This repository was archived by the owner on Mar 27, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathPipeline.pm
More file actions
288 lines (243 loc) · 6.01 KB
/
Copy pathPipeline.pm
File metadata and controls
288 lines (243 loc) · 6.01 KB
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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
=head1 NAME
Pipeline - Pipelines for map, filters processes.
=head1 SYNOPSIS
reduce(
fileSource( $ARGV[0] ),
pipeline(
step { decode_json $_ },
step { $_->{name} },
bufferedStep { my @v = sort { $a cmp $b } @$_; \@v } 50,
filter { /^A/ },
step { $_ =~ s/^A/E/g; $_ },
),
fileSink( $ARGV[1] )
);
=head1 DESCRIPTION
Toolbox for data processing using MAP and REDUCE paradigm. Includes helper methods
for defining filters...
=over 4
=item mongoSource( $host, $dbName, $collName, $findParams )
Creates a data source using a MongoDB query cursor
=item fileSource( $filename )
Creates a data source for a file and reads it line by line.
=item step { CODE }
A step in the pipeline.
=item bufferedStep { CODE }
A step in the pipeline.
=item filter {CODE}
Adds a filter to the pipeline.
=item pipeline( \&step1, \&step2, ... )
Defines a data source and a set of transformations. Can be passed as
a datasource to another pipeline.
=item reduce( $src, $pipe, $acc )
Processes stream from pipeline to accumulator function.
=back
=head2 AUTHOR
Shawn Tan, shawn@semantics3.com
=cut
package Pipeline;
use strict;
use warnings FATAL => 'uninitialized';
use lib('/usr/local/lib/perl/');
use Data::Dumper;
use JSON::XS;
use Carp ();
use Time::HiRes qw( usleep );
$SIG{__DIE__} = \&Carp::confess;
binmode STDOUT, ':utf8';
select( ( select( STDOUT ), $| = 1 )[0] );
binmode STDIN, ':utf8';
binmode STDERR, ':utf8';
use Exporter;
our @ISA= qw( Exporter );
our @EXPORT = qw(
mongoSource
step
bufferedStep
filter
pipeline
reduce
fileSource
fileSink
);
our @EXPORT_OK = qw();
#----------------------------------------------------------------------
# fileSource( $filename )
#----------------------------------------------------------------------
#
# Creates a data source for a file and reads it line by line.
#
#----------------------------------------------------------------------
sub fileSource {
my ( $filename ) = @_;
my $filePointer;
return sub {
if ( !defined( $filePointer ) ) {
eval {
open( $filePointer, "< $filename" );
};
if ( $@ ) {
die { end_of_stream => "Error opening '$filename'" };
}
}
if( my $line = <$filePointer> ) {
return $line;
} else {
print "FILE END.\n";
close( $filePointer );
die { end_of_stream => "End of '$filename'" };
}
}
}
#----------------------------------------------------------------------
# fileSink( $filename )
#----------------------------------------------------------------------
#
# Creates a data sink for a file and writes to it line by line.
#
#----------------------------------------------------------------------
sub fileSink {
my ( $filename ) = @_;
my $filePointer;
return sub {
my ( $line ) = @_;
if ( scalar( @_ ) == 0 ) { close( $filePointer ); }
else {
if ( !defined( $filePointer ) ) {
eval {
open( $filePointer, "> $filename" );
};
if ( $@ ) {
die { end_of_stream => "Error opening '$filename'" };
}
}
print $filePointer $line."\n";
}
}
}
#----------------------------------------------------------------------
# step { CODE }
#----------------------------------------------------------------------
#
# A step in the pipeline.
#
#----------------------------------------------------------------------
sub step (&) {
my $code = \&{shift @_};
return sub {
my ( $iter ) = @_;
return sub {
local $_ = $iter->();
return &$code( $_ );
};
}
}
#----------------------------------------------------------------------
# bufferedStep { CODE }
#----------------------------------------------------------------------
#
# A step in the pipeline.
#
#----------------------------------------------------------------------
sub bufferedStep {
my $bufferSize = shift @_;
my $code = \&{shift @_};
my $inBuffer = [];
my $outBuffer = [];
my $ended;
return sub {
my ( $iter ) = @_;
return sub {
if ( scalar( @$outBuffer ) == 0 ) {
if ( !defined( $ended ) ) {
# eval {
# fill buffer
while( scalar( @$inBuffer ) < $bufferSize ) {
push( @$inBuffer, $iter->() );
}
# };
if ( my $err = $@ ) {
if ( ref( $err ) eq 'HASH' && ( my $info = $err->{end_of_stream} ) ) {
$ended = $err;
}
}
#transform
local $_ = $inBuffer;
$outBuffer = &$code( $_ );
$inBuffer = [];
} else {
die $ended;
}
}
# outbuffer definitely has stuff.
my $data = shift @$outBuffer;
return $data;
};
}
}
#----------------------------------------------------------------------
# filter {CODE}
#----------------------------------------------------------------------
#
# Adds a filter to the pipeline.
#
#----------------------------------------------------------------------
sub filter (&) {
my $code = \&{shift @_};
return sub {
my ( $iter ) = @_;
return sub {
while( 1 ) {
local $_ = $iter->();
if ( &$code( $_ ) ){
return $_ ;
} else {
# print "REMOVED\n";
}
}
};
}
}
#----------------------------------------------------------------------
# pipeline( \&step1, \&step2, ... )
#----------------------------------------------------------------------
#
# Defines a data source and a set of transformations. Can be passed as
# a datasource to another pipeline.
#
#----------------------------------------------------------------------
sub pipeline {
my $steps = \@_;
return sub {
my ( $sourceIter ) = @_;
my $currIter = $sourceIter;
foreach my $step ( @$steps ) { $currIter = &$step( $currIter ); }
return $currIter;
}
}
#----------------------------------------------------------------------
# reduce( $src, $pipe, $acc )
#----------------------------------------------------------------------
#
# Processes stream from pipeline to accumulator function.
#
#----------------------------------------------------------------------
sub reduce {
my ( $src, $pipe, $acc ) = @_;
my $stream = &$pipe( $src );
eval {
while ( 1 ) {
my $item = $stream->();
$acc->( $item );
}
};
if ( my $err = $@ ) {
if ( ref( $err ) eq 'HASH' && ( my $info = $err->{end_of_stream} ) ) {
} else {
print "STREAM ERROR: \n";
print Dumper $err;
}
}
return $acc->();
}
1;