776 lines
25 KiB
Python
Raw Permalink Normal View History

from __future__ import annotations
import os
import pathlib
import tempfile
from unittest import mock
import pytest
from PIL import Image
from pytesseract import TesseractError
from unstructured_inference.inference import layout
from test_unstructured.partition.pdf_image.test_pdf import assert_element_extraction
from test_unstructured.unit_utils import assert_round_trips_through_JSON, example_doc_path
from unstructured.chunking.title import chunk_by_title
from unstructured.documents.elements import ElementType
from unstructured.partition import image, pdf
from unstructured.partition.pdf_image import ocr
from unstructured.partition.utils.constants import (
UNSTRUCTURED_INCLUDE_DEBUG_METADATA,
PartitionStrategy,
)
from unstructured.utils import only
DIRECTORY = pathlib.Path(__file__).parent.resolve()
class MockResponse:
def __init__(self, status_code, response):
self.status_code = status_code
self.response = response
def json(self):
return self.response
def mock_healthy_get(url, **kwargs):
return MockResponse(status_code=200, response={})
def mock_unhealthy_get(url, **kwargs):
return MockResponse(status_code=500, response={})
def mock_unsuccessful_post(url, **kwargs):
return MockResponse(status_code=500, response={})
def mock_successful_post(url, **kwargs):
response = {
"pages": [
{
"number": 0,
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
"elements": [
{"type": "Title", "text": "Charlie Brown and the Great Pumpkin"},
],
},
{
"number": 1,
"elements": [{"type": "Title", "text": "A Charlie Brown Christmas"}],
},
],
}
return MockResponse(status_code=200, response=response)
class MockPageLayout(layout.PageLayout):
def __init__(self, number: int, image: Image):
self.number = number
self.image = image
self.elements = [
chore: process chipper hierarchy (#1634) PR to support schema changes introduced from [PR 232](https://github.com/Unstructured-IO/unstructured-inference/pull/232) in `unstructured-inference`. Specifically what needs to be supported is: * Change to the way `LayoutElement` from `unstructured-inference` is structured, specifically that this class is no longer a subclass of `Rectangle`, and instead `LayoutElement` has a `bbox` property that captures the location information and a `from_coords` method that allows construction of a `LayoutElement` directly from coordinates. * Removal of `LocationlessLayoutElement` since chipper now exports bounding boxes, and if we need to support elements without bounding boxes, we can make the `bbox` property mentioned above optional. * Getting hierarchy data directly from the inference elements rather than in post-processing * Don't try to reorder elements received from chipper v2, as they should already be ordered. #### Testing: The following demonstrates that the new version of chipper is inferring hierarchy. ```python from unstructured.partition.pdf import partition_pdf elements = partition_pdf("example-docs/layout-parser-paper-fast.pdf", strategy="hi_res", model_name="chipper") children = [el for el in elements if el.metadata.parent_id is not None] print(children) ``` Also verify that running the traditional `hi_res` gives different results: ```python from unstructured.partition.pdf import partition_pdf elements = partition_pdf("example-docs/layout-parser-paper-fast.pdf", strategy="hi_res") ``` --------- Co-authored-by: Sebastian Laverde Alfonso <lavmlk20201@gmail.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com>
2023-10-12 20:28:46 -05:00
layout.LayoutElement.from_coords(
type="Title",
2023-04-04 19:59:06 -07:00
x1=0,
y1=0,
x2=2,
y2=2,
text="Charlie Brown and the Great Pumpkin",
),
]
class MockDocumentLayout(layout.DocumentLayout):
@property
def pages(self):
return [
MockPageLayout(number=0, image=Image.new("1", (1, 1))),
]
@pytest.mark.parametrize(
("filename", "file"),
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
[
("example-docs/example.jpg", None),
(None, b"0000"),
],
)
def test_partition_image_local(monkeypatch, filename, file):
monkeypatch.setattr(
layout,
"process_data_with_model",
lambda *args, **kwargs: MockDocumentLayout(),
)
monkeypatch.setattr(
layout,
"process_file_with_model",
lambda *args, **kwargs: MockDocumentLayout(),
)
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
monkeypatch.setattr(
ocr,
"process_data_with_ocr",
lambda *args, **kwargs: MockDocumentLayout(),
)
monkeypatch.setattr(
ocr,
"process_data_with_ocr",
lambda *args, **kwargs: MockDocumentLayout(),
)
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
partition_image_response = pdf._partition_pdf_or_image_local(
filename,
file,
is_image=True,
)
assert partition_image_response[0].text == "Charlie Brown and the Great Pumpkin"
@pytest.mark.skip("Needs to be fixed upstream in unstructured-inference")
def test_partition_image_local_raises_with_no_filename():
with pytest.raises(FileNotFoundError):
pdf._partition_pdf_or_image_local(filename="", file=None, is_image=True)
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_with_auto_strategy(
filename="example-docs/layout-parser-paper-fast.jpg",
):
elements = image.partition_image(filename=filename, strategy=PartitionStrategy.AUTO)
titles = [
el for el in elements if el.category == ElementType.TITLE and len(el.text.split(" ")) > 10
]
title = "LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis"
Chore (refactor): support table extraction with pre-computed ocr data (#1801) ### 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>
2023-10-20 20:24:23 -04:00
idx = 3
assert titles[0].text == title
assert elements[idx].metadata.detection_class_prob is not None
assert isinstance(elements[idx].metadata.detection_class_prob, float)
def test_partition_image_with_table_extraction(
filename="example-docs/layout-parser-paper-with-table.jpg",
):
elements = image.partition_image(
filename=filename,
strategy=PartitionStrategy.HI_RES,
infer_table_structure=True,
)
table = [el.metadata.text_as_html for el in elements if el.metadata.text_as_html]
assert len(table) == 1
assert "<table><thead><tr>" in table[0]
assert "</thead><tbody><tr>" in table[0]
def test_partition_image_with_multipage_tiff(
filename="example-docs/layout-parser-paper-combined.tiff",
):
elements = image.partition_image(filename=filename, strategy=PartitionStrategy.AUTO)
assert elements[-1].metadata.page_number == 2
def test_partition_image_with_bmp(
tmpdir,
filename="example-docs/layout-parser-paper-with-table.jpg",
):
bmp_filename = os.path.join(tmpdir.dirname, "example.bmp")
img = Image.open(filename)
img.save(bmp_filename)
elements = image.partition_image(
filename=bmp_filename,
strategy=PartitionStrategy.HI_RES,
infer_table_structure=True,
)
table = [el.metadata.text_as_html for el in elements if el.metadata.text_as_html]
assert len(table) == 1
assert "<table><thead><tr>" in table[0]
assert "</thead><tbody><tr>" in table[0]
def test_partition_image_with_language_passed(filename="example-docs/example.jpg"):
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
with mock.patch.object(
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
ocr,
"process_file_with_ocr",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
mock.MagicMock(),
) as mock_partition:
image.partition_image(
filename=filename,
strategy=PartitionStrategy.HI_RES,
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
ocr_languages="eng+swe",
)
assert mock_partition.call_args.kwargs.get("ocr_languages") == "eng+swe"
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_from_file_with_language_passed(
filename="example-docs/example.jpg",
):
with mock.patch.object(
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
ocr,
"process_data_with_ocr",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
mock.MagicMock(),
) as mock_partition, open(filename, "rb") as f:
image.partition_image(file=f, strategy=PartitionStrategy.HI_RES, ocr_languages="eng+swe")
assert mock_partition.call_args.kwargs.get("ocr_languages") == "eng+swe"
# NOTE(crag): see https://github.com/Unstructured-IO/unstructured/issues/1086
@pytest.mark.skip(reason="Current catching too many tesseract errors")
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_raises_with_invalid_language(
filename="example-docs/example.jpg",
):
with pytest.raises(TesseractError):
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
image.partition_image(
filename=filename,
strategy=PartitionStrategy.HI_RES,
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
ocr_languages="fakeroo",
)
Jj/2011 missing languages metadata (#2037) ### Summary Closes #2011 `languages` was missing from the metadata when partitioning pdfs via `hi_res` and `fast` strategies and missing from image partitions via `hi_res`. This PR adds `languages` to the relevant function calls so it is included in the resulting elements. ### Testing On the main branch, `partition_image` will include `languages` when `strategy='ocr_only'`, but not when `strategy='hi_res'`: ``` filename = "example-docs/english-and-korean.png" from unstructured.partition.image import partition_image elements = partition_image(filename, strategy="ocr_only", languages=['eng', 'kor']) elements[0].metadata.languages elements = partition_image(filename, strategy="hi_res", languages=['eng', 'kor']) elements[0].metadata.languages ``` For `partition_pdf`, `'ocr_only'` will include `languages` in the metadata, but `'fast'` and `'hi_res'` will not. ``` filename = "example-docs/korean-text-with-tables.pdf" from unstructured.partition.pdf import partition_pdf elements = partition_pdf(filename, strategy="ocr_only", languages=['kor']) elements[0].metadata.languages elements = partition_pdf(filename, strategy="fast", languages=['kor']) elements[0].metadata.languages elements = partition_pdf(filename, strategy="hi_res", languages=['kor']) elements[0].metadata.languages ``` On this branch, `languages` is included in the metadata regardless of strategy --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: Coniferish <Coniferish@users.noreply.github.com>
2023-11-13 10:47:05 -06:00
@pytest.mark.parametrize(
("strategy"),
[
(PartitionStrategy.HI_RES),
(PartitionStrategy.OCR_ONLY),
Jj/2011 missing languages metadata (#2037) ### Summary Closes #2011 `languages` was missing from the metadata when partitioning pdfs via `hi_res` and `fast` strategies and missing from image partitions via `hi_res`. This PR adds `languages` to the relevant function calls so it is included in the resulting elements. ### Testing On the main branch, `partition_image` will include `languages` when `strategy='ocr_only'`, but not when `strategy='hi_res'`: ``` filename = "example-docs/english-and-korean.png" from unstructured.partition.image import partition_image elements = partition_image(filename, strategy="ocr_only", languages=['eng', 'kor']) elements[0].metadata.languages elements = partition_image(filename, strategy="hi_res", languages=['eng', 'kor']) elements[0].metadata.languages ``` For `partition_pdf`, `'ocr_only'` will include `languages` in the metadata, but `'fast'` and `'hi_res'` will not. ``` filename = "example-docs/korean-text-with-tables.pdf" from unstructured.partition.pdf import partition_pdf elements = partition_pdf(filename, strategy="ocr_only", languages=['kor']) elements[0].metadata.languages elements = partition_pdf(filename, strategy="fast", languages=['kor']) elements[0].metadata.languages elements = partition_pdf(filename, strategy="hi_res", languages=['kor']) elements[0].metadata.languages ``` On this branch, `languages` is included in the metadata regardless of strategy --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: Coniferish <Coniferish@users.noreply.github.com>
2023-11-13 10:47:05 -06:00
],
)
def test_partition_image_strategies_keep_languages_metadata(strategy):
filename = os.path.join(
DIRECTORY,
"..",
"..",
"..",
"example-docs",
"english-and-korean.png",
)
elements = image.partition_image(
filename=filename,
languages=["eng", "kor"],
strategy=strategy,
)
assert elements[0].metadata.languages == ["eng", "kor"]
def test_partition_image_with_ocr_detects_korean():
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
filename = os.path.join(
DIRECTORY,
"..",
"..",
"..",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
"example-docs",
"english-and-korean.png",
)
elements = image.partition_image(
filename=filename,
ocr_languages="eng+kor",
strategy=PartitionStrategy.OCR_ONLY,
)
assert elements[0].text == "RULES AND INSTRUCTIONS"
assert elements[3].text.replace(" ", "").startswith("안녕하세요")
def test_partition_image_with_ocr_detects_korean_from_file():
filename = os.path.join(DIRECTORY, "..", "..", "..", "example-docs", "english-and-korean.png")
with open(filename, "rb") as f:
elements = image.partition_image(
file=f,
ocr_languages="eng+kor",
strategy=PartitionStrategy.OCR_ONLY,
)
assert elements[0].text == "RULES AND INSTRUCTIONS"
assert elements[3].text.replace(" ", "").startswith("안녕하세요")
def test_partition_image_raises_with_bad_strategy():
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
filename = os.path.join(
DIRECTORY,
"..",
"..",
"..",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
"example-docs",
"english-and-korean.png",
)
with pytest.raises(ValueError):
image.partition_image(filename=filename, strategy="fakeroo")
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_default_strategy_hi_res():
filename = os.path.join(
DIRECTORY,
"..",
"..",
"..",
"example-docs",
"layout-parser-paper-fast.jpg",
)
with open(filename, "rb") as f:
elements = image.partition_image(file=f)
title = "LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis"
idx = 2
assert elements[idx].text == title
assert elements[idx].metadata.coordinates is not None
assert elements[idx].metadata.detection_class_prob is not None
assert isinstance(elements[idx].metadata.detection_class_prob, float)
if UNSTRUCTURED_INCLUDE_DEBUG_METADATA:
# A bug in partition_groups_from_regions in unstructured-inference losses some sources
refactor: `partition_pdf()` for `ocr_only` strategy (#1811) ### Summary Update `ocr_only` strategy in `partition_pdf()`. This PR adds the functionality to get accurate coordinate data when partitioning PDFs and Images with the `ocr_only` strategy. - Add functionality to perform OCR region grouping based on the OCR text taken from `pytesseract.image_to_string()` - Add functionality to get layout elements from OCR regions (ocr_layout) for both `tesseract` and `paddle` - Add functionality to determine the `source` of merged text regions when merging text regions in `merge_text_regions()` - Merge multiple test functions related to "ocr_only" strategy into `test_partition_pdf_with_ocr_only_strategy()` - This PR also fixes [issue #1792](https://github.com/Unstructured-IO/unstructured/issues/1792) ### Evaluation ``` # Image PYTHONPATH=. python examples/custom-layout-order/evaluate_natural_reading_order.py example-docs/double-column-A.jpg ocr_only xy-cut image # PDF PYTHONPATH=. python examples/custom-layout-order/evaluate_natural_reading_order.py example-docs/multi-column-2p.pdf ocr_only xy-cut pdf ``` ### Test - **Before update** All elements have the same coordinate data ![multi-column-2p_1_xy-cut](https://github.com/Unstructured-IO/unstructured/assets/9475974/aae0195a-2943-4fa8-bdd8-807f2f09c768) - **After update** All elements have accurate coordinate data ![multi-column-2p_1_xy-cut](https://github.com/Unstructured-IO/unstructured/assets/9475974/0f6c6202-9e65-4acf-bcd4-ac9dd01ab64a) --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-30 13:13:29 -07:00
assert {element.metadata.detection_origin for element in elements} == {
"yolox",
"ocr_tesseract",
}
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
elements = image.partition_image(filename=filename)
assert elements[0].metadata.last_modified == mocked_last_modification_date
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_with_hi_res_strategy_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
elements = image.partition_image(filename=filename, strategy=PartitionStrategy.HI_RES)
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
assert elements[0].metadata.last_modified == mocked_last_modification_date
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_metadata_date_custom_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
expected_last_modification_date = "2009-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
elements = image.partition_image(
filename=filename,
metadata_last_modified=expected_last_modification_date,
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
)
assert elements[0].metadata.last_modified == expected_last_modification_date
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_with_hi_res_strategy_metadata_date_custom_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
expected_last_modification_date = "2009-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
elements = image.partition_image(
filename=filename,
strategy=PartitionStrategy.HI_RES,
metadata_last_modified=expected_last_modification_date,
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
)
assert elements[0].metadata.last_modified == expected_last_modification_date
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_from_file_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
elements = image.partition_image(file=f)
assert elements[0].metadata.last_modified is None
def test_partition_image_from_file_explicit_get_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"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:
elements = image.partition_image(file=f, date_from_file_object=True)
assert elements[0].metadata.last_modified == mocked_last_modification_date
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_from_file_with_hi_res_strategy_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
elements = image.partition_image(file=f, strategy=PartitionStrategy.HI_RES)
assert elements[0].metadata.last_modified is None
def test_partition_image_from_file_with_hi_res_strategy_explicit_get_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
mocker.patch(
"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:
elements = image.partition_image(
file=f, strategy=PartitionStrategy.HI_RES, date_from_file_object=True
)
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
assert elements[0].metadata.last_modified == mocked_last_modification_date
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_from_file_metadata_date_custom_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
expected_last_modification_date = "2009-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
elements = image.partition_image(
file=f,
metadata_last_modified=expected_last_modification_date,
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
)
assert elements[0].metadata.last_modified == expected_last_modification_date
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
def test_partition_image_from_file_with_hi_res_strategy_metadata_date_custom_metadata_date(
mocker,
filename="example-docs/english-and-korean.png",
):
mocked_last_modification_date = "2029-07-05T09:24:28"
expected_last_modification_date = "2009-07-05T09:24:28"
mocker.patch(
"unstructured.partition.pdf_image.pdf_image_utils.get_last_modified_date_from_file",
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
return_value=mocked_last_modification_date,
)
with open(filename, "rb") as f:
elements = image.partition_image(
file=f,
metadata_last_modified=expected_last_modification_date,
strategy=PartitionStrategy.HI_RES,
feat: add document date for remaining file types (#930) (#969) * feat: add document date for remaining file types (#930) * feat: add functions for getting modification date * feat: add date field to metadata from csv file * feat: add tests for csv patition * feat: add date field to metadata from html file * feat: add tests for html partition * fix: return file name onlyif possible * feat: add csv tests * fix: renaming * feat: add filed metadata_date as date of last mod * feat: add tests for partition_docx * feat: add filed metadata_date to .doc file * feat: add tests for partition_doc * feat: add metadata_date to .epub file * feat: add tests for partition_epub * fix: fix test mocking * feat: add metadata_date for image partition * feat: add test for image partition * feat: add coorrdinate system argument * feat: add date to element metadata * feat: add metadata_date for JSON partition * feat: add test for JSON partition * fix: rename variable * feat: add metadata_date for md partition * feat: add test for md partition * feat: update doc string * feat: add metadata_date for .odt partition * feat: update .odt string * feat: add metadata_date for .org partition * feat: add tests for .org partition * feat: add metadata_date for .pdf partition * feat: add tests for .pdf partition * feat: add metadata_date for .pptx partition * feat: add metadata_date for .ppt partition * feat: add tests for .ppt partition * feat: add tests for .pptx partition * feat: add metadata_date for .rst partition * feat: add tests for .rst partition * fix: get modification date after file checking * feat: add tests for .rtf partition * feat: add tests for .rtf partition * feat: add metadata_date for .txt partition * fix: rename argument * feat: add tests for .txt partition * feat: update doc string rst patrition function * feat: add metadata_date for .tsv partition * feat: add tests for .tsv partition * feat: add metadata_date for .xlsx partition * feat: add tests for .xlsx partition * fix: clean up * feat: add tests for .xml partition * feat: add tests for .xml partition * fix: use `or ` instead of `if` * fix: fix epub tests * fix: remove not used code * fix: add try block for getting file name * fix: applying linter changes * fix: fix test_partition_file * feat: add metadata_date for email * feat: add test for email partition * feat: add metadata_date for msg * feat: add tests for msg partition * feat: update CHANGELOG file * fix: update partitions doc string * don't push * fix: clean up code * linting, linting, linting * remove unnecessary example doc * update version and changelog * ingest-test-fixtures-update * set metadata date in test --------- Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> * ingest-test-fixtures-update * Update ingest test fixtures (#970) Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com> * Revert "Update ingest test fixtures (#970)" This reverts commit 1d182ae474b3545b15551fffc15977757d552cd2. * remove date from metadata in outputs * update docstring ordering * remove print * remove print * remove print * linting, linting, linting * fix version and test * fix changelog * fix changelog * update version --------- Co-authored-by: kravetsmic <79907559+kravetsmic@users.noreply.github.com> Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: MthwRobinson <MthwRobinson@users.noreply.github.com>
2023-07-26 15:10:14 -04:00
)
assert elements[0].metadata.last_modified == expected_last_modification_date
def test_partition_image_from_file_without_metadata_date(
filename="example-docs/english-and-korean.png",
):
"""Test partition_image() with file that are not possible to get last modified date"""
with open(filename, "rb") as f:
sf = tempfile.SpooledTemporaryFile()
sf.write(f.read())
sf.seek(0)
elements = image.partition_image(file=sf, date_from_file_object=True)
assert elements[0].metadata.last_modified is None
def test_partition_msg_with_json():
elements = image.partition_image(
example_doc_path("layout-parser-paper-fast.jpg"),
strategy=PartitionStrategy.AUTO,
)
assert_round_trips_through_JSON(elements)
def test_partition_image_with_ocr_has_coordinates_from_filename(
filename="example-docs/english-and-korean.png",
):
elements = image.partition_image(filename=filename, strategy=PartitionStrategy.OCR_ONLY)
int_coordinates = [(int(x), int(y)) for x, y in elements[0].metadata.coordinates.points]
refactor: `partition_pdf()` for `ocr_only` strategy (#1811) ### Summary Update `ocr_only` strategy in `partition_pdf()`. This PR adds the functionality to get accurate coordinate data when partitioning PDFs and Images with the `ocr_only` strategy. - Add functionality to perform OCR region grouping based on the OCR text taken from `pytesseract.image_to_string()` - Add functionality to get layout elements from OCR regions (ocr_layout) for both `tesseract` and `paddle` - Add functionality to determine the `source` of merged text regions when merging text regions in `merge_text_regions()` - Merge multiple test functions related to "ocr_only" strategy into `test_partition_pdf_with_ocr_only_strategy()` - This PR also fixes [issue #1792](https://github.com/Unstructured-IO/unstructured/issues/1792) ### Evaluation ``` # Image PYTHONPATH=. python examples/custom-layout-order/evaluate_natural_reading_order.py example-docs/double-column-A.jpg ocr_only xy-cut image # PDF PYTHONPATH=. python examples/custom-layout-order/evaluate_natural_reading_order.py example-docs/multi-column-2p.pdf ocr_only xy-cut pdf ``` ### Test - **Before update** All elements have the same coordinate data ![multi-column-2p_1_xy-cut](https://github.com/Unstructured-IO/unstructured/assets/9475974/aae0195a-2943-4fa8-bdd8-807f2f09c768) - **After update** All elements have accurate coordinate data ![multi-column-2p_1_xy-cut](https://github.com/Unstructured-IO/unstructured/assets/9475974/0f6c6202-9e65-4acf-bcd4-ac9dd01ab64a) --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-30 13:13:29 -07:00
assert int_coordinates == [(14, 16), (14, 37), (381, 37), (381, 16)]
@pytest.mark.parametrize(
("filename"),
[
("example-docs/layout-parser-paper-with-table.jpg"),
("example-docs/english-and-korean.png"),
("example-docs/layout-parser-paper-fast.jpg"),
],
)
def test_partition_image_with_ocr_coordinates_are_not_nan_from_filename(
filename,
):
import math
elements = image.partition_image(filename=filename, strategy=PartitionStrategy.OCR_ONLY)
for element in elements:
# TODO (jennings) One or multiple elements is an empty string
# without coordinates. This should be fixed in a new issue
if element.text:
box = element.metadata.coordinates.points
for point in box:
assert point[0] is not math.nan
assert point[1] is not math.nan
def test_partition_image_formats_languages_for_tesseract():
filename = "example-docs/jpn-vert.jpeg"
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
with mock.patch(
Refactor: support merging `extracted` layout with `inferred` layout (#2158) ### Summary This PR is the second part of `pdfminer` refactor to move it from `unstructured-inference` repo to `unstructured` repo, the first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/294. This PR adds logic to merge the extracted layout with the inferred layout. The updated workflow for the `hi_res` strategy: * pass the document (as data/filename) to the `inference` repo to get `inferred_layout` (DocumentLayout) * pass the `inferred_layout` returned from the `inference` repo and the document (as data/filename) to the `pdfminer_processing` module, which first opens the document (create temp file/dir as needed), and splits the document by pages * if is_image is `True`, return the passed inferred_layout(DocumentLayout) * if is_image is `False`: * get extracted_layout (TextRegions) from the passed document(data/filename) by pdfminer * merge `extracted_layout` (TextRegions) with the passed `inferred_layout` (DocumentLayout) * return the `inferred_layout `(DocumentLayout) with updated elements (all merged LayoutElements) as merged_layout (DocumentLayout) * pass merged_layout and the document (as data/filename) to the `OCR` module, which first opens the document (create temp file/dir as needed), and splits the document by pages (convert PDF pages to image pages for PDF file) ### Note This PR also fixes issue #2164 by using functionality similar to the one implemented in the `fast` strategy workflow when extracting elements by `pdfminer`. ### TODO * image extraction refactor to move it from `unstructured-inference` repo to `unstructured` repo * improving natural reading order by applying the current default `xycut` sorting to the elements extracted by `pdfminer`
2023-12-01 12:56:31 -08:00
"unstructured.partition.pdf_image.ocr.process_file_with_ocr",
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
) as mock_process_file_with_ocr:
image.partition_image(
filename=filename, strategy=PartitionStrategy.HI_RES, languages=["jpn_vert"]
)
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
_, kwargs = mock_process_file_with_ocr.call_args_list[0]
assert "ocr_languages" in kwargs
assert kwargs["ocr_languages"] == "jpn_vert"
def test_partition_image_warns_with_ocr_languages(caplog):
filename = "example-docs/layout-parser-paper-fast.jpg"
image.partition_image(filename=filename, strategy=PartitionStrategy.HI_RES, ocr_languages="eng")
assert "The ocr_languages kwarg will be deprecated" in caplog.text
def test_add_chunking_strategy_on_partition_image(
filename="example-docs/layout-parser-paper-fast.jpg",
):
elements = image.partition_image(filename=filename)
chunk_elements = image.partition_image(filename, chunking_strategy="by_title")
chunks = chunk_by_title(elements)
assert chunk_elements != elements
assert chunk_elements == chunks
chore: Table chunking (#1540) This change is adding to our `add_chunking_strategy` logic so that we are able to chunk Table elements' `text` and `text_as_html` params. In order to keep the functionality under the same `by_title` chunking strategy we have renamed the `combine_under_n_chars` to `max_characters`. It functions the same way for the combining elements under Title's, as well as specifying a chunk size (in chars) for TableChunk elements. *renaming the variable to `max_characters` will also reflect the 'hard max' we will implement for large elements in followup PRs Additionally -> some lint changes snuck in when I ran `make tidy` hence the minor changes in unrelated files :) TODO: ✅ add unit tests --> note: added where I could to unit tests! Some unit tests I just clarified that the chunking strategy was now 'by_title' because we don't have a file example that has Table elements to test the 'by_num_characters' chunking strategy ✅ update changelog To manually test: ``` In [1]: filename="example-docs/example-10k.html" In [2]: from unstructured.chunking.title import chunk_table_element In [3]: from unstructured.partition.auto import partition In [4]: elements = partition(filename) # element at -2 happens to be a Table, and we'll get chunks of char size 4 here In [5]: chunks = chunk_table_element(elements[-2], 4) # examine text and text_as_html params ln [6]: for c in chunks: print(c.text) print(c.metadata.text_as_html) ``` --------- Co-authored-by: Yao You <theyaoyou@gmail.com>
2023-10-03 09:40:34 -07:00
def test_add_chunking_strategy_on_partition_image_hi_res(
filename="example-docs/layout-parser-paper-with-table.jpg",
):
elements = image.partition_image(
filename=filename,
strategy=PartitionStrategy.HI_RES,
chore: Table chunking (#1540) This change is adding to our `add_chunking_strategy` logic so that we are able to chunk Table elements' `text` and `text_as_html` params. In order to keep the functionality under the same `by_title` chunking strategy we have renamed the `combine_under_n_chars` to `max_characters`. It functions the same way for the combining elements under Title's, as well as specifying a chunk size (in chars) for TableChunk elements. *renaming the variable to `max_characters` will also reflect the 'hard max' we will implement for large elements in followup PRs Additionally -> some lint changes snuck in when I ran `make tidy` hence the minor changes in unrelated files :) TODO: ✅ add unit tests --> note: added where I could to unit tests! Some unit tests I just clarified that the chunking strategy was now 'by_title' because we don't have a file example that has Table elements to test the 'by_num_characters' chunking strategy ✅ update changelog To manually test: ``` In [1]: filename="example-docs/example-10k.html" In [2]: from unstructured.chunking.title import chunk_table_element In [3]: from unstructured.partition.auto import partition In [4]: elements = partition(filename) # element at -2 happens to be a Table, and we'll get chunks of char size 4 here In [5]: chunks = chunk_table_element(elements[-2], 4) # examine text and text_as_html params ln [6]: for c in chunks: print(c.text) print(c.metadata.text_as_html) ``` --------- Co-authored-by: Yao You <theyaoyou@gmail.com>
2023-10-03 09:40:34 -07:00
infer_table_structure=True,
)
chunk_elements = image.partition_image(
filename,
strategy=PartitionStrategy.HI_RES,
chore: Table chunking (#1540) This change is adding to our `add_chunking_strategy` logic so that we are able to chunk Table elements' `text` and `text_as_html` params. In order to keep the functionality under the same `by_title` chunking strategy we have renamed the `combine_under_n_chars` to `max_characters`. It functions the same way for the combining elements under Title's, as well as specifying a chunk size (in chars) for TableChunk elements. *renaming the variable to `max_characters` will also reflect the 'hard max' we will implement for large elements in followup PRs Additionally -> some lint changes snuck in when I ran `make tidy` hence the minor changes in unrelated files :) TODO: ✅ add unit tests --> note: added where I could to unit tests! Some unit tests I just clarified that the chunking strategy was now 'by_title' because we don't have a file example that has Table elements to test the 'by_num_characters' chunking strategy ✅ update changelog To manually test: ``` In [1]: filename="example-docs/example-10k.html" In [2]: from unstructured.chunking.title import chunk_table_element In [3]: from unstructured.partition.auto import partition In [4]: elements = partition(filename) # element at -2 happens to be a Table, and we'll get chunks of char size 4 here In [5]: chunks = chunk_table_element(elements[-2], 4) # examine text and text_as_html params ln [6]: for c in chunks: print(c.text) print(c.metadata.text_as_html) ``` --------- Co-authored-by: Yao You <theyaoyou@gmail.com>
2023-10-03 09:40:34 -07:00
infer_table_structure=True,
chunking_strategy="by_title",
)
chunks = chunk_by_title(elements)
assert chunk_elements != elements
assert chunk_elements == chunks
def test_partition_image_uses_model_name():
with mock.patch.object(
pdf,
"_partition_pdf_or_image_local",
) as mockpartition:
image.partition_image("example-docs/layout-parser-paper-fast.jpg", model_name="test")
print(mockpartition.call_args)
assert "model_name" in mockpartition.call_args.kwargs
assert mockpartition.call_args.kwargs["model_name"]
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
def test_partition_image_uses_hi_res_model_name():
with mock.patch.object(
pdf,
"_partition_pdf_or_image_local",
) as mockpartition:
image.partition_image("example-docs/layout-parser-paper-fast.jpg", hi_res_model_name="test")
print(mockpartition.call_args)
assert "model_name" not in mockpartition.call_args.kwargs
assert "hi_res_model_name" in mockpartition.call_args.kwargs
assert mockpartition.call_args.kwargs["hi_res_model_name"] == "test"
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
@pytest.mark.parametrize(
("ocr_mode", "idx_title_element"),
[
("entire_page", 2),
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
("individual_blocks", 1),
],
)
def test_partition_image_hi_res_ocr_mode(ocr_mode, idx_title_element):
filename = "example-docs/layout-parser-paper-fast.jpg"
elements = image.partition_image(
filename=filename, ocr_mode=ocr_mode, strategy=PartitionStrategy.HI_RES
)
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
# Note(yuming): idx_title_element is different based on xy-cut and ocr mode
assert elements[idx_title_element].category == ElementType.TITLE
Refactor: support entire page OCR with `ocr_mode` and `ocr_languages` (#1579) ## Summary Second part of OCR refactor to move it from inference repo to unstructured repo, first part is done in https://github.com/Unstructured-IO/unstructured-inference/pull/231. This PR adds OCR process logics to entire page OCR, and support two OCR modes, "entire_page" or "individual_blocks". The updated workflow for `Hi_res` partition: * pass the document as data/filename to inference repo to get `inferred_layout` (DocumentLayout) * pass the document as data/filename to OCR module, which first open the document (create temp file/dir as needed), and split the document by pages (convert PDF pages to image pages for PDF file) * if ocr mode is `"entire_page"` * OCR the entire image * merge the OCR layout with inferred page layout * if ocr mode is `"individual_blocks"` * from inferred page layout, find element with no extracted text, crop the entire image by the bboxes of the element * replace empty text element with the text obtained from OCR the cropped image * return all merged PageLayouts and form a DocumentLayout subject for later on process This PR also bump `unstructured-inference==0.7.2` since the branch relay on OCR refactor from unstructured-inference. ## Test ``` from unstructured.partition.auto import partition entrie_page_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="entire_page", ocr_languages="eng+kor", strategy="hi_res") individual_blocks_ocr_mode_elements = partition(filename="example-docs/english-and-korean.png", ocr_mode="individual_blocks", ocr_languages="eng+kor", strategy="hi_res") print([el.text for el in entrie_page_ocr_mode_elements]) print([el.text for el in individual_blocks_ocr_mode_elements]) ``` latest output: ``` # entrie_page ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'accounts.', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASUREWH HARUTOM|2] 팬 입니다. 팬 으 로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 불 공 평 함 을 LRU, 이 일 을 통해 저 희 의 의 혹 을 전 달 하여 귀 사 의 진지한 민 과 적극적인 답 변 을 받을 수 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were', 'successfully sent', '4. Use the hashtag of Haruto on your tweet to show that vou have sent vour email]', '메 고'] # individual_blocks ['RULES AND INSTRUCTIONS 1. Template for day 1 (korean) , for day 2 (English) for day 3 both English and korean. 2. Use all your accounts. use different emails to send. Its better to have many email', 'Note: Remember to write your own "OPENING MESSAGE" before you copy and paste the template. please always include [TREASURE HARUTO] for example:', '안녕하세요, 저 희 는 YGEAS 그룹 TREASURES HARUTOM| 2] 팬 입니다. 팬 으로서, HARUTO 씨 받 는 대 우 에 대해 의 구 심 과 habe ERO, 이 머 일 을 적극 저 희 의 ASS 전 달 하여 귀 사 의 진지한 고 2 있 기 를 바랍니다.', '3. CC Harutonations@gmail.com so we can keep track of how many emails were ciiccecefisliy cant', 'VULLESSIULY Set 4. Use the hashtag of Haruto on your tweet to show that you have sent your email'] ``` --------- Co-authored-by: ryannikolaidis <1208590+ryannikolaidis@users.noreply.github.com> Co-authored-by: yuming-long <yuming-long@users.noreply.github.com> Co-authored-by: christinestraub <christinemstraub@gmail.com> Co-authored-by: christinestraub <christinestraub@users.noreply.github.com>
2023-10-06 18:54:49 -04:00
def test_partition_image_hi_res_invalid_ocr_mode():
filename = "example-docs/layout-parser-paper-fast.jpg"
with pytest.raises(ValueError):
_ = image.partition_image(
filename=filename, ocr_mode="invalid_ocr_mode", strategy=PartitionStrategy.HI_RES
)
Chore (refactor): support table extraction with pre-computed ocr data (#1801) ### 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>
2023-10-20 20:24:23 -04:00
@pytest.mark.parametrize(
("ocr_mode"),
[
("entire_page"),
("individual_blocks"),
],
)
def test_partition_image_hi_res_ocr_mode_with_table_extraction(ocr_mode):
filename = "example-docs/layout-parser-paper-with-table.jpg"
elements = image.partition_image(
filename=filename,
ocr_mode=ocr_mode,
strategy=PartitionStrategy.HI_RES,
Chore (refactor): support table extraction with pre-computed ocr data (#1801) ### 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>
2023-10-20 20:24:23 -04:00
infer_table_structure=True,
)
table = [el.metadata.text_as_html for el in elements if el.metadata.text_as_html]
assert len(table) == 1
assert "<table><thead><tr>" in table[0]
assert "</thead><tbody><tr>" in table[0]
Chore (refactor): support table extraction with pre-computed ocr data (#1801) ### 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>
2023-10-20 20:24:23 -04:00
assert "Layouts of history Japanese documents" in table[0]
assert "Layouts of scanned modern magazines and scientific reports" in table[0]
Chore (refactor): support table extraction with pre-computed ocr data (#1801) ### 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>
2023-10-20 20:24:23 -04:00
def test_partition_image_raises_TypeError_for_invalid_languages():
filename = "example-docs/layout-parser-paper-fast.jpg"
with pytest.raises(TypeError):
image.partition_image(filename=filename, strategy=PartitionStrategy.HI_RES, languages="eng")
@pytest.fixture()
def inference_results():
page = layout.PageLayout(
number=1,
image=mock.MagicMock(format="JPEG"),
)
page.elements = [layout.LayoutElement.from_coords(0, 0, 600, 800, text="hello")]
doc = layout.DocumentLayout(pages=[page])
return doc
def test_partition_image_has_filename(inference_results):
doc_path = "example-docs"
filename = "layout-parser-paper-fast.jpg"
# Mock inference call with known return results
with mock.patch(
"unstructured_inference.inference.layout.process_file_with_model",
return_value=inference_results,
) as mock_inference_func:
elements = image.partition_image(
filename=os.path.join(doc_path, filename),
strategy=PartitionStrategy.HI_RES,
)
# Make sure we actually went down the path we expect.
mock_inference_func.assert_called_once()
# Unpack element but also make sure there is only one
element = only(elements)
# This makes sure we are still getting the filetype metadata (should be translated from the
# fixtures)
assert element.metadata.filetype == "JPEG"
# This should be kept from the filename we originally gave
assert element.metadata.filename == filename
@pytest.mark.parametrize("file_mode", ["filename", "rb"])
@pytest.mark.parametrize("extract_image_block_to_payload", [False, True])
def test_partition_image_element_extraction(
file_mode,
extract_image_block_to_payload,
filename=example_doc_path("embedded-images-tables.jpg"),
):
extract_image_block_types = ["Image", "Table"]
with tempfile.TemporaryDirectory() as tmpdir:
if file_mode == "filename":
elements = image.partition_image(
filename=filename,
extract_image_block_types=extract_image_block_types,
extract_image_block_to_payload=extract_image_block_to_payload,
extract_image_block_output_dir=tmpdir,
)
else:
with open(filename, "rb") as f:
elements = image.partition_image(
file=f,
extract_image_block_types=extract_image_block_types,
extract_image_block_to_payload=extract_image_block_to_payload,
extract_image_block_output_dir=tmpdir,
)
assert_element_extraction(
elements, extract_image_block_types, extract_image_block_to_payload, tmpdir
)
def test_partition_image_works_on_heic_file(
filename="example-docs/DA-1p.heic",
):
elements = image.partition_image(filename=filename, strategy=PartitionStrategy.AUTO)
titles = [el.text for el in elements if el.category == ElementType.TITLE]
assert "CREATURES" in titles
@pytest.mark.parametrize(
("strategy"),
[PartitionStrategy.HI_RES, PartitionStrategy.OCR_ONLY],
)
def test_deterministic_element_ids(strategy: str):
elements_1 = image.partition_image(
example_doc_path("layout-parser-paper-with-table.jpg"),
strategy=strategy,
starting_page_number=2,
)
elements_2 = image.partition_image(
example_doc_path("layout-parser-paper-with-table.jpg"),
strategy=strategy,
starting_page_number=2,
)
ids_1 = [element.id for element in elements_1]
ids_2 = [element.id for element in elements_2]
assert ids_1 == ids_2
def test_multipage_tiff_starts_on_starting_page_number():
elements = image.partition_image(
example_doc_path("layout-parser-paper-combined.tiff"),
starting_page_number=2,
)
pages = {element.metadata.page_number for element in elements}
assert pages == {2, 3}