aboutsummaryrefslogtreecommitdiffstats
path: root/libmproxy/utils.py
blob: 871beb3556c8a0bae68bdd213fa4d3aa350d9f53 (plain)
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
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
# Copyright (C) 2010  Aldo Cortesi
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
import os, datetime, urlparse, string, urllib, re
import time, functools, cgi
import json
from netlib import http

def timestamp():
    """
        Returns a serializable UTC timestamp.
    """
    return time.time()


def format_timestamp(s):
    s = time.localtime(s)
    d = datetime.datetime.fromtimestamp(time.mktime(s))
    return d.strftime("%Y-%m-%d %H:%M:%S")


def isBin(s):
    """
        Does this string have any non-ASCII characters?
    """
    for i in s:
        i = ord(i)
        if i < 9:
            return True
        elif i > 13 and i < 32:
            return True
        elif i > 126:
            return True
    return False


def isXML(s):
    for i in s:
        if i in "\n \t":
            continue
        elif i == "<":
            return True
        else:
            return False


def cleanBin(s, fixspacing=False):
    """
        Cleans binary data to make it safe to display. If fixspacing is True,
        tabs, newlines and so forth will be maintained, if not, they will be
        replaced with a placeholder.
    """
    parts = []
    for i in s:
        o = ord(i)
        if (o > 31 and o < 127):
            parts.append(i)
        elif i in "\n\r\t" and not fixspacing:
            parts.append(i)
        else:
            parts.append(".")
    return "".join(parts)


def pretty_json(s):
    try:
        p = json.loads(s)
    except ValueError:
        return None
    return json.dumps(p, sort_keys=True, indent=4).split("\n")


def urldecode(s):
    """
        Takes a urlencoded string and returns a list of (key, value) tuples.
    """
    return cgi.parse_qsl(s)


def urlencode(s):
    """
        Takes a list of (key, value) tuples and returns a urlencoded string.
    """
    s = [tuple(i) for i in s]
    return urllib.urlencode(s, False)


def hexdump(s):
    """
        Returns a set of typles:
            (offset, hex, str)
    """
    parts = []
    for i in range(0, len(s), 16):
        o = "%.10x"%i
        part = s[i:i+16]
        x = " ".join("%.2x"%ord(i) for i in part)
        if len(part) < 16:
            x += " "
            x += " ".join("  " for i in range(16 - len(part)))
        parts.append(
            (o, x, cleanBin(part, True))
        )
    return parts


def del_all(dict, keys):
    for key in keys:
        if key in dict:
            del dict[key]


def pretty_size(size):
    suffixes = [
        ("B",   2**10),
        ("kB",   2**20),
        ("M",   2**30),
    ]
    for suf, lim in suffixes:
        if size >= lim:
            continue
        else:
            x = round(size/float(lim/2**10), 2)
            if x == int(x):
                x = int(x)
            return str(x) + suf


class Data:
    def __init__(self, name):
        m = __import__(name)
        dirname, _ = os.path.split(m.__file__)
        self.dirname = os.path.abspath(dirname)

    def path(self, path):
        """
            Returns a path to the package data housed at 'path' under this
            module.Path can be a path to a file, or to a directory.

            This function will raise ValueError if the path does not exist.
        """
        fullpath = os.path.join(self.dirname, path)
        if not os.path.exists(fullpath):
            raise ValueError, "dataPath: %s does not exist."%fullpath
        return fullpath
pkg_data = Data(__name__)


class LRUCache:
    """
        A decorator that implements a self-expiring LRU cache for class
        methods (not functions!).

        Cache data is tracked as attributes on the object itself. There is
        therefore a separate cache for each object instance.
    """
    def __init__(self, size=100):
        self.size = size

    def __call__(self, f):
        cacheName = "_cached_%s"%f.__name__
        cacheListName = "_cachelist_%s"%f.__name__
        size = self.size

        @functools.wraps(f)
        def wrap(self, *args):
            if not hasattr(self, cacheName):
                setattr(self, cacheName, {})
                setattr(self, cacheListName, [])
            cache = getattr(self, cacheName)
            cacheList = getattr(self, cacheListName)
            if cache.has_key(args):
                cacheList.remove(args)
                cacheList.insert(0, args)
                return cache[args]
            else:
                ret = f(self, *args)
                cacheList.insert(0, args)
                cache[args] = ret
                if len(cacheList) > size:
                    d = cacheList.pop()
                    cache.pop(d)
                return ret
        return wrap


def parse_proxy_spec(url):
    p = http.parse_url(url)
    if not p or not p[1]:
        return None
    return p[:3]


def parse_content_type(c):
    """
        A simple parser for content-type values. Returns a (type, subtype,
        parameters) tuple, where type and subtype are strings, and parameters
        is a dict. If the string could not be parsed, return None.

        E.g. the following string:

            text/html; charset=UTF-8

        Returns:

            ("text", "html", {"charset": "UTF-8"})
    """
    parts = c.split(";", 1)
    ts = parts[0].split("/", 1)
    if len(ts) != 2:
        return None
    d = {}
    if len(parts) == 2:
        for i in parts[1].split(";"):
            clause = i.split("=", 1)
            if len(clause) == 2:
                d[clause[0].strip()] = clause[1].strip()
    return ts[0].lower(), ts[1].lower(), d


def hostport(scheme, host, port):
    """
        Returns the host component, with a port specifcation if needed.
    """
    if (port, scheme) in [(80, "http"), (443, "https")]:
        return host
    else:
        return "%s:%s"%(host, port)


def unparse_url(scheme, host, port, path=""):
    """
        Returns a URL string, constructed from the specified compnents.
    """
    return "%s://%s%s"%(scheme, hostport(scheme, host, port), path)


def clean_hanging_newline(t):
    """
        Many editors will silently add a newline to the final line of a
        document (I'm looking at you, Vim). This function fixes this common
        problem at the risk of removing a hanging newline in the rare cases
        where the user actually intends it.
    """
    if t[-1] == "\n":
        return t[:-1]
    return t


def parse_size(s):
    """
        Parses a size specification. Valid specifications are:

            123: bytes
            123k: kilobytes
            123m: megabytes
            123g: gigabytes
    """
    if not s:
        return None
    mult = None
    if s[-1].lower() == "k":
        mult = 1024**1
    elif s[-1].lower() == "m":
        mult = 1024**2
    elif s[-1].lower() == "g":
        mult = 1024**3

    if mult:
        s = s[:-1]
    else:
        mult = 1
    try:
        return int(s) * mult
    except ValueError:
        raise ValueError("Invalid size specification: %s"%s)


def safe_subn(pattern, repl, target, *args, **kwargs):
    """
        There are Unicode conversion problems with re.subn. We try to smooth
        that over by casting the pattern and replacement to strings. We really
        need a better solution that is aware of the actual content ecoding.
    """
    return re.subn(str(pattern), str(repl), target, *args, **kwargs)