rfctr(part): remove double-decoration 3 (#3687)

**Summary**
Install new `@apply_metadata()` on HTML and remove decorators from
delegating partitioners EPUB, MD, ORG, RST, and RTF.

**Additional Context**
- All five of these delegating partitioners delegate to
`partition_html()` so they're something of a matched set. EML and MSG
also partially delegate to HTML but that's a harder problem (they also
delegate to all other partitioners for attachments) that we'll address a
couple PRs later .
- Replace use of `@process_metadata()` and
`@add_metadata_with_filetype()` decorators with `@apply_metadata()` on
`partition_html()`.
- Remove all decorators from delegating partitioners; this removes the
"double-decorating".

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.15.14-dev8
+## 0.15.14-dev9
 
 ### Enhancements
 
@@ -14,6 +14,7 @@
 * **Allow empty text files.** Fixes an issue where text files with only white space would fail to be partitioned.
 * **Remove double-decoration for CSV, DOC, ODT partitioners.** Refactor these partitioners to use the new `@apply_metadata()` decorator and only decorate the principal partitioner (CSV and DOCX in this case); remove decoration from delegating partitioners.
 * **Remove double-decoration for PPT, PPTX, TSV, XLSX, and XML partitioners.** Refactor these partitioners to use the new `@apply_metadata()` decorator and only decorate the principal partitioner; remove decoration from delegating partitioners.
+* **Remove double-decoration for HTML, EPUB, MD, ORG, RST, and RTF partitioners.** Refactor these partitioners to use the new `@apply_metadata()` decorator and only decorate the principal partitioner (HTML in this case); remove decoration from delegating partitioners.
 
 ## 0.15.13
 

test_unstructured/partition/html/test_partition.py

@@ -1200,7 +1200,6 @@ def opts_args() -> dict[str, Any]:
         "url": None,
         "headers": {},
         "ssl_verify": True,
-        "metadata_last_modified": None,
         "skip_headers_and_footers": False,
         "detection_origin": None,
     }
@@ -1301,15 +1300,7 @@ class DescribeHtmlPartitionerOptions:
 
     # -- .last_modified --------------------------
 
-    def it_gets_the_last_modified_date_of_the_document_from_the_caller_when_provided(
-        self, opts_args: dict[str, Any]
-    ):
-        opts_args["metadata_last_modified"] = "2024-03-05T17:02:53"
-        opts = HtmlPartitionerOptions(**opts_args)
-
-        assert opts.last_modified == "2024-03-05T17:02:53"
-
-    def and_it_falls_back_to_the_last_modified_date_of_the_file_when_a_path_is_provided(
+    def it_gets_last_modified_from_the_filesystem_when_file_path_is_provided(
         self, opts_args: dict[str, Any], get_last_modified_date_: Mock
     ):
         opts_args["file_path"] = "a/b/document.html"

test_unstructured/partition/test_epub.py

@@ -10,12 +10,11 @@ from unstructured.partition.utils.constants import UNSTRUCTURED_INCLUDE_DEBUG_ME
 
 
 def test_partition_epub_from_filename():
-    filename = example_doc_path("winter-sports.epub")
-    elements = partition_epub(filename=filename)
+    elements = partition_epub(example_doc_path("simple.epub"))
+
     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"
+    assert isinstance(elements[0], Text)
+    assert elements[0].text.startswith("a shared culture")
     if UNSTRUCTURED_INCLUDE_DEBUG_METADATA:
         assert {element.metadata.detection_origin for element in elements} == {"epub"}
 
@@ -28,37 +27,56 @@ def test_partition_epub_from_filename_returns_table_in_elements():
     )
 
 
-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:
+    with open(example_doc_path("winter-sports.epub"), "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")
+# -- .metadata.filename --------------------------------------------------------------------------
+
+
+def test_partition_epub_from_filename_gets_filename_from_filename_arg():
+    elements = partition_epub(example_doc_path("simple.epub"))
+
     assert len(elements) > 0
-    for element in elements:
-        assert element.metadata.filename == "test"
+    assert all(e.metadata.filename == "simple.epub" for e in elements)
+
+
+def test_partition_epub_from_file_gets_filename_None():
+    with open(example_doc_path("simple.epub"), "rb") as f:
+        elements = partition_epub(file=f)
+
+    assert len(elements) > 0
+    assert all(e.metadata.filename is None for e in elements)
+
+
+def test_partition_epub_from_filename_prefers_metadata_filename():
+    elements = partition_epub(example_doc_path("simple.epub"), metadata_filename="orig-name.epub")
+
+    assert len(elements) > 0
+    assert all(element.metadata.filename == "orig-name.epub" for element in elements)
+
+
+def test_partition_epub_from_file_prefers_metadata_filename():
+    with open(example_doc_path("simple.epub"), "rb") as f:
+        elements = partition_epub(file=f, metadata_filename="orig-name.epub")
+
+    assert all(e.metadata.filename == "orig-name.epub" for e in elements)
+
+
+# -- .metadata.filetype --------------------------------------------------------------------------
+
+
+def test_partition_epub_gets_the_EPUB_MIME_type_in_metadata_filetype():
+    EPUB_MIME_TYPE = "application/epub"
+    elements = partition_epub(example_doc_path("simple.epub"))
+    assert all(e.metadata.filetype == EPUB_MIME_TYPE for e in elements), (
+        f"Expected all elements to have '{EPUB_MIME_TYPE}' as their filetype, but got:"
+        f" {repr(elements[0].metadata.filetype)}"
+    )
 
 
 # -- .metadata.last_modified ---------------------------------------------------------------------
@@ -72,10 +90,17 @@ def test_partition_epub_from_file_path_gets_last_modified_from_filesystem(mocker
 
     elements = partition_epub(example_doc_path("winter-sports.epub"))
 
-    assert elements[0].metadata.last_modified == filesystem_last_modified
+    assert all(e.metadata.last_modified == filesystem_last_modified for e in elements)
 
 
-def test_partition_xml_from_file_path_prefers_metadata_last_modified(mocker: MockFixture):
+def test_partition_epub_from_file_gets_last_modified_None():
+    with open(example_doc_path("simple.epub"), "rb") as f:
+        elements = partition_epub(file=f)
+
+    assert all(e.metadata.last_modified is None for e in elements)
+
+
+def test_partition_epub_from_file_path_prefers_metadata_last_modified(mocker: MockFixture):
     filesystem_last_modified = "2024-06-14T16:01:29"
     metadata_last_modified = "2020-03-08T06:10:23"
     mocker.patch(
@@ -89,6 +114,14 @@ def test_partition_xml_from_file_path_prefers_metadata_last_modified(mocker: Moc
     assert all(e.metadata.last_modified == metadata_last_modified for e in elements)
 
 
+def test_partition_epub_from_file_prefers_metadata_last_modified():
+    metadata_last_modified = "2020-03-08T06:10:23"
+    with open(example_doc_path("simple.epub"), "rb") as f:
+        elements = partition_epub(file=f, metadata_last_modified=metadata_last_modified)
+
+    assert all(e.metadata.last_modified is metadata_last_modified for e in elements)
+
+
 # ------------------------------------------------------------------------------------------------
 
 

test_unstructured/partition/test_md.py

@@ -17,55 +17,29 @@ from unstructured.partition.utils.constants import UNSTRUCTURED_INCLUDE_DEBUG_ME
 def test_partition_md_from_filename():
     filename = example_doc_path("README.md")
     elements = partition_md(filename=filename)
-    assert "PageBreak" not in [elem.category for elem in elements]
+
     assert len(elements) > 0
-    for element in elements:
-        assert element.metadata.filename == "README.md"
+    assert "PageBreak" not in [elem.category for elem in elements]
+    assert isinstance(elements[0], Title)
     if UNSTRUCTURED_INCLUDE_DEBUG_METADATA:
         assert {element.metadata.detection_origin for element in elements} == {"md"}
 
 
-def test_partition_md_from_filename_returns_uns_elements():
-    filename = example_doc_path("README.md")
-    elements = partition_md(filename=filename)
-    assert len(elements) > 0
-    assert isinstance(elements[0], Title)
-
-
-def test_partition_md_from_filename_with_metadata_filename():
-    filename = example_doc_path("README.md")
-    elements = partition_md(filename=filename, metadata_filename="test")
-    assert "PageBreak" not in [elem.category for elem in elements]
-    assert len(elements) > 0
-    for element in elements:
-        assert element.metadata.filename == "test"
-
-
 def test_partition_md_from_file():
     filename = example_doc_path("README.md")
     with open(filename, "rb") as f:
         elements = partition_md(file=f)
     assert len(elements) > 0
-    for element in elements:
-        assert element.metadata.filename is None
-
-
-def test_partition_md_from_file_with_metadata_filename():
-    filename = example_doc_path("README.md")
-    with open(filename, "rb") as f:
-        elements = partition_md(file=f, metadata_filename="test")
-    assert len(elements) > 0
-    assert all(element.metadata.filename == "test" for element in elements)
 
 
 def test_partition_md_from_text():
-    filename = example_doc_path("README.md")
-    with open(filename) as f:
+    with open(example_doc_path("README.md")) as f:
         text = f.read()
+
     elements = partition_md(text=text)
+
     assert len(elements) > 0
-    for element in elements:
-        assert element.metadata.filename is None
+    assert all(e.metadata.filename is None for e in elements)
 
 
 class MockResponse:
@@ -90,8 +64,7 @@ def test_partition_md_from_url():
         elements = partition_md(url="https://fake.url")
 
     assert len(elements) > 0
-    for element in elements:
-        assert element.metadata.filename is None
+    assert all(e.metadata.filename is None for e in elements)
 
 
 def test_partition_md_from_url_raises_with_bad_status_code():
@@ -136,6 +109,50 @@ def test_partition_md_raises_with_too_many_specified():
         partition_md(filename=filename, text=text)
 
 
+# -- .metadata.filename --------------------------------------------------------------------------
+
+
+def test_partition_md_from_filename_gets_filename_from_filename_arg():
+    elements = partition_md(example_doc_path("README.md"))
+
+    assert len(elements) > 0
+    assert all(e.metadata.filename == "README.md" for e in elements)
+
+
+def test_partition_md_from_file_gets_filename_None():
+    with open(example_doc_path("README.md"), "rb") as f:
+        elements = partition_md(file=f)
+
+    assert len(elements) > 0
+    assert all(e.metadata.filename is None for e in elements)
+
+
+def test_partition_md_from_filename_prefers_metadata_filename():
+    elements = partition_md(example_doc_path("README.md"), metadata_filename="orig-name.md")
+
+    assert len(elements) > 0
+    assert all(element.metadata.filename == "orig-name.md" for element in elements)
+
+
+def test_partition_md_from_file_prefers_metadata_filename():
+    with open(example_doc_path("README.md"), "rb") as f:
+        elements = partition_md(file=f, metadata_filename="orig-name.md")
+
+    assert all(e.metadata.filename == "orig-name.md" for e in elements)
+
+
+# -- .metadata.filetype --------------------------------------------------------------------------
+
+
+def test_partition_md_gets_the_MD_MIME_type_in_metadata_filetype():
+    MD_MIME_TYPE = "text/markdown"
+    elements = partition_md(example_doc_path("README.md"))
+    assert all(e.metadata.filetype == MD_MIME_TYPE for e in elements), (
+        f"Expected all elements to have '{MD_MIME_TYPE}' as their filetype, but got:"
+        f" {repr(elements[0].metadata.filetype)}"
+    )
+
+
 # -- .metadata.last_modified ---------------------------------------------------------------------
 
 

test_unstructured/partition/test_org.py

@@ -15,30 +15,61 @@ def test_partition_org_from_filename():
     assert elements[0].metadata.filetype == "text/org"
 
 
-def test_partition_org_from_filename_with_metadata_filename():
-    elements = partition_org(example_doc_path("README.org"), metadata_filename="test")
-
-    assert elements[0] == Title("Example Docs")
-    assert elements[0].metadata.filename == "test"
-
-
 def test_partition_org_from_file():
     with open(example_doc_path("README.org"), "rb") as f:
         elements = partition_org(file=f)
 
     assert elements[0] == Title("Example Docs")
-    assert elements[0].metadata.filetype == "text/org"
 
 
-def test_partition_org_from_file_with_metadata_filename():
+# -- .metadata.filename --------------------------------------------------------------------------
+
+
+def test_partition_org_from_filename_gets_filename_from_filename_arg():
+    elements = partition_org(example_doc_path("README.org"))
+
+    assert len(elements) > 0
+    assert all(e.metadata.filename == "README.org" for e in elements)
+
+
+def test_partition_org_from_file_gets_filename_None():
     with open(example_doc_path("README.org"), "rb") as f:
-        elements = partition_org(file=f, metadata_filename="test")
+        elements = partition_org(file=f)
 
-    assert elements[0] == Title("Example Docs")
-    assert elements[0].metadata.filename == "test"
+    assert len(elements) > 0
+    assert all(e.metadata.filename is None for e in elements)
 
 
-def test_partition_org_pulls_last_modified_from_filesystem(mocker: MockFixture):
+def test_partition_org_from_filename_prefers_metadata_filename():
+    elements = partition_org(example_doc_path("README.org"), metadata_filename="orig-name.org")
+
+    assert len(elements) > 0
+    assert all(element.metadata.filename == "orig-name.org" for element in elements)
+
+
+def test_partition_org_from_file_prefers_metadata_filename():
+    with open(example_doc_path("README.org"), "rb") as f:
+        elements = partition_org(file=f, metadata_filename="orig-name.org")
+
+    assert all(e.metadata.filename == "orig-name.org" for e in elements)
+
+
+# -- .metadata.filetype --------------------------------------------------------------------------
+
+
+def test_partition_org_gets_the_ORG_MIME_type_in_metadata_filetype():
+    ORG_MIME_TYPE = "text/org"
+    elements = partition_org(example_doc_path("README.org"))
+    assert all(e.metadata.filetype == ORG_MIME_TYPE for e in elements), (
+        f"Expected all elements to have '{ORG_MIME_TYPE}' as their filetype, but got:"
+        f" {repr(elements[0].metadata.filetype)}"
+    )
+
+
+# -- .metadata.last_modified ---------------------------------------------------------------------
+
+
+def test_partition_org_from_filename_gets_last_modified_from_filesystem(mocker: MockFixture):
     filesystem_last_modified = "2024-06-14T16:01:29"
     mocker.patch(
         "unstructured.partition.org.get_last_modified_date", return_value=filesystem_last_modified
@@ -46,10 +77,17 @@ def test_partition_org_pulls_last_modified_from_filesystem(mocker: MockFixture):
 
     elements = partition_org(example_doc_path("README.org"))
 
-    assert elements[0].metadata.last_modified == filesystem_last_modified
+    assert all(e.metadata.last_modified == filesystem_last_modified for e in elements)
 
 
-def test_partition_org_prefers_metadata_last_modified(mocker: MockFixture):
+def test_partition_org_from_file_gets_last_modified_None():
+    with open(example_doc_path("README.org"), "rb") as f:
+        elements = partition_org(file=f)
+
+    assert all(e.metadata.last_modified is None for e in elements)
+
+
+def test_partition_org_from_filename_prefers_metadata_last_modified(mocker: MockFixture):
     filesystem_last_modified = "2020-08-04T06:11:47"
     metadata_last_modified = "2024-06-14T16:01:29"
     mocker.patch(
@@ -63,6 +101,17 @@ def test_partition_org_prefers_metadata_last_modified(mocker: MockFixture):
     assert all(e.metadata.last_modified == metadata_last_modified for e in elements)
 
 
+def test_partition_org_from_file_prefers_metadata_last_modified():
+    metadata_last_modified = "2020-07-05T09:24:28"
+    with open(example_doc_path("README.org"), "rb") as f:
+        elements = partition_org(file=f, metadata_last_modified=metadata_last_modified)
+
+    assert all(e.metadata.last_modified == metadata_last_modified for e in elements)
+
+
+# ------------------------------------------------------------------------------------------------
+
+
 def test_partition_org_with_json():
     elements = partition_org(example_doc_path("README.org"))
     assert_round_trips_through_JSON(elements)

test_unstructured/partition/test_rst.py

@@ -10,21 +10,7 @@ from unstructured.partition.rst import partition_rst
 
 def test_partition_rst_from_filename():
     elements = partition_rst(example_doc_path("README.rst"))
-
     assert elements[0] == Title("Example Docs")
-    assert elements[0].metadata.filetype == "text/x-rst"
-    for element in elements:
-        assert element.metadata.filename == "README.rst"
-
-
-def test_partition_rst_from_filename_returns_uns_elements():
-    elements = partition_rst(example_doc_path("README.rst"))
-    assert isinstance(elements[0], Title)
-
-
-def test_partition_rst_from_filename_with_metadata_filename():
-    elements = partition_rst(example_doc_path("README.rst"), metadata_filename="test")
-    assert all(element.metadata.filename == "test" for element in elements)
 
 
 def test_partition_rst_from_file():
@@ -32,18 +18,50 @@ def test_partition_rst_from_file():
         elements = partition_rst(file=f)
 
     assert elements[0] == Title("Example Docs")
-    assert elements[0].metadata.filetype == "text/x-rst"
-    for element in elements:
-        assert element.metadata.filename is None
 
 
-def test_partition_rst_from_file_with_metadata_filename():
+# -- .metadata.filename --------------------------------------------------------------------------
+
+
+def test_partition_rst_from_filename_gets_filename_from_filename_arg():
+    elements = partition_rst(example_doc_path("README.rst"))
+
+    assert len(elements) > 0
+    assert all(e.metadata.filename == "README.rst" for e in elements)
+
+
+def test_partition_rst_from_file_gets_filename_None():
     with open(example_doc_path("README.rst"), "rb") as f:
-        elements = partition_rst(file=f, metadata_filename="test")
+        elements = partition_rst(file=f)
 
-    assert elements[0] == Title("Example Docs")
-    for element in elements:
-        assert element.metadata.filename == "test"
+    assert len(elements) > 0
+    assert all(e.metadata.filename is None for e in elements)
+
+
+def test_partition_rst_from_filename_prefers_metadata_filename():
+    elements = partition_rst(example_doc_path("README.rst"), metadata_filename="orig-name.rst")
+
+    assert len(elements) > 0
+    assert all(element.metadata.filename == "orig-name.rst" for element in elements)
+
+
+def test_partition_rst_from_file_prefers_metadata_filename():
+    with open(example_doc_path("README.rst"), "rb") as f:
+        elements = partition_rst(file=f, metadata_filename="orig-name.rst")
+
+    assert all(e.metadata.filename == "orig-name.rst" for e in elements)
+
+
+# -- .metadata.filetype --------------------------------------------------------------------------
+
+
+def test_partition_rst_gets_the_RST_MIME_type_in_metadata_filetype():
+    RST_MIME_TYPE = "text/x-rst"
+    elements = partition_rst(example_doc_path("README.rst"))
+    assert all(e.metadata.filetype == RST_MIME_TYPE for e in elements), (
+        f"Expected all elements to have '{RST_MIME_TYPE}' as their filetype, but got:"
+        f" {repr(elements[0].metadata.filetype)}"
+    )
 
 
 # -- .metadata.last_modified ---------------------------------------------------------------------

test_unstructured/partition/test_rtf.py

@@ -9,41 +9,68 @@ from unstructured.partition.rtf import partition_rtf
 
 
 def test_partition_rtf_from_filename():
-    filename = example_doc_path("fake-doc.rtf")
-    elements = partition_rtf(filename=filename)
+    elements = partition_rtf(example_doc_path("fake-doc.rtf"))
+
     assert len(elements) > 0
     assert elements[0] == Title("My First Heading")
     assert elements[-1] == Table(
         text="Column 1 Column 2 Row 1, Cell 1 Row 1, Cell 2 Row 2, Cell 1 Row 2, Cell 2"
     )
-    for element in elements:
-        assert element.metadata.filename == "fake-doc.rtf"
-
-
-def test_partition_rtf_from_filename_with_metadata_filename():
-    filename = example_doc_path("fake-doc.rtf")
-    elements = partition_rtf(filename=filename, metadata_filename="test")
-    assert len(elements) > 0
-    assert all(element.metadata.filename == "test" for element in elements)
 
 
 def test_partition_rtf_from_file():
-    filename = example_doc_path("fake-doc.rtf")
-    with open(filename, "rb") as f:
+    with open(example_doc_path("fake-doc.rtf"), "rb") as f:
         elements = partition_rtf(file=f)
+
     assert len(elements) > 0
     assert elements[0] == Title("My First Heading")
-    for element in elements:
-        assert element.metadata.filename is None
 
 
-def test_partition_rtf_from_file_with_metadata_filename():
-    filename = example_doc_path("fake-doc.rtf")
-    with open(filename, "rb") as f:
-        elements = partition_rtf(file=f, metadata_filename="test")
-    assert elements[0] == Title("My First Heading")
-    for element in elements:
-        assert element.metadata.filename == "test"
+# -- .metadata.filename --------------------------------------------------------------------------
+
+
+def test_partition_rtf_from_filename_gets_filename_from_filename_arg():
+    elements = partition_rtf(example_doc_path("fake-doc.rtf"))
+
+    assert len(elements) > 0
+    assert all(e.metadata.filename == "fake-doc.rtf" for e in elements)
+
+
+def test_partition_rtf_from_file_gets_filename_None():
+    with open(example_doc_path("fake-doc.rtf"), "rb") as f:
+        elements = partition_rtf(file=f)
+
+    assert len(elements) > 0
+    assert all(e.metadata.filename is None for e in elements)
+
+
+def test_partition_rtf_from_filename_prefers_metadata_filename():
+    elements = partition_rtf(example_doc_path("fake-doc.rtf"), metadata_filename="orig-name.rtf")
+
+    assert len(elements) > 0
+    assert all(element.metadata.filename == "orig-name.rtf" for element in elements)
+
+
+def test_partition_rtf_from_file_prefers_metadata_filename():
+    with open(example_doc_path("fake-doc.rtf"), "rb") as f:
+        elements = partition_rtf(file=f, metadata_filename="orig-name.rtf")
+
+    assert all(e.metadata.filename == "orig-name.rtf" for e in elements)
+
+
+# -- .metadata.filetype --------------------------------------------------------------------------
+
+
+def test_partition_rtf_gets_the_RTF_MIME_type_in_metadata_filetype():
+    RTF_MIME_TYPE = "text/rtf"
+    elements = partition_rtf(example_doc_path("fake-doc.rtf"))
+    assert all(e.metadata.filetype == RTF_MIME_TYPE for e in elements), (
+        f"Expected all elements to have '{RTF_MIME_TYPE}' as their filetype, but got:"
+        f" {repr(elements[0].metadata.filetype)}"
+    )
+
+
+# -- .metadata.last_modified ---------------------------------------------------------------------
 
 
 def test_partition_rtf_pulls_last_modified_from_filesystem(mocker: MockFixture):
@@ -70,6 +97,9 @@ def test_partition_rtf_prefers_metadata_last_modified(mocker: MockFixture):
     assert all(e.metadata.last_modified == metadata_last_modified for e in elements)
 
 
+# -- other ---------------------------------------------------------------------------------------
+
+
 def test_partition_rtf_with_json():
     elements = partition_rtf(filename=example_doc_path("fake-doc.rtf"))
     assert_round_trips_through_JSON(elements)

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.15.14-dev8"  # pragma: no cover
+__version__ = "0.15.14-dev9"  # pragma: no cover

unstructured/partition/epub.py

@@ -2,10 +2,8 @@ from __future__ import annotations
 
 from typing import IO, Any, Optional
 
-from unstructured.chunking import add_chunking_strategy
-from unstructured.documents.elements import Element, process_metadata
+from unstructured.documents.elements import Element
 from unstructured.file_utils.file_conversion import convert_file_to_html_text_using_pandoc
-from unstructured.file_utils.filetype import add_metadata_with_filetype
 from unstructured.file_utils.model import FileType
 from unstructured.partition.common.common import exactly_one
 from unstructured.partition.common.metadata import get_last_modified_date
@@ -14,9 +12,6 @@ from unstructured.partition.html import partition_html
 DETECTION_ORIGIN: str = "epub"
 
 
-@process_metadata()
-@add_metadata_with_filetype(FileType.EPUB)
-@add_chunking_strategy
 def partition_epub(
     filename: Optional[str] = None,
     *,
@@ -57,9 +52,11 @@ def partition_epub(
     return partition_html(
         text=html_text,
         encoding="unicode",
-        metadata_filename=metadata_filename,
+        metadata_filename=metadata_filename or filename,
+        metadata_file_type=FileType.EPUB,
         metadata_last_modified=metadata_last_modified or last_modified,
         languages=languages,
         detect_language_per_element=detect_language_per_element,
         detection_origin=DETECTION_ORIGIN,
+        **kwargs,
     )

unstructured/partition/html/partition.py

@@ -10,18 +10,15 @@ import requests
 from lxml import etree
 
 from unstructured.chunking import add_chunking_strategy
-from unstructured.documents.elements import Element, process_metadata
+from unstructured.documents.elements import Element
 from unstructured.file_utils.encoding import read_txt_file
-from unstructured.file_utils.filetype import add_metadata_with_filetype
 from unstructured.file_utils.model import FileType
-from unstructured.partition.common.lang import apply_lang_metadata
-from unstructured.partition.common.metadata import get_last_modified_date
+from unstructured.partition.common.metadata import apply_metadata, get_last_modified_date
 from unstructured.partition.html.parser import Flow, html_parser
 from unstructured.utils import is_temp_file_path, lazyproperty
 
 
-@process_metadata()
-@add_metadata_with_filetype(FileType.HTML)
+@apply_metadata(FileType.HTML)
 @add_chunking_strategy
 def partition_html(
     filename: Optional[str] = None,
@@ -32,9 +29,6 @@ def partition_html(
     url: Optional[str] = None,
     headers: dict[str, str] = {},
     ssl_verify: bool = True,
-    detect_language_per_element: bool = False,
-    languages: Optional[list[str]] = ["auto"],
-    metadata_last_modified: Optional[str] = None,
     skip_headers_and_footers: bool = False,
     detection_origin: Optional[str] = None,
     **kwargs: Any,
@@ -60,18 +54,6 @@ def partition_html(
         on the HTTP request.
     encoding
         The encoding method used to decode the text input. If None, utf-8 will be used.
-
-    Other parameters
-    ----------------
-    languages
-        User defined value for `metadata.languages` if provided. Otherwise language is detected
-        using naive Bayesian filter via `langdetect`. Multiple languages indicates text could be
-        in either language.
-        Additional Parameters:
-            detect_language_per_element
-                Detect language per element instead of at the document level.
-    metadata_last_modified
-        The last modified date for the document.
     skip_headers_and_footers
         If True, ignores any content that is within <header> or <footer> tags
     """
@@ -87,20 +69,11 @@ def partition_html(
         url=url,
         headers=headers,
         ssl_verify=ssl_verify,
-        metadata_last_modified=metadata_last_modified,
         skip_headers_and_footers=skip_headers_and_footers,
         detection_origin=detection_origin,
     )
 
-    elements = list(
-        apply_lang_metadata(
-            _HtmlPartitioner.iter_elements(opts),
-            languages=languages,
-            detect_language_per_element=detect_language_per_element,
-        )
-    )
-
-    return elements
+    return list(_HtmlPartitioner.iter_elements(opts))
 
 
 class HtmlPartitionerOptions:
@@ -116,7 +89,6 @@ class HtmlPartitionerOptions:
         url: str | None,
         headers: dict[str, str],
         ssl_verify: bool,
-        metadata_last_modified: str | None,
         skip_headers_and_footers: bool,
         detection_origin: str | None,
     ):
@@ -127,7 +99,6 @@ class HtmlPartitionerOptions:
         self._url = url
         self._headers = headers
         self._ssl_verify = ssl_verify
-        self._metadata_last_modified = metadata_last_modified
         self._skip_headers_and_footers = skip_headers_and_footers
         self._detection_origin = detection_origin
 
@@ -173,19 +144,11 @@ class HtmlPartitionerOptions:
     @lazyproperty
     def last_modified(self) -> str | None:
         """The best last-modified date available, None if no sources are available."""
-        # -- Value explicitly specified by caller takes precedence. This is used for example when
-        # -- this file was converted from another format.
-        if self._metadata_last_modified:
-            return self._metadata_last_modified
-
-        if self._file_path:
-            return (
-                None
-                if is_temp_file_path(self._file_path)
-                else get_last_modified_date(self._file_path)
-            )
-
-        return None
+        return (
+            None
+            if not self._file_path or is_temp_file_path(self._file_path)
+            else get_last_modified_date(self._file_path)
+        )
 
     @lazyproperty
     def skip_headers_and_footers(self) -> bool:

unstructured/partition/md.py

@@ -1,20 +1,18 @@
 from __future__ import annotations
 
-from typing import IO, Any, Optional, Union
+from typing import IO, Any
 
 import markdown
 import requests
 
-from unstructured.chunking import add_chunking_strategy
-from unstructured.documents.elements import Element, process_metadata
-from unstructured.file_utils.filetype import add_metadata_with_filetype
+from unstructured.documents.elements import Element
 from unstructured.file_utils.model import FileType
 from unstructured.partition.common.common import exactly_one
 from unstructured.partition.common.metadata import get_last_modified_date
 from unstructured.partition.html import partition_html
 
 
-def optional_decode(contents: Union[str, bytes]) -> str:
+def optional_decode(contents: str | bytes) -> str:
     if isinstance(contents, bytes):
         return contents.decode("utf-8")
     return contents
@@ -23,19 +21,13 @@ def optional_decode(contents: Union[str, bytes]) -> str:
 DETECTION_ORIGIN: str = "md"
 
 
-@process_metadata()
-@add_metadata_with_filetype(FileType.MD)
-@add_chunking_strategy
 def partition_md(
-    filename: Optional[str] = None,
-    file: Optional[IO[bytes]] = None,
-    text: Optional[str] = None,
-    url: Optional[str] = None,
-    include_page_breaks: bool = False,
-    metadata_filename: Optional[str] = None,
-    metadata_last_modified: Optional[str] = None,
-    languages: Optional[list[str]] = ["auto"],
-    detect_language_per_element: bool = False,
+    filename: str | None = None,
+    file: IO[bytes] | None = None,
+    text: str | None = None,
+    url: str | None = None,
+    metadata_filename: str | None = None,
+    metadata_last_modified: str | None = None,
     **kwargs: Any,
 ) -> list[Element]:
     """Partitions a markdown file into its constituent elements
@@ -50,24 +42,13 @@ def partition_md(
         The string representation of the markdown document.
     url
         The URL of a webpage to parse. Only for URLs that return a markdown document.
-    include_page_breaks
-        If True, the output will include page breaks if the filetype supports it.
-    parser
-        The parser to use for parsing the markdown document. If None, default parser will be used.
     metadata_last_modified
         The last modified date for the document.
-    languages
-        User defined value for `metadata.languages` if provided. Otherwise language is detected
-        using naive Bayesian filter via `langdetect`. Multiple languages indicates text could be
-        in either language.
-        Additional Parameters:
-            detect_language_per_element
-                Detect language per element instead of at the document level.
     """
-    # Verify that only one of the arguments was provided
     if text is None:
         text = ""
 
+    # -- verify that only one of the arguments was provided --
     exactly_one(filename=filename, file=file, text=text, url=url)
 
     last_modified = get_last_modified_date(filename) if filename else None
@@ -96,11 +77,9 @@ def partition_md(
 
     return partition_html(
         text=html,
-        include_page_breaks=include_page_breaks,
-        source_format="md",
-        metadata_filename=metadata_filename,
+        metadata_filename=metadata_filename or filename,
+        metadata_file_type=FileType.MD,
         metadata_last_modified=metadata_last_modified or last_modified,
-        languages=languages,
-        detect_language_per_element=detect_language_per_element,
         detection_origin=DETECTION_ORIGIN,
+        **kwargs,
     )

unstructured/partition/org.py

@@ -1,11 +1,9 @@
 from __future__ import annotations
 
-from typing import IO, Any, Optional
+from typing import IO, Any
 
-from unstructured.chunking import add_chunking_strategy
 from unstructured.documents.elements import Element
 from unstructured.file_utils.file_conversion import convert_file_to_html_text_using_pandoc
-from unstructured.file_utils.filetype import add_metadata_with_filetype
 from unstructured.file_utils.model import FileType
 from unstructured.partition.common.common import exactly_one
 from unstructured.partition.common.metadata import get_last_modified_date
@@ -14,16 +12,12 @@ from unstructured.partition.html import partition_html
 DETECTION_ORIGIN: str = "org"
 
 
-@add_metadata_with_filetype(FileType.ORG)
-@add_chunking_strategy
 def partition_org(
-    filename: Optional[str] = None,
+    filename: str | None = None,
     *,
-    file: Optional[IO[bytes]] = None,
-    metadata_filename: Optional[str] = None,
-    metadata_last_modified: Optional[str] = None,
-    languages: Optional[list[str]] = ["auto"],
-    detect_language_per_element: bool = False,
+    file: IO[bytes] | None = None,
+    metadata_filename: str | None = None,
+    metadata_last_modified: str | None = None,
     **kwargs: Any,
 ) -> list[Element]:
     """Partitions an org document. The document is first converted to HTML and then
@@ -37,13 +31,6 @@ def partition_org(
         A file-like object using "rb" mode --> open(filename, "rb").
     metadata_last_modified
         The last modified date for the document.
-    languages
-        User defined value for `metadata.languages` if provided. Otherwise language is detected
-        using naive Bayesian filter via `langdetect`. Multiple languages indicates text could be
-        in either language.
-        Additional Parameters:
-            detect_language_per_element
-                Detect language per element instead of at the document level.
     """
     exactly_one(filename=filename, file=file)
 
@@ -56,9 +43,9 @@ def partition_org(
     return partition_html(
         text=html_text,
         encoding="unicode",
-        metadata_filename=metadata_filename,
+        metadata_filename=metadata_filename or filename,
+        metadata_file_type=FileType.ORG,
         metadata_last_modified=metadata_last_modified or last_modified,
-        languages=languages,
-        detect_language_per_element=detect_language_per_element,
         detection_origin=DETECTION_ORIGIN,
+        **kwargs,
     )

unstructured/partition/rst.py

@@ -2,10 +2,8 @@ from __future__ import annotations
 
 from typing import IO, Any, Optional
 
-from unstructured.chunking import add_chunking_strategy
-from unstructured.documents.elements import Element, process_metadata
+from unstructured.documents.elements import Element
 from unstructured.file_utils.file_conversion import convert_file_to_html_text_using_pandoc
-from unstructured.file_utils.filetype import add_metadata_with_filetype
 from unstructured.file_utils.model import FileType
 from unstructured.partition.common.common import exactly_one
 from unstructured.partition.common.metadata import get_last_modified_date
@@ -14,17 +12,12 @@ from unstructured.partition.html import partition_html
 DETECTION_ORIGIN: str = "rst"
 
 
-@process_metadata()
-@add_metadata_with_filetype(FileType.RST)
-@add_chunking_strategy
 def partition_rst(
     filename: Optional[str] = None,
     *,
     file: Optional[IO[bytes]] = None,
     metadata_filename: Optional[str] = None,
     metadata_last_modified: Optional[str] = None,
-    languages: Optional[list[str]] = ["auto"],
-    detect_language_per_element: bool = False,
     **kwargs: Any,
 ) -> list[Element]:
     """Partitions an RST document. The document is first converted to HTML and then
@@ -38,13 +31,6 @@ def partition_rst(
         A file-like object using "rb" mode --> open(filename, "rb").
     metadata_last_modified
         The last modified date for the document.
-    languages
-        User defined value for `metadata.languages` if provided. Otherwise language is detected
-        using naive Bayesian filter via `langdetect`. Multiple languages indicates text could be
-        in either language.
-        Additional Parameters:
-            detect_language_per_element
-                Detect language per element instead of at the document level.
     """
     exactly_one(filename=filename, file=file)
 
@@ -57,9 +43,9 @@ def partition_rst(
     return partition_html(
         text=html_text,
         encoding="unicode",
-        metadata_filename=metadata_filename,
+        metadata_filename=metadata_filename or filename,
+        metadata_file_type=FileType.RST,
         metadata_last_modified=metadata_last_modified or last_modified,
-        languages=languages,
-        detect_language_per_element=detect_language_per_element,
         detection_origin=DETECTION_ORIGIN,
+        **kwargs,
     )

unstructured/partition/rtf.py

@@ -2,10 +2,8 @@ from __future__ import annotations
 
 from typing import IO, Any, Optional
 
-from unstructured.chunking import add_chunking_strategy
-from unstructured.documents.elements import Element, process_metadata
+from unstructured.documents.elements import Element
 from unstructured.file_utils.file_conversion import convert_file_to_html_text_using_pandoc
-from unstructured.file_utils.filetype import add_metadata_with_filetype
 from unstructured.file_utils.model import FileType
 from unstructured.partition.common.common import exactly_one
 from unstructured.partition.common.metadata import get_last_modified_date
@@ -14,17 +12,12 @@ from unstructured.partition.html import partition_html
 DETECTION_ORIGIN: str = "rtf"
 
 
-@process_metadata()
-@add_metadata_with_filetype(FileType.RTF)
-@add_chunking_strategy
 def partition_rtf(
     filename: Optional[str] = None,
     *,
     file: Optional[IO[bytes]] = None,
     metadata_filename: Optional[str] = None,
     metadata_last_modified: Optional[str] = None,
-    languages: Optional[list[str]] = ["auto"],
-    detect_language_per_element: bool = False,
     **kwargs: Any,
 ) -> list[Element]:
     """Partitions an RTF document. The document is first converted to HTML and then
@@ -38,13 +31,6 @@ def partition_rtf(
         A file-like object using "rb" mode --> open(filename, "rb").
     metadata_last_modified
         The last modified date for the document.
-    languages
-        User defined value for `metadata.languages` if provided. Otherwise language is detected
-        using naive Bayesian filter via `langdetect`. Multiple languages indicates text could be
-        in either language.
-        Additional Parameters:
-            detect_language_per_element
-                Detect language per element instead of at the document level.
     """
     exactly_one(filename=filename, file=file)
 
@@ -57,9 +43,9 @@ def partition_rtf(
     return partition_html(
         text=html_text,
         encoding="unicode",
-        metadata_filename=metadata_filename,
+        metadata_filename=metadata_filename or filename,
+        metadata_file_type=FileType.RTF,
         metadata_last_modified=metadata_last_modified or last_modified,
-        languages=languages,
-        detect_language_per_element=detect_language_per_element,
         detection_origin=DETECTION_ORIGIN,
+        **kwargs,
     )