csv-utils 0.3.0 → 0.3.1
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/bin/csv-validator +47 -0
- data/csv-utils.gemspec +1 -1
- metadata +3 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: '019dcd269f036bc21e93019e567e8a0223d8436e87c56519d74af02383640bdf'
|
|
4
|
+
data.tar.gz: 34b4e8035a533e897c395943e892de0bae16fbdc3847a4990cc0281225d21bd4
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e770276baa097fa30551266882910818f331890c6e9bfd7fa92ab01654826a14ad3b67f151f2ce858c816d6d628170174fcc872038636998c15c818dc129130a
|
|
7
|
+
data.tar.gz: a1689e7404f5d9b70f092b7cda83c8f200df0af1725d27ecc222d798bafcbb1ea1612cbff74dbef493fe427a12ff8330f7828ed608becb4a3d3cd7267179319e
|
data/bin/csv-validator
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
1
|
+
#!/usr/bin/env ruby
|
|
2
|
+
|
|
3
|
+
require 'csv'
|
|
4
|
+
require 'rchardet'
|
|
5
|
+
|
|
6
|
+
def utf8?(str)
|
|
7
|
+
str
|
|
8
|
+
.force_encoding('utf-8')
|
|
9
|
+
.valid_encoding?
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
def convert_to_utf8(str, current_encoding)
|
|
13
|
+
str.force_encoding(current_encoding)
|
|
14
|
+
return nil unless str.valid_encoding?
|
|
15
|
+
|
|
16
|
+
str.encode('utf-8')
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
def detect_encoding(col)
|
|
20
|
+
CharDet.detect(col)['encoding']
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
csv = CSV.open(ARGV[0], 'rb')
|
|
24
|
+
|
|
25
|
+
headers = csv.shift
|
|
26
|
+
csv_lineno = 1
|
|
27
|
+
|
|
28
|
+
while (row = csv.shift)
|
|
29
|
+
csv_lineno += 1
|
|
30
|
+
|
|
31
|
+
unless row.size == headers.size
|
|
32
|
+
$stderr.puts "row(#{csv_lineno}): invalid number of columns, expected #{headers.size} got #{row.size}"
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
row.each_with_index do |col, idx|
|
|
36
|
+
next if utf8?(col)
|
|
37
|
+
|
|
38
|
+
$stderr.puts "row(#{csv_lineno}),col(#{idx + 1}): none UTF-8 characters found in \"#{col}\""
|
|
39
|
+
if (col_utf8_encoded = convert_to_utf8(col, detect_encoding(col)))
|
|
40
|
+
puts "row(#{csv_lineno}),col(#{idx + 1}): converted to UTF-8 from #{detect_encoding(col)} \"#{col_utf8_encoded}\""
|
|
41
|
+
else
|
|
42
|
+
$stderr.puts "row(#{csv_lineno}),col(#{idx + 1}): unknown character encoding"
|
|
43
|
+
end
|
|
44
|
+
end
|
|
45
|
+
end
|
|
46
|
+
|
|
47
|
+
csv.close
|
data/csv-utils.gemspec
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: csv-utils
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.3.
|
|
4
|
+
version: 0.3.1
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Doug Youch
|
|
@@ -30,6 +30,7 @@ executables:
|
|
|
30
30
|
- csv-change-eol
|
|
31
31
|
- csv-find-error
|
|
32
32
|
- csv-readline
|
|
33
|
+
- csv-validator
|
|
33
34
|
extensions: []
|
|
34
35
|
extra_rdoc_files: []
|
|
35
36
|
files:
|
|
@@ -43,6 +44,7 @@ files:
|
|
|
43
44
|
- bin/csv-change-eol
|
|
44
45
|
- bin/csv-find-error
|
|
45
46
|
- bin/csv-readline
|
|
47
|
+
- bin/csv-validator
|
|
46
48
|
- csv-utils.gemspec
|
|
47
49
|
- lib/csv-utils.rb
|
|
48
50
|
- lib/csv_utils/csv_extender.rb
|