Source Code for Module yum.mdparser

  1   
  2  # This program is free software; you can redistribute it and/or modify 
  3  # it under the terms of the GNU General Public License as published by 
  4  # the Free Software Foundation; either version 2 of the License, or 
  5  # (at your option) any later version. 
  6  # 
  7  # This program is distributed in the hope that it will be useful, 
  8  # but WITHOUT ANY WARRANTY; without even the implied warranty of 
  9  # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the 
 10  # GNU Library General Public License for more details. 
 11  # 
 12  # You should have received a copy of the GNU General Public License 
 13  # along with this program; if not, write to the Free Software 
 14  # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. 
 15  # Copyright 2005 Duke University  
 16   
 17  import gzip 
 18  try: 
 19      from xml.etree import cElementTree 
 20  except ImportError: 
 21      import cElementTree 
 22  iterparse = cElementTree.iterparse 
 23   
 24  from cStringIO import StringIO 
 25  import warnings 
 26   
 27  import Errors 
 28   
 29  #TODO: document everything here 
 30   
 31 -class MDParser: 
 32   
 33 -    def __init__(self, filename): 
 34   
 35          # Set up mapping of meta types to handler classes  
 36          handlers = { 
 37              '{http://linux.duke.edu/metadata/common}metadata': PrimaryEntry, 
 38              '{http://linux.duke.edu/metadata/filelists}filelists': FilelistsEntry, 
 39              '{http://linux.duke.edu/metadata/other}otherdata': OtherEntry, 
 40          } 
 41               
 42          self.total = None 
 43          self.count = 0 
 44          self._handlercls = None 
 45   
 46          # Read in type, set package node handler and get total number of 
 47          # packages 
 48          if filename[-3:] == '.gz': fh = gzip.open(filename, 'r') 
 49          else: fh = open(filename, 'r') 
 50          parser = iterparse(fh, events=('start', 'end')) 
 51          self.reader = parser.__iter__() 
 52          event, elem = self.reader.next() 
 53          self._handlercls = handlers.get(elem.tag, None) 
 54          if not self._handlercls: 
 55              raise ValueError('Unknown repodata type "%s" in %s' % ( 
 56                  elem.tag, filename)) 
 57          # Get the total number of packages 
 58          self.total = int(elem.get('packages', 0)) 
 59   
 60 -    def __iter__(self): 
 61          return self 
 62   
 63 -    def next(self): 
 64          for event, elem in self.reader: 
 65              if event == 'end' and elem.tag[-7:] == 'package': 
 66                  self.count += 1 
 67                  return self._handlercls(elem) 
 68          raise StopIteration 
 69   
 70   
 71 -class BaseEntry: 
 72 -    def __init__(self, elem): 
 73          self._p = {}  
 74   
 75 -    def __getitem__(self, k): 
 76          return self._p[k] 
 77   
 78 -    def keys(self): 
 79          return self._p.keys() 
 80   
 81 -    def values(self): 
 82          return self._p.values() 
 83   
 84 -    def has_key(self, k): 
 85          warnings.warn('has_key() will go away in a future version of Yum.\n', 
 86                        Errors.YumFutureDeprecationWarning, stacklevel=2) 
 87          return k in self._p 
 88   
 89 -    def __iter__(self): 
 90          return iter(self._p) 
 91   
 92 -    def __str__(self): 
 93          out = StringIO() 
 94          keys = self.keys() 
 95          keys.sort() 
 96          for k in keys: 
 97              line = u'%s=%s\n' % (k, self[k]) 
 98              out.write(line.encode('utf8')) 
 99          return out.getvalue() 
100   
101 -    def _bn(self, qn): 
102          if qn.find('}') == -1: return qn  
103          return qn.split('}')[1] 
104           
105 -    def _prefixprops(self, elem, prefix): 
106          ret = {} 
107          for key in elem.attrib: 
108              ret[prefix + '_' + self._bn(key)] = elem.attrib[key] 
109          return ret 
110   
111 -class PrimaryEntry(BaseEntry): 
112 -    def __init__(self, elem): 
113          BaseEntry.__init__(self, elem) 
114          # Avoid excess typing :) 
115          p = self._p 
116   
117          self.prco = {} 
118          self.files = {} 
119   
120          for child in elem: 
121              name = self._bn(child.tag) 
122              if name in ('name', 'arch', 'summary', 'description', 'url',  
123                      'packager'):  
124                  p[name] = child.text 
125   
126              elif name == 'version':  
127                  p.update(child.attrib) 
128   
129              elif name in ('time', 'size'): 
130                  p.update(self._prefixprops(child, name)) 
131   
132              elif name in ('checksum', 'location'):  
133                  p.update(self._prefixprops(child, name)) 
134                  p[name + '_value'] = child.text 
135                  if name == 'location' and not p.has_key("location_base"): 
136                      p["location_base"] = None 
137               
138              elif name == 'format':  
139                  self.setFormat(child) 
140   
141          p['pkgId'] = p['checksum_value'] 
142          elem.clear() 
143   
144 -    def setFormat(self, elem): 
145   
146          # Avoid excessive typing :) 
147          p = self._p 
148   
149          for child in elem: 
150              name = self._bn(child.tag) 
151   
152              if name in ('license', 'vendor', 'group', 'buildhost', 
153                          'sourcerpm'): 
154                  p[name] = child.text 
155   
156              elif name in ('provides', 'requires', 'conflicts',  
157                            'obsoletes'): 
158                  self.prco[name] = self.getPrco(child) 
159   
160              elif name == 'header-range': 
161                  p.update(self._prefixprops(child, 'rpm_header')) 
162   
163              elif name == 'file': 
164                  file_type = child.get('type', 'file') 
165                  path = child.text 
166                  self.files[path] = file_type 
167   
168 -    def getPrco(self, elem): 
169          members = [] 
170          for child in elem: 
171              members.append(child.attrib) 
172          return members 
173           
174           
175 -class FilelistsEntry(BaseEntry): 
176 -    def __init__(self, elem): 
177          BaseEntry.__init__(self, elem) 
178          self._p['pkgId'] = elem.attrib['pkgid'] 
179          self.files = {} 
180          for child in elem: 
181              name = self._bn(child.tag) 
182              if name == 'file': 
183                  file_type = child.get('type', 'file') 
184                  path = child.text 
185                  self.files[path] = file_type 
186          elem.clear() 
187                   
188 -class OtherEntry(BaseEntry): 
189 -    def __init__(self, elem): 
190          BaseEntry.__init__(self, elem) 
191          self._p['pkgId'] = elem.attrib['pkgid'] 
192          self._p['changelog'] = [] 
193          for child in elem: 
194              name = self._bn(child.tag) 
195              if name == 'changelog': 
196                  entry = child.attrib 
197                  entry['value'] = child.text 
198                  self._p['changelog'].append(entry) 
199          elem.clear() 
200   
201   
202   
203 -def test(): 
204      import sys 
205   
206      parser = MDParser(sys.argv[1]) 
207   
208      for pkg in parser: 
209          print '-' * 40 
210          print pkg 
211   
212      print 'read: %s packages (%s suggested)' % (parser.count, parser.total) 
213   
214  if __name__ == '__main__': 
215      test() 
216