fn run_ls()

in tensor-tools/src/main.rs [299:396]

• 98 lines of code
• 10 McCabe index (conditional complexity)

fn run_ls(
    file: &std::path::PathBuf,
    format: Option<Format>,
    verbose: bool,
    device: &Device,
) -> Result<()> {
    let format = match format {
        Some(format) => format,
        None => match Format::infer(file) {
            Some(format) => format,
            None => {
                println!(
                    "{file:?}: cannot infer format from file extension, use the --format flag"
                );
                return Ok(());
            }
        },
    };
    match format {
        Format::Npz => {
            let tensors = candle::npy::NpzTensors::new(file)?;
            let mut names = tensors.names();
            names.sort();
            for name in names {
                let shape_dtype = match tensors.get_shape_and_dtype(name) {
                    Ok((shape, dtype)) => format!("[{shape:?}; {dtype:?}]"),
                    Err(err) => err.to_string(),
                };
                println!("{name}: {shape_dtype}")
            }
        }
        Format::Safetensors => {
            let tensors = unsafe { candle::safetensors::MmapedSafetensors::new(file)? };
            let mut tensors = tensors.tensors();
            tensors.sort_by(|a, b| a.0.cmp(&b.0));
            for (name, view) in tensors.iter() {
                let dtype = view.dtype();
                let dtype = match candle::DType::try_from(dtype) {
                    Ok(dtype) => format!("{dtype:?}"),
                    Err(_) => format!("{dtype:?}"),
                };
                let shape = view.shape();
                println!("{name}: [{shape:?}; {dtype}]")
            }
        }
        Format::Pth => {
            let mut tensors = candle::pickle::read_pth_tensor_info(file, verbose, None)?;
            tensors.sort_by(|a, b| a.name.cmp(&b.name));
            for tensor_info in tensors.iter() {
                println!(
                    "{}: [{:?}; {:?}]",
                    tensor_info.name,
                    tensor_info.layout.shape(),
                    tensor_info.dtype,
                );
                if verbose {
                    println!("    {tensor_info:?}");
                }
            }
        }
        Format::Pickle => {
            let file = std::fs::File::open(file)?;
            let mut reader = std::io::BufReader::new(file);
            let mut stack = candle::pickle::Stack::empty();
            stack.read_loop(&mut reader)?;
            for (i, obj) in stack.stack().iter().enumerate() {
                println!("{i} {obj:?}");
            }
        }
        Format::Ggml => {
            let mut file = std::fs::File::open(file)?;
            let content = candle::quantized::ggml_file::Content::read(&mut file, device)?;
            let mut tensors = content.tensors.into_iter().collect::<Vec<_>>();
            tensors.sort_by(|a, b| a.0.cmp(&b.0));
            for (name, qtensor) in tensors.iter() {
                println!("{name}: [{:?}; {:?}]", qtensor.shape(), qtensor.dtype());
            }
        }
        Format::Gguf => {
            let mut file = std::fs::File::open(file)?;
            let content = gguf_file::Content::read(&mut file)?;
            if verbose {
                let mut metadata = content.metadata.into_iter().collect::<Vec<_>>();
                metadata.sort_by(|a, b| a.0.cmp(&b.0));
                println!("metadata entries ({})", metadata.len());
                for (key, value) in metadata.iter() {
                    println!("  {key}: {value:?}");
                }
            }
            let mut tensors = content.tensor_infos.into_iter().collect::<Vec<_>>();
            tensors.sort_by(|a, b| a.0.cmp(&b.0));
            for (name, info) in tensors.iter() {
                println!("{name}: [{:?}; {:?}]", info.shape, info.ggml_dtype);
            }
        }
    }
    Ok(())
}