Skip to content

Commit 2e0fe16

Browse files
✨ add support for image and pdf compression (#297)
1 parent 349502c commit 2e0fe16

35 files changed

+906
-48
lines changed

examples/auto_invoice_splitter_extraction_example.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
from mindee import Client
22
from mindee.extraction.pdf_extractor import PdfExtractor
3-
from mindee.input.sources import PathInput
3+
from mindee.input.sources.path_input import PathInput
44
from mindee.product.invoice.invoice_v4 import InvoiceV4
55
from mindee.product.invoice_splitter.invoice_splitter_v1 import InvoiceSplitterV1
66

mindee/client.py

Lines changed: 6 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -7,14 +7,12 @@
77
from mindee.input import WorkflowOptions
88
from mindee.input.local_response import LocalResponse
99
from mindee.input.page_options import PageOptions
10-
from mindee.input.sources import (
11-
Base64Input,
12-
BytesInput,
13-
FileInput,
14-
LocalInputSource,
15-
PathInput,
16-
UrlInputSource,
17-
)
10+
from mindee.input.sources.base_64_input import Base64Input
11+
from mindee.input.sources.bytes_input import BytesInput
12+
from mindee.input.sources.file_input import FileInput
13+
from mindee.input.sources.local_input_source import LocalInputSource
14+
from mindee.input.sources.path_input import PathInput
15+
from mindee.input.sources.url_input_source import UrlInputSource
1816
from mindee.logger import logger
1917
from mindee.mindee_http.endpoint import CustomEndpoint, Endpoint
2018
from mindee.mindee_http.mindee_api import MindeeApi

mindee/error/__init__.py

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,3 +7,5 @@
77
MindeeHTTPServerError,
88
handle_error,
99
)
10+
from mindee.error.mindee_image_error import MindeeImageError
11+
from mindee.error.mindee_pdf_error import MindeePDFError

mindee/error/mindee_image_error.py

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
class MindeeImageError(RuntimeError):
2+
"""An exception relating to errors during image operations."""

mindee/error/mindee_pdf_error.py

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
class MindeePDFError(RuntimeError):
2+
"""An exception relating to errors during PDF operations."""

mindee/extraction/common/extracted_image.py

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,8 @@
55
from PIL import Image
66

77
from mindee.error.mindee_error import MindeeError
8-
from mindee.input.sources import FileInput, LocalInputSource
8+
from mindee.input.sources.file_input import FileInput
9+
from mindee.input.sources.local_input_source import LocalInputSource
910
from mindee.logger import logger
1011

1112

mindee/extraction/common/image_extractor.py

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,8 @@
88
from mindee.extraction.common.extracted_image import ExtractedImage
99
from mindee.geometry.point import Point
1010
from mindee.geometry.polygon import get_min_max_x, get_min_max_y
11-
from mindee.input.sources import BytesInput, LocalInputSource
11+
from mindee.input.sources.bytes_input import BytesInput
12+
from mindee.input.sources.local_input_source import LocalInputSource
1213

1314

1415
def attach_image_as_new_file( # type: ignore
@@ -158,6 +159,6 @@ def load_pdf_doc(input_file: LocalInputSource) -> pdfium.PdfDocument: # type: i
158159
"""
159160
if input_file.is_pdf():
160161
input_file.file_object.seek(0)
161-
return pdfium.PdfDocument(input_file.file_object)
162+
return pdfium.PdfDocument(input_file.file_object.read())
162163

163164
return attach_image_as_new_file(input_file.file_object)

mindee/extraction/multi_receipts_extractor/multi_receipts_extractor.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
from mindee.extraction.common.image_extractor import (
66
extract_multiple_images_from_source,
77
)
8-
from mindee.input.sources import LocalInputSource
8+
from mindee.input.sources.local_input_source import LocalInputSource
99
from mindee.parsing.common.inference import Inference
1010

1111

mindee/extraction/pdf_extractor/extracted_pdf.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
import pypdfium2 as pdfium
55

66
from mindee.error.mindee_error import MindeeError
7-
from mindee.input.sources import BytesInput
7+
from mindee.input.sources.bytes_input import BytesInput
88

99

1010
class ExtractedPdf:

mindee/extraction/pdf_extractor/pdf_extractor.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@
77

88
from mindee.error.mindee_error import MindeeError
99
from mindee.extraction.pdf_extractor.extracted_pdf import ExtractedPdf
10-
from mindee.input.sources import LocalInputSource
10+
from mindee.input.sources.local_input_source import LocalInputSource
1111
from mindee.product.invoice_splitter.invoice_splitter_v1_page_group import (
1212
InvoiceSplitterV1PageGroup,
1313
)

0 commit comments

Comments
 (0)