"""Small HTML tree used by official metadata adapters."""
from html.parser import HTMLParser


class Node:
    def __init__(self,tag='',attrs=None):
        self.tag=tag
        self.attrs={key:value or '' for key,value in attrs or []}
        self.children=[]

    def text(self):
        if self.tag in ('script','style'):
            return ''
        content=''.join(child.text() if isinstance(child,Node) else child for child in self.children)
        return ' '+content+' ' if self.tag in ('p','div','section','li','br') else content

    def walk(self):
        yield self
        for child in self.children:
            if isinstance(child,Node):
                yield from child.walk()


class Document(HTMLParser):
    VOID={'area','base','br','col','embed','hr','img','input','link','meta','param','source','track','wbr'}

    def __init__(self,html):
        super().__init__(convert_charrefs=True)
        self.root=Node()
        self.stack=[self.root]
        self.feed(html)

    def handle_starttag(self,tag,attrs):
        node=Node(tag,attrs)
        self.stack[-1].children.append(node)
        if tag not in self.VOID:
            self.stack.append(node)

    def handle_endtag(self,tag):
        for index in range(len(self.stack)-1,0,-1):
            if self.stack[index].tag==tag:
                del self.stack[index:]
                break

    def handle_data(self,data):
        self.stack[-1].children.append(data)


def clean(text):
    return ' '.join(text.split())