csv-utils 0.2.3 → 0.3.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/bin/csv-validator +77 -0
- data/csv-utils.gemspec +1 -1
- data/lib/csv-utils.rb +2 -0
- data/lib/csv_utils/csv_extender.rb +13 -26
- data/lib/csv_utils/csv_transformer.rb +119 -0
- data/lib/csv_utils/csv_wrapper.rb +47 -0
- metadata +6 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8e649e8e220856a0676e01ef58811ab9df3822a1757eae4e776a45256063c510
|
4
|
+
data.tar.gz: fad8bcac595659bc5d91b4ebc19ee8f18ebbdf910568e75ff812768e1c23515f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 4e4a26c3494c466a0099f72db534b8bd73910444c6eadf1b1faa78213d225b6752e9e8b60818bbeabe57f4542bd235da1969a9b6a3bad968328622531f89f077
|
7
|
+
data.tar.gz: d35d7a46f4f58a0fe87e10c6bcfec3ededc840d5d3c7ce0f1e5162e22f6f9ddb1516ed23a59b93877529ae326d597dfbde5089d9676393d488e476f6a9ad0924
|
data/bin/csv-validator
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'csv'
|
4
|
+
begin
|
5
|
+
require 'rchardet'
|
6
|
+
rescue LoadError
|
7
|
+
$stderr.puts 'gem install rchardet'
|
8
|
+
exit 1
|
9
|
+
end
|
10
|
+
|
11
|
+
def utf8?(str)
|
12
|
+
str
|
13
|
+
.force_encoding('utf-8')
|
14
|
+
.valid_encoding?
|
15
|
+
end
|
16
|
+
|
17
|
+
def convert_to_utf8(str, current_encoding)
|
18
|
+
str.force_encoding(current_encoding)
|
19
|
+
return nil unless str.valid_encoding?
|
20
|
+
|
21
|
+
str.encode('utf-8')
|
22
|
+
end
|
23
|
+
|
24
|
+
def detect_encoding(col)
|
25
|
+
CharDet.detect(col)['encoding']
|
26
|
+
end
|
27
|
+
|
28
|
+
def strip_bom!(col)
|
29
|
+
col.sub!("\xEF\xBB\xBF".force_encoding('ASCII-8BIT'), '')
|
30
|
+
end
|
31
|
+
|
32
|
+
csv = CSV.open(ARGV[0], 'rb')
|
33
|
+
id_column_name = ARGV[1]
|
34
|
+
|
35
|
+
headers = csv.shift
|
36
|
+
strip_bom!(headers[0])
|
37
|
+
|
38
|
+
id_column_num = nil
|
39
|
+
if id_column_name
|
40
|
+
unless headers.include?(id_column_name)
|
41
|
+
$stderr.puts("header #{id_column_name} not found in current set of headers")
|
42
|
+
exit 1
|
43
|
+
end
|
44
|
+
|
45
|
+
id_column_num = headers.index(id_column_name)
|
46
|
+
end
|
47
|
+
|
48
|
+
out = nil
|
49
|
+
if id_column_num
|
50
|
+
out = CSV.open('utf8-correctsion.csv', 'wb')
|
51
|
+
out << [id_column_name, 'Row', 'Col', 'Header', 'Value']
|
52
|
+
end
|
53
|
+
|
54
|
+
csv_lineno = 1
|
55
|
+
|
56
|
+
while (row = csv.shift)
|
57
|
+
csv_lineno += 1
|
58
|
+
|
59
|
+
unless row.size == headers.size
|
60
|
+
$stderr.puts "row(#{csv_lineno}): invalid number of columns, expected #{headers.size} got #{row.size}"
|
61
|
+
end
|
62
|
+
|
63
|
+
row.each_with_index do |col, idx|
|
64
|
+
next if utf8?(col)
|
65
|
+
|
66
|
+
$stderr.puts "row(#{csv_lineno}),col(#{idx + 1}) #{headers[idx]}: none UTF-8 characters found in \"#{col}\""
|
67
|
+
if (col_utf8_encoded = convert_to_utf8(col, detect_encoding(col)))
|
68
|
+
puts "row(#{csv_lineno}),col(#{idx + 1}) #{headers[idx]}: converted to UTF-8 from #{detect_encoding(col)} \"#{col_utf8_encoded}\""
|
69
|
+
out << [row[id_column_num], csv_lineno, (idx + 1), headers[idx], col_utf8_encoded]
|
70
|
+
else
|
71
|
+
$stderr.puts "row(#{csv_lineno}),col(#{idx + 1}) #{headers[idx]}: unknown character encoding"
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
csv.close
|
77
|
+
out.close if out
|
data/csv-utils.gemspec
CHANGED
data/lib/csv-utils.rb
CHANGED
@@ -1,20 +1,15 @@
|
|
1
1
|
# Utility class for appending data to a csv file.
|
2
2
|
class CSVUtils::CSVExtender
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
def initialize(csv_file, new_csv_file, csv_options = {})
|
8
|
-
@csv_file = csv_file
|
9
|
-
@new_csv_file = new_csv_file
|
10
|
-
@csv_options = csv_options
|
3
|
+
def initialize(src_csv, dest_csv, csv_options = {})
|
4
|
+
@src_csv = CSVUtils::CSVWrapper.new(src_csv, 'rb', csv_options)
|
5
|
+
@dest_csv = CSVUtils::CSVWrapper.new(dest_csv, 'wb', csv_options)
|
11
6
|
end
|
12
7
|
|
13
8
|
def append(additional_headers)
|
14
9
|
process(additional_headers) do |current_headers|
|
15
|
-
while (row =
|
10
|
+
while (row = @src_csv.shift)
|
16
11
|
additional_columns = yield row, current_headers
|
17
|
-
|
12
|
+
@dest_csv << (row + additional_columns)
|
18
13
|
end
|
19
14
|
end
|
20
15
|
end
|
@@ -27,13 +22,13 @@ class CSVUtils::CSVExtender
|
|
27
22
|
additional_rows = yield batch, current_headers
|
28
23
|
|
29
24
|
batch.each_with_index do |row, idx|
|
30
|
-
|
25
|
+
@dest_csv << (row + additional_rows[idx])
|
31
26
|
end
|
32
27
|
|
33
28
|
batch = []
|
34
29
|
end
|
35
30
|
|
36
|
-
while (row =
|
31
|
+
while (row = @src_csv.shift)
|
37
32
|
batch << row
|
38
33
|
|
39
34
|
process_batch_proc.call if batch.size >= batch_size
|
@@ -43,6 +38,8 @@ class CSVUtils::CSVExtender
|
|
43
38
|
end
|
44
39
|
end
|
45
40
|
|
41
|
+
private
|
42
|
+
|
46
43
|
def process(additional_headers)
|
47
44
|
current_headers = append_headers(additional_headers)
|
48
45
|
|
@@ -51,26 +48,16 @@ class CSVUtils::CSVExtender
|
|
51
48
|
close
|
52
49
|
end
|
53
50
|
|
54
|
-
def src
|
55
|
-
@src ||= CSV.open(csv_file, 'rb', csv_options)
|
56
|
-
end
|
57
|
-
|
58
|
-
def dest
|
59
|
-
@dest ||= CSV.open(new_csv_file, 'wb', csv_options)
|
60
|
-
end
|
61
|
-
|
62
51
|
def close
|
63
|
-
|
64
|
-
|
52
|
+
@src_csv.close
|
53
|
+
@dest_csv.close
|
65
54
|
end
|
66
55
|
|
67
|
-
private
|
68
|
-
|
69
56
|
def append_headers(additional_headers)
|
70
57
|
return nil unless additional_headers
|
71
58
|
|
72
|
-
current_headers =
|
73
|
-
|
59
|
+
current_headers = @src_csv.shift
|
60
|
+
@dest_csv << (current_headers + additional_headers)
|
74
61
|
current_headers
|
75
62
|
end
|
76
63
|
end
|
@@ -0,0 +1,119 @@
|
|
1
|
+
# Transforms a CSV given a series of steps
|
2
|
+
class CSVUtils::CSVTransformer
|
3
|
+
attr_reader :headers
|
4
|
+
|
5
|
+
def initialize(src_csv, dest_csv, csv_options = {})
|
6
|
+
@src_csv = CSVUtils::CSVWrapper.new(src_csv, 'rb', csv_options)
|
7
|
+
@dest_csv = CSVUtils::CSVWrapper.new(dest_csv, 'wb', csv_options)
|
8
|
+
end
|
9
|
+
|
10
|
+
def read_headers
|
11
|
+
@headers = @src_csv.shift
|
12
|
+
self
|
13
|
+
end
|
14
|
+
|
15
|
+
def additional_data(&block)
|
16
|
+
steps << [:additional_data, @headers, block]
|
17
|
+
self
|
18
|
+
end
|
19
|
+
|
20
|
+
def select(&block)
|
21
|
+
steps << [:select, @headers, block]
|
22
|
+
self
|
23
|
+
end
|
24
|
+
|
25
|
+
def reject(&block)
|
26
|
+
steps << [:reject, @headers, block]
|
27
|
+
self
|
28
|
+
end
|
29
|
+
|
30
|
+
def map(new_headers, &block)
|
31
|
+
steps << [:map, @headers, block]
|
32
|
+
@headers = new_headers
|
33
|
+
self
|
34
|
+
end
|
35
|
+
|
36
|
+
def append(additional_headers, &block)
|
37
|
+
steps << [:append, @headers, block]
|
38
|
+
|
39
|
+
if additional_headers
|
40
|
+
@headers += additional_headers
|
41
|
+
else
|
42
|
+
@headers = nil
|
43
|
+
end
|
44
|
+
|
45
|
+
self
|
46
|
+
end
|
47
|
+
|
48
|
+
def each(&block)
|
49
|
+
steps << [:each, @headers, block]
|
50
|
+
self
|
51
|
+
end
|
52
|
+
|
53
|
+
def set_headers(headers)
|
54
|
+
@headers = headers
|
55
|
+
self
|
56
|
+
end
|
57
|
+
|
58
|
+
def process(batch_size = 10_000, &block)
|
59
|
+
batch = []
|
60
|
+
|
61
|
+
@dest_csv << @headers if @headers
|
62
|
+
|
63
|
+
steps_proc = Proc.new do
|
64
|
+
steps.each do |step_type, current_headers, proc|
|
65
|
+
batch = process_step(step_type, current_headers, batch, &proc)
|
66
|
+
end
|
67
|
+
|
68
|
+
batch.each { |row| @dest_csv << row }
|
69
|
+
|
70
|
+
batch = []
|
71
|
+
end
|
72
|
+
|
73
|
+
while (row = @src_csv.shift)
|
74
|
+
batch << row
|
75
|
+
steps_proc.call if batch.size >= batch_size
|
76
|
+
end
|
77
|
+
|
78
|
+
steps_proc.call if batch.size > 0
|
79
|
+
|
80
|
+
@src_csv.close
|
81
|
+
@dest_csv.close
|
82
|
+
end
|
83
|
+
|
84
|
+
private
|
85
|
+
|
86
|
+
def steps
|
87
|
+
@steps ||= []
|
88
|
+
end
|
89
|
+
|
90
|
+
|
91
|
+
def process_step(step_type, current_headers, batch, &block)
|
92
|
+
case step_type
|
93
|
+
when :select
|
94
|
+
batch.select! do |row|
|
95
|
+
block.call row, current_headers, @additional_data
|
96
|
+
end
|
97
|
+
when :reject
|
98
|
+
batch.reject! do |row|
|
99
|
+
block.call row, current_headers, @additional_data
|
100
|
+
end
|
101
|
+
when :map
|
102
|
+
batch.map! do |row|
|
103
|
+
block.call row, current_headers, @additional_data
|
104
|
+
end
|
105
|
+
when :append
|
106
|
+
batch.map! do |row|
|
107
|
+
row + block.call(row, current_headers, @additional_data)
|
108
|
+
end
|
109
|
+
when :additional_data
|
110
|
+
@additional_data = block.call(batch, current_headers)
|
111
|
+
when :each
|
112
|
+
batch.each do |row|
|
113
|
+
block.call(row, current_headers, @additional_data)
|
114
|
+
end
|
115
|
+
end
|
116
|
+
|
117
|
+
batch
|
118
|
+
end
|
119
|
+
end
|
@@ -0,0 +1,47 @@
|
|
1
|
+
# Wraps a CSV object, if wrapper opens the csv file it will close it
|
2
|
+
class CSVUtils::CSVWrapper
|
3
|
+
attr_reader :csv
|
4
|
+
|
5
|
+
def initialize(csv, mode, csv_options)
|
6
|
+
open(csv, mode, csv_options)
|
7
|
+
end
|
8
|
+
|
9
|
+
def self.open(file, mode, csv_options = {})
|
10
|
+
csv = new(file, mode, csv_options)
|
11
|
+
|
12
|
+
if block_given?
|
13
|
+
yield csv
|
14
|
+
csv.close
|
15
|
+
else
|
16
|
+
csv
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def open(csv, mode, csv_options)
|
21
|
+
if csv.is_a?(String)
|
22
|
+
@close_when_done = true
|
23
|
+
@csv = CSV.open(csv, mode, csv_options)
|
24
|
+
else
|
25
|
+
@close_when_done = false
|
26
|
+
@csv = csv
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def <<(row)
|
31
|
+
csv << row
|
32
|
+
end
|
33
|
+
|
34
|
+
def shift
|
35
|
+
csv.shift
|
36
|
+
end
|
37
|
+
|
38
|
+
def close
|
39
|
+
csv.close if close_when_done?
|
40
|
+
end
|
41
|
+
|
42
|
+
private
|
43
|
+
|
44
|
+
def close_when_done?
|
45
|
+
@close_when_done
|
46
|
+
end
|
47
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: csv-utils
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.4
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Doug Youch
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2020-07-
|
11
|
+
date: 2020-07-20 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: inheritance-helper
|
@@ -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
|
@@ -50,6 +52,8 @@ files:
|
|
50
52
|
- lib/csv_utils/csv_report.rb
|
51
53
|
- lib/csv_utils/csv_row.rb
|
52
54
|
- lib/csv_utils/csv_sort.rb
|
55
|
+
- lib/csv_utils/csv_transformer.rb
|
56
|
+
- lib/csv_utils/csv_wrapper.rb
|
53
57
|
- script/console
|
54
58
|
homepage: https://github.com/dougyouch/csv-utils
|
55
59
|
licenses:
|