strong_csv 0.1.0 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +334 -15
- data/lib/strong_csv/i18n.rb +45 -0
- data/lib/strong_csv/let.rb +56 -6
- data/lib/strong_csv/row.rb +5 -4
- data/lib/strong_csv/types/boolean.rb +24 -0
- data/lib/strong_csv/types/float.rb +17 -0
- data/lib/strong_csv/types/integer.rb +3 -1
- data/lib/strong_csv/types/literal.rb +91 -0
- data/lib/strong_csv/types/optional.rb +22 -0
- data/lib/strong_csv/types/string.rb +29 -0
- data/lib/strong_csv/types/time.rb +26 -0
- data/lib/strong_csv/types/union.rb +27 -0
- data/lib/strong_csv/value_result.rb +5 -5
- data/lib/strong_csv/version.rb +1 -1
- data/lib/strong_csv.rb +14 -1
- metadata +32 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 8078bf75d84307eb32f647a418d2cd2214d6891a78a25a73f7589b82fec0716c
|
4
|
+
data.tar.gz: 318af2a0c3a42ac7141819b06e729a5e98967c5106988bc4349b308f9c9d87f8
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 63aa30f83182e0cab08f816124945d9da91149faaa82017ba0a80ca8b39ef57fed5eab521db1efd8404045aadba189550bd779f195434cef2294975dc30216f3
|
7
|
+
data.tar.gz: e4e74ea2446efcf32f6e67fe8be5df207ae8dbd66b392df4c2fb8895cd71aebf70894d062e64eee2814295aa00f29876afcb95b4c3a88ffffd7be0c8e9a9ba21
|
data/README.md
CHANGED
@@ -1,10 +1,12 @@
|
|
1
1
|
# strong_csv
|
2
2
|
|
3
|
+
<a href="https://rubygems.org/gems/strong_csv"><img alt="strong_csv" src="https://img.shields.io/gem/v/strong_csv"></a>
|
4
|
+
|
3
5
|
NOTE: This repository is still under development 🚧🚜🚧
|
4
6
|
|
5
7
|
Type checker for a CSV file inspired by [strong_json](https://github.com/soutaro/strong_json).
|
6
8
|
|
7
|
-
|
9
|
+
## Motivation
|
8
10
|
|
9
11
|
Some applications have a feature to receive a CSV file uploaded by a user,
|
10
12
|
and in general, it needs to validate each cell of the CSV file.
|
@@ -21,7 +23,7 @@ strong_json helps you to mitigate such a drudgery by letting you declare desired
|
|
21
23
|
Add this line to your application's Gemfile:
|
22
24
|
|
23
25
|
```ruby
|
24
|
-
gem
|
26
|
+
gem "strong_csv"
|
25
27
|
```
|
26
28
|
|
27
29
|
And then execute:
|
@@ -38,22 +40,34 @@ gem install strong_csv
|
|
38
40
|
|
39
41
|
## Usage
|
40
42
|
|
41
|
-
|
43
|
+
The most important APIs of strong_csv are `StrongCSV.new` and `StrongCSV#parse`.
|
44
|
+
`StrongCSV.new` lets you declare types for each CSV column with Ruby's block syntax.
|
45
|
+
Inside the block, you will mainly use `let` and declare types for a column.
|
46
|
+
|
47
|
+
After defining types, you can parse CSV content with `StrongCSV#parse`.
|
48
|
+
`StrongCSV#parse` won't raise errors as possible and just store error messages in its rows.
|
49
|
+
The reason why it won't raise errors is CSV content may contain _invalid_ rows,
|
50
|
+
but sometimes, it makes sense to ignore them and process something for _valid_ rows.
|
51
|
+
If you want to stop all processes with invalid rows,
|
52
|
+
check whether all rows are valid before proceeding with computation.
|
53
|
+
|
54
|
+
Here is an example usage of this gem:
|
42
55
|
|
43
56
|
```ruby
|
57
|
+
require "strong_csv"
|
58
|
+
|
44
59
|
strong_csv = StrongCSV.new do
|
45
60
|
let :stock, integer
|
46
61
|
let :tax_rate, float
|
47
|
-
let :name, string(255)
|
48
|
-
let :description, string?(1000)
|
62
|
+
let :name, string(within: 1..255)
|
63
|
+
let :description, string?(within: 1..1000)
|
49
64
|
let :active, boolean
|
50
|
-
let :started_at, time?
|
51
|
-
let :data, any?
|
65
|
+
let :started_at, time?(format: "%Y-%m-%dT%H:%M:%S")
|
52
66
|
|
53
67
|
# Literal declaration
|
54
68
|
let :status, 0..6
|
55
|
-
let :priority, 10
|
56
|
-
let :size, "S"
|
69
|
+
let :priority, 10, 20, 30, 40, 50
|
70
|
+
let :size, "S", "M", "L" do |value|
|
57
71
|
case value
|
58
72
|
when "S"
|
59
73
|
1
|
@@ -67,7 +81,9 @@ strong_csv = StrongCSV.new do
|
|
67
81
|
# Regular expressions
|
68
82
|
let :url, %r{\Ahttps://}
|
69
83
|
|
70
|
-
#
|
84
|
+
# TODO: The followings are not implemented so far.
|
85
|
+
|
86
|
+
# Custom validation
|
71
87
|
#
|
72
88
|
# This example sees the database to fetch exactly stored `User` IDs,
|
73
89
|
# and it checks the `:user_id` cell really exists in the `users` table.
|
@@ -75,7 +91,7 @@ strong_csv = StrongCSV.new do
|
|
75
91
|
pick :user_id, as: :user_ids do |ids|
|
76
92
|
User.where(id: ids).ids
|
77
93
|
end
|
78
|
-
let :user_id, integer {
|
94
|
+
let :user_id, integer(constraint: ->(i) { user_ids.include?(i) })
|
79
95
|
end
|
80
96
|
|
81
97
|
data = <<~CSV
|
@@ -89,7 +105,7 @@ strong_csv.parse(data, field_size_limit: 2048) do |row|
|
|
89
105
|
row[:active] # => true
|
90
106
|
# do something with row
|
91
107
|
else
|
92
|
-
row.errors # =>
|
108
|
+
row.errors # => { user_id: ["must be present", "must be an integer"] }
|
93
109
|
# do something with row.errors
|
94
110
|
end
|
95
111
|
end
|
@@ -97,9 +113,312 @@ end
|
|
97
113
|
|
98
114
|
## Available types
|
99
115
|
|
100
|
-
|
101
|
-
|
102
|
-
|
116
|
+
<table>
|
117
|
+
<tr>
|
118
|
+
<th>Type</th>
|
119
|
+
<th>Description</th>
|
120
|
+
</tr>
|
121
|
+
<tr>
|
122
|
+
<td><a href="#integer-and-integer"><code>integer</code> and <code>integer?</code></a></td>
|
123
|
+
<td>The value must be casted to <code>Integer</code>.</td>
|
124
|
+
</tr>
|
125
|
+
<tr>
|
126
|
+
<td><a href="#float-and-float"><code>float</code> and <code>float?</code></a></td>
|
127
|
+
<td>The value must be casted to <code>Float</code>.</td>
|
128
|
+
</tr>
|
129
|
+
<tr>
|
130
|
+
<td><a href="#boolean-and-boolean"><code>boolean</code> and <code>boolean?</code></a></td>
|
131
|
+
<td>The value must be casted to Boolean (<code>true</code> or <code>false</code>).</td>
|
132
|
+
</tr>
|
133
|
+
<tr>
|
134
|
+
<td><a href="#string-and-string"><code>string</code> and <code>string?</code></a></td>
|
135
|
+
<td>The value must be casted to <code>String</code>.</td>
|
136
|
+
</tr>
|
137
|
+
<tr>
|
138
|
+
<td><a href="#time-and-time"><code>time</code> and <code>time?</code></a></td>
|
139
|
+
<td>The value must be casted to <code>Time</code>.</td>
|
140
|
+
</tr>
|
141
|
+
<tr>
|
142
|
+
<td><a href="#optional"><code>optional</code></a></td>
|
143
|
+
<td>The value can be <code>nil</code>. If the value exists, it must satisfy the given type constraint.</td>
|
144
|
+
</tr>
|
145
|
+
<tr>
|
146
|
+
<td><a href="#literal"><code>23</code> (Integer literal)</a></td>
|
147
|
+
<td>The value must be casted to the specific <code>Integer</code> literal.</td>
|
148
|
+
</tr>
|
149
|
+
<tr>
|
150
|
+
<td><a href="#literal"><code>15.12</code> (Float literal)</a></td>
|
151
|
+
<td>The value must be casted to the specific <code>Float</code> literal.</td>
|
152
|
+
</tr>
|
153
|
+
<tr>
|
154
|
+
<td><a href="#literal"><code>1..10</code> (Range literal)</a></td>
|
155
|
+
<td>The value must be casted to the beginning of <code>Range</code> and be covered with it.</td>
|
156
|
+
</tr>
|
157
|
+
<tr>
|
158
|
+
<td><a href="#literal"><code>"abc"</code> (String literal)</a></td>
|
159
|
+
<td>The value must be casted to the specific <code>String</code> literal.</td>
|
160
|
+
</tr>
|
161
|
+
<tr>
|
162
|
+
<td><a href="#literal"><code>%r{\Ahttps://}</code> (Regexp literal)</a></td>
|
163
|
+
<td>The value must be casted to a <code>String</code> that matches the specified Regexp.</td>
|
164
|
+
</tr>
|
165
|
+
<tr>
|
166
|
+
<td><a href="#union"><code>,</code> (Union type)</a></td>
|
167
|
+
<td>The value must satisfy one of the subtypes.</td>
|
168
|
+
</tr>
|
169
|
+
</table>
|
170
|
+
|
171
|
+
### `integer` and `integer?`
|
172
|
+
|
173
|
+
The value must be casted to Integer. `integer?` allows the value to be `nil`, so you can declare optional integer type
|
174
|
+
for columns.
|
175
|
+
|
176
|
+
_Example_
|
177
|
+
|
178
|
+
```ruby
|
179
|
+
strong_csv = StrongCSV.new do
|
180
|
+
let :stock, integer
|
181
|
+
let :state, integer?
|
182
|
+
end
|
183
|
+
|
184
|
+
result = strong_csv.parse(<<~CSV)
|
185
|
+
stock,state
|
186
|
+
12,0
|
187
|
+
20,
|
188
|
+
non-integer,1
|
189
|
+
CSV
|
190
|
+
|
191
|
+
result.map(&:valid?) # => [true, true, false]
|
192
|
+
result[0].slice(:stock, :state) # => {:stock=>12, :state=>0}
|
193
|
+
result[1].slice(:stock, :state) # => {:stock=>20, :state=>nil}
|
194
|
+
result[2].slice(:stock, :state) # => {:stock=>"non-integer", :state=>1} ("non-integer" cannot be casted to Integer)
|
195
|
+
```
|
196
|
+
|
197
|
+
### `float` and `float?`
|
198
|
+
|
199
|
+
The value must be casted to Float. `float?` allows the value to be `nil`, so you can declare optional float type for
|
200
|
+
columns.
|
201
|
+
|
202
|
+
_Example_
|
203
|
+
|
204
|
+
```ruby
|
205
|
+
strong_csv = StrongCSV.new do
|
206
|
+
let :tax_rate, float
|
207
|
+
let :fail_rate, float?
|
208
|
+
end
|
209
|
+
|
210
|
+
result = strong_csv.parse(<<~CSV)
|
211
|
+
tax_rate,fail_rate
|
212
|
+
0.02,0.1
|
213
|
+
0.05,
|
214
|
+
,0.8
|
215
|
+
CSV
|
216
|
+
|
217
|
+
result.map(&:valid?) # => [true, true, false]
|
218
|
+
result[0].slice(:tax_rate, :fail_rate) # => {:tax_rate=>0.02, :fail_rate=>0.1}
|
219
|
+
result[1].slice(:tax_rate, :fail_rate) # => {:tax_rate=>0.05, :fail_rate=>nil}
|
220
|
+
result[2].slice(:tax_rate, :fail_rate) # => {:tax_rate=>nil, :fail_rate=>0.8} (`nil` is not allowed for `tax_rate`)
|
221
|
+
```
|
222
|
+
|
223
|
+
### `boolean` and `boolean?`
|
224
|
+
|
225
|
+
The value must be casted to Boolean (`true` of `false`).
|
226
|
+
`"true"`, `"True"`, and `"TRUE"` are casted to `true`,
|
227
|
+
while `"false"`, `"False"`, and `"FALSE"` are casted to `false`.
|
228
|
+
`boolean?` allows the value to be `nil` as an optional boolean
|
229
|
+
value.
|
230
|
+
|
231
|
+
_Example_
|
232
|
+
|
233
|
+
```ruby
|
234
|
+
strong_csv = StrongCSV.new do
|
235
|
+
let :enabled, boolean
|
236
|
+
let :active, boolean?
|
237
|
+
end
|
238
|
+
|
239
|
+
result = strong_csv.parse(<<~CSV)
|
240
|
+
enabled,active
|
241
|
+
True,True
|
242
|
+
False,
|
243
|
+
,
|
244
|
+
CSV
|
245
|
+
|
246
|
+
result.map(&:valid?) # => [true, true, false]
|
247
|
+
result[0].slice(:enabled, :active) # => {:enabled=>true, :active=>true}
|
248
|
+
result[1].slice(:enabled, :active) # => {:enabled=>false, :active=>nil}
|
249
|
+
result[2].slice(:enabled, :active) # => {:enabled=>nil, :active=>nil} (`nil` is not allowed for `enabled`)
|
250
|
+
```
|
251
|
+
|
252
|
+
### `string` and `string?`
|
253
|
+
|
254
|
+
The value must be casted to String. `string?` allows the value to be `nil` as an optional string value.
|
255
|
+
They also support `:within` in its arguments, and it limits the length of the string value within the specified `Range`.
|
256
|
+
|
257
|
+
_Example_
|
258
|
+
|
259
|
+
```ruby
|
260
|
+
strong_csv = StrongCSV.new do
|
261
|
+
let :name, string(within: 1..4)
|
262
|
+
let :description, string?
|
263
|
+
end
|
264
|
+
|
265
|
+
result = strong_csv.parse(<<~CSV)
|
266
|
+
name,description
|
267
|
+
JB,Hello
|
268
|
+
yykamei,
|
269
|
+
,🤷
|
270
|
+
CSV
|
271
|
+
|
272
|
+
result.map(&:valid?) # => [true, false, false]
|
273
|
+
result[0].slice(:name, :description) # => {:name=>"JB", :description=>"Hello"}
|
274
|
+
result[1].slice(:name, :description) # => {:name=>"yykamei", :description=>nil} ("yykamei" exceeds the `Range` specified with `:within`)
|
275
|
+
result[2].slice(:name, :description) # => {:name=>nil, :description=>"🤷"} (`nil` is not allowed for `name`)
|
276
|
+
```
|
277
|
+
|
278
|
+
### `time` and `time?`
|
279
|
+
|
280
|
+
The value must be casted to Time. `time?` allows the value to be `nil` as an optional time value.
|
281
|
+
They have the `:format` argument, which is used as the format
|
282
|
+
of [`Time.strptime`](https://rubydoc.info/stdlib/time/Time.strptime);
|
283
|
+
it means you can ensure the value must satisfy the time format. The default value of `:format` is `"%Y-%m-%d"`.
|
284
|
+
|
285
|
+
_Example_
|
286
|
+
|
287
|
+
```ruby
|
288
|
+
strong_csv = StrongCSV.new do
|
289
|
+
let :start_on, time
|
290
|
+
let :updated_at, time?(format: "%FT%T")
|
291
|
+
end
|
292
|
+
|
293
|
+
result = strong_csv.parse(<<~CSV)
|
294
|
+
start_on,updated_at
|
295
|
+
2022-04-01,2022-04-30T15:30:59
|
296
|
+
2022-05-03
|
297
|
+
05-03,2021-09-03T09:48:23
|
298
|
+
CSV
|
299
|
+
|
300
|
+
result.map(&:valid?) # => [true, true, false]
|
301
|
+
result[0].slice(:start_on, :updated_at) # => {:start_on=>2022-04-01 00:00:00 +0900, :updated_at=>2022-04-30 15:30:59 +0900}
|
302
|
+
result[1].slice(:start_on, :updated_at) # => {:start_on=>2022-05-03 00:00:00 +0900, :updated_at=>nil}
|
303
|
+
result[2].slice(:start_on, :updated_at) # => {:start_on=>"05-03", :updated_at=>2021-09-03 09:48:23 +0900} ("05-03" does not satisfy the default format `"%Y-%m-%d"`)
|
304
|
+
```
|
305
|
+
|
306
|
+
### `optional`
|
307
|
+
|
308
|
+
While each type above has its optional type with `?`, literals cannot be suffixed with `?`.
|
309
|
+
However, there would be a case to have an optional literal type.
|
310
|
+
In this case, `optional` might be useful and lets you declare such types.
|
311
|
+
|
312
|
+
_Example_
|
313
|
+
|
314
|
+
```ruby
|
315
|
+
strong_csv = StrongCSV.new do
|
316
|
+
let :foo, optional(123)
|
317
|
+
let :bar, optional("test")
|
318
|
+
end
|
319
|
+
|
320
|
+
result = strong_csv.parse(<<~CSV)
|
321
|
+
foo,bar
|
322
|
+
123,test
|
323
|
+
,
|
324
|
+
124
|
325
|
+
CSV
|
326
|
+
|
327
|
+
result.map(&:valid?) # => [true, true, false]
|
328
|
+
result[0].slice(:foo, :bar) # => {:foo=>123, :bar=>"test"}
|
329
|
+
result[1].slice(:foo, :bar) # => {:foo=>nil, :bar=>nil}
|
330
|
+
result[2].slice(:foo, :bar) # => {:foo=>"124", :bar=>nil} (124 is not equal to 123)
|
331
|
+
```
|
332
|
+
|
333
|
+
### Literal
|
334
|
+
|
335
|
+
You can declare literal value as types. The supported literals are `Integer`, `Float`, `String`, and `Range`.
|
336
|
+
|
337
|
+
_Example_
|
338
|
+
|
339
|
+
```ruby
|
340
|
+
strong_csv = StrongCSV.new do
|
341
|
+
let 0, 123
|
342
|
+
let 1, "test"
|
343
|
+
let 2, 2.5
|
344
|
+
let 3, 1..10
|
345
|
+
let 4, /[a-z]+/
|
346
|
+
end
|
347
|
+
|
348
|
+
result = strong_csv.parse(<<~CSV)
|
349
|
+
123,test,2.5,9,abc
|
350
|
+
123,test,2.5,0,xyz
|
351
|
+
123,Hey,2.5,10,!
|
352
|
+
CSV
|
353
|
+
|
354
|
+
result.map(&:valid?) # => [true, false, false]
|
355
|
+
result[0].slice(0, 1, 2, 3, 4) # => {0=>123, 1=>"test", 2=>2.5, 3=>9, 4=>"abc"}
|
356
|
+
result[1].slice(0, 1, 2, 3, 4) # => {0=>123, 1=>"test", 2=>2.5, 3=>"0", 4=>"xyz"} (0 is out of 1..10)
|
357
|
+
result[2].slice(0, 1, 2, 3, 4) # => {0=>123, 1=>"Hey", 2=>2.5, 3=>10, 4=>"!"} ("Hey" is not equal to "test", and "!" does not match /[a-z]+/)
|
358
|
+
```
|
359
|
+
|
360
|
+
### Union
|
361
|
+
|
362
|
+
There would be a case that it's alright if a value satisfies one of the types.
|
363
|
+
Union types are useful for such a case.
|
364
|
+
|
365
|
+
_Example_
|
366
|
+
|
367
|
+
```ruby
|
368
|
+
strong_csv = StrongCSV.new do
|
369
|
+
let :priority, 10, 20, 30
|
370
|
+
let :size, "S", "M", "L"
|
371
|
+
end
|
372
|
+
|
373
|
+
result = strong_csv.parse(<<~CSV)
|
374
|
+
priority,size
|
375
|
+
10,M
|
376
|
+
30,A
|
377
|
+
11,S
|
378
|
+
CSV
|
379
|
+
|
380
|
+
result.map(&:valid?) # => [true, false, false]
|
381
|
+
result[0].slice(:priority, :size) # => {:priority=>10, :size=>"M"}
|
382
|
+
result[1].slice(:priority, :size) # => {:priority=>30, :size=>"A"} ("A" is not one of "S", "M", and "L")
|
383
|
+
result[2].slice(:priority, :size) # => {:priority=>"11", :size=>"S"} (11 is not one of 10, 20, and 30)
|
384
|
+
```
|
385
|
+
|
386
|
+
## I18n (Internationalization)
|
387
|
+
|
388
|
+
strong_csv depends on [i18n](https://rubygems.org/gems/i18n) for internationalization.
|
389
|
+
If you want to have a locale-specific error message, put the message catalog in your locale files.
|
390
|
+
Here is an example of a locale file.
|
391
|
+
|
392
|
+
```yaml
|
393
|
+
ja:
|
394
|
+
strong_csv:
|
395
|
+
boolean:
|
396
|
+
cant_be_casted: "`%{value}`はBooleanに変換できません"
|
397
|
+
float:
|
398
|
+
cant_be_casted: "`%{value}`はFloatに変換できません"
|
399
|
+
integer:
|
400
|
+
cant_be_casted: "`%{value}`はIntegerに変換できません"
|
401
|
+
literal:
|
402
|
+
integer:
|
403
|
+
unexpected: "`%{expected}`ではなく`%{value}`が入力されています"
|
404
|
+
cant_be_casted: "`%{expected}`ではなく`%{value}`が入力されています"
|
405
|
+
float:
|
406
|
+
unexpected: "`%{expected}`ではなく`%{value}`が入力されています"
|
407
|
+
cant_be_casted: "`%{value}`はFloatに変換できません"
|
408
|
+
string:
|
409
|
+
unexpected: "`%{expected}`ではなく`%{value}`が入力されています"
|
410
|
+
range:
|
411
|
+
cant_be_casted: "`%{value}`は`%{expected}`の始端に変換できません"
|
412
|
+
out_of_range: "`%{value}`は`%{range}`の範囲外です"
|
413
|
+
regexp:
|
414
|
+
cant_be_casted: "`%{value}`はStringに変換できません"
|
415
|
+
unexpected: "`%{value}`は`%{expected}`とマッチしませんでした"
|
416
|
+
string:
|
417
|
+
cant_be_casted: "`%{value}`はStringに変換できません"
|
418
|
+
out_of_range: "`%{value}`の文字数は`%{range}`の範囲外です"
|
419
|
+
time:
|
420
|
+
cant_be_casted: "`%{value}`は`%{time_format}`でTimeに変換できません"
|
421
|
+
```
|
103
422
|
|
104
423
|
## Contributing
|
105
424
|
|
@@ -0,0 +1,45 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
I18n.backend.store_translations(
|
4
|
+
:en, {
|
5
|
+
_strong_csv: {
|
6
|
+
boolean: {
|
7
|
+
cant_be_casted: "`%{value}` can't be casted to Boolean",
|
8
|
+
},
|
9
|
+
float: {
|
10
|
+
cant_be_casted: "`%{value}` can't be casted to Float",
|
11
|
+
},
|
12
|
+
integer: {
|
13
|
+
cant_be_casted: "`%{value}` can't be casted to Integer",
|
14
|
+
},
|
15
|
+
literal: {
|
16
|
+
integer: {
|
17
|
+
unexpected: "`%{expected}` is expected, but `%{value}` was given",
|
18
|
+
cant_be_casted: "`%{value}` can't be casted to Integer",
|
19
|
+
},
|
20
|
+
float: {
|
21
|
+
unexpected: "`%{expected}` is expected, but `%{value}` was given",
|
22
|
+
cant_be_casted: "`%{value}` can't be casted to Float",
|
23
|
+
},
|
24
|
+
string: {
|
25
|
+
unexpected: "`%{expected}` is expected, but `%{value}` was given",
|
26
|
+
},
|
27
|
+
range: {
|
28
|
+
cant_be_casted: "`%{value}` can't be casted to the beginning of `%{expected}`",
|
29
|
+
out_of_range: "`%{value}` is not within `%{range}`",
|
30
|
+
},
|
31
|
+
regexp: {
|
32
|
+
cant_be_casted: "`%{value}` can't be casted to String",
|
33
|
+
unexpected: "`%{value}` did not match `%{expected}`",
|
34
|
+
},
|
35
|
+
},
|
36
|
+
string: {
|
37
|
+
cant_be_casted: "`%{value}` can't be casted to String",
|
38
|
+
out_of_range: "The length of `%{value}` is out of range `%{range}`",
|
39
|
+
},
|
40
|
+
time: {
|
41
|
+
cant_be_casted: "`%{value}` can't be casted to Time with the format `%{time_format}`",
|
42
|
+
},
|
43
|
+
},
|
44
|
+
},
|
45
|
+
)
|
data/lib/strong_csv/let.rb
CHANGED
@@ -3,7 +3,11 @@
|
|
3
3
|
class StrongCSV
|
4
4
|
# Let is a class that is used to define types for columns.
|
5
5
|
class Let
|
6
|
-
|
6
|
+
# @return [Hash{Symbol => [Types::Base, Proc]}]
|
7
|
+
attr_reader :types
|
8
|
+
|
9
|
+
# @return [Boolean]
|
10
|
+
attr_reader :headers
|
7
11
|
|
8
12
|
def initialize
|
9
13
|
@types = {}
|
@@ -11,12 +15,15 @@ class StrongCSV
|
|
11
15
|
end
|
12
16
|
|
13
17
|
# @param name [String, Symbol, Integer]
|
14
|
-
|
18
|
+
# @param type [StrongCSV::Type::Base]
|
19
|
+
# @param types [Array<StrongCSV::Type::Base>]
|
20
|
+
def let(name, type, *types, &block)
|
21
|
+
type = types.empty? ? type : Types::Union.new(type, *types)
|
15
22
|
case name
|
16
|
-
when Integer
|
17
|
-
@types[name] = type
|
18
|
-
when String, Symbol
|
19
|
-
@types[name.to_sym] = type
|
23
|
+
when ::Integer
|
24
|
+
@types[name] = [type, block]
|
25
|
+
when ::String, ::Symbol
|
26
|
+
@types[name.to_sym] = [type, block]
|
20
27
|
else
|
21
28
|
raise TypeError, "Invalid type specified for `name`. `name` must be String, Symbol, or Integer: #{name.inspect}"
|
22
29
|
end
|
@@ -27,6 +34,49 @@ class StrongCSV
|
|
27
34
|
Types::Integer.new
|
28
35
|
end
|
29
36
|
|
37
|
+
def integer?
|
38
|
+
optional(integer)
|
39
|
+
end
|
40
|
+
|
41
|
+
def boolean
|
42
|
+
Types::Boolean.new
|
43
|
+
end
|
44
|
+
|
45
|
+
def boolean?
|
46
|
+
optional(boolean)
|
47
|
+
end
|
48
|
+
|
49
|
+
def float
|
50
|
+
Types::Float.new
|
51
|
+
end
|
52
|
+
|
53
|
+
def float?
|
54
|
+
optional(float)
|
55
|
+
end
|
56
|
+
|
57
|
+
# @param options [Hash] See `Types::String#initialize` for more details.
|
58
|
+
def string(**options)
|
59
|
+
Types::String.new(**options)
|
60
|
+
end
|
61
|
+
|
62
|
+
def string?(**options)
|
63
|
+
optional(string(**options))
|
64
|
+
end
|
65
|
+
|
66
|
+
# @param options [Hash] See `Types::Time#initialize` for more details.
|
67
|
+
def time(**options)
|
68
|
+
Types::Time.new(**options)
|
69
|
+
end
|
70
|
+
|
71
|
+
def time?(**options)
|
72
|
+
optional(time(**options))
|
73
|
+
end
|
74
|
+
|
75
|
+
# @param args [Array] See `Types::Optional#initialize` for more details.
|
76
|
+
def optional(*args)
|
77
|
+
Types::Optional.new(*args)
|
78
|
+
end
|
79
|
+
|
30
80
|
private
|
31
81
|
|
32
82
|
def validate_columns
|
data/lib/strong_csv/row.rb
CHANGED
@@ -4,8 +4,9 @@ class StrongCSV
|
|
4
4
|
# Row is a representation of a row in a CSV file, which has casted values with specified types.
|
5
5
|
class Row
|
6
6
|
extend Forwardable
|
7
|
+
using Types::Literal
|
7
8
|
|
8
|
-
def_delegators :@values, :[], :fetch
|
9
|
+
def_delegators :@values, :[], :fetch, :slice
|
9
10
|
|
10
11
|
# @return [Hash]
|
11
12
|
attr_reader :errors
|
@@ -20,10 +21,10 @@ class StrongCSV
|
|
20
21
|
@values = {}
|
21
22
|
@errors = {}
|
22
23
|
@lineno = lineno
|
23
|
-
types.each do |key, type|
|
24
|
+
types.each do |key, (type, block)|
|
24
25
|
value_result = type.cast(row[key])
|
25
|
-
@values[key] = value_result.value
|
26
|
-
@errors[key] = value_result.
|
26
|
+
@values[key] = block && value_result.success? ? block.call(value_result.value) : value_result.value
|
27
|
+
@errors[key] = value_result.error_messages unless value_result.success?
|
27
28
|
end
|
28
29
|
end
|
29
30
|
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class StrongCSV
|
4
|
+
module Types
|
5
|
+
# Boolean type
|
6
|
+
class Boolean < Base
|
7
|
+
TRUE_VALUES = %w[true True TRUE].to_set.freeze
|
8
|
+
FALSE_VALUES = %w[false False FALSE].to_set.freeze
|
9
|
+
private_constant :TRUE_VALUES, :FALSE_VALUES
|
10
|
+
|
11
|
+
# @param value [Object] Value to be casted to Boolean
|
12
|
+
# @return [ValueResult]
|
13
|
+
def cast(value)
|
14
|
+
boolean = TRUE_VALUES.include?(value) ? true : nil
|
15
|
+
return ValueResult.new(value: boolean, original_value: value) unless boolean.nil?
|
16
|
+
|
17
|
+
boolean = FALSE_VALUES.include?(value) ? false : nil
|
18
|
+
return ValueResult.new(value: boolean, original_value: value) unless boolean.nil?
|
19
|
+
|
20
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.boolean.cant_be_casted", value: value.inspect, default: :"_strong_csv.boolean.cant_be_casted")])
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class StrongCSV
|
4
|
+
module Types
|
5
|
+
# Float type
|
6
|
+
class Float < Base
|
7
|
+
# @todo Use :exception for Float after we drop the support of Ruby 2.5
|
8
|
+
# @param value [Object] Value to be casted to Float
|
9
|
+
# @return [ValueResult]
|
10
|
+
def cast(value)
|
11
|
+
ValueResult.new(value: Float(value), original_value: value)
|
12
|
+
rescue ArgumentError, TypeError
|
13
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.float.cant_be_casted", value: value.inspect, default: :"_strong_csv.float.cant_be_casted")])
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
@@ -5,10 +5,12 @@ class StrongCSV
|
|
5
5
|
# Integer type
|
6
6
|
class Integer < Base
|
7
7
|
# @todo Use :exception for Integer after we drop the support of Ruby 2.5
|
8
|
+
# @param value [Object] Value to be casted to Integer
|
9
|
+
# @return [ValueResult]
|
8
10
|
def cast(value)
|
9
11
|
ValueResult.new(value: Integer(value), original_value: value)
|
10
12
|
rescue ArgumentError, TypeError
|
11
|
-
ValueResult.new(original_value: value,
|
13
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.integer.cant_be_casted", value: value.inspect, default: :"_strong_csv.integer.cant_be_casted")])
|
12
14
|
end
|
13
15
|
end
|
14
16
|
end
|
@@ -0,0 +1,91 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class StrongCSV
|
4
|
+
module Types
|
5
|
+
# Literal is a module to collect all the literal types for CSV parsing.
|
6
|
+
# This module is intended for refining built-in classes and provide `#cast` like `Base` class.
|
7
|
+
module Literal
|
8
|
+
refine ::Integer do
|
9
|
+
# @param value [Object] Value to be casted to Integer
|
10
|
+
# @return [ValueResult]
|
11
|
+
def cast(value)
|
12
|
+
int = Integer(value)
|
13
|
+
if int == self
|
14
|
+
ValueResult.new(value: int, original_value: value)
|
15
|
+
else
|
16
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.integer.unexpected", value: int.inspect, expected: inspect, default: :"_strong_csv.literal.integer.unexpected")])
|
17
|
+
end
|
18
|
+
rescue ArgumentError, TypeError
|
19
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.integer.cant_be_casted", value: value.inspect, default: :"_strong_csv.literal.integer.cant_be_casted")])
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
refine ::Float do
|
24
|
+
# @param value [Object] Value to be casted to Float
|
25
|
+
# @return [ValueResult]
|
26
|
+
def cast(value)
|
27
|
+
float = Float(value)
|
28
|
+
if float == self
|
29
|
+
ValueResult.new(value: float, original_value: value)
|
30
|
+
else
|
31
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.float.unexpected", value: float.inspect, expected: inspect, default: :"_strong_csv.literal.float.unexpected")])
|
32
|
+
end
|
33
|
+
rescue ArgumentError, TypeError
|
34
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.float.cant_be_casted", value: value.inspect, default: :"_strong_csv.literal.float.cant_be_casted")])
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
refine ::Range do
|
39
|
+
# @param value [Object] Value to be casted to Range
|
40
|
+
# @return [ValueResult]
|
41
|
+
def cast(value)
|
42
|
+
return ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.range.cant_be_casted", value: value.inspect, expected: inspect, default: :"_strong_csv.literal.range.cant_be_casted")]) if value.nil?
|
43
|
+
|
44
|
+
casted = case self.begin
|
45
|
+
when ::Float
|
46
|
+
Float(value)
|
47
|
+
when ::Integer
|
48
|
+
Integer(value)
|
49
|
+
when ::String
|
50
|
+
value
|
51
|
+
else
|
52
|
+
raise TypeError, "#{self.begin.class} is not supported"
|
53
|
+
end
|
54
|
+
if cover?(casted)
|
55
|
+
ValueResult.new(value: casted, original_value: value)
|
56
|
+
else
|
57
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.range.out_of_range", value: casted.inspect, range: inspect, default: :"_strong_csv.literal.range.out_of_range")])
|
58
|
+
end
|
59
|
+
rescue ArgumentError
|
60
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.range.cant_be_casted", value: value.inspect, expected: inspect, default: :"_strong_csv.literal.range.cant_be_casted")])
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
refine ::String do
|
65
|
+
# @param value [Object] Value to be casted to String
|
66
|
+
# @return [ValueResult]
|
67
|
+
def cast(value)
|
68
|
+
if self == value
|
69
|
+
ValueResult.new(value: self, original_value: value)
|
70
|
+
else
|
71
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.string.unexpected", value: value.inspect, expected: inspect, default: :"_strong_csv.literal.string.unexpected")])
|
72
|
+
end
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
refine ::Regexp do
|
77
|
+
# @param value [Object] Value to be casted to String
|
78
|
+
# @return [ValueResult]
|
79
|
+
def cast(value)
|
80
|
+
return ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.regexp.cant_be_casted", value: value.inspect, default: :"_strong_csv.literal.regexp.cant_be_casted")]) if value.nil?
|
81
|
+
|
82
|
+
if self =~ value
|
83
|
+
ValueResult.new(value: value, original_value: value)
|
84
|
+
else
|
85
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.literal.regexp.unexpected", value: value.inspect, expected: inspect, default: :"_strong_csv.literal.regexp.unexpected")])
|
86
|
+
end
|
87
|
+
end
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|
91
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class StrongCSV
|
4
|
+
module Types
|
5
|
+
# Optional type
|
6
|
+
class Optional < Base
|
7
|
+
using Types::Literal
|
8
|
+
|
9
|
+
# @param type [Base]
|
10
|
+
def initialize(type)
|
11
|
+
super()
|
12
|
+
@type = type
|
13
|
+
end
|
14
|
+
|
15
|
+
# @param value [Object]
|
16
|
+
# @return [ValueResult]
|
17
|
+
def cast(value)
|
18
|
+
value.nil? ? ValueResult.new(value: nil, original_value: value) : @type.cast(value)
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class StrongCSV
|
4
|
+
module Types
|
5
|
+
# String type
|
6
|
+
class String < Base
|
7
|
+
# @param within [Range, nil]
|
8
|
+
def initialize(within: nil)
|
9
|
+
raise ArgumentError, "`within` must be a Range" unless within.nil? || within.is_a?(Range)
|
10
|
+
|
11
|
+
super()
|
12
|
+
@within = within
|
13
|
+
end
|
14
|
+
|
15
|
+
# @param value [Object] Value to be casted to Boolean
|
16
|
+
# @return [ValueResult]
|
17
|
+
def cast(value)
|
18
|
+
return ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.string.cant_be_casted", value: value.inspect, default: :"_strong_csv.string.cant_be_casted")]) if value.nil?
|
19
|
+
|
20
|
+
casted = String(value)
|
21
|
+
if @within && !@within.cover?(casted.size)
|
22
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.string.out_of_range", value: value.inspect, range: @within.inspect, default: :"_strong_csv.string.out_of_range")])
|
23
|
+
else
|
24
|
+
ValueResult.new(value: casted, original_value: value)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class StrongCSV
|
4
|
+
module Types
|
5
|
+
# Time type
|
6
|
+
class Time < Base
|
7
|
+
# @param format [String] The format of #strptime
|
8
|
+
def initialize(format: "%Y-%m-%d")
|
9
|
+
raise ArgumentError, "`format` must be a String" unless format.is_a?(::String)
|
10
|
+
|
11
|
+
super()
|
12
|
+
@format = format
|
13
|
+
end
|
14
|
+
|
15
|
+
# @param value [Object] Value to be casted to Time
|
16
|
+
# @return [ValueResult]
|
17
|
+
def cast(value)
|
18
|
+
return ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.time.cant_be_casted", value: value.inspect, time_format: @format.inspect, default: :"_strong_csv.time.cant_be_casted")]) if value.nil?
|
19
|
+
|
20
|
+
ValueResult.new(value: ::Time.strptime(value.to_s, @format), original_value: value)
|
21
|
+
rescue ArgumentError
|
22
|
+
ValueResult.new(original_value: value, error_messages: [I18n.t("strong_csv.time.cant_be_casted", value: value.inspect, time_format: @format.inspect, default: :"_strong_csv.time.cant_be_casted")])
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
@@ -0,0 +1,27 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
class StrongCSV
|
4
|
+
module Types
|
5
|
+
# Union type is a type that combine multiple types.
|
6
|
+
class Union < Base
|
7
|
+
using Types::Literal
|
8
|
+
|
9
|
+
# @param type [Base]
|
10
|
+
# @param types [Array<Base>]
|
11
|
+
def initialize(type, *types)
|
12
|
+
super()
|
13
|
+
@types = [type, *types]
|
14
|
+
end
|
15
|
+
|
16
|
+
# @param value [Object] Value to be casted to Integer
|
17
|
+
# @return [ValueResult]
|
18
|
+
def cast(value)
|
19
|
+
results = @types.map { |type| type.cast(value) }
|
20
|
+
results.find(&:success?) || results.reduce do |memo, result|
|
21
|
+
memo.error_messages.concat(result.error_messages).uniq!
|
22
|
+
memo
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
@@ -6,13 +6,13 @@ class StrongCSV
|
|
6
6
|
DEFAULT_VALUE = Object.new
|
7
7
|
private_constant :DEFAULT_VALUE
|
8
8
|
|
9
|
-
# @return [String
|
10
|
-
attr_reader :
|
9
|
+
# @return [Array<String>, nil] The error messages for the field.
|
10
|
+
attr_reader :error_messages
|
11
11
|
|
12
|
-
def initialize(original_value:, value: DEFAULT_VALUE,
|
12
|
+
def initialize(original_value:, value: DEFAULT_VALUE, error_messages: nil)
|
13
13
|
@value = value
|
14
14
|
@original_value = original_value
|
15
|
-
@
|
15
|
+
@error_messages = error_messages
|
16
16
|
end
|
17
17
|
|
18
18
|
# @return [Object] The casted value if it's valid. Otherwise, returns the original value.
|
@@ -22,7 +22,7 @@ class StrongCSV
|
|
22
22
|
|
23
23
|
# @return [Boolean]
|
24
24
|
def success?
|
25
|
-
@
|
25
|
+
@error_messages.nil?
|
26
26
|
end
|
27
27
|
end
|
28
28
|
end
|
data/lib/strong_csv/version.rb
CHANGED
data/lib/strong_csv.rb
CHANGED
@@ -2,12 +2,23 @@
|
|
2
2
|
|
3
3
|
require "csv"
|
4
4
|
require "forwardable"
|
5
|
+
require "set"
|
6
|
+
require "time"
|
7
|
+
require "i18n"
|
5
8
|
|
6
9
|
require_relative "strong_csv/version"
|
7
|
-
require_relative "strong_csv/
|
10
|
+
require_relative "strong_csv/i18n"
|
8
11
|
require_relative "strong_csv/value_result"
|
9
12
|
require_relative "strong_csv/types/base"
|
13
|
+
require_relative "strong_csv/types/boolean"
|
14
|
+
require_relative "strong_csv/types/float"
|
10
15
|
require_relative "strong_csv/types/integer"
|
16
|
+
require_relative "strong_csv/types/literal"
|
17
|
+
require_relative "strong_csv/types/optional"
|
18
|
+
require_relative "strong_csv/types/string"
|
19
|
+
require_relative "strong_csv/types/time"
|
20
|
+
require_relative "strong_csv/types/union"
|
21
|
+
require_relative "strong_csv/let"
|
11
22
|
require_relative "strong_csv/row"
|
12
23
|
|
13
24
|
# The top-level namespace for the strong_csv gem.
|
@@ -22,6 +33,8 @@ class StrongCSV
|
|
22
33
|
# @param csv [String, IO]
|
23
34
|
# @param options [Hash] CSV options for parsing.
|
24
35
|
def parse(csv, **options)
|
36
|
+
# NOTE: Some options are overridden here to ensure that StrongCSV can handle parsed values correctly.
|
37
|
+
options.delete(:nil_value)
|
25
38
|
options = options.merge(headers: @let.headers, header_converters: :symbol)
|
26
39
|
csv = CSV.new(csv, **options)
|
27
40
|
if block_given?
|
metadata
CHANGED
@@ -1,15 +1,35 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: strong_csv
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Yutaka Kamei
|
8
8
|
autorequire:
|
9
|
-
bindir:
|
9
|
+
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2022-
|
12
|
-
dependencies:
|
11
|
+
date: 2022-05-10 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: i18n
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 1.8.11
|
20
|
+
- - "<"
|
21
|
+
- !ruby/object:Gem::Version
|
22
|
+
version: '2'
|
23
|
+
type: :runtime
|
24
|
+
prerelease: false
|
25
|
+
version_requirements: !ruby/object:Gem::Requirement
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 1.8.11
|
30
|
+
- - "<"
|
31
|
+
- !ruby/object:Gem::Version
|
32
|
+
version: '2'
|
13
33
|
description: strong_csv is a type checker for a CSV file. It lets developers declare
|
14
34
|
types for each column to ensure all cells are satisfied with desired types.
|
15
35
|
email:
|
@@ -21,10 +41,18 @@ files:
|
|
21
41
|
- LICENSE
|
22
42
|
- README.md
|
23
43
|
- lib/strong_csv.rb
|
44
|
+
- lib/strong_csv/i18n.rb
|
24
45
|
- lib/strong_csv/let.rb
|
25
46
|
- lib/strong_csv/row.rb
|
26
47
|
- lib/strong_csv/types/base.rb
|
48
|
+
- lib/strong_csv/types/boolean.rb
|
49
|
+
- lib/strong_csv/types/float.rb
|
27
50
|
- lib/strong_csv/types/integer.rb
|
51
|
+
- lib/strong_csv/types/literal.rb
|
52
|
+
- lib/strong_csv/types/optional.rb
|
53
|
+
- lib/strong_csv/types/string.rb
|
54
|
+
- lib/strong_csv/types/time.rb
|
55
|
+
- lib/strong_csv/types/union.rb
|
28
56
|
- lib/strong_csv/value_result.rb
|
29
57
|
- lib/strong_csv/version.rb
|
30
58
|
homepage: https://github.com/yykamei/strong_csv
|