Mercurial > repos > urgi-team > teiso
diff TEisotools-1.1.a/commons/core/parsing/GffParser.py @ 16:836ce3d9d47a draft default tip
Uploaded
| author | urgi-team |
|---|---|
| date | Thu, 21 Jul 2016 07:42:47 -0400 |
| parents | 255c852351c5 |
| children |
line wrap: on
line diff
--- a/TEisotools-1.1.a/commons/core/parsing/GffParser.py Thu Jul 21 07:36:44 2016 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,149 +0,0 @@ -# -# Copyright INRA-URGI 2009-2010 -# -# This software is governed by the CeCILL license under French law and -# abiding by the rules of distribution of free software. You can use, -# modify and/ or redistribute the software under the terms of the CeCILL -# license as circulated by CEA, CNRS and INRIA at the following URL -# "http://www.cecill.info". -# -# As a counterpart to the access to the source code and rights to copy, -# modify and redistribute granted by the license, users are provided only -# with a limited warranty and the software's author, the holder of the -# economic rights, and the successive licensors have only limited -# liability. -# -# In this respect, the user's attention is drawn to the risks associated -# with loading, using, modifying and/or developing or reproducing the -# software by the user in light of its specific status of free software, -# that may mean that it is complicated to manipulate, and that also -# therefore means that it is reserved for developers and experienced -# professionals having in-depth computer knowledge. Users are therefore -# encouraged to load and test the software's suitability as regards their -# requirements in conditions enabling the security of their systems and/or -# data to be ensured and, more generally, to use and operate it in the -# same conditions as regards security. -# -# The fact that you are presently reading this means that you have had -# knowledge of the CeCILL license and that you accept its terms. -# -import re -import sys -from SMART.Java.Python.structure.Interval import Interval -from SMART.Java.Python.structure.Transcript import Transcript -from commons.core.parsing.TranscriptListParser import TranscriptListParser - - -class GffParser(TranscriptListParser): - """A class that parses a GFF file and create a transcript list""" - - - def __init__(self, fileName, verbosity = 0): - super(GffParser, self).__init__(fileName, verbosity) - - - def __del__(self): - super(GffParser, self).__del__() - - - def getFileFormats(): - return ["gff", "gff2", "gff3"] - getFileFormats = staticmethod(getFileFormats) - - - def skipFirstLines(self): - pass - - - def getInfos(self): - self.chromosomes = set() - self.nbTranscripts = 0 - self.size = 0 - self.reset() - if self.verbosity >= 10: - print "Getting information on %s." % (self.fileName) - self.reset() - for line in self.handle: - line = line.strip() - if line == "" or line[0] == "#": - continue - parts = line.split("\t") - if len(parts) != 9: - raise Exception("Error! Line '%s' has %d tab-separated fields instead of 9!" % (line, len(parts))) - self.chromosomes.add(parts[0]) - if parts[8].find("Parent") == -1: - self.nbTranscripts += 1 - else: - self.size += max(int(parts[3]), int(parts[4])) - min(int(parts[3]), int(parts[4])) + 1 - if self.verbosity >= 10 and self.nbTranscripts % 100000 == 0: - sys.stdout.write(" %d transcripts read\r" % (self.nbTranscripts)) - sys.stdout.flush() - self.reset() - if self.verbosity >= 10: - print " %d transcripts read" % (self.nbTranscripts) - print "Done." - - - def parseLine(self, line): - if not line or line[0] == "#": - return None - m = re.search(r"^\s*(\S+)\s+(\S+)\s+(\S+)\s+(\d+)\s+(\d+)\s+(\S+)\s+([+-.])\s+(\S+)\s+(\S.*)$", line) - if m == None: - raise Exception("\nLine %d '%s' does not have a GFF format\n" % (self.currentLineNb, line)) - interval = Interval() - interval.setChromosome(m.group(1)) - interval.setName("unnamed transcript") - interval.setStart(min(int(m.group(4)), int(m.group(5)))) - interval.setEnd(max(int(m.group(4)), int(m.group(5)))) - if m.group(7) == ".": - interval.setDirection("+") - else: - interval.setDirection(m.group(7)) - interval.setTagValue("feature", m.group(3)) - if m.group(6).isdigit(): - interval.setTagValue("score", m.group(6)) - - remainings = m.group(9).split(";") - for remaining in remainings: - remaining = remaining.strip() - if remaining == "": - continue - posSpace = remaining.find(" ") - posEqual = remaining.find("=") - if posEqual != -1 and (posEqual < posSpace or posSpace == -1): - parts = remaining.split("=") - else: - parts = remaining.split() - field = parts[0].strip() - value = " ".join(parts[1:]).strip(" \"") - if field in ("Name", "name", "Sequence", "TE", "SAT"): - interval.setName(value) - else: - try: - intValue = int(value) - interval.setTagValue(field, intValue) - except ValueError: - interval.setTagValue(field, value) - - self.currentTranscriptAddress = self.previousTranscriptAddress - if "Parent" in interval.getTagNames(): - if self.currentTranscript == None: - raise Exception("GFF file does not start with a transcript! First line is '%s'." % (line.strip())) - if interval.getTagValue("Parent") != self.currentTranscript.getTagValue("ID"): - raise Exception("Exon '%s' is not right after its transcript in GFF file!" % (interval)) - self.currentTranscript.addExon(interval) - if interval.name == None: - interval.name = self.currentTranscript.name - return None - - if interval is not None and interval.name.startswith("unnamed"): - if "ID" in interval.getTagNames(): - interval.name = interval.getTagValue("ID") - else: - interval.name = "unnamed transcript %s" % (self.currentLineNb) - - transcript = self.currentTranscript - self.currentTranscript = Transcript() - self.currentTranscript.copy(interval) - self.previousTranscriptAddress = self.currentAddress - return transcript
