kopipasta 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

kopipasta/main.py

@@ -11,11 +11,17 @@ def read_gitignore():
         '.terraform', 'output', 'poetry.lock', 'package-lock.json', '.env',
         '*.log', '*.bak', '*.swp', '*.swo', '*.tmp', 'tmp', 'temp', 'logs',
         'build', 'target', '.DS_Store', 'Thumbs.db', '*.class', '*.jar',
-        '*.war', '*.ear', '*.sqlite', '*.db', '.github', '.gitignore'
+        '*.war', '*.ear', '*.sqlite', '*.db', '.github', '.gitignore',
+        '*.jpg', '*.jpeg', '*.png', '*.gif', '*.bmp', '*.tiff',
+        '*.ico', '*.svg', '*.webp', '*.mp3', '*.mp4', '*.avi',
+        '*.mov', '*.wmv', '*.flv', '*.pdf', '*.doc', '*.docx',
+        '*.xls', '*.xlsx', '*.ppt', '*.pptx', '*.zip', '*.rar',
+        '*.tar', '*.gz', '*.7z', '*.exe', '*.dll', '*.so', '*.dylib'
     ]
     gitignore_patterns = default_ignore_patterns.copy()
 
     if os.path.exists('.gitignore'):
+        print(".gitignore detected.")
         with open('.gitignore', 'r') as file:
             for line in file:
                 line = line.strip()
@@ -30,12 +36,23 @@ def is_ignored(path, ignore_patterns):
             return True
     return False
 
+def is_binary(file_path):
+    try:
+        with open(file_path, 'rb') as file:
+            return b'\0' in file.read(1024)
+    except IOError:
+        return False
+
+def get_human_readable_size(size):
+    for unit in ['B', 'KB', 'MB', 'GB', 'TB']:
+        if size < 1024.0:
+            return f"{size:.2f} {unit}"
+        size /= 1024.0
+
 def get_project_structure(ignore_patterns):
     tree = []
     for root, dirs, files in os.walk('.'):
-        # Remove ignored directories
         dirs[:] = [d for d in dirs if not is_ignored(os.path.join(root, d), ignore_patterns)]
-        # Remove ignored files
         files = [f for f in files if not is_ignored(os.path.join(root, f), ignore_patterns)]
         level = root.replace('.', '').count(os.sep)
         indent = ' ' * 4 * level + '|-- '
@@ -77,104 +94,111 @@ def get_language_for_file(file_path):
     }
     return language_map.get(extension, '')
 
-def select_files_in_directory(directory, ignore_patterns):
+def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
     files = [f for f in os.listdir(directory)
-             if os.path.isfile(os.path.join(directory, f)) and not is_ignored(os.path.join(directory, f), ignore_patterns)]
+             if os.path.isfile(os.path.join(directory, f)) and not is_ignored(os.path.join(directory, f), ignore_patterns) and not is_binary(os.path.join(directory, f))]
 
     if not files:
-        return []
+        return [], current_char_count
 
     print(f"\nDirectory: {directory}")
     print("Files:")
     for file in files:
-        print(f"- {file}")
+        file_path = os.path.join(directory, file)
+        file_size = os.path.getsize(file_path)
+        file_size_readable = get_human_readable_size(file_size)
+        file_char_estimate = file_size  # Assuming 1 byte ≈ 1 character for text files
+        file_token_estimate = file_char_estimate // 4
+        print(f"- {file} ({file_size_readable}, ~{file_char_estimate} chars, ~{file_token_estimate} tokens)")
 
     while True:
-        choice = input("\n(y)es add all / (n)o ignore all / (s)elect individually / (q)uit? ").lower()
+        print_char_count(current_char_count)
+        choice = input("(y)es add all / (n)o ignore all / (s)elect individually / (q)uit? ").lower()
         if choice == 'y':
+            for file in files:
+                current_char_count += os.path.getsize(os.path.join(directory, file))
             print(f"Added all files from {directory}")
-            return files
+            return files, current_char_count
         elif choice == 'n':
             print(f"Ignored all files from {directory}")
-            return []
+            return [], current_char_count
         elif choice == 's':
             selected_files = []
             for file in files:
+                file_path = os.path.join(directory, file)
+                file_size = os.path.getsize(file_path)
+                file_size_readable = get_human_readable_size(file_size)
+                file_char_estimate = file_size
+                file_token_estimate = file_char_estimate // 4
                 while True:
-                    file_choice = input(f"{file} (y/n/q)? ").lower()
+                    if current_char_count > 0:
+                        print_char_count(current_char_count)
+                    file_choice = input(f"{file} ({file_size_readable}, ~{file_char_estimate} chars, ~{file_token_estimate} tokens) (y/n/q)? ").lower()
                     if file_choice == 'y':
                         selected_files.append(file)
+                        current_char_count += file_char_estimate
                         break
                     elif file_choice == 'n':
                         break
                     elif file_choice == 'q':
                         print(f"Quitting selection for {directory}")
-                        return selected_files
+                        return selected_files, current_char_count
                     else:
                         print("Invalid choice. Please enter 'y', 'n', or 'q'.")
             print(f"Added {len(selected_files)} files from {directory}")
-            return selected_files
+            return selected_files, current_char_count
         elif choice == 'q':
             print(f"Quitting selection for {directory}")
-            return []
+            return [], current_char_count
         else:
             print("Invalid choice. Please try again.")
 
-def process_directory(directory, ignore_patterns):
+def process_directory(directory, ignore_patterns, current_char_count=0):
     files_to_include = []
     processed_dirs = set()
 
     for root, dirs, files in os.walk(directory):
-        # Remove ignored directories
         dirs[:] = [d for d in dirs if not is_ignored(os.path.join(root, d), ignore_patterns)]
-        # Remove ignored files
-        files = [f for f in files if not is_ignored(os.path.join(root, f), ignore_patterns)]
+        files = [f for f in files if not is_ignored(os.path.join(root, f), ignore_patterns) and not is_binary(os.path.join(root, f))]
 
         if root in processed_dirs:
             continue
 
-        selected_files = select_files_in_directory(root, ignore_patterns)
+        selected_files, current_char_count = select_files_in_directory(root, ignore_patterns, current_char_count)
         full_paths = [os.path.join(root, f) for f in selected_files]
         files_to_include.extend(full_paths)
         processed_dirs.add(root)
 
-    return files_to_include, processed_dirs
+    return files_to_include, processed_dirs, current_char_count
 
 def generate_prompt(files_to_include, ignore_patterns):
     prompt = "# Project Overview\n\n"
-    prompt += "## Summary of Included Files\n\n"
-    for file in files_to_include:
-        relative_path = get_relative_path(file)
-        prompt += f"- {relative_path}\n"
-    prompt += "\n"
-
     prompt += "## Project Structure\n\n"
     prompt += "```\n"
     prompt += get_project_structure(ignore_patterns)
     prompt += "\n```\n\n"
-
     prompt += "## File Contents\n\n"
     for file in files_to_include:
         relative_path = get_relative_path(file)
         language = get_language_for_file(file)
-        prompt += f"### {relative_path}\n\n"
-        prompt += f"```{language}\n"
-        prompt += read_file_contents(file)
-        prompt += "\n```\n\n"
-
+        file_content = f"### {relative_path}\n\n```{language}\n{read_file_contents(file)}\n```\n\n"
+        prompt += file_content
     prompt += "## Task Instructions\n\n"
     task_instructions = input("Enter the task instructions: ")
     prompt += f"{task_instructions}\n\n"
-
     prompt += "## Task Analysis and Planning\n\n"
-    prompt += (
+    analysis_text = (
         "Before starting, explain the task back to me in your own words. "
         "Ask for any clarifications if needed. Once you're clear, ask to proceed.\n\n"
         "Then, outline a plan for the task. Finally, use your plan to complete the task."
     )
-
+    prompt += analysis_text
     return prompt
 
+def print_char_count(count):
+    token_estimate = count // 4
+    print(f"\rCurrent prompt size: {count} characters (~ {token_estimate} tokens)", flush=True)
+
 def main():
     parser = argparse.ArgumentParser(description="Generate a prompt with project structure and file contents.")
     parser.add_argument('inputs', nargs='+', help='Files or directories to include in the prompt')
@@ -184,16 +208,17 @@ def main():
 
     files_to_include = []
     processed_dirs = set()
+    current_char_count = 0
 
     for input_path in args.inputs:
         if os.path.isfile(input_path):
-            if not is_ignored(input_path, ignore_patterns):
+            if not is_ignored(input_path, ignore_patterns) and not is_binary(input_path):
                 files_to_include.append(input_path)
                 print(f"Added file: {input_path}")
             else:
                 print(f"Ignored file: {input_path}")
         elif os.path.isdir(input_path):
-            dir_files, dir_processed = process_directory(input_path, ignore_patterns)
+            dir_files, dir_processed, current_char_count = process_directory(input_path, ignore_patterns, current_char_count)
             files_to_include.extend(dir_files)
             processed_dirs.update(dir_processed)
         else:
@@ -204,19 +229,23 @@ def main():
         return
 
     print("\nFile selection complete.")
+    print_char_count(current_char_count)
     print(f"Summary: Added {len(files_to_include)} files from {len(processed_dirs)} directories.")
 
     prompt = generate_prompt(files_to_include, ignore_patterns)
-    print("\nGenerated prompt:")
+    print("\n\nGenerated prompt:")
     print(prompt)
 
     # Copy the prompt to clipboard
     try:
         pyperclip.copy(prompt)
-        print("\nPrompt has been copied to clipboard.")
+        separator = "\n" + "=" * 40 + "\n☕🍝       Kopipasta Complete!       🍝☕\n" + "=" * 40 + "\n"
+        print(separator)
+        final_char_count = len(prompt)
+        final_token_estimate = final_char_count // 4
+        print(f"Prompt has been copied to clipboard. Final size: {final_char_count} characters (~ {final_token_estimate} tokens)")
     except pyperclip.PyperclipException as e:
         print(f"Failed to copy to clipboard: {e}")
 
 if __name__ == "__main__":
-    main()
-
+    main()

kopipasta-0.2.0.dist-info/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Mikko Korpela
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

{kopipasta-0.1.0.dist-info → kopipasta-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: kopipasta
-Version: 0.1.0
+Version: 0.2.0
 Summary: A CLI tool to generate prompts with project structure and file contents
 Home-page: https://github.com/mkorpela/kopipasta
 Author: Mikko Korpela
@@ -21,10 +21,13 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pyperclip ==1.9.0
 
+
 # kopipasta
 
 A CLI tool to generate prompts with project structure and file contents.
 
+<img src="kopipasta.jpg" alt="kopipasta" width="300">
+
 ## Installation
 
 You can install kopipasta using pipx (or pip):
@@ -45,7 +48,7 @@ Replace `[files_or_directories]` with the paths to the files or directories you
 
 Example:
 ```
-kopipasta . src/ config.json
+kopipasta src/ config.json
 ```
 
 This will generate a prompt including the project structure and contents of the specified files and directories, ignoring files and directories typically excluded in version control (based on common .gitignore patterns).
@@ -59,6 +62,61 @@ The generated prompt will be displayed in the console and automatically copied t
 - Allows interactive selection of files to include
 - Automatically copies the generated prompt to the clipboard
 
+## Example output
+
+```bash
+    ❯ kopipasta .
+
+    Directory: .
+    Files:
+    - __init__.py
+    - main.py
+
+    (y)es add all / (n)o ignore all / (s)elect individually / (q)uit? s
+    __init__.py (y/n/q)? y
+    main.py (y/n/q)? n
+    Added 1 files from .
+
+    File selection complete.
+    Summary: Added 1 files from 1 directories.
+    Enter the task instructions: Do my work
+
+    Generated prompt:
+    # Project Overview
+
+    ## Summary of Included Files
+
+    - __init__.py
+
+    ## Project Structure
+
+    ```
+    |-- ./
+        |-- __init__.py
+        |-- main.py
+    ```
+
+    ## File Contents
+
+    ### __init__.py
+
+    ```python
+
+    ```
+
+    ## Task Instructions
+
+    Do my work
+
+    ## Task Analysis and Planning
+
+    Before starting, explain the task back to me in your own words. Ask for any clarifications if needed. Once you're clear, ask to proceed.
+
+    Then, outline a plan for the task. Finally, use your plan to complete the task.
+
+    Prompt has been copied to clipboard.
+```
+
 ## License
 
 This project is licensed under the MIT License.

kopipasta-0.2.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+kopipasta/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kopipasta/main.py,sha256=-3K3Pnv6auCjsQGwxTip8GlBZD2RiPAj9h7h_zeMbSc,10268
+kopipasta-0.2.0.dist-info/LICENSE,sha256=xw4C9TAU7LFu4r_MwSbky90uzkzNtRwAo3c51IWR8lk,1091
+kopipasta-0.2.0.dist-info/METADATA,sha256=hGK30wSKHEPuLh1DRibm6k1iq9Zsx-Dg7uGTO8bBBRo,3033
+kopipasta-0.2.0.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+kopipasta-0.2.0.dist-info/entry_points.txt,sha256=but54qDNz1-F8fVvGstq_QID5tHjczP7bO7rWLFkc6Y,50
+kopipasta-0.2.0.dist-info/top_level.txt,sha256=iXohixMuCdw8UjGDUp0ouICLYBDrx207sgZIJ9lxn0o,10
+kopipasta-0.2.0.dist-info/RECORD,,

kopipasta-0.1.0.dist-info/RECORD

@@ -1,8 +0,0 @@
-kopipasta/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kopipasta/main.py,sha256=cTYEe92iZLg9S0MpQGBL01MOcDF6zTjW328QgUPCVHo,7886
-kopipasta-0.1.0.dist-info/LICENSE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kopipasta-0.1.0.dist-info/METADATA,sha256=WjpoxaAhAzwT3IXHEM8vTqR6mgUUjhlyQhC-m9YQiCM,1987
-kopipasta-0.1.0.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-kopipasta-0.1.0.dist-info/entry_points.txt,sha256=but54qDNz1-F8fVvGstq_QID5tHjczP7bO7rWLFkc6Y,50
-kopipasta-0.1.0.dist-info/top_level.txt,sha256=iXohixMuCdw8UjGDUp0ouICLYBDrx207sgZIJ9lxn0o,10
-kopipasta-0.1.0.dist-info/RECORD,,