From a9ad8ac8d13da38a6fc7c05bbe83c169cecc2be7 Mon Sep 17 00:00:00 2001
From: Ahmet Melek <39141206+ahmetmeleq@users.noreply.github.com>
Date: Fri, 19 Jan 2024 00:21:22 +0000
Subject: [PATCH] fix: update flatten dict to support flattening tuples 
 (#2423)

This PR updates flatten_dict function to support flattening tuples.

This is necessary for objects like Coordinates, when the object is not
written to the disk, therefore not being converted to a list before
getting flattened.
---
 CHANGELOG.md                                   |  1 +
 test_unstructured/staging/test_base_staging.py | 14 ++++++++++++++
 unstructured/staging/base.py                   |  4 ++--
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 27187ad00..2ae6e13f4 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -27,6 +27,7 @@
 * **Fix the serialization of the Elasticsearch destination connector.** Presence of the _client object breaks serialization due to TypeError: cannot pickle '_thread.lock' object. This removes that object before serialization.
 * **Fix the serialization of the Postgres destination connector.** Presence of the _client object breaks serialization due to TypeError: cannot pickle '_thread.lock' object. This removes that object before serialization.
 * **Fix documentation and sample code for Chroma.** Was pointing to wrong examples..
+* **Fix flatten_dict to be able to flatten tuples inside dicts** Update flatten_dict function to support flattening tuples inside dicts. This is necessary for objects like Coordinates, when the object is not written to the disk, therefore not being converted to a list before getting flattened (still being a tuple).
 
 ## 0.12.0
 
diff --git a/test_unstructured/staging/test_base_staging.py b/test_unstructured/staging/test_base_staging.py
index 741d9b676..f113f1f3d 100644
--- a/test_unstructured/staging/test_base_staging.py
+++ b/test_unstructured/staging/test_base_staging.py
@@ -409,6 +409,13 @@ def test_flatten_nested_dict():
     assert base.flatten_dict(dictionary) == expected_result
 
 
+def test_flatten_dict_with_tuples():
+    """Flattening a dictionary with tuples"""
+    dictionary = {"a": 1, "b": (2, 3, 4), "c": {"d": 5, "e": (6, 7)}}
+    expected_result = {"a": 1, "b": (2, 3, 4), "c_d": 5, "c_e": (6, 7)}
+    assert base.flatten_dict(dictionary) == expected_result
+
+
 def test_flatten_dict_with_lists():
     """Flattening a dictionary with lists"""
     dictionary = {"a": 1, "b": [2, 3, 4], "c": {"d": 5, "e": [6, 7]}}
@@ -432,6 +439,13 @@ def test_flatten_dict_alt_separator():
     assert base.flatten_dict(dictionary, separator=separator) == expected_result
 
 
+def test_flatten_dict_flatten_tuple():
+    """Flattening a dictionary with flatten_lists set to True, to flatten tuples"""
+    dictionary = {"a": 1, "b": (2, 3, 4), "c": {"d": 5, "e": (6, 7)}}
+    expected_result = {"a": 1, "b_0": 2, "b_1": 3, "b_2": 4, "c_d": 5, "c_e_0": 6, "c_e_1": 7}
+    assert base.flatten_dict(dictionary, flatten_lists=True) == expected_result
+
+
 def test_flatten_dict_flatten_list():
     """Flattening a dictionary with flatten_lists set to True"""
     dictionary = {"a": 1, "b": [2, 3, 4], "c": {"d": 5, "e": [6, 7]}}
diff --git a/unstructured/staging/base.py b/unstructured/staging/base.py
index 2056c12f6..08f29e9d1 100644
--- a/unstructured/staging/base.py
+++ b/unstructured/staging/base.py
@@ -181,7 +181,7 @@ def flatten_dict(
 ):
     """Flattens a nested dictionary into a single level dictionary. keys_to_omit is a list of keys
     that don't get flattened. If omitting a nested key, format as {parent_key}{separator}{key}.
-    If flatten_lists is True, then lists are flattened as well."""
+    If flatten_lists is True, then lists and tuples are flattened as well."""
     keys_to_omit = keys_to_omit if keys_to_omit else []
     flattened_dict = {}
     for key, value in dictionary.items():
@@ -192,7 +192,7 @@ def flatten_dict(
             flattened_dict.update(
                 flatten_dict(value, new_key, separator, flatten_lists, keys_to_omit=keys_to_omit),
             )
-        elif isinstance(value, list) and flatten_lists:
+        elif isinstance(value, (list, tuple)) and flatten_lists:
             for index, item in enumerate(value):
                 flattened_dict.update(
                     flatten_dict(