feat: Replace main.py with Typer-based CLI app

.devcontainer/devcontainer.json

@@ -40,7 +40,6 @@
         ],
         "editor.tabSize": 4,
         "editor.formatOnSave": true,
-        "python.formatting.provider": "none",
         "python.envFile": "${workspaceFolder}/.env",
         "editor.codeActionsOnSave": {
           "source.organizeImports": true

.github/workflows/linters.yml

@@ -10,7 +10,6 @@ jobs:
       - uses: psf/black@stable
         with:
           options: "--check --diff --verbose"
-          version: "~= 22.0"
   ruff:
     runs-on: ubuntu-latest
     steps:

pyproject.toml

@@ -1,3 +1,7 @@
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
 [tool.poetry]
 name = "regtech-data-validator"
 version = "0.1.0"
@@ -13,15 +17,18 @@ pandera = "0.16.1"
 [tool.poetry.group.dev.dependencies]
 pytest = "7.4.0"
 pytest-cov = "4.1.0"
-black = "23.3.0"
-ruff = "0.0.259"
+black = "23.10.1"
+ruff = "0.1.4"
 
 [tool.poetry.group.data.dependencies]
 openpyxl = "^3.1.2"
 
-[build-system]
-requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+[tool.poetry.group.cli.dependencies]
+tabulate = "^0.9.0"
+typer = "^0.9.0"
+
+[tool.poetry.scripts]
+cfpb-val = 'regtech_data_validator.cli:app'
 
 # Black formatting
 [tool.black]

regtech_data_validator/check_functions.py

@@ -11,7 +11,6 @@
 the function. This may or may not align with the name of the validation
 in the fig."""
 
-
 import re
 from datetime import datetime, timedelta
 from typing import Dict

regtech_data_validator/cli.py

@@ -0,0 +1,147 @@
+from dataclasses import dataclass
+from enum import StrEnum
+import json
+from pathlib import Path
+from typing import Annotated, Optional
+
+import pandas as pd
+from tabulate import tabulate
+import typer
+
+from regtech_data_validator.create_schemas import validate_phases
+
+
+app = typer.Typer(no_args_is_help=True, pretty_exceptions_enable=False)
+
+
+@dataclass
+class KeyValueOpt:
+    key: str
+    value: str
+
+
+def parse_key_value(kv_str: str) -> KeyValueOpt:
+    split_str = kv_str.split('=')
+
+    if len(split_str) != 2:
+        raise ValueError(f'Invalid key/value pair: {kv_str}')
+
+    return KeyValueOpt(split_str[0], split_str[1])
+
+
+class OutputFormat(StrEnum):
+    CSV = 'csv'
+    JSON = 'json'
+    PANDAS = 'pandas'
+    TABLE = 'table'
+
+
+def df_to_str(df: pd.DataFrame) -> str:
+    with pd.option_context('display.width', None, 'display.max_rows', None):
+        return str(df)
+
+
+def df_to_csv(df: pd.DataFrame) -> str:
+    return df.to_csv()
+
+
+def df_to_table(df: pd.DataFrame) -> str:
+    # trim field_value field to just 50 chars, similar to DataFrame default
+    table_df = df.drop(columns='validation_desc').sort_index()
+    table_df['field_value'] = table_df['field_value'].str[0:50]
+
+    # NOTE: `type: ignore` because tabulate package typing does not include Pandas
+    #        DataFrame as input, but the library itself does support it. ¯\_(ツ)_/¯
+    return tabulate(table_df, headers='keys', showindex=True, tablefmt='rounded_outline')  # type: ignore
+
+
+def df_to_json(df: pd.DataFrame) -> str:
+    findings_json = []
+    findings_by_v_id_df = df.reset_index().set_index(['validation_id', 'record_no', 'field_name'])
+
+    for v_id_idx, v_id_df in findings_by_v_id_df.groupby(by='validation_id'):
+        v_head = v_id_df.iloc[0]
+
+        finding_json = {
+            'validation': {
+                'id': v_id_idx,
+                'name': v_head.at['validation_name'],
+                'description': v_head.at['validation_desc'],
+                'severity': v_head.at['validation_severity'],
+            },
+            'records': [],
+        }
+        findings_json.append(finding_json)
+
+        for rec_idx, rec_df in v_id_df.groupby(by='record_no'):
+            record_json = {'record_no': rec_idx, 'fields': []}
+            finding_json['records'].append(record_json)
+
+            for field_idx, field_df in rec_df.groupby(by='field_name'):
+                field_head = field_df.iloc[0]
+                record_json['fields'].append({'name': field_idx, 'value': field_head.at['field_value']})
+
+    json_str = json.dumps(findings_json, indent=4)
+
+    return json_str
+
+
+@app.command()
+def describe() -> None:
+    """
+    Describe CFPB data submission formats and validations
+    """
+
+    print('Feature coming soon...')
+
+
+@app.command(no_args_is_help=True)
+def validate(
+    path: Annotated[
+        Path,
+        typer.Argument(
+            exists=True,
+            dir_okay=False,
+            readable=True,
+            resolve_path=True,
+            show_default=False,
+            help='Path of file to be validated',
+        ),
+    ],
+    context: Annotated[
+        Optional[list[KeyValueOpt]],
+        typer.Option(
+            parser=parse_key_value,
+            metavar='<key>=<value>',
+            help='[example: lei=12345678901234567890]',
+            show_default=False,
+        ),
+    ] = None,
+    output: Annotated[Optional[OutputFormat], typer.Option()] = OutputFormat.TABLE,
+) -> tuple[bool, pd.DataFrame]:
+    """
+    Validate CFPB data submission
+    """
+    context_dict = {x.key: x.value for x in context} if context else {}
+    input_df = pd.read_csv(path, dtype=str, na_filter=False)
+    is_valid, findings_df = validate_phases(input_df, context_dict)
+
+    if not is_valid:
+        match output:
+            case OutputFormat.PANDAS:
+                print(df_to_str(findings_df))
+            case OutputFormat.CSV:
+                print(df_to_csv(findings_df))
+            case OutputFormat.JSON:
+                print(df_to_json(findings_df))
+            case OutputFormat.TABLE:
+                print(df_to_table(findings_df))
+            case _:
+                raise ValueError(f'output format "{output}" not supported')
+
+    # returned values are only used in unit tests
+    return is_valid, findings_df
+
+
+if __name__ == '__main__':
+    app()