def test1():
fields = (
["Andrew", "Dalke", "12"],
["Liz", "Nelson", "22"],
["Mandrake", "Moose", "23"],
["Lisa", "Marie", "91"],
)
text = ""
for line in fields:
text = text + string.join(line, " ") + "\n"
format = Martel.Rep1(
Martel.Group("line",
Martel.Word("name", {"type": "first"}) + \
Martel.Spaces() + \
Martel.Word("name", {"type": "last"}) + \
Martel.Spaces() + \
Martel.Integer("age") + \
Martel.AnyEol()
))
iterator = format.make_iterator("line")
i = 0
for record in iterator.iterateString(text, LAX.LAX()):
assert record["name"] == fields[i][:2], (record["name"], fields[i][:2])
assert record["age"] == fields[i][2:3], (record["age"], fields[i][2:3])
i = i + 1
i = 0
for record in iterator.iterateString(text, LAX.LAXAttrs()):
assert [x[0] for x in record["name"]] == fields[i][:2], \
([x[0] for x in record["name"]], fields[i][:2])
assert [x[0] for x in record["age"]] == fields[i][2:3], \
([x[0] for x in record["age"]], fields[i][2:3])
assert record["name"][0][1]["type"] == "first"
assert record["name"][1][1]["type"] == "last"
assert record["age"][0][1].keys() == []
i = i + 1
Martel.Str(tag + " ") + Martel.Group(tag_data, Martel.Re("[^\R]*")) +
Martel.AnyEol())
#--- ID
ID = Martel.Group("ID", Martel.Re(
r"ID (?P<entry_name>\w+) +(?P<data_class_table>\w+); +" \
r"(?P<molecule_type>\w+); +(?P<sequence_length>\d+) AA\.\R"
))
#--- AC
AC = Martel.Group(
"AC", Martel.Re(r"AC (?P<ac_number>\w+);( (?P<ac_number>\w+);)*\R"))
AC_block = Martel.Group("AC_block", Martel.Rep1(AC))
#--- DT
DT_created = Martel.Group("DT_created", Martel.Re(
r"DT (?P<day>\d\d)-(?P<month>...)-(?P<year>\d{4}) \(Rel. "\
r"(?P<release>\d\d), Created\)\R"
))
DT_seq_update = Martel.Group("DT_seq_update", Martel.Re(
r"DT (?P<day>\d\d)-(?P<month>...)-(?P<year>\d{4}) \(Rel. "\
r"(?P<release>\d\d), Last sequence update\)\R"
))
DT_ann_update = Martel.Group("DT_ann_update", Martel.Re(
r"DT (?P<day>\d\d)-(?P<month>...)-(?P<year>\d{4}) \(Rel. "\
r"(?P<release>\d\d), Last annotation update\)\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
from Martel import UntilSep
from Bio.NBRF.ValSeq import valid_sequence_dict
sequence_types = map(Str, valid_sequence_dict.keys())
sequence_type = Group("sequence_type", Alt(*sequence_types))
name_line = Martel.Group( "name_line", \
Str( ">" ) +
sequence_type +
Str( ";" ) +
UntilEol("sequence_name") +
AnyEol() )
comment_line = UntilEol("comment") + AnyEol()
# 0x2a -- '*'
# 10 -- '\n', 13 -- '\r' newline endings
excluded_chars = chr(0x2a) + chr(10) + chr(13)
# sequence lines with only sequence
sequence_text = Group( "sequence_text", \
Martel.Rep1( AnyBut( excluded_chars ) ) )
sequence_line = Group("sequence_line", sequence_text + AnyEol())
# the final line, has a '*' and potentially some sequence
sequence_final_line = Group(
"sequence_final_line",
UntilSep("sequence_final_text", chr(0x2a)) + Str(chr(0x2a)) +
Rep1(AnyEol()))
sequence_block = Group("sequence_block", Rep(sequence_line))
nbrf_record = name_line + comment_line + sequence_block + sequence_final_line
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)))