td 0.10.52 → 0.10.53
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/ChangeLog +7 -0
- data/lib/td/command/bulk_import.rb +5 -2
- data/lib/td/file_reader.rb +26 -1
- data/lib/td/version.rb +1 -1
- metadata +2 -2
data/ChangeLog
CHANGED
@@ -1,4 +1,11 @@
|
|
1
1
|
|
2
|
+
== 2012-10-02 version 0.10.53
|
3
|
+
|
4
|
+
* bulk_import:prepare_parts works with Ruby 1.8
|
5
|
+
* bulk_import:prepare_parts supports 'msgpack' format
|
6
|
+
* bulk_import:prepare_parts supports gzip decompression
|
7
|
+
|
8
|
+
|
2
9
|
== 2012-09-26 version 0.10.52
|
3
10
|
|
4
11
|
* bulk_import:upload_parts subcommand supports --parallel option to upload
|
@@ -321,7 +321,10 @@ module Command
|
|
321
321
|
outdir = s
|
322
322
|
}
|
323
323
|
|
324
|
-
|
324
|
+
files = op.cmd_parse
|
325
|
+
|
326
|
+
# TODO ruby 1.9
|
327
|
+
files = [files] unless files.is_a?(Array)
|
325
328
|
|
326
329
|
unless outdir
|
327
330
|
$stderr.puts "-o, --output DIR option is required."
|
@@ -350,7 +353,7 @@ module Command
|
|
350
353
|
$stderr.puts "Processing #{ifname}..."
|
351
354
|
record_num = 0
|
352
355
|
|
353
|
-
basename = File.basename(ifname).split('.').
|
356
|
+
basename = File.basename(ifname).sub(/\.(?:csv|tsv|json|msgpack)(?:\.gz)?$/i,'').split('.').join('_')
|
354
357
|
File.open(ifname) {|io|
|
355
358
|
of_index = 0
|
356
359
|
out = nil
|
data/lib/td/file_reader.rb
CHANGED
@@ -1,6 +1,28 @@
|
|
1
1
|
|
2
2
|
module TreasureData
|
3
3
|
class FileReader
|
4
|
+
require 'zlib'
|
5
|
+
|
6
|
+
class DecompressIOFilter
|
7
|
+
def self.filter(io, error, opts)
|
8
|
+
case opts[:compress]
|
9
|
+
when 'gzip'
|
10
|
+
return Zlib::GzipReader.new(io)
|
11
|
+
when 'plain'
|
12
|
+
return io
|
13
|
+
when nil
|
14
|
+
data = io.read(2)
|
15
|
+
io.rewind
|
16
|
+
if data.unpack('CC') == [0x1f, 0x8b]
|
17
|
+
return Zlib::GzipReader.new(io)
|
18
|
+
else
|
19
|
+
return io
|
20
|
+
end
|
21
|
+
else
|
22
|
+
raise "unknown compression type #{opts[:compress]}"
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
4
26
|
|
5
27
|
class MessagePackParsingReader
|
6
28
|
def initialize(io, error, opts)
|
@@ -11,7 +33,7 @@ module TreasureData
|
|
11
33
|
end
|
12
34
|
|
13
35
|
def forward
|
14
|
-
@u.
|
36
|
+
@u.each {|r| break r }
|
15
37
|
end
|
16
38
|
end
|
17
39
|
|
@@ -313,6 +335,7 @@ module TreasureData
|
|
313
335
|
case @format
|
314
336
|
when 'text'
|
315
337
|
Proc.new {|io,error|
|
338
|
+
io = DecompressIOFilter.filter(io, error, opts)
|
316
339
|
reader = LineReader.new(io, error, opts)
|
317
340
|
parser = DelimiterParser.new(reader, error, opts)
|
318
341
|
if opts[:column_header]
|
@@ -337,6 +360,7 @@ module TreasureData
|
|
337
360
|
|
338
361
|
when 'json'
|
339
362
|
Proc.new {|io,error|
|
363
|
+
io = DecompressIOFilter.filter(io, error, opts)
|
340
364
|
reader = LineReader.new(io, error, opts)
|
341
365
|
parser = JSONParser.new(reader, error, opts)
|
342
366
|
if opts[:column_header]
|
@@ -356,6 +380,7 @@ module TreasureData
|
|
356
380
|
|
357
381
|
when 'msgpack'
|
358
382
|
Proc.new {|io,error|
|
383
|
+
io = DecompressIOFilter.filter(io, error, opts)
|
359
384
|
parser = MessagePackParsingReader.new(io, error, opts)
|
360
385
|
if opts[:column_header]
|
361
386
|
column_names = parser.forward
|
data/lib/td/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: td
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.10.
|
4
|
+
version: 0.10.53
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-
|
12
|
+
date: 2012-10-03 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: msgpack
|