Fixing test for unstructured-api (#425)

Ran into an error in tests for unstructured-api (see below for output). Somewhere along the lines we were reading a txt file into bytes and then the PARAGRAPH_PATTERN (a string) was not able to be compared to the bytes file.

Author: amanda103

CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.5.9
+
+### Enhancements
+
+### Features
+
+### Fixes
+
+* Convert file to str in helper `split_by_paragraph` for `partition_text`
+
 ## 0.5.8
 
 ### Enhancements

test_unstructured/partition/test_text.py

@@ -50,6 +50,14 @@ def test_partition_text_from_file():
     assert elements == EXPECTED_OUTPUT
 
 
+def test_partition_text_from_bytes_file():
+    filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-text.txt")
+    with open(filename, "rb") as f:
+        elements = partition_text(file=f)
+    assert len(elements) > 0
+    assert elements == EXPECTED_OUTPUT
+
+
 def test_partition_text_from_text():
     filename = os.path.join(DIRECTORY, "..", "..", "example-docs", "fake-text.txt")
     with open(filename) as f:

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.5.8"  # pragma: no cover
+__version__ = "0.5.9"  # pragma: no cover

unstructured/partition/text.py

@@ -58,6 +58,8 @@ def partition_text(
 
     elif file is not None:
         file_text = file.read()
+        if isinstance(file_text, bytes):
+            file_text = file_text.decode(encoding)
 
     elif text is not None:
         file_text = str(text)