csvpp 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.gitlab-ci.yml +13 -0
- data/.ruby-version +1 -0
- data/.travis.yml +5 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +51 -0
- data/LICENSE.txt +21 -0
- data/README.md +47 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/config.ru +4 -0
- data/csvpp.gemspec +42 -0
- data/exe/csvpp +29 -0
- data/lib/csvpp/api.rb +25 -0
- data/lib/csvpp/conversions.rb +102 -0
- data/lib/csvpp/format.rb +126 -0
- data/lib/csvpp/parser.rb +162 -0
- data/lib/csvpp/version.rb +3 -0
- data/lib/csvpp.rb +49 -0
- data/ui/.gitignore +21 -0
- data/ui/README.md +2229 -0
- data/ui/package.json +19 -0
- data/ui/public/favicon.ico +0 -0
- data/ui/public/index.html +40 -0
- data/ui/public/manifest.json +15 -0
- data/ui/src/App.css +7 -0
- data/ui/src/App.js +105 -0
- data/ui/src/App.test.js +8 -0
- data/ui/src/Editor.js +20 -0
- data/ui/src/index.css +5 -0
- data/ui/src/index.js +8 -0
- data/ui/src/logo.svg +7 -0
- data/ui/src/registerServiceWorker.js +108 -0
- data/ui/yarn.lock +6642 -0
- metadata +192 -0
data/lib/csvpp/parser.rb
ADDED
@@ -0,0 +1,162 @@
|
|
1
|
+
module CSVPP
|
2
|
+
class Parser
|
3
|
+
include Conversions
|
4
|
+
|
5
|
+
attr_reader :format, :col_sep
|
6
|
+
|
7
|
+
# @param input [String] path to input file
|
8
|
+
# @param format [Format]
|
9
|
+
# @param col_sep [String]
|
10
|
+
#
|
11
|
+
# @return [Array<Object>]
|
12
|
+
def self.parse(input:,
|
13
|
+
format:,
|
14
|
+
col_sep: DEFAULT_COL_SEP,
|
15
|
+
convert_type: true,
|
16
|
+
&block)
|
17
|
+
|
18
|
+
new(
|
19
|
+
format: format,
|
20
|
+
col_sep: col_sep,
|
21
|
+
convert_type: convert_type,
|
22
|
+
).parse(input, &block)
|
23
|
+
end
|
24
|
+
|
25
|
+
# @param input [String] input string
|
26
|
+
# @param format [Format]
|
27
|
+
# @param col_sep [String]
|
28
|
+
#
|
29
|
+
# @return [Array<Object>]
|
30
|
+
def self.parse_str(input:,
|
31
|
+
format:,
|
32
|
+
col_sep: DEFAULT_COL_SEP,
|
33
|
+
convert_type: true,
|
34
|
+
&block)
|
35
|
+
|
36
|
+
new(
|
37
|
+
format: format,
|
38
|
+
col_sep: col_sep,
|
39
|
+
convert_type: convert_type,
|
40
|
+
).parse_str(input, &block)
|
41
|
+
end
|
42
|
+
|
43
|
+
def initialize(format:, col_sep: DEFAULT_COL_SEP, convert_type: true)
|
44
|
+
@format = format
|
45
|
+
@col_sep = col_sep
|
46
|
+
@convert_type = convert_type
|
47
|
+
end
|
48
|
+
|
49
|
+
def convert_type?
|
50
|
+
!!@convert_type
|
51
|
+
end
|
52
|
+
|
53
|
+
def parse(path, &block)
|
54
|
+
parse_io(File.open(path), &block)
|
55
|
+
end
|
56
|
+
|
57
|
+
def parse_str(str, &block)
|
58
|
+
parse_io(str, &block)
|
59
|
+
end
|
60
|
+
|
61
|
+
def multiline?
|
62
|
+
format.multiline?
|
63
|
+
end
|
64
|
+
|
65
|
+
private
|
66
|
+
|
67
|
+
def set_value!(hash, var, value)
|
68
|
+
hash[var] = value
|
69
|
+
|
70
|
+
if convert_type?
|
71
|
+
type = format.type(var)
|
72
|
+
return if type.nil?
|
73
|
+
|
74
|
+
hash[var] = convert(value,
|
75
|
+
to: type,
|
76
|
+
missings: format.missings(var),
|
77
|
+
true_values: format.true_values(var),
|
78
|
+
false_values: format.false_values(var))
|
79
|
+
end
|
80
|
+
end
|
81
|
+
|
82
|
+
def add_result!(results, hash, &block)
|
83
|
+
if block_given? && (obj = block.call(hash))
|
84
|
+
results << obj
|
85
|
+
else
|
86
|
+
results << hash
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
def parse_io(io, &block)
|
91
|
+
return parse_multiline(io, &block) if multiline?
|
92
|
+
|
93
|
+
results = []
|
94
|
+
|
95
|
+
each_line_with_index(io) do |line, index|
|
96
|
+
line_number = index + 1
|
97
|
+
columns = line.split(col_sep, -1)
|
98
|
+
|
99
|
+
hash = {}
|
100
|
+
format.var_names.each do |var|
|
101
|
+
hash["line_number"] = line_number
|
102
|
+
|
103
|
+
index = format.index(var)
|
104
|
+
value = columns[index].strip
|
105
|
+
set_value!(hash, var, value)
|
106
|
+
end
|
107
|
+
|
108
|
+
add_result!(results, hash, &block)
|
109
|
+
end
|
110
|
+
|
111
|
+
results
|
112
|
+
end
|
113
|
+
|
114
|
+
def parse_multiline(io, &block)
|
115
|
+
results = []
|
116
|
+
hash = nil
|
117
|
+
|
118
|
+
each_line_with_index(io) do |line, index|
|
119
|
+
line_number = index + 1
|
120
|
+
columns = line.split(col_sep, -1)
|
121
|
+
line_id = columns[0]
|
122
|
+
|
123
|
+
# If we reach a start of a group...
|
124
|
+
if multiline_start?(line_id)
|
125
|
+
# ...yield the previous group...
|
126
|
+
add_result!(results, hash, &block) if hash
|
127
|
+
|
128
|
+
# ...and start building a new one.
|
129
|
+
hash = {}
|
130
|
+
hash["line_number"] = line_number
|
131
|
+
end
|
132
|
+
|
133
|
+
next if hash.nil?
|
134
|
+
|
135
|
+
format.vars_for_line(line_id).each do |var|
|
136
|
+
index = format.index(var)
|
137
|
+
value = columns[index].strip
|
138
|
+
set_value!(hash, var, value)
|
139
|
+
end
|
140
|
+
end
|
141
|
+
|
142
|
+
# Yield the last group.
|
143
|
+
add_result!(results, hash, &block) if hash
|
144
|
+
|
145
|
+
results
|
146
|
+
end
|
147
|
+
|
148
|
+
def multiline_start?(line_id)
|
149
|
+
format.multiline_start?(line_id)
|
150
|
+
end
|
151
|
+
|
152
|
+
# Yield each line and corresponding index of io to given block, but skipping
|
153
|
+
# the first lines according to the skip parameter defined in format.
|
154
|
+
def each_line_with_index(io)
|
155
|
+
offset = format.skip
|
156
|
+
io.each_line.with_index do |line, index|
|
157
|
+
yield(line, index) unless index < offset
|
158
|
+
end
|
159
|
+
end
|
160
|
+
|
161
|
+
end
|
162
|
+
end
|
data/lib/csvpp.rb
ADDED
@@ -0,0 +1,49 @@
|
|
1
|
+
require 'oj'
|
2
|
+
|
3
|
+
require_relative './csvpp/version'
|
4
|
+
require_relative './csvpp/conversions'
|
5
|
+
require_relative './csvpp/format'
|
6
|
+
require_relative './csvpp/parser'
|
7
|
+
|
8
|
+
module CSVPP
|
9
|
+
|
10
|
+
DEFAULT_COL_SEP = '|'
|
11
|
+
|
12
|
+
# @param input [String] path to input file
|
13
|
+
# @param format [String] path to format file
|
14
|
+
# @param col_sep [String]
|
15
|
+
#
|
16
|
+
# @return [Array<Object>]
|
17
|
+
def self.parse(input:, format:, col_sep: DEFAULT_COL_SEP, &block)
|
18
|
+
Parser.parse(
|
19
|
+
input: input,
|
20
|
+
format: Format.load(format),
|
21
|
+
col_sep: col_sep,
|
22
|
+
&block
|
23
|
+
)
|
24
|
+
end
|
25
|
+
|
26
|
+
# @param input [String] input string
|
27
|
+
# @param format [String] format string
|
28
|
+
# @param col_sep [String]
|
29
|
+
#
|
30
|
+
# @return [Array<Object>]
|
31
|
+
def self.parse_str(input:, format:, col_sep: DEFAULT_COL_SEP, &block)
|
32
|
+
Parser.parse_str(
|
33
|
+
input: input,
|
34
|
+
format: Format.load_from_str(format),
|
35
|
+
col_sep: col_sep,
|
36
|
+
&block
|
37
|
+
)
|
38
|
+
end
|
39
|
+
|
40
|
+
# @param input [String] input string
|
41
|
+
# @param format [String] format string
|
42
|
+
# @param col_sep [String]
|
43
|
+
#
|
44
|
+
# @return [String]
|
45
|
+
def self.json(input:, format:, col_sep: DEFAULT_COL_SEP)
|
46
|
+
h = { 'vars' => parse_str(input: input, format: format, col_sep: col_sep) }
|
47
|
+
Oj.dump(h)
|
48
|
+
end
|
49
|
+
end
|
data/ui/.gitignore
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# See https://help.github.com/ignore-files/ for more about ignoring files.
|
2
|
+
|
3
|
+
# dependencies
|
4
|
+
/node_modules
|
5
|
+
|
6
|
+
# testing
|
7
|
+
/coverage
|
8
|
+
|
9
|
+
# production
|
10
|
+
/build
|
11
|
+
|
12
|
+
# misc
|
13
|
+
.DS_Store
|
14
|
+
.env.local
|
15
|
+
.env.development.local
|
16
|
+
.env.test.local
|
17
|
+
.env.production.local
|
18
|
+
|
19
|
+
npm-debug.log*
|
20
|
+
yarn-debug.log*
|
21
|
+
yarn-error.log*
|