ci: update pipeline

.github/workflows/release.yml

@@ -3,6 +3,7 @@ name: Release Juzgadores 2024-2025 data
 on:
   release:
     types: [created]
+  workflow_dispatch:
 
 jobs:
   build:
@@ -24,7 +25,7 @@ jobs:
 
       - name: Generate files
         run: |
-          python -m dof_utils.extract_juzgadores_202 data/15122024-MAT.pdf ./output
+          python -m dof_utils.extract_juzgadores data/15122024-MAT.pdf ./output
 
       - name: Upload Release Assets
         env:

README.md

@@ -7,5 +7,5 @@ Utilities for extracting data from DOF (Diario Oficial de la Federación) public
 Public data downloaded from: <https://www.dof.gob.mx/2024/CJF/listado_peritos_PJF_2025.pdf>
 
 ```bash
-python -m dof_utils.extract_juzgadores_202 data/15122024-MAT.pdf ./output
+python -m dof_utils.extract_juzgadores data/15122024-MAT.pdf ./output
 ```

dof_utils/pdf_table_extractor.py

@@ -1,19 +1,24 @@
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Callable, TypeAlias
+from typing import Any, Callable, Protocol, TypeAlias, TypedDict
 
 import pandas as pd
 import pdfplumber
 from pdfplumber.page import Page
-from typing_extensions import Protocol
 
-
-TableRow: TypeAlias = list[str]
+TableRow: TypeAlias = list[str | None]
 TableData: TypeAlias = list[TableRow]
 ExtractedTable: TypeAlias = tuple[int, str, TableData]
 BBox: TypeAlias = tuple[float, float, float, float]
 
 
+class TableState(TypedDict):
+    tables: list[ExtractedTable]
+    table: TableData
+    heading: str
+    table_id: int
+
+
 class TableValidator(Protocol):
     """Protocol for table validation"""
 
@@ -47,11 +52,14 @@ def __init__(
         self.post_process = post_process or (lambda x: x)
 
     def process_table_data(
-        self, table_data: TableData, heading: str, current_state: dict[str, any]
+        self, table_data: TableData, heading: str, current_state: TableState
     ) -> None:
         """Process extracted table data and update current state."""
         # Replace newlines with spaces in all table data cells
-        table_data = [[cell.replace("\n", " ") for cell in row] for row in table_data]
+        table_data = [
+            [cell.replace("\n", " ") if cell is not None else "" for cell in row]
+            for row in table_data
+        ]
 
         if not table_data or not self.validator.is_valid_table(table_data):
             return
@@ -77,7 +85,12 @@ def process_table_data(
 
     def extract_tables(self, pdf_path: Path) -> list[ExtractedTable]:
         """Extract and merge tables from PDF with their headings."""
-        state = {"tables": [], "table": [], "heading": "", "table_id": 0}
+        state: TableState = {
+            "tables": [],
+            "table": [],
+            "heading": "",
+            "table_id": 0,
+        }
 
         with pdfplumber.open(pdf_path) as pdf:
             for page in pdf.pages:

pyproject.toml

@@ -43,7 +43,6 @@ include = '\.pyi?$'
 [tool.isort]
 profile = "black"
 multi_line_output = 3
-line-length = 88
 
 [tool.mypy]
 python_version = "3.13"