tauri-plugin-indexer 0.1.1

use walkdir::DirEntry;
use std::process::Command;
use std::io;
use std::fs::{self, OpenOptions};
use std::io::Write;
use std::path::Path;
use anyhow::Result;
use crate::indexer::config::config::indexable_extensions;

const MAX_FILE_SIZE_BYTES: u64 = 6 * 1024 * 1024; // 6 MB

pub fn is_indexable_file(entry: &DirEntry) -> bool {
    let path = entry.path();
    if !path.is_file() {
        return false;
    }

    // Check file size
    if let Ok(metadata) = fs::metadata(path) {
        if metadata.len() > MAX_FILE_SIZE_BYTES {
            return false;
        }
    } else {
        return false;
    }
    
    // Check extension against configured extensions
    if let Some(ext) = path.extension() {
        let ext = ext.to_string_lossy().to_lowercase();
        indexable_extensions().iter().any(|valid_ext| valid_ext == &ext)
    } else {
        false
    }
}

pub fn save_to_file<T: serde::Serialize>(path: &Path, data: &T) -> Result<()> {
    let temp_path = path.with_extension("tmp");
    let mut file = OpenOptions::new()
        .create(true)
        .write(true)
        .truncate(true)
        .open(&temp_path)?;
    serde_json::to_writer_pretty(&mut file, data)?;
    file.flush()?;
    fs::rename(temp_path, path)?;
    Ok(())
}

pub fn pdftotext(path: &Path) -> io::Result<String> {
    let output = Command::new("pdftotext")
        .arg(path)
        .arg("-") // Output to stdout
        .output()?;

    if output.status.success() {
        Ok(String::from_utf8_lossy(&output.stdout).to_string())
    } else {
        Err(io::Error::new(
            io::ErrorKind::Other,
            format!(
                "pdftotext failed: {}",
                String::from_utf8_lossy(&output.stderr)
            ),
        ))
    }
}