despacho/exportar.py

#!/usr/bin/env python3
"""
Exportador de contratos a .docx con formato forense mexicano.
Convierte los archivos _v2.md a documentos Word con:
  - Times New Roman 12
  - Interlineado 1.5
  - Sangría 1.27 cm en cuerpo
  - Título centrado y MAYÚSCULAS
  - Alineación justificada

Uso:
    python3 exportar.py                        # Exporta todos los _v2.md
    python3 exportar.py contrato-cdmx-ejemplo_v2.md   # Exporta uno específico
"""

import re
import sys
import os
from pathlib import Path

try:
    from docx import Document
    from docx.shared import Pt, Cm
    from docx.enum.text import WD_ALIGN_PARAGRAPH
    from docx.oxml.ns import qn
except ImportError:
    print("ERROR: Se requiere python-docx. Instalar con: pip install python-docx")
    sys.exit(1)


def configure_font(run, size=12, bold=False, italic=False, name="Times New Roman"):
    run.font.name = name
    run.font.size = Pt(size)
    run.bold = bold
    run.italic = italic
    # Forzar fuente en XML para compatibilidad
    rpr = run._element.get_or_add_rPr()
    rFonts = rpr.find(qn('w:rFonts'))
    if rFonts is None:
        rFonts = run._element.makeelement(qn('w:rFonts'), {})
        rpr.insert(0, rFonts)
    rFonts.set(qn('w:eastAsia'), name)
    rFonts.set(qn('w:cs'), name)


def set_paragraph_spacing(paragraph, line_spacing=1.5):
    pf = paragraph.paragraph_format
    pf.line_spacing = line_spacing
    pf.space_before = Pt(0)
    pf.space_after = Pt(6)


def add_formatted_paragraph(doc, text, alignment=WD_ALIGN_PARAGRAPH.JUSTIFY,
                            bold=False, size=12, indent_cm=0, space_after=6):
    """Agrega un párrafo con formato estándar."""
    p = doc.add_paragraph()
    p.alignment = alignment
    set_paragraph_spacing(p)
    pf = p.paragraph_format
    pf.space_after = Pt(space_after)
    if indent_cm > 0:
        pf.first_line_indent = Cm(indent_cm)

    run = p.add_run(text)
    configure_font(run, size=size, bold=bold)
    return p


def add_separator(doc):
    """Agrega una línea separadora."""
    p = doc.add_paragraph()
    p.alignment = WD_ALIGN_PARAGRAPH.CENTER
    run = p.add_run("— — —")
    configure_font(run, size=12, bold=False)
    return p


def add_signature_block(doc, lines):
    """Agrega un bloque de firmas."""
    for line in lines:
        p = doc.add_paragraph()
        p.alignment = WD_ALIGN_PARAGRAPH.LEFT
        set_paragraph_spacing(p)
        run = p.add_run(line)
        configure_font(run, size=12, bold=False)


def markdown_to_docx(md_path, output_dir=None):
    """Convierte un archivo markdown de contrato a .docx."""
    print(f"Procesando: {md_path}")

    with open(md_path, "r", encoding="utf-8") as f:
        content = f.read()

    doc = Document()

    # Configurar márgenes
    for section in doc.sections:
        section.top_margin = Cm(2.5)
        section.bottom_margin = Cm(2.5)
        section.left_margin = Cm(3)
        section.right_margin = Cm(2.5)

    lines = content.split("\n")
    i = 0

    while i < len(lines):
        line = lines[i].strip()
        i += 1

        if not line:
            continue

        # Separador de secciones
        if line == "- - -":
            add_separator(doc)
            continue

        # Título principal (primera línea en MAYÚSCULAS)
        if line == line.upper() and len(line) > 10 and not line.startswith("**") and i < 10:
            add_formatted_paragraph(
                doc, line,
                alignment=WD_ALIGN_PARAGRAPH.CENTER,
                bold=True,
                size=14,
                space_after=12
            )
            continue

        # Encabezados de secciones: D E C L A R A C I O N E S, C L Á U S U L A S
        if line.startswith("**") and line.endswith("**") and i < len(lines):
            clean = line.strip("*")
            add_formatted_paragraph(
                doc, clean,
                alignment=WD_ALIGN_PARAGRAPH.CENTER,
                bold=True,
                size=12,
                space_after=10
            )
            continue

        if line.startswith("D E C L A R A C I O N E S") or line.startswith("C L Á U S U L A S"):
            add_formatted_paragraph(
                doc, line,
                alignment=WD_ALIGN_PARAGRAPH.CENTER,
                bold=True,
                size=12,
                space_after=10
            )
            continue

        # Líneas en negritas con ** (títulos de cláusulas como PRIMERA. — OBJETO)
        if line.startswith("**") and line.endswith("**") and len(line) > 4:
            clean = line.strip("*")
            add_formatted_paragraph(
                doc, clean,
                alignment=WD_ALIGN_PARAGRAPH.LEFT,
                bold=True,
                size=12,
                space_after=6
            )
            continue

        # Negritas dentro de la línea (formato **texto**)
        if "**" in line:
            add_formatted_paragraph(
                doc, line.replace("**", ""),
                alignment=WD_ALIGN_PARAGRAPH.JUSTIFY,
                bold=False,
                size=12,
                indent_cm=1.27,
                space_after=6
            )
            continue

        # Bloque de ciudad y fecha
        if " a " in line and (" de " in line) and i < 5:
            add_formatted_paragraph(
                doc, line,
                alignment=WD_ALIGN_PARAGRAPH.LEFT,
                bold=False,
                size=12,
                space_after=6
            )
            continue

        # Texto normal — cuerpo del contrato
        add_formatted_paragraph(
            doc, line,
            alignment=WD_ALIGN_PARAGRAPH.JUSTIFY,
            bold=False,
            size=12,
            indent_cm=1.27,
            space_after=6
        )

    # Guardar archivo
    md_path = Path(md_path)
    if output_dir:
        output_dir = Path(output_dir)
        output_dir.mkdir(parents=True, exist_ok=True)
        output_path = output_dir / f"{md_path.stem}.docx"
    else:
        output_path = md_path.with_suffix(".docx")

    doc.save(str(output_path))
    print(f"  ✓ Exportado: {output_path}")
    return output_path


def main():
    # Buscar archivos _v2.md
    script_dir = Path(__file__).parent
    md_files = list(script_dir.glob("*_v2.md"))

    if not md_files:
        print("No se encontraron archivos *_v2.md en el directorio.")
        return

    # Crear directorio de salida
    output_dir = script_dir / "docx_output"

    for md_file in md_files:
        try:
            markdown_to_docx(md_file, output_dir=output_dir)
        except Exception as e:
            print(f"  ✗ Error en {md_file}: {e}")

    print(f"\nExportación completa. Archivos en: {output_dir}/")


if __name__ == "__main__":
    main()