mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-07-25 01:50:21 +00:00
ce40cdc55f
### Summary Table OCR refactor, move the OCR part for table model in inference repo to unst repo. * Before this PR, table model extracts OCR tokens with texts and bounding box and fills the tokens to the table structure in inference repo. This means we need to do an additional OCR for tables. * After this PR, we use the OCR data from entire page OCR and pass the OCR tokens to inference repo, which means we only do one OCR for the entire document. **Tech details:** * Combined env `ENTIRE_PAGE_OCR` and `TABLE_OCR` to `OCR_AGENT`, this means we use the same OCR agent for entire page and tables since we only do one OCR. * Bump inference repo to `0.7.9`, which allow table model in inference to use pre-computed OCR data from unst repo. Please check in [PR](https://github.com/Unstructured-IO/unstructured-inference/pull/256). * All notebooks lint are made by `make tidy` * This PR also fixes [issue](https://github.com/Unstructured-IO/unstructured/issues/1564), I've added test for the issue in `test_pdf.py::test_partition_pdf_hi_table_extraction_with_languages` * Add same scaling logic to image [similar to previous Table OCR](https://github.com/Unstructured-IO/unstructured-inference/blob/main/unstructured_inference/models/tables.py#L109C1-L113), but now scaling is applied to entire image ### Test * Not much to manually testing expect table extraction still works * But due to change on scaling and use pre-computed OCR data from entire page, there are some slight (better) changes on table output, here is an comparison on test outputs i found from the same test `test_partition_image_with_table_extraction`: screen shot for table in `layout-parser-paper-with-table.jpg`: <img width="343" alt="expected" src="https://github.com/Unstructured-IO/unstructured/assets/63475068/278d7665-d212-433d-9a05-872c4502725c"> before refactor: <img width="709" alt="before" src="https://github.com/Unstructured-IO/unstructured/assets/63475068/347fbc3b-f52b-45b5-97e9-6f633eaa0d5e"> after refactor: <img width="705" alt="after" src="https://github.com/Unstructured-IO/unstructured/assets/63475068/b3cbd809-cf67-4e75-945a-5cbd06b33b2d"> ### TODO (added as a ticket) Still have some clean up to do in inference repo since now unst repo have duplicate logic, but can keep them as a fall back plan. If we want to remove anything OCR related in inference, here are items that is deprecated and can be removed: * [`get_tokens`](https://github.com/Unstructured-IO/unstructured-inference/blob/main/unstructured_inference/models/tables.py#L77) (already noted in code) * parameter `extract_tables` in inference * [`interpret_table_block`](https://github.com/Unstructured-IO/unstructured-inference/blob/main/unstructured_inference/inference/layoutelement.py#L88) * [`load_agent`](https://github.com/Unstructured-IO/unstructured-inference/blob/main/unstructured_inference/models/tables.py#L197) * env `TABLE_OCR` ### Note if we want to fallback for an additional table OCR (may need this for using paddle for table), we need to: * pass `infer_table_structure` to inference with `extract_tables` parameter * stop passing `infer_table_structure` to `ocr.py` --------- Co-authored-by: Yao You <yao@unstructured.io>
538 lines
17 KiB
Python
538 lines
17 KiB
Python
# pyright: reportPrivateUsage=false
|
|
|
|
from typing import List
|
|
|
|
import pytest
|
|
|
|
from unstructured.chunking.title import (
|
|
_split_elements_by_title_and_table,
|
|
chunk_by_title,
|
|
)
|
|
from unstructured.documents.coordinates import CoordinateSystem
|
|
from unstructured.documents.elements import (
|
|
CheckBox,
|
|
CompositeElement,
|
|
CoordinatesMetadata,
|
|
Element,
|
|
ElementMetadata,
|
|
RegexMetadata,
|
|
Table,
|
|
Text,
|
|
Title,
|
|
)
|
|
from unstructured.partition.html import partition_html
|
|
|
|
|
|
def test_split_elements_by_title_and_table():
|
|
elements: List[Element] = [
|
|
Title("A Great Day"),
|
|
Text("Today is a great day."),
|
|
Text("It is sunny outside."),
|
|
Table("<table></table>"),
|
|
Title("An Okay Day"),
|
|
Text("Today is an okay day."),
|
|
Text("It is rainy outside."),
|
|
Title("A Bad Day"),
|
|
Text("Today is a bad day."),
|
|
Text("It is storming outside."),
|
|
CheckBox(),
|
|
]
|
|
sections = _split_elements_by_title_and_table(elements, combine_text_under_n_chars=0)
|
|
|
|
assert sections == [
|
|
[
|
|
Title("A Great Day"),
|
|
Text("Today is a great day."),
|
|
Text("It is sunny outside."),
|
|
],
|
|
[
|
|
Table("<table></table>"),
|
|
],
|
|
[
|
|
Title("An Okay Day"),
|
|
Text("Today is an okay day."),
|
|
Text("It is rainy outside."),
|
|
],
|
|
[
|
|
Title("A Bad Day"),
|
|
Text("Today is a bad day."),
|
|
Text("It is storming outside."),
|
|
],
|
|
[
|
|
CheckBox(),
|
|
],
|
|
]
|
|
|
|
|
|
def test_chunk_by_title():
|
|
elements: List[Element] = [
|
|
Title("A Great Day", metadata=ElementMetadata(emphasized_text_contents=["Day"])),
|
|
Text("Today is a great day.", metadata=ElementMetadata(emphasized_text_contents=["day"])),
|
|
Text("It is sunny outside."),
|
|
Table("<table></table>"),
|
|
Title("An Okay Day"),
|
|
Text("Today is an okay day."),
|
|
Text("It is rainy outside."),
|
|
Title("A Bad Day"),
|
|
Text(
|
|
"Today is a bad day.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"a": [RegexMetadata(text="A", start=0, end=1)]},
|
|
),
|
|
),
|
|
Text("It is storming outside."),
|
|
CheckBox(),
|
|
]
|
|
chunks = chunk_by_title(elements, combine_text_under_n_chars=0)
|
|
|
|
assert chunks == [
|
|
CompositeElement(
|
|
"A Great Day\n\nToday is a great day.\n\nIt is sunny outside.",
|
|
),
|
|
Table("<table></table>"),
|
|
CompositeElement("An Okay Day\n\nToday is an okay day.\n\nIt is rainy outside."),
|
|
CompositeElement(
|
|
"A Bad Day\n\nToday is a bad day.\n\nIt is storming outside.",
|
|
),
|
|
CheckBox(),
|
|
]
|
|
|
|
assert chunks[0].metadata == ElementMetadata(emphasized_text_contents=["Day", "day"])
|
|
assert chunks[3].metadata == ElementMetadata(
|
|
regex_metadata={"a": [RegexMetadata(text="A", start=11, end=12)]},
|
|
)
|
|
|
|
|
|
def test_chunk_by_title_respects_section_change():
|
|
elements: List[Element] = [
|
|
Title("A Great Day", metadata=ElementMetadata(section="first")),
|
|
Text("Today is a great day.", metadata=ElementMetadata(section="second")),
|
|
Text("It is sunny outside.", metadata=ElementMetadata(section="second")),
|
|
Table("<table></table>"),
|
|
Title("An Okay Day"),
|
|
Text("Today is an okay day."),
|
|
Text("It is rainy outside."),
|
|
Title("A Bad Day"),
|
|
Text(
|
|
"Today is a bad day.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"a": [RegexMetadata(text="A", start=0, end=1)]},
|
|
),
|
|
),
|
|
Text("It is storming outside."),
|
|
CheckBox(),
|
|
]
|
|
chunks = chunk_by_title(elements, combine_text_under_n_chars=0)
|
|
|
|
assert chunks == [
|
|
CompositeElement(
|
|
"A Great Day",
|
|
),
|
|
CompositeElement(
|
|
"Today is a great day.\n\nIt is sunny outside.",
|
|
),
|
|
Table("<table></table>"),
|
|
CompositeElement("An Okay Day\n\nToday is an okay day.\n\nIt is rainy outside."),
|
|
CompositeElement(
|
|
"A Bad Day\n\nToday is a bad day.\n\nIt is storming outside.",
|
|
),
|
|
CheckBox(),
|
|
]
|
|
|
|
|
|
def test_chunk_by_title_separates_by_page_number():
|
|
elements: List[Element] = [
|
|
Title("A Great Day", metadata=ElementMetadata(page_number=1)),
|
|
Text("Today is a great day.", metadata=ElementMetadata(page_number=2)),
|
|
Text("It is sunny outside.", metadata=ElementMetadata(page_number=2)),
|
|
Table("<table></table>"),
|
|
Title("An Okay Day"),
|
|
Text("Today is an okay day."),
|
|
Text("It is rainy outside."),
|
|
Title("A Bad Day"),
|
|
Text(
|
|
"Today is a bad day.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"a": [RegexMetadata(text="A", start=0, end=1)]},
|
|
),
|
|
),
|
|
Text("It is storming outside."),
|
|
CheckBox(),
|
|
]
|
|
chunks = chunk_by_title(elements, multipage_sections=False, combine_text_under_n_chars=0)
|
|
|
|
assert chunks == [
|
|
CompositeElement(
|
|
"A Great Day",
|
|
),
|
|
CompositeElement(
|
|
"Today is a great day.\n\nIt is sunny outside.",
|
|
),
|
|
Table("<table></table>"),
|
|
CompositeElement("An Okay Day\n\nToday is an okay day.\n\nIt is rainy outside."),
|
|
CompositeElement(
|
|
"A Bad Day\n\nToday is a bad day.\n\nIt is storming outside.",
|
|
),
|
|
CheckBox(),
|
|
]
|
|
|
|
|
|
def test_chunk_by_title_does_not_break_on_regex_metadata_change():
|
|
"""Sectioner is insensitive to regex-metadata changes.
|
|
|
|
A regex-metadata match in an element does not signify a semantic boundary and a section should
|
|
not be split based on such a difference.
|
|
"""
|
|
elements: List[Element] = [
|
|
Title(
|
|
"Lorem Ipsum",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"ipsum": [RegexMetadata(text="Ipsum", start=6, end=11)]},
|
|
),
|
|
),
|
|
Text(
|
|
"Lorem ipsum dolor sit amet consectetur adipiscing elit.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"dolor": [RegexMetadata(text="dolor", start=12, end=17)]},
|
|
),
|
|
),
|
|
Text(
|
|
"In rhoncus ipsum sed lectus porta volutpat.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"ipsum": [RegexMetadata(text="ipsum", start=11, end=16)]},
|
|
),
|
|
),
|
|
]
|
|
|
|
chunks = chunk_by_title(elements)
|
|
|
|
assert chunks == [
|
|
CompositeElement(
|
|
"Lorem Ipsum\n\nLorem ipsum dolor sit amet consectetur adipiscing elit.\n\nIn rhoncus"
|
|
" ipsum sed lectus porta volutpat.",
|
|
),
|
|
]
|
|
|
|
|
|
def test_chunk_by_title_consolidates_and_adjusts_offsets_of_regex_metadata():
|
|
"""ElementMetadata.regex_metadata of chunk is union of regex_metadatas of its elements.
|
|
|
|
The `start` and `end` offsets of each regex-match are adjusted to reflect their new position in
|
|
the chunk after element text has been concatenated.
|
|
"""
|
|
elements: List[Element] = [
|
|
Title(
|
|
"Lorem Ipsum",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"ipsum": [RegexMetadata(text="Ipsum", start=6, end=11)]},
|
|
),
|
|
),
|
|
Text(
|
|
"Lorem ipsum dolor sit amet consectetur adipiscing elit.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={
|
|
"dolor": [RegexMetadata(text="dolor", start=12, end=17)],
|
|
"ipsum": [RegexMetadata(text="ipsum", start=6, end=11)],
|
|
},
|
|
),
|
|
),
|
|
Text(
|
|
"In rhoncus ipsum sed lectus porta volutpat.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"ipsum": [RegexMetadata(text="ipsum", start=11, end=16)]},
|
|
),
|
|
),
|
|
]
|
|
chunks = chunk_by_title(elements)
|
|
|
|
assert len(chunks) == 1
|
|
chunk = chunks[0]
|
|
assert chunk == CompositeElement(
|
|
"Lorem Ipsum\n\nLorem ipsum dolor sit amet consectetur adipiscing elit.\n\nIn rhoncus"
|
|
" ipsum sed lectus porta volutpat.",
|
|
)
|
|
assert chunk.metadata.regex_metadata == {
|
|
"dolor": [RegexMetadata(text="dolor", start=25, end=30)],
|
|
"ipsum": [
|
|
RegexMetadata(text="Ipsum", start=6, end=11),
|
|
RegexMetadata(text="ipsum", start=19, end=24),
|
|
RegexMetadata(text="ipsum", start=81, end=86),
|
|
],
|
|
}
|
|
|
|
|
|
def test_chunk_by_title_groups_across_pages():
|
|
elements: List[Element] = [
|
|
Title("A Great Day", metadata=ElementMetadata(page_number=1)),
|
|
Text("Today is a great day.", metadata=ElementMetadata(page_number=2)),
|
|
Text("It is sunny outside.", metadata=ElementMetadata(page_number=2)),
|
|
Table("<table></table>"),
|
|
Title("An Okay Day"),
|
|
Text("Today is an okay day."),
|
|
Text("It is rainy outside."),
|
|
Title("A Bad Day"),
|
|
Text(
|
|
"Today is a bad day.",
|
|
metadata=ElementMetadata(
|
|
regex_metadata={"a": [RegexMetadata(text="A", start=0, end=1)]},
|
|
),
|
|
),
|
|
Text("It is storming outside."),
|
|
CheckBox(),
|
|
]
|
|
chunks = chunk_by_title(elements, multipage_sections=True, combine_text_under_n_chars=0)
|
|
|
|
assert chunks == [
|
|
CompositeElement(
|
|
"A Great Day\n\nToday is a great day.\n\nIt is sunny outside.",
|
|
),
|
|
Table("<table></table>"),
|
|
CompositeElement("An Okay Day\n\nToday is an okay day.\n\nIt is rainy outside."),
|
|
CompositeElement(
|
|
"A Bad Day\n\nToday is a bad day.\n\nIt is storming outside.",
|
|
),
|
|
CheckBox(),
|
|
]
|
|
|
|
|
|
def test_add_chunking_strategy_on_partition_html():
|
|
filename = "example-docs/example-10k-1p.html"
|
|
chunk_elements = partition_html(filename, chunking_strategy="by_title")
|
|
elements = partition_html(filename)
|
|
chunks = chunk_by_title(elements)
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|
|
|
|
|
|
def test_add_chunking_strategy_respects_max_characters():
|
|
filename = "example-docs/example-10k-1p.html"
|
|
chunk_elements = partition_html(
|
|
filename,
|
|
chunking_strategy="by_title",
|
|
combine_text_under_n_chars=0,
|
|
new_after_n_chars=50,
|
|
max_characters=100,
|
|
)
|
|
elements = partition_html(filename)
|
|
chunks = chunk_by_title(
|
|
elements,
|
|
combine_text_under_n_chars=0,
|
|
new_after_n_chars=50,
|
|
max_characters=100,
|
|
)
|
|
|
|
for chunk in chunks:
|
|
assert isinstance(chunk, Text)
|
|
assert len(chunk.text) <= 100
|
|
for chunk_element in chunk_elements:
|
|
assert isinstance(chunk_element, Text)
|
|
assert len(chunk_element.text) <= 100
|
|
assert chunk_elements != elements
|
|
assert chunk_elements == chunks
|
|
|
|
|
|
def test_add_chunking_strategy_on_partition_html_respects_multipage():
|
|
filename = "example-docs/example-10k-1p.html"
|
|
partitioned_elements_multipage_false_combine_chars_0 = partition_html(
|
|
filename,
|
|
chunking_strategy="by_title",
|
|
multipage_sections=False,
|
|
combine_text_under_n_chars=0,
|
|
new_after_n_chars=300,
|
|
max_characters=400,
|
|
)
|
|
partitioned_elements_multipage_true_combine_chars_0 = partition_html(
|
|
filename,
|
|
chunking_strategy="by_title",
|
|
multipage_sections=True,
|
|
combine_text_under_n_chars=0,
|
|
new_after_n_chars=300,
|
|
max_characters=400,
|
|
)
|
|
elements = partition_html(filename)
|
|
cleaned_elements_multipage_false_combine_chars_0 = chunk_by_title(
|
|
elements,
|
|
multipage_sections=False,
|
|
combine_text_under_n_chars=0,
|
|
new_after_n_chars=300,
|
|
max_characters=400,
|
|
)
|
|
cleaned_elements_multipage_true_combine_chars_0 = chunk_by_title(
|
|
elements,
|
|
multipage_sections=True,
|
|
combine_text_under_n_chars=0,
|
|
new_after_n_chars=300,
|
|
max_characters=400,
|
|
)
|
|
assert (
|
|
partitioned_elements_multipage_false_combine_chars_0
|
|
== cleaned_elements_multipage_false_combine_chars_0
|
|
)
|
|
assert (
|
|
partitioned_elements_multipage_true_combine_chars_0
|
|
== cleaned_elements_multipage_true_combine_chars_0
|
|
)
|
|
assert len(partitioned_elements_multipage_true_combine_chars_0) != len(
|
|
partitioned_elements_multipage_false_combine_chars_0,
|
|
)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("combine_text_under_n_chars", "new_after_n_chars", "max_characters"),
|
|
[
|
|
(-1, -1, -1), # invalid chunk size
|
|
(0, 0, 0), # invalid max_characters
|
|
(-5666, -6777, -8999), # invalid chunk size
|
|
(-5, 40, 50), # invalid chunk size
|
|
(50, 70, 20), # max_characters needs to be greater than new_after_n_chars
|
|
(70, 50, 50), # combine_text_under_n_chars needs to be les than new_after_n_chars
|
|
],
|
|
)
|
|
def test_add_chunking_strategy_raises_error_for_invalid_n_chars(
|
|
combine_text_under_n_chars: int,
|
|
new_after_n_chars: int,
|
|
max_characters: int,
|
|
):
|
|
elements: List[Element] = [
|
|
Title("A Great Day"),
|
|
Text("Today is a great day."),
|
|
Text("It is sunny outside."),
|
|
Table("<table></table>"),
|
|
Title("An Okay Day"),
|
|
Text("Today is an okay day."),
|
|
Text("It is rainy outside."),
|
|
Title("A Bad Day"),
|
|
Text("It is storming outside."),
|
|
CheckBox(),
|
|
]
|
|
with pytest.raises(ValueError):
|
|
chunk_by_title(
|
|
elements,
|
|
combine_text_under_n_chars=combine_text_under_n_chars,
|
|
new_after_n_chars=new_after_n_chars,
|
|
max_characters=max_characters,
|
|
)
|
|
|
|
|
|
def test_chunk_by_title_drops_detection_class_prob():
|
|
elements: List[Element] = [
|
|
Title(
|
|
"A Great Day",
|
|
metadata=ElementMetadata(
|
|
detection_class_prob=0.5,
|
|
),
|
|
),
|
|
Text(
|
|
"Today is a great day.",
|
|
metadata=ElementMetadata(
|
|
detection_class_prob=0.62,
|
|
),
|
|
),
|
|
Text(
|
|
"It is sunny outside.",
|
|
metadata=ElementMetadata(
|
|
detection_class_prob=0.73,
|
|
),
|
|
),
|
|
Title(
|
|
"An Okay Day",
|
|
metadata=ElementMetadata(
|
|
detection_class_prob=0.84,
|
|
),
|
|
),
|
|
Text(
|
|
"Today is an okay day.",
|
|
metadata=ElementMetadata(
|
|
detection_class_prob=0.95,
|
|
),
|
|
),
|
|
]
|
|
chunks = chunk_by_title(elements, combine_text_under_n_chars=0)
|
|
assert str(chunks[0]) == str(
|
|
CompositeElement("A Great Day\n\nToday is a great day.\n\nIt is sunny outside."),
|
|
)
|
|
assert str(chunks[1]) == str(CompositeElement("An Okay Day\n\nToday is an okay day."))
|
|
|
|
|
|
def test_chunk_by_title_drops_extra_metadata():
|
|
elements: List[Element] = [
|
|
Title(
|
|
"A Great Day",
|
|
metadata=ElementMetadata(
|
|
coordinates=CoordinatesMetadata(
|
|
points=(
|
|
(0.1, 0.1),
|
|
(0.2, 0.1),
|
|
(0.1, 0.2),
|
|
(0.2, 0.2),
|
|
),
|
|
system=CoordinateSystem(width=0.1, height=0.1),
|
|
),
|
|
),
|
|
),
|
|
Text(
|
|
"Today is a great day.",
|
|
metadata=ElementMetadata(
|
|
coordinates=CoordinatesMetadata(
|
|
points=(
|
|
(0.2, 0.2),
|
|
(0.3, 0.2),
|
|
(0.2, 0.3),
|
|
(0.3, 0.3),
|
|
),
|
|
system=CoordinateSystem(width=0.2, height=0.2),
|
|
),
|
|
),
|
|
),
|
|
Text(
|
|
"It is sunny outside.",
|
|
metadata=ElementMetadata(
|
|
coordinates=CoordinatesMetadata(
|
|
points=(
|
|
(0.3, 0.3),
|
|
(0.4, 0.3),
|
|
(0.3, 0.4),
|
|
(0.4, 0.4),
|
|
),
|
|
system=CoordinateSystem(width=0.3, height=0.3),
|
|
),
|
|
),
|
|
),
|
|
Title(
|
|
"An Okay Day",
|
|
metadata=ElementMetadata(
|
|
coordinates=CoordinatesMetadata(
|
|
points=(
|
|
(0.3, 0.3),
|
|
(0.4, 0.3),
|
|
(0.3, 0.4),
|
|
(0.4, 0.4),
|
|
),
|
|
system=CoordinateSystem(width=0.3, height=0.3),
|
|
),
|
|
),
|
|
),
|
|
Text(
|
|
"Today is an okay day.",
|
|
metadata=ElementMetadata(
|
|
coordinates=CoordinatesMetadata(
|
|
points=(
|
|
(0.4, 0.4),
|
|
(0.5, 0.4),
|
|
(0.4, 0.5),
|
|
(0.5, 0.5),
|
|
),
|
|
system=CoordinateSystem(width=0.4, height=0.4),
|
|
),
|
|
),
|
|
),
|
|
]
|
|
|
|
chunks = chunk_by_title(elements, combine_text_under_n_chars=0)
|
|
|
|
assert str(chunks[0]) == str(
|
|
CompositeElement("A Great Day\n\nToday is a great day.\n\nIt is sunny outside."),
|
|
)
|
|
|
|
assert str(chunks[1]) == str(CompositeElement("An Okay Day\n\nToday is an okay day."))
|