fix: link_texts was breaking postgres destination connector (#2460)

Formatting of link_texts was breaking metadata storage. Turns out it
didn't need any conforming and came in correctly from json.

---------

Co-authored-by: potter-potter <david.potter@gmail.com>

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.12.3-dev6
+## 0.12.3-dev7
 
 ### Enhancements
 
@@ -17,6 +17,7 @@
 * **Fix databricks-volumes extra location.** `setup.py` is currently pointing to the wrong location for the databricks-volumes extra requirements. This results in errors when trying to build the wheel for unstructured. This change updates to point to the correct path.
 * **Fix uploading None values to Chroma and Pinecone.** Removes keys with None values with Pinecone and Chroma destinations. Pins Pinecone dependency
 * **Update documentation.** (i) best practice for table extration by using 'skip_infer_table_types' param, instead of 'pdf_infer_table_structure', and (ii) fixed CSS, RST issues and typo in the documentation.
+* **Fix postgres storage of link_texts.** Formatting of link_texts was breaking metadata storage.
 
 
 ## 0.12.2

test_unstructured_ingest/unit/test_sql_conform_dict.py

@@ -60,6 +60,23 @@ TEST_DATA_2 = {
     "embeddings": [0.1, 0.2, 0.3],
 }
 
+TEST_DATA_3 = {
+    "metadata": {
+        "coordinates": {"points": [1, 2, 3]},
+        "data_source": {
+            "date_created": "2021-01-01T00:00:00",
+            "date_modified": "2021-01-02T00:00:00",
+            "date_processed": "2022-12-13T15:44:08",
+            "version": 1.1,
+        },
+        "last_modified": "2021-01-03T00:00:00",
+        "page_number": 10,
+        "link_texts": ["Skip to main content"],
+        "link_urls": ["#main-content"],
+    },
+    "embeddings": [0.1, 0.2, 0.3],
+}
+
 
 def test_conform_dict_1():
     """Validate that the conform_dict method returns the expected output for a real example"""
@@ -125,3 +142,30 @@ def test_conform_dict_2():
         "version": "1.1",
         "points": "[1, 2, 3]",
     }
+
+
+def test_conform_dict_link_texts():
+    """Validate that the conform_dict method returns the expected output link_texts"""
+    # Create a mock instance of the connector class
+    connector = SqlDestinationConnector(write_config=Mock(), connector_config=Mock())
+
+    # Mock the uuid.uuid4 function to return a fixed value
+    with patch("uuid.uuid4", return_value="mocked_uuid"):
+        # Call the conform_dict method
+        data_out = TEST_DATA_3.copy()
+        connector.conform_dict(data_out)
+
+    # Assert that the result matches the expected output
+    assert data_out == {
+        "embeddings": "[0.1, 0.2, 0.3]",
+        "id": "mocked_uuid",
+        "last_modified": datetime.datetime(2021, 1, 3, 0, 0),
+        "link_texts": ["Skip to main content"],
+        "link_urls": ["#main-content"],
+        "page_number": "10",
+        "date_created": datetime.datetime(2021, 1, 1, 0, 0),
+        "date_modified": datetime.datetime(2021, 1, 2, 0, 0),
+        "date_processed": datetime.datetime(2022, 12, 13, 15, 44, 8),
+        "version": "1.1",
+        "points": "[1, 2, 3]",
+    }

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.12.3-dev6"  # pragma: no cover
+__version__ = "0.12.3-dev7"  # pragma: no cover

unstructured/ingest/connector/sql.py

@@ -127,9 +127,6 @@ class SqlDestinationConnector(BaseDestinationConnector):
         ):
             data["metadata"]["data_source"]["permissions_data"] = json.dumps(permissions_data)
 
-        if link_texts := data.get("metadata", {}).get("link_texts", {}):
-            data["metadata"]["link_texts"] = str(json.dumps(link_texts))
-
         if sent_from := data.get("metadata", {}).get("sent_from", {}):
             data["metadata"]["sent_from"] = str(json.dumps(sent_from))