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
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"
internal_oligo_seq = Martel.Group("internal_seq", sequence)
internal_line = Martel.Group(
"internal_line", primer_space + Martel.Str("INTERNAL OLIGO") + any_space +
internal_oligo_start + any_space + internal_oligo_length + any_space +
internal_oligo_tm + any_space + internal_oligo_gc + any_space +
internal_oligo_seq + Martel.AnyEol())
# XXX This record definition is ugly. But it works :-)
record = Martel.Group("primer3_record",
comments + \
Martel.Alt(
# case 1. primer file with nothing
Martel.Str("\n" * 3) +
Martel.Opt(Martel.Str("\n" * 4)),
# case 2. some primers have been picked
Martel.Rep(
# case 2a. we are designing a primer pair
Martel.Alt(blank_line + primer_start_line,
# case 2b. we are designing a single primer
single_primer_line) +
# case 2a. both primer pairs
Martel.Alt(forward_line + blank_line +
reverse_line + blank_line,
# case 2b1. Reverse primer
reverse_line + blank_line,
# case 2b2, Forward primer
forward_line + blank_line,
# case 2b3, Internal oligo
internal_line + blank_line)) +
blank_line + blank_line + Martel.Rep(blank_line)))
Martel.Opt(RT_block) + \
RL_block
)
############
#--- CC
CC_begin = Martel.Group("CC",
Martel.Re("CC -!- ") + \
Martel.ToEol("comment_text"))
CC = Martel.Group("CC",
Martel.Re("CC ") + \
Martel.ToEol("comment_text"))
single_comment = Martel.Group("comment", CC_begin + Martel.Rep(CC))
CC_copyright_begin = Martel.Group("CC_copyright_begin", Martel.Re("CC -+\R"))
CC_copyright = Martel.Group("CC_copyright",
Martel.Re("CC (?!-+\R)") + \
Martel.ToEol("copyright"))
CC_copyright_end = Martel.Group("CC_copyright_end", Martel.Re("CC -+\R"))
# From N33_HUMAN
bogus_DR_group = Martel.Group("bogus_DR_block",
Martel.Re(r"(?P<DR>DR (?P<database_identifier>MIM); " \
r"(?P<primary_identifier>601385); " \
r"(?P<secondary_identifier>-).\R)")
)
# 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
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
amplifier_length = Martel.Group("amplifier_length", Martel.Re("[\d]+"))
amplifier_length_line = seq_indent + Martel.Str("Amplimer length: ") + \
amplifier_length + Martel.Str(" bp") + \
Martel.AnyEol()
record = Martel.Group(
"primersearch_record",
Martel.Rep1(blank_line + primer_name_line +
Martel.Rep(amplimer_line + amplifier_sequence_lines +
amplifier_length_line)))
