pseudo_date 0.2.0 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/Gemfile.lock +4 -7
- data/lib/core_extensions/string.rb +2 -2
- data/lib/pseudo_date/parser.rb +99 -94
- data/lib/pseudo_date/version.rb +1 -1
- data/pseudo_date.gemspec +2 -3
- data/spec/spec_helper.rb +1 -2
- metadata +8 -23
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
|
-
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
2
|
+
SHA256:
|
3
|
+
metadata.gz: 194f7ad213e4723e13dadd0bb7e4808b0e7d078d96302f27e67c926a471740a7
|
4
|
+
data.tar.gz: 5924349cb3530554acc4778d3983351afecb4f22a413906555259b3a70a008b8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 6af99fbd3a7e1a14c4e0966e145e60abd25242b9bc127e24304134eee90a35c66224878da002fb8f7e168d61065cdf22b7ed99c4ab56d3e134d13e7ef56e9a1f
|
7
|
+
data.tar.gz: f18fde6cdade727c95c9768a713a664dc4842a80afc8e4d464c2c44d02d78d30b4cf83930a0359b22f03772f2f9a464ed79227844995412ee8ee27024277161c
|
data/Gemfile.lock
CHANGED
@@ -1,16 +1,11 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
pseudo_date (0.
|
4
|
+
pseudo_date (0.2.0)
|
5
5
|
|
6
6
|
GEM
|
7
7
|
remote: https://rubygems.org/
|
8
8
|
specs:
|
9
|
-
byebug (3.1.2)
|
10
|
-
columnize (~> 0.8)
|
11
|
-
debugger-linecache (~> 1.2)
|
12
|
-
columnize (0.8.9)
|
13
|
-
debugger-linecache (1.2.0)
|
14
9
|
diff-lcs (1.2.5)
|
15
10
|
rspec (3.0.0)
|
16
11
|
rspec-core (~> 3.0.0)
|
@@ -29,6 +24,8 @@ PLATFORMS
|
|
29
24
|
ruby
|
30
25
|
|
31
26
|
DEPENDENCIES
|
32
|
-
byebug
|
33
27
|
pseudo_date!
|
34
28
|
rspec
|
29
|
+
|
30
|
+
BUNDLED WITH
|
31
|
+
2.1.4
|
data/lib/pseudo_date/parser.rb
CHANGED
@@ -1,110 +1,115 @@
|
|
1
1
|
require 'date'
|
2
|
-
|
2
|
+
require_relative 'pseudo_date'
|
3
|
+
|
4
|
+
class PseudoDate
|
5
|
+
class Parser
|
3
6
|
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
def self.parse(input)
|
8
|
-
date_hash = {}
|
9
|
-
# Minor Pre Cleanup
|
10
|
-
input.strip!; input.gsub!('~','')
|
11
|
-
|
12
|
-
date = parse_with_poro_date(input)
|
13
|
-
|
14
|
-
if date
|
15
|
-
date_hash = { :year => date.year.to_s, :month => date.month.to_s, :day => date.day.to_s }
|
16
|
-
else
|
17
|
-
year, month, day = parse_string(input)
|
18
|
-
date_hash = { :year => year, :month => month, :day => day }
|
19
|
-
end
|
7
|
+
AMERICAN_DATE_FORMAT = '%m/%d/%Y'
|
8
|
+
EUROPEAN_DATE_FORMAT = '%Y-%m-%d'
|
20
9
|
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
10
|
+
def self.parse(input)
|
11
|
+
date_hash = {}
|
12
|
+
# Minor Pre Cleanup
|
13
|
+
input.strip!; input.gsub!('~','')
|
14
|
+
|
15
|
+
date = parse_with_poro_date(input)
|
16
|
+
|
17
|
+
if date
|
18
|
+
date_hash = { :year => date.year.to_s, :month => date.month.to_s, :day => date.day.to_s }
|
25
19
|
else
|
26
|
-
|
20
|
+
year, month, day = parse_string(input)
|
21
|
+
date_hash = { :year => year, :month => month, :day => day }
|
27
22
|
end
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
23
|
+
|
24
|
+
# Post parsing cleanup
|
25
|
+
date_hash.each do |key, value|
|
26
|
+
date_hash[key] = if value.nil?
|
27
|
+
key.to_s == 'year' ? '0000' : '00'
|
28
|
+
else
|
29
|
+
date_hash[key] = value.to_s.strip
|
30
|
+
end
|
34
31
|
end
|
32
|
+
|
33
|
+
# Cleanup the single digit values
|
34
|
+
unless date_hash.empty?
|
35
|
+
date_hash.each do |key,value|
|
36
|
+
date_hash[key] = "0#{value}" if value.to_s.length == 1
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
# Two character years
|
41
|
+
if date_hash[:year].length == 2
|
42
|
+
date_hash[:year] = date_hash[:year].to_i > Date.today.year.to_s.slice(2..4).to_i ? "19#{date_hash[:year]}" : "20#{date_hash[:year]}"
|
43
|
+
end
|
44
|
+
|
45
|
+
# Attempt to correct some known OCR issues
|
46
|
+
if date_hash[:year].to_s.match('00') && date_hash[:year] != '0000'
|
47
|
+
date_hash[:year] = "2#{date_hash[:year].slice(1..3)}"
|
48
|
+
end
|
49
|
+
|
50
|
+
return date_hash.empty? ? nil : date_hash
|
35
51
|
end
|
36
52
|
|
37
|
-
|
38
|
-
if date_hash[:year].length == 2
|
39
|
-
date_hash[:year] = date_hash[:year].to_i > Date.today.year.to_s.slice(2..4).to_i ? "19#{date_hash[:year]}" : "20#{date_hash[:year]}"
|
40
|
-
end
|
41
|
-
|
42
|
-
# Attempt to correct some known OCR issues
|
43
|
-
if date_hash[:year].to_s.match('00') && date_hash[:year] != '0000'
|
44
|
-
date_hash[:year] = "2#{date_hash[:year].slice(1..3)}"
|
45
|
-
end
|
53
|
+
private
|
46
54
|
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
when /\// # Americans usually use a / to separate date pieces
|
59
|
-
Date.strptime(string, AMERICAN_DATE_FORMAT)
|
55
|
+
def self.parse_with_poro_date(string)
|
56
|
+
# If our date has 3 parts then let's try to parse it with Date::strptime
|
57
|
+
if string.split(/\/|-/).length < 3
|
58
|
+
case string
|
59
|
+
when /-/ # Europeans generally use hyphens to separate date pieces
|
60
|
+
Date.strptime(string, EUROPEAN_DATE_FORMAT)
|
61
|
+
when /\// # Americans usually use a / to separate date pieces
|
62
|
+
Date.strptime(string, AMERICAN_DATE_FORMAT)
|
63
|
+
end
|
64
|
+
else
|
65
|
+
nil # Not enough parts so just return nil
|
60
66
|
end
|
61
|
-
|
62
|
-
nil #
|
67
|
+
rescue
|
68
|
+
nil # We don't actually care why Date is complaining. We'll fall back to slower parsing later.
|
63
69
|
end
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
month,
|
70
|
+
|
71
|
+
def self.parse_string(input)
|
72
|
+
day, month, year = "00", "00", "0000"
|
73
|
+
if input.match('/') # 02/25/2008
|
74
|
+
date_array = input.split('/')
|
75
|
+
if date_array.length == 3
|
76
|
+
begin
|
77
|
+
parsed_date = Date.parse(self)
|
78
|
+
month, day, year = parsed_date.month, parsed_date.day, parsed_date.year
|
79
|
+
rescue
|
80
|
+
month, day, year = date_array
|
81
|
+
end
|
82
|
+
elsif date_array.length == 2
|
83
|
+
month, year = date_array
|
78
84
|
end
|
79
|
-
elsif
|
80
|
-
month,
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
month =
|
93
|
-
day = date_array[1]
|
85
|
+
elsif input.length == 8 && is_numeric?(input) # 20080225
|
86
|
+
year, month, day = input.slice(0..3), input.slice(4..5), input.slice(6..7)
|
87
|
+
elsif input.match('-') # 1985-09-25 or 02-25-2008
|
88
|
+
date_array = input.split('-')
|
89
|
+
year = date_array.select{ |part| part.length == 4 }.first
|
90
|
+
unless year.nil? || date_array.length != 3
|
91
|
+
if date_array.first == year
|
92
|
+
month = date_array.last
|
93
|
+
day = date_array[1]
|
94
|
+
else
|
95
|
+
month = date_array.first
|
96
|
+
day = date_array[1]
|
97
|
+
end
|
98
|
+
month, day = [day, month] if month.to_i > 12 && month.to_i > day.to_i
|
94
99
|
end
|
95
|
-
|
100
|
+
elsif input.length == 4 # 2004
|
101
|
+
year = input.to_s
|
102
|
+
elsif input.length == 2 # 85
|
103
|
+
year = (input.to_i > Date.today.year.to_s.slice(2..4).to_i) ? "19#{input}" : "20#{input}"
|
104
|
+
elsif input.match(/\w/) # Jun 23, 2004
|
105
|
+
begin
|
106
|
+
d = Date.parse(input)
|
107
|
+
year, month, day = d.year.to_s, d.month.to_s, d.day.to_s
|
108
|
+
rescue; end
|
96
109
|
end
|
97
|
-
|
98
|
-
year = input.to_s
|
99
|
-
elsif input.length == 2 # 85
|
100
|
-
year = (input.to_i > Date.today.year.to_s.slice(2..4).to_i) ? "19#{input}" : "20#{input}"
|
101
|
-
elsif input.match(/\w/) # Jun 23, 2004
|
102
|
-
begin
|
103
|
-
d = Date.parse(input)
|
104
|
-
year, month, day = d.year.to_s, d.month.to_s, d.day.to_s
|
105
|
-
rescue; end
|
110
|
+
return [year, month, day]
|
106
111
|
end
|
107
|
-
|
112
|
+
|
108
113
|
end
|
109
|
-
|
110
|
-
end
|
114
|
+
|
115
|
+
end
|
data/lib/pseudo_date/version.rb
CHANGED
data/pseudo_date.gemspec
CHANGED
@@ -17,7 +17,6 @@ Gem::Specification.new do |gem|
|
|
17
17
|
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
18
|
gem.require_paths = ["lib"]
|
19
19
|
gem.license = 'MIT'
|
20
|
-
|
21
|
-
gem.add_development_dependency("rspec"
|
22
|
-
gem.add_development_dependency("byebug", "~> 0")
|
20
|
+
|
21
|
+
gem.add_development_dependency("rspec")
|
23
22
|
end
|
data/spec/spec_helper.rb
CHANGED
metadata
CHANGED
@@ -1,41 +1,27 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: pseudo_date
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Patrick Tulskie
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2022-06-09 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rspec
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - "
|
17
|
+
- - ">="
|
18
18
|
- !ruby/object:Gem::Version
|
19
19
|
version: '0'
|
20
20
|
type: :development
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - "
|
25
|
-
- !ruby/object:Gem::Version
|
26
|
-
version: '0'
|
27
|
-
- !ruby/object:Gem::Dependency
|
28
|
-
name: byebug
|
29
|
-
requirement: !ruby/object:Gem::Requirement
|
30
|
-
requirements:
|
31
|
-
- - "~>"
|
32
|
-
- !ruby/object:Gem::Version
|
33
|
-
version: '0'
|
34
|
-
type: :development
|
35
|
-
prerelease: false
|
36
|
-
version_requirements: !ruby/object:Gem::Requirement
|
37
|
-
requirements:
|
38
|
-
- - "~>"
|
24
|
+
- - ">="
|
39
25
|
- !ruby/object:Gem::Version
|
40
26
|
version: '0'
|
41
27
|
description: Date parser and container for partial or incomplete dates.
|
@@ -66,7 +52,7 @@ homepage: http://github.com/PatrickTulskie/pseudo_date
|
|
66
52
|
licenses:
|
67
53
|
- MIT
|
68
54
|
metadata: {}
|
69
|
-
post_install_message:
|
55
|
+
post_install_message:
|
70
56
|
rdoc_options: []
|
71
57
|
require_paths:
|
72
58
|
- lib
|
@@ -81,9 +67,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
81
67
|
- !ruby/object:Gem::Version
|
82
68
|
version: '0'
|
83
69
|
requirements: []
|
84
|
-
|
85
|
-
|
86
|
-
signing_key:
|
70
|
+
rubygems_version: 3.2.3
|
71
|
+
signing_key:
|
87
72
|
specification_version: 4
|
88
73
|
summary: Date parser and container for partial or incomplete dates.
|
89
74
|
test_files:
|