154 lines
5.6 KiB
Python
Raw Normal View History

from __future__ import annotations
from pytest_mock import MockFixture
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 Table, Text
from unstructured.partition.epub import partition_epub
from unstructured.partition.utils.constants import UNSTRUCTURED_INCLUDE_DEBUG_METADATA
def test_partition_epub_from_filename():
filename = example_doc_path("winter-sports.epub")
elements = partition_epub(filename=filename)
assert len(elements) > 0
assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
for element in elements:
assert element.metadata.filename == "winter-sports.epub"
if UNSTRUCTURED_INCLUDE_DEBUG_METADATA:
assert {element.metadata.detection_origin for element in elements} == {"epub"}
def test_partition_epub_from_filename_returns_table_in_elements():
rfctr(html): replace html parser (#3218) **Summary** Replace legacy HTML parser with recursive version that captures all content and provides flexibility to add new metadata. It's also substantially faster although that's just a happy side-effect. **Additional Context** The prior HTML parsing algorithm that makes up the core of HTML partitioning was buggy and very difficult to reason about because it did not conform to the inherently recursive structure of HTML. The new version retains `lxml` as the performant and reliable base library but uses `lxml`'s custom element classes to efficiently classify HTML elements by their behaviors (block-item and inline (phrasing) primarily) and give those elements the desired partitioning behaviors. This solves a host of existing problems with content being skipped and elements (paragraphs) being divided improperly, but also provides a clear domain model for reasoning about its behavior and reliably adjusting it to suit our existing and future purposes. The parser's operation is recursive, closely modeling the recursive structure of HTML itself. It's behaviors are based on the HTML Standard and reliably produce proper and explainable results even for novel cases. Fixes #2325 Fixes #2562 Fixes #2675 Fixes #3168 Fixes #3227 Fixes #3228 Fixes #3230 Fixes #3237 Fixes #3245 Fixes #3247 Fixes #3255 Fixes #3309 ### BEHAVIOR DIFFERENCES #### `emphasized_text_tags` encoding is changed: - `<strong>` is encoded as `"b"` rather than `"strong"`. - `<em>` is encoded as `"i"` rather than `"em"`. - `<span>` is no longer recorded in `emphasized_text_tags` (because without the CSS we can't tell whether it's used for emphasis or if so what kind). - nested emphasis (e.g. bold+italic) is encoded as multiple characters ("bi"). - `emphasized_text_contents` is broken on emphasis-change boundaries, like: ```html `<p>foo <b>bar <i>baz</i> bada</b> bing</p>` ``` produces: ```json { "emphasized_text_contents": ["bar", "baz", "bada"], "emphasized_text_tags": ["b", "bi", "b"] } ``` whereas previously it would have produced: ```json { "emphasized_text_contents": ["bar baz bada", "baz"], "emphasized_text_tags": ["b", "i"] } ``` #### `<pre>` text is preserved as it appears in the html Except that a leading newline is removed if present (has to be in position 0 of text). Also, a trailing newline is stripped but only if it appears in the very last position ([-1]) of the `<pre>` text. Old parser stripped all leading and trailing whitespace. Result is that: ```html <pre> foo bar baz </pre> ``` parses to `"foo\nbar\nbaz"` which is the same result produced for: ```html <pre>foo bar baz</pre> ``` This equivalence is the same behavior exhibited by a browser, which is why we did the extra work to make it this way. #### Whitespace normalization Leading and trailing whitespace are removed from element text, just as it is removed in the browser. Runs of whitespace within the element text are reduced to a single space character (like in the browser). Note this means that `\t`, `\n`, and `&nbsp;` are replaced with a regular space character. All text derived from elements is whitespace normalized except the text within a `<pre>` tag. Any leading or trailing newline is trimmed from `<pre>` element text; all other whitespace is preserved just as it appeared in the HTML source. #### `link_start_indexes` metadata is no longer captured. Rationale: - It was frequently wrong, often `-1`. - It was deprecated but then added back in a community PR. - Maintaining it across any possible downstream transformations (e.g. chunking) would be expensive and almost certainly lead to wrong values as distant code evolves. - It is complex to compute and recompute when whitespace is normalized, adding substantial complexity to the code and reducing readability and maintainability #### `<br/>` element is replaced with a single newline (`"\n"`) but that is usually replaced with a space in `Element.text` when it is normalized. The newline is preserved within a `<pre>` element. - Related: _No paragraph-break on `<br/><br/>`_ #### Empty `h1..h6` elements are dropped. HTML heading elements (`<h1..h6>`) are "skipped" (do not generate a `Title` element) when they contain no text or contain only whitespace. --------- Co-authored-by: scanny <scanny@users.noreply.github.com>
2024-07-10 17:14:28 -07:00
elements = partition_epub(example_doc_path("winter-sports.epub"))
assert elements[10] == Table(
"Contents. List of Illustrations (In certain versions of this etext [in certain\nbrowsers]"
" clicking on the image will bring up a larger\nversion.) (etext transcriber's note)"
)
def test_partition_epub_from_filename_returns_uns_elements():
filename = example_doc_path("winter-sports.epub")
elements = partition_epub(filename=filename)
assert len(elements) > 0
assert isinstance(elements[0], Text)
def test_partition_epub_from_filename_with_metadata_filename():
filename = example_doc_path("winter-sports.epub")
elements = partition_epub(filename=filename, metadata_filename="test")
assert len(elements) > 0
assert all(element.metadata.filename == "test" for element in elements)
def test_partition_epub_from_file():
filename = example_doc_path("winter-sports.epub")
with open(filename, "rb") as f:
elements = partition_epub(file=f)
assert len(elements) > 0
assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
for element in elements:
assert element.metadata.filename is None
def test_partition_epub_from_file_with_metadata_filename():
filename = example_doc_path("winter-sports.epub")
with open(filename, "rb") as f:
elements = partition_epub(file=f, metadata_filename="test")
assert len(elements) > 0
for element in elements:
assert element.metadata.filename == "test"
def test_partition_epub_from_filename_exclude_metadata():
filename = example_doc_path("winter-sports.epub")
elements = partition_epub(filename=filename, include_metadata=False)
assert elements[0].metadata.filetype is None
assert elements[0].metadata.page_name is None
assert elements[0].metadata.filename is None
def test_partition_epub_from_file_exlcude_metadata():
filename = example_doc_path("winter-sports.epub")
with open(filename, "rb") as f:
elements = partition_epub(file=f, include_metadata=False)
assert elements[0].metadata.filetype is None
assert elements[0].metadata.page_name is None
assert elements[0].metadata.filename is None
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_epub_pulls_last_modified_from_filesystem(mocker: MockFixture):
filesystem_last_modified = "2024-06-14T16:01:29"
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
mocker.patch(
"unstructured.partition.epub.get_last_modified", return_value=filesystem_last_modified
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 = partition_epub("example-docs/winter-sports.epub")
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 == filesystem_last_modified
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_epub_prefers_metadata_last_modified(mocker: MockFixture):
metadata_last_modified = "2024-06-14T16:01:29"
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
mocker.patch(
"unstructured.partition.epub.get_last_modified", return_value="2029-07-05T09:24:28"
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 = partition_epub(
"example-docs/winter-sports.epub", metadata_last_modified=metadata_last_modified
)
assert all(e.metadata.last_modified == metadata_last_modified for e in elements)
def test_partition_epub_with_json():
filename = "example-docs/winter-sports.epub"
elements = partition_epub(filename=filename)
assert_round_trips_through_JSON(elements)
def test_add_chunking_strategy_on_partition_epub(
filename=example_doc_path("winter-sports.epub"),
):
elements = partition_epub(filename=filename)
chunk_elements = partition_epub(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_epub_non_default(
filename=example_doc_path("winter-sports.epub"),
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
):
elements = partition_epub(filename=filename)
chunk_elements = partition_epub(
filename,
chunking_strategy="by_title",
max_characters=5,
new_after_n_chars=5,
combine_text_under_n_chars=0,
)
chunks = chunk_by_title(
elements,
max_characters=5,
new_after_n_chars=5,
combine_text_under_n_chars=0,
)
assert chunk_elements != elements
assert chunk_elements == chunks
def test_partition_epub_element_metadata_has_languages():
filename = example_doc_path("winter-sports.epub")
elements = partition_epub(filename=filename)
assert elements[0].metadata.languages == ["eng"]
def test_partition_epub_respects_detect_language_per_element():
filename = "example-docs/language-docs/eng_spa_mult.epub"
elements = partition_epub(filename=filename, detect_language_per_element=True)
langs = [element.metadata.languages for element in elements]
assert langs == [["eng"], ["spa", "eng"], ["eng"], ["eng"], ["spa"]]