kopipasta 0.14.0__py3-none-any.whl → 0.16.0__py3-none-any.whl

kopipasta/main.py

@@ -4,14 +4,15 @@ import io
 import json
 import os
 import argparse
-import ast
 import re
-from textwrap import dedent
+from typing import Dict, List, Optional, Set, Tuple
 import pyperclip
 import fnmatch
 
 import requests
 
+FileTuple = Tuple[str, bool, Optional[List[str]], str]
+
 def read_gitignore():
     default_ignore_patterns = [
         '.git', 'node_modules', 'venv', '.venv', 'dist', '.idea', '__pycache__',
@@ -425,7 +426,7 @@ def print_char_count(count):
     token_estimate = count // 4
     print(f"\rCurrent prompt size: {count} characters (~ {token_estimate} tokens)", flush=True)
 
-def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
+def select_files_in_directory(directory: str, ignore_patterns: List[str], current_char_count: int = 0) -> Tuple[List[FileTuple], int]:
     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) and not is_binary(os.path.join(directory, f))]
 
@@ -445,8 +446,8 @@ def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
     while True:
         print_char_count(current_char_count)
         choice = input("(y)es add all / (n)o ignore all / (s)elect individually / (q)uit? ").lower()
+        selected_files: List[FileTuple] = []
         if choice == 'y':
-            selected_files = []
             for file in files:
                 file_path = os.path.join(directory, file)
                 if is_large_file(file_path):
@@ -456,13 +457,13 @@ def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
                             break
                         print("Invalid choice. Please enter 'f' or 's'.")
                     if snippet_choice == 's':
-                        selected_files.append((file, True))
+                        selected_files.append((file, True, None, get_language_for_file(file)))
                         current_char_count += len(get_file_snippet(file_path))
                     else:
-                        selected_files.append((file, False))
+                        selected_files.append((file, False, None, get_language_for_file(file)))
                         current_char_count += os.path.getsize(file_path)
                 else:
-                    selected_files.append((file, False))
+                    selected_files.append((file, False, None, get_language_for_file(file)))
                     current_char_count += os.path.getsize(file_path)
             print(f"Added all files from {directory}")
             return selected_files, current_char_count
@@ -470,7 +471,6 @@ def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
             print(f"Ignored all files from {directory}")
             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)
@@ -489,13 +489,13 @@ def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
                                     break
                                 print("Invalid choice. Please enter 'f' or 's'.")
                             if snippet_choice == 's':
-                                selected_files.append((file, True))
+                                selected_files.append((file, True, None, get_language_for_file(file_path)))
                                 current_char_count += len(get_file_snippet(file_path))
                             else:
-                                selected_files.append((file, False))
+                                selected_files.append((file, False, None, get_language_for_file(file_path)))
                                 current_char_count += file_char_estimate
                         else:
-                            selected_files.append((file, False))
+                            selected_files.append((file, False, None, get_language_for_file(file_path)))
                             current_char_count += file_char_estimate
                         break
                     elif file_choice == 'n':
@@ -503,7 +503,7 @@ def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
                     elif file_choice == 'p':
                         chunks, char_count = select_file_patches(file_path)
                         if chunks:
-                            selected_files.append((file_path, False, chunks))
+                            selected_files.append((file_path, False, chunks, get_language_for_file(file_path)))
                             current_char_count += char_count
                         break
                     elif file_choice == 'q':
@@ -519,9 +519,9 @@ def select_files_in_directory(directory, ignore_patterns, current_char_count=0):
         else:
             print("Invalid choice. Please try again.")
 
-def process_directory(directory, ignore_patterns, current_char_count=0):
-    files_to_include = []
-    processed_dirs = set()
+def process_directory(directory: str, ignore_patterns: List[str], current_char_count: int = 0) -> Tuple[List[FileTuple], Set[str], int]:
+    files_to_include: List[FileTuple] = []
+    processed_dirs: Set[str] = set()
 
     for root, dirs, files in os.walk(directory):
         dirs[:] = [d for d in dirs if not is_ignored(os.path.join(root, d), ignore_patterns)]
@@ -535,12 +535,8 @@ def process_directory(directory, ignore_patterns, current_char_count=0):
         if choice == 'y':
             selected_files, current_char_count = select_files_in_directory(root, ignore_patterns, current_char_count)
             for file_tuple in selected_files:
-                if len(file_tuple) == 3:
-                    f, use_snippet, chunks = file_tuple
-                    files_to_include.append((os.path.join(root, f), use_snippet, chunks))
-                else:
-                    f, use_snippet = file_tuple
-                    files_to_include.append((os.path.join(root, f), use_snippet))
+                full_path = os.path.join(root, file_tuple[0])
+                files_to_include.append((full_path, file_tuple[1], file_tuple[2], file_tuple[3]))
             processed_dirs.add(root)
         elif choice == 'n':
             dirs[:] = []  # Skip all subdirectories
@@ -553,20 +549,25 @@ def process_directory(directory, ignore_patterns, current_char_count=0):
 
     return files_to_include, processed_dirs, current_char_count
 
-def fetch_web_content(url):
+def fetch_web_content(url: str) -> Tuple[Optional[FileTuple], Optional[str], Optional[str]]:
     try:
         response = requests.get(url)
         response.raise_for_status()
         content_type = response.headers.get('content-type', '').lower()
+        full_content = response.text
+        snippet = full_content[:10000] + "..." if len(full_content) > 10000 else full_content
+        
         if 'json' in content_type:
-            return response.json(), 'json'
+            content_type = 'json'
         elif 'csv' in content_type:
-            return response.text, 'csv'
+            content_type = 'csv'
         else:
-            return response.text, 'text'
+            content_type = 'text'
+        
+        return (url, False, None, content_type), full_content, snippet
     except requests.RequestException as e:
         print(f"Error fetching content from {url}: {e}")
-        return None, None
+        return None, None, None
 
 def read_file_content(file_path):
     _, ext = os.path.splitext(file_path)
@@ -670,34 +671,34 @@ def handle_env_variables(content, env_vars):
 
     return content
 
-def generate_prompt(files_to_include, ignore_patterns, web_contents, env_vars):
+def generate_prompt(files_to_include: List[FileTuple], ignore_patterns: List[str], web_contents: Dict[str, Tuple[FileTuple, str]], env_vars: Dict[str, str]) -> str:
     prompt = "# Project Overview\n\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_tuple in files_to_include:
-        if len(file_tuple) == 4:
-            file, content, is_snippet, content_type = file_tuple
-            chunks = None
-        else:
-            file, content, is_snippet, content_type, chunks = file_tuple
+    for file, use_snippet, chunks, content_type in files_to_include:
         relative_path = get_relative_path(file)
-        language = get_language_for_file(file) if content_type == 'text' else content_type
+        language = content_type if content_type else get_language_for_file(file)
 
         if chunks is not None:
             prompt += f"### {relative_path} (selected patches)\n\n```{language}\n"
             for chunk in chunks:
                 prompt += f"{chunk}\n"
             prompt += "```\n\n"
+        elif use_snippet:
+            file_content = get_file_snippet(file)
+            prompt += f"### {relative_path} (snippet)\n\n```{language}\n{file_content}\n```\n\n"
         else:
-            content = handle_env_variables(content, env_vars)
-            prompt += f"### {relative_path}{' (snippet)' if is_snippet else ''}\n\n```{language}\n{content}\n```\n\n"
+            file_content = read_file_contents(file)
+            file_content = handle_env_variables(file_content, env_vars)
+            prompt += f"### {relative_path}\n\n```{language}\n{file_content}\n```\n\n"
     
     if web_contents:
         prompt += "## Web Content\n\n"
-        for url, (content, is_snippet, content_type) in web_contents.items():
+        for url, (file_tuple, content) in web_contents.items():
+            _, is_snippet, _, content_type = file_tuple
             content = handle_env_variables(content, env_vars)
             language = content_type if content_type in ['json', 'csv'] else ''
             prompt += f"### {url}{' (snippet)' if is_snippet else ''}\n\n```{language}\n{content}\n```\n\n"
@@ -722,25 +723,52 @@ def main():
     ignore_patterns = read_gitignore()
     env_vars = read_env_file()
 
-    files_to_include = []
+    files_to_include: List[FileTuple] = []
     processed_dirs = set()
-    web_contents = {}
+    web_contents: Dict[str, Tuple[FileTuple, str]] = {}
     current_char_count = 0
 
     for input_path in args.inputs:
         if input_path.startswith(('http://', 'https://')):
-            full_content, snippet = fetch_web_content(input_path)
-            if full_content:
-                web_contents[input_path] = (full_content, snippet)
-                current_char_count += len(snippet if len(full_content) > 10000 else full_content)
-                print(f"Added web content from: {input_path}")
+            result = fetch_web_content(input_path)
+            if result:
+                file_tuple, full_content, snippet = result
+                is_large = len(full_content) > 10000
+                if is_large:
+                    print(f"\nContent from {input_path} is large. Here's a snippet:\n")
+                    print(snippet)
+                    print("\n" + "-"*40 + "\n")
+                    
+                    while True:
+                        choice = input("Use (f)ull content or (s)nippet? ").lower()
+                        if choice in ['f', 's']:
+                            break
+                        print("Invalid choice. Please enter 'f' or 's'.")
+                    
+                    if choice == 'f':
+                        content = full_content
+                        is_snippet = False
+                        print("Using full content.")
+                    else:
+                        content = snippet
+                        is_snippet = True
+                        print("Using snippet.")
+                else:
+                    content = full_content
+                    is_snippet = False
+                    print(f"Content from {input_path} is not large. Using full content.")
+                
+                file_tuple = (file_tuple[0], is_snippet, file_tuple[2], file_tuple[3])
+                web_contents[input_path] = (file_tuple, content)
+                current_char_count += len(content)
+                print(f"Added {'snippet of ' if is_snippet else ''}web content from: {input_path}")
         elif os.path.isfile(input_path):
             if not is_ignored(input_path, ignore_patterns) and not is_binary(input_path):
                 while True:
                     file_choice = input(f"{input_path} (y)es include / (n)o skip / (p)atches / (q)uit? ").lower()
                     if file_choice == 'y':
                         use_snippet = is_large_file(input_path)
-                        files_to_include.append((input_path, use_snippet))
+                        files_to_include.append((input_path, use_snippet, None, get_language_for_file(input_path)))
                         if use_snippet:
                             current_char_count += len(get_file_snippet(input_path))
                         else:
@@ -752,7 +780,7 @@ def main():
                     elif file_choice == 'p':
                         chunks, char_count = select_file_patches(input_path)
                         if chunks:
-                            files_to_include.append((input_path, False, chunks))
+                            files_to_include.append((input_path, False, chunks, get_language_for_file(input_path)))
                             current_char_count += char_count
                         break
                     elif file_choice == 'q':

{kopipasta-0.14.0.dist-info → kopipasta-0.16.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: kopipasta
-Version: 0.14.0
+Version: 0.16.0
 Summary: A CLI tool to generate prompts with project structure and file contents
 Home-page: https://github.com/mkorpela/kopipasta
 Author: Mikko Korpela

kopipasta-0.16.0.dist-info/RECORD

@@ -0,0 +1,8 @@
+kopipasta/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kopipasta/main.py,sha256=saG3HuptoAg7kPz-VqiGF9Bh3oznMmATxsQbRpZc_ZY,33134
+kopipasta-0.16.0.dist-info/LICENSE,sha256=xw4C9TAU7LFu4r_MwSbky90uzkzNtRwAo3c51IWR8lk,1091
+kopipasta-0.16.0.dist-info/METADATA,sha256=e6kZrq96erWpl2HRyGiknXTRHQdnERd3eWccFEK0kC0,5646
+kopipasta-0.16.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+kopipasta-0.16.0.dist-info/entry_points.txt,sha256=but54qDNz1-F8fVvGstq_QID5tHjczP7bO7rWLFkc6Y,50
+kopipasta-0.16.0.dist-info/top_level.txt,sha256=iXohixMuCdw8UjGDUp0ouICLYBDrx207sgZIJ9lxn0o,10
+kopipasta-0.16.0.dist-info/RECORD,,

kopipasta-0.14.0.dist-info/RECORD

@@ -1,8 +0,0 @@
-kopipasta/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kopipasta/main.py,sha256=xoH5I0vAbKbz51trNtqItc-d72s2J2f9b7dIKTTFSCE,31094
-kopipasta-0.14.0.dist-info/LICENSE,sha256=xw4C9TAU7LFu4r_MwSbky90uzkzNtRwAo3c51IWR8lk,1091
-kopipasta-0.14.0.dist-info/METADATA,sha256=onX0C9YmxAPItIrKTlJfoSggPPKZJNs-M1bGaXIlCTY,5646
-kopipasta-0.14.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-kopipasta-0.14.0.dist-info/entry_points.txt,sha256=but54qDNz1-F8fVvGstq_QID5tHjczP7bO7rWLFkc6Y,50
-kopipasta-0.14.0.dist-info/top_level.txt,sha256=iXohixMuCdw8UjGDUp0ouICLYBDrx207sgZIJ9lxn0o,10
-kopipasta-0.14.0.dist-info/RECORD,,