# 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 Olivia Mackall <olivia@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.

import gc

import os

import time

from ..i18n import _

from .common import (

    ErrorResponse,

    HTTP_SERVER_ERROR,

    cspvalues,

    get_contact,

    get_mtime,

    ismember,

    paritygen,

    staticfile,

    statusmessage,

)

from .. import (

    configitems,

    encoding,

    error,

    extensions,

    hg,

    pathutil,

    profiling,

    pycompat,

    rcutil,

    registrar,

    scmutil,

    templater,

    templateutil,

    ui as uimod,

    util,

)

from . import (

    hgweb_mod,

    request as requestmod,

    webutil,

    wsgicgi,

)

from ..utils import dateutil

def cleannames(items):

    return [(util.pconvert(name).strip(b'/'), 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 = {b'*': False, b'**': True}[roottail]

        except KeyError:

            repos.append((prefix, root))

            continue

        roothead = os.path.normpath(util.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(b'hg', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))

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

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

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

    """

    for path in paths:

        path = os.path.normpath(path)

        yield (

            prefix + b'/' + util.pconvert(path[len(roothead) :]).lstrip(b'/')

        ).strip(b'/'), path

def readallowed(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.remoteuser

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

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

        return False

    allow_read = ui.configlist(b'web', b'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 rawindexentries(ui, repos, req, subdir=b''):

    descend = ui.configbool(b'web', b'descend')

    collapse = ui.configbool(b'web', b'collapse')

    seenrepos = set()

    seendirs = set()

    for name, path in repos:

        if not name.startswith(subdir):

            continue

        name = name[len(subdir) :]

        directory = False

        if b'/' in name:

            if not descend:

                continue

            nameparts = name.split(b'/')

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

                # remove name parts plus accompanying slash

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

                try:

                    hg.repository(ui, path)

                    directory = False

                except (IOError, error.RepoError):

                    pass

        parts = [

            req.apppath.strip(b'/'),

            subdir.strip(b'/'),

            name.strip(b'/'),

        ]

        url = b'/' + b'/'.join(p for p in parts if p) + b'/'

        # show either a directory entry or a repository

        if directory:

            # get the directory's time information

            try:

                d = (get_mtime(path), dateutil.makedate()[1])

            except OSError:

                continue

            # add '/' to the name to make it obvious that

            # the entry is a directory, not a regular repository

            row = {

                b'contact': b"",

                b'contact_sort': b"",

                b'name': name + b'/',

                b'name_sort': name,

                b'url': url,

                b'description': b"",

                b'description_sort': b"",

                b'lastchange': d,

                b'lastchange_sort': d[1] - d[0],

                b'archives': templateutil.mappinglist([]),

                b'isdirectory': True,

                b'labels': templateutil.hybridlist([], name=b'label'),

            }

            seendirs.add(name)

            yield row

            continue

        u = ui.copy()

        if rcutil.use_repo_hgrc():

            try:

                u.readconfig(os.path.join(path, b'.hg', b'hgrc'))

            except Exception as e:

                u.warn(_(b'error reading %s/.hg/hgrc: %s\n') % (path, e))

                continue

        def get(section, name, default=uimod._unset):

            return u.config(section, name, default, untrusted=True)

        if u.configbool(b"web", b"hidden", untrusted=True):

            continue

        if not readallowed(u, req):

            continue

        # update time with local timezone

        try:

            r = hg.repository(ui, path)

        except IOError:

            u.warn(_(b'error accessing repository at %s\n') % path)

            continue

        except error.RepoError:

            u.warn(_(b'error accessing repository at %s\n') % path)

            continue

        try:

            d = (get_mtime(r.spath), dateutil.makedate()[1])

        except OSError:

            continue

        contact = get_contact(get)

        description = get(b"web", b"description")

        seenrepos.add(name)

        name = get(b"web", b"name", name)

        labels = u.configlist(b'web', b'labels', untrusted=True)

        row = {

            b'contact': contact or b"unknown",

            b'contact_sort': contact.upper() or b"unknown",

            b'name': name,

            b'name_sort': name,

            b'url': url,

            b'description': description or b"unknown",

            b'description_sort': description.upper() or b"unknown",

            b'lastchange': d,

            b'lastchange_sort': d[1] - d[0],

            b'archives': webutil.archivelist(u, b"tip", url),

            b'isdirectory': None,

            b'labels': templateutil.hybridlist(labels, name=b'label'),

        }

        yield row

def _indexentriesgen(

    context, ui, repos, req, stripecount, sortcolumn, descending, subdir

):

    rows = rawindexentries(ui, repos, req, subdir=subdir)

    sortdefault = None, False

    if sortcolumn and sortdefault != (sortcolumn, descending):

        sortkey = b'%s_sort' % sortcolumn

        rows = sorted(rows, key=lambda x: x[sortkey], reverse=descending)

    for row, parity in zip(rows, paritygen(stripecount)):

        row[b'parity'] = parity

        yield row

def indexentries(

    ui, repos, req, stripecount, sortcolumn=b'', descending=False, subdir=b''

):

    args = (ui, repos, req, stripecount, sortcolumn, descending, subdir)

    return templateutil.mappinggenerator(_indexentriesgen, args=args)

class hgwebdir:

    """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()

        self.requests_count = 0

        if not baseui:

            # set up environment for new ui

            extensions.loadall(self.ui)

            extensions.populateui(self.ui)

    def refresh(self):

        if self.ui:

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

        else:

            item = configitems.coreitems[b'web'][b'refreshinterval']

            refreshinterval = item.default

        # 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(b'ui', b'report_untrusted', b'off', b'hgwebdir')

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

            # displaying bundling progress bar while serving feels wrong and may

            # break some wsgi implementations.

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

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

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

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

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

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

            paths = []

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

                for path in u.configlist(b'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()

        extensions.populateui(u)

        repos = findrepos(paths)

        for prefix, root in u.configitems(b'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(b'/'), repo))

        self.repos = repos

        self.ui = u

        self.gc_full_collect_rate = self.ui.configint(

            b'experimental', b'web.full-garbage-collection-rate'

        )

        self.gc_full_collections_done = 0

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

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

        self.templatepath = self.ui.config(

            b'web', b'templates', untrusted=False

        )

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

        if self.stripecount:

            self.stripecount = int(self.stripecount)

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

        if prefix.startswith(b'/'):

            prefix = prefix[1:]

        if prefix.endswith(b'/'):

            prefix = prefix[:-1]

        self.prefix = prefix

        self.lastrefresh = time.time()

    def run(self):

        if not encoding.environ.get(b'GATEWAY_INTERFACE', b'').startswith(

            b"CGI/1."

        ):

            raise RuntimeError(