focus-validator 0.5.2.dev3__tar.gz → 0.5.2.dev4__tar.gz

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/PKG-INFO

@@ -1,15 +1,14 @@
 Metadata-Version: 2.1
 Name: focus_validator
-Version: 0.5.2.dev3
+Version: 0.5.2.dev4
 Summary: FOCUS spec validator.
-Requires-Python: >=3.8.3,<4.0.0
+Requires-Python: >=3.9,<4.0
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Requires-Dist: numpy (>=1.24,<1.25) ; python_version >= "3.8" and python_version < "3.9"
-Requires-Dist: numpy (>=1.26,<1.27) ; python_version >= "3.12" and python_version < "3.13"
+Requires-Dist: numpy (>=1.26,<2.0)
 Requires-Dist: pandas (>=2,<3)
 Requires-Dist: pandasql (>=0.7.3,<0.8.0)
 Requires-Dist: pandera (>=0.17.2,<0.18.0)
@@ -34,7 +33,7 @@ tbd
 
 ### Prerequisites
 
-- Python 3.8+
+- Python 3.9+
 - Poetry (Package & Dependency Manager)
 
 ### Installation

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/README.md

@@ -10,7 +10,7 @@ tbd
 
 ### Prerequisites
 
-- Python 3.8+
+- Python 3.9+
 - Poetry (Package & Dependency Manager)
 
 ### Installation

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/focus_validator/config_objects/common.py

@@ -68,3 +68,8 @@ def generate_check_friendly_name(check, column_id):
             return f"{column_id} does not allow null values."
     elif isinstance(check, DataTypeCheck):
         return f"{column_id} requires values of type {check.data_type.value}."
+    elif isinstance(check, SQLQueryCheck):
+        sql_query = " ".join([word.strip() for word in check.sql_query.split()])
+        return f"{column_id} requires values that return true when evaluated by the following SQL query: {sql_query}"
+    else:
+        raise NotImplementedError(f"Check {check} not implemented.")

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/focus_validator/config_objects/focus_to_pandera_schema_converter.py

@@ -72,7 +72,7 @@ class FocusToPanderaSchemaConverter:
             )
         elif isinstance(check, AllowNullsCheck):
             return pa.Check.check_not_null(
-                error=error_string, ignore_na=False, allow_nulls=check.allow_nulls
+                error=error_string, ignore_na=check.allow_nulls
             )
         else:
             raise FocusNotImplementedError(

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/focus_validator/config_objects/rule.py

@@ -1,8 +1,9 @@
 import os
-from typing import Optional, Union
+from typing import Annotated, Optional, Union
 
 import yaml
-from pydantic import BaseModel, ConfigDict, model_validator
+from pydantic import BaseModel, ConfigDict, Field, field_validator
+from pydantic_core.core_schema import ValidationInfo
 
 from focus_validator.config_objects.common import (
     SIMPLE_CHECKS,
@@ -33,44 +34,47 @@ class Rule(BaseModel):
         SIMPLE_CHECKS, AllowNullsCheck, ValueInCheck, DataTypeCheck, SQLQueryCheck
     ]
 
-    check_friendly_name: Optional[
-        str
+    check_friendly_name: Annotated[
+        Optional[str], Field(validate_default=True)
     ] = None  # auto generated or else can be overwritten
-    check_type_friendly_name: Optional[str] = None
+    check_type_friendly_name: Annotated[
+        Optional[str], Field(validate_default=True)
+    ] = None
 
     model_config = ConfigDict(
         extra="forbid",  # prevents config from containing any undesirable keys
         frozen=True,  # prevents any modification to any attribute onces loaded from config
     )
 
-    # @root_validator
-    @model_validator(mode="before")
-    @classmethod
-    def root_val(cls, values):
-        """
-        Root validator that checks for all options passed in the config and generate missing options.
-        """
-        if values is None:
-            values = {}
-
-        check = values.get("check")
-        check_friendly_name = values.get("check_friendly_name")
-        column_id = values.get("column_id")
-        if check is not None:
+    @field_validator("check_friendly_name")
+    def validate_or_generate_check_friendly_name(
+        cls, check_friendly_name, validation_info: ValidationInfo
+    ):
+        values = validation_info.data
+        if (
+            check_friendly_name is None
+            and values.get("check") is not None
+            and values.get("column_id") is not None
+        ):
+            check_friendly_name = generate_check_friendly_name(
+                check=values["check"], column_id=values["column_id"]
+            )
+        return check_friendly_name
+
+    @field_validator("check_type_friendly_name")
+    def validate_or_generate_check_type_friendly_name(
+        cls, check_type_friendly_name, validation_info: ValidationInfo
+    ):
+        values = validation_info.data
+        if values.get("check") is not None and values.get("column_id") is not None:
+            check = values.get("check")
             if isinstance(check, str):
                 check_type_friendly_name = "".join(
                     [word.title() for word in check.split("_")]
                 )
             else:
                 check_type_friendly_name = check.__class__.__name__
-            values["check_type_friendly_name"] = check_type_friendly_name
-
-        if check_friendly_name is None and column_id is not None:
-            values["check_friendly_name"] = generate_check_friendly_name(
-                check=check, column_id=column_id
-            )
-
-        return values
+        return check_type_friendly_name
 
     @staticmethod
     def load_yaml(

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/focus_validator/data_loaders/csv_data_loader.py

@@ -6,4 +6,4 @@ class CSVDataLoader:
         self.data_filename = data_filename
 
     def load(self):
-        return pd.read_csv(self.data_filename, keep_default_na=False)
+        return pd.read_csv(self.data_filename)

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/focus_validator/main.py

@@ -1,8 +1,7 @@
 import argparse
-import os
 import sys
 
-from focus_validator.validator import Validator
+from focus_validator.validator import DEFAULT_VERSION_SETS_PATH, Validator
 
 
 def main():
@@ -37,7 +36,7 @@ def main():
     )
     parser.add_argument(
         "--rule-set-path",
-        default=os.path.join("focus_validator", "rules", "version_sets"),
+        default=DEFAULT_VERSION_SETS_PATH,
         help="Path to rules definitions",
     )
     parser.add_argument(

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/focus_validator/outputter/outputter_unittest.py

@@ -1,5 +1,4 @@
 import logging
-import re
 import sys
 import xml.etree.cElementTree as ET
 from datetime import datetime, timezone
@@ -146,9 +145,9 @@ class UnittestOutputter:
 
         # Add the testcases to the testsuites
         added_testsuites = {}
-        for testcase in [
-            r for r in rows if re.match(r"^FV-[D,M][0-9]{3}-[0-9]{4}$", r["check_name"])
-        ]:
+        for testcase in rows:
+            if testcase["status"].value == "errored":
+                continue
             test_suite_id = testcase["check_name"].rsplit("-", 1)[0]
             if test_suite_id not in added_testsuites:
                 formatter.add_testsuite(

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/focus_validator/rules/checks.py

@@ -21,11 +21,8 @@ def is_camel_case(column_name):
 
 
 @extensions.register_check_method()
-def check_not_null(pandas_obj: pd.Series, allow_nulls: bool):
-    # TODO: works for string type, need to verify for other data types
-    check_values = pandas_obj.isnull() | (pandas_obj == "")
-    if not allow_nulls:
-        check_values = check_values | (pandas_obj == "NULL")
+def check_not_null(pandas_obj: pd.Series):
+    check_values = pandas_obj.isnull()
     return ~check_values
 
 

{focus_validator-0.5.2.dev3 → focus_validator-0.5.2.dev4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "focus_validator"
-version = "0.5.2-dev3"
+version = "0.5.2-dev4"
 description = "FOCUS spec validator."
 authors = []
 readme = "README.md"
@@ -19,7 +19,7 @@ generate-setup-file = false
 script = "build.py"
 
 [tool.poetry.dependencies]
-python = "^3.8.3"
+python = "^3.9"
 pandas = "^2"
 tabulate = "*"
 pyarrow = "*"
@@ -28,12 +28,7 @@ pyyaml = "*"
 requests = "*"
 pandera = { version = "^0.17.2" }
 sqlglot = "^18.7.0"
-
-# for Python 3.12, force higher version of numpy
-numpy = [
-    { version = "~1.24", python = "~3.8" },
-    { version = "~1.26", python = "~3.12" }
-]
+numpy = { version = "^1.26"}
 pytz = "^2023.3.post1"
 pandasql = "^0.7.3"