Add App 3 initial implementation: classifier, catalog, indexer and GUI

.gitignore

@@ -1,207 +1,36 @@
-# Byte-compiled / optimized / DLL files
+# Python
 __pycache__/
-*.py[codz]
+*.py[cod]
 *$py.class
 
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py.cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# UV
-#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#uv.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-#poetry.toml
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
-#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
-#pdm.lock
-#pdm.toml
-.pdm-python
-.pdm-build/
-
-# pixi
-#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
-#pixi.lock
-#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
-#   in the .venv directory. It is recommended not to include this directory in version control.
-.pixi
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.envrc
-.venv
-env/
+# Virtualenvs
+.venv/
 venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
+env/
 
-# mypy
+# Tool caches
+.pytest_cache/
 .mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-
-# Abstra
-# Abstra is an AI-powered process automation framework.
-# Ignore directories containing user credentials, local state, and settings.
-# Learn more at https://abstra.io/docs
-.abstra/
-
-# Visual Studio Code
-#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
-#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
-#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
-#  you could uncomment the following to ignore the entire vscode folder
-# .vscode/
-
-# Ruff stuff:
 .ruff_cache/
+.coverage
+htmlcov/
+
+# OS / editors
+.DS_Store
+Thumbs.db
+.vscode/
+.idea/
 
-# PyPI configuration file
-.pypirc
+# Local runtime artifacts
+*.log
+*.tmp
+*.sqlite
+*.sqlite3
 
-# Cursor
-#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
-#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
-#  refer to https://docs.cursor.com/context/ignore-files
-.cursorignore
-.cursorindexingignore
+# Project metadata generated in client folders
+**/.metadata/
 
-# Marimo
-marimo/_static/
-marimo/_lsp/
-__marimo__/
+# Build artifacts
+build/
+dist/
+*.egg-info/

README.md

@@ -314,3 +314,35 @@ App 3 reemplaza a App 2 cuando cumpla todo esto:
 - No hardcodear rutas — usar siempre `get_setting('network_drive')` de `settings.py`
 - Para SQLite con múltiples hilos: usar `threading.Lock()` como en `StateDB` de `gmail_utils.py`
 - Para PDFs firmados digitalmente: usar `pymupdf`, no `PyPDF2`
+
+---
+
+## Estado implementación App 3 (v1 inicial)
+
+Se agregó una primera versión ejecutable en `app3/` que reutiliza lógica de App 1 y App 2:
+
+- Reusa `CRXMLManager` (App 2) para parsing XML y datos de factura.
+- Reusa `extract_clave_and_cedula` (App 1) para asociar PDFs con clave numérica.
+- Reusa `settings.py` y `client_profiles.py` (App 1) para resolver rutas y sesión cliente.
+- Implementa `clasificacion.sqlite` y movimiento seguro con SHA256 antes de borrar origen.
+- Implementa `catalogo_cuentas.json` con guardado atómico.
+
+### Ejecutar App 3 v1
+
+```bash
+python -m app3.main
+```
+
+### Dependencias (App 3 v1)
+
+Instalar dependencias base:
+
+```bash
+pip install -r requirements.txt
+```
+
+Para desarrollo y pruebas:
+
+```bash
+pip install -r requirements-dev.txt
+```

app3/__init__.py

@@ -0,0 +1 @@
+"""App 3 package."""

app3/bootstrap.py

@@ -0,0 +1,14 @@
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+
+def bootstrap_legacy_paths() -> None:
+    """Add legacy app folders to sys.path so App 3 can reuse App1/App2 modules."""
+    repo_root = Path(__file__).resolve().parent.parent
+    legacy_paths = [repo_root / "APP 1", repo_root / "APP 2"]
+    for path in legacy_paths:
+        path_str = str(path)
+        if path.exists() and path_str not in sys.path:
+            sys.path.insert(0, path_str)

app3/config.py

@@ -0,0 +1,23 @@
+from __future__ import annotations
+
+from pathlib import Path
+
+from .bootstrap import bootstrap_legacy_paths
+
+bootstrap_legacy_paths()
+
+from facturacion_system.core.settings import get_setting  # noqa: E402
+
+
+def network_drive() -> Path:
+    return Path(str(get_setting("network_drive", "Z:/DATA")))
+
+
+def client_root(year: int) -> Path:
+    return network_drive() / f"PF-{year}" / "CLIENTES"
+
+
+def metadata_dir(client_folder: Path) -> Path:
+    path = client_folder / ".metadata"
+    path.mkdir(parents=True, exist_ok=True)
+    return path

app3/core/catalog.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+
+DEFAULT_CATALOG = {
+    "INGRESOS": {"FACTURAS ELECTRONICAS": {}, "TIQUETES ELECTRONICOS": {}},
+    "COMPRAS": {"COMPRAS DE CONTADO": {}, "COMPRAS DE CREDITO": {}},
+    "GASTOS": {
+        "GASTOS ESPECIFICOS": {"ALQUILER": {}, "HONORARIOS PROFESIONALES": {}},
+        "GASTOS GENERALES": {"ELECTRICIDAD": {}, "PAPELERIA Y UTILES DE OFICINA": {}},
+    },
+}
+
+
+class CatalogManager:
+    def __init__(self, metadata_dir: Path) -> None:
+        self.path = metadata_dir / "catalogo_cuentas.json"
+
+    def load(self) -> dict:
+        if self.path.exists():
+            try:
+                raw_text = self.path.read_text(encoding="utf-8").strip()
+                if not raw_text:
+                    raise ValueError("archivo vacío")
+                data = json.loads(raw_text)
+                if isinstance(data, dict):
+                    return data
+                raise ValueError("catálogo inválido")
+            except Exception:
+                # Respaldo y recuperación automática a default.
+                backup = self.path.with_suffix(".invalid.json")
+                try:
+                    if self.path.exists():
+                        self.path.replace(backup)
+                except Exception:
+                    pass
+                self.save(DEFAULT_CATALOG)
+                return DEFAULT_CATALOG
+        self.save(DEFAULT_CATALOG)
+        return DEFAULT_CATALOG
+
+    def save(self, data: dict) -> None:
+        self.path.parent.mkdir(parents=True, exist_ok=True)
+        tmp = self.path.with_suffix(".tmp")
+        tmp.write_text(json.dumps(data, ensure_ascii=False, indent=2, sort_keys=True), encoding="utf-8")
+        tmp.replace(self.path)