areneau's picture
Add complete Clairic Transformers package
dc7d8aa verified
Raw History Blame Contribute Delete
3.49 kB
"""Validate embedded PDFs and render their pages inside the request encoder."""
from __future__ import annotations
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from PIL import Image
import base64
import binascii
import math
import re
from .embedded import MAX_IMAGE_BYTES, MAX_IMAGES
from pydantic import BaseModel, ConfigDict, StrictStr, model_validator
class ClairDocument(BaseModel):
model_config = ConfigDict(extra="forbid", frozen=True)
content_type: StrictStr
base64: StrictStr
@model_validator(mode="before")
@classmethod
def parse_document(cls, value: object) -> dict[str, str]:
if isinstance(value, str):
match = re.fullmatch(
r"data:application/pdf;base64,([A-Za-z0-9+/]*={0,2})",
value,
re.IGNORECASE,
)
if match is None:
raise ValueError("document must be an embedded PDF data URI")
value = {"content_type": "application/pdf", "base64": match[1]}
if type(value) is not dict or set(value) != {"content_type", "base64"}:
raise ValueError("document object must contain content_type and base64")
if value["content_type"] != "application/pdf" or not isinstance(
value["base64"], str
):
raise ValueError("document content type must be application/pdf")
try:
data = base64.b64decode(value["base64"], validate=True)
except (binascii.Error, ValueError) as error:
raise ValueError("document base64 is malformed") from error
if not data.startswith(b"%PDF-") or len(data) > MAX_IMAGE_BYTES:
raise ValueError("document must be a PDF within the decoded byte limit")
return {
"content_type": "application/pdf",
"base64": base64.b64encode(data).decode("ascii"),
}
def render(self, available_pages: int = MAX_IMAGES) -> list[Image.Image]:
import pypdfium2 as pdfium
from .orientation import orient_document
try:
pdf = pdfium.PdfDocument(base64.b64decode(self.base64))
try:
if not 0 < len(pdf) <= available_pages:
raise ValueError(
f"PDF pages and images together must not exceed {MAX_IMAGES}"
)
images = []
for index in range(len(pdf)):
page = pdf[index]
try:
width, height = page.get_size()
if not (
math.isfinite(width * height) and width > 0 and height > 0
):
raise ValueError("PDF page has invalid dimensions")
scale = min(2.0, math.sqrt(4_000_000 / (width * height)))
bitmap = page.render(scale=scale)
try:
images.append(
orient_document(bitmap.to_pil().convert("RGB"))
)
finally:
bitmap.close()
finally:
page.close()
return images
finally:
pdf.close()
except pdfium.PdfiumError as error:
raise ValueError(
"PDF cannot be opened or rendered; encrypted PDFs are unsupported"
) from error