"""
    sphinx.builders.linkcheck
    ~~~~~~~~~~~~~~~~~~~~~~~~~

    The CheckExternalLinksBuilder class.

    :copyright: Copyright 2007-2020 by the Sphinx team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

import json
import queue
import re
import socket
import threading
from html.parser import HTMLParser
from os import path
from typing import Any, Dict, List, Set, Tuple
from urllib.parse import unquote, urlparse

from docutils import nodes
from docutils.nodes import Node
from requests.exceptions import HTTPError

from sphinx.application import Sphinx
from sphinx.builders import Builder
from sphinx.locale import __
from sphinx.util import encode_uri, requests, logging
from sphinx.util.console import (  # type: ignore
    purple, red, darkgreen, darkgray, turquoise
)
from sphinx.util.nodes import get_node_line
from sphinx.util.requests import is_ssl_error


logger = logging.getLogger(__name__)


DEFAULT_REQUEST_HEADERS = {
    'Accept': 'text/html,application/xhtml+xml;q=0.9,*/*;q=0.8',
}


class AnchorCheckParser(HTMLParser):
    """Specialized HTML parser that looks for a specific anchor."""

    def __init__(self, search_anchor: str) -> None:
        super().__init__()

        self.search_anchor = search_anchor
        self.found = False

    def handle_starttag(self, tag: Any, attrs: Any) -> None:
        for key, value in attrs:
            if key in ('id', 'name') and value == self.search_anchor:
                self.found = True
                break


def check_anchor(response: requests.requests.Response, anchor: str) -> bool:
    """Reads HTML data from a response object `response` searching for `anchor`.
    Returns True if anchor was found, False otherwise.
    """
    parser = AnchorCheckParser(anchor)
    # Read file in chunks. If we find a matching anchor, we break
    # the loop early in hopes not to have to download the whole thing.
    for chunk in response.iter_content(chunk_size=4096, decode_unicode=True):
        if isinstance(chunk, bytes):    # requests failed to decode
            chunk = chunk.decode()      # manually try to decode it

        parser.feed(chunk)
        if parser.found:
            break
    parser.close()
    return parser.found


class CheckExternalLinksBuilder(Builder):
    """
    Checks for broken external links.
    """
    name = 'linkcheck'
    epilog = __('Look for any errors in the above output or in '
                '%(outdir)s/output.txt')

    def init(self) -> None:
        self.to_ignore = [re.compile(x) for x in self.app.config.linkcheck_ignore]
        self.anchors_ignore = [re.compile(x)
                               for x in self.app.config.linkcheck_anchors_ignore]
        self.auth = [(re.compile(pattern), auth_info) for pattern, auth_info
                     in self.app.config.linkcheck_auth]
        self.good = set()       # type: Set[str]
        self.broken = {}        # type: Dict[str, str]
        self.redirected = {}    # type: Dict[str, Tuple[str, int]]
        # set a timeout for non-responding servers
        socket.setdefaulttimeout(5.0)
        # create output file
        open(path.join(self.outdir, 'output.txt'), 'w').close()
        # create JSON output file
        open(path.join(self.outdir, 'output.json'), 'w').close()

        # create queues and worker threads
        self.wqueue = queue.Queue()  # type: queue.Queue
        self.rqueue = queue.Queue()  # type: queue.Queue
        self.workers = []  # type: List[threading.Thread]
        for i in range(self.app.config.linkcheck_workers):
            thread = threading.Thread(target=self.check_thread)
            thread.setDaemon(True)
            thread.start()
            self.workers.append(thread)

    def check_thread(self) -> None:
        kwargs = {
            'allow_redirects': True,
        }  # type: Dict
        if self.app.config.linkcheck_timeout:
            kwargs['timeout'] = self.app.config.linkcheck_timeout

        def get_request_headers() -> Dict:
            url = urlparse(uri)
            candidates = ["%s://%s" % (url.scheme, url.netloc),
                          "%s://%s/" % (url.scheme, url.netloc),
                          uri,
                          "*"]

            for u in candidates:
                if u in self.config.linkcheck_request_headers:
                    headers = dict(DEFAULT_REQUEST_HEADERS)
                    headers.update(self.config.linkcheck_request_headers[u])
                    return headers

            return {}

        def check_uri() -> Tuple[str, str, int]:
            # split off anchor
            if '#' in uri:
                req_url, anchor = uri.split('#', 1)
                for rex in self.anchors_ignore:
                    if rex.match(anchor):
                        anchor = None
                        break
            else:
                req_url = uri
                anchor = None

            # handle non-ASCII URIs
            try:
                req_url.encode('ascii')
            except UnicodeError:
                req_url = encode_uri(req_url)

            # Get auth info, if any
            for pattern, auth_info in self.auth:
                if pattern.match(uri):
                    break
            else:
                auth_info = None

            # update request headers for the URL
            kwargs['headers'] = get_request_headers()

            try:
                if anchor and self.app.config.linkcheck_anchors:
                    # Read the whole document and see if #anchor exists
                    response = requests.get(req_url, stream=True, config=self.app.config,
                                            auth=auth_info, **kwargs)
                    found = check_anchor(response, unquote(anchor))

                    if not found:
                        raise Exception(__("Anchor '%s' not found") % anchor)
                else:
                    try:
                        # try a HEAD request first, which should be easier on
                        # the server and the network
                        response = requests.head(req_url, config=self.app.config,
                                                 auth=auth_info, **kwargs)
                        response.raise_for_status()
                    except HTTPError:
                        # retry with GET request if that fails, some servers
                        # don't like HEAD requests.
                        response = requests.get(req_url, stream=True, config=self.app.config,
                                                auth=auth_info, **kwargs)
                        response.raise_for_status()
            except HTTPError as err:
                if err.response.status_code == 401:
                    # We'll take "Unauthorized" as working.
                    return 'working', ' - unauthorized', 0
                elif err.response.status_code == 503:
                    # We'll take "Service Unavailable" as ignored.
                    return 'ignored', str(err), 0
                else:
                    return 'broken', str(err), 0
            except Exception as err:
                if is_ssl_error(err):
                    return 'ignored', str(err), 0
                else:
                    return 'broken', str(err), 0
            if response.url.rstrip('/') == req_url.rstrip('/'):
                return 'working', '', 0
            else:
                new_url = response.url
                if anchor:
                    new_url += '#' + anchor
                # history contains any redirects, get last
                if response.history:
                    code = response.history[-1].status_code
                    return 'redirected', new_url, code
                else:
                    return 'redirected', new_url, 0

        def check() -> Tuple[str, str, int]:
            # check for various conditions without bothering the network
            if len(uri) == 0 or uri.startswith(('#', 'mailto:', 'ftp:')):
                return 'unchecked', '', 0
            elif not uri.startswith(('http:', 'https:')):
                return 'local', '', 0
            elif uri in self.good:
                return 'working', 'old', 0
            elif uri in self.broken:
                return 'broken', self.broken[uri], 0
            elif uri in self.redirected:
                return 'redirected', self.redirected[uri][0], self.redirected[uri][1]
            for rex in self.to_ignore:
                if rex.match(uri):
                    return 'ignored', '', 0

            # need to actually check the URI
            for _ in range(self.app.config.linkcheck_retries):
                status, info, code = check_uri()
                if status != "broken":
                    break

            if status == "working":
                self.good.add(uri)
            elif status == "broken":
                self.broken[uri] = info
            elif status == "redirected":
                self.redirected[uri] = (info, code)

            return (status, info, code)

        while True:
            uri, docname, lineno = self.wqueue.get()
            if uri is None:
                break
            status, info, code = check()
            self.rqueue.put((uri, docname, lineno, status, info, code))

    def process_result(self, result: Tuple[str, str, int, str, str, int]) -> None:
        uri, docname, lineno, status, info, code = result

        filename = self.env.doc2path(docname, None)
        linkstat = dict(filename=filename, lineno=lineno,
                        status=status, code=code, uri=uri,
                        info=info)
        if status == 'unchecked':
            self.write_linkstat(linkstat)
            return
        if status == 'working' and info == 'old':
            self.write_linkstat(linkstat)
            return
        if lineno:
            logger.info('(line %4d) ', lineno, nonl=True)
        if status == 'ignored':
            if info:
                logger.info(darkgray('-ignored- ') + uri + ': ' + info)
            else:
                logger.info(darkgray('-ignored- ') + uri)
            self.write_linkstat(linkstat)
        elif status == 'local':
            logger.info(darkgray('-local-   ') + uri)
            self.write_entry('local', docname, filename, lineno, uri)
            self.write_linkstat(linkstat)
        elif status == 'working':
            logger.info(darkgreen('ok        ') + uri + info)
            self.write_linkstat(linkstat)
        elif status == 'broken':
            if self.app.quiet or self.app.warningiserror:
                logger.warning(__('broken link: %s (%s)'), uri, info,
                               location=(filename, lineno))
            else:
                logger.info(red('broken    ') + uri + red(' - ' + info))
            self.write_entry('broken', docname, filename, lineno, uri + ': ' + info)
            self.write_linkstat(linkstat)
        elif status == 'redirected':
            try:
                text, color = {
                    301: ('permanently', purple),
                    302: ('with Found', purple),
                    303: ('with See Other', purple),
                    307: ('temporarily', turquoise),
                    308: ('permanently', purple),
                }[code]
            except KeyError:
                text, color = ('with unknown code', purple)
            linkstat['text'] = text
            logger.info(color('redirect  ') + uri + color(' - ' + text + ' to ' + info))
            self.write_entry('redirected ' + text, docname, filename,
                             lineno, uri + ' to ' + info)
            self.write_linkstat(linkstat)

    def get_target_uri(self, docname: str, typ: str = None) -> str:
        return ''

    def get_outdated_docs(self) -> Set[str]:
        return self.env.found_docs

    def prepare_writing(self, docnames: Set[str]) -> None:
        return

    def write_doc(self, docname: str, doctree: Node) -> None:
        logger.info('')
        n = 0

        # reference nodes
        for refnode in doctree.traverse(nodes.reference):
            if 'refuri' not in refnode:
                continue
            uri = refnode['refuri']
            lineno = get_node_line(refnode)
            self.wqueue.put((uri, docname, lineno), False)
            n += 1

        # image nodes
        for imgnode in doctree.traverse(nodes.image):
            uri = imgnode['candidates'].get('?')
            if uri and '://' in uri:
                lineno = get_node_line(imgnode)
                self.wqueue.put((uri, docname, lineno), False)
                n += 1

        done = 0
        while done < n:
            self.process_result(self.rqueue.get())
            done += 1

        if self.broken:
            self.app.statuscode = 1

    def write_entry(self, what: str, docname: str, filename: str, line: int,
                    uri: str) -> None:
        with open(path.join(self.outdir, 'output.txt'), 'a') as output:
            output.write("%s:%s: [%s] %s\n" % (filename, line, what, uri))

    def write_linkstat(self, data: dict) -> None:
        with open(path.join(self.outdir, 'output.json'), 'a') as output:
            output.write(json.dumps(data))
            output.write('\n')

    def finish(self) -> None:
        for worker in self.workers:
            self.wqueue.put((None, None, None), False)


def setup(app: Sphinx) -> Dict[str, Any]:
    app.add_builder(CheckExternalLinksBuilder)

    app.add_config_value('linkcheck_ignore', [], None)
    app.add_config_value('linkcheck_auth', [], None)
    app.add_config_value('linkcheck_request_headers', {}, None)
    app.add_config_value('linkcheck_retries', 1, None)
    app.add_config_value('linkcheck_timeout', None, None, [int])
    app.add_config_value('linkcheck_workers', 5, None)
    app.add_config_value('linkcheck_anchors', True, None)
    # Anchors starting with ! are ignored since they are
    # commonly used for dynamic pages
    app.add_config_value('linkcheck_anchors_ignore', ["^!"], None)

    return {
        'version': 'builtin',
        'parallel_read_safe': True,
        'parallel_write_safe': True,
    }