def testAddColumnHeaderRowToCsvFile(self):
adit_fn = (
"adit_nmr_matched_pdb_bmrb_entry_ids.csv"
) # already contains one header row but let's add another one.
src = os.path.join(cingRoot, matchBmrbPdbDataDir, adit_fn)
copyfile(src, adit_fn)
columnOrder = "bmrb_id pdb_id".split()
self.assertFalse(addColumnHeaderRowToCsvFile(adit_fn, columnOrder))
def prepare(self):
'Return True on error.'
if self.restartFromScratch:
rmdir(matchBmrbPdbDir)
if not os.path.exists(matchBmrbPdbDir):
csvFileDir = os.path.join(cingRoot, matchBmrbPdbDataDir)
nTmessage("Recreating data dir %s from SVN %s" % (matchBmrbPdbDir, csvFileDir))
# mkdirs( matchBmrbPdbDir )
copytree(csvFileDir, matchBmrbPdbDir)
else:
nTmessage("Reusing existing data dir " + matchBmrbPdbDir)
os.chdir(matchBmrbPdbDir)
if 1: # DEFAULT: 1
nTmessage("Getting ADIT from: %s" % self.adit_url)
if os.path.exists(self.adit_fn):
os.unlink(self.adit_fn) # prevent buildup of endless copies.
wgetProgram = ExecuteProgram('wget --no-verbose %s' % self.adit_url, redirectOutputToFile ='getAdit.log' )
exitCode = wgetProgram()
if exitCode:
nTerror("Failed to download file %s" % self.adit_url)
return True
if not os.path.exists(self.adit_fn):
nTerror("Failed to find downloaded file %s" % self.adit_url)
return True
columnOrder = 'bmrb_id pdb_id'.split()
if addColumnHeaderRowToCsvFile(self.adit_fn, columnOrder):
nTerror("Failed to add header row to " + self.adit_fn)
return True
nTmessage("Got the ADIT info")
if 1: # DEFAULT: 1
nTmessage("Getting BMRB file list from : %s" % bmrbDir)
bmrbFileList = findFiles("bmr*_21.str", bmrbDir)
bmrbIdList = []
for bmrbFile in bmrbFileList:
_directory, basename, _extension = nTpath(bmrbFile)
bmrbId = int(basename[3:-3]) # bmr970_21 -> 970
bmrbIdList.append(bmrbId)
bmrbIdList.sort()
bmrbId2List = getBmrbEntries()
bmrbIdNTList = NTlist(*bmrbIdList)
bmrbId2NTList = NTlist(*bmrbId2List)
bmrbIdNTmissingList = bmrbIdNTList.difference(bmrbId2NTList)
if bmrbIdNTmissingList:
nTmessage("Found %d entries on file but not in DB: %s" % (len(bmrbIdNTmissingList), str(bmrbIdNTmissingList)))
bmrbId2NTmissingList = bmrbId2NTList.difference(bmrbIdNTList)
if bmrbId2NTmissingList:
nTmessage("Found %d entries in DB but not on file: %s" % (len(bmrbId2NTmissingList), str(bmrbId2NTmissingList)))
if len( bmrbIdNTmissingList + bmrbId2NTmissingList ) > 40: # was 18 + 3=21 on April 11, 2011.
nTwarning("More than one hundred inconsistencies between BMRB DB and on file.")
bmrbIdStrList = ['bmrb_id'] + [ str(x) for x in bmrbIdList] # add header for CSV reader.
fileName = os.path.join( matchBmrbPdbDir, 'bmrb.csv')
txt = '\n'.join(bmrbIdStrList)
if writeTextToFile(fileName, txt):
return True
if 1: # DEFAULT: 1
dbms2 = DBMS()
pdbList = getPdbEntries(onlyNmr = True)
pdbNmrTable = Relation('pdbNmr', dbms2, columnList=['pdb_id'])
pdbIdColumn = pdbNmrTable.getColumnByIdx(0) # pylint: disable=W0612
pdbIdColumn += pdbList
pdbNmrTable.writeCsvFile('pdbNmrTable.csv')
def testAddColumnHeaderRowToCsvFile(self):
adit_fn = 'adit_nmr_matched_pdb_bmrb_entry_ids.csv' # already contains one header row but let's add another one.
src = os.path.join(cingRoot, matchBmrbPdbDataDir, adit_fn)
copyfile(src, adit_fn)
columnOrder = 'bmrb_id pdb_id'.split()
self.assertFalse(addColumnHeaderRowToCsvFile(adit_fn, columnOrder))
def prepare(self):
'Return True on error.'
if self.restartFromScratch:
rmdir(matchBmrbPdbDir)
if not os.path.exists(matchBmrbPdbDir):
csvFileDir = os.path.join(cingRoot, matchBmrbPdbDataDir)
nTmessage("Recreating data dir %s from SVN %s" %
(matchBmrbPdbDir, csvFileDir))
# mkdirs( matchBmrbPdbDir )
copytree(csvFileDir, matchBmrbPdbDir)
else:
nTmessage("Reusing existing data dir " + matchBmrbPdbDir)
os.chdir(matchBmrbPdbDir)
if 1: # DEFAULT: 1
nTmessage("Getting ADIT from: %s" % self.adit_url)
if os.path.exists(self.adit_fn):
os.unlink(self.adit_fn) # prevent buildup of endless copies.
wgetProgram = ExecuteProgram('wget --no-verbose %s' %
self.adit_url,
redirectOutputToFile='getAdit.log')
exitCode = wgetProgram()
if exitCode:
nTerror("Failed to download file %s" % self.adit_url)
return True
if not os.path.exists(self.adit_fn):
nTerror("Failed to find downloaded file %s" % self.adit_url)
return True
columnOrder = 'bmrb_id pdb_id'.split()
if addColumnHeaderRowToCsvFile(self.adit_fn, columnOrder):
nTerror("Failed to add header row to " + self.adit_fn)
return True
nTmessage("Got the ADIT info")
if 1: # DEFAULT: 1
nTmessage("Getting BMRB file list from : %s" % bmrbDir)
bmrbFileList = findFiles("bmr*_21.str", bmrbDir)
bmrbIdList = []
for bmrbFile in bmrbFileList:
_directory, basename, _extension = nTpath(bmrbFile)
bmrbId = int(basename[3:-3]) # bmr970_21 -> 970
bmrbIdList.append(bmrbId)
bmrbIdList.sort()
bmrbId2List = getBmrbEntries()
bmrbIdNTList = NTlist(*bmrbIdList)
bmrbId2NTList = NTlist(*bmrbId2List)
bmrbIdNTmissingList = bmrbIdNTList.difference(bmrbId2NTList)
if bmrbIdNTmissingList:
nTmessage("Found %d entries on file but not in DB: %s" %
(len(bmrbIdNTmissingList), str(bmrbIdNTmissingList)))
bmrbId2NTmissingList = bmrbId2NTList.difference(bmrbIdNTList)
if bmrbId2NTmissingList:
nTmessage(
"Found %d entries in DB but not on file: %s" %
(len(bmrbId2NTmissingList), str(bmrbId2NTmissingList)))
if len(bmrbIdNTmissingList + bmrbId2NTmissingList
) > 40: # was 18 + 3=21 on April 11, 2011.
nTwarning(
"More than one hundred inconsistencies between BMRB DB and on file."
)
bmrbIdStrList = ['bmrb_id'] + [str(x) for x in bmrbIdList
] # add header for CSV reader.
fileName = os.path.join(matchBmrbPdbDir, 'bmrb.csv')
txt = '\n'.join(bmrbIdStrList)
if writeTextToFile(fileName, txt):
return True
if 1: # DEFAULT: 1
dbms2 = DBMS()
pdbList = getPdbEntries(onlyNmr=True)
pdbNmrTable = Relation('pdbNmr', dbms2, columnList=['pdb_id'])
pdbIdColumn = pdbNmrTable.getColumnByIdx(0) # pylint: disable=W0612
pdbIdColumn += pdbList
pdbNmrTable.writeCsvFile('pdbNmrTable.csv')
