#!/usr/bin/env python3
"""Fix PBZO v1.0 → v1.1: Professional organogram + polished tables."""
import shutil, os, tempfile
from pathlib import Path
from docx import Document
from docx.shared import Inches, Pt, 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, OxmlElement
from playwright.sync_api import sync_playwright
BASE = Path("/root/projects/jg/2026-PM-VBS-Element1")
SRC = BASE / "deliverables" / "PM_VBS01_01_PBZO_Beleidsdocument_v1.0.docx"
DST = BASE / "deliverables" / "PM_VBS01_01_PBZO_Beleidsdocument_v1.1.docx"
ARCHIVE = BASE / "archive" / "PM_VBS01_01_PBZO_Beleidsdocument_v1.0.docx"
# Step 0: Archive
ARCHIVE.parent.mkdir(parents=True, exist_ok=True)
shutil.copy2(SRC, ARCHIVE)
# Step 1: Generate organogram image
HTML = """
Organisatorische Structuur — Phoenix Metals B.V.
Managing Director
Stijn van Zelst
Operations Manager
HSE Manager
Maintenance Manager
Field Operators
HSE Supervisor
E&I Technicians
Office Staff / Administration
Administratie & Ondersteuning
Directie
Management
Supervisie
Uitvoering
"""
img_path = "/tmp/_pbzo_organogram.png"
with tempfile.NamedTemporaryFile(suffix='.html', mode='w', delete=False) as f:
f.write(HTML)
html_path = f.name
with sync_playwright() as p:
br = p.chromium.launch()
pg = br.new_page(viewport={"width": 820, "height": 600})
pg.goto(f"file://{html_path}")
pg.wait_for_timeout(500)
pg.query_selector("body").screenshot(path=img_path)
br.close()
os.unlink(html_path)
print(f"✓ Organogram image generated")
# Step 2: Work with DOCX - use HARD-CODED indices from Heading analysis
# Heading paragraphs (confirmed from original document):
# 116: [Heading 1] 5. Organisatorische structuur
# 117: [Heading 2] 5.1 Veiligheidsorganigram
# 129: [Heading 2] 5.2 Rollen en verantwoordelijkheden
# 166: [Heading 2] Bijlage A: Organigram
# 193: [Heading 2] Bijlage B: Overzicht VBS-elementen en documenten
doc = Document(str(SRC))
body = doc.element.body
# 2a: Remove ASCII art between §5.1 intro (118) and §5.2 heading (129)
# Keep paragraph 118 (intro text), remove 119-128, keep 129 (§5.2 heading)
s52_el = doc.paragraphs[129]._element # Heading 5.2
intro_el = doc.paragraphs[118]._element # "De veiligheidsorganisatiestructuur..."
to_remove = []
el = intro_el.getnext()
while el is not None and el != s52_el:
to_remove.append(el)
el = el.getnext()
for el in to_remove:
body.remove(el)
print(f"✓ Removed {len(to_remove)} elements from §5.1 (ASCII art)")
# Insert image after intro
img_para = doc.add_paragraph()
img_para.alignment = WD_ALIGN_PARAGRAPH.CENTER
run = img_para.add_run()
run.add_picture(img_path, width=Inches(5.5))
img_el = img_para._element
body.remove(img_el)
intro_el.addnext(img_el)
print("✓ Inserted organogram image in §5.1")
# 2b: Remove ASCII art in Bijlage A (between heading 166 and heading 193)
bijA_el = doc.paragraphs[166]._element # Heading "Bijlage A"
bijB_el = doc.paragraphs[193]._element # Heading "Bijlage B"
to_remove2 = []
el = bijA_el.getnext()
while el is not None and el != bijB_el:
to_remove2.append(el)
el = el.getnext()
for el in to_remove2:
body.remove(el)
print(f"✓ Removed {len(to_remove2)} elements from Bijlage A (ASCII art)")
# Insert image after Bijlage A heading
img_para2 = doc.add_paragraph()
img_para2.alignment = WD_ALIGN_PARAGRAPH.CENTER
run2 = img_para2.add_run()
run2.add_picture(img_path, width=Inches(5.5))
img_el2 = img_para2._element
body.remove(img_el2)
bijA_el.addnext(img_el2)
print("✓ Inserted organogram image in Bijlage A")
# Step 3: Polish tables
for table in doc.tables:
table.alignment = WD_TABLE_ALIGNMENT.CENTER
for j, row in enumerate(table.rows):
for cell in row.cells:
for para in cell.paragraphs:
for run in para.runs:
run.font.name = 'Calibri'
if run.font.size is None:
run.font.size = Pt(10)
if j == 0:
bg = "003366"
for para in cell.paragraphs:
for run in para.runs:
run.font.color.rgb = RGBColor(255, 255, 255)
run.font.bold = True
elif j % 2 == 1:
bg = "F3F4F6"
else:
bg = "FFFFFF"
tc_pr = cell._element.get_or_add_tcPr()
for old in tc_pr.findall(qn('w:shd')):
tc_pr.remove(old)
tc_pr.append(parse_xml(f''))
for old in tc_pr.findall(qn('w:tcMar')):
tc_pr.remove(old)
tc_mar = OxmlElement('w:tcMar')
for side in ['top', 'left', 'bottom', 'right']:
n = OxmlElement(f'w:{side}')
n.set(qn('w:w'), '60')
n.set(qn('w:type'), 'dxa')
tc_mar.append(n)
tc_pr.append(tc_mar)
# Step 4: Save
doc.save(str(DST))
os.unlink(img_path)
print(f"\n✅ Saved → {DST}")
print(f"✅ Archive → {ARCHIVE}")