csv_separator_detector 0.1.0
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 +7 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/.travis.yml +6 -0
- data/Gemfile +4 -0
- data/README.md +42 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/csv_separator_detector.gemspec +25 -0
- data/lib/csv_separator_detector.rb +49 -0
- data/lib/csv_separator_detector/version.rb +3 -0
- metadata +96 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 3fb3aafd4be7410864b3da814faf00fcdbfab984
|
4
|
+
data.tar.gz: c25146c943306ee463a6068e111637579fdf44b3
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 32111c5a1b813bf7a25c9a61dce58b82cb8f830dd0dfabbe64dc5268b40e8c387f7c5ea831e03081553b95784680308cf7d5cfdd68bcfeb7c54cfd2f503f1ec4
|
7
|
+
data.tar.gz: a36d8bef9a4ebe54d2ccce9432a191c7f427482a78457ba785e790531545d95c03ce3791b4fc3c1a206cd0ad7534d5e3866ea193d621ae9223700d2b05c3cce9
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,42 @@
|
|
1
|
+
# CsvSeparatorDetector
|
2
|
+
|
3
|
+

|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'csv_separator_detector'
|
11
|
+
```
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install csv_separator_detector
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
``` ruby
|
24
|
+
begin
|
25
|
+
content = File.read('/path/to/csv.file')
|
26
|
+
separator = CsvSeparatorDetector.new(content).call # => ';'
|
27
|
+
rescue CsvSeparatorDetector::Error
|
28
|
+
# we couldn't reliably determine separator.
|
29
|
+
end
|
30
|
+
```
|
31
|
+
|
32
|
+
## Explanation
|
33
|
+
|
34
|
+
This class knows a few common csv delimiters and tries to parse given content using them
|
35
|
+
(by passing each delimiter as `col_sep` option to `CSV` from stdlib). Then it tries to make
|
36
|
+
sense of the result. All rows turned out to be just one column wide? That's likely because
|
37
|
+
we used comma separator and the file is tab-delimited.
|
38
|
+
|
39
|
+
## Contributing
|
40
|
+
|
41
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/stulentsev/csv_separator_detector.
|
42
|
+
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "csv_separator_detector"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start
|
data/bin/setup
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'csv_separator_detector/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "csv_separator_detector"
|
8
|
+
spec.version = CsvSeparatorDetector::VERSION
|
9
|
+
spec.authors = ["Sergio Tulentsev"]
|
10
|
+
spec.email = ["sergei.tulentsev@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Detect separators in CSV content}
|
13
|
+
spec.homepage = "https://github.com/stulentsev/csv_separator_detector"
|
14
|
+
|
15
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
16
|
+
f.match(%r{^(test|spec|features)/})
|
17
|
+
end
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.13"
|
23
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
24
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
25
|
+
end
|
@@ -0,0 +1,49 @@
|
|
1
|
+
require "csv_separator_detector/version"
|
2
|
+
require 'csv'
|
3
|
+
|
4
|
+
class CsvSeparatorDetector
|
5
|
+
class Error < StandardError;
|
6
|
+
end
|
7
|
+
|
8
|
+
attr_reader :csv_text
|
9
|
+
|
10
|
+
def initialize(csv_text)
|
11
|
+
@csv_text = csv_text
|
12
|
+
end
|
13
|
+
|
14
|
+
def call
|
15
|
+
separator_with_most_columns or fail CsvSeparatorDetector::Error
|
16
|
+
end
|
17
|
+
|
18
|
+
def supported_separators
|
19
|
+
[',', ';', "\t", '|']
|
20
|
+
end
|
21
|
+
|
22
|
+
private
|
23
|
+
|
24
|
+
# when two separators are equally good (produce the same amount of columns),
|
25
|
+
# return neither of them.
|
26
|
+
def separator_with_most_columns
|
27
|
+
counts = count_columns_for_separators
|
28
|
+
|
29
|
+
top_separators = counts.max_by(&:first).last
|
30
|
+
top_separators.first if top_separators.length == 1
|
31
|
+
end
|
32
|
+
|
33
|
+
# returns
|
34
|
+
# {
|
35
|
+
# 2 => [',', ';'],
|
36
|
+
# 0 => ['\t']
|
37
|
+
# }
|
38
|
+
def count_columns_for_separators
|
39
|
+
supported_separators.each_with_object({}) do |sep, memo|
|
40
|
+
begin
|
41
|
+
columns = ::CSV.parse_line(csv_text, col_sep: sep)
|
42
|
+
memo[columns.length] ||= []
|
43
|
+
memo[columns.length] << sep
|
44
|
+
rescue ::CSV::MalformedCSVError
|
45
|
+
# do nothing
|
46
|
+
end
|
47
|
+
end
|
48
|
+
end
|
49
|
+
end
|
metadata
ADDED
@@ -0,0 +1,96 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: csv_separator_detector
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Sergio Tulentsev
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2017-04-30 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.13'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.13'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '3.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '3.0'
|
55
|
+
description:
|
56
|
+
email:
|
57
|
+
- sergei.tulentsev@gmail.com
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- ".gitignore"
|
63
|
+
- ".rspec"
|
64
|
+
- ".travis.yml"
|
65
|
+
- Gemfile
|
66
|
+
- README.md
|
67
|
+
- Rakefile
|
68
|
+
- bin/console
|
69
|
+
- bin/setup
|
70
|
+
- csv_separator_detector.gemspec
|
71
|
+
- lib/csv_separator_detector.rb
|
72
|
+
- lib/csv_separator_detector/version.rb
|
73
|
+
homepage: https://github.com/stulentsev/csv_separator_detector
|
74
|
+
licenses: []
|
75
|
+
metadata: {}
|
76
|
+
post_install_message:
|
77
|
+
rdoc_options: []
|
78
|
+
require_paths:
|
79
|
+
- lib
|
80
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
81
|
+
requirements:
|
82
|
+
- - ">="
|
83
|
+
- !ruby/object:Gem::Version
|
84
|
+
version: '0'
|
85
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
requirements: []
|
91
|
+
rubyforge_project:
|
92
|
+
rubygems_version: 2.6.11
|
93
|
+
signing_key:
|
94
|
+
specification_version: 4
|
95
|
+
summary: Detect separators in CSV content
|
96
|
+
test_files: []
|