Source Code for Module yum.repoMDObject

  1  #!/usr/bin/python -tt 
  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 2006 Duke University 
 16   
 17  try: 
 18      from xml.etree import cElementTree 
 19  except ImportError: 
 20      import cElementTree 
 21  iterparse = cElementTree.iterparse 
 22  from Errors import RepoMDError 
 23   
 24  import sys 
 25  import types 
 26  from misc import AutoFileChecksums 
 27   
 28 -def ns_cleanup(qn): 
 29      if qn.find('}') == -1: return qn  
 30      return qn.split('}')[1] 
 31   
 32 -class RepoData: 
 33      """represents anything beneath a <data> tag""" 
 34 -    def __init__(self, elem): 
 35          self.type = elem.attrib.get('type') 
 36          self.location = (None, None) 
 37          self.checksum = (None,None) # type,value 
 38          self.openchecksum = (None,None) # type,value 
 39          self.timestamp = None 
 40          self.dbversion = None 
 41          self.size      = None 
 42          self.opensize  = None 
 43       
 44          self.parse(elem) 
 45   
 46 -    def parse(self, elem): 
 47           
 48          for child in elem: 
 49              child_name = ns_cleanup(child.tag) 
 50              if child_name == 'location': 
 51                  relative = child.attrib.get('href') 
 52                  base = child.attrib.get('base') 
 53                  self.location = (base, relative) 
 54               
 55              elif child_name == 'checksum': 
 56                  csum_value = child.text 
 57                  csum_type = child.attrib.get('type') 
 58                  self.checksum = (csum_type,csum_value) 
 59   
 60              elif child_name == 'open-checksum': 
 61                  csum_value = child.text 
 62                  csum_type = child.attrib.get('type') 
 63                  self.openchecksum = (csum_type, csum_value) 
 64               
 65              elif child_name == 'timestamp': 
 66                  self.timestamp = child.text 
 67              elif child_name == 'database_version': 
 68                  self.dbversion = child.text 
 69              elif child_name == 'size': 
 70                  self.size = child.text 
 71              elif child_name == 'open-size': 
 72                  self.opensize = child.text 
 73           
 74 -class RepoMD: 
 75      """represents the repomd xml file""" 
 76       
 77 -    def __init__(self, repoid, srcfile): 
 78          """takes a repoid and a filename for the repomd.xml""" 
 79           
 80          self.timestamp = 0 
 81          self.repoid    = repoid 
 82          self.repoData  = {} 
 83          self.checksums = {} 
 84          self.length    = 0 
 85          self.revision  = None 
 86          self.tags      = {'content' : set(), 'distro' : {}} 
 87           
 88          if type(srcfile) in types.StringTypes: 
 89              # srcfile is a filename string 
 90              try: 
 91                  infile = open(srcfile, 'rt') 
 92              except IOError: 
 93                  raise RepoMDError, "Unable to open %s" %(srcfile,) 
 94          else: 
 95              # srcfile is a file object 
 96              infile = srcfile 
 97   
 98          # We trust any of these to mean the repomd.xml is valid. 
 99          infile = AutoFileChecksums(infile, ['sha256', 'sha512'], 
100                                     ignore_missing=True, ignore_none=True) 
101          parser = iterparse(infile) 
102           
103          try: 
104              for event, elem in parser: 
105                  elem_name = ns_cleanup(elem.tag) 
106                   
107                  if elem_name == "data": 
108                      thisdata = RepoData(elem=elem) 
109                      self.repoData[thisdata.type] = thisdata 
110                      try: 
111                          nts = int(thisdata.timestamp) 
112                          if nts > self.timestamp: # max() not in old python 
113                              self.timestamp = nts 
114                      except: 
115                          pass 
116                  elif elem_name == "revision": 
117                      self.revision = elem.text 
118                  elif elem_name == "tags": 
119                      for child in elem: 
120                          child_name = ns_cleanup(child.tag) 
121                          if child_name == 'content': 
122                              self.tags['content'].add(child.text) 
123                          if child_name == 'distro': 
124                              cpeid = child.attrib.get('cpeid', '') 
125                              distro = self.tags['distro'].setdefault(cpeid,set()) 
126                              distro.add(child.text) 
127   
128              self.checksums = infile.checksums.hexdigests() 
129              self.length    = len(infile.checksums) 
130          except SyntaxError, e: 
131              raise RepoMDError, "Damaged repomd.xml file" 
132               
133 -    def fileTypes(self): 
134          """return list of metadata file types available""" 
135          return self.repoData.keys() 
136       
137 -    def getData(self, type): 
138          if type in self.repoData: 
139              return self.repoData[type] 
140          else: 
141              raise RepoMDError, "requested datatype %s not available" % type 
142               
143 -    def dump(self): 
144          """dump fun output""" 
145   
146          print "file timestamp: %s" % self.timestamp 
147          print "file length   : %s" % self.length 
148          for csum in sorted(self.checksums): 
149              print "file checksum : %s/%s" % (csum, self.checksums[csum]) 
150          if self.revision is not None: 
151              print 'revision: %s' % self.revision 
152          if self.tags['content']: 
153              print 'tags content: %s' % ", ".join(sorted(self.tags['content'])) 
154          if self.tags['distro']: 
155              for distro in sorted(self.tags['distro']): 
156                  print 'tags distro: %s' % distro 
157                  tags = self.tags['distro'][distro] 
158                  print '  tags: %s' % ", ".join(sorted(tags)) 
159          print '\n---- Data ----' 
160          for ft in sorted(self.fileTypes()): 
161              thisdata = self.repoData[ft] 
162              print '  datatype: %s' % thisdata.type 
163              print '    location     : %s %s' % thisdata.location 
164              print '    timestamp    : %s' % thisdata.timestamp 
165              print '    size         : %s' % thisdata.size 
166              print '    open size    : %s' % thisdata.opensize 
167              print '    checksum     : %s - %s' % thisdata.checksum 
168              print '    open checksum: %s - %s' %  thisdata.openchecksum 
169              print '    dbversion    : %s' % thisdata.dbversion 
170              print '' 
171   
172 -def main(): 
173   
174      try: 
175          print "file          : %s" % sys.argv[1] 
176          p = RepoMD('repoid', sys.argv[1]) 
177          p.dump() 
178           
179      except IOError: 
180          print >> sys.stderr, "newcomps.py: No such file:\'%s\'" % sys.argv[1] 
181          sys.exit(1) 
182           
183  if __name__ == '__main__': 
184      main() 
185