blz 0.2.0.20181203 → 0.2.0.20190603
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.
- checksums.yaml +4 -4
- data/CHANGELOG.md +5 -0
- data/Gemfile +1 -0
- data/blz.gemspec +1 -1
- data/data/2019_06_03.tsv.gz +0 -0
- data/scripts/fetch.rb +25 -15
- metadata +3 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b10c9a3ddad85875050f3f6aed75714a09692a95
|
4
|
+
data.tar.gz: 971d1fa6f38e48ec43fc90a7571f8f473383ef45
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 14a2e5ffcbddf0c97d0431517a82effa37e9bc824be630cfb84f23ee82b1459b4c08ff9aac740a529a4327afd3c5f007259c2f892b6fdc95a44d3ad8e0486b78
|
7
|
+
data.tar.gz: 5cb61246b47a9903f788b175da47233474e9e2ac82f025098cd1aadc93e72817d743e271787a266e9e678164607a0f393fd12c0436a82175b704d9e2c82e7b9e
|
data/CHANGELOG.md
CHANGED
data/Gemfile
CHANGED
data/blz.gemspec
CHANGED
Binary file
|
data/scripts/fetch.rb
CHANGED
@@ -3,6 +3,7 @@
|
|
3
3
|
require "mechanize"
|
4
4
|
require "logger"
|
5
5
|
require "zlib"
|
6
|
+
require "zip"
|
6
7
|
|
7
8
|
if (f = File.expand_path("~/.extranet")) && File.exist?(f)
|
8
9
|
username, password = File.read(f).strip.split(":", 2)
|
@@ -44,9 +45,10 @@ begin
|
|
44
45
|
sleep 1
|
45
46
|
page = agent.get NAVIGATION[:table]
|
46
47
|
|
47
|
-
target_link = page.links
|
48
|
-
!!(link.text.strip =~ /BLZ_\d{8}.
|
49
|
-
|
48
|
+
target_link = page.links
|
49
|
+
.select {|link| !!(link.text.strip =~ /BLZ_\d{8}.zip/) }
|
50
|
+
.sort_by {|link| link.text.strip }
|
51
|
+
.last
|
50
52
|
|
51
53
|
if !target_link
|
52
54
|
logger.info("no new download found")
|
@@ -54,7 +56,7 @@ begin
|
|
54
56
|
end
|
55
57
|
|
56
58
|
name = target_link.text.strip
|
57
|
-
if name == format("BLZ_%4d%02d%02d.
|
59
|
+
if name == format("BLZ_%4d%02d%02d.zip", last_match[:y].to_i, last_match[:m].to_i, last_match[:d].to_i)
|
58
60
|
logger.info("no matching link found")
|
59
61
|
exit 0
|
60
62
|
end
|
@@ -63,21 +65,29 @@ begin
|
|
63
65
|
sleep 1
|
64
66
|
blz = agent.get(target_link.href)
|
65
67
|
|
66
|
-
name_match = name.match(/BLZ_(?<y>\d{4})(?<m>\d\d)(?<d>\d\d)\.
|
68
|
+
name_match = name.match(/BLZ_(?<y>\d{4})(?<m>\d\d)(?<d>\d\d)\.zip$/)
|
67
69
|
target_name = format("../data/%4d_%02d_%02d.tsv.gz", name_match[:y].to_i, name_match[:m].to_i, name_match[:d].to_i)
|
68
70
|
target_file = File.expand_path(target_name, __dir__)
|
69
71
|
|
70
|
-
logger.info("
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
72
|
+
logger.info("extracting ZIP file")
|
73
|
+
Zip::File.open_buffer(blz.body).each do |entry|
|
74
|
+
next unless entry.name == "BLZ.txt"
|
75
|
+
logger.info("found BLZ data")
|
76
|
+
|
77
|
+
entry.get_input_stream do |stream|
|
78
|
+
logger.info("reformatting, saving as #{target_file}")
|
79
|
+
Zlib::GzipWriter.open(target_file, Zlib::BEST_COMPRESSION) do |gz|
|
80
|
+
while line = stream.gets
|
81
|
+
line = line.encode(Encoding::UTF_8, Encoding::ISO_8859_15).chomp!
|
82
|
+
if line.length != METRIC_LEN
|
83
|
+
logger.error("expected line length #{METRIC_LEN}, got #{line.length} in '#{line}'")
|
84
|
+
next
|
85
|
+
end
|
86
|
+
|
87
|
+
i = 0
|
88
|
+
gz.puts METRIC.inject([]) {|s, m| s << line[i ... (i+=m)].strip }.join("\t")
|
89
|
+
end
|
77
90
|
end
|
78
|
-
|
79
|
-
i = 0
|
80
|
-
gz.puts METRIC.inject([]) {|s, m| s << line[i ... (i+=m)].strip }.join("\t")
|
81
91
|
end
|
82
92
|
end
|
83
93
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: blz
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.0.
|
4
|
+
version: 0.2.0.20190603
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Oliver Eilhard
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date:
|
12
|
+
date: 2019-05-03 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: bundler
|
@@ -87,6 +87,7 @@ files:
|
|
87
87
|
- data/2018_06_04.tsv.gz
|
88
88
|
- data/2018_09_03.tsv.gz
|
89
89
|
- data/2018_12_03.tsv.gz
|
90
|
+
- data/2019_06_03.tsv.gz
|
90
91
|
- lib/blz.rb
|
91
92
|
- lib/blz/bank.rb
|
92
93
|
- scripts/Makefile
|