:
+        logger.exception("Unexpected error during validation")
+        raise HTTPException(
+            status_code=500,
+            detail={"error": "Internal server error", "message": str(e)},
+        ) from e
+
+
+app.include_router(router, prefix="/v1")

config.py

@@ -0,0 +1,4 @@
+import logging
+
+loglevel = logging.INFO
+user_agent = "EntityValidator (https://github.com/dpriskorn/entityvalidator)"