fix: correct order of kwargs in pandoc (#421)

* fix: correct order of kwargs in pandoc

* only skip epub tests in Docker

* changelog

---------

Co-authored-by: Crag Wolfe <[email protected]>
Co-authored-by: cragwolfe <[email protected]>

Author: MthwRobinson

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.5.8-dev6
+## 0.5.8
 
 ### Enhancements
 
@@ -16,6 +16,7 @@
 ### Fixes
 
 * `convert_file_to_text` now passes through the `source_format` and `target_format` kwargs.
+  Previously they were hard coded.
 * Partitioning functions that accept a `text` kwarg no longer raise an error if an empty
   string is passed (and empty list of elements is returned instead).
 * `partition_json` no longer fails if the input is an empty list.

test_unstructured/partition/test_auto.py

@@ -28,6 +28,8 @@
     ListItem(text="Violets are blue"),
 ]
 
+is_in_docker = os.path.exists("/.dockerenv")
+
 
 def test_auto_partition_email_from_filename():
     filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-email.eml")
@@ -312,7 +314,7 @@ def test_auto_partition_pptx_from_filename():
     assert elements[0].metadata.filename == filename
 
 
-@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
+@pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
 def test_auto_partition_ppt_from_filename():
     filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "fake-power-point.ppt")
     elements = partition(filename=filename)
@@ -326,15 +328,15 @@ def test_auto_with_page_breaks():
     assert PageBreak() in elements
 
 
-@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
+@pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
 def test_auto_partition_epub_from_filename():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
     elements = partition(filename=filename)
     assert len(elements) > 0
     assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
 
 
-@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
+@pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
 def test_auto_partition_epub_from_file():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
     with open(filename, "rb") as f:

test_unstructured/partition/test_epub.py

@@ -7,16 +7,18 @@
 
 DIRECTORY = pathlib.Path(__file__).parent.resolve()
 
+is_in_docker = os.path.exists("/.dockerenv")
 
-@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
+
+@pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
 def test_partition_epub_from_filename():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
     elements = partition_epub(filename=filename)
     assert len(elements) > 0
     assert elements[0].text.startswith("The Project Gutenberg eBook of Winter Sports")
 
 
-@pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test")
+@pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container")
 def test_partition_epub_from_file():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "winter-sports.epub")
     with open(filename, "rb") as f:

test_unstructured/partition/test_json.py

@@ -10,6 +10,8 @@
 
 DIRECTORY = pathlib.Path(__file__).parent.resolve()
 
+is_in_docker = os.path.exists("/.dockerenv")
+
 test_files = [
     "fake-text.txt",
     "layout-parser-paper-fast.pdf",
@@ -18,12 +20,14 @@
     "fake-email.eml",
     pytest.param(
         "fake-power-point.ppt",
-        marks=pytest.mark.xfail(reason="Requirements mismatch, should only fail in docker test"),
+        marks=pytest.mark.skipif(is_in_docker, reason="Skipping this test in Docker container"),
     ),
     "fake.docx",
     "fake-power-point.pptx",
 ]
 
+is_in_docker = os.path.exists("/.dockerenv")
+
 
 @pytest.mark.parametrize("filename", test_files)
 def test_partition_json_from_filename(filename: str):

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.5.8-dev6"  # pragma: no cover
+__version__ = "0.5.8"  # pragma: no cover

unstructured/file_utils/file_conversion.py

@@ -9,7 +9,7 @@
 def convert_file_to_text(filename: str, source_format: str, target_format: str) -> str:
     """Uses pandoc to convert the source document to a raw text string."""
     try:
-        text = pypandoc.convert_file(filename, source_format, format=target_format)
+        text = pypandoc.convert_file(filename, target_format, format=source_format)
     except FileNotFoundError as err:
         msg = (
             "Error converting the file to text. Ensure you have the pandoc "