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
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
|
#! /usr/bin/env python
#############################################################
# #
# Author: Bertrand Neron #
# Organization:'Biological Software and Databases' Group, #
# Institut Pasteur, Paris. #
# Distributed under GPLv2 Licence. Please refer to the #
# COPYING.LIB document. #
# #
#############################################################
import os , sys
import time
from lxml import etree
MOBYLEHOME = None
if os.environ.has_key('MOBYLEHOME'):
MOBYLEHOME = os.environ['MOBYLEHOME']
if not MOBYLEHOME:
sys.exit('MOBYLEHOME must be defined in your environment')
if ( MOBYLEHOME ) not in sys.path:
sys.path.append( MOBYLEHOME )
if ( os.path.join( MOBYLEHOME , 'Src' ) ) not in sys.path:
sys.path.append( os.path.join( MOBYLEHOME , 'Src' ) )
from Mobyle.Classes.DataType import DataTypeFactory
import Mobyle.Parser
import Mobyle.Classes.Core
import Local.CustomClasses
from Mobyle.MobyleError import ParserError
class XmlDataTypeRepository:
TAIL = '//'
SEP = '|'
COMMENT = '#'
XML_HEADER = "%-30.30s %s %-15.15s %s %s" % ( " xml class" , SEP , "python class", SEP , "description" )
PYTHON_HEADER = " Mobyle python class used "
BIOTYPE_HEADER = " biotypes used "
def __init__(self, path):
self._dataTypeFactory = DataTypeFactory()
self.descriptions = {}
self.biotypes = []
self.xmlTypes = [] # [ xmlType, python Type ]
self.pythonTypes = []
self.parse( path )
def parse(self, xmlPaths):
self.name = 'xml list'
errors = []
biotypes = {}
for xmlPath in xmlPaths:
doc = etree.parse( "file://%s" % os.path.abspath( xmlPath ) )
parameters = doc.xpath( './/parameter' )
for parameter in parameters:
try:
typeNode = parameter.xpath( 'type' )[0]
mt = Mobyle.Parser.parseType( typeNode , self._dataTypeFactory )
for biotype in mt.getBioTypes():
biotypes[ biotype ] = None
except IndexError:
parameterName = parameter.xpath( 'name/text()')[0]
errors.append( "%s/%s haven't any type" % (xmlPath , parameterName ) )
except ParserError , err:
parameterName = parameter.xpath( 'name/text()')[0]
errors.append( "%s/%s : %s" % (xmlPath , parameterName , err ) )
if errors:
for error in errors:
print >> sys.stderr , "ERROR ", error
sys.exit(1)
for dtName in self._dataTypeFactory.definedDataTypes.keys():
ancestors = self._dataTypeFactory.definedDataTypes[ dtName ].ancestors
mobyleClasses = dir( Mobyle.Classes )
localCustomClasses = dir( Local.CustomClasses )
if dtName in mobyleClasses:
self.pythonTypes.append( dtName )
elif dtName in localCustomClasses:
self.pythonTypes.append( dtName )
else:
self.xmlTypes.append( ( ancestors[0] , ancestors[1] ) )
self.biotypes = biotypes.keys()
self.biotypes.sort()
self.pythonTypes.sort()
self.xmlTypes.sort()
def mistakeDetector(self):
warnings = []
xmlCaseError = {}
for xmlType , pythonType in self.xmlTypes:
upXmlType = xmlType.upper()
if xmlCaseError.has_key( upXmlType ):
warnings.append( "found to similar xml datatype %s and %s" % ( xmlType , xmlCaseError[ upXmlType ] ))
else:
xmlCaseError[ upXmlType ] = xmlType
biotypeCaseError = {}
for biotype in self.biotypes:
upBiotype = biotype.upper()
if biotypeCaseError.has_key( upBiotype ):
warnings.append( "found to similar biotype %s and %s" % (biotype , biotypeCaseError[ upBiotype] ) )
else:
biotypeCaseError[ upBiotype ] = biotype
return warnings
def __str__(self):
repr = ''
comment = '# mobyle datatype repositotry %s #' % time.strftime( '%x %X' , time.localtime() )
pythonBody = '\n'.join( [ "%-25.25s %s " % ( pythonType , self.SEP ) for pythonType in self.pythonTypes ] )
repr = repr + "%(comment)s\n%(diese)s\n%(header)s\n%(diese)s\n%(body)s\n%(tail)s\n" % {"comment": comment ,
"diese" : '#'*26 ,
"header" : self.PYTHON_HEADER ,
"body" : pythonBody ,
"tail" : self.TAIL
}
xmlBody = '\n'.join( [ "%-30.30s %s %-15.15s %s " % ( xmlType , self.SEP , pythonType , self.SEP ) for xmlType , pythonType in self.xmlTypes ] )
repr = repr + "\n%(diese)s\n%(header)s\n%(diese)s\n%(body)s\n%(tail)s\n" % {"diese" : '#'*64 ,
"header" : self.XML_HEADER ,
"body" : xmlBody ,
"tail" : self.TAIL
}
biotypesBody = '\n'.join([ '%-15.15s %s' % ( biotype , self.SEP ) for biotype in self.biotypes ] )
repr = repr + "\n%(diese)s\n%(header)s\n%(diese)s\n%(body)s\n%(tail)s\n" % {"diese" : '#'*15 ,
"header" : self.BIOTYPE_HEADER ,
"body" : biotypesBody ,
"tail" : self.TAIL
}
return repr
def diff(self , repository ):
import difflib
sm = difflib.SequenceMatcher()
pythonDiff = ''
xmlDiff = ''
bioDiff = ''
#sm.set_seqs( self.pythonTypes , repository.pythonTypes )
sm.set_seqs( repository.pythonTypes , self.pythonTypes )
blocks = sm.get_opcodes()
for block in blocks:
if block[0] == 'equal' :
continue
elif block[0] == 'insert' :
pythonDiff += '\n'.join( [ '+ '+ str( Type ) for Type in self.pythonTypes[ block[3] : block[4] ] ] )
pythonDiff += '\n'
elif block[0] == 'delete':
pythonDiff += '\n'.join( [ '- '+ str( Type ) for Type in repository.pythonTypes[ block[1] : block[2] ] ])
pythonDiff += '\n'
if pythonDiff:
pythonDiff = "Mobyle python diff\n%s\n%s\n" % ( "="*20 , pythonDiff )
sm.set_seqs( repository.xmlTypes , self.xmlTypes )
blocks = sm.get_opcodes()
for block in blocks:
if block[0] == 'equal' :
continue
elif block[0] == 'insert' :
xmlDiff += '\n'.join( ["+ %-15.15s %s %-30.30s %s" % ( Type[0] , self.SEP , Type[1] , self.SEP ) for Type in self.xmlTypes[ block[3] : block[4] ] ] )
xmlDiff += '\n'
elif block[0] == 'delete':
xmlDiff += '\n'.join( ["- %-15.15s %s %-30.30s %s" % ( Type[0] , self.SEP , Type[1] , self.SEP ) for Type in repository.xmlTypes[ block[1] : block[2] ] ] )
xmlDiff += '\n'
if xmlDiff:
xmlDiff = "xml class diff\n%s\n%s\n" % ( "="*15 , xmlDiff)
sm.set_seqs( repository.biotypes , self.biotypes )
blocks = sm.get_opcodes()
for block in blocks:
if block[0] == 'equal' :
continue
elif block[0] == 'insert' :
bioDiff += '\n'.join( [ '+ '+ str( Type ) for Type in self.biotypes[ block[3] : block[4] ] ] )
pythonDiff += '\n'
elif block[0] == 'delete':
bioDiff += '\n'.join( [ '- '+ str( Type ) for Type in repository.biotypes[ block[1] : block[2] ] ])
bioDiff += '\n'
if bioDiff:
bioDiff = "biotypes diff\n%s\n%s\n" % ( "="*14 , bioDiff )
if pythonDiff or xmlDiff or bioDiff:
return "--- %s\n+++ %s\n\n %s%s%s" % ( repository.name , self.name , pythonDiff , xmlDiff , bioDiff )
class DataTypeReference( XmlDataTypeRepository ):
def parse(self , repositoryPath ):
self.name = repositoryPath
f = file( repositoryPath , 'r' )
header_found = False
tail_found = False
for line in f:
line = line.strip()
if line.startswith( self.COMMENT ):
continue
elif line == self.PYTHON_HEADER.strip():
header_found = True
self.pythonTypes = self._parsePythonType( f )
elif line == self.XML_HEADER.strip():
header_found = True
self.xmlTypes , self.descriptions = self._parseXmlType( f )
elif line == self.BIOTYPE_HEADER.strip():
header_found = True
self.biotypes = self._parseBiotype( f )
elif line.startswith( self.TAIL ):
tail_found = True
break
else:
if not header_found:
print >> sys.stderr , "ERROR bad file format for DataType Reference %s : No header found" % f.name
sys.exit(2)
def _parsePythonType(self , refFile ):
tail_found = False
pythonTypes = {}
for line in refFile:
if line.startswith( self.COMMENT ):
continue
elif line.startswith( self.TAIL ):
tail_found = True
break
else:
fields = line.split( self.SEP )
fields = [ item.strip() for item in fields ]
if fields == ['']: # skip blank line
continue
else:
pythonType = fields[0]
if pythonTypes.has_key( pythonType ):
print >> sys.stderr , "the reference %s has 2 %s entries" % ( ref.name , pythonType )
sys.exit(2)
else:
pythonTypes[ pythonType ] = None
if not tail_found:
print >> sys.stderr , "ERROR bad file format for DataType Reference %s : Unexpected end of file " % refFile.name
sys.exit(2)
pythonTypes = pythonTypes.keys()
pythonTypes.sort()
return pythonTypes
def _parseXmlType(self, refFile ):
tail_found = False
descriptions = {}
for line in refFile:
if line.startswith( self.COMMENT ):
continue
elif line.startswith( self.TAIL ):
tail_found = True
break
else:
fields = line.split( self.SEP )
fields = [ item.strip() for item in fields ]
if fields == ['']: # skip blank line
continue
else:
xmlKlass , pythonKlass , description = fields
dataType = self._dataTypeFactory.newDataType( pythonKlass , xmlName = xmlKlass )
descriptions[ xmlKlass ] = description
if not tail_found:
print >> sys.stderr , "ERROR bad file format for DataType Reference %s : Unexpected end of file " % refFile.name
sys.exit(2)
xmlTypes = []
for dtName in self._dataTypeFactory.definedDataTypes.keys():
ancestors = self._dataTypeFactory.definedDataTypes[ dtName ].ancestors
mobyleClasses = dir( Mobyle.Classes )
localCustomClasses = dir( Local.CustomClasses )
if dtName in mobyleClasses:
pass
elif dtName in localCustomClasses:
pass
else:
xmlTypes.append( ( ancestors[0] , ancestors[1] ) )
xmlTypes.sort()
return xmlTypes , descriptions
def _parseBiotype(self, refFile ):
biotypes = {}
tail_found = False
for line in refFile:
if line.startswith( self.COMMENT ):
continue
elif line.startswith( self.TAIL ):
tail_found = True
break
else:
fields = line.split( self.SEP )
fields = [ item.strip() for item in fields ]
if fields == ['']: # skip blank line
continue
else:
biotype = fields[0]
if biotypes.has_key( biotype ):
print >> sys.stderr , "the reference %s has 2 %s entries" % ( ref.name , biotype )
sys.exit(2)
else:
biotypes[ biotype ] = None
if not tail_found:
print >> sys.stderr , "ERROR bad file format for DataType Reference %s : Unexpected end of file " % refFile.name
sys.exit(2)
biotypes = biotypes.keys()
biotypes.sort()
return biotypes
if __name__ == '__main__':
from getopt import gnu_getopt , GetoptError
def usage():
print """
generate on the standart output a mobyle types repository ( python , xml and biotype ).
if -ref is specified do a diff between the ref and the xml
usage: mobtypes < --ref path to a datatype repository > < xmlpaths to analyze >
if no paths are provide as arguments, use the xmlpaths installed (local and imported) for this portal.
options:
-h or --help ... Print this message and exit.
-r or --ref ... the path to a datatype repository.
"""
try:
opts, xmlPaths = gnu_getopt( sys.argv[1:], "hr:", [ "help" , "ref=" ] )
refPath = None
for option , value in opts:
if option in ( "-h","--help" ):
usage()
sys.exit( 0 )
elif option in ( "-r" , "--ref=" ):
refPath = value
if not os.path.exists( value ):
print >> sys.stderr , "ERROR : %s %s the No such file" % ( option , value )
sys.exit(1)
if not xmlPaths:
from Mobyle.Registry import registry
xmlPaths = [ p.path for p in registry.programs ]
except GetoptError:
print usage()
sys.exit( 1 )
xmlRepository = XmlDataTypeRepository( xmlPaths )
if refPath:
ref = DataTypeReference( refPath )
print ref.diff( xmlRepository )
else:
print xmlRepository
w = xmlRepository.mistakeDetector()
if w:
print >> sys.stderr , " -- WARNINGS -- "
print >> sys.stderr , '\n'.join( w )
|
