Fix conflict-marker lint false positives

.copilotignore

@@ -0,0 +1,39 @@
+# Reduce context size for GitHub Copilot (including coding agent runs)
+# Keep this focused on generated, vendored, or binary-heavy paths.
+
+# Python caches / local envs
+__pycache__/
+.mypy_cache/
+.pytest_cache/
+.ruff_cache/
+.venv/
+.venv*/
+
+# Coverage / build artifacts
+htmlcov/
+.coverage*
+coverage.xml
+build/
+dist/
+
+# Node vendored deps
+node_modules/
+
+# Large binaries
+*.vsix
+*.zip
+*.7z
+*.tar
+*.gz
+
+# Data artifacts (keep templates/docs tracked elsewhere)
+data/bronze/
+data/silver/
+data/gold/
+data/analytics/
+data/manual/raw_downloads/
+data/manual/processed/
+data/manual/outputs/
+
+# Large generated artifacts
+stress_artifacts/

.github/workflows/lint.yml

@@ -38,7 +38,9 @@ jobs:
           import pathlib
           import sys
 
-          markers = ("<<<<<<<", "=======", ">>>>>>>")
+          # Only flag real git conflict marker lines.
+          # In particular, don't treat long doc separators like "=====" as conflicts.
+          START_MARKERS = ("<<<<<<<", ">>>>>>>", "|||||||")
           matches: list[tuple[str, int, str]] = []
 
           allowed_suffixes = {".py", ".yml", ".yaml", ".md"}
@@ -66,8 +68,9 @@ jobs:
                   continue
               for i, line in enumerate(text, start=1):
                   stripped = line.lstrip()
-                  if stripped.startswith(markers):
-                      matches.append((str(path), i, stripped.strip()))
+                  cleaned = stripped.strip()
+                  if cleaned.startswith(START_MARKERS) or cleaned == "=======":
+                      matches.append((str(path), i, cleaned))
 
           if matches:
               print("Found git merge conflict markers in tracked sources:")

.gitignore

@@ -251,6 +251,12 @@ cython_debug/
 #  you could uncomment the following to ignore the entire vscode folder
 # .vscode/
 
+# Node
+node_modules/
+
+# VS Code extension bundles (avoid committing large binaries)
+*.vsix
+
 # Ruff stuff:
 .ruff_cache/
 

.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.1.6
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+      - id: ruff-format

data_pipeline/anatel/acesso_fixo_aggregator.py

@@ -2,7 +2,7 @@
 
 import json
 from dataclasses import dataclass
-from datetime import UTC, datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any
 
@@ -71,12 +71,12 @@ def aggregate_acesso_fixo(
     group_by_technology: bool = False,
     strict: bool = False,
 ) -> AcessoFixoAggregateResult:
-    started_at = datetime.now(UTC)
+    started_at = datetime.now(timezone.utc)
 
     if df.empty:
         report = {
             "started_at": started_at.isoformat(),
-            "ended_at": datetime.now(UTC).isoformat(),
+            "ended_at": datetime.now(timezone.utc).isoformat(),
             "input_rows": 0,
             "output_rows_summary": 0,
             "output_rows_by_velocidade": 0,
@@ -152,7 +152,7 @@ def aggregate_acesso_fixo(
     else:
         by_tec_vel = None
 
-    ended_at = datetime.now(UTC)
+    ended_at = datetime.now(timezone.utc)
     report = {
         "started_at": started_at.isoformat(),
         "ended_at": ended_at.isoformat(),
@@ -186,7 +186,7 @@ def write_acesso_fixo_outputs(
     output_dir = Path(output_dir)
     output_dir.mkdir(parents=True, exist_ok=True)
 
-    ts = datetime.now(UTC).strftime("%Y%m%d_%H%M%S")
+    ts = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
 
     written: dict[str, str] = {}