#!/usr/bin/env python3
"""Batch fix: footer + documentheader for all 12 Element 1 documents."""
from docx import Document
from docx.shared import Pt, Cm, Inches, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.enum.table import WD_TABLE_ALIGNMENT
from docx.oxml.ns import qn, nsdecls
from docx.oxml import parse_xml
import os, re, copy
SRC = "/root/projects/jg/2026-PM-VBS-Element1/archive/batch-fix-pre"
DST = "/root/projects/jg/2026-PM-VBS-Element1/deliverables"
LOGO = "/root/projects/jg/assets/branding/jvg-logo-white-medium.png"
FOOTER_TEXT = "JvG Consultancy | Safety • Governance • Advisory | © 2026"
# Mapping: (source file, output file, doc_type)
DOCS = [
("PM_VBS01_01_PBZO_Beleidsdocument_v1.2.docx", "PM_VBS01_01_PBZO_Beleidsdocument_v1.3.docx", "Beleidsdocument"),
("PM_VBS01_02_Functieprofielen_Veiligheid_v1.1.docx", "PM_VBS01_02_Functieprofielen_Veiligheid_v1.2.docx", "Functieprofielen"),
("PM_VBS01_03_Organigram_Veiligheid_v1.1.docx", "PM_VBS01_03_Organigram_Veiligheid_v1.2.docx", "Organigram"),
("PM_VBS01_04_Training_Matrix_v1.1.docx", "PM_VBS01_04_Training_Matrix_v1.2.docx", "Training Matrix"),
("PM_VBS01_05_Inwerkprogramma_v1.1.docx", "PM_VBS01_05_Inwerkprogramma_v1.2.docx", "Inwerkprogramma"),
("PM_VBS01_06_Toolbox_Meeting_Procedure_v1.0.docx", "PM_VBS01_06_Toolbox_Meeting_Procedure_v1.1.docx", "Procedure"),
("PM_VBS01_07_Competentie_Assessment_v1.0.docx", "PM_VBS01_07_Competentie_Assessment_v1.1.docx", "Assessment Formulier"),
("PM_VBS01_08_BASIS_Training_Programma_v1.0.docx", "PM_VBS01_08_BASIS_Training_Programma_v1.1.docx", "Training Programma"),
("PM_VBS01_09_SPECIFIEKE_Training_Programma_v1.0.docx", "PM_VBS01_09_SPECIFIEKE_Training_Programma_v1.1.docx", "Training Programma"),
("PM_VBS01_10_Procedure_Onderaannemers_v1.0.docx", "PM_VBS01_10_Procedure_Onderaannemers_v1.1.docx", "Procedure"),
("PM_VBS01_11_Veiligheidsprestatie_Indicatoren_v1.0.docx", "PM_VBS01_11_Veiligheidsprestatie_Indicatoren_v1.1.docx", "KPI Document"),
("PM_VBS01_12_Communicatie_Meldingsprocedure_v1.0.docx", "PM_VBS01_12_Communicatie_Meldingsprocedure_v1.1.docx", "Procedure"),
]
def get_version(outfname):
m = re.search(r'_v(\d+\.\d+)', outfname)
return m.group(1) if m else "1.0"
def extract_author(doc):
"""Try to find existing author from document properties or first tables."""
# Check document properties
core = doc.core_properties
if core.author:
return core.author
return "JvG Consultancy"
def extract_date(doc):
"""Try to find date in existing header table or use default."""
core = doc.core_properties
if core.created:
return core.created.strftime("%Y-%m-%d")
return "2026-04-28"
def has_documentheader(doc):
"""Check if documentheader table already exists."""
for t in doc.tables:
text = ""
for row in t.rows:
for cell in row.cells:
text += cell.text.lower()
if "project" in text and "versie" in text:
return True
return False
def add_documentheader(doc, doc_type, version, author, date):
"""Insert documentheader table at the beginning of the document."""
# Find insertion point - after any existing title, before main content
# We'll insert after the first paragraph or at position 1
body = doc.element.body
# Create header table
table = doc.add_table(rows=6, cols=2)
table.style = 'Table Grid'
table.alignment = WD_TABLE_ALIGNMENT.LEFT
data = [
("Project", "2026-PM-VBS-Element1"),
("Type", doc_type),
("Auteur", author),
("Versie", version),
("Datum", date),
("Status", "Final"),
]
for i, (label, value) in enumerate(data):
cell_l = table.cell(i, 0)
cell_r = table.cell(i, 1)
cell_l.text = label
cell_r.text = value
# Style
for cell in [cell_l, cell_r]:
for p in cell.paragraphs:
p.style = doc.styles['Normal']
for run in p.runs:
run.font.name = 'Calibri'
run.font.size = Pt(10)
# Bold label
for run in cell_l.paragraphs[0].runs:
run.bold = True
# Background for label column
shading = parse_xml(f'')
cell_l._tc.get_or_add_tcPr().append(shading)
for run in cell_l.paragraphs[0].runs:
run.font.color.rgb = RGBColor(0xFF, 0xFF, 0xFF)
# Move table to just after the first element (title)
# Find first paragraph in body and insert table after it
first_p = body.find(qn('w:p'))
if first_p is not None:
tbl_elem = table._tbl
body.remove(tbl_elem)
first_p.addnext(tbl_elem)
# Add a blank paragraph after the table
spacer = doc.add_paragraph()
spacer_elem = spacer._p
body.remove(spacer_elem)
table._tbl.addnext(spacer_elem)
def fix_footers(doc):
"""Add footer to all sections."""
for section in doc.sections:
footer = section.footer
footer.is_linked_to_previous = False
# Clear existing footer content
for p in footer.paragraphs:
p.clear()
if not footer.paragraphs:
p = footer.add_paragraph()
else:
p = footer.paragraphs[0]
p.alignment = WD_ALIGN_PARAGRAPH.CENTER
run = p.add_run(FOOTER_TEXT)
run.font.name = 'Calibri'
run.font.size = Pt(10)
run.font.color.rgb = RGBColor(0xFF, 0xFF, 0xFF)
# Add dark background to footer paragraph
pPr = p._p.get_or_add_pPr()
shading = parse_xml(f'')
pPr.append(shading)
def process_file(src_name, dst_name, doc_type):
src_path = os.path.join(SRC, src_name)
dst_path = os.path.join(DST, dst_name)
version = get_version(dst_name)
print(f"Processing: {src_name} → {dst_name}")
doc = Document(src_path)
author = extract_author(doc)
date = extract_date(doc)
# Fix 1: Footer
fix_footers(doc)
# Fix 2: Documentheader (only if not present)
if not has_documentheader(doc):
add_documentheader(doc, doc_type, version, author, date)
else:
print(f" → Documentheader already present, skipping")
doc.save(dst_path)
print(f" ✓ Saved: {dst_path}")
if __name__ == "__main__":
os.makedirs(DST, exist_ok=True)
for src_name, dst_name, doc_type in DOCS:
process_file(src_name, dst_name, doc_type)
print("\n✅ Batch fix complete: all 12 documents processed.")