mirror of
https://github.com/Unstructured-IO/unstructured.git
synced 2025-09-01 04:43:59 +00:00
82c8adba3f
**Executive Summary.** Code inspection in preparation for adding the
chunk-overlap feature revealed a bug causing split-chunks to be inserted
out-of-order. For example, elements like this:
```
Text("One" + 400 chars)
Text("Two" + 400 chars)
Text("Three" + 600 chars)
Text("Four" + 400 chars)
Text("Five" + 600 chars)
```
Should produce chunks:
```
CompositeElement("One ...") # (400 chars)
CompositeElement("Two ...") # (400 chars)
CompositeElement("Three ...") # (500 chars)
CompositeElement("rest of Three ...") # (100 chars)
CompositeElement("Four") # (400 chars)
CompositeElement("Five ...") # (500 chars)
CompositeElement("rest of Five ...") # (100 chars)
```
but produced this instead:
```
CompositeElement("Five ...") # (500 chars)
CompositeElement("rest of Five ...") # (100 chars)
CompositeElement("Three ...") # (500 chars)
CompositeElement("rest of Three ...") # (100 chars)
CompositeElement("One ...") # (400 chars)
CompositeElement("Two ...") # (400 chars)
CompositeElement("Four") # (400 chars)
```
This PR fixes that behavior that was introduced on Oct 9 this year in
commit: f98d5e65 when adding chunk splitting.
**Technical Summary**
The essential transformation of chunking is:
```
elements sections chunks
List[Element] -> List[List[Element]] -> List[CompositeElement]
```
1. The _sectioner_ (`_split_elements_by_title_and_table()`) _groups_
semantically-related elements into _sections_ (`List[Element]`), in the
best case, that would be a title (heading) and the text that follows it
(until the next title). A heading and its text is often referred to as a
_section_ in publishing parlance, hence the name.
2. The _chunker_ (`chunk_by_title()` currently) does two things:
1. first it _consolidates_ the elements of each section into a single
`ConsolidatedElement` object (a "chunk"). This includes both joining the
element text into a single string as well as consolidating the metadata
of the section elements.
2. then if necessary it _splits_ the chunk into two or more
`ConsolidatedElement` objects when the consolidated text is too long to
fit in the specified window (`max_characters`).
Chunk splitting is only required when a single element (like a big
paragraph) has text longer than the specified window. Otherwise a
section and the chunk that derives from it reflects an even element
boundary.
`chunk_by_title()` was elaborated in commit f98d5e65 to add this
"chunk-splitting" behavior.
At the time there was some notion of wanting to "split from the end
backward" such that any small remainder chunk would appear first, and
could possibly be combined with a small prior chunk. To accomplish this,
split chunks were _inserted_ at the beginning of the list instead of
_appended_ to the end.
The `chunked_elements` variable (`List[CompositeElement]`) holds the
sequence of chunks that result from the chunking operation and is the
returned value for `chunk_by_title()`. This was the list
"split-from-the-end" chunks were inserted at the beginning of and that
unfortunately produces this out-of-order behavior because the insertion
was at the beginning of this "all-chunks-in-document" list, not a
sublist just for this chunk.
Further, the "split-from-the-end" behavior can produce no benefit
because chunks are never combined, only _elements_ are combined (across
semantic boundaries into a single section when a section is small) and
sectioning occurs _prior_ to chunking.
The fix is to rework the chunk-splitting passage to a straighforward
iterative algorithm that works both when a chunk must be split and when
it doesn't. This algorithm is also very easily extended to implement
split-chunk-overlap which is coming up in an immediately following PR.
```python
# -- split chunk into CompositeElements objects maxlen or smaller --
text_len = len(text)
start = 0
remaining = text_len
while remaining > 0:
end = min(start + max_characters, text_len)
chunked_elements.append(CompositeElement(text=text[start:end], metadata=chunk_meta))
start = end - overlap
remaining = text_len - end
```
*Forensic analysis*
The out-of-order-chunks behavior was introduced in commit 4ea71683 on
10/09/2023 in the same PR in which chunk-splitting was introduced.
---------
Co-authored-by: Shreya Nidadavolu <shreyanid9@gmail.com>
Co-authored-by: shreyanid <42684285+shreyanid@users.noreply.github.com>
556 lines
18 KiB
Python
556 lines
18 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_it_splits_a_large_section_into_multiple_chunks():
|
|
elements: List[Element] = [
|
|
Title("Introduction"),
|
|
Text(
|
|
"Lorem ipsum dolor sit amet consectetur adipiscing elit. In rhoncus ipsum sed lectus"
|
|
" porta volutpat."
|
|
),
|
|
]
|
|
|
|
chunks = chunk_by_title(elements, combine_text_under_n_chars=50, max_characters=50)
|
|
|
|
assert chunks == [
|
|
CompositeElement("Introduction"),
|
|
CompositeElement("Lorem ipsum dolor sit amet consectetur adipiscing "),
|
|
CompositeElement("elit. In rhoncus ipsum sed lectus porta volutpat."),
|
|
]
|
|
|
|
|
|
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."))
|