app.py

import pandas as pd
import sqlite3
import gradio as gr
import unicodedata
import re
import ast
import requests

database_url = "https://raw.githubusercontent.com/R3gm/database_zip_files/main/archive/database.csv"
database_path = "database.csv"
description = "This app digs through Hugging Face’s public zip files hunting for RVC models… and occasionally brings back random stuff that has nothing to do with them. Don’t worry though—the best RVC matches are always shown first, because we like to pretend we’re organized."


def clean_file_url(val):
    # If missing
    if pd.isna(val):
        return ""

    # If it's already a list (e.g. from JSON/df directly)
    if isinstance(val, list):
        return ", ".join(map(str, val))

    # If it's a string like '["a","b"]'
    if isinstance(val, str) and val.strip().startswith("[") and val.strip().endswith("]"):
        try:
            parsed = ast.literal_eval(val)
            if isinstance(parsed, list):
                return ", ".join(map(str, parsed))
        except Exception:
            return val  # fallback: leave as-is

    # Otherwise, return as-is
    return str(val)


def normalize(text: str) -> str:
    if pd.isna(text):
        return ""
    # Convert to lowercase
    text = text.lower()
    # Remove accents
    text = ''.join(
        c for c in unicodedata.normalize('NFD', text)
        if unicodedata.category(c) != 'Mn'
    )
    # Replace separators with space
    return re.sub(r"[+()\-_/.]", " ", text)


def search_files(query: str):
    if not query.strip():
        return pd.DataFrame([{"Result": "Empty query"}])

    keywords = normalize(query).split()

    whole_conditions = " AND ".join([
        f"(FILENAME_NORM LIKE '% {k} %' OR FILENAME_NORM LIKE '{k} %' OR FILENAME_NORM LIKE '% {k}' OR FILENAME_NORM = '{k}')"
        for k in keywords
    ])
    partial_conditions = " AND ".join([f"FILENAME_NORM LIKE '%{k}%'" for k in keywords])

    sql = f"""
    SELECT *, 
           CASE WHEN {whole_conditions} THEN 1 ELSE 0 END AS whole_match
    FROM files
    WHERE {partial_conditions}
    ORDER BY whole_match DESC, orig_index ASC;
    """

    df = pd.read_sql(sql, conn)

    if df.empty:
        return "<p>No matches found</p>"

    df_subset = df.head(250)  # limit 250 results

    rows = []
    for i, row in enumerate(df_subset.itertuples(index=False)):
        filename = row.FILENAME
        url = row.PARSED_URL
        model_id = row.MODEL_ID

        rows.append(f"""
        <tr>
            <td>{filename}</td>
            <td>
                <input type="text" value="{url}" id="copytext{i}" readonly 
                      style="width:300px; padding:4px; border-radius:6px; border:1px solid #666; 
                            background-color:var(--block-background-fill); 
                            color:var(--body-text-color);" />
                <button style="margin-left:5px; padding:4px 8px; border-radius:6px; 
                              background-color:var(--button-primary-background-fill);
                              color:var(--button-primary-text-color);
                              border:none; cursor:pointer;"
                        onclick="navigator.clipboard.writeText(document.getElementById('copytext{i}').value)">
                    Copy
                </button>
            </td>
            <td>{model_id}</td>
        </tr>
        """)

    html = f"""
    <table border=1 style="border-collapse:collapse; width:100%; text-align:left;">
    <thead>
        <tr>
            <th style="padding:6px;">Filename</th>
            <th style="padding:6px;">File URL</th>
            <th style="padding:6px;">Repo ID</th>
        </tr>
    </thead>
    <tbody>
    {''.join(rows)}
    </tbody>
    </table>
    """

    return html


response = requests.get(database_url, stream=True)
with open(database_path, "wb") as f:
    for chunk in response.iter_content(chunk_size=8192):
        f.write(chunk)

df = pd.read_csv(database_path)

df["FILENAME_NORM"] = df["FILENAME"].apply(normalize)
df["PARSED_URL"] = df["PARSED_URL"].apply(clean_file_url)

df = df.reset_index(drop=True)
df["orig_index"] = df.index

# Connect to SQLite
conn = sqlite3.connect(":memory:", check_same_thread=False)
df.to_sql("files", conn, index=False, if_exists="replace")

with gr.Blocks() as demo:
    gr.Markdown("## 🔍 RVC Voice Finder")
    query_input = gr.Textbox(label="Search here", placeholder="Hatsune Miku")
    button_query = gr.Button("Search")
    output = gr.HTML(label="Search Results")
    gr.Markdown(description)

    query_input.submit(search_files, inputs=query_input, outputs=output)
    button_query.click(search_files, inputs=query_input, outputs=output)

if __name__ == "__main__":
    demo.launch(debug=True, show_error=True)