app.py

import gradio as gr
import regex as re
import csv
import pandas as pd
from analyzer import combine_repo_files_for_llm, analyze_combined_file, parse_llm_json_response
from hf_utils import download_space_repo

# from hf_utils import download_space_repo

def process_repo_input(text):
    if not text:
        return pd.DataFrame(columns=["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
    # Split by newlines and commas, strip whitespace
    repo_ids = [repo.strip() for repo in re.split(r'[\n,]+', text) if repo.strip()]
    # Write to CSV
    csv_filename = "repo_ids.csv"
    with open(csv_filename, mode="w", newline='', encoding="utf-8") as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
        for repo_id in repo_ids:
            writer.writerow([repo_id, "", "", "", ""])
    # Read the CSV into a DataFrame to display
    df = pd.read_csv(csv_filename)
    return df

# Store the last entered repo ids and the current index in global variables for button access
last_repo_ids = []
current_repo_idx = 0

def process_repo_input_and_store(text):
    global last_repo_ids, current_repo_idx
    if not text:
        last_repo_ids = []
        current_repo_idx = 0
        return pd.DataFrame(columns=["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
    repo_ids = [repo.strip() for repo in re.split(r'[\n,]+', text) if repo.strip()]
    last_repo_ids = repo_ids
    current_repo_idx = 0
    csv_filename = "repo_ids.csv"
    with open(csv_filename, mode="w", newline='', encoding="utf-8") as csvfile:
        writer = csv.writer(csvfile)
        writer.writerow(["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
        for repo_id in repo_ids:
            writer.writerow([repo_id, "", "", "", ""])
    df = pd.read_csv(csv_filename)
    return df

def show_combined_repo_and_llm():
    global current_repo_idx
    if not last_repo_ids:
        return "No repo ID available. Please submit repo IDs first.", "", pd.DataFrame(), None
    if current_repo_idx >= len(last_repo_ids):
        return "All repo IDs have been processed.", "", pd.read_csv("repo_ids.csv"), None
    repo_id = last_repo_ids[current_repo_idx]
    try:
        download_space_repo(repo_id, local_dir="repo_files")
    except Exception as e:
        return f"Error downloading repo: {e}", "", pd.read_csv("repo_ids.csv"), None
    txt_path = combine_repo_files_for_llm()
    try:
        with open(txt_path, "r", encoding="utf-8") as f:
            combined_content = f.read()
    except Exception as e:
        return f"Error reading {txt_path}: {e}", "", pd.read_csv("repo_ids.csv"), None
    llm_output = analyze_combined_file(txt_path)
    llm_json = parse_llm_json_response(llm_output)
    # Update CSV for the current repo id
    csv_filename = "repo_ids.csv"
    try:
        df = pd.read_csv(csv_filename)
        highlight_idx = None
        # Cast columns to string to avoid dtype issues
        for col in ["strength", "weaknesses", "speciality", "relevance rating"]:
            df[col] = df[col].astype(str)
        for idx, row in df.iterrows():
            if row["repo id"] == repo_id:
                highlight_idx = idx
                if isinstance(llm_json, dict):
                    df.at[idx, "strength"] = llm_json.get("strength", "")
                    df.at[idx, "weaknesses"] = llm_json.get("weaknesses", "")
                    df.at[idx, "speciality"] = llm_json.get("speciality", "")
                    df.at[idx, "relevance rating"] = llm_json.get("relevance rating", "")
                break
        df.to_csv(csv_filename, index=False)
    except Exception as e:
        df = pd.read_csv(csv_filename)
        highlight_idx = None
    # Move to next repo for next click
    current_repo_idx += 1
    return combined_content, llm_output, (df, [highlight_idx] if highlight_idx is not None else [])

repo_id_input = gr.Textbox(label="Enter repo IDs (comma or newline separated)", lines=5, placeholder="repo1, repo2\nrepo3")
df_output = gr.Dataframe(headers=["repo id", "strength", "weaknesses", "speciality", "relevance rating", "Usecase"])

with gr.Blocks() as demo:
    gr.Markdown("## Repo ID Input")
    repo_id_box = repo_id_input.render()
    df_box = df_output.render()
    submit_btn = gr.Button("Submit Repo IDs")
    submit_btn.click(process_repo_input_and_store, inputs=repo_id_box, outputs=df_box)

    gr.Markdown("---")
    gr.Markdown("## Combine and Display Repo Files")
    combine_btn = gr.Button("Download, Combine & Show .py/.md Files from Next Repo and Analyze")
    combined_txt = gr.Textbox(label="Combined Repo Files", lines=20)
    llm_output_txt = gr.Textbox(label="LLM Analysis Output", lines=10)
    df_display = gr.Dataframe(
        headers=["repo id", "strength", "weaknesses", "speciality", "relevance rating", "Usecase"],
        highlight_row=True
    )
    combine_btn.click(show_combined_repo_and_llm, inputs=None, outputs=[combined_txt, llm_output_txt, df_display])

demo.launch()