Skip to content
This repository was archived by the owner on Sep 20, 2023. It is now read-only.

feat: added hints.language_hints field in OcrConfig #470

Merged
holtskinner merged 2 commits into from
Mar 9, 2023
Merged

feat: added hints.language_hints field in OcrConfig #470

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3f12b53
feat: added hints.language_hints field in OcrConfig
gcf-owl-bot[bot] Mar 8, 2023
f6cf4d0
🦉 Updates from OwlBot post-processor
gcf-owl-bot[bot] Mar 8, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 45 additions & 0 deletions google/cloud/documentai_v1beta3/types/document_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,23 +225,68 @@ class OcrConfig(proto.Message):
r"""Config for Document OCR.

Attributes:
hints (google.cloud.documentai_v1beta3.types.OcrConfig.Hints):
Hints for the OCR model.
enable_native_pdf_parsing (bool):
Enables special handling for PDFs with
existing text information. Results in better
text extraction quality in such PDF inputs.
enable_image_quality_scores (bool):
Enables intelligent document quality scores
after OCR. Can help with diagnosing why OCR
responses are of poor quality for a given input.
Adds additional latency comparable to regular
OCR to the process call.
advanced_ocr_options (MutableSequence[str]):
A list of advanced OCR options to further
fine-tune OCR behavior.
enable_symbol (bool):
Includes symbol level OCR information if set
to true.
"""

class Hints(proto.Message):
r"""Hints for OCR Engine

Attributes:
language_hints (MutableSequence[str]):
List of BCP-47 language codes to use for OCR.
In most cases, not specifying it yields the best
results since it enables automatic language
detection. For languages based on the Latin
alphabet, setting hints is not needed. In rare
cases, when the language of the text in the
image is known, setting a hint will help get
better results (although it will be a
significant hindrance if the hint is wrong).
"""

language_hints: MutableSequence[str] = proto.RepeatedField(
proto.STRING,
number=1,
)

hints: Hints = proto.Field(
proto.MESSAGE,
number=2,
message=Hints,
)
enable_native_pdf_parsing: bool = proto.Field(
proto.BOOL,
number=3,
)
enable_image_quality_scores: bool = proto.Field(
proto.BOOL,
number=4,
)
advanced_ocr_options: MutableSequence[str] = proto.RepeatedField(
proto.STRING,
number=5,
)
enable_symbol: bool = proto.Field(
proto.BOOL,
number=6,
)


__all__ = tuple(sorted(__protobuf__.manifest))