Ejemplo n.º 1
0
def delimiter(delim):
    assert len(delim) == 1, \
           "delimiter can only be a single character long, not %s" % repr(delim)
    assert delim not in "\n\r", "Cannot use %s as a delimiter" % repr(delim)

    field = Martel.Group("field", Martel.Rep(Martel.AnyBut(delim + "\r\n")))

    line = field + Martel.Rep(Martel.Str(delim) + field) + Martel.AnyEol()
    record = Martel.Group("record", line)

    format = Martel.ParseRecords("delimited", {}, record,
                                 RecordReader.CountLines, (1, ))
    return format
Ejemplo n.º 2
0
def test_reader_parser():
    record = Martel.Group("start", Martel.Rep(Martel.Str("abc"))) + \
             Martel.Group("end", Martel.Rep(Martel.Str("xyz")))
    parser = record.make_parser()

    parser = Parser.Parser(parser.tagtable)
    parser.setErrorHandler(handler.ErrorHandler())

    parser.parseString("abc" * 10 + "xyz")

    try:
        parser.parseString("abc" * 10 + "xyzQ")
    except Parser.ParserPositionException:
        pass
    else:
        raise AssertionError, "didn't get a position exception"

    try:
        parser.parseString("abc" * 10 + "x")
    except Parser.ParserPositionException:
        pass
    else:
        raise AssertionError, "didn't get a position exception"
Ejemplo n.º 3
0
def test_record_parser():
    record = Martel.Group("A", Martel.Str("X\n") + Martel.Re("a*\n"))
    p = record.make_parser()

    parser = Parser.RecordParser("blah", {}, p.tagtable, (0, 1, {}),
                                 RecordReader.StartsWith, ("X", ))

    err = CountErrors()
    parser.setErrorHandler(err)
    count = CountRecords("A")
    parser.setContentHandler(count)

    parser.parseString("X\na\nX\nb\nX\naaa\nX\naaaa\nX\nq\nX\na\n")

    assert err.fatal_error_count == 0, err.fatal_error_count
    assert err.error_count == 2, err.error_count
    assert count.count == 4, count.count
Ejemplo n.º 4
0
"""Martel definitions for the output files produced by primer3.
"""
import Martel

any_space = Martel.Re("[ ]+")
blank_line = Martel.AnyEol()

comment_line = Martel.Str("#") + Martel.ToEol()

# comments and blank lines in the file
comments = Martel.Group("comments",
                        blank_line + comment_line + blank_line + comment_line)

#   1 PRODUCT SIZE: 289
product_size = Martel.Group("product_size", Martel.Re("[\d]+"))
start_primer = Martel.Group(
    "start_primer",
    any_space + Martel.Re("[\d]+") + Martel.Str(" PRODUCT SIZE: "))
primer_start_line = Martel.Group("primer_start_line",
                                 start_primer + product_size + Martel.AnyEol())

# a blank line that signifies a new primer is coming up
single_primer_line = Martel.Group("single_primer_line", blank_line)

#      FORWARD PRIMER    1725   20  59.96  55.00  AGGGAAGGGATGCTAGGTGT
primer_space = Martel.Str(" " * 5)

any_integer = Martel.Re("[\d]+")
any_float = Martel.Re("[\d\.]+")
sequence = Martel.Re("[GATCN]+")
Ejemplo n.º 5
0
def Simple(tag, tag_data):
    return Martel.Group(
        tag,
        Martel.Str(tag + "   ") + Martel.Group(tag_data, Martel.Re("[^\R]*")) +
        Martel.AnyEol())
Ejemplo n.º 6
0
DR_general = Martel.Re("(?P<database_identifier>[^;]+);" \
                       "(?P<primary_identifier>[^;]+); " \
                       "(?P<secondary_identifier>([^.\R]|(?!.\R)\.)+)")

DR_prosite = Martel.Re("(?P<database_identifier>(PROSITE|PFAM)); " \
                       "(?P<primary_identifier>[^;]+); " \
                       "(?P<secondary_identifier>[^;]+); " \
                       "(?P<status_identifier>[^.]+)")

DR_embl = Martel.Re("(?P<database_identifier>EMBL); " \
                    "(?P<primary_identifier>[^;]+); " \
                    "(?P<secondary_identifier>[^;]+); " \
                    "(?P<status_identifier>[^.]+)")

DR = Martel.Group("DR", Martel.Str("DR   ") + \
           Martel.Group("database_reference",
                        Martel.Alt(DR_embl, DR_prosite, DR_general)) + \
           Martel.Str(".") + Martel.AnyEol())

DR_block = Martel.Group("DR_block", Martel.Rep1(DR))

#--- KW

KW = Simple("KW", "keyword")
KW_block = Martel.Group("KW_block", Martel.Rep1(KW))

#--- FT

# FT   DOMAIN       77     88       ASP/GLU-RICH (ACIDIC).
# 123456789012345678901234567890123456789012345678901234567890123456789012345
Ejemplo n.º 7
0
# Copyright 2001 by Katharine Lindner.  All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license.  Please see the LICENSE file that should have been included
# as part of this package.
"""Martel regular expression for Intelligenetic format (DEPRECATED).

This is a huge regular regular expression for the IntelliGenetics/MASE format,
built using the 'regular expressions on steroids' capabilities of Martel.
"""
#http://immuno.bme.nwu.edu/seqhunt.html

# Martel
import Martel

# --- first set up some helper constants and functions
comment_line = Martel.Group( "comment_line", \
                             Martel.Str( ';' ) +
                             Martel.ToEol( "comment" ) )
comment_lines = Martel.Group("comment_lines", Martel.Rep(comment_line))
title_line = Martel.Group( "title_line", \
    Martel.Expression.Assert( Martel.Str( ';' ), 1 ) +
    Martel.ToEol() )
residue_line = Martel.Group( "residue_line", \
    Martel.Expression.Assert( Martel.Str( ';' ), 1 ) +
    Martel.ToEol( "sequence" ) )
residue_lines = Martel.Group("residue_lines", Martel.Rep1(residue_line))
intelligenetics_record = comment_lines + title_line + residue_lines
Ejemplo n.º 8
0
def test_single():
    ele = get_element(
        Martel.Group("spam", Martel.Str("X"), {"format": "swissprot"}))
    check_element(ele, ("spam", {"format": "swissprot"}))
Ejemplo n.º 9
0
def test_none():
    ele = get_element(Martel.Group("spam", Martel.Str("X")))
    check_element(ele, ("spam", {}))

    ele = get_element(Martel.Group("spam", Martel.Str("X"), {}))
    check_element(ele, ("spam", {}))
Ejemplo n.º 10
0
"""Example of registering a database with the Biopython-specific system.
"""
from Bio.sources import CGI
local_cgi = CGI(name = "local_cgi",
                delay = 0.0,
                cgi = "http://www.myserver.org/cgi-bin/my_local.cgi",
                url = "http://www.myserver.org/cgi_documentation.html",
                doc = "Query a local databases",
                failure_cases = [])

import Martel
my_failures = [
     (Martel.Str("Sequence not available"), "No sequence found")]

from Bio import register_db
register_db(name = "nucleotide-genbank-local",
            key = "uid",
            source = local_cgi,
            failure = my_failures)

register_db(name = "genbank", behavior = "concurrent")
from Bio import group_db
group_db("genbank", "nucleotide-genbank-local")
group_db("genbank", "nucleotide-genbank-cgi")

from Bio import db
print db.keys()
Ejemplo n.º 11
0
"""Martel format for primersearch output files,
"""
import Martel

blank_line = Martel.AnyEol()

# Primer name D1S2660
primer_name = Martel.Group("primer_name", Martel.ToEol())
primer_name_line = Martel.Str("Primer name ") + primer_name

# Amplimer 1
amplifier = Martel.Group("amplifier", Martel.Re("[\d]+"))
amplimer_line = Martel.Str("Amplimer ") + amplifier + Martel.AnyEol()

# Sequence: AC074298 AC074298
# Telomere associated sequence for Arabidopsis thaliana TEL1N
# CCGGTTTCTCTGGTTGAAAA hits forward strand at 114 with 0 mismatches
# TCACATTCCCAAATGTAGATCG hits reverse strand at [114] with 0 mismatches
seq_indent = Martel.Str("\t")

sequence_id = Martel.Group("sequence_id", Martel.ToEol())
sequence_descr = Martel.Group("sequence_descr", Martel.ToEol())
sequence_info = sequence_id + sequence_descr
forward_strand_info = Martel.Group("forward_strand_info", Martel.ToEol())
reverse_strand_info = Martel.Group("reverse_strand_info", Martel.ToEol())
amplifier_sequence = Martel.Group(
    "amplifier_sequence",
    sequence_info + forward_strand_info + reverse_strand_info)
amplifier_sequence_lines = seq_indent + Martel.Str("Sequence: ") + \
                           amplifier_sequence