fix: text kwargs no longer fail with empty string (#413)

* fix: text kwargs no longer fail with empty string

* linting

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.5.8-dev0
+## 0.5.8-dev1
 
 ### Enhancements
 
@@ -11,6 +11,9 @@
 ### Fixes
 
 * `convert_file_to_text` now passes through the `source_format` and `target_format` kwargs.
+* 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.
 
 ## 0.5.7
 

test_unstructured/partition/test_email.py

@@ -140,6 +140,10 @@ def test_partition_email_from_text():
     assert elements == EXPECTED_OUTPUT
 
 
+def test_partition_email_from_text_work_with_empty_string():
+    assert partition_email(text="") == []
+
+
 def test_partition_email_from_filename_with_embedded_image():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-email-image-embedded.eml")
     elements = partition_email(filename=filename, content_source="text/plain")

test_unstructured/partition/test_html_partition.py

@@ -41,6 +41,10 @@ def test_partition_html_from_text():
     assert len(elements) > 0
 
 
+def test_partition_html_from_text_works_with_empty_string():
+    assert partition_html(text="") == []
+
+
 class MockResponse:
     def __init__(self, text, status_code, headers={}):
         self.text = text

test_unstructured/partition/test_json.py

@@ -87,6 +87,14 @@ def test_partition_json_raises_with_none_specified():
         partition_json()
 
 
+def test_partition_json_works_with_empty_string():
+    assert partition_json(text="") == []
+
+
+def test_partition_json_works_with_empty_list():
+    assert partition_json(text="[]") == []
+
+
 def test_partition_json_raises_with_too_many_specified():
     path = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-text.txt")
     elements = partition(filename=path)

test_unstructured/partition/test_text.py

@@ -59,6 +59,10 @@ def test_partition_text_from_text():
     assert elements == EXPECTED_OUTPUT
 
 
+def test_partition_text_from_text_works_with_empty_string():
+    assert partition_text(text="") == []
+
+
 def test_partition_text_raises_with_none_specified():
     with pytest.raises(ValueError):
         partition_text()

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.5.8-dev0"  # pragma: no cover
+__version__ = "0.5.8-dev1"  # pragma: no cover

unstructured/partition/email.py

@@ -168,6 +168,9 @@ def partition_email(
             f"Valid content sources are: {VALID_CONTENT_SOURCES}",
         )
 
+    if text is not None and text.strip() == "" and not file and not filename:
+        return []
+
     # Verify that only one of the arguments was provided
     exactly_one(filename=filename, file=file, text=text)
 

unstructured/partition/html.py

@@ -45,6 +45,9 @@ def partition_html(
     parser
         The parser to use for parsing the HTML document. If None, default parser will be used.
     """
+    if text is not None and text.strip() == "" and not file and not filename and not url:
+        return []
+
     # Verify that only one of the arguments was provided
     exactly_one(filename=filename, file=file, text=text, url=url)
 

unstructured/partition/json.py

@@ -6,7 +6,7 @@ from unstructured.documents.elements import Element
 from unstructured.partition.common import exactly_one
 from unstructured.staging.base import dict_to_elements
 
-LIST_OF_DICTS_PATTERN = r"\A\s*\[\s*{"
+LIST_OF_DICTS_PATTERN = r"\A\s*\[\s*{?"
 
 
 def partition_json(
@@ -15,6 +15,9 @@ def partition_json(
     text: Optional[str] = None,
 ) -> List[Element]:
     """Partitions an .json document into its constituent elements."""
+    if text is not None and text.strip() == "" and not file and not filename:
+        return []
+
     exactly_one(filenmae=filename, file=file, text=text)
 
     if filename is not None:

unstructured/partition/text.py

@@ -43,6 +43,8 @@ def partition_text(
     encoding
         The encoding method used to decode the text input. If None, utf-8 will be used.
     """
+    if text is not None and text.strip() == "" and not file and not filename:
+        return []
 
     # Verify that only one of the arguments was provided
     exactly_one(filename=filename, file=file, text=text)