Ejemplo n.º 1
0
 def testReading(self):
     reader = log_reader.ApacheReader(file('access.log'))
     lines = [f for f in reader]
     reader = None
     reader = log_reader.ApacheReader(file('access.log'))
     for fields in reader:
         pass
Ejemplo n.º 2
0
 def testDatetime(self):
     input = ("[03/Mar/2005:06:47:18 -0500]\n\n",
              "[03/Jan/2005:00:41:10 -0800]")
     reader = log_reader.ApacheReader(iter(input), '%t')
     lines = [f for f in reader]
     self.assertEquals(lines[0]['time'],
                       datetime.datetime(2005, 3, 3, 6, 47, 18))
     self.assertEquals(lines[1]['time'],
                       datetime.datetime(2005, 1, 3, 0, 41, 10))
Ejemplo n.º 3
0
 def testCustomFormat(self):
     input = ('"test" "test2"\n', '"another test" "more spaces"')
     reader = log_reader.ApacheReader(iter(input), '"%{Foo}i" "%{Bar}i"')
     lines = [f for f in reader]
     self.assertEquals(lines[0], {'Foo': 'test', 'Bar': 'test2'})
     self.assertEquals(lines[1], {
         'Foo': 'another test',
         'Bar': 'more spaces'
     })
Ejemplo n.º 4
0
 def testRequest(self):
     input = ('"GET /path/to/page.html HTTP/1.0"\n\n',
              '"POST /foo/bar/?betz=10 HTTP/1.0"')
     reader = log_reader.ApacheReader(iter(input), '"%r"')
     lines = [f for f in reader]
     self.assertEquals(lines[0]['method'], 'GET')
     self.assertEquals(lines[0]['protocol'], 'HTTP/1.0')
     self.assertEquals(lines[0]['path'], '/path/to/page.html')
     self.assertEquals(lines[1]['method'], 'POST')
     self.assertEquals(lines[1]['protocol'], 'HTTP/1.0')
     self.assertEquals(lines[1]['path'], '/foo/bar/?betz=10')
Ejemplo n.º 5
0
 def testRefererUser(self):
     input = ('"test" username\n\n', '"test test" foobar')
     reader = log_reader.ApacheReader(iter(input), '"%{Referer}i" %u')
     lines = [f for f in reader]
     self.assertEquals(lines[0], {
         'referer': 'test',
         'username': '******'
     })
     self.assertEquals(lines[1], {
         'referer': 'test test',
         'username': '******'
     })
Ejemplo n.º 6
0
 def testOptionalFields(self):
     input = ('foo\n', 'foo2 bar\n', 'foo3 bar2 baz\n', 'foo3 - baz2')
     reader = log_reader.ApacheReader(iter(input),
                                      '%{Foo}i%? %{Bar}i %{Baz}i')
     lines = [f for f in reader]
     self.assertEquals(lines[0], {'Foo': 'foo'})
     self.assertEquals(lines[1], {'Foo': 'foo2', 'Bar': 'bar'})
     self.assertEquals(lines[2], {
         'Foo': 'foo3',
         'Bar': 'bar2',
         'Baz': 'baz'
     })
     self.assertEquals(lines[3], {'Foo': 'foo3', 'Bar': '-', 'Baz': 'baz2'})
Ejemplo n.º 7
0
 def testDoubleQuotes(self):
     input = ('"noquote" "escape test\\" test"\n',
              '"test" "double ""quote test"')
     reader = log_reader.ApacheReader(iter(input), '"%u" "%{User-Agent}i"')
     lines = [f for f in reader]
     self.assertEquals(lines[0], {
         'username': '******',
         'user-agent': 'escape test" test'
     })
     self.assertEquals(lines[1], {
         'username': '******',
         'user-agent': 'double "quote test'
     })
Ejemplo n.º 8
0
    def testIps(self):
        input = ("0.0.0.0\n", "1.2.3.4, 5.6.7.8\n",
                 'unknown, 255.255.255.255\n', '255.0.255.0, unknown\n',
                 '100.100.100.100\n', '200.169.54.33, unknown, 200.169.63.242')
        reader = log_reader.ApacheReader(iter(input), '%h')

        lines = [f for f in reader]
        self.assertEquals(lines[0]['ips'], ['0.0.0.0'])
        self.assertEquals(lines[1]['ips'], ['1.2.3.4', '5.6.7.8'])
        self.assertEquals(lines[2]['ips'], ['unknown', '255.255.255.255'])
        self.assertEquals(lines[3]['ips'], ['255.0.255.0', 'unknown'])
        self.assertEquals(lines[4]['ips'], ['100.100.100.100'])
        self.assertEquals(lines[5]['ips'],
                          ['200.169.54.33', 'unknown', '200.169.63.242'])
Ejemplo n.º 9
0
def read_log(filename,
             path_guesser,
             date_hasher=daily_date_hasher,
             max_reads=None):
    assert callable(path_guesser)
    lr = log_reader.ApacheReader(filename)
    ret = {}
    keys = []
    for num, i in enumerate(lr):
        if max_reads and num > max_reads:
            return keys, ret
        if 'path' in i:
            if path_guesser(i['path']):
                hash = date_hasher(i['time'])
                if hash in ret:
                    ret[hash] += 1
                else:
                    ret[hash] = 1
                    keys.append(hash)
    return keys, ret
Ejemplo n.º 10
0
 def testNginxUpstreamCommaSpaceSeparation(self):
     input = ('success1 success2\n', 'fail1, success1 success2\n',
              'success1 fail2, success2\n',
              'fail1, success1 fail2, success2')
     reader = log_reader.ApacheReader(iter(input),
                                      '%{upstream_Foo}i %{upstream_Bar}i')
     lines = [f for f in reader]
     self.assertEquals(lines[0], {
         'upstream_Foo': 'success1',
         'upstream_Bar': 'success2'
     })
     self.assertEquals(lines[1], {
         'upstream_Foo': 'fail1, success1',
         'upstream_Bar': 'success2'
     })
     self.assertEquals(lines[2], {
         'upstream_Foo': 'success1',
         'upstream_Bar': 'fail2, success2'
     })
     self.assertEquals(lines[3], {
         'upstream_Foo': 'fail1, success1',
         'upstream_Bar': 'fail2, success2'
     })
Ejemplo n.º 11
0
import gc
import sys
try:
  import log_reader
except ImportError:
  print "unable to find log_reader module"
  sys.exit(1)


line = ('"1.2.3.4 - - [03/Jul/2007:18:48:56 +1000] "GET /example'
        ' HTTP/1.1" 200 1234 "http://www.example.com/referrer"'
        ' "user-agent/1.0"')

for i in xrange(1000000):
  #parse_line = log_reader.ApacheReader.parse_line
  #parse_line(line)
  #continue

  reader = log_reader.ApacheReader('access.log')
  for fields in reader:
    pass
  reader = None
  gc.collect()
  reader = log_reader.ApacheReader(file('access.log'))
  for fields in reader:
    pass
  sys.stdout.write('.');
  sys.stdout.flush()
  reader = None
  gc.collect()
Ejemplo n.º 12
0
 def testSizeAndReferer(self):
     input = ('1234 "test"\n\n', '22345 "test test"')
     reader = log_reader.ApacheReader(iter(input), '%b "%{Referer}i"')
     lines = [f for f in reader]
     self.assertEquals(lines[0], {'referer': 'test', 'size': 1234})
     self.assertEquals(lines[1], {'referer': 'test test', 'size': 22345})
Ejemplo n.º 13
0
 def testEscaping(self):
     input = ('"test test test"\n', '"foo"')
     reader = log_reader.ApacheReader(iter(input), '"%u"')
     lines = [f for f in reader]
     self.assertEquals(lines[0]['username'], 'test test test')
     self.assertEquals(lines[1]['username'], 'foo')
Ejemplo n.º 14
0
 def testUsername(self):
     input = ["test\n", "foo"]
     reader = log_reader.ApacheReader(iter(input), '%u')
     lines = [f for f in reader]
     self.assertEquals(lines[0]['username'], 'test')
     self.assertEquals(lines[1]['username'], 'foo')
Ejemplo n.º 15
0
 def testCurline(self):
     input = ('"test" username\n\n', '"test test" foobar')
     reader = log_reader.ApacheReader(iter(input), '"%{Referer}i" %u')
     lines = [reader.curline for f in reader]
     self.assertEquals(lines[0], input[0])
     self.assertEquals(lines[1], input[1])