yujunjun/unstructured
1
0
Fork 0
mirror of https://github.com/Unstructured-IO/unstructured.git synced 2025-08-31 12:23:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Feat: form parsing placeholders (#3034)

Browse Source 
Allows introduction of form extraction in the future - sets up the
FormKeysValues element & format, puts in an empty function call in the
partition_pdf_or_image pipeline.
This commit is contained in:
Jan Kanty Milczek 2024-05-16 16:21:31 +02:00 committed by GitHub
parent 1fb0fe5cf5
commit e6ada05c55
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
9 changed files with 285 additions and 29 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
CHANGELOG.md
View File

@ -1,4 +1,4 @@
## 0.13.8-dev12
## 0.13.8-dev13
### Enhancements
@ -7,6 +7,7 @@
* **Add strategy parameter to `partition_docx()`.** Behavior of future enhancements may be sensitive the partitioning strategy. Add this parameter so `partition_docx()` is aware of the requested strategy.
### Features
* **Add form extraction basics (document elements and placeholder code in partition)**. This is to lay the ground work for the future. Form extraction models are not currently available in the library. An attempt to use this functionality will end in a `NotImplementedError`.
### Fixes

149
example-docs/test_evaluate_files/unstructured_output/form.json Normal file
View File

@ -0,0 +1,149 @@
[
{
"type": "FormKeysValues",
"element_id": "MOCK_FORM_ID",
"text": "",
"metadata": {
"coordinates": {
"points": [
[
35.15625,
95.556640625
],
[
710.357666015625,
95.556640625
],
[
710.357666015625,
887.890625
],
[
35.15625,
887.890625
]
],
"system": "PixelSpace",
"layout_width": 754,
"layout_height": 1000
},
"page_number": 1,
"key_value_pairs": [
{
"key": {
"text": "MOCK KEY",
"custom_element": {
"type": "UncategorizedText",
"element_id": "MOCK_KEY_ID_1",
"text": "MOCK KEY",
"metadata": {
"coordinates": {
"points": [
[
503.271484375,
96.3897705078125
],
[
503.271484375,
107.5164794921875
],
[
606.103515625,
107.5164794921875
],
[
606.103515625,
96.3897705078125
]
],
"system": "PixelSpace",
"layout_width": 754,
"layout_height": 1000
},
"page_number": 1
}
},
"layout_element_id": null
},
"value": {
"text": "MOCK VALUE",
"custom_element": {
"type": "UncategorizedText",
"element_id": "MOCK_VALUE_ID",
"text": "MOCK VALUE",
"metadata": {
"coordinates": {
"points": [
[
557.568359375,
124.8626708984375
],
[
557.568359375,
136.6607666015625
],
[
595.556640625,
136.6607666015625
],
[
595.556640625,
124.8626708984375
]
],
"system": "PixelSpace",
"layout_width": 754,
"layout_height": 1000
},
"page_number": 1
}
},
"layout_element_id": null
},
"confidence": 0.0
},
{
"key": {
"text": "MOCK KEY 2",
"custom_element": {
"type": "UncategorizedText",
"element_id": "MOCK_KEY_ID_2",
"text": "MOCK KEY 2",
"metadata": {
"coordinates": {
"points": [
[
428.52783203125,
124.0478515625
],
[
428.52783203125,
136.6943359375
],
[
473.81591796875,
136.6943359375
],
[
473.81591796875,
124.0478515625
]
],
"system": "PixelSpace",
"layout_width": 754,
"layout_height": 1000
},
"page_number": 1
}
},
"layout_element_id": null
},
"value": null,
"confidence": 0.0
}
],
"file_directory": "dataset/testing_data/images",
"filename": "MOCK.png"
}
}
]

14
test_unstructured/documents/test_elements.py
View File

@ -5,13 +5,14 @@
from __future__ import annotations
import copy
import io
import json
import pathlib
from functools import partial
import pytest
from test_unstructured.unit_utils import assign_hash_ids
from test_unstructured.unit_utils import assign_hash_ids, example_doc_path
from unstructured.cleaners.core import clean_bullets, clean_prefix
from unstructured.documents.coordinates import (
CoordinateSystem,
@ -31,6 +32,7 @@ from unstructured.documents.elements import (
Title,
assign_and_map_hash_ids,
)
from unstructured.partition.json import partition_json
@pytest.mark.parametrize("element", [Element(), Text(text=""), CheckBox()])
@ -744,3 +746,13 @@ def test_id_to_hash_calculates(text, sequence_number, filename, page_number, exp
)
assert element.id_to_hash(sequence_number) == expected_hash, "Returned ID does not match"
assert element.id == expected_hash, "ID should be set"
def test_formskeysvalues_reads_saves():
filename = example_doc_path("test_evaluate_files/unstructured_output/form.json")
as_read = partition_json(filename=filename)
tmp_file = io.StringIO()
json.dump([element.to_dict() for element in as_read], tmp_file)
tmp_file.seek(0)
as_read_2 = partition_json(file=tmp_file)
assert as_read == as_read_2

2
unstructured/__version__.py
View File

@ -1 +1 @@
__version__ = "0.13.8-dev12" # pragma: no cover
__version__ = "0.13.8-dev13" # pragma: no cover

64
unstructured/documents/elements.py
View File

@ -143,6 +143,18 @@ class Link(TypedDict):
start_index: int
class FormKeyOrValue(TypedDict):
text: str
layout_element_id: Optional[str]
custom_element: Optional[Text]
class FormKeyValuePair(TypedDict):
key: FormKeyOrValue
value: Optional[FormKeyOrValue]
confidence: float
class ElementMetadata:
"""Fully-dynamic replacement for dataclass-based ElementMetadata."""
@ -176,6 +188,7 @@ class ElementMetadata:
header_footer_type: Optional[str]
# -- used in chunks only, when chunk must be split mid-text to fit window --
is_continuation: Optional[bool]
key_value_pairs: Optional[list[FormKeyValuePair]]
languages: Optional[list[str]]
last_modified: Optional[str]
link_texts: Optional[list[str]]
@ -327,6 +340,8 @@ class ElementMetadata:
self.data_source = DataSourceMetadata.from_dict(field_value)
elif field_name == "orig_elements":
self.orig_elements = elements_from_base64_gzipped_json(field_value)
elif field_name == "key_value_pairs":
self.key_value_pairs = _kvform_rehydrate_internal_elements(field_value)
else:
setattr(self, field_name, field_value)
@ -392,6 +407,8 @@ class ElementMetadata:
meta_dict["data_source"] = self.data_source.to_dict()
if self.orig_elements is not None:
meta_dict["orig_elements"] = elements_to_base64_gzipped_json(self.orig_elements)
if self.key_value_pairs is not None:
meta_dict["key_value_pairs"] = _kvform_pairs_to_dict(self.key_value_pairs)
return meta_dict
@ -494,6 +511,7 @@ class ConsolidationStrategy(enum.Enum):
"text_as_html": cls.FIRST, # -- only occurs in Table --
"table_as_cells": cls.FIRST, # -- only occurs in Table --
"url": cls.FIRST,
"key_value_pairs": cls.DROP, # -- only occurs in FormKeysValues --
}
@ -660,6 +678,7 @@ class ElementType:
PAGE_FOOTER = "Page-footer"
PAGE_NUMBER = "PageNumber"
CODE_SNIPPET = "CodeSnippet"
FORM_KEYS_VALUES = "FormKeysValues"
@classmethod
def to_dict(cls):
@ -992,6 +1011,12 @@ class PageNumber(Text):
category = "PageNumber"
class FormKeysValues(Text):
"""An element for capturing Key-Value dicts (forms)."""
category = "FormKeysValues"
TYPE_TO_TEXT_ELEMENT_MAP: dict[str, type[Text]] = {
ElementType.TITLE: Title,
ElementType.SECTION_HEADER: Title,
@ -1029,4 +1054,43 @@ TYPE_TO_TEXT_ELEMENT_MAP: dict[str, type[Text]] = {
ElementType.PAGE_BREAK: PageBreak,
ElementType.CODE_SNIPPET: CodeSnippet,
ElementType.PAGE_NUMBER: PageNumber,
ElementType.FORM_KEYS_VALUES: FormKeysValues,
}
def _kvform_rehydrate_internal_elements(kv_pairs: list[dict]) -> list[FormKeyValuePair]:
"""
The key_value_pairs metadata field contains (in the vast majority of cases)
nested Text elements. Those need to be turned from dicts into Elements explicitly,
e.g. when partition_json is used.
"""
from unstructured.staging.base import elements_from_dicts
# safe to overwrite - deepcopy already happened
for kv_pair in kv_pairs:
if kv_pair["key"]["custom_element"] is not None:
(kv_pair["key"]["custom_element"],) = elements_from_dicts(
[kv_pair["key"]["custom_element"]]
)
if kv_pair["value"] is not None and kv_pair["value"]["custom_element"] is not None:
(kv_pair["value"]["custom_element"],) = elements_from_dicts(
[kv_pair["value"]["custom_element"]]
)
return kv_pairs
def _kvform_pairs_to_dict(kv_pairs: list[FormKeyValuePair]) -> list[dict]:
"""
The key_value_pairs metadata field contains (in the vast majority of cases)
nested Text elements. Those need to be turned from Elements to dicts recursively,
e.g. when FormKeysValues.to_dict() is used.
"""
kv_pairs: list[dict] = copy.deepcopy(kv_pairs)
for kv_pair in kv_pairs:
if kv_pair["key"]["custom_element"] is not None:
kv_pair["key"]["custom_element"] = kv_pair["key"]["custom_element"].to_dict()
if kv_pair["value"] is not None and kv_pair["value"]["custom_element"] is not None:
kv_pair["value"]["custom_element"] = kv_pair["value"]["custom_element"].to_dict()
return kv_pairs

13
unstructured/partition/image.py
View File

@ -6,9 +6,7 @@ from unstructured.chunking import add_chunking_strategy
from unstructured.documents.elements import Element, process_metadata
from unstructured.file_utils.filetype import add_metadata
from unstructured.partition.common import exactly_one
from unstructured.partition.lang import (
check_language_args,
)
from unstructured.partition.lang import check_language_args
from unstructured.partition.pdf import partition_pdf_or_image
from unstructured.partition.utils.constants import PartitionStrategy
@ -33,6 +31,8 @@ def partition_image(
extract_image_block_to_payload: bool = False,
date_from_file_object: bool = False,
starting_page_number: int = 1,
extract_forms: bool = False,
form_extraction_skip_tables: bool = True,
**kwargs: Any,
) -> list[Element]:
"""Parses an image into a list of interpreted elements.
@ -90,6 +90,11 @@ def partition_image(
date_from_file_object
Applies only when providing file via `file` parameter. If this option is True, attempt
infer last_modified metadata from bytes, otherwise set it to None.
extract_forms
Whether the form extraction logic should be run
(results in adding FormKeysValues elements to output).
form_extraction_skip_tables
Whether the form extraction logic should ignore regions designated as Tables.
"""
exactly_one(filename=filename, file=file)
@ -111,5 +116,7 @@ def partition_image(
extract_image_block_to_payload=extract_image_block_to_payload,
date_from_file_object=date_from_file_object,
starting_page_number=starting_page_number,
extract_forms=extract_forms,
form_extraction_skip_tables=form_extraction_skip_tables,
**kwargs,
)

53
unstructured/partition/pdf.py
View File

@ -12,13 +12,7 @@ import numpy as np
import pdf2image
import wrapt
from pdfminer import psparser
from pdfminer.layout import (
LTChar,
LTContainer,
LTImage,
LTItem,
LTTextBox,
)
from pdfminer.layout import LTChar, LTContainer, LTImage, LTItem, LTTextBox
from pdfminer.pdftypes import PDFObjRef
from pdfminer.utils import open_filename
from PIL import Image as PILImage
@ -42,10 +36,7 @@ from unstructured.documents.elements import (
Text,
process_metadata,
)
from unstructured.file_utils.filetype import (
FileType,
add_metadata_with_filetype,
)
from unstructured.file_utils.filetype import FileType, add_metadata_with_filetype
from unstructured.logger import logger, trace_logger
from unstructured.nlp.patterns import PARAGRAPH_PATTERN
from unstructured.partition.common import (
@ -57,10 +48,8 @@ from unstructured.partition.common import (
ocr_data_to_elements,
spooled_to_bytes_io_if_needed,
)
from unstructured.partition.lang import (
check_language_args,
prepare_languages_for_tesseract,
)
from unstructured.partition.lang import check_language_args, prepare_languages_for_tesseract
from unstructured.partition.pdf_image.form_extraction import run_form_extraction
from unstructured.partition.pdf_image.pdf_image_utils import (
annotate_layout_elements,
check_element_types_to_extract,
@ -85,10 +74,7 @@ from unstructured.partition.utils.constants import (
OCRMode,
PartitionStrategy,
)
from unstructured.partition.utils.sorting import (
coord_has_valid_points,
sort_page_elements,
)
from unstructured.partition.utils.sorting import coord_has_valid_points, sort_page_elements
from unstructured.patches.pdfminer import parse_keyword
from unstructured.utils import requires_dependencies
@ -135,6 +121,8 @@ def partition_pdf(
extract_image_block_to_payload: bool = False,
date_from_file_object: bool = False,
starting_page_number: int = 1,
extract_forms: bool = False,
form_extraction_skip_tables: bool = True,
**kwargs: Any,
) -> list[Element]:
"""Parses a pdf document into a list of interpreted elements.
@ -191,6 +179,11 @@ def partition_pdf(
date_from_file_object
Applies only when providing file via `file` parameter. If this option is True, attempt
infer last_modified metadata from bytes, otherwise set it to None.
extract_forms
Whether the form extraction logic should be run
(results in adding FormKeysValues elements to output).
form_extraction_skip_tables
Whether the form extraction logic should ignore regions designated as Tables.
"""
exactly_one(filename=filename, file=file)
@ -212,6 +205,7 @@ def partition_pdf(
extract_image_block_to_payload=extract_image_block_to_payload,
date_from_file_object=date_from_file_object,
starting_page_number=starting_page_number,
extract_forms=extract_forms,
**kwargs,
)
@ -233,6 +227,8 @@ def partition_pdf_or_image(
extract_image_block_to_payload: bool = False,
date_from_file_object: bool = False,
starting_page_number: int = 1,
extract_forms: bool = False,
form_extraction_skip_tables: bool = True,
**kwargs: Any,
) -> list[Element]:
"""Parses a pdf or image document into a list of interpreted elements."""
@ -304,6 +300,8 @@ def partition_pdf_or_image(
extract_image_block_output_dir=extract_image_block_output_dir,
extract_image_block_to_payload=extract_image_block_to_payload,
starting_page_number=starting_page_number,
extract_forms=extract_forms,
form_extraction_skip_tables=form_extraction_skip_tables,
**kwargs,
)
out_elements = _process_uncategorized_text_elements(elements)
@ -390,6 +388,8 @@ def _partition_pdf_or_image_local(
analysis: bool = False,
analyzed_image_output_dir_path: Optional[str] = None,
starting_page_number: int = 1,
extract_forms: bool = False,
form_extraction_skip_tables: bool = True,
**kwargs: Any,
) -> list[Element]:
"""Partition using package installed locally"""
@ -398,10 +398,7 @@ def _partition_pdf_or_image_local(
process_file_with_model,
)
from unstructured.partition.pdf_image.ocr import (
process_data_with_ocr,
process_file_with_ocr,
)
from unstructured.partition.pdf_image.ocr import process_data_with_ocr, process_file_with_ocr
from unstructured.partition.pdf_image.pdfminer_processing import (
process_data_with_pdfminer,
process_file_with_pdfminer,
@ -581,6 +578,16 @@ def _partition_pdf_or_image_local(
if el.text or isinstance(el, PageBreak) or hi_res_model_name.startswith("chipper"):
out_elements.append(cast(Element, el))
if extract_forms:
forms = run_form_extraction(
file=file,
filename=filename,
model_name=hi_res_model_name,
elements=out_elements,
skip_table_regions=form_extraction_skip_tables,
)
out_elements.extend(forms)
return out_elements

15
unstructured/partition/pdf_image/form_extraction.py Normal file
View File

@ -0,0 +1,15 @@
from __future__ import annotations
from typing import IO
from unstructured.documents.elements import Element, FormKeysValues
def run_form_extraction(
filename: str,
file: IO[bytes],
model_name: str,
elements: list[Element],
skip_table_regions: bool,
) -> list[FormKeysValues]:
raise NotImplementedError("Form extraction not yet available.")

1
unstructured/staging/weaviate.py
View File

@ -17,6 +17,7 @@ exclude_metadata_keys = (
"links",
"orig_elements",
"regex_metadata",
"key_value_pairs",
)