JiriUhlirandClaude Opus 5
156289fe2d
Sluzba prijme adresu HTML dokumentu nebo HTML v tele requestu a vrati PDF. Navrzena pro dokumenty o stovkach az tisicich stranek. Rendering: - WeasyPrint jako vychozi engine, spravne CSS Paged Media, nizka pametova narocnost, bez JavaScriptu - Chromium pres Playwright pro dokumenty dokreslovane skripty - rezim auto s detekci skriptu a fallbackem pri selhani WeasyPrintu Velke dokumenty: - deleni na casti na strukturalnich hranicich, rez nikdy uvnitr tabulky nebo odstavce - dvoupruchodovy render obsahu se skutecnymi cisly stranek, pozice nadpisu se ctou z kotev hlasenych u kazde stranky - cislovani stranek bud pres CSS countery, nebo pres cislovaci vrstvu nastampovanou na hotove PDF, rozmer stranky se cte z vysledneho souboru - Chromium se restartuje po N jobech, nikdy vsak behem beziciho renderu API: - POST /convert synchronne, POST /jobs asynchronne se sledovanim stavu, stahovanim vysledku, rusenim a volitelnym callbackem - GET /health s overenim dostupnosti obou enginu a stavem fronty - OpenAPI respektuje prefix reverse proxy pres root_path Bezpecnost a provoz: - SSRF kontrola po DNS resolvu, na kazdem presmerovani a u vsech pozadavku prohlizece - nedostupne assety render nezastavi, ale hlasi se v odpovedi i v logu - fronta s omezenym poctem workeru, rozpracovane joby se pri ukonceni oznaci jako failed, nezmizi potichu - strukturovane JSON logovani s job_id - vsechny limity vypnute ve vychozim stavu Dockerfile je dvoufazovy, obsahuje zavislosti WeasyPrintu, Chromium a fonty s ceskou diakritikou. Autentizace zamerne neni implementovana, zpusob predavani neni domluveny. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
81 lines
2.6 KiB
Python
81 lines
2.6 KiB
Python
"""Page numbering of the merged document.
|
|
|
|
Two ways to number pages:
|
|
|
|
css
|
|
CSS counters do the work during the render. Correct and cheap, but it only
|
|
works when the whole document is rendered in one pass, because each chunk
|
|
restarts the page counter.
|
|
|
|
overlay
|
|
A transparent numbering layer with the same page size is rendered once and
|
|
merged onto the finished PDF. This is the only option for a chunked document
|
|
and for Chromium, which has no usable page counters.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
from ..errors import EngineUnavailableError
|
|
from ..models import PageNumbers, PageSettings
|
|
from .styles import build_overlay_css
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def build_overlay(
|
|
total_pages: int,
|
|
width_pt: float,
|
|
height_pt: float,
|
|
page: PageSettings,
|
|
page_numbers: PageNumbers,
|
|
output_path: Path,
|
|
) -> Path:
|
|
"""Render the numbering layer, one empty page per page of the document."""
|
|
try:
|
|
from weasyprint import HTML
|
|
except ImportError as exc:
|
|
raise EngineUnavailableError(
|
|
"Cislovani stranek vyzaduje nainstalovany WeasyPrint, ktery kresli cislovaci vrstvu.",
|
|
) from exc
|
|
|
|
css = build_overlay_css(width_pt, height_pt, page, page_numbers, total_pages)
|
|
slots = '<div class="pdf-page-slot"></div>' * total_pages
|
|
html = (
|
|
"<!DOCTYPE html><html><head><meta charset=\"utf-8\">"
|
|
f"<style>{css}</style></head><body>{slots}</body></html>"
|
|
)
|
|
|
|
HTML(string=html).write_pdf(target=str(output_path))
|
|
logger.info("Numbering overlay rendered", extra={"pages": total_pages})
|
|
return output_path
|
|
|
|
|
|
def apply_overlay(document_path: Path, overlay_path: Path, output_path: Path) -> None:
|
|
"""Stamp the numbering layer onto every page of the document."""
|
|
from pypdf import PdfReader, PdfWriter
|
|
|
|
writer = PdfWriter(clone_from=str(document_path))
|
|
try:
|
|
with overlay_path.open("rb") as handle:
|
|
overlay = PdfReader(handle)
|
|
available = len(overlay.pages)
|
|
|
|
if available < len(writer.pages):
|
|
logger.warning(
|
|
"Numbering overlay has fewer pages than the document, tail will stay unnumbered",
|
|
extra={"overlay_pages": available, "document_pages": len(writer.pages)},
|
|
)
|
|
|
|
for index, page in enumerate(writer.pages):
|
|
if index >= available:
|
|
break
|
|
page.merge_page(overlay.pages[index])
|
|
|
|
with output_path.open("wb") as target:
|
|
writer.write(target)
|
|
finally:
|
|
writer.close()
|