"""Report generation for HTML and PDF output."""
import subprocess
from pathlib import Path
from typing import Optional
from jinja2 import Environment, FileSystemLoader
from .models import Assessment, MATRIX_LABELS, EMPFEHLUNG_CONFIG
from .bundeslaender import BUNDESLAENDER
# ECOnGOOD Colors
COLORS = {
"darkgray": "#5a5a5a",
"green": "#889e33",
"blue": "#009da5",
"lightgray": "#bfbfbf",
"orange": "#F7941D",
"red": "#d00000",
}
def get_score_color(score: float) -> str:
"""Get color for a score value."""
if score >= 7:
return COLORS["blue"]
if score >= 4:
return COLORS["green"]
if score >= 2:
return "#FFC20E"
if score >= 1:
return COLORS["orange"]
return COLORS["red"]
def get_rating_symbol(rating: int) -> str:
"""Convert numeric rating to symbol."""
if rating >= 2:
return "++"
if rating == 1:
return "+"
if rating == 0:
return "○"
if rating == -1:
return "−"
return "−−"
def format_redline_html(text: str) -> str:
"""Convert redline markup to HTML."""
import re
# **text** → green bold (inserted)
text = re.sub(r'\*\*([^*]+)\*\*', r'\1', text)
# ~~text~~ → red strikethrough (deleted)
text = re.sub(r'~~([^~]+)~~', r'\1', text)
return text
def build_matrix_html(assessment: Assessment) -> str:
"""Build HTML matrix table."""
rating_map = {e.field: e for e in assessment.gwoe_matrix}
rows = ["A", "B", "C", "D", "E"]
row_labels = {
"A": "Lieferant:innen",
"B": "Finanzen",
"C": "Führung/Verwaltung",
"D": "Bürger:innen",
"E": "Gesellschaft/Natur",
}
html = ['
']
html.append('')
html.append(' | ')
for col in range(1, 6):
html.append(f'{col} | ')
html.append('
')
html.append('')
for row in rows:
html.append(f'| {row}: {row_labels[row]} | ')
for col in range(1, 6):
field = f"{row}{col}"
entry = rating_map.get(field)
if entry:
symbol = get_rating_symbol(entry.rating)
css_class = "positive" if entry.rating > 0 else ("negative" if entry.rating < 0 else "neutral")
html.append(f'{symbol} | ')
else:
html.append(' | ')
html.append('
')
html.append('
')
return '\n'.join(html)
async def generate_html_report(
assessment: Assessment,
output_path: Path,
bundesland: Optional[str] = None,
) -> None:
"""Generate HTML report.
``bundesland`` is the optional state code (e.g. ``"NRW"``, ``"LSA"``).
When set and known in ``BUNDESLAENDER``, the resulting report carries
the parlament name in its header so the source parliament is always
visible — important since assessments from multiple bundesländer share
the same Drucksachen-ID space.
"""
empf_config = EMPFEHLUNG_CONFIG.get(assessment.empfehlung.value, {})
parlament_name = ""
if bundesland and bundesland in BUNDESLAENDER:
parlament_name = BUNDESLAENDER[bundesland].parlament_name
html = f"""
GWÖ-Antragsprüfung: {assessment.title}
Drucksache: {assessment.drucksache} |
Datum: {assessment.datum} |
Fraktion(en): {', '.join(assessment.fraktionen)} |
GWÖ-Score: {assessment.gwoe_score}/10
{empf_config.get('symbol', '[?]')}
Empfehlung: {assessment.empfehlung.value}
Der Antrag im Überblick
{assessment.antrag_zusammenfassung or 'Keine Zusammenfassung verfügbar.'}
{('' + ''.join(f'- {k}
' for k in assessment.antrag_kernpunkte) + '
') if assessment.antrag_kernpunkte else ''}
GWÖ-Treue
Score: {assessment.gwoe_score}/10
Begründung: {assessment.gwoe_begruendung}
Schwerpunkte: {', '.join(assessment.gwoe_schwerpunkt)}
Matrix-Zuordnung (Matrix 2.0 für Gemeinden)
{build_matrix_html(assessment)}
Legende: ++ stark fördernd, + fördernd, ○ neutral, − widersprechend, −− stark widersprechend
Berührte Themenfelder
{''.join(f'- {e.field}: {e.aspect} [{get_rating_symbol(e.rating)}]
' for e in assessment.gwoe_matrix)}
Programmtreue
{''.join(f'''
{s.fraktion} {' (Antragsteller)' if s.ist_antragsteller else ''}{' (Regierung)' if s.ist_regierung else ''}
Wahlprogramm: {s.wahlprogramm.score}/10 — {s.wahlprogramm.begruendung}
Parteiprogramm: {s.parteiprogramm.score}/10 — {s.parteiprogramm.begruendung}
''' for s in assessment.wahlprogramm_scores)}
Verbesserungsvorschläge
{''.join(f'''
Original:
{v.original}
Vorschlag:
{format_redline_html(v.vorschlag)}
{v.begruendung}
''' for v in assessment.verbesserungen) or 'Keine Verbesserungsvorschläge.
'}
Zusammenfassung
Stärken
{''.join(f'- {s}
' for s in assessment.staerken) or '- (keine)
'}
Schwächen
{''.join(f'- {s}
' for s in assessment.schwaechen) or '- (keine)
'}
"""
output_path.write_text(html)
async def generate_pdf_report(
assessment: Assessment,
output_path: Path,
bundesland: Optional[str] = None,
) -> None:
"""Generate PDF report using WeasyPrint, then append the original Antrag.
Two-step pipeline:
1. Render the GWÖ-Report HTML and convert to PDF via WeasyPrint
(existing behaviour).
2. If ``assessment.link`` is a fetchable PDF URL, download it via
``httpx`` and append it after a separator page so the resulting
single file contains both the analysis and its source document
(issue #9).
The append step is best-effort: a missing/empty link is silently
skipped, network errors and parse errors fall back to a single
placeholder page so the report itself is always delivered.
``bundesland`` is forwarded to ``generate_html_report`` so the source
parlament name appears in the report header.
"""
# Step 1 — render the report itself
html_path = output_path.with_suffix('.tmp.html')
await generate_html_report(assessment, html_path, bundesland=bundesland)
try:
from weasyprint import HTML
HTML(filename=str(html_path)).write_pdf(str(output_path))
finally:
html_path.unlink(missing_ok=True)
# Step 2 — append the original Antrag (best-effort)
await _append_original_antrag(assessment, output_path)
async def _append_original_antrag(
assessment: Assessment,
report_path: Path,
) -> None:
"""Try to download the original Antrag PDF and append it to ``report_path``.
Failure modes (download error, non-PDF content, parse error) are
handled gracefully: a single placeholder page is appended noting the
issue, so the user always sees that an attempt was made.
"""
import fitz # PyMuPDF
import httpx
link = (assessment.link or "").strip()
if not link or not link.startswith(("http://", "https://")):
# Manual upload / pasted text — nothing to append.
return
download_error: Optional[str] = None
pdf_bytes: Optional[bytes] = None
try:
async with httpx.AsyncClient(
timeout=30,
follow_redirects=True,
headers={"User-Agent": "Mozilla/5.0 GWOE-Antragspruefer"},
) as client:
resp = await client.get(link)
if resp.status_code != 200:
download_error = f"HTTP {resp.status_code}"
elif not resp.content[:5].startswith(b"%PDF-"):
download_error = f"kein PDF (Content-Type: {resp.headers.get('content-type', 'unknown')})"
else:
pdf_bytes = resp.content
except Exception as e:
download_error = f"Download-Fehler: {e}"
try:
report_doc = fitz.open(report_path)
try:
# Always insert a divider page so the user sees what comes next
_insert_divider_page(report_doc, assessment, download_error)
if pdf_bytes is not None:
try:
src_doc = fitz.open(stream=pdf_bytes, filetype="pdf")
try:
report_doc.insert_pdf(src_doc)
finally:
src_doc.close()
except Exception as e:
print(f"_append_original_antrag: PDF-Parse-Fehler für {assessment.drucksache}: {e}")
# PyMuPDF refuses to overwrite the source file in non-incremental
# mode — write to a sibling temp file and atomically replace.
tmp_path = report_path.with_suffix(report_path.suffix + ".tmp")
report_doc.save(
str(tmp_path),
deflate=True,
garbage=3,
)
finally:
report_doc.close()
tmp_path.replace(report_path)
except Exception as e:
# Hard failure — leave the original report file untouched.
print(f"_append_original_antrag: Konnte Report nicht erweitern für {assessment.drucksache}: {e}")
def _insert_divider_page(
report_doc, # fitz.Document
assessment: Assessment,
download_error: Optional[str],
) -> None:
"""Append a single A4 separator page that introduces the original Antrag.
Uses PyMuPDF's text drawing API directly so we don't need a second
WeasyPrint round-trip just for one page.
"""
page = report_doc.new_page(width=595, height=842) # A4
margin_left = 60
y = 200
# Title
page.insert_text(
(margin_left, y),
"Original-Antrag",
fontsize=24,
fontname="helv",
color=(0 / 255, 157 / 255, 165 / 255), # var(--color-blue)
)
y += 38
# Drucksache
page.insert_text(
(margin_left, y),
f"Drucksache {assessment.drucksache}",
fontsize=14,
fontname="helv",
color=(0.35, 0.35, 0.35),
)
y += 22
# Title (truncated to ~75 chars to fit one line)
title = assessment.title or ""
if len(title) > 75:
title = title[:72] + "…"
page.insert_text(
(margin_left, y),
title,
fontsize=11,
fontname="helv",
color=(0.35, 0.35, 0.35),
)
y += 40
if download_error:
page.insert_text(
(margin_left, y),
"⚠ Original-PDF konnte nicht angehängt werden.",
fontsize=11,
fontname="helv",
color=(0.82, 0.0, 0.0),
)
y += 18
page.insert_text(
(margin_left, y),
f"Grund: {download_error}",
fontsize=10,
fontname="helv",
color=(0.5, 0.5, 0.5),
)
y += 18
if assessment.link:
page.insert_text(
(margin_left, y),
f"Quelle: {assessment.link[:90]}",
fontsize=9,
fontname="helv",
color=(0.5, 0.5, 0.5),
)
else:
page.insert_text(
(margin_left, y),
"Die folgenden Seiten enthalten den unveränderten Originalantrag.",
fontsize=11,
fontname="helv",
color=(0.35, 0.35, 0.35),
)