Spaces:
Running
Running
File size: 32,513 Bytes
ce8f04a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 | import os
import markdown
import datetime
from bs4 import BeautifulSoup
def export_to_docx(
content: str,
output_path: str,
template: str = "standard",
project_title: str = "Wniosek o Dofinansowanie",
company_name: str = "Brak nazwy",
version: str = "1.0",
date_str: str = "",
extra_context: dict = None,
):
"""
Eksportuje wygenerowany przez Wizarda wniosek do formatu Microsoft Word (DOCX).
Wczytuje gotowy szablon docx z wymaganymi stalami i spisem treści.
Integruje się z `docxtpl` by umożliwić elastyczne wstrzykiwanie zmiennych (np {{ beneficjent.krs }}).
"""
if extra_context is None:
extra_context = {}
try:
from docxtpl import DocxTemplate
template_name = (
template if template in ["standard", "official", "modern"] else "standard"
)
template_path = os.path.join(
os.path.dirname(__file__),
"..",
"templates",
f"template_{template_name}.docx",
)
if not os.path.exists(template_path):
print(f"Brak pliku {template_path}, upewnij się, że wygenerowano szablony!")
return False
tpl = DocxTemplate(template_path)
# Puste wartości dla formatowania markdown (usuwamy duplikujące title jeśli zaczyna się od H1)
if content.startswith("# "):
content = "\n".join(content.split("\n")[1:])
# Przygotowanie pełnego kontekstu dla DocxTemplate (Jinja2 tags)
# Zostawiamy 'tresc_wniosku' puste, bo zastąpimy ten paragraf natywnym kodem python-docx
render_context = {
"tytul_projektu": project_title,
"nazwa_firmy": company_name,
"data_generowania": date_str,
"wersja": version,
"tresc_wniosku": "",
}
render_context.update(extra_context)
tpl.render(render_context)
# === Pełna integracja Świadectwa Zgodności w eksporcie (Cycle 4) ===
if extra_context and extra_context.get("include_grounding_certificate"):
append_grounding_certificate_to_docx(tpl._document, {
"title": project_title,
"company_name": company_name,
"version_hash": extra_context.get("version_hash"),
"precise_regulation_url": extra_context.get("precise_regulation_url"),
"regulation_link_quality": extra_context.get("regulation_link_quality"),
"snapshot_data": extra_context.get("snapshot_data"),
})
tpl.save(output_path)
# 2. Otwieramy zapisany plik za pomocą natywnego python-docx
import docx
doc = docx.Document(output_path)
# Usuwamy ostatni paragraf (który zawierał wyczyszczoną zmienną 'tresc_wniosku')
if len(doc.paragraphs) > 0 and doc.paragraphs[-1].text.strip() == "":
p = doc.paragraphs[-1]
p._element.getparent().remove(p._element)
# Konwersja MD do prostego HTML, a potem interpretacja BeautifulSoup
html = markdown.markdown(content)
soup = BeautifulSoup(html, "html.parser")
for element in soup:
if element.name in ["h1", "h2", "h3", "h4", "h5", "h6"]:
level = int(element.name[1])
try:
doc.add_paragraph(element.text, style=f"Heading {level}")
except KeyError:
doc.add_heading(element.text, level=level)
elif element.name == "p":
# Złożona obsługa bold/italic
p = doc.add_paragraph()
if template == "official":
p.paragraph_format.alignment = 3 # Justify
for child in element.children:
if child.name is None:
p.add_run(child.string)
elif child.name in ["strong", "b"]:
p.add_run(child.text).bold = True
elif child.name in ["em", "i"]:
p.add_run(child.text).italic = True
else:
p.add_run(child.text)
elif element.name in ["ul", "ol"]:
for li in element.find_all("li"):
style_name = (
"List Bullet" if element.name == "ul" else "List Number"
)
try:
p = doc.add_paragraph(style=style_name)
except KeyError:
p = doc.add_paragraph(style="Normal")
p.add_run("• ")
for child in li.children:
if child.name is None:
p.add_run(child.string)
elif child.name in ["strong", "b"]:
p.add_run(child.text).bold = True
elif child.name in ["em", "i"]:
p.add_run(child.text).italic = True
else:
p.add_run(child.text)
elif element.name == "table":
# Ulepszona obsługa tabel dla DOCX
rows = element.find_all("tr")
if rows:
cols = max(len(row.find_all(["th", "td"])) for row in rows)
table = doc.add_table(rows=0, cols=cols)
try:
table.style = "Light Shading Accent 1"
except KeyError:
table.style = "Table Grid"
for idx_row, tr in enumerate(rows):
row = table.add_row()
cells = tr.find_all(["th", "td"])
for idx, cell in enumerate(cells):
if idx < cols:
p = row.cells[idx].paragraphs[0]
p.text = ""
for child in cell.children:
if child.name is None:
p.add_run(child.string.strip() if child.string else "")
elif child.name in ["strong", "b"]:
p.add_run(child.text.strip()).bold = True
elif child.name in ["em", "i"]:
p.add_run(child.text.strip()).italic = True
else:
p.add_run(child.text.strip())
# Zawsze pogrubiamy nagłówki (<th> lub pierwszy wiersz)
if cell.name == "th" or idx_row == 0:
for run in p.runs:
run.bold = True
doc.save(output_path)
return True
except Exception:
import traceback
print(f"Błąd eksportu do DOCX: {traceback.format_exc()}")
return False
def append_grounding_certificate_to_docx(doc, project_data: dict):
"""Dodaje stronę Świadectwa Zgodności na końcu dokumentu DOCX."""
from docx.shared import Pt, RGBColor
from docx.enum.text import WD_ALIGN_PARAGRAPH
doc.add_page_break()
# Nagłówek świadectwa
p = doc.add_paragraph()
run = p.add_run("ŚWIADECTWO ZGODNOŚCI WERSJI / REGULATION GROUNDING CERTIFICATE")
run.bold = True
run.font.size = Pt(14)
run.font.color.rgb = RGBColor(26, 54, 93)
p.alignment = WD_ALIGN_PARAGRAPH.CENTER
p2 = doc.add_paragraph("GrantForge AI — Najwyższy poziom ugruntowania w regulaminach i prawie UE")
p2.alignment = WD_ALIGN_PARAGRAPH.CENTER
doc.add_paragraph()
# Kluczowe dane
cert_info = [
("Projekt", project_data.get("title", "")),
("Beneficjent", project_data.get("company_name", "")),
("Data wygenerowania", datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M UTC")),
("Version Hash", project_data.get("version_hash", "N/A")),
("Precise Regulation URL", project_data.get("precise_regulation_url", "N/A")),
("Regulation Link Quality", project_data.get("regulation_link_quality", "N/A")),
]
for label, value in cert_info:
p = doc.add_paragraph()
run = p.add_run(f"{label}: ")
run.bold = True
p.add_run(str(value)[:120])
# Snapshot summary jeśli dostępny
if project_data.get("snapshot_data"):
doc.add_paragraph()
p = doc.add_paragraph()
p.add_run("SNAPSHOT REGULAMINU (źródło prawdy)").bold = True
for k, v in project_data["snapshot_data"].items():
if k in ["key_rules", "exclusions"]:
continue
doc.add_paragraph(f" {k}: {v}")
doc.add_paragraph()
p = doc.add_paragraph("Dokument ten potwierdza, że wszystkie wygenerowane treści opierają się na konkretnej, wersjonowanej wersji regulaminu oraz aktualnych aktach prawnych UE.")
p.alignment = WD_ALIGN_PARAGRAPH.JUSTIFY
p = doc.add_paragraph("https://grantforge.ai | Regulation Engine jako źródło prawdy")
p.alignment = WD_ALIGN_PARAGRAPH.CENTER
def export_full_application_with_certificate(
output_path: str,
project_title: str,
company_name: str,
main_content: str,
certificate_data: dict,
) -> bool:
"""Eksportuje pełny wniosek + stronę Świadectwa Zgodności na końcu (PDF). Używane w cyklu finałowym."""
try:
from reportlab.lib.pagesizes import A4
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
from reportlab.lib.styles import getSampleStyleSheet
doc = SimpleDocTemplate(output_path, pagesize=A4)
styles = getSampleStyleSheet()
story = []
# Główna treść wniosku (uproszczona)
for line in (main_content or "").split("\n")[:80]:
if line.strip():
story.append(Paragraph(line[:200], styles["Normal"]))
story.append(PageBreak())
# Świadectwo
cert = certificate_data or {}
story.append(Paragraph("ŚWIADECTWO ZGODNOŚCI WERSJI / REGULATION GROUNDING CERTIFICATE", styles["Heading1"]))
story.append(Spacer(1, 10))
story.append(Paragraph(f"Projekt: {project_title}", styles["Normal"]))
story.append(Paragraph(f"Beneficjent: {company_name}", styles["Normal"]))
story.append(Paragraph(f"Version Hash: {cert.get('version_hash', 'N/A')}", styles["Normal"]))
story.append(Paragraph(f"Precise Regulation URL: {cert.get('precise_regulation_url', 'N/A')}", styles["Normal"]))
story.append(Paragraph(f"Link Quality: {cert.get('regulation_link_quality', 'N/A')}", styles["Normal"]))
doc.build(story)
return True
except Exception as e:
print(f"Błąd eksportu PDF z certificate: {e}")
return False
def export_grounding_certificate_pdf(
output_path: str,
project_title: str,
company_name: str,
snapshot_data: dict,
eurlex_links: list = None,
pkd_list: list = None,
msp_status: str = "",
engine_checks: dict = None,
version_hash: str = "",
v5_certificate: dict = None, # v5.0 extended: citation_score, trap_risk, trust_score etc.
) -> bool:
"""
Generuje publiczne, profesjonalne Świadectwo Zgodności (Regulation Grounding Certificate) w formacie PDF.
Zawiera wszystkie metadane snapshotu, hash, linki EUR-Lex, PKD, status MSP, wyniki silnika.
To jest kluczowy element dla najwyższej wiarygodności — dokument można załączyć do wniosku lub pokazać instytucji.
"""
try:
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import cm
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle, HRFlowable
from reportlab.lib import colors
from reportlab.lib.enums import TA_CENTER, TA_LEFT, TA_JUSTIFY
import datetime
doc = SimpleDocTemplate(
output_path,
pagesize=A4,
rightMargin=1.5*cm,
leftMargin=1.5*cm,
topMargin=1.5*cm,
bottomMargin=1.5*cm
)
styles = getSampleStyleSheet()
title_style = ParagraphStyle(
'TitlePL',
parent=styles['Heading1'],
fontSize=16,
alignment=TA_CENTER,
spaceAfter=12,
textColor=colors.HexColor('#1a365d')
)
subtitle_style = ParagraphStyle(
'SubtitlePL',
parent=styles['Normal'],
fontSize=10,
alignment=TA_CENTER,
textColor=colors.HexColor('#2d3748')
)
body_style = ParagraphStyle(
'BodyPL',
parent=styles['Normal'],
fontSize=9,
alignment=TA_JUSTIFY,
spaceAfter=6
)
small_style = ParagraphStyle(
'SmallPL',
parent=styles['Normal'],
fontSize=8,
textColor=colors.gray
)
story = []
# Header
story.append(Paragraph("ŚWIADECTWO ZGODNOŚCI WERSJI / REGULATION GROUNDING CERTIFICATE", title_style))
story.append(Paragraph("GrantForge AI — Najwyższy poziom ugruntowania w aktualnych regulaminach i prawie UE", subtitle_style))
story.append(Spacer(1, 0.4*cm))
story.append(HRFlowable(width="100%", thickness=2, color=colors.HexColor('#1a365d')))
story.append(Spacer(1, 0.3*cm))
# Basic info
now = datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M UTC")
info_data = [
["Projekt:", project_title],
["Beneficjent:", company_name],
["Data wygenerowania świadectwa:", now],
["Wersja silnika:", "Regulation Engine v3 + Live EUR-Lex"],
]
info_table = Table(info_data, colWidths=[5*cm, 11*cm])
info_table.setStyle(TableStyle([
('FONTNAME', (0, 0), (0, -1), 'Helvetica-Bold'),
('FONTSIZE', (0, 0), (-1, -1), 9),
('VALIGN', (0, 0), (-1, -1), 'TOP'),
('BOTTOMPADDING', (0, 0), (-1, -1), 4),
]))
story.append(info_table)
story.append(Spacer(1, 0.3*cm))
# Snapshot section
story.append(Paragraph("<b>ŹRÓDŁO PRAWNE (SNAPSHOT REGULAMINU)</b>", body_style))
if snapshot_data:
snap_text = f"""
<b>Program:</b> {snapshot_data.get('program', 'N/A')}<br/>
<b>Snapshot ID:</b> {snapshot_data.get('id', 'N/A')}<br/>
<b>Version Hash (SHA256 skrót):</b> {snapshot_data.get('version_hash') or version_hash or 'N/A'}<br/>
<b>Data pobrania:</b> {snapshot_data.get('fetched_at', 'N/A')}<br/>
<b>Źródło:</b> {snapshot_data.get('source_url', 'N/A')}<br/>
<b>Wersja dokumentu:</b> {snapshot_data.get('document_version', 'N/A')}<br/>
<b>Obowiązuje od:</b> {snapshot_data.get('effective_date', 'N/A')}<br/>
<b>Instytucja:</b> {snapshot_data.get('source_institution', 'N/A')}<br/>
<b>Liczba kluczowych reguł:</b> {len(snapshot_data.get('key_rules', []))}<br/>
<b>Liczba wykluczeń:</b> {len(snapshot_data.get('exclusions', []))}
"""
story.append(Paragraph(snap_text, body_style))
else:
story.append(Paragraph("Brak snapshotu — dokument wygenerowany bez pełnego ugruntowania.", body_style))
story.append(Spacer(1, 0.3*cm))
# v5.0 Extended Grounding Certificate fields (citation/trap/trust)
if v5_certificate:
story.append(Paragraph("<b>v5.0 MASTER ORCHESTRATOR GROUNDING CERTIFICATE (EXPORTABLE)</b>", body_style))
v5_text = f"""
<b>Snapshot ID:</b> {v5_certificate.get('snapshot_id', 'N/A')}<br/>
<b>Version Hash:</b> {v5_certificate.get('version_hash', version_hash or 'N/A')}<br/>
<b>Effective Date:</b> {v5_certificate.get('effective_date', 'N/A')}<br/>
<b>Citation Score:</b> {v5_certificate.get('citation_score', 0.0)}<br/>
<b>Trap Risk (Kruczkowski):</b> {v5_certificate.get('trap_risk', 'unknown')}<br/>
<b>Trust Score:</b> {v5_certificate.get('trust_score', 50)}/100<br/>
<b>Data Quality Avg:</b> {v5_certificate.get('data_quality_avg', 0.0)}<br/>
<b>Timestamp:</b> {v5_certificate.get('timestamp', '')}<br/>
<b>Query Intent:</b> {v5_certificate.get('query_intent', '')}<br/>
<b>Synthesis:</b> {str(v5_certificate.get('synthesis_summary', ''))[:180]}
"""
story.append(Paragraph(v5_text, body_style))
story.append(Spacer(1, 0.2*cm))
# EUR-Lex
story.append(Paragraph("<b>LIVE LEGAL CONTROL — EUR-LEX (ŹRÓDŁO PRAWY UE)</b>", body_style))
if eurlex_links:
for link in eurlex_links[:3]:
story.append(Paragraph(f"• {link.get('title', '')} — {link.get('url', '')}", small_style))
else:
story.append(Paragraph("Brak bezpośrednich linków EUR-Lex w tym świadectwie.", small_style))
story.append(Spacer(1, 0.3*cm))
# PKD + MSP
story.append(Paragraph("<b>UZIEMIENIE W DANYCH FIRMY (GUS + MSP)</b>", body_style))
if pkd_list:
story.append(Paragraph(f"Kody PKD wnioskodawcy (GUS): {', '.join(pkd_list[:5])}", body_style))
story.append(Paragraph(f"Status MŚP: {msp_status or 'Zweryfikowany przez GraphRAG'}", body_style))
story.append(Spacer(1, 0.3*cm))
# Engine checks
if engine_checks:
story.append(Paragraph("<b>WYNIKI AKTYWNEJ WERYFIKACJI (REGULATION ENGINE)</b>", body_style))
story.append(Paragraph(str(engine_checks), body_style))
story.append(Spacer(1, 0.5*cm))
story.append(HRFlowable(width="100%", thickness=1, color=colors.gray))
story.append(Paragraph(
"To świadectwo potwierdza, że wszystkie wygenerowane treści opierają się na konkretnej, wersjonowanej wersji regulaminu + aktualnych aktach prawnych UE (EUR-Lex). "
"Hash wersji pozwala na późniejszą weryfikację. Dokument jest integralną częścią wniosku i może być przedstawiony instytucji finansującej.",
small_style
))
story.append(Spacer(1, 0.3*cm))
story.append(Paragraph("GrantForge AI — Regulation Engine jako źródło prawdy | https://grantforge.ai", subtitle_style))
doc.build(story)
return True
except ImportError:
print("Brak reportlab — zainstaluj: pip install reportlab")
# Fallback: zapisz jako tekst
with open(output_path.replace('.pdf', '.txt'), 'w', encoding='utf-8') as f:
f.write(f"ŚWIADECTWO ZGODNOŚCI — {project_title}\nHash: {version_hash}\nSnapshot: {snapshot_data}\n")
return False
except Exception as e:
print(f"Błąd generowania Świadectwa PDF: {e}")
return False
def get_pdf_css(template: str) -> str:
if template == "official":
return """
@page { size: A4; margin: 2.5cm; }
body { font-family: "DejaVu Sans", "Arial", serif; font-size: 11pt; line-height: 1.5; text-align: justify; color: #000; }
h1, h2, h3 { color: #000; page-break-after: avoid; font-family: "DejaVu Sans", "Arial", serif; }
h1 { border-bottom: 2px solid #000; padding-bottom: 5px; text-transform: uppercase; text-align: center; font-size: 16pt; margin-top: 2em; }
h2 { font-size: 14pt; margin-top: 1.5em; }
h3 { font-size: 12pt; margin-top: 1.2em; font-style: italic; }
table { width: 100%; border-collapse: collapse; margin: 1em 0; page-break-inside: avoid; }
th, td { border: 1px solid #000; padding: 8px; text-align: left; }
p { margin-bottom: 1em; orphans: 3; widows: 3; }
a { color: #000; text-decoration: none; }
.toc { page-break-after: always; }
.toc ul { list-style-type: none; padding-left: 1.5em; }
.toc > ul { padding-left: 0; }
.toc a { text-decoration: none; color: #000; }
"""
elif template == "modern":
return """
@page { size: A4; margin: 2.5cm; }
body { font-family: "DejaVu Sans", "Arial", sans-serif; font-size: 11pt; line-height: 1.6; color: #1e293b; background: #fff; }
h1, h2, h3 { page-break-after: avoid; color: #0f172a; font-family: "DejaVu Sans", "Arial", sans-serif; }
h1 { border-bottom: 2px solid #3b82f6; padding-bottom: 0.5em; font-size: 24pt; margin-top: 1em; }
h2 { border-bottom: 1px solid #e2e8f0; padding-bottom: 0.3em; font-size: 18pt; margin-top: 1.5em; color: #2563eb; }
h3 { font-size: 14pt; margin-top: 1.2em; color: #334155; }
p { margin-bottom: 1em; text-align: justify; orphans: 3; widows: 3; }
table { width: 100%; border-collapse: collapse; margin: 1.5em 0; background: #f8fafc; font-size: 10pt; page-break-inside: avoid; }
th, td { border: 1px solid #e2e8f0; padding: 10px 14px; text-align: left; }
th { background-color: #e2e8f0; color: #1e293b; font-weight: bold; border-bottom: 2px solid #cbd5e1; }
tr:nth-child(even) { background-color: #f1f5f9; }
ul, ol { margin-bottom: 1em; padding-left: 2em; }
li { margin-bottom: 0.5em; }
.toc { page-break-after: always; padding: 2em; background: #f8fafc; border-radius: 8px; }
.toc ul { list-style-type: none; padding-left: 1.5em; }
.toc > ul { padding-left: 0; }
.toc a { text-decoration: none; color: #4f46e5; border-bottom: 1px dotted #cbd5e1; display: block; padding-bottom: 5px; margin-bottom: 5px; }
"""
elif template == "enterprise":
return """
@page { size: A4; margin: 2.5cm; }
body { font-family: "DejaVu Sans", "Arial", sans-serif; font-size: 11pt; line-height: 1.6; color: #1f2937; background: #fff; }
h1, h2, h3 { page-break-after: avoid; color: #1e3a8a; font-family: "DejaVu Sans", "Arial", sans-serif; }
h1 { border-bottom: 2px solid #10b981; padding-bottom: 0.5em; font-size: 24pt; margin-top: 1em; }
h2 { border-bottom: 1px solid #e5e7eb; padding-bottom: 0.3em; font-size: 18pt; margin-top: 1.5em; color: #1e40af; }
h3 { font-size: 14pt; margin-top: 1.2em; color: #374151; }
p { margin-bottom: 1em; text-align: justify; orphans: 3; widows: 3; }
table { width: 100%; border-collapse: collapse; margin: 1.5em 0; background: #ffffff; }
th, td { border: 1px solid #d1d5db; padding: 12px; text-align: left; }
th { background-color: #f3f4f6; color: #1f2937; font-weight: bold; }
ul, ol { margin-bottom: 1em; padding-left: 2em; }
li { margin-bottom: 0.5em; }
.toc { page-break-after: always; padding: 2em; background: #f9fafb; border-radius: 8px; border-left: 4px solid #10b981; }
.toc ul { list-style-type: none; padding-left: 1.5em; }
.toc > ul { padding-left: 0; }
.toc a { text-decoration: none; color: #1e3a8a; border-bottom: 1px dotted #9ca3af; display: block; padding-bottom: 5px; margin-bottom: 5px; }
"""
else: # standard
return """
@page { size: A4; margin: 2cm; }
body { font-family: "DejaVu Sans", "Arial", sans-serif; font-size: 11pt; line-height: 1.6; color: #333; }
h1, h2, h3 { page-break-after: avoid; }
h1 { border-bottom: 2px solid #3498db; padding-bottom: 10px; color: #2c3e50; }
h2 { color: #2980b9; margin-top: 1.5em; }
table { width: 100%; border-collapse: collapse; margin: 1em 0; }
th, td { border: 1px solid #bdc3c7; padding: 8px; text-align: left; }
th { background-color: #ecf0f1; }
p { margin-bottom: 1em; text-align: justify; orphans: 3; widows: 3; }
.toc { page-break-after: always; margin-top: 2em; }
.toc ul { list-style-type: none; padding-left: 1.5em; }
.toc > ul { padding-left: 0; }
.toc a { text-decoration: none; color: #2980b9; border-bottom: 1px dotted #bdc3c7; display: block; padding-bottom: 5px; margin-bottom: 5px; }
"""
def export_to_pdf(
content: str,
output_path: str,
template: str = "standard",
project_title: str = "Wniosek o Dofinansowanie",
company_name: str = "Brak nazwy",
version: str = "1.0",
date_str: str = "",
extra_context: dict = None,
):
"""
Eksportuje wniosek do PDF wykorzystując WeasyPrint.
"""
if extra_context is None:
extra_context = {}
try:
from xhtml2pdf import pisa
from reportlab.pdfbase.ttfonts import TTFont
from reportlab.pdfbase import pdfmetrics
import xhtml2pdf.default
except ImportError:
print("Nie mozna pobrac xhtml2pdf.")
raise Exception("Należy zainstalować xhtml2pdf (pip install xhtml2pdf).")
try:
# Usuwamy ewentualny nadmiarowy title na poczatku markdown by nie dublowac cover page
if content.startswith("# "):
content = "\n".join(content.split("\n")[1:])
md_content = f"[TOC]\n\n{content}"
html_body = markdown.markdown(
md_content,
extensions=["tables", "fenced_code", "toc"],
extension_configs={'toc': {'title': 'Spis Treści'}}
)
import urllib.request
backend_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), ".."))
font_dir = os.path.join(backend_dir, "assets")
os.makedirs(font_dir, exist_ok=True)
dejavu_path = os.path.join(backend_dir, "DejaVuSans.ttf")
dejavu_bold_path = os.path.join(backend_dir, "DejaVuSans-Bold.ttf")
if not os.path.exists(dejavu_path):
try:
urllib.request.urlretrieve(
"https://cdn.jsdelivr.net/npm/@vintproykt/dejavu-fonts-ttf/ttf/DejaVuSans.ttf",
dejavu_path,
)
except Exception as e:
print(f"Nie udało się pobrać DejaVuSans: {e}")
if not os.path.exists(dejavu_bold_path):
try:
urllib.request.urlretrieve(
"https://cdn.jsdelivr.net/npm/@vintproykt/dejavu-fonts-ttf/ttf/DejaVuSans-Bold.ttf",
dejavu_bold_path,
)
except Exception as e:
print(f"Nie udało się pobrać DejaVuSans-Bold: {e}")
font_face = ""
if os.path.exists(dejavu_path):
pdfmetrics.registerFont(TTFont("DejaVu Sans", dejavu_path))
if os.path.exists(dejavu_bold_path):
pdfmetrics.registerFont(TTFont("DejaVu Sans-Bold", dejavu_bold_path))
xhtml2pdf.default.DEFAULT_FONT["helvetica"] = "DejaVu Sans"
xhtml2pdf.default.DEFAULT_FONT["sans-serif"] = "DejaVu Sans"
xhtml2pdf.default.DEFAULT_FONT["arial"] = "DejaVu Sans"
font_face = f"""
@font-face {{ font-family: "DejaVu Sans"; src: url("file://{dejavu_path}"); }}
"""
if os.path.exists(dejavu_bold_path):
font_face += f"""
@font-face {{ font-family: "DejaVu Sans"; font-weight: bold; src: url("file://{dejavu_bold_path}"); }}
"""
css_style = font_face + get_pdf_css(template)
if not date_str:
date_str = datetime.datetime.now().strftime("%d.%m.%Y")
logo_html = ""
if template == "enterprise":
logo_html = '<div style="color: #10b981; font-size: 24pt; font-weight: bold; margin-bottom: 20px;">♦ GrantForge</div>'
# Cert logic
cert_html = ""
if extra_context and extra_context.get("include_grounding_certificate"):
cert = extra_context
snap = cert.get("snapshot_data", {})
cert_html = f"""
<pdf:nextpage />
<div style="margin-top: 50px;">
<h1 style="color: #1a365d; text-align: center; border-bottom: none;">ŚWIADECTWO ZGODNOŚCI WERSJI / REGULATION GROUNDING CERTIFICATE</h1>
<p style="text-align: center; color: #2d3748;">GrantForge AI — Najwyższy poziom ugruntowania w regulaminach i prawie UE</p>
<hr style="border: 1px solid #1a365d; margin-top: 20px; margin-bottom: 20px;" />
<p><b>Projekt:</b> {project_title}</p>
<p><b>Beneficjent:</b> {company_name}</p>
<p><b>Data wygenerowania:</b> {datetime.datetime.utcnow().strftime("%Y-%m-%d %H:%M UTC")}</p>
<p><b>Version Hash:</b> {cert.get("version_hash", "N/A")}</p>
<p><b>Precise Regulation URL:</b> {cert.get("precise_regulation_url", "N/A")}</p>
<p><b>Link Quality:</b> {cert.get("regulation_link_quality", "N/A")}</p>
"""
if snap:
cert_html += "<h3>SNAPSHOT REGULAMINU (źródło prawdy)</h3><ul>"
for k, v in snap.items():
if k not in ["key_rules", "exclusions"]:
cert_html += f"<li><b>{k}:</b> {v}</li>"
cert_html += "</ul>"
cert_html += """
<hr style="border: 1px solid #cbd5e1; margin-top: 30px; margin-bottom: 20px;" />
<p style="text-align: justify; font-size: 9pt; color: #64748b;">
To świadectwo potwierdza, że wszystkie wygenerowane treści opierają się na konkretnej, wersjonowanej wersji regulaminu oraz aktualnych aktach prawnych UE.
</p>
<p style="text-align: center; font-size: 10pt; color: #475569;">
https://grantforge.ai | Regulation Engine jako źródło prawdy
</p>
</div>
"""
html_content = f"""
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<style>
{css_style}
.cover-page {{
text-align: center;
padding-top: 250px;
}}
</style>
</head>
<body>
<div class="cover-page">
{logo_html}
<h1 style="border: none; font-size: 32pt; margin-bottom: 20px;">{project_title}</h1>
<p style="font-size: 16pt; color: #2c3e50; font-weight: bold;">{company_name}</p>
<div style="margin-top: 150px;">
<p style="font-size: 11pt; color: #95a5a6; font-weight: bold; margin-bottom: 5px;">Wygenerowano z użyciem systemu wsparcia DotacjeAI</p>
<p style="font-size: 10pt; color: #95a5a6;">Dokument utworzony: {date_str} | Wersja: {version}</p>
</div>
</div>
<!-- Wymuszenie nowej strony po stronie tytułowej -->
<pdf:nextpage />
{html_body}
{cert_html}
</body>
</html>
"""
with open(output_path, "wb") as pdf_file:
pisa_status = pisa.CreatePDF(html_content.encode("utf-8"), dest=pdf_file, encoding='utf-8')
if pisa_status.err:
print(f"Błąd pisa: {pisa_status.err}")
return False
return True
except Exception:
import traceback
print(f"Błąd eksportu do PDF: {traceback.format_exc()}")
return False
def localize_markdown_headings(content: str, lang: str = "pl") -> str:
"""Map English section headings to Polish (lang=pl)."""
if lang != "pl" or not content:
return content
mapping = {
"Executive Summary": "Streszczenie wykonawcze",
"Project Description": "Opis projektu",
"Budget": "Budżet",
"Timeline": "Harmonogram",
"Risk Analysis": "Analiza ryzyka",
"Expected Results": "Oczekiwane rezultaty",
}
lines = content.splitlines()
out: list[str] = []
for line in lines:
new_line = line
for en, pl in mapping.items():
if line.strip() == f"# {en}":
new_line = f"# {pl}"
break
if line.strip() == f"## {en}":
new_line = f"## {pl}"
break
if line.strip() == en:
new_line = pl
break
out.append(new_line)
return "\n".join(out)
|