html5ever 0.22.2

// Copyright 2014-2017 The html5ever Project Developers. See the
// COPYRIGHT file at the top-level directory of this distribution.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

#[macro_use] extern crate html5ever;

use std::io;
use std::iter::repeat;
use std::default::Default;
use std::string::String;

use html5ever::parse_document;
use html5ever::rcdom::{NodeData, RcDom, Handle};
use html5ever::tendril::TendrilSink;

// This is not proper HTML serialization, of course.

fn walk(indent: usize, handle: Handle) {
    let node = handle;
    // FIXME: don't allocate
    print!("{}", repeat(" ").take(indent).collect::<String>());
    match node.data {
        NodeData::Document
            => println!("#Document"),

        NodeData::Doctype { ref name, ref public_id, ref system_id }
            => println!("<!DOCTYPE {} \"{}\" \"{}\">", name, public_id, system_id),

        NodeData::Text { ref contents }
            => println!("#text: {}", escape_default(&contents.borrow())),

        NodeData::Comment { ref contents }
            => println!("<!-- {} -->", escape_default(contents)),

        NodeData::Element { ref name, ref attrs, .. } => {
            assert!(name.ns == ns!(html));
            print!("<{}", name.local);
            for attr in attrs.borrow().iter() {
                assert!(attr.name.ns == ns!());
                print!(" {}=\"{}\"", attr.name.local, attr.value);
            }
            println!(">");
        }

        NodeData::ProcessingInstruction { .. } => unreachable!()
    }

    for child in node.children.borrow().iter() {
        walk(indent+4, child.clone());
    }
}

// FIXME: Copy of str::escape_default from std, which is currently unstable
pub fn escape_default(s: &str) -> String {
    s.chars().flat_map(|c| c.escape_default()).collect()
}

fn main() {
    let stdin = io::stdin();
    let dom = parse_document(RcDom::default(), Default::default())
        .from_utf8()
        .read_from(&mut stdin.lock())
        .unwrap();
    walk(0, dom.document);

    if !dom.errors.is_empty() {
        println!("\nParse errors:");
        for err in dom.errors.into_iter() {
            println!("    {}", err);
        }
    }
}