Function estimate_file_workload

src/utils/estimation.rs:25–78

Estimate workload for quick scan (file) mode

(
    input_file_path: &str, 
    prefix: &str, 
    suffix: &str,
    infix: Option<&str>
)

/// Estimate workload for quick scan (file) mode
async fn estimate_file_workload(
    input_file_path: &str, 
    prefix: &str, 
    suffix: &str,
    infix: Option<&str>
) -> Result<u64, Error> {
    // Check if file exists
    if !Path::new(input_file_path).exists() {
        return Err(anyhow!("File not found: {}", input_file_path));
    }
    
    // Get file size for estimation
    let metadata = tokio::fs::metadata(input_file_path).await?;
    let file_size = metadata.len();
    
    // Check if file is empty
    if file_size == 0 {
        return Err(anyhow!("File is empty: {}", input_file_path));
    }
    
    // Sample a portion of the file for better accuracy
    const SAMPLE_SIZE: u64 = 50_000;
    let (sample_matched, sample_count, sample_bytes_read) = sample_file(
        input_file_path, 
        SAMPLE_SIZE, 
        prefix, 
        suffix,
        infix
    ).await?;
    
    // Handle the case where no valid lines were found
    if sample_count == 0 {
        return Err(anyhow!("No valid phone numbers found in file: {}", input_file_path));
    }
    
    // Calculate total estimate
    let match_ratio = sample_matched as f64 / sample_count as f64;
    let bytes_per_line = if sample_count > 0 { 
        sample_bytes_read as f64 / sample_count as f64 
    } else { 
        50.0 // Default estimate
    };
    
    let estimated_total_lines = (file_size as f64 / bytes_per_line).ceil() as u64;
    let estimated_matches = (estimated_total_lines as f64 * match_ratio).ceil() as u64;
    
    // Add a buffer to ensure we don't underestimate (increase by 10%)
    let estimated_matches = (estimated_matches as f64 * 1.1).ceil() as u64;
    
    // Ensure a reasonable minimum
    let estimated_matches = std::cmp::max(estimated_matches, 1000);
    
    Ok(estimated_matches)
}

/// Sample a file to get an estimate of matching lines
async fn sample_file(