Description: Fix Python3.12 string syntax Bug-Debian: https://bugs.debian.org/1085772 Author: Andreas Tille Last-Update: 2024-06-09 --- a/pbsuite/utils/BamStat.py +++ b/pbsuite/utils/BamStat.py @@ -72,7 +72,7 @@ def expandMd(md): Turns abbreviated MD into a full array """ ret = [] - for i in re.findall("\d+|\^?[ATCGN]+", md): + for i in re.findall(r"\d+|\^?[ATCGN]+", md): if i.startswith('^'): ret.extend(list(i[1:])) elif i[0] in ["A","T","C","G","N"]: --- a/pbsuite/utils/FileHandlers.py +++ b/pbsuite/utils/FileHandlers.py @@ -46,7 +46,7 @@ class FastaFile(dict): buffer.append( ">" + key + "\n" + wrap(self[key]).strip()) return "\n".join(buffer) -splRE = re.compile("\s+") +splRE = re.compile(r"\s+") class QualFile(dict): def __init__(self, fileName, convert=True): @@ -57,7 +57,7 @@ class QualFile(dict): self.fileHandler.close() def __parse(self): - splRE = re.compile("\s+") + splRE = re.compile(r"\s+") for line in self.fileHandler.readlines(): if line.startswith('>'): curName = line.strip()[1:] @@ -84,7 +84,7 @@ class QualFile(dict): self[curName].write(line.strip() + " ") for key in self: - self[key] = list(map(int, re.split("\s+", self[key].getvalue().strip()))) + self[key] = list(map(int, re.split(r"\s+", self[key].getvalue().strip()))) def toString(self): buffer = [] @@ -472,7 +472,7 @@ qname tname score pctsimilarity qstrand tstrand tstart tend tseqlength [mapqv ncells npaths] """ -subreadGrab = re.compile(".*/(\d+)_(\d+)$") +subreadGrab = re.compile(r".*/(\d+)_(\d+)$") class M4File(list): @@ -496,7 +496,7 @@ class M4File(list): class M4Line(): def __init__(self, line): - data = re.split("\s+",line) + data = re.split(r"\s+",line) self.qname = data[0] self.tname = data[1] @@ -606,7 +606,7 @@ class M5File(list): class M5Line(): def __init__(self, line): - data = re.split("\s+",line) + data = re.split(r"\s+",line) self.qname = data[0] self.qseqlength = int(data[1]) --- a/pbsuite/utils/VCFIO.py +++ b/pbsuite/utils/VCFIO.py @@ -107,10 +107,10 @@ class VCFFile(): -METARE = re.compile(('##\s*(?P\w+)\s*=\s*\<\s*ID\s*=\s*(?P\w+)\s*' - ',\s*(Number\s*=\s*(?P[0-9.])\s*,' - '\s*Type\s*=\s*(?P\w+)\s*,)?' - '\s*Description\s*=\s*"(?P.*)"\s*\>\s*'),\ +METARE = re.compile((r'##\s*(?P\w+)\s*=\s*\<\s*ID\s*=\s*(?P\w+)\s*' + r',\s*(Number\s*=\s*(?P[0-9.])\s*,' + r'\s*Type\s*=\s*(?P\w+)\s*,)?' + r'\s*Description\s*=\s*"(?P.*)"\s*\>\s*'),\ re.IGNORECASE) class META(): --- a/pbsuite/utils/jellyoutputrename.py +++ b/pbsuite/utils/jellyoutputrename.py @@ -19,7 +19,7 @@ for entry in fasta: liftOver = json.load(open(sys.argv[2],'r')) jellyFasta = FastaFile(sys.argv[3]) -regex = re.compile("ref\d{7}") +regex = re.compile(r"ref\d{7}") for key in liftOver: myRefs = set() for id, strand, size in liftOver[key]: --- a/pbsuite/banana/MakeOverlapTable.py +++ b/pbsuite/banana/MakeOverlapTable.py @@ -7,7 +7,7 @@ from collections import deque from pbsuite.utils.setupLogging import * from pbsuite.jelly.Support import AlignmentConnector, SUPPORTFLAGS -subreadGrab = re.compile(".*/(\d+)_(\d+)$") +subreadGrab = re.compile(r".*/(\d+)_(\d+)$") def natural_sort(l): """ @@ -23,7 +23,7 @@ def natural_sort(l): class M4Line(): def __init__(self, line): - data = re.split("\s+",line) + data = re.split(r"\s+",line) self.qname = data[0] self.tname = data[1] --- a/pbsuite/banana/MakeReciprocal.py +++ b/pbsuite/banana/MakeReciprocal.py @@ -9,7 +9,7 @@ USAGE = """%prog Run this in the directory where you've made a whole bunch of alignment chunks. For any Chunk A that has been Mapped to B, we'll make the reciprocal of B mapped to A""" -subreadGrab = re.compile(".*/(\d+)_(\d+)$") +subreadGrab = re.compile(r".*/(\d+)_(\d+)$") class M4File(list): @@ -33,7 +33,7 @@ class M4File(list): class M4Line(): def __init__(self, line): - data = re.split("\s+",line) + data = re.split(r"\s+",line) self.qname = data[0] self.tname = data[1] --- a/pbsuite/banana/OLCAssembly.py +++ b/pbsuite/banana/OLCAssembly.py @@ -274,7 +274,7 @@ class OLCAssembly: fout.close() def splitIIDs(self, m): - _exe("grep iid alignments.overlaps_realigned | cut -f2 -d\: > internal.ids") + _exe(r"grep iid alignments.overlaps_realigned | cut -f2 -d\: > internal.ids") fh = open("internal.ids",'r') n = fh.readlines() fh.close() @@ -301,7 +301,7 @@ class OLCAssembly: TODO: Need to know the exception that's thrown when there are no contigOuts """ logging.info("Renaming Contigs") - getContigName = re.compile("(\d+)_contig") + getContigName = re.compile(r"(\d+)_contig") contigNames = {} bank = amos.AmosBank("out.bank") --- a/pbsuite/banana/chunkyBlasr.py +++ b/pbsuite/banana/chunkyBlasr.py @@ -120,7 +120,7 @@ class ChunkyBlasr(): for chunk in glob.glob(os.path.join(self.refDir, self.refBase+"*_chunk_*")): logging.info("Filtering out reads < 500bp from %s" % chunk) r, o, e = _exe(("fastalength {0} | " - "awk -F\ '{{if ($1 < 500) print $2}}' | " + r"awk -F\ '{{if ($1 < 500) print $2}}' | " "fastaremove {0} stdin > {0}.fasta").format(chunk)) logging.debug("RETCODE - %d\nSTDOUT - %s\nSTDERR - %s" %(r,str(o),str(e))) if r != 0: --- a/pbsuite/jelly/Setup.py +++ b/pbsuite/jelly/Setup.py @@ -13,7 +13,7 @@ If an exists bes we'll create and incorporate it into PBJelly. Otherwise, it is not necessary """ -refParser = re.compile("(.*)\|(ref\d{7})/?(\d+)?$") +refParser = re.compile(r"(.*)\|(ref\d{7})/?(\d+)?$") class Setup(): def __init__(self): --- a/pbsuite/jelly/Stages.py +++ b/pbsuite/jelly/Stages.py @@ -79,7 +79,7 @@ def mapping(jobDirs, outDir, reference, logging.warning("Output File %s already exists and will be overwritten." % (outFile)) #Build Blasr Command - nprocRe = re.compile("--nproc (\d+)") + nprocRe = re.compile(r"--nproc (\d+)") np = nprocRe.findall(parameters + extras) if len(np) == 0: np = '1' --- a/pbsuite/jelly/m4pie.py +++ b/pbsuite/jelly/m4pie.py @@ -14,7 +14,7 @@ WARNING! -- Input.bam should be produced """ def extractTails(aligns, reads, outFq, minLength=100): - """ + r""" 0x1 -- template has multiple segments in sequencing 0x40 -- first segment in template 0x80 -- last segment in template @@ -105,7 +105,7 @@ def uniteTails(origAligns, tailMapFn, ou prolog and eplog will only point to the primary and the primary will point to both """ - datGrab = re.compile("^(?P\d+)(?P[pe])(?P\d+)__(?P.*)$") + datGrab = re.compile(r"^(?P\d+)(?P[pe])(?P\d+)__(?P.*)$") aligns = M4File(tailMapFn) mode = 'a' if inplace else 'w' --- a/pbsuite/honey/Force.py +++ b/pbsuite/honey/Force.py @@ -520,7 +520,7 @@ def spotsSearch(bam, bed, args): return anyCoverage, ref, vars #Here are some helper methods for parsing force annotation results -forceRe = re.compile("(?PTrue|False|\?)\[(?P.*)\|(?P.*)\]") +forceRe = re.compile(r"(?PTrue|False|\?)\[(?P.*)\|(?P.*)\]") def parseForce(data): """ turns the force output into a dict --- a/pbsuite/honey/bampie.py +++ b/pbsuite/honey/bampie.py @@ -82,7 +82,7 @@ def callBlasr(inFile, refFile, params, n def extractTails(bam, outFq, minLength=100): - """ + r""" 0x1 -- template has multiple segments in sequencing 0x40 -- first segment in template 0x80 -- last segment in template @@ -163,7 +163,7 @@ def uniteTails(mappedFiles, outBam="mult prolog and eplog will only point to the primary and the primary will point to both """ - datGrab = re.compile("^(?P\d+)(?P[pe])(?P[01])(?P.*):(?P\d+)__(?P.*)$") + datGrab = re.compile(r"^(?P\d+)(?P[pe])(?P[01])(?P.*):(?P\d+)__(?P.*)$") bout = None for ibam, tbam in mappedFiles: sam = pysam.Samfile(tbam, 'r') --- a/pbsuite/jelly/Extraction.py +++ b/pbsuite/jelly/Extraction.py @@ -56,7 +56,7 @@ class Extraction(): """ Build a TrimInfo namedtuple for this read """ - getSub = re.compile("(.*)##(\d+)#(\d+)##$") + getSub = re.compile(r"(.*)##(\d+)#(\d+)##$") #Check for trims if readName.endswith('##'):#just endswith? not safe.. logging.debug("%s -- Missed Adapter" % readName) @@ -323,7 +323,7 @@ class Extraction(): selection is a dictionary of { readNames : True } for lookup I'm trying to speed up Extraction as much as possible """ - splRE = re.compile("\s+") + splRE = re.compile(r"\s+") fasta = FastaFile(fastaFn) qual = QualFile(qualFn, convert=False) logging.info("Selective loading from %d reads" % (len(list(fasta.values())))) --- a/pbsuite/honey/realign.py +++ b/pbsuite/honey/realign.py @@ -196,7 +196,7 @@ def expandMd(md): Turns abbreviated MD into a full array """ ret = [] - for i in re.findall("\d+|\^?[ATCGN]+", md): + for i in re.findall(r"\d+|\^?[ATCGN]+", md): if i.startswith('^'): ret.extend(list(i[1:])) elif i[0] in ["A","T","C","G","N"]: