- Modify the process_files function to handle processing of a singl…

…e file or a directory

- Update the `should_process_file` function to simplify and clarify the criteria for processing a file
- Remove unnecessary comments from the code
- Improve code readability and maintainability

code2prompt/main.py

@@ -4,23 +4,78 @@
 from code2prompt.process_files import process_files
 from code2prompt.write_output import write_output
 
-VERSION = "0.5.0" # Define the version of the CLI tool
+VERSION = "0.5.0"  # Define the version of the CLI tool
+
 
 @click.command()
-@click.version_option(VERSION, '-v', '--version', message='code2prompt version %(version)s')
-@click.option("--path", "-p", type=click.Path(exists=True), required=True, help="Path to the directory to navigate.")
-@click.option("--output", "-o", type=click.Path(), help="Name of the output Markdown file.")
-@click.option("--gitignore", "-g", type=click.Path(exists=True), help="Path to the .gitignore file.")
-@click.option("--filter", "-f", type=str, help='Comma-separated filter patterns to include files (e.g., "*.py,*.js").')
-@click.option("--exclude", "-e", type=str, help='Comma-separated patterns to exclude files (e.g., "*.txt,*.md").')
-@click.option("--case-sensitive", is_flag=True, help="Perform case-sensitive pattern matching.")
-@click.option("--suppress-comments", "-s", is_flag=True, help="Strip comments from the code files.", default=False)
-@click.option("--line-number", "-ln", is_flag=True, help="Add line numbers to source code blocks.", default=False)
-@click.option("--no-codeblock", is_flag=True, help="Disable wrapping code inside markdown code blocks.")
-@click.option("--template", "-t", type=click.Path(exists=True), help="Path to a Jinja2 template file for custom prompt generation.")
-@click.option("--tokens", is_flag=True, help="Display the token count of the generated prompt.")
-@click.option("--encoding", type=click.Choice(['cl100k_base', 'p50k_base', 'p50k_edit', 'r50k_base']), 
-              default='cl100k_base', help="Specify the tokenizer encoding to use.")
+@click.version_option(
+    VERSION, "-v", "--version", message="code2prompt version %(version)s"
+)
+@click.option(
+    "--path",
+    "-p",
+    type=click.Path(exists=True),
+    required=True,
+    help="Path to the directory or file to process.",
+)
+@click.option(
+    "--output", "-o", type=click.Path(), help="Name of the output Markdown file."
+)
+@click.option(
+    "--gitignore",
+    "-g",
+    type=click.Path(exists=True),
+    help="Path to the .gitignore file.",
+)
+@click.option(
+    "--filter",
+    "-f",
+    type=str,
+    help='Comma-separated filter patterns to include files (e.g., "*.py,*.js").',
+)
+@click.option(
+    "--exclude",
+    "-e",
+    type=str,
+    help='Comma-separated patterns to exclude files (e.g., "*.txt,*.md").',
+)
+@click.option(
+    "--case-sensitive", is_flag=True, help="Perform case-sensitive pattern matching."
+)
+@click.option(
+    "--suppress-comments",
+    "-s",
+    is_flag=True,
+    help="Strip comments from the code files.",
+    default=False,
+)
+@click.option(
+    "--line-number",
+    "-ln",
+    is_flag=True,
+    help="Add line numbers to source code blocks.",
+    default=False,
+)
+@click.option(
+    "--no-codeblock",
+    is_flag=True,
+    help="Disable wrapping code inside markdown code blocks.",
+)
+@click.option(
+    "--template",
+    "-t",
+    type=click.Path(exists=True),
+    help="Path to a Jinja2 template file for custom prompt generation.",
+)
+@click.option(
+    "--tokens", is_flag=True, help="Display the token count of the generated prompt."
+)
+@click.option(
+    "--encoding",
+    type=click.Choice(["cl100k_base", "p50k_base", "p50k_edit", "r50k_base"]),
+    default="cl100k_base",
+    help="Specify the tokenizer encoding to use.",
+)
 def create_markdown_file(**options):
     """
     Creates a Markdown file based on the provided options.
@@ -41,13 +96,14 @@ def create_markdown_file(**options):
     """
     files_data = process_files(options)
     content = generate_content(files_data, options)
-    
-    if options['tokens']:
-        token_count = count_tokens(content, options['encoding'])
+
+    if options["tokens"]:
+        token_count = count_tokens(content, options["encoding"])
         click.echo(f"Token count: {token_count}")
-
-    write_output(content, options['output'])
+
+    write_output(content, options["output"])
+
 
 if __name__ == "__main__":
     # pylint: disable=no-value-for-parameter
-    create_markdown_file()
+    create_markdown_file()

code2prompt/process_files.py

@@ -1,29 +1,34 @@
+from pathlib import Path
 from code2prompt.get_gitignore_patterns import get_gitignore_patterns
 from code2prompt.process_file import process_file
 from code2prompt.should_process_file import should_process_file
 
-
-from pathlib import Path
-
-
 def process_files(options):
     """
-    Processes files within a specified directory, applying filters and transformations
-    based on the provided options.
-
+    Processes files or a single file based on the provided path.
+    
     Args:
-        options (dict): A dictionary containing options such as path, gitignore patterns,
-                        and flags for processing files.
-
+    options (dict): A dictionary containing options such as path, gitignore patterns, and flags for processing files.
+    
     Returns:
-        list: A list of dictionaries containing processed file data.
+    list: A list of dictionaries containing processed file data.
     """
     path = Path(options['path'])
-    gitignore_patterns = get_gitignore_patterns(path, options['gitignore'])
+    gitignore_patterns = get_gitignore_patterns(path.parent if path.is_file() else path, options['gitignore'])
     files_data = []
-    for file_path in path.rglob("*"):
-        if should_process_file(file_path, gitignore_patterns, path, options):
-            result = process_file(file_path, options['suppress_comments'], options['line_number'], options['no_codeblock'])
+
+    if path.is_file():
+        # Process single file
+        if should_process_file(path, gitignore_patterns, path.parent, options):
+            result = process_file(path, options['suppress_comments'], options['line_number'], options['no_codeblock'])
             if result:
                 files_data.append(result)
+    else:
+        # Process directory
+        for file_path in path.rglob("*"):
+            if should_process_file(file_path, gitignore_patterns, path, options):
+                result = process_file(file_path, options['suppress_comments'], options['line_number'], options['no_codeblock'])
+                if result:
+                    files_data.append(result)
+
     return files_data

code2prompt/should_process_file.py

@@ -2,23 +2,18 @@
 from code2prompt.utils.is_filtered import is_filtered
 from code2prompt.utils.is_ignored import is_ignored
 
-
 def should_process_file(file_path, gitignore_patterns, root_path, options):
     """
     Determine whether a file should be processed based on several criteria.
 
-    Checks if the file is indeed a file, not ignored according to gitignore patterns,
-    matches the filter criteria, is not excluded, is case sensitive if specified,
-    and is not a binary file.
-
     Args:
-        file_path (Path): The path to the file being considered.
-        gitignore_patterns (set): A set of patterns to ignore files.
-        root_path (Path): The root path of the project for relative comparisons.
-        options (dict): A dictionary of options including filter, exclude, and case sensitivity settings.
+    file_path (Path): The path to the file being considered.
+    gitignore_patterns (set): A set of patterns to ignore files.
+    root_path (Path): The root path of the project for relative comparisons.
+    options (dict): A dictionary of options including filter, exclude, and case sensitivity settings.
 
     Returns:
-        bool: True if the file should be processed, False otherwise.
+    bool: True if the file should be processed, False otherwise.
     """
     return (
         file_path.is_file()