# hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.

#

# Copyright 21 May 2005 - (c) 2005 Jake Edge <jake@edge2.net>

# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

from __future__ import absolute_import

import os

import re

import time

from ..i18n import _

from .common import (

    ErrorResponse,

    HTTP_NOT_FOUND,

    HTTP_OK,

    HTTP_SERVER_ERROR,

    cspvalues,

    get_contact,

    get_mtime,

    ismember,

    paritygen,

    staticfile,

)

from .request import wsgirequest

from .. import (

    encoding,

    error,

    hg,

    profiling,

    scmutil,

    templater,

    ui as uimod,

    util,

)

from . import (

    hgweb_mod,

    webutil,

    wsgicgi,

)

def cleannames(items):

    return [(util.pconvert(name).strip('/'), path) for name, path in items]

def findrepos(paths):

    repos = []

    for prefix, root in cleannames(paths):

        roothead, roottail = os.path.split(root)

        # "foo = /bar/*" or "foo = /bar/**" lets every repo /bar/N in or below

        # /bar/ be served as as foo/N .

        # '*' will not search inside dirs with .hg (except .hg/patches),

        # '**' will search inside dirs with .hg (and thus also find subrepos).

        try:

            recurse = {'*': False, '**': True}[roottail]

        except KeyError:

            repos.append((prefix, root))

            continue

        roothead = os.path.normpath(os.path.abspath(roothead))

        paths = scmutil.walkrepos(roothead, followsym=True, recurse=recurse)

        repos.extend(urlrepos(prefix, roothead, paths))

    return repos

def urlrepos(prefix, roothead, paths):

    """yield url paths and filesystem paths from a list of repo paths

    >>> conv = lambda seq: [(v, util.pconvert(p)) for v,p in seq]

    >>> conv(urlrepos('hg', '/opt', ['/opt/r', '/opt/r/r', '/opt']))

    [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]

    >>> conv(urlrepos('', '/opt', ['/opt/r', '/opt/r/r', '/opt']))

    [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]

    """

    for path in paths:

        path = os.path.normpath(path)

        yield (prefix + '/' +

               util.pconvert(path[len(roothead):]).lstrip('/')).strip('/'), path

def geturlcgivars(baseurl, port):

    """

    Extract CGI variables from baseurl

    >>> geturlcgivars("http://host.org/base", "80")

    ('host.org', '80', '/base')

    >>> geturlcgivars("http://host.org:8000/base", "80")

    ('host.org', '8000', '/base')

    >>> geturlcgivars('/base', 8000)

    ('', '8000', '/base')

    >>> geturlcgivars("base", '8000')

    ('', '8000', '/base')

    >>> geturlcgivars("http://host", '8000')

    ('host', '8000', '/')

    >>> geturlcgivars("http://host/", '8000')

    ('host', '8000', '/')

    """

    u = util.url(baseurl)

    name = u.host or ''

    if u.port:

        port = u.port

    path = u.path or ""

    if not path.startswith('/'):

        path = '/' + path

    return name, str(port), path

class hgwebdir(object):

    """HTTP server for multiple repositories.

    Given a configuration, different repositories will be served depending

    on the request path.

    Instances are typically used as WSGI applications.

    """

    def __init__(self, conf, baseui=None):

        self.conf = conf

        self.baseui = baseui

        self.ui = None

        self.lastrefresh = 0

        self.motd = None

        self.refresh()

    def refresh(self):

        refreshinterval = 20

        if self.ui:

            refreshinterval = self.ui.configint('web', 'refreshinterval',

                                                refreshinterval)

        # refreshinterval <= 0 means to always refresh.

        if (refreshinterval > 0 and

            self.lastrefresh + refreshinterval > time.time()):

            return

        if self.baseui:

            u = self.baseui.copy()

        else:

            u = uimod.ui.load()

            u.setconfig('ui', 'report_untrusted', 'off', 'hgwebdir')

            u.setconfig('ui', 'nontty', 'true', 'hgwebdir')

            # displaying bundling progress bar while serving feels wrong and may

            # break some wsgi implementations.

            u.setconfig('progress', 'disable', 'true', 'hgweb')

        if not isinstance(self.conf, (dict, list, tuple)):

            map = {'paths': 'hgweb-paths'}

            if not os.path.exists(self.conf):

                raise error.Abort(_('config file %s not found!') % self.conf)

            u.readconfig(self.conf, remap=map, trust=True)

            paths = []

            for name, ignored in u.configitems('hgweb-paths'):

                for path in u.configlist('hgweb-paths', name):

                    paths.append((name, path))

        elif isinstance(self.conf, (list, tuple)):

            paths = self.conf

        elif isinstance(self.conf, dict):

            paths = self.conf.items()

        repos = findrepos(paths)

        for prefix, root in u.configitems('collections'):

            prefix = util.pconvert(prefix)

            for path in scmutil.walkrepos(root, followsym=True):

                repo = os.path.normpath(path)

                name = util.pconvert(repo)

                if name.startswith(prefix):

                    name = name[len(prefix):]

                repos.append((name.lstrip('/'), repo))

        self.repos = repos

        self.ui = u

        encoding.encoding = self.ui.config('web', 'encoding',

                                           encoding.encoding)

        self.style = self.ui.config('web', 'style', 'paper')

        self.templatepath = self.ui.config('web', 'templates', None)

        self.stripecount = self.ui.config('web', 'stripes', 1)

        if self.stripecount:

            self.stripecount = int(self.stripecount)

        self._baseurl = self.ui.config('web', 'baseurl')

        prefix = self.ui.config('web', 'prefix', '')

        if prefix.startswith('/'):

            prefix = prefix[1:]

        if prefix.endswith('/'):

            prefix = prefix[:-1]

        self.prefix = prefix

        self.lastrefresh = time.time()

    def run(self):

        if not encoding.environ.get('GATEWAY_INTERFACE',

                                    '').startswith("CGI/1."):

            raise RuntimeError("This function is only intended to be "

                               "called while running as a CGI script.")

        wsgicgi.launch(self)

    def __call__(self, env, respond):

        req = wsgirequest(env, respond)

        return self.run_wsgi(req)

    def read_allowed(self, ui, req):

        """Check allow_read and deny_read config options of a repo's ui object

        to determine user permissions.  By default, with neither option set (or

        both empty), allow all users to read the repo.  There are two ways a

        user can be denied read access:  (1) deny_read is not empty, and the

        user is unauthenticated or deny_read contains user (or *), and (2)

        allow_read is not empty and the user is not in allow_read.  Return True

        if user is allowed to read the repo, else return False."""

        user = req.env.get('REMOTE_USER')

        deny_read = ui.configlist('web', 'deny_read', untrusted=True)

        if deny_read and (not user or ismember(ui, user, deny_read)):

            return False

        allow_read = ui.configlist('web', 'allow_read', untrusted=True)

        # by default, allow reading if no allow_read option has been set

        if (not allow_read) or ismember(ui, user, allow_read):

            return True

        return False

    def run_wsgi(self, req):

        with profiling.maybeprofile(self.ui):

            for r in self._runwsgi(req):

                yield r

    def _runwsgi(self, req):

        try:

            self.refresh()

            csp, nonce = cspvalues(self.ui)

            if csp:

                req.headers.append(('Content-Security-Policy', csp))

            virtual = req.env.get("PATH_INFO", "").strip('/')

            tmpl = self.templater(req, nonce)

            ctype = tmpl('mimetype', encoding=encoding.encoding)

            ctype = templater.stringify(ctype)

            # a static file

            if virtual.startswith('static/') or 'static' in req.form:

                if virtual.startswith('static/'):

                    fname = virtual[7:]

                else:

                    fname = req.form['static'][0]

                static = self.ui.config("web", "static", None,

                                        untrusted=False)

                if not static:

                    tp = self.templatepath or templater.templatepaths()

                    if isinstance(tp, str):

                        tp = [tp]

                    static = [os.path.join(p, 'static') for p in tp]

                staticfile(static, fname, req)

                return []

            # top-level index

                req.respond(HTTP_OK, ctype)

                return self.makeindex(req, tmpl)

            # nested indexes and hgwebs

            virtualrepo = virtual

            while virtualrepo:

                real = repos.get(virtualrepo)

                if real:

                    req.env['REPO_NAME'] = virtualrepo

                    try:

                        # ensure caller gets private copy of ui

                        repo = hg.repository(self.ui.copy(), real)

                        return hgweb_mod.hgweb(repo).run_wsgi(req)

                    except IOError as inst:

                        msg = inst.strerror

                        raise ErrorResponse(HTTP_SERVER_ERROR, msg)

                    except error.RepoError as inst:

                        raise ErrorResponse(HTTP_SERVER_ERROR, str(inst))

                up = virtualrepo.rfind('/')

                if up < 0:

                    break

                virtualrepo = virtualrepo[:up]

            # browse subdirectories

            subdir = virtual + '/'

            if [r for r in repos if r.startswith(subdir)]:

                req.respond(HTTP_OK, ctype)

                return self.makeindex(req, tmpl, subdir)

            # prefixes not found

            req.respond(HTTP_NOT_FOUND, ctype)

            return tmpl("notfound", repo=virtual)

        except ErrorResponse as err:

            req.respond(err, ctype)

            return tmpl('error', error=err.message or '')

        finally:

            tmpl = None

    def makeindex(self, req, tmpl, subdir=""):

        def archivelist(ui, nodeid, url):

            allowed = ui.configlist("web", "allow_archive", untrusted=True)

            archives = []

            for typ, spec in hgweb_mod.archivespecs.iteritems():

                if typ in allowed or ui.configbool("web", "allow" + typ,

                                                    untrusted=True):

                    archives.append({"type" : typ, "extension": spec[2],

                                     "node": nodeid, "url": url})

            return archives

        def rawentries(subdir="", **map):

            descend = self.ui.configbool('web', 'descend', True)

            collapse = self.ui.configbool('web', 'collapse', False)

            seenrepos = set()

            seendirs = set()

            for name, path in self.repos:

                if not name.startswith(subdir):

                    continue

                name = name[len(subdir):]

                directory = False

                if '/' in name:

                    if not descend:

                        continue

                    nameparts = name.split('/')

                    rootname = nameparts[0]

                    if not collapse:

                        pass

                    elif rootname in seendirs:

                        continue

                    elif rootname in seenrepos:

                        pass

                    else:

                        directory = True

                        name = rootname

                        # redefine the path to refer to the directory

                        discarded = '/'.join(nameparts[1:])

                        # remove name parts plus accompanying slash

                        path = path[:-len(discarded) - 1]

                        try:

                            r = hg.repository(self.ui, path)

                            directory = False

                        except (IOError, error.RepoError):

                            pass

                parts = [name]

                if req.env['SCRIPT_NAME']:

                    parts.insert(0, req.env['SCRIPT_NAME'])

                url = re.sub(r'/+', '/', '/'.join(parts) + '/')

                # show either a directory entry or a repository

                if directory:

                    # get the directory's time information