1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
|
# 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.
"""Code for more fancy file handles.
Classes:
Filtered is a decorator for File that allows the user to filter the output
on a line by line basis.
The FilteredReader module reads a file and applies a sequence of filters to the input
The constructor sets a default filter chain, but the user can select another filter by setting
Bio.FilteredReader.filter_chain.
handle = open( "filename" )
filtered_reader = Bio.FilteredReader( handle )
filtered_reader.filter_chain = [ remove_asterisks, replace_dot_with_dash ]
filtered_reasder.read()
All filters in the chain must provide the same interface with a line of text as the single
input parameter and altered text as the return value.
"""
import os
import string
import copy
from File import UndoHandle
"""Used for debugging"""
def dump_saved( name, text, j ):
dump_file = open( name + '%d' % j, "w" )
k = 0
for i in range ( 0, len( text ), 80 ):
dump_file.write( '%s\n' % text[ i : i + 80 ] )
dump_file.close()
def remove_leading_whitespace( line ):
return line.lstrip()
def remove_empty_line( line ):
stripped_line = line.strip()
if( stripped_line ):
return line[ : ]
else:
return ''
def remove_useless_dot( line ):
before = line
while( 1 ):
after = before.replace( "\t.\t", "\t\t" )
if( len( before ) == len( after ) ):
break
before = after
if( after.endswith( '.' ) ):
after = after[ :-1 ]
return after
def fix_punctuation( line ):
line = line.replace( "'", '' )
line = line.replace( '"', '' )
line = line.replace( ';', '\t' )
line = line.replace( 'entryname', 'id' )
# line = line.lower( )
if( line ):
return line[ : ]
else:
return ''
class FilteredReader:
def __init__(self, handle ):
self._handle = handle
self._start_line = ''
self._debug_count = 0
self.filter_chain = [ remove_empty_line, remove_useless_dot, fix_punctuation ]
def __getattr__(self, attr):
return getattr(self._handle, attr)
def close(self, *args, **keywds ):
return self._handle.close( *args, **keywds)
def read( self, *args, **keywds ):
line = ''
len_expected = self._get_len_expected( args, keywds )
if( len_expected ):
filtered_text = self.read_block( len_expected )
else:
filtered_text = self.read_to_end()
return filtered_text
def read_block( self, len_expected ):
len_filtered = 0
len_adjusted = len_expected - len( self._start_line )
filtered_text = ''
while( len_filtered < len_expected ):
text_read = self._handle.read( len_adjusted )
full_text = self._start_line + text_read
lines = full_text.splitlines( 1 )
if( text_read == '' ):
filtered_text = filtered_text + self.filter( lines )
break
else:
all_but_last_line = lines[ :-1 ]
self._start_line = lines[ -1 ]
filtered_text = filtered_text + self.filter( all_but_last_line )
len_filtered_text = len( filtered_text )
len_adjusted = len_adjusted - len_filtered_text
return filtered_text[ : ]
def read_to_end( self ):
filtered_text = ''
text_read = self._handle.read()
full_text = self._start_line + text_read
lines = full_text.splitlines( 1 )
filtered_text = filtered_text + self.filter( lines[:] )
return filtered_text[ : ]
def _get_len_expected( self, args, keywds ):
if( len( args) > 0 ):
len_expected = args[ 0 ]
if( len_expected < 0 ):
len_expected = None
elif( keywds.has_key( 'size' ) ):
len_expected = keywds[ 'size' ]
else:
len_expected = None
return len_expected
def filter( self, lines ):
filter_chain = self.filter_chain
filtered_text = ''
for line in lines:
for filter in filter_chain:
line = filter( *( line, ) )
filtered_text = filtered_text + line
return filtered_text
def has_trailing_linefeed( line ):
if( line.endswith( chr( 13 ) ) or \
line.endswith( chr( 10 ) ) ):
return 1
else:
return 0
|
