Source Code for Module madrona.common.uaparser.parser

  1  #!/usr/bin/python2.4 
  2  # 
  3  # Copyright 2009 Google Inc. 
  4  # 
  5  # Licensed under the Apache License, Version 2.0 (the "License"); 
  6  # you may not use this file except in compliance with the License. 
  7  # You may obtain a copy of the License at 
  8  # 
  9  #     http://www.apache.org/licenses/LICENSE-2.0 
 10  # 
 11  # Unless required by applicable law or agreed to in writing, software 
 12  # distributed under the License is distributed on an "AS IS" BASIS, 
 13  # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 
 14  # See the License for the specific language governing permissions and 
 15  # limitations under the License. 
 16   
 17  """Parser.""" 
 18   
 19  import re 
 20  import regexes 
 21   
 22 -class UserAgent(object): 
 23 -    def __init__(self, user_agent_string, js_user_agent_string=None): 
 24          self.user_agent_string = user_agent_string 
 25          self.js_user_agent_string = js_user_agent_string 
 26          for ua_parser in regexes.USER_AGENT_PARSERS: 
 27              family, v1, v2, v3 = ua_parser.Parse(user_agent_string) 
 28              if family: 
 29                  break 
 30   
 31          if js_user_agent_string and user_agent_string.find('chromeframe') > -1: 
 32              family = 'Chrome Frame (%s %s)' % (family, v1) 
 33              cf_family, v1, v2, v3 = cls.parse(js_user_agent_string) 
 34   
 35          self.family = family or 'Other' 
 36          self.v1 = v1 
 37          self.v2 = v2 
 38          self.v3 = v3 
 39   
 40 -    def pretty(self): 
 41          return UserAgent.pretty_print(self.family, self.v1, self.v2, self.v3) 
 42   
 43      @staticmethod 
 44 -    def parse_pretty(pretty_string): 
 45          """Parse a user agent pretty (e.g. 'Chrome 4.0.203') to parts. 
 46   
 47          Args: 
 48              pretty_string: a user agent pretty string (e.g. 'Chrome 4.0.203') 
 49          Returns: 
 50              [family, v1, v2, v3] e.g. ['Chrome', '4', '0', '203'] 
 51          """ 
 52          v1, v2, v3 = None, None, None 
 53          family, sep, version_str = pretty_string.rpartition(' ') 
 54          if not family: 
 55              family = version_str 
 56          else: 
 57              version_bits = version_str.split('.') 
 58              v1 = version_bits.pop(0) 
 59              if not v1.isdigit(): 
 60                  family = pretty_string 
 61                  v1 = None 
 62              elif version_bits: 
 63                  v2 = version_bits.pop(0) 
 64                  if not v2.isdigit(): 
 65                      nondigit_index = min(i for i, c in enumerate(v2) if not c.isdigit()) 
 66                      v2, v3 = v2[:nondigit_index], v2[nondigit_index:] 
 67                  elif version_bits: 
 68                      v3 = version_bits.pop(0) 
 69          return family, v1, v2, v3 
 70   
 71      @staticmethod 
 72 -    def pretty_print(family, v1=None, v2=None, v3=None): 
 73          """Pretty browser string.""" 
 74          if v3: 
 75              if v3[0].isdigit(): 
 76                  return '%s %s.%s.%s' % (family, v1, v2, v3) 
 77              else: 
 78                  return '%s %s.%s%s' % (family, v1, v2, v3) 
 79          elif v2: 
 80              return '%s %s.%s' % (family, v1, v2) 
 81          elif v1: 
 82              return '%s %s' % (family, v1) 
 83          return family 
 84   
 85 -class UserAgentParser(object): 
 86 -    def __init__(self, pattern, family_replacement=None, v1_replacement=None): 
 87          """Initialize UserAgentParser. 
 88   
 89          Args: 
 90              pattern: a regular expression string 
 91              family_replacement: a string to override the matched family (optional) 
 92              v1_replacement: a string to override the matched v1 (optional) 
 93          """ 
 94          self.pattern = pattern 
 95          self.user_agent_re = re.compile(self.pattern) 
 96          self.family_replacement = family_replacement 
 97          self.v1_replacement = v1_replacement 
 98   
 99 -    def MatchSpans(self, user_agent_string): 
100          match_spans = [] 
101          match = self.user_agent_re.search(user_agent_string) 
102          if match: 
103              match_spans = [match.span(group_index) 
104                                           for group_index in range(1, match.lastindex + 1)] 
105          return match_spans 
106   
107 -    def Parse(self, user_agent_string): 
108          family, v1, v2, v3 = None, None, None, None 
109          match = self.user_agent_re.search(user_agent_string) 
110          if match: 
111              if self.family_replacement: 
112                  if re.search(r'\$1', self.family_replacement): 
113                      family = re.sub(r'\$1', match.group(1), self.family_replacement) 
114                  else: 
115                      family = self.family_replacement 
116              else: 
117                  family = match.group(1) 
118   
119              if self.v1_replacement: 
120                  v1 = self.v1_replacement 
121              elif match.lastindex >= 2: 
122                  v1 = match.group(2) 
123              if match.lastindex >= 3: 
124                  v2 = match.group(3) 
125                  if match.lastindex >= 4: 
126                      v3 = match.group(4) 
127          return family, v1, v2, v3 
128