From bcc32cc441d475a9dd5f1cfd04062b8bc5cd024c Mon Sep 17 00:00:00 2001
From: k-boikov <64261260+k-boikov@users.noreply.github.com>
Date: Sun, 21 May 2023 04:20:03 +0300
Subject: [PATCH] Fix split_file when overlap = 0, add test (#3599)

Co-authored-by: Nicholas Tindle <nick@ntindle.com>
---
 autogpt/commands/file_operations.py |  2 +-
 tests/unit/test_file_operations.py  | 39 +++++++++++++++++++++++++----
 2 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/autogpt/commands/file_operations.py b/autogpt/commands/file_operations.py
index 28198ebae..528f8d669 100644
--- a/autogpt/commands/file_operations.py
+++ b/autogpt/commands/file_operations.py
@@ -131,7 +131,7 @@ def split_file(
     while start < content_length:
         end = start + max_length
         if end + overlap < content_length:
-            chunk = content[start : end + overlap - 1]
+            chunk = content[start : end + max(overlap - 1, 0)]
         else:
             chunk = content[start:content_length]
 
diff --git a/tests/unit/test_file_operations.py b/tests/unit/test_file_operations.py
index fb8300d47..98d4efb77 100644
--- a/tests/unit/test_file_operations.py
+++ b/tests/unit/test_file_operations.py
@@ -151,12 +151,41 @@ def test_log_operation_with_checksum(config: Config):
     assert f"log_test: path/to/test #ABCDEF\n" in content
 
 
+@pytest.mark.parametrize(
+    "max_length, overlap, content, expected",
+    [
+        (
+            4,
+            1,
+            "abcdefghij",
+            ["abcd", "defg", "ghij"],
+        ),
+        (
+            4,
+            0,
+            "abcdefghijkl",
+            ["abcd", "efgh", "ijkl"],
+        ),
+        (
+            4,
+            0,
+            "abcdefghijklm",
+            ["abcd", "efgh", "ijkl", "m"],
+        ),
+        (
+            4,
+            0,
+            "abcdefghijk",
+            ["abcd", "efgh", "ijk"],
+        ),
+    ],
+)
 # Test splitting a file into chunks
-def test_split_file():
-    content = "abcdefghij"
-    chunks = list(file_ops.split_file(content, max_length=4, overlap=1))
-    expected = ["abcd", "defg", "ghij"]
-    assert chunks == expected
+def test_split_file(max_length, overlap, content, expected):
+    assert (
+        list(file_ops.split_file(content, max_length=max_length, overlap=overlap))
+        == expected
+    )
 
 
 def test_read_file(test_file_with_content_path: Path, file_content):