chore: rename Element's "date" field to "last_modified" (#997)

Change the Element's date field name to the more specific last_modified so there is less room for confusion of what that field represents.

Author: cragwolfe

Diff for: CHANGELOG.md

@@ -1,9 +1,12 @@
-## 0.8.8-dev0
+## 0.8.8
 
 ### Enhancements
 
 ### Features
 
+### Fixes
+
+* Rename "date" field to "last_modified"
 * Adds Box connector
 
 ### Fixes

Diff for: test_unstructured/partition/test_api.py

@@ -29,7 +29,6 @@ def text(self):
         "text": "This is a test email to use for unit tests.",
         "type": "NarrativeText",
         "metadata": {
-            "date": "2022-12-16T17:04:16-05:00",
             "sent_from": [
                 "Matthew Robinson <[email protected]>"
             ],
@@ -97,6 +96,8 @@ def test_partition_via_api_raises_with_bad_response(monkeypatch):
         partition_via_api(filename=filename)
 
 
+@pytest.mark.skipif(skip_outside_ci, reason="Skipping test run outside of CI")
+@pytest.mark.skipif(skip_not_on_main, reason="Skipping test run outside of main branch")
 def test_partition_via_api_with_no_strategy():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "layout-parser-paper-fast.jpg")
 
@@ -108,6 +109,8 @@ def test_partition_via_api_with_no_strategy():
     assert elements_hi_res[0].text.startswith("LayoutParser")
 
 
+@pytest.mark.skipif(skip_outside_ci, reason="Skipping test run outside of CI")
+@pytest.mark.skipif(skip_not_on_main, reason="Skipping test run outside of main branch")
 def test_partition_via_api_with_image_hi_res_strategy_includes_coordinates():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "layout-parser-paper-fast.jpg")
 
@@ -154,7 +157,6 @@ def text(self):
             "text": "This is a test email to use for unit tests.",
             "type": "NarrativeText",
             "metadata": {
-                "date": "2022-12-16T17:04:16-05:00",
                 "sent_from": [
                     "Matthew Robinson <[email protected]>"
                 ],
@@ -173,7 +175,6 @@ def text(self):
             "text": "This is a test email to use for unit tests.",
             "type": "NarrativeText",
             "metadata": {
-                "date": "2022-12-16T17:04:16-05:00",
                 "sent_from": [
                     "Matthew Robinson <[email protected]>"
                 ],

Diff for: test_unstructured/partition/test_csv.py

@@ -65,7 +65,7 @@ def test_partition_csv_metadata_date(mocker, filename="example-docs/stanley-cups
 
     assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
     assert isinstance(elements[0], Table)
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_csv_custom_metadata_date(
@@ -82,12 +82,12 @@ def test_partition_csv_custom_metadata_date(
 
     elements = partition_csv(
         filename=filename,
-        metadata_date=expected_last_modification_date,
+        metadata_last_modified=expected_last_modification_date,
     )
 
     assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
     assert isinstance(elements[0], Table)
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date
 
 
 def test_partition_csv_from_file_metadata_date(
@@ -106,7 +106,7 @@ def test_partition_csv_from_file_metadata_date(
 
     assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
     assert isinstance(elements[0], Table)
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_csv_from_file_custom_metadata_date(
@@ -122,11 +122,11 @@ def test_partition_csv_from_file_custom_metadata_date(
     )
 
     with open(filename, "rb") as f:
-        elements = partition_csv(file=f, metadata_date=expected_last_modification_date)
+        elements = partition_csv(file=f, metadata_last_modified=expected_last_modification_date)
 
     assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
     assert isinstance(elements[0], Table)
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date
 
 
 def test_partition_csv_from_file_without_metadata(
@@ -143,4 +143,4 @@ def test_partition_csv_from_file_without_metadata(
 
     assert clean_extra_whitespace(elements[0].text) == EXPECTED_TEXT
     assert isinstance(elements[0], Table)
-    assert elements[0].metadata.date is None
+    assert elements[0].metadata.last_modified is None

Diff for: test_unstructured/partition/test_doc.py

@@ -200,7 +200,7 @@ def test_partition_doc_metadata_date(
 
     elements = partition_doc(filename=filename)
 
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_doc_metadata_date_with_custom_metadata(
@@ -217,10 +217,10 @@ def test_partition_doc_metadata_date_with_custom_metadata(
 
     elements = partition_doc(
         filename=filename,
-        metadata_date=expected_last_modified_date,
+        metadata_last_modified=expected_last_modified_date,
     )
 
-    assert elements[0].metadata.date == expected_last_modified_date
+    assert elements[0].metadata.last_modified == expected_last_modified_date
 
 
 def test_partition_doc_from_file_metadata_date(
@@ -237,7 +237,7 @@ def test_partition_doc_from_file_metadata_date(
     with open(filename, "rb") as f:
         elements = partition_doc(file=f)
 
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_doc_from_file_metadata_date_with_custom_metadata(
@@ -252,11 +252,12 @@ def test_partition_doc_from_file_metadata_date_with_custom_metadata(
         return_value=mocked_last_modification_date,
     )
     with open(filename, "rb") as f:
-        elements = partition_doc(file=f, metadata_date=expected_last_modified_date)
+        elements = partition_doc(file=f, metadata_last_modified=expected_last_modified_date)
 
-    assert elements[0].metadata.date == expected_last_modified_date
+    assert elements[0].metadata.last_modified == expected_last_modified_date
 
 
+@pytest.mark.xfail(reason="handling of last_modified for file vs. filename to be refined later")
 def test_partition_doc_from_file_without_metadata_date(
     filename="example-docs/fake.doc",
 ):
@@ -266,6 +267,6 @@ def test_partition_doc_from_file_without_metadata_date(
         sf = SpooledTemporaryFile()
         sf.write(f.read())
         sf.seek(0)
-        elements = partition_doc(file=sf, metadata_date=None)
+        elements = partition_doc(file=sf, metadata_last_modified=None)
 
-    assert elements[0].metadata.date is None
+    assert elements[0].metadata.last_modified is None

Diff for: test_unstructured/partition/test_docx.py

@@ -216,7 +216,7 @@ def test_partition_docx_metadata_date(
 
     elements = partition_docx(filename=filename)
 
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_docx_metadata_date_with_custom_metadata(
@@ -233,10 +233,10 @@ def test_partition_docx_metadata_date_with_custom_metadata(
 
     elements = partition_docx(
         filename=filename,
-        metadata_date=expected_last_modified_date,
+        metadata_last_modified=expected_last_modified_date,
     )
 
-    assert elements[0].metadata.date == expected_last_modified_date
+    assert elements[0].metadata.last_modified == expected_last_modified_date
 
 
 def test_partition_docx_from_file_metadata_date(
@@ -253,7 +253,7 @@ def test_partition_docx_from_file_metadata_date(
     with open(filename, "rb") as f:
         elements = partition_docx(file=f)
 
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_docx_from_file_metadata_date_with_custom_metadata(
@@ -268,9 +268,9 @@ def test_partition_docx_from_file_metadata_date_with_custom_metadata(
         return_value=mocked_last_modification_date,
     )
     with open(filename, "rb") as f:
-        elements = partition_docx(file=f, metadata_date=expected_last_modified_date)
+        elements = partition_docx(file=f, metadata_last_modified=expected_last_modified_date)
 
-    assert elements[0].metadata.date == expected_last_modified_date
+    assert elements[0].metadata.last_modified == expected_last_modified_date
 
 
 def test_partition_docx_from_file_without_metadata_date(
@@ -284,4 +284,4 @@ def test_partition_docx_from_file_without_metadata_date(
         sf.seek(0)
         elements = partition_docx(file=sf)
 
-    assert elements[0].metadata.date is None
+    assert elements[0].metadata.last_modified is None

Diff for: test_unstructured/partition/test_email.py

@@ -302,7 +302,7 @@ def test_partition_email_from_filename_has_metadata():
         == ElementMetadata(
             coordinates=None,
             filename=filename,
-            date="2022-12-16T17:04:16-05:00",
+            last_modified="2022-12-16T17:04:16-05:00",
             page_number=None,
             url=None,
             sent_from=["Matthew Robinson <[email protected]>"],
@@ -312,7 +312,7 @@ def test_partition_email_from_filename_has_metadata():
         ).to_dict()
     )
     expected_dt = datetime.datetime.fromisoformat("2022-12-16T17:04:16-05:00")
-    assert elements[0].metadata.get_date() == expected_dt
+    assert elements[0].metadata.get_last_modified() == expected_dt
     for element in elements:
         assert element.metadata.filename == "fake-email.eml"
 
@@ -388,7 +388,7 @@ def test_partition_email_still_works_with_no_content():
 def test_partition_email_from_filename_exclude_metadata():
     filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-email-header.eml")
     elements = partition_email(filename=filename, include_metadata=False)
-    assert elements[0].metadata.get_date() is None
+    assert elements[0].metadata.get_last_modified() is None
     assert elements[0].metadata.filetype is None
     assert elements[0].metadata.page_name is None
     assert elements[0].metadata.filename is None
@@ -402,7 +402,7 @@ def test_partition_email_from_text_file_exclude_metadata():
             content_source="text/plain",
             include_metadata=False,
         )
-    assert elements[0].metadata.get_date() is None
+    assert elements[0].metadata.get_last_modified() is None
     assert elements[0].metadata.filetype is None
     assert elements[0].metadata.page_name is None
     assert elements[0].metadata.filename is None
@@ -412,7 +412,7 @@ def test_partition_email_from_file_exclude_metadata():
     filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-email.eml")
     with open(filename) as f:
         elements = partition_email(file=f, include_metadata=False)
-    assert elements[0].metadata.get_date() is None
+    assert elements[0].metadata.get_last_modified() is None
     assert elements[0].metadata.filetype is None
     assert elements[0].metadata.page_name is None
     assert elements[0].metadata.filename is None
@@ -466,9 +466,9 @@ def test_partition_email_from_file_custom_metadata_date(
     expected_last_modification_date = "2020-07-05T09:24:28"
 
     with open(filename) as f:
-        elements = partition_email(file=f, metadata_date=expected_last_modification_date)
+        elements = partition_email(file=f, metadata_last_modified=expected_last_modification_date)
 
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date
 
 
 def test_partition_email_custom_metadata_date(
@@ -478,7 +478,7 @@ def test_partition_email_custom_metadata_date(
 
     elements = partition_email(
         filename=filename,
-        metadata_date=expected_last_modification_date,
+        metadata_last_modified=expected_last_modification_date,
     )
 
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date

Diff for: test_unstructured/partition/test_epub.py

@@ -69,7 +69,7 @@ def test_partition_epub_metadata_date(
     )
     elements = partition_epub(filename=filename)
 
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_epub_custom_metadata_date(
@@ -86,10 +86,10 @@ def test_partition_epub_custom_metadata_date(
 
     elements = partition_epub(
         filename=filename,
-        metadata_date=expected_last_modification_date,
+        metadata_last_modified=expected_last_modification_date,
     )
 
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date
 
 
 def test_partition_epub_from_file_metadata_date(
@@ -106,7 +106,7 @@ def test_partition_epub_from_file_metadata_date(
     with open(filename, "rb") as f:
         elements = partition_epub(file=f)
 
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_epub_from_file_custom_metadata_date(
@@ -122,6 +122,6 @@ def test_partition_epub_from_file_custom_metadata_date(
     )
 
     with open(filename, "rb") as f:
-        elements = partition_epub(file=f, metadata_date=expected_last_modification_date)
+        elements = partition_epub(file=f, metadata_last_modified=expected_last_modification_date)
 
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date

Diff for: test_unstructured/partition/test_html_partition.py

@@ -357,7 +357,7 @@ def test_partition_html_metadata_date(mocker, filename="example-docs/fake-html.h
     elements = partition_html(filename=filename)
 
     assert isinstance(elements[0], Title)
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_html_from_file_metadata_date(
@@ -375,7 +375,7 @@ def test_partition_html_from_file_metadata_date(
         elements = partition_html(file=f)
 
     assert isinstance(elements[0], Title)
-    assert elements[0].metadata.date == mocked_last_modification_date
+    assert elements[0].metadata.last_modified == mocked_last_modification_date
 
 
 def test_partition_html_custom_metadata_date(
@@ -392,11 +392,11 @@ def test_partition_html_custom_metadata_date(
 
     elements = partition_html(
         filename=filename,
-        metadata_date=expected_last_modification_date,
+        metadata_last_modified=expected_last_modification_date,
     )
 
     assert isinstance(elements[0], Title)
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date
 
 
 def test_partition_html_from_file_custom_metadata_date(
@@ -412,17 +412,17 @@ def test_partition_html_from_file_custom_metadata_date(
     )
 
     with open(filename) as f:
-        elements = partition_html(file=f, metadata_date=expected_last_modification_date)
+        elements = partition_html(file=f, metadata_last_modified=expected_last_modification_date)
 
     assert isinstance(elements[0], Title)
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date
 
 
 def test_partition_html_from_text_metadata_date(filename="example-docs/fake-html.html"):
     elements = partition_html(text="<html><div><p>TEST</p></div></html>")
 
     assert isinstance(elements[0], Title)
-    assert elements[0].metadata.date is None
+    assert elements[0].metadata.last_modified is None
 
 
 def test_partition_html_from_text_custom_metadata_date(
@@ -432,11 +432,11 @@ def test_partition_html_from_text_custom_metadata_date(
 
     elements = partition_html(
         text="<html><div><p>TEST</p></div></html>",
-        metadata_date=expected_last_modification_date,
+        metadata_last_modified=expected_last_modification_date,
     )
 
     assert isinstance(elements[0], Title)
-    assert elements[0].metadata.date == expected_last_modification_date
+    assert elements[0].metadata.last_modified == expected_last_modification_date
 
 
 def test_partition_html_grabs_links():