summary refs log tree commit diff
path: root/synapse/push/push_rule_evaluator.py
blob: 172c27c13737cb309d7d62d9ea26817617a3af7a (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
# -*- coding: utf-8 -*-
# Copyright 2015, 2016 OpenMarket Ltd
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import logging
import re

from synapse.types import UserID
from synapse.util.caches import CACHE_SIZE_FACTOR, register_cache
from synapse.util.caches.lrucache import LruCache

logger = logging.getLogger(__name__)


GLOB_REGEX = re.compile(r'\\\[(\\\!|)(.*)\\\]')
IS_GLOB = re.compile(r'[\?\*\[\]]')
INEQUALITY_EXPR = re.compile("^([=<>]*)([0-9]*)$")


def _room_member_count(ev, condition, room_member_count):
    if 'is' not in condition:
        return False
    m = INEQUALITY_EXPR.match(condition['is'])
    if not m:
        return False
    ineq = m.group(1)
    rhs = m.group(2)
    if not rhs.isdigit():
        return False
    rhs = int(rhs)

    if ineq == '' or ineq == '==':
        return room_member_count == rhs
    elif ineq == '<':
        return room_member_count < rhs
    elif ineq == '>':
        return room_member_count > rhs
    elif ineq == '>=':
        return room_member_count >= rhs
    elif ineq == '<=':
        return room_member_count <= rhs
    else:
        return False


def tweaks_for_actions(actions):
    tweaks = {}
    for a in actions:
        if not isinstance(a, dict):
            continue
        if 'set_tweak' in a and 'value' in a:
            tweaks[a['set_tweak']] = a['value']
    return tweaks


class PushRuleEvaluatorForEvent(object):
    def __init__(self, event, room_member_count):
        self._event = event
        self._room_member_count = room_member_count

        # Maps strings of e.g. 'content.body' -> event["content"]["body"]
        self._value_cache = _flatten_dict(event)

    def matches(self, condition, user_id, display_name):
        if condition['kind'] == 'event_match':
            return self._event_match(condition, user_id)
        elif condition['kind'] == 'contains_display_name':
            return self._contains_display_name(display_name)
        elif condition['kind'] == 'room_member_count':
            return _room_member_count(
                self._event, condition, self._room_member_count
            )
        else:
            return True

    def _event_match(self, condition, user_id):
        pattern = condition.get('pattern', None)

        if not pattern:
            pattern_type = condition.get('pattern_type', None)
            if pattern_type == "user_id":
                pattern = user_id
            elif pattern_type == "user_localpart":
                pattern = UserID.from_string(user_id).localpart

        if not pattern:
            logger.warn("event_match condition with no pattern")
            return False

        # XXX: optimisation: cache our pattern regexps
        if condition['key'] == 'content.body':
            body = self._event["content"].get("body", None)
            if not body:
                return False

            return _glob_matches(pattern, body, word_boundary=True)
        else:
            haystack = self._get_value(condition['key'])
            if haystack is None:
                return False

            return _glob_matches(pattern, haystack)

    def _contains_display_name(self, display_name):
        if not display_name:
            return False

        body = self._event["content"].get("body", None)
        if not body:
            return False

        return _glob_matches(display_name, body, word_boundary=True)

    def _get_value(self, dotted_key):
        return self._value_cache.get(dotted_key, None)


# Caches (glob, word_boundary) -> regex for push. See _glob_matches
regex_cache = LruCache(50000 * CACHE_SIZE_FACTOR)
register_cache("regex_push_cache", regex_cache)


def _glob_matches(glob, value, word_boundary=False):
    """Tests if value matches glob.

    Args:
        glob (string)
        value (string): String to test against glob.
        word_boundary (bool): Whether to match against word boundaries or entire
            string. Defaults to False.

    Returns:
        bool
    """

    try:
        r = regex_cache.get((glob, word_boundary), None)
        if not r:
            r = _glob_to_re(glob, word_boundary)
            regex_cache[(glob, word_boundary)] = r
        return r.search(value)
    except re.error:
        logger.warn("Failed to parse glob to regex: %r", glob)
        return False


def _glob_to_re(glob, word_boundary):
    """Generates regex for a given glob.

    Args:
        glob (string)
        word_boundary (bool): Whether to match against word boundaries or entire
            string. Defaults to False.

    Returns:
        regex object
    """
    if IS_GLOB.search(glob):
        r = re.escape(glob)

        r = r.replace(r'\*', '.*?')
        r = r.replace(r'\?', '.')

        # handle [abc], [a-z] and [!a-z] style ranges.
        r = GLOB_REGEX.sub(
            lambda x: (
                '[%s%s]' % (
                    x.group(1) and '^' or '',
                    x.group(2).replace(r'\\\-', '-')
                )
            ),
            r,
        )
        if word_boundary:
            r = r"\b%s\b" % (r,)

            return re.compile(r, flags=re.IGNORECASE)
        else:
            r = "^" + r + "$"

            return re.compile(r, flags=re.IGNORECASE)
    elif word_boundary:
        r = re.escape(glob)
        r = r"\b%s\b" % (r,)

        return re.compile(r, flags=re.IGNORECASE)
    else:
        r = "^" + re.escape(glob) + "$"
        return re.compile(r, flags=re.IGNORECASE)


def _flatten_dict(d, prefix=[], result=None):
    if result is None:
        result = {}
    for key, value in d.items():
        if isinstance(value, basestring):
            result[".".join(prefix + [key])] = value.lower()
        elif hasattr(value, "items"):
            _flatten_dict(value, prefix=(prefix + [key]), result=result)

    return result