Marmelator/image-classification-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 29 Wiki Activity

[WIP] Monadic refactoring

Browse Source 
Integrate image validation step into monadic chain.

At the moment we lost the error information through this. Refactoring to
Either monad can bring it back.
This commit is contained in:
Matthias Bisping 2023-02-06 16:12:40 +01:00
parent 022bd4856a
commit 89989543d8
1 changed files with 16 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
image_prediction/image_extractor/extractors/parsable.py
View File

@ -1,22 +1,18 @@
import atexit
import json
import traceback
from _operator import itemgetter
from functools import partial, lru_cache
from itertools import chain, starmap, filterfalse
from itertools import chain, filterfalse
from operator import itemgetter
from typing import Iterable, Iterator, List, Union
from typing import List, Union
import IPython
import fitz
import numpy as np
from PIL import Image
from funcy import merge, compose, rcompose, keep, identity
from funcy import merge, compose, rcompose, keep
from pymonad.maybe import Maybe, Nothing, Just
from pymonad.tools import curry
from image_prediction.exceptions import InvalidBox, BadXref
from image_prediction.formatter.formatters.enum import EnumFormatter
from image_prediction.image_extractor.extractor import ImageExtractor, ImageMetadataPair
from image_prediction.info import Info
from image_prediction.stitching.stitching import stitch_pairs
@ -25,8 +21,6 @@ from image_prediction.utils import get_logger
logger = get_logger()
Maybe
class ParsablePDFImageExtractor(ImageExtractor):
def __init__(self, verbose=False, tolerance=0):
@ -57,29 +51,10 @@ class ParsablePDFImageExtractor(ImageExtractor):
image_metadata_pairs = [pair.value for pair in maybe_image_metadata_pairs if pair.is_just()]
clear_caches()
# TODO: In the future, consider to introduce an image validator as a pipeline component rather than doing the
# validation here. Invalid images can then be split into a different stream and joined with the intact images
# again for the formatting step.
image_metadata_pairs = self.__filter_valid_images(image_metadata_pairs)
image_metadata_pairs = stitch_pairs(list(image_metadata_pairs), tolerance=self.tolerance)
yield from image_metadata_pairs
@staticmethod
def __filter_valid_images(image_metadata_pairs: Iterable[ImageMetadataPair]) -> Iterator[ImageMetadataPair]:
def validate(image: Image.Image, metadatum: dict):
try:
# TODO: stand-in heuristic for testing if image is valid => find cleaner solution (RED-5148)
image.resize((100, 100)).convert("RGB")
return ImageMetadataPair(image, metadatum)
except (OSError, Exception):
metadatum = json.dumps(EnumFormatter()(metadatum), indent=2)
logger.warning(f"Invalid image encountered. Image metadata:\n{metadatum}\n\n{traceback.format_exc()}")
return None
return keep(starmap(validate, image_metadata_pairs))
def extract_pages(doc, page_range):
page_range = range(page_range.start + 1, page_range.stop + 1)
@ -88,6 +63,16 @@ def extract_pages(doc, page_range):
yield from pages
def validate_image(image: Image.Image) -> Maybe:
try:
# TODO: stand-in heuristic for testing if image is valid => find cleaner solution (RED-5148)
image.resize((100, 100)).convert("RGB")
return Just(image)
except (OSError, Exception):
logger.warning(f"Invalid image encountered.")
return Nothing
def extract_valid_metadata(doc: fitz.fitz.Document, page: fitz.fitz.Page):
return compose(
list,
@ -98,8 +83,9 @@ def extract_valid_metadata(doc: fitz.fitz.Document, page: fitz.fitz.Page):
def metadatum_to_image_metadata_pair(doc, metadatum: dict) -> Maybe:
maybe_image = xref_to_maybe_image(doc, metadatum[Info.XREF])
return make_maybe_image_metadata_pair(maybe_image, Just(metadatum))
maybe_image = xref_to_maybe_image(doc, metadatum[Info.XREF]).bind(validate_image)
maybe_image_metadata_pair = make_maybe_image_metadata_pair(maybe_image, Just(metadatum))
return maybe_image_metadata_pair
def add_alpha_channel_info(doc, metadata):