From 84df8a64ae4095c40f364d990537a5657a8e029d Mon Sep 17 00:00:00 2001
From: Simon Willison <swillison@gmail.com>
Date: Sun, 7 Apr 2024 23:03:40 -0700
Subject: [PATCH] Warn and continue on binary files, closes #5

---
 files_to_prompt/cli.py        | 38 ++++++++++++++++++++++-------------
 tests/test_files_to_prompt.py | 24 ++++++++++++++++++++++
 2 files changed, 48 insertions(+), 14 deletions(-)

diff --git a/files_to_prompt/cli.py b/files_to_prompt/cli.py
index ef0b83a..db5c07e 100644
--- a/files_to_prompt/cli.py
+++ b/files_to_prompt/cli.py
@@ -27,13 +27,17 @@ def process_path(
     path, include_hidden, ignore_gitignore, gitignore_rules, ignore_patterns
 ):
     if os.path.isfile(path):
-        with open(path, "r") as f:
-            file_contents = f.read()
-        click.echo(path)
-        click.echo("---")
-        click.echo(file_contents)
-        click.echo()
-        click.echo("---")
+        try:
+            with open(path, "r") as f:
+                file_contents = f.read()
+            click.echo(path)
+            click.echo("---")
+            click.echo(file_contents)
+            click.echo()
+            click.echo("---")
+        except UnicodeDecodeError:
+            warning_message = f"Warning: Skipping file {path} due to UnicodeDecodeError"
+            click.echo(click.style(warning_message, fg="red"), err=True)
     elif os.path.isdir(path):
         for root, dirs, files in os.walk(path):
             if not include_hidden:
@@ -62,14 +66,20 @@ def process_path(
 
             for file in files:
                 file_path = os.path.join(root, file)
-                with open(file_path, "r") as f:
-                    file_contents = f.read()
+                try:
+                    with open(file_path, "r") as f:
+                        file_contents = f.read()
 
-                click.echo(file_path)
-                click.echo("---")
-                click.echo(file_contents)
-                click.echo()
-                click.echo("---")
+                    click.echo(file_path)
+                    click.echo("---")
+                    click.echo(file_contents)
+                    click.echo()
+                    click.echo("---")
+                except UnicodeDecodeError:
+                    warning_message = (
+                        f"Warning: Skipping file {file_path} due to UnicodeDecodeError"
+                    )
+                    click.echo(click.style(warning_message, fg="red"), err=True)
 
 
 @click.command()
diff --git a/tests/test_files_to_prompt.py b/tests/test_files_to_prompt.py
index 4b94dd1..5e20af1 100644
--- a/tests/test_files_to_prompt.py
+++ b/tests/test_files_to_prompt.py
@@ -162,3 +162,27 @@ def test_mixed_paths_with_options(tmpdir):
         assert "test_dir/.hidden_included.txt" in result.output
         assert "single_file.txt" in result.output
         assert "Contents of single file" in result.output
+
+
+def test_binary_file_warning(tmpdir):
+    runner = CliRunner(mix_stderr=False)
+    with tmpdir.as_cwd():
+        os.makedirs("test_dir")
+        with open("test_dir/binary_file.bin", "wb") as f:
+            f.write(b"\xff")
+        with open("test_dir/text_file.txt", "w") as f:
+            f.write("This is a text file")
+
+        result = runner.invoke(cli, ["test_dir"])
+        assert result.exit_code == 0
+
+        stdout = result.stdout
+        stderr = result.stderr
+
+        assert "test_dir/text_file.txt" in stdout
+        assert "This is a text file" in stdout
+        assert "\ntest_dir/binary_file.bin" not in stdout
+        assert (
+            "Warning: Skipping file test_dir/binary_file.bin due to UnicodeDecodeError"
+            in stderr
+        )