def get_mappingfile(strTaxID, fApprox=True, strDir=c_strDirMapping):
if not (strTaxID):
return None
else:
if not (sfle.isempty(c_strFileManualMapping)):
pHash = {
k: v
for k, v in [
a.split('\t')
for a in sfle.readcomment(open(c_strFileManualMapping))
]
}
astrMapOutTmp = list(
filter(bool, [
pHash.get(item)
for item in [" ".join(taxid2org(strTaxID).split(" ")[:2])]
]))
astrMapOut = [sfle.d( c_strDirMapping, x) for x in astrMapOutTmp] \
if astrMapOutTmp else []
if not (astrMapOut):
# give an un-prioritized list
astrIDs = [strTaxID] if not (fApprox) else org2taxid(
taxid2org(strTaxID), True)
for strID in astrIDs:
astrGlob = glob.glob(sfle.d(strDir, strID + "_*"))
if astrGlob:
astrMapOut = astrGlob
break
return (astrMapOut[0] if astrMapOut else None)
def MaAsLin(filePCL):
#Build input file name if they exist or give ""
strBase = filePCL.get_abspath().replace(sfle.c_strSufPCL, "")
strR, strRC, strArgs = ((strBase + s)
for s in (sfle.c_strSufR, c_strSufRC, sArgsExt))
fileR, fileRC, fileArgs = ((File(s) if os.path.exists(s) else "")
for s in (strR, strRC, strArgs))
## Read in an args file if it exists
lsArgs = []
if fileArgs:
fReader = csv.reader(open(fileArgs.get_abspath(), 'r'), delimiter=" ")
lsArgsTmp = []
[lsArgsTmp.extend(lsLine) for lsLine in fReader]
fSkip = False
for s in lsArgsTmp:
if s in lsIgnore:
fSkip = True
continue
if fSkip:
fSkip = not fSkip
continue
lsArgs.append(s)
lsInputArgs = ["-I", [fileR]] if fileR else []
lsInputArgs.extend(["-i", [fileRC]] if fileRC else [])
lsArgs.extend(lsInputArgs)
strBase = os.path.basename(strBase)
fileTSVFile = File(
sfle.d(fileDirTmp,
sfle.rebase(filePCL, sfle.c_strSufPCL, sfle.c_strSufTSV)))
strT = File(
sfle.d(
os.path.join(fileDirOutput.get_abspath(), strBase,
strBase + sfle.c_strSufTXT)))
#Transpose PCL
sfle.spipe(pE, filePCL, c_fileProgTranspose, fileTSVFile)
#Run MaAsLin
sfle.op(pE, c_fileProgMaaslin,
lsArgs + [[True, strT], [False, fileTSVFile]])
if fileArgs: Depends(c_fileProgMaaslin, fileArgs)
Default(strT)
def funcDownloadRAW(alistTs):
def _nnnModify(strID):
strStrip = re.findall(r'GSM\d+', strID)[0]
strNNN = strStrip[0:len(strStrip) - 3] + "nnn/"
return strNNN, strStrip
for GSMCEL in alistTs:
GSMid = str(GSMCEL).split(".")[0]
sfle.download( pE, sfle.d( c_strURLSupp, _nnnModify( GSMid )[0],\
_nnnModify( GSMid )[1], str(GSMCEL) ) )
def path_repo():
strRet = os.getcwd()
strRet = strRet[len(path_arepa()):]
while True:
strHead, strTail = os.path.split(strRet)
if not strHead:
strRet = path_arepa() + strRet
break
strRet = strHead
return sfle.d(strRet, "")
def funcIDsTXT(target, source, env):
strT, astrSs = sfle.ts(target, source)
astrFiles = sfle.ftpls(c_strHost, sfle.d(c_strPath, c_strID))
astrFiles = [
mtch.group(1) for mtch in [
_f for _f in (re.search(r'(GSE\d+(?:-GPL\d+)?)', s)
for s in astrFiles) if _f
]
]
with open(strT, "w") as fileOut:
fileOut.write("%s\n" % "\n".join(astrFiles))
return None
def _taxdump():
global s_lockTaxdump, s_hashTaxID2Org, s_hashOrg2TaxID
s_lockTaxdump.acquire()
if (s_hashTaxID2Org == None) or (s_hashOrg2TaxID == None):
s_hashTaxID2Org = {}
s_hashOrg2TaxID = {}
strTaxIDs = sfle.d(path_arepa(), sfle.c_strDirTmp, "taxdump.txt")
try:
for strLine in open(strTaxIDs):
strOrg, strID = strLine.strip().split("\t")
s_hashTaxID2Org[strID] = strOrg
s_hashOrg2TaxID[strOrg] = strID
except IOError:
pass
s_lockTaxdump.release()
return (s_hashTaxID2Org, s_hashOrg2TaxID)
def getGPL(target, source, env):
astrTs, astrSs = ([f.get_abspath() for f in a] for a in (target, source))
strAnnot, strPlatform = astrTs[:2]
strRMeta = astrSs[0]
pid = [row for row in csv.DictReader(open(strRMeta))][0]["platform_id"]
strGPLID = c_strID.split("-")[1] if len(c_strID.split("-")) == 2 else pid
listGPL = [
v.replace(".annot.gz", "") for v in sfle.readcomment(c_fileAnnot)
]
if strGPLID in listGPL:
#Annotation file exist, download
sfle.ex([
"wget",
sfle.d(c_strURLGPL, strGPLID + ".annot.gz"), "-O", strAnnot
])
else:
#Annotation file does not exist, skip download
sfle.ex(["touch", strAnnot])
#Make platform file containing gpl identifier
with open(strPlatform, "w") as outputf:
outputf.write(strGPLID)
def glob(self, fn):
return sorted([
self.fin(a) for a in self.lenv.Glob(sfle.d(self.fileDirInput, fn))
])
def glob_tmp(self, fn):
return sorted(
[str(a) for a in self.lenv.Glob(sfle.d(self.fileDirTmp, fn))])
def level():
strPath = path_repo()
strPath = os.getcwd()[len(strPath):]
iRet = 0
while True:
strHead, strTail = os.path.split(strPath)
if not strHead:
break
iRet += 1
strPath = strHead
return iRet
c_strProgSConstruct = sfle.d(path_arepa(), sfle.c_strDirSrc, "SConstruct.py")
#===============================================================================
# Gene ID conversion
#===============================================================================
#Constants
c_strDirMapping = sfle.d(path_arepa(), "GeneMapper", sfle.c_strDirEtc,
"uniprotko")
c_strFileManualMapping = sfle.d(path_arepa(), "GeneMapper", sfle.c_strDirEtc,
"manual_mapping.txt")
def genemapper():
return sfle.d(path_arepa(), sfle.c_strDirSrc, "SConscript_genemapping.py")
import sys
import metadata
import glob
def test(iLevel, strID, hashArgs):
return (iLevel == 1)
if "testing" in locals():
sys.exit()
pE = DefaultEnvironment()
c_strID = arepa.cwd()
c_fileInputC = sfle.d(pE, arepa.path_repo(), sfle.c_strDirTmp, "mpidbc")
c_fileIDPKL = sfle.d(pE, c_strID + ".pkl")
c_fileIDDAB = sfle.d(pE, c_strID + ".dab")
c_fileIDQUANT = sfle.d(c_strID + ".quant")
c_fileIDRawDAT = sfle.d(pE, c_strID + "_00raw.dat")
c_fileIDDAT = sfle.d(pE, c_strID + ".dat")
c_fileProgUnpickle = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirSrc,
"unpickle.py")
c_fileProgC2Metadata = sfle.d(pE, arepa.path_repo(), sfle.c_strDirSrc,
"c2metadata.py")
c_fileProgC2DAT = sfle.d(pE, arepa.path_repo(), sfle.c_strDirSrc, "c2dat.py")
c_fileInputManCurTXT = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc,
"manual_curation/", c_strID + sfle.c_strSufTXT)
c_fileInputSConscriptGM = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirSrc,
import gzip
def test(iLevel, strID, hashArgs):
return (iLevel == 2) and (strID.find("GDS") == 0)
if "testing" in locals():
sys.exit()
pE = DefaultEnvironment()
c_strID = arepa.cwd()
c_strGDS, c_strGPL = c_strID.split("-")[:2]
c_fileInputSConscript = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirSrc,
"SConscript_pcl-dab.py")
c_fileRSConscript = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirSrc,
"SConscript_rpackage.py")
c_fileInputSOFTGZ = sfle.d(pE, "../" + c_strGDS + ".soft.gz")
c_fileInputManCurTXT = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc,
"manual_curation/", c_strID + ".txt")
c_filePPfun = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc, "preprocess")
c_strPPfun = sfle.readcomment(c_filePPfun)[0]
c_fileTaxa = sfle.d(pE, "taxa.txt")
c_fileStatus = sfle.d(pE, "status.txt")
c_filePlatform = sfle.d(pE, "platform.txt")
c_fileIDMap = sfle.d(pE, c_strID + ".map")
c_fileIDMapRaw = sfle.d(pE, c_strID + "_raw.map")
c_fileIDPKL = sfle.d(pE, c_strID + ".pkl")
c_fileGPLTXTGZ = sfle.d(pE, c_strGPL + ".annot.gz")
import sys
def test(iLevel, strID, hashArgs):
return (iLevel == 1) and (strID.find("GSE") == 0)
if "testing" in locals():
sys.exit()
pE = DefaultEnvironment()
c_strID = arepa.cwd()
c_strHost = "ftp.ncbi.nih.gov"
c_strPath = "pub/geo/DATA/SeriesMatrix/"
c_fileIDTXT = sfle.d(pE, c_strID + ".txt")
Import("hashArgs")
#==============================================================================
# Fetch platform count and recurse
#==============================================================================
def funcIDsTXT(target, source, env):
strT, astrSs = sfle.ts(target, source)
astrFiles = sfle.ftpls(c_strHost, sfle.d(c_strPath, c_strID))
astrFiles = [
mtch.group(1) for mtch in [
_f for _f in (re.search(r'(GSE\d+(?:-GPL\d+)?)', s)
for s in astrFiles) if _f
def funcGeneIDMapping(pE,
fileDATin,
strGeneFrom=None,
fileLOGout=None,
strMAPin=None,
aiCOL=[0, 1],
iSkip=0,
iLevel=2):
try:
int(strMAPin)
strTaxID, strMAPin = strMAPin, None
except (ValueError, TypeError):
strTaxID = None
# Try to find taxid
if not strTaxID:
astrMatch = re.findall(r'taxid_([0-9]+)', c_strID)
strTaxID = astrMatch[0].strip() if astrMatch else None
if not strGeneFrom:
#if strGeneFrom is not specified, try to retrieve it from
#the "manual_geneids.txt" file in the respective etc directory, else None
#this problem tends to arise in mixed microbial network data
if strTaxID and m_hashGeneIDs:
strOrg = " ".join(arepa.taxid2org(strTaxID).split(" ")[:iLevel])
strGeneFrom = m_hashGeneIDs.get(strOrg)
if not (strMAPin):
strDirAuto = c_strDirData if (c_strID == c_strPathRepo) else ""
strAutoMAPtmp = sfle.d(strDirAuto, c_strID + c_strSufMap)
strAutoMAP = strAutoMAPtmp if os.path.exists(strAutoMAPtmp) else None
# Use manual mapping files, files that are deeper down have priority
#else try automatically generated mapping file
afileMaps = Glob(sfle.d(c_strPathTopMapping, "*" + c_strSufMap))
strTopMAP = str(afileMaps[0]) if afileMaps else None
strMAPManTmp = sfle.d(c_strDirManMap, c_strID + c_strSufMap)
strMAPin = (strMAPManTmp if os.path.exists(strMAPManTmp) else
None) or strTopMAP or strAutoMAP
# Use provided mapping files
if not (strMAPin) and strTaxID:
for fileMAPname in Glob(
sfle.d(c_strPathUniprotKO, "*" + c_strSufMap)):
if re.search(r'\D' + strTaxID + r'\D', str(fileMAPname)):
strMAPin = str(fileMAPname)
break
# Else ask arepa to figure out an appropriate mapping file
if not (strMAPin) and strTaxID:
strMAPin = arepa.get_mappingfile(strTaxID)
# Else use BridgeDB files
if not (strMAPin) and strTaxID:
for strSpeciesName in list(c_pHashBridgeDB.keys()):
if strSpeciesName in arepa.taxid2org(strTaxID):
strMAPin = c_pHashBridgeDB[strSpeciesName]
break
strBase, strExt = os.path.splitext(str(fileDATin))
strCount = funcCounter(g_iterCounter)
strT = strBase + c_strMapped + strCount + strExt
aastrPrefix = [[str(fileDATin)], [True, strT], "-c", str(aiCOL)]
astrGeneFrom = ["-f", strGeneFrom] if strGeneFrom else ["-x"]
astrGeneTo = ["-t", c_astrGeneTo[0]]
astrSkip = ["-s", iSkip]
afileLOGout = ["-l", [True, str(fileLOGout)]] if fileLOGout else []
astrMapIn = ["-m", [strMAPin]] if strMAPin else []
aastrArgs = aastrPrefix + astrGeneFrom + astrGeneTo + astrSkip + afileLOGout + astrMapIn
pE.Precious(strMAPin)
return pE.Depends(
sfle.op(pE, c_funcGeneMapper, aastrArgs),
sfle.scons_child(
pE, c_strPathGeneMapper, None, None,
None, ([strMAPin] if not (sfle.in_directory(
strMAPin, os.path.abspath(arepa.cwd()))) else None)))
"""
import sys
import csv
import pickle
import sfle
import arepa
import os
import metadata
import glob
from subprocess import call as ex
c_aiCOL = [0]
c_iSkip = 2
c_iCOL = len(c_aiCOL)
c_fileIDNormPCL = sfle.d(pE, c_strID + "_01norm.pcl")
c_fileIDPCL = sfle.d(pE, c_strID + ".pcl")
c_fileIDDAB = sfle.d(pE, c_strID + ".dab")
c_fileIDQUANT = sfle.d(pE, c_strID + ".quant")
c_fileIDPKL = sfle.d(pE, c_strID + ".pkl")
c_fileStatus = sfle.d(pE, "status.txt")
c_fileIDMap = sfle.d(pE, c_strID + ".map")
c_fileIDMapRaw = sfle.d(pE, c_strID + "_raw.map")
c_strDirManMap = sfle.d(arepa.path_repo(), sfle.c_strDirEtc, "manual_mapping")
c_fileIDMappedPCL = sfle.d(pE, c_strID + "_00mapped.pcl")
c_fileIDMappedPCL2 = sfle.d(pE, c_strID + "_01mapped.pcl")
c_fileFlagSleipnir = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc,
"sleipnir")
def fsrc(self, fn):
return self.lenv.File(sfle.d(self.fileDirSrc, fn)).path
annot2map.py:
parse mapping files
begins with !platform_table_begin
ends with !platform_table_end
"""
import sfle
import glob
import csv
import sys
import re
import arepa
import gzip
c_fileMapping = sfle.d(arepa.path_repo(), sfle.c_strDirEtc, "mapping")
c_hashHead = { k:v for (k, v) in [[y.strip() for y in x.split("%")] for x in sfle.readcomment( open( c_fileMapping))] } if sfle.readcomment(open(c_fileMapping))\
else {
"^ID .*? platform" : "Affy",
"Entrez Gene Symbol" : "HGNC",
"Uniprot .*? Symbol" : "Uniprot/TrEMBL",
"^(Entrez)? UniGene Symbol" : "UniGene",
"Entrez Unigene Identifier" : "UniGene_ID",
"GenBank Accession" : "GB_ACC",
"Entrez Gene identifier" : "Entrez Gene",
"GenBank Identifier" : "GenBank"
}
iArg = len(sys.argv)
strFileAnnotGZ = sys.argv[1] if iArg > 1 else None
strFileOut = sys.argv[2] if iArg > 2 else None
def fin(self, fn):
if isinstance(fn, str):
return str(self.lenv.File(sfle.d(self.fileDirInput, fn)))
else:
return str(self.lenv.File(fn))
import metadata
import re
def test(iLevel, strID, hashArgs):
return (iLevel == 2) and (strID.find("GSE") == 0)
if "testing" in locals():
sys.exit()
pE = DefaultEnvironment()
c_strID = arepa.cwd()
c_strSufRPackage = "_rpackage"
c_fileGPL = sfle.d(pE, arepa.path_repo(), sfle.c_strDirTmp, "gpl.txt")
c_fileAnnot = sfle.d(pE, arepa.path_repo(), sfle.c_strDirTmp, "annot.txt")
c_fileInputSConscript = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirSrc,
"SConscript_pcl-dab.py")
c_fileRSConscript = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirSrc,
"SConscript_rpackage.py")
c_fileProgUnpickle = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirSrc,
"unpickle.py")
c_fileInputGSER = sfle.d(pE, arepa.path_repo(), sfle.c_strDirSrc, "gse.R")
c_fileInputManCurTXT = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc,
"manual_curation/", c_strID + ".txt")
c_filePPfun = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc, "preprocess")
c_fileRunRaw = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc, "raw")
c_fileIDPKL = sfle.d(pE, c_strID + ".pkl")
def genemapper():
return sfle.d(path_arepa(), sfle.c_strDirSrc, "SConscript_genemapping.py")
if "testing" in locals():
sys.exit()
pE = DefaultEnvironment()
c_strID = arepa.cwd().replace("-RAW", "")
c_strURLGEO = 'ftp.ncbi.nih.gov'
c_strURLGEOsupp = 'pub/geo/DATA/supplementary/samples/'
c_strURLSupp = 'ftp://' + c_strURLGEO + '/' + c_strURLGEOsupp
c_strFileGSM = "../GSM.txt"
c_strFilePCL = "../" + c_strID + ".pcl"
c_listTs = sfle.readcomment(c_strFileGSM)
c_fileProgReadCel = sfle.d(pE, arepa.path_repo(), sfle.c_strDirSrc,
"readCel.R")
c_fileProgProcessRaw = sfle.d(pE, arepa.path_repo(), sfle.c_strDirSrc,
"preprocessRaw.R")
c_strInputRData = arepa.cwd() + ".RData"
c_strOutputRData = c_strInputRData.replace("-RAW", "")
c_filePPfun = sfle.d(pE, arepa.path_repo(), sfle.c_strDirEtc, "preprocess")
c_strPPfun = sfle.readcomment( c_filePPfun )[0] if \
sfle.readcomment( c_filePPfun ) else "affy::rma"
c_fileExpTable = sfle.d(pE, "../" + c_strID + "_exp_metadata.txt")
c_fileCondTable = sfle.d(pE, "../" + c_strID + "_cond_metadata.txt")
Import("hashArgs")
#Download CEL files (if they exist)
def path_arepa():
return sfle.d(os.path.abspath(sfle.d(os.path.dirname(__file__), "..")), "")
def fout(self, fn, mult=None):
if mult:
return [self.fout(fn.format(m)) for m in mult]
return str(self.lenv.File(sfle.d(self.fileDirOutput, fn)))
hashRet.get(i) for i in [c_strCount, c_strQuery, c_strWebEnv]
]
#===========================================================================
# Iteratively download temporary xml files
#===========================================================================
def discrete_list(num, increment):
iTries = (num / increment) + 1
return [str(1 + (a * increment)) for a in range(iTries)]
count_list = discrete_list(int(id_count), c_iIncrement)
astrOutput = [
sfle.d(sfle.c_strDirTmp, geo_id + str(i) + c_strSufXML)
for i in range(1,
len(count_list) + 1)
]
query_list = list(
zip(astrOutput, count_list, [query_key] * len(count_list),
[web_env] * len(count_list)))
# Download
for astr in query_list:
strT, strCount, strQuery, strWeb = astr
sfle.ex([
"curl", "-g", "-f", "-z", '"' + strT + '"',
'"' + c_strURLSum % (strCount, strQuery, strWeb) + '"', ">", strT
])
def ftmp(self, fn, mult=None):
if mult:
return [self.ftmp(fn.format(m)) for m in mult]
return str(self.lenv.File(sfle.d(self.fileDirTmp, fn)))
Maintainer: $arepa_maintainer
Description: Automatically generated R package by arepa
Depends: R (>= 2.10.0), affy
Suggests: survival
License: MIT
URL: http://huttenhower.sph.harvard.edu/arepa
"""
import sfle
import arepa
import sys
import pickle
c_strNAMESPACE = r"'exportPattern("'"^[[:alpha:]]+"'")'"
c_fileProgUnpickle = sfle.d( pE, arepa.path_arepa(), sfle.c_strDirSrc, "unpickle.py" )
def funcCheckRStructure( pE, strDatasetName, filePKL, fileNAMESPACE, fileDESCRIPTION, fileManMaster, strNAMESPACE = c_strNAMESPACE ):
'''
Completes necessary components for R package building
Assumes that data/ and man/ directories have the corresponding data and manual files per dataset
Input:
fileNAMESPACE = pointer to NAMESPACE file to be tracked
fileManMaster = pointer to the master manual file in man/
'''
def _makeDescription( target, source, env ):
strT, astrSs = sfle.ts( target, source )
pHash = pickle.load(open(astrSs[0]))
pHashDescription = { "Package": strDatasetName.replace("-", "."), "Type": "Package", "Title": pHash.get("title"),
import os
import sys
import sfle
import pickle
import itertools
import re
import time
import sfle
g_iterCounter = itertools.count(0)
c_strID = arepa.cwd()
c_strPathRepo = arepa.name_repo()
c_strSufMap = ".map"
c_strMapped = "_mapped"
c_strDirData = sfle.d(arepa.path_repo(), sfle.c_strDirData)
c_strDirManMap = sfle.d(arepa.path_repo(), sfle.c_strDirEtc, "manual_mapping")
c_astrGeneTo = sfle.readcomment(
sfle.d(arepa.path_arepa(), sfle.c_strDirEtc, "geneid")
or [arepa.genemap_genename()])
c_strPathGeneMapper = sfle.d(arepa.path_arepa(), "GeneMapper")
c_strFileUnzipLog = sfle.d(c_strPathGeneMapper, sfle.c_strDirTmp, "unzip.log")
c_strFileCompileLog = sfle.d(c_strPathGeneMapper, sfle.c_strDirTmp,
"compile.log")
c_strPathTopMapping = sfle.d(c_strPathGeneMapper, sfle.c_strDirEtc,
"manual_mapping")
c_strPathUniprotKO = sfle.d(c_strPathGeneMapper, sfle.c_strDirEtc, "uniprotko")
c_fileProgMakeUnique = sfle.d(arepa.path_arepa(), sfle.c_strDirSrc,
"makeunique.py")
c_funcGeneMapper = sfle.d(c_strPathGeneMapper, sfle.c_strDirSrc,
"bridgemapper.py")
__author__ = "Timothy Tickle and Curtis Huttenhower"
__copyright__ = "Copyright 2012"
__credits__ = ["Timothy Tickle", "Curtis Huttenhower"]
__maintainer__ = "Timothy Tickle"
__email__ = "*****@*****.**"
import argparse
import os
import sfle
import sys
c_strSufRC = ".read.config"
c_fileDirSrc = Dir(
sfle.d(os.path.dirname(sfle.current_file()), sfle.c_strDirSrc))
c_fileProgMaaslin = File(sfle.d(c_fileDirSrc, "Maaslin.R"))
sArgsExt = ".args"
#Commandline to ignore
lsIgnore = ["-i", "-I", "--input_config", "--input_process"]
def MaAsLin(filePCL):
#Build input file name if they exist or give ""
strBase = filePCL.get_abspath().replace(sfle.c_strSufPCL, "")
strR, strRC, strArgs = ((strBase + s)
for s in (sfle.c_strSufR, c_strSufRC, sArgsExt))
fileR, fileRC, fileArgs = ((File(s) if os.path.exists(s) else "")
for s in (strR, strRC, strArgs))
## Read in an args file if it exists
import arepa import gzip import os import re import sfle import sys def test( iLevel, strID, hashArgs ): return ( iLevel == 1 ) and ( strID.find( "GDS" ) == 0 ) if "testing" in locals( ): sys.exit( ) pE = DefaultEnvironment( ) c_strID = arepa.cwd( ) c_fileIDTXT = sfle.d( pE, c_strID + ".txt" ) c_fileIDSOFTGZ = sfle.d( pE, c_strID + ".soft.gz" ) Import( "hashArgs" ) #=============================================================================== # Download SOFT file #=============================================================================== sfle.download( pE, hashArgs["c_strURLGDS"] + os.path.basename( str(c_fileIDSOFTGZ) ) ) def funcGPLsTXT( target, source, env ): strT, astrSs = sfle.ts( target, source ) setstrGPLs = set() for strLine in gzip.open( astrSs[0] ): mtch = re.search( r'^!dataset_platform\s*=\s*(\S+)', strLine )
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE
OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
SConscript_dat-dab.py:
shared code across modules
handles all behavior pertaining to
mapping dat to dab and generating quant files
"""
import sfle
import arepa
c_fileFlagSleipnir = sfle.d(pE, arepa.path_arepa(), sfle.c_strDirEtc,
"sleipnir")
def funcDAB(pE, fileOutDAB, afileInDAT):
astrSleipnir = sfle.readcomment(c_fileFlagSleipnir)
bSleipnir = (astrSleipnir[0] == "True")
print("sleipnir", ("On" if bSleipnir else "Off"))
def _funcDAB(target, source, env):
strT, astrSs = sfle.ts(target, source)
strOut, strMap = astrSs[:2]
return sfle.ex(("Dat2Dab", "-o", strT, "-i",
(strOut if sfle.isempty(strMap) else strMap)))
if bSleipnir:
