Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

refactor: partition_pdf() pass kwargs through fast strategy pipeline #3040

Merged
merged 11 commits into from
May 17, 2024
Merged

refactor: partition_pdf() pass kwargs through fast strategy pipeline #3040

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
7e087d0
feat: pass `kwargs` through `fast` strategy pipeline
christinestraub May 16, 2024
431d067
Merge branch 'main' into refactor/pdf-pass-kwargs-fast-strategy-pipeline
christinestraub May 16, 2024
84f814e
refactor: reorganization
christinestraub May 16, 2024
5dd0aee
chore: bump version
christinestraub May 16, 2024
9c844e8
fix: pass `kwargs` through `fast` strategy pipeline
christinestraub May 16, 2024
9e6393a
test: update unit tests
christinestraub May 16, 2024
cbecbc5
Merge branch 'main' into refactor/pdf-pass-kwargs-fast-strategy-pipeline
christinestraub May 16, 2024
c1ea7fc
Merge branch 'main' into refactor/pdf-pass-kwargs-fast-strategy-pipeline
christinestraub May 17, 2024
bbef2ba
Merge branch 'main' into refactor/pdf-pass-kwargs-fast-strategy-pipeline
christinestraub May 17, 2024
e2df3aa
Merge branch 'main' into refactor/pdf-pass-kwargs-fast-strategy-pipeline
christinestraub May 17, 2024
ec505e6
Merge branch 'main' into refactor/pdf-pass-kwargs-fast-strategy-pipeline
christinestraub May 17, 2024
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
2 changes: 1 addition & 1 deletion CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
## 0.13.8-dev15
## 0.13.8

### Enhancements

Expand Down
20 changes: 10 additions & 10 deletions test_unstructured/partition/pdf_image/test_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -326,7 +326,7 @@ def test_partition_image_metadata_date(
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf.get_last_modified_date",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
return_value=mocked_last_modification_date,
)
elements = image.partition_image(filename=filename)
Expand All @@ -340,7 +340,7 @@ def test_partition_image_with_hi_res_strategy_metadata_date(
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf.get_last_modified_date",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
return_value=mocked_last_modification_date,
)
elements = image.partition_image(filename=filename, strategy=PartitionStrategy.HI_RES)
Expand All @@ -356,7 +356,7 @@ def test_partition_image_metadata_date_custom_metadata_date(
expected_last_modification_date = "2009-07-05T09:24:28"

mocker.patch(
"unstructured.partition.pdf.get_last_modified_date",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
return_value=mocked_last_modification_date,
)
elements = image.partition_image(
Expand All @@ -375,7 +375,7 @@ def test_partition_image_with_hi_res_strategy_metadata_date_custom_metadata_date
expected_last_modification_date = "2009-07-05T09:24:28"

mocker.patch(
"unstructured.partition.pdf.get_last_modified_date",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
return_value=mocked_last_modification_date,
)
elements = image.partition_image(
Expand All @@ -393,7 +393,7 @@ def test_partition_image_from_file_metadata_date(
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf.get_last_modified_date_from_file",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
Expand All @@ -408,7 +408,7 @@ def test_partition_image_from_file_explicit_get_metadata_date(
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf.get_last_modified_date_from_file",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
Expand All @@ -423,7 +423,7 @@ def test_partition_image_from_file_with_hi_res_strategy_metadata_date(
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf.get_last_modified_date_from_file",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
return_value=mocked_last_modification_date,
)

Expand All @@ -439,7 +439,7 @@ def test_partition_image_from_file_with_hi_res_strategy_explicit_get_metadata_da
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf.get_last_modified_date_from_file",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
return_value=mocked_last_modification_date,
)

Expand All @@ -459,7 +459,7 @@ def test_partition_image_from_file_metadata_date_custom_metadata_date(
expected_last_modification_date = "2009-07-05T09:24:28"

mocker.patch(
"unstructured.partition.pdf.get_last_modified_date_from_file",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
Expand All @@ -479,7 +479,7 @@ def test_partition_image_from_file_with_hi_res_strategy_metadata_date_custom_met
expected_last_modification_date = "2009-07-05T09:24:28"

mocker.patch(
"unstructured.partition.pdf.get_last_modified_date_from_file",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
Expand Down
4 changes: 2 additions & 2 deletions test_unstructured/partition/pdf_image/test_pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -715,11 +715,11 @@ def test_partition_pdf_metadata_date(
expected_last_modification_date = None

mocker.patch(
"unstructured.partition.pdf.get_last_modified_date_from_file",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
return_value=mocked_last_modification_date,
)
mocker.patch(
"unstructured.partition.pdf.get_last_modified_date",
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
return_value=mocked_last_modification_date,
)

Expand Down
2 changes: 1 addition & 1 deletion unstructured/__version__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
__version__ = "0.13.8-dev15" # pragma: no cover
__version__ = "0.13.8" # pragma: no cover
Loading
Loading