/usr/lib/python2.7/dist-packages/yum/mdparser.py is in yum 3.4.3-3.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | #! /usr/bin/python -tt
# 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 2 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 Library General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
# Copyright 2005 Duke University
import gzip
try:
from xml.etree import cElementTree
except ImportError:
import cElementTree
iterparse = cElementTree.iterparse
from cStringIO import StringIO
import warnings
import Errors
#TODO: document everything here
class MDParser:
def __init__(self, filename):
# Set up mapping of meta types to handler classes
handlers = {
'{http://linux.duke.edu/metadata/common}metadata': PrimaryEntry,
'{http://linux.duke.edu/metadata/filelists}filelists': FilelistsEntry,
'{http://linux.duke.edu/metadata/other}otherdata': OtherEntry,
}
self.total = None
self.count = 0
self._handlercls = None
# Read in type, set package node handler and get total number of
# packages
if filename[-3:] == '.gz': fh = gzip.open(filename, 'r')
else: fh = open(filename, 'r')
parser = iterparse(fh, events=('start', 'end'))
self.reader = parser.__iter__()
event, elem = self.reader.next()
self._handlercls = handlers.get(elem.tag, None)
if not self._handlercls:
raise ValueError('Unknown repodata type "%s" in %s' % (
elem.tag, filename))
# Get the total number of packages
self.total = int(elem.get('packages', 0))
def __iter__(self):
return self
def next(self):
for event, elem in self.reader:
if event == 'end' and elem.tag[-7:] == 'package':
self.count += 1
return self._handlercls(elem)
raise StopIteration
class BaseEntry:
def __init__(self, elem):
self._p = {}
def __getitem__(self, k):
return self._p[k]
def keys(self):
return self._p.keys()
def values(self):
return self._p.values()
def has_key(self, k):
warnings.warn('has_key() will go away in a future version of Yum.\n',
Errors.YumFutureDeprecationWarning, stacklevel=2)
return k in self._p
def __iter__(self):
return iter(self._p)
def __str__(self):
out = StringIO()
keys = self.keys()
keys.sort()
for k in keys:
line = u'%s=%s\n' % (k, self[k])
out.write(line.encode('utf8'))
return out.getvalue()
def _bn(self, qn):
if qn.find('}') == -1: return qn
return qn.split('}')[1]
def _prefixprops(self, elem, prefix):
ret = {}
for key in elem.attrib:
ret[prefix + '_' + self._bn(key)] = elem.attrib[key]
return ret
class PrimaryEntry(BaseEntry):
def __init__(self, elem):
BaseEntry.__init__(self, elem)
# Avoid excess typing :)
p = self._p
self.prco = {}
self.files = {}
for child in elem:
name = self._bn(child.tag)
if name in ('name', 'arch', 'summary', 'description', 'url',
'packager'):
p[name] = child.text
elif name == 'version':
p.update(child.attrib)
elif name in ('time', 'size'):
p.update(self._prefixprops(child, name))
elif name in ('checksum', 'location'):
p.update(self._prefixprops(child, name))
p[name + '_value'] = child.text
if name == 'location' and "location_base" not in p:
p["location_base"] = None
elif name == 'format':
self.setFormat(child)
p['pkgId'] = p['checksum_value']
elem.clear()
def setFormat(self, elem):
# Avoid excessive typing :)
p = self._p
for child in elem:
name = self._bn(child.tag)
if name in ('license', 'vendor', 'group', 'buildhost',
'sourcerpm'):
p[name] = child.text
elif name in ('provides', 'requires', 'conflicts',
'obsoletes'):
self.prco[name] = self.getPrco(child)
elif name == 'header-range':
p.update(self._prefixprops(child, 'rpm_header'))
elif name == 'file':
file_type = child.get('type', 'file')
path = child.text
self.files[path] = file_type
def getPrco(self, elem):
members = []
for child in elem:
members.append(child.attrib)
return members
class FilelistsEntry(BaseEntry):
def __init__(self, elem):
BaseEntry.__init__(self, elem)
self._p['pkgId'] = elem.attrib['pkgid']
self.files = {}
for child in elem:
name = self._bn(child.tag)
if name == 'file':
file_type = child.get('type', 'file')
path = child.text
self.files[path] = file_type
elem.clear()
class OtherEntry(BaseEntry):
def __init__(self, elem):
BaseEntry.__init__(self, elem)
self._p['pkgId'] = elem.attrib['pkgid']
self._p['changelog'] = []
for child in elem:
name = self._bn(child.tag)
if name == 'changelog':
entry = child.attrib
entry['value'] = child.text
self._p['changelog'].append(entry)
elem.clear()
def test():
import sys
parser = MDParser(sys.argv[1])
for pkg in parser:
print '-' * 40
print pkg
print 'read: %s packages (%s suggested)' % (parser.count, parser.total)
if __name__ == '__main__':
test()
|