fix: ElementMetadata serializes when the filename is a Path object (#233)

Author: MthwRobinson

Diff for: CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.4.10
+
+* Fixes `ElementMetadata` so that it's JSON serializable when the filename is a `Path` object.
+
 ## 0.4.9
 
 * Added ingest modules and s3 connector, sample ingest script

Diff for: test_unstructured/staging/test_base_staging.py

@@ -1,12 +1,14 @@
 import csv
+import json
 import os
+import pathlib
 import pytest
 
 import pandas as pd
 
 import unstructured.staging.base as base
 
-from unstructured.documents.elements import Title, NarrativeText, ListItem
+from unstructured.documents.elements import ElementMetadata, Title, NarrativeText, ListItem
 
 
 @pytest.fixture
@@ -64,3 +66,14 @@ def test_convert_to_dataframe():
     )
     assert df.type.equals(expected_df.type) is True
     assert df.text.equals(expected_df.text) is True
+
+
+def test_convert_to_isd_serializes_with_posix_paths():
+    metadata = ElementMetadata(filename=pathlib.PosixPath("../../fake-file.txt"))
+    elements = [
+        Title(text="Title 1", metadata=metadata),
+        NarrativeText(text="Narrative 1", metadata=metadata),
+    ]
+    output = base.convert_to_isd(elements)
+    # NOTE(robinson) - json.dumps should run without raising an exception
+    json.dumps(output)

Diff for: unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.4.9"  # pragma: no cover
+__version__ = "0.4.10"  # pragma: no cover

Diff for: unstructured/documents/elements.py

@@ -2,6 +2,7 @@
 from dataclasses import dataclass
 import hashlib
 from typing import Callable, List, Optional, Union
+import pathlib
 
 
 class NoID(ABC):
@@ -16,6 +17,10 @@ class ElementMetadata:
     page_number: Optional[int] = None
     url: Optional[str] = None
 
+    def __post_init__(self):
+        if isinstance(self.filename, pathlib.Path):
+            self.filename = str(self.filename)
+
     def to_dict(self):
         return {key: value for key, value in self.__dict__.items() if value is not None}