string_pattern 2.1.4 → 2.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +2 -0
- data/lib/string/pattern/add_to_ruby.rb +64 -66
- data/lib/string_pattern.rb +14 -987
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a5ea5dcf2857bafae800bd597d980c72aacb0c84b774ba698fc1107e1b9f29cf
|
4
|
+
data.tar.gz: a69ccae4e72b74692c61cbcf58d987a07c5a320e8d82c14165cba389df49615b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 1d8a2fe7b5923924787234724b7f50a8f3cc860cbd7c01066e7ff7239a611ae3c64f1155e07ffe974344a1a8f91c4b1655230f7d0f92d54607c1e0289334bbab
|
7
|
+
data.tar.gz: bc3abd91a3885901f6c4e265ef21f4e65fc0053482328d864dd3ac7b31214129bd2c198c78f94976e160a55af6e07631cd32b8478a9e0decd87f04851d265b8d
|
data/README.md
CHANGED
@@ -1,6 +1,8 @@
|
|
1
1
|
# StringPattern
|
2
2
|
|
3
3
|
[![Gem Version](https://badge.fury.io/rb/string_pattern.svg)](https://rubygems.org/gems/string_pattern)
|
4
|
+
[![Build Status](https://travis-ci.com/MarioRuiz/string_pattern.svg?branch=master)](https://github.com/MarioRuiz/string_pattern)
|
5
|
+
[![Coverage Status](https://coveralls.io/repos/github/MarioRuiz/string_pattern/badge.svg?branch=master)](https://coveralls.io/github/MarioRuiz/string_pattern?branch=master)
|
4
6
|
|
5
7
|
With this gem, you can easily generate strings supplying a very simple pattern. Even generate random words in English or Spanish.
|
6
8
|
Also, you can validate if a text fulfills a specific pattern or even generate a string following a pattern and returning the wrong length, value... for testing your applications. Perfect to be used in test data factories.
|
@@ -35,10 +35,10 @@ class String
|
|
35
35
|
# Convert to CamelCase a string
|
36
36
|
########################################################
|
37
37
|
def to_camel_case
|
38
|
-
return self if self !~ /_/ && self !~ /\s/ && self =~
|
38
|
+
return self if self !~ /_/ && self !~ /\s/ && self =~ /^[A-Z]+.*/
|
39
39
|
|
40
|
-
gsub(/\W/,
|
41
|
-
.split(
|
40
|
+
gsub(/\W/, "_")
|
41
|
+
.split("_").map(&:capitalize).join
|
42
42
|
end
|
43
43
|
end
|
44
44
|
|
@@ -70,40 +70,39 @@ class Regexp
|
|
70
70
|
# adds method to convert a Regexp to StringPattern
|
71
71
|
# returns an array of string patterns or just one string pattern
|
72
72
|
def to_sp
|
73
|
-
regexp_s = self.to_s
|
73
|
+
regexp_s = self.to_s
|
74
74
|
return StringPattern.cache[regexp_s] unless StringPattern.cache[regexp_s].nil?
|
75
75
|
regexp = Regexp.new regexp_s
|
76
|
-
require
|
76
|
+
require "regexp_parser"
|
77
77
|
default_infinite = StringPattern.default_infinite
|
78
78
|
pata = []
|
79
|
-
pats =
|
79
|
+
pats = ""
|
80
80
|
patg = [] # for (aa|bb|cc) group
|
81
81
|
set = false
|
82
82
|
capture = false
|
83
83
|
|
84
|
-
range =
|
85
|
-
fixed_text=false
|
86
|
-
last_char = (regexp.to_s.gsub("?-mix:",
|
84
|
+
range = ""
|
85
|
+
fixed_text = false
|
86
|
+
last_char = (regexp.to_s.gsub("?-mix:", "").length) - 2
|
87
87
|
Regexp::Scanner.scan regexp do |type, token, text, ts, te|
|
88
88
|
if type == :escape
|
89
89
|
if token == :dot
|
90
90
|
token = :literal
|
91
|
-
text =
|
91
|
+
text = "."
|
92
92
|
elsif token == :literal and text.size == 2
|
93
93
|
text = text[1]
|
94
|
-
else
|
94
|
+
else
|
95
95
|
puts "Report token not controlled: type: #{type}, token: #{token}, text: '#{text}' [#{ts}..#{te}]"
|
96
96
|
end
|
97
97
|
end
|
98
98
|
|
99
|
-
|
100
99
|
unless set || (token == :interval) || (token == :zero_or_one) ||
|
101
|
-
(token == :zero_or_more) || (token == :one_or_more) || (pats ==
|
102
|
-
if (pats[0] ==
|
103
|
-
pats[0] =
|
100
|
+
(token == :zero_or_more) || (token == :one_or_more) || (pats == "")
|
101
|
+
if (pats[0] == "[") && (pats[-1] == "]")
|
102
|
+
pats[0] = ""
|
104
103
|
if (token == :alternation) || !patg.empty?
|
105
|
-
if fixed_text
|
106
|
-
if patg.size==0
|
104
|
+
if fixed_text
|
105
|
+
if patg.size == 0
|
107
106
|
patg << (pata.pop + pats.chop)
|
108
107
|
else
|
109
108
|
patg[-1] += pats.chop
|
@@ -112,15 +111,15 @@ class Regexp
|
|
112
111
|
patg << pats.chop
|
113
112
|
end
|
114
113
|
else
|
115
|
-
if fixed_text
|
116
|
-
pata[-1]+=pats.chop
|
114
|
+
if fixed_text
|
115
|
+
pata[-1] += pats.chop
|
117
116
|
else
|
118
|
-
if pats.size==2
|
117
|
+
if pats.size == 2
|
119
118
|
pata << pats.chop #jal
|
120
119
|
else
|
121
120
|
pata << "1:[#{pats}" #jal
|
122
121
|
end
|
123
|
-
if last_char==te and type
|
122
|
+
if last_char == te and type == :literal and token == :literal
|
124
123
|
pata << text
|
125
124
|
pats = ""
|
126
125
|
next
|
@@ -134,66 +133,66 @@ class Regexp
|
|
134
133
|
pata << "1:#{pats}"
|
135
134
|
end
|
136
135
|
end
|
137
|
-
pats =
|
136
|
+
pats = ""
|
138
137
|
end
|
139
|
-
fixed_text=false
|
138
|
+
fixed_text = false
|
140
139
|
|
141
140
|
case token
|
142
141
|
when :open
|
143
142
|
set = true
|
144
|
-
pats +=
|
143
|
+
pats += "["
|
145
144
|
when :close
|
146
145
|
if type == :set
|
147
146
|
set = false
|
148
|
-
if pats[-1] ==
|
147
|
+
if pats[-1] == "["
|
149
148
|
pats.chop!
|
150
149
|
else
|
151
|
-
pats +=
|
150
|
+
pats += "]"
|
152
151
|
end
|
153
152
|
elsif type == :group
|
154
153
|
capture = false
|
155
154
|
unless patg.empty?
|
156
|
-
patg << pats if pats.to_s !=
|
155
|
+
patg << pats if pats.to_s != ""
|
157
156
|
pata << patg
|
158
157
|
patg = []
|
159
|
-
pats =
|
158
|
+
pats = ""
|
160
159
|
end
|
161
160
|
end
|
162
161
|
when :capture
|
163
162
|
capture = true if type == :group
|
164
163
|
when :alternation
|
165
164
|
if type == :meta
|
166
|
-
if pats !=
|
165
|
+
if pats != ""
|
167
166
|
patg << pats
|
168
|
-
pats =
|
167
|
+
pats = ""
|
169
168
|
elsif patg.empty?
|
170
169
|
# for the case the first element was not added to patg and was on pata fex: (a+|b|c)
|
171
170
|
patg << pata.pop
|
172
|
-
|
171
|
+
end
|
173
172
|
end
|
174
173
|
when :range
|
175
174
|
range = pats[-1]
|
176
175
|
pats.chop!
|
177
176
|
when :digit
|
178
|
-
pats +=
|
177
|
+
pats += "n"
|
179
178
|
when :nondigit
|
180
|
-
pats +=
|
179
|
+
pats += "*[%0123456789%]"
|
181
180
|
when :space
|
182
|
-
pats +=
|
181
|
+
pats += "_"
|
183
182
|
when :nonspace
|
184
|
-
pats +=
|
183
|
+
pats += "*[% %]"
|
185
184
|
when :word
|
186
|
-
pats +=
|
185
|
+
pats += "Ln_"
|
187
186
|
when :nonword
|
188
|
-
pats +=
|
187
|
+
pats += "$"
|
189
188
|
when :word_boundary
|
190
|
-
pats +=
|
189
|
+
pats += "$"
|
191
190
|
when :dot
|
192
|
-
pats +=
|
191
|
+
pats += "*"
|
193
192
|
when :literal
|
194
|
-
if range ==
|
193
|
+
if range == ""
|
195
194
|
if text.size > 1
|
196
|
-
fixed_text=true
|
195
|
+
fixed_text = true
|
197
196
|
if !patg.empty?
|
198
197
|
patg << text.chop
|
199
198
|
else
|
@@ -204,42 +203,41 @@ class Regexp
|
|
204
203
|
pats += text
|
205
204
|
end
|
206
205
|
else
|
207
|
-
range = range +
|
208
|
-
if range ==
|
209
|
-
pats =
|
210
|
-
elsif range ==
|
211
|
-
pats =
|
212
|
-
elsif range ==
|
213
|
-
pats =
|
206
|
+
range = range + "-" + text
|
207
|
+
if range == "a-z"
|
208
|
+
pats = "x" + pats
|
209
|
+
elsif range == "A-Z"
|
210
|
+
pats = "X" + pats
|
211
|
+
elsif range == "0-9"
|
212
|
+
pats = "n" + pats
|
214
213
|
else
|
215
214
|
pats += if set
|
216
215
|
(range[0]..range[2]).to_a.join
|
217
216
|
else
|
218
|
-
|
219
|
-
|
220
|
-
|
217
|
+
"[" + (range[0]..range[2]).to_a.join + "]"
|
218
|
+
end
|
221
219
|
end
|
222
|
-
range =
|
220
|
+
range = ""
|
223
221
|
end
|
224
|
-
pats =
|
222
|
+
pats = "[" + pats + "]" unless set
|
225
223
|
when :interval
|
226
|
-
size = text.sub(
|
227
|
-
size.chop! if size[-1] ==
|
228
|
-
pats = size +
|
224
|
+
size = text.sub(",", "-").sub("{", "").sub("}", "")
|
225
|
+
size.chop! if size[-1] == "-"
|
226
|
+
pats = size + ":" + pats
|
229
227
|
if !patg.empty?
|
230
228
|
patg << pats
|
231
229
|
else
|
232
230
|
pata << pats
|
233
231
|
end
|
234
|
-
pats =
|
232
|
+
pats = ""
|
235
233
|
when :zero_or_one
|
236
|
-
pats =
|
234
|
+
pats = "0-1:" + pats
|
237
235
|
if !patg.empty?
|
238
236
|
patg << pats
|
239
237
|
else
|
240
238
|
pata << pats
|
241
239
|
end
|
242
|
-
pats =
|
240
|
+
pats = ""
|
243
241
|
when :zero_or_more
|
244
242
|
pats = "0-#{default_infinite}:" + pats
|
245
243
|
if !patg.empty?
|
@@ -247,7 +245,7 @@ class Regexp
|
|
247
245
|
else
|
248
246
|
pata << pats
|
249
247
|
end
|
250
|
-
pats =
|
248
|
+
pats = ""
|
251
249
|
when :one_or_more
|
252
250
|
pats = "1-#{default_infinite}:" + pats
|
253
251
|
if !patg.empty?
|
@@ -255,19 +253,19 @@ class Regexp
|
|
255
253
|
else
|
256
254
|
pata << pats
|
257
255
|
end
|
258
|
-
pats =
|
256
|
+
pats = ""
|
259
257
|
end
|
260
258
|
end
|
261
|
-
if pats!=""
|
262
|
-
if pata.empty?
|
263
|
-
if pats[0]=="[" and pats[-1]=="]" #fex: /[12ab]/
|
259
|
+
if pats != ""
|
260
|
+
if pata.empty?
|
261
|
+
if pats[0] == "[" and pats[-1] == "]" #fex: /[12ab]/
|
264
262
|
pata = ["1:#{pats}"]
|
265
263
|
end
|
266
264
|
else
|
267
|
-
pata[-1]+=pats[1] #fex: /allo/
|
265
|
+
pata[-1] += pats[1] #fex: /allo/
|
268
266
|
end
|
269
267
|
end
|
270
|
-
if pata.size==1 and pata[0].kind_of?(String)
|
268
|
+
if pata.size == 1 and pata[0].kind_of?(String)
|
271
269
|
res = pata[0]
|
272
270
|
else
|
273
271
|
res = pata
|
data/lib/string_pattern.rb
CHANGED
@@ -1,5 +1,8 @@
|
|
1
1
|
SP_ADD_TO_RUBY = true if !defined?(SP_ADD_TO_RUBY)
|
2
|
-
require_relative
|
2
|
+
require_relative "string/pattern/add_to_ruby" if SP_ADD_TO_RUBY
|
3
|
+
require_relative "string/pattern/analyze"
|
4
|
+
require_relative "string/pattern/generate"
|
5
|
+
require_relative "string/pattern/validate"
|
3
6
|
|
4
7
|
# SP_ADD_TO_RUBY: (TrueFalse, default: true) You need to add this constant value before requiring the library if you want to modify the default.
|
5
8
|
# If true it will add 'generate' and 'validate' methods to the classes: Array, String and Symbol. Also it will add 'generate' method to Kernel
|
@@ -19,24 +22,24 @@ require_relative 'string/pattern/add_to_ruby' if SP_ADD_TO_RUBY
|
|
19
22
|
# dont_repeat: (TrueFalse, default: false)
|
20
23
|
# If you want to generate for example 1000 strings and be sure all those strings are different you can set it to true
|
21
24
|
# default_infinite: (Integer, default: 10)
|
22
|
-
# In case using regular expressions the maximum when using * or + for repetitions
|
25
|
+
# In case using regular expressions the maximum when using * or + for repetitions
|
23
26
|
# word_separator: (String, default: '_')
|
24
27
|
# When generating words using symbol types 'w' or 'p' the character to separate the english or spanish words.
|
25
28
|
class StringPattern
|
26
29
|
class << self
|
27
30
|
attr_accessor :national_chars, :optimistic, :dont_repeat, :cache, :cache_values, :default_infinite, :word_separator
|
28
31
|
end
|
29
|
-
@national_chars = ((
|
32
|
+
@national_chars = (("a".."z").to_a + ("A".."Z").to_a).join
|
30
33
|
@optimistic = true
|
31
34
|
@cache = Hash.new()
|
32
35
|
@cache_values = Hash.new()
|
33
36
|
@dont_repeat = false
|
34
37
|
@default_infinite = 10
|
35
|
-
@word_separator =
|
36
|
-
NUMBER_SET = (
|
37
|
-
SPECIAL_SET = [
|
38
|
-
ALPHA_SET_LOWER = (
|
39
|
-
ALPHA_SET_CAPITAL = (
|
38
|
+
@word_separator = "_"
|
39
|
+
NUMBER_SET = ("0".."9").to_a
|
40
|
+
SPECIAL_SET = [" ", "~", "!", "@", "#", "$", "%", "^", "&", "*", "(", ")", "-", "_", "+", "=", "{", "}", "[", "]", "'", ";", ":", "?", ">", "<", "`", "|", "/", '"']
|
41
|
+
ALPHA_SET_LOWER = ("a".."z").to_a
|
42
|
+
ALPHA_SET_CAPITAL = ("A".."Z").to_a
|
40
43
|
@palabras = []
|
41
44
|
@palabras_camel = []
|
42
45
|
@words = []
|
@@ -49,984 +52,8 @@ class StringPattern
|
|
49
52
|
Pattern = Struct.new(:min_length, :max_length, :symbol_type, :required_data, :excluded_data, :data_provided,
|
50
53
|
:string_set, :all_characters_set, :unique)
|
51
54
|
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
###############################################
|
56
|
-
def StringPattern.analyze(pattern, silent: false)
|
57
|
-
return @cache[pattern.to_s] unless @cache[pattern.to_s].nil?
|
58
|
-
min_length, max_length, symbol_type = pattern.to_s.scan(/(\d+)-(\d+):(.+)/)[0]
|
59
|
-
if min_length.nil?
|
60
|
-
min_length, symbol_type = pattern.to_s.scan(/^!?(\d+):(.+)/)[0]
|
61
|
-
max_length = min_length
|
62
|
-
if min_length.nil?
|
63
|
-
puts "pattern argument not valid on StringPattern.generate: #{pattern.inspect}" unless silent
|
64
|
-
return pattern.to_s
|
65
|
-
end
|
66
|
-
end
|
67
|
-
if symbol_type[-1]=="&"
|
68
|
-
symbol_type.chop!
|
69
|
-
unique = true
|
70
|
-
else
|
71
|
-
unique = false
|
72
|
-
end
|
73
|
-
|
74
|
-
symbol_type = '!' + symbol_type if pattern.to_s[0] == '!'
|
75
|
-
min_length = min_length.to_i
|
76
|
-
max_length = max_length.to_i
|
77
|
-
|
78
|
-
required_data = Array.new
|
79
|
-
excluded_data = Array.new
|
80
|
-
required = false
|
81
|
-
excluded = false
|
82
|
-
data_provided = Array.new
|
83
|
-
a = symbol_type
|
84
|
-
begin_provided = a.index('[')
|
85
|
-
excluded_end_tag = false
|
86
|
-
unless begin_provided.nil?
|
87
|
-
c = begin_provided + 1
|
88
|
-
until c == a.size or (a[c..c] == ']' and a[c..c + 1] != ']]')
|
89
|
-
if a[c..c + 1] == ']]'
|
90
|
-
data_provided.push(']')
|
91
|
-
c = c + 2
|
92
|
-
elsif a[c..c + 1] == '%%' and !excluded then
|
93
|
-
data_provided.push('%')
|
94
|
-
c = c + 2
|
95
|
-
else
|
96
|
-
if a[c..c] == '/' and !excluded
|
97
|
-
if a[c..c + 1] == '//'
|
98
|
-
data_provided.push(a[c..c])
|
99
|
-
if required
|
100
|
-
required_data.push([a[c..c]])
|
101
|
-
end
|
102
|
-
c = c + 1
|
103
|
-
else
|
104
|
-
if !required
|
105
|
-
required = true
|
106
|
-
else
|
107
|
-
required = false
|
108
|
-
end
|
109
|
-
end
|
110
|
-
else
|
111
|
-
if required
|
112
|
-
required_data.push([a[c..c]])
|
113
|
-
else
|
114
|
-
if a[c..c] == '%'
|
115
|
-
if a[c..c + 1] == '%%' and excluded
|
116
|
-
excluded_data.push([a[c..c]])
|
117
|
-
c = c + 1
|
118
|
-
else
|
119
|
-
if !excluded
|
120
|
-
excluded = true
|
121
|
-
else
|
122
|
-
excluded = false
|
123
|
-
excluded_end_tag = true
|
124
|
-
end
|
125
|
-
end
|
126
|
-
else
|
127
|
-
if excluded
|
128
|
-
excluded_data.push([a[c..c]])
|
129
|
-
end
|
130
|
-
end
|
131
|
-
|
132
|
-
end
|
133
|
-
if excluded == false and excluded_end_tag == false
|
134
|
-
data_provided.push(a[c..c])
|
135
|
-
end
|
136
|
-
excluded_end_tag = false
|
137
|
-
end
|
138
|
-
c = c + 1
|
139
|
-
end
|
140
|
-
end
|
141
|
-
symbol_type = symbol_type[0..begin_provided].to_s + symbol_type[c..symbol_type.size].to_s
|
142
|
-
end
|
143
|
-
|
144
|
-
required = false
|
145
|
-
required_symbol = ''
|
146
|
-
if symbol_type.include?("/")
|
147
|
-
symbol_type.chars.each {|stc|
|
148
|
-
if stc == '/'
|
149
|
-
if !required
|
150
|
-
required = true
|
151
|
-
else
|
152
|
-
required = false
|
153
|
-
end
|
154
|
-
else
|
155
|
-
if required
|
156
|
-
required_symbol += stc
|
157
|
-
end
|
158
|
-
end
|
159
|
-
}
|
160
|
-
end
|
161
|
-
|
162
|
-
national_set = @national_chars.chars
|
163
|
-
|
164
|
-
if symbol_type.include?('L') then
|
165
|
-
alpha_set = ALPHA_SET_LOWER + ALPHA_SET_CAPITAL
|
166
|
-
elsif symbol_type.include?('x')
|
167
|
-
alpha_set = ALPHA_SET_LOWER
|
168
|
-
if symbol_type.include?('X')
|
169
|
-
alpha_set = alpha_set + ALPHA_SET_CAPITAL
|
170
|
-
end
|
171
|
-
elsif symbol_type.include?('X')
|
172
|
-
alpha_set = ALPHA_SET_CAPITAL
|
173
|
-
else
|
174
|
-
alpha_set = []
|
175
|
-
end
|
176
|
-
if symbol_type.include?('T')
|
177
|
-
alpha_set = alpha_set + national_set
|
178
|
-
end
|
179
|
-
|
180
|
-
unless required_symbol.nil?
|
181
|
-
if required_symbol.include?('x')
|
182
|
-
required_data.push ALPHA_SET_LOWER
|
183
|
-
end
|
184
|
-
if required_symbol.include?('X')
|
185
|
-
required_data.push ALPHA_SET_CAPITAL
|
186
|
-
end
|
187
|
-
if required_symbol.include?('L')
|
188
|
-
required_data.push(ALPHA_SET_CAPITAL + ALPHA_SET_LOWER)
|
189
|
-
end
|
190
|
-
if required_symbol.include?('T')
|
191
|
-
required_data.push national_set
|
192
|
-
end
|
193
|
-
required_symbol = required_symbol.downcase
|
194
|
-
end
|
195
|
-
string_set = Array.new
|
196
|
-
all_characters_set = ALPHA_SET_CAPITAL + ALPHA_SET_LOWER + NUMBER_SET + SPECIAL_SET + data_provided + national_set
|
197
|
-
|
198
|
-
if symbol_type.include?('_')
|
199
|
-
unless symbol_type.include?('$')
|
200
|
-
string_set.push(' ')
|
201
|
-
end
|
202
|
-
if required_symbol.include?('_')
|
203
|
-
required_data.push([' '])
|
204
|
-
end
|
205
|
-
end
|
206
|
-
|
207
|
-
#symbol_type = symbol_type.downcase
|
208
|
-
|
209
|
-
if symbol_type.downcase.include?('x') or symbol_type.downcase.include?('l') or symbol_type.downcase.include?('t')
|
210
|
-
string_set = string_set + alpha_set
|
211
|
-
end
|
212
|
-
if symbol_type.downcase.include?('n')
|
213
|
-
string_set = string_set + NUMBER_SET
|
214
|
-
end
|
215
|
-
if symbol_type.include?('$')
|
216
|
-
string_set = string_set + SPECIAL_SET
|
217
|
-
end
|
218
|
-
if symbol_type.include?('*')
|
219
|
-
string_set = string_set + all_characters_set
|
220
|
-
end
|
221
|
-
if data_provided.size != 0
|
222
|
-
string_set = string_set + data_provided
|
223
|
-
end
|
224
|
-
unless required_symbol.empty?
|
225
|
-
if required_symbol.include?('n')
|
226
|
-
required_data.push NUMBER_SET
|
227
|
-
end
|
228
|
-
if required_symbol.include?('$')
|
229
|
-
required_data.push SPECIAL_SET
|
230
|
-
end
|
231
|
-
end
|
232
|
-
unless excluded_data.empty?
|
233
|
-
string_set = string_set - excluded_data.flatten
|
234
|
-
end
|
235
|
-
string_set.uniq!
|
236
|
-
@cache[pattern.to_s] = Pattern.new(min_length, max_length, symbol_type, required_data, excluded_data, data_provided,
|
237
|
-
string_set, all_characters_set, unique)
|
238
|
-
return @cache[pattern.to_s]
|
55
|
+
def self.national_chars=(par)
|
56
|
+
@cache = Hash.new()
|
57
|
+
@national_chars = par
|
239
58
|
end
|
240
|
-
|
241
|
-
###############################################
|
242
|
-
# Generate a random string based on the pattern supplied
|
243
|
-
# (if SP_ADD_TO_RUBY==true, by default is true) To simplify its use it is part of the String, Array, Symbol and Kernel Ruby so can be easily used also like this:
|
244
|
-
# "10-15:Ln/x/".generate #generate method on String class (alias: gen)
|
245
|
-
# ['(', :'3:N', ')', :'6-8:N'].generate #generate method on Array class (alias: gen)
|
246
|
-
# generate("10-15:Ln/x/") #generate Ruby Kernel method
|
247
|
-
# generate(['(', :'3:N', ')', :'6-8:N']) #generate Ruby Kernel method
|
248
|
-
# "(,3:N,) ,3:N,-,2:N,-,2:N".split(",").generate #>(937) #generate method on Array class (alias: gen)
|
249
|
-
# %w{( 3:N ) 1:_ 3:N - 2:N - 2:N}.gen #generate method on Array class, using alias gen method
|
250
|
-
# Input:
|
251
|
-
# pattern: array or string of different patterns. A pattern is a string with this info:
|
252
|
-
# "length:symbol_type" or "min_length-max_length:symbol_type"
|
253
|
-
# In case an array supplied, the positions using a string pattern should be supplied as symbols if StringPattern.optimistic==false
|
254
|
-
#
|
255
|
-
# These are the possible string patterns you will be able to supply:
|
256
|
-
# If at the beginning we supply the character ! the resulting string won't fulfill the pattern. This character need to be the first character of the pattern.
|
257
|
-
# min_length -- minimum length of the string
|
258
|
-
# max_length (optional) -- maximum length of the string. If not provided the result will be with the min_length provided
|
259
|
-
# symbol_type -- the type of the string we want.
|
260
|
-
# you can use a combination of any ot these:
|
261
|
-
# x for alpha in lowercase
|
262
|
-
# X for alpha in capital letters
|
263
|
-
# L for all kind of alpha in capital and lower letters
|
264
|
-
# T for the national characters defined on StringPattern.national_chars
|
265
|
-
# n for number
|
266
|
-
# $ for special characters (includes space)
|
267
|
-
# _ for space
|
268
|
-
# * all characters
|
269
|
-
# [characters] the characters we want. If we want to add also the ] character you have to write: ]]. If we want to add also the % character you have to write: %%
|
270
|
-
# %characters% the characters we don't want on the resulting string. %% to exclude the character %
|
271
|
-
# /symbols or characters/ If we want these characters to be included on the resulting string. If we want to add also the / character you have to write: //
|
272
|
-
# We can supply 0 to allow empty strings, this character need to be at the beginning
|
273
|
-
# If you want to include the character " use \"
|
274
|
-
# If you want to include the character \ use \\
|
275
|
-
# If you want to include the character [ use \[
|
276
|
-
# Other uses:
|
277
|
-
# @ for email
|
278
|
-
# W for English words, capital and lower
|
279
|
-
# w for English words only lower and words separated by underscore
|
280
|
-
# P for Spanish words, capital and lower
|
281
|
-
# p for Spanish words only lower and words separated by underscore
|
282
|
-
# Examples:
|
283
|
-
# [:"6:X", :"3-8:_N"]
|
284
|
-
# # it will return a string starting with 6 capital letters and then a string containing numbers and space from 3 to 8 characters, for example: "LDJKKD34 555"
|
285
|
-
# [:"6-15:L_N", "fixed text", :"3:N"]
|
286
|
-
# # it will return a string of 6-15 characters containing Letters-spaces-numbers, then the text: 'fixed text' and at the end a string of 3 characters containing numbers, for example: ["L_N",6,15],"fixed text",["N",3] "3 Am399 afixed text882"
|
287
|
-
# "10-20:LN[=#]"
|
288
|
-
# # it will return a string of 10-20 characters containing Letters and/or numbers and/or the characters = and #, for example: eiyweQFWeL#do4Vl
|
289
|
-
# "30:TN_[#=]/x/"
|
290
|
-
# # it will return a string of 30 characters containing national characters defined on StringPattern.national_chars and/or numbers and/or spaces and/or the characters # = and it is necessary the resultant string includes lower alpha chars. For example: HaEdQTzJ3=OtXMh1mAPqv7NCy=upLy
|
291
|
-
# "10:N[%0%]"
|
292
|
-
# # 10 characters length containing numbers and excluding the character 0, for example: 3523497757
|
293
|
-
# "10:N[%0%/AB/]"
|
294
|
-
# # 10 characters length containing numbers and excluding the character 0 and necessary to contain the characters A B, for example: 3AA4AA57BB
|
295
|
-
# "!10:N[%0%/AB/]"
|
296
|
-
# # it will generate a string that doesn't fulfill the pattern supplied, examples:
|
297
|
-
# # a6oMQ4JK9g
|
298
|
-
# # /Y<N6Aa[ae
|
299
|
-
# # 3444439A34B32
|
300
|
-
# "10:N[%0%/AB/]", errors: [:length]
|
301
|
-
# # it will generate a string following the pattern and with the errors supplied, in this case, length, example: AB44
|
302
|
-
# Output:
|
303
|
-
# the generated string
|
304
|
-
###############################################
|
305
|
-
def StringPattern.generate(pattern, expected_errors: [], **synonyms)
|
306
|
-
tries = 0
|
307
|
-
begin
|
308
|
-
good_result = true
|
309
|
-
tries += 1
|
310
|
-
string = ''
|
311
|
-
|
312
|
-
expected_errors = synonyms[:errors] if synonyms.keys.include?(:errors)
|
313
|
-
|
314
|
-
if expected_errors.kind_of?(Symbol)
|
315
|
-
expected_errors = [expected_errors]
|
316
|
-
end
|
317
|
-
|
318
|
-
if pattern.kind_of?(Array)
|
319
|
-
pattern.each {|pat|
|
320
|
-
|
321
|
-
if pat.kind_of?(Array) # for the case it is one of the values
|
322
|
-
pat = pat.sample
|
323
|
-
end
|
324
|
-
|
325
|
-
if pat.kind_of?(Symbol)
|
326
|
-
if pat.to_s.scan(/^!?\d+-?\d*:.+/).size > 0
|
327
|
-
string << StringPattern.generate(pat.to_s, expected_errors: expected_errors)
|
328
|
-
else
|
329
|
-
string << pat.to_s
|
330
|
-
end
|
331
|
-
elsif pat.kind_of?(String) then
|
332
|
-
if @optimistic and pat.to_s.scan(/^!?\d+-?\d*:.+/).size > 0
|
333
|
-
string << StringPattern.generate(pat.to_s, expected_errors: expected_errors)
|
334
|
-
else
|
335
|
-
string << pat
|
336
|
-
end
|
337
|
-
else
|
338
|
-
puts "StringPattern.generate: it seems you supplied wrong array of patterns: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
339
|
-
return ''
|
340
|
-
end
|
341
|
-
}
|
342
|
-
return string
|
343
|
-
elsif pattern.kind_of?(String) or pattern.kind_of?(Symbol)
|
344
|
-
patt = StringPattern.analyze(pattern)
|
345
|
-
min_length = patt.min_length
|
346
|
-
max_length = patt.max_length
|
347
|
-
symbol_type = patt.symbol_type
|
348
|
-
|
349
|
-
required_data = patt.required_data
|
350
|
-
excluded_data = patt.excluded_data
|
351
|
-
string_set = patt.string_set
|
352
|
-
all_characters_set = patt.all_characters_set
|
353
|
-
|
354
|
-
required_chars = Array.new
|
355
|
-
unless required_data.size == 0
|
356
|
-
required_data.each {|rd|
|
357
|
-
required_chars << rd if rd.size == 1
|
358
|
-
}
|
359
|
-
unless excluded_data.size == 0
|
360
|
-
if (required_chars.flatten & excluded_data.flatten).size > 0
|
361
|
-
puts "pattern argument not valid on StringPattern.generate, a character cannot be required and excluded at the same time: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
362
|
-
return ''
|
363
|
-
end
|
364
|
-
end
|
365
|
-
end
|
366
|
-
string_set_not_allowed = Array.new
|
367
|
-
elsif pattern.kind_of?(Regexp)
|
368
|
-
return generate(pattern.to_sp, expected_errors: expected_errors)
|
369
|
-
else
|
370
|
-
puts "pattern argument not valid on StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
371
|
-
return pattern.to_s
|
372
|
-
end
|
373
|
-
|
374
|
-
|
375
|
-
allow_empty = false
|
376
|
-
deny_pattern = false
|
377
|
-
if symbol_type[0..0] == '!'
|
378
|
-
deny_pattern = true
|
379
|
-
possible_errors = [:length, :value, :required_data, :excluded_data, :string_set_not_allowed]
|
380
|
-
(rand(possible_errors.size) + 1).times {
|
381
|
-
expected_errors << possible_errors.sample
|
382
|
-
}
|
383
|
-
expected_errors.uniq!
|
384
|
-
if symbol_type[1..1] == '0'
|
385
|
-
allow_empty = true
|
386
|
-
end
|
387
|
-
elsif symbol_type[0..0] == '0' then
|
388
|
-
allow_empty = true
|
389
|
-
end
|
390
|
-
|
391
|
-
if expected_errors.include?(:min_length) or expected_errors.include?(:length) or
|
392
|
-
expected_errors.include?(:max_length)
|
393
|
-
allow_empty = !allow_empty
|
394
|
-
elsif expected_errors.include?(:value) or
|
395
|
-
expected_errors.include?(:excluded_data) or
|
396
|
-
expected_errors.include?(:required_data) or
|
397
|
-
expected_errors.include?(:string_set_not_allowed) and allow_empty
|
398
|
-
allow_empty = false
|
399
|
-
end
|
400
|
-
|
401
|
-
length = min_length
|
402
|
-
symbol_type_orig = symbol_type
|
403
|
-
|
404
|
-
expected_errors_left = expected_errors.dup
|
405
|
-
|
406
|
-
symbol_type = symbol_type_orig
|
407
|
-
|
408
|
-
unless deny_pattern
|
409
|
-
if required_data.size == 0 and expected_errors_left.include?(:required_data)
|
410
|
-
puts "required data not supplied on pattern so it won't be possible to generate a wrong string. StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
411
|
-
return ''
|
412
|
-
end
|
413
|
-
|
414
|
-
if excluded_data.size == 0 and expected_errors_left.include?(:excluded_data)
|
415
|
-
puts "excluded data not supplied on pattern so it won't be possible to generate a wrong string. StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
416
|
-
return ''
|
417
|
-
end
|
418
|
-
|
419
|
-
if expected_errors_left.include?(:string_set_not_allowed)
|
420
|
-
string_set_not_allowed = all_characters_set - string_set
|
421
|
-
if string_set_not_allowed.size == 0 then
|
422
|
-
puts "all characters are allowed so it won't be possible to generate a wrong string. StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
423
|
-
return ''
|
424
|
-
end
|
425
|
-
end
|
426
|
-
end
|
427
|
-
|
428
|
-
if expected_errors_left.include?(:min_length) or
|
429
|
-
expected_errors_left.include?(:max_length) or
|
430
|
-
expected_errors_left.include?(:length)
|
431
|
-
if expected_errors_left.include?(:min_length) or
|
432
|
-
(min_length > 0 and expected_errors_left.include?(:length) and rand(2) == 0)
|
433
|
-
if min_length > 0
|
434
|
-
if allow_empty
|
435
|
-
length = rand(min_length).to_i
|
436
|
-
else
|
437
|
-
length = rand(min_length - 1).to_i + 1
|
438
|
-
end
|
439
|
-
if required_data.size > length and required_data.size < min_length
|
440
|
-
length = required_data.size
|
441
|
-
end
|
442
|
-
expected_errors_left.delete(:length)
|
443
|
-
expected_errors_left.delete(:min_length)
|
444
|
-
else
|
445
|
-
puts "min_length is 0 so it won't be possible to generate a wrong string smaller than 0 characters. StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
446
|
-
return ''
|
447
|
-
end
|
448
|
-
elsif expected_errors_left.include?(:max_length) or expected_errors_left.include?(:length)
|
449
|
-
length = max_length + 1 + rand(max_length).to_i
|
450
|
-
expected_errors_left.delete(:length)
|
451
|
-
expected_errors_left.delete(:max_length)
|
452
|
-
end
|
453
|
-
else
|
454
|
-
if allow_empty and rand(7) == 1
|
455
|
-
length = 0
|
456
|
-
else
|
457
|
-
if max_length == min_length
|
458
|
-
length = min_length
|
459
|
-
else
|
460
|
-
length = min_length + rand(max_length - min_length + 1)
|
461
|
-
end
|
462
|
-
end
|
463
|
-
end
|
464
|
-
|
465
|
-
if deny_pattern
|
466
|
-
if required_data.size == 0 and expected_errors_left.include?(:required_data)
|
467
|
-
expected_errors_left.delete(:required_data)
|
468
|
-
end
|
469
|
-
|
470
|
-
if excluded_data.size == 0 and expected_errors_left.include?(:excluded_data)
|
471
|
-
expected_errors_left.delete(:excluded_data)
|
472
|
-
end
|
473
|
-
|
474
|
-
if expected_errors_left.include?(:string_set_not_allowed)
|
475
|
-
string_set_not_allowed = all_characters_set - string_set
|
476
|
-
if string_set_not_allowed.size == 0
|
477
|
-
expected_errors_left.delete(:string_set_not_allowed)
|
478
|
-
end
|
479
|
-
end
|
480
|
-
|
481
|
-
if symbol_type == '!@' and expected_errors_left.size == 0 and !expected_errors.include?(:length) and
|
482
|
-
(expected_errors.include?(:required_data) or expected_errors.include?(:excluded_data))
|
483
|
-
expected_errors_left.push(:value)
|
484
|
-
end
|
485
|
-
|
486
|
-
end
|
487
|
-
|
488
|
-
string = ''
|
489
|
-
if symbol_type != '@' and symbol_type != '!@' and length != 0 and string_set.size != 0
|
490
|
-
if string_set.size != 0
|
491
|
-
1.upto(length) {|i| string << string_set.sample.to_s
|
492
|
-
}
|
493
|
-
end
|
494
|
-
if required_data.size > 0
|
495
|
-
positions_to_set = (0..(string.size - 1)).to_a
|
496
|
-
required_data.each {|rd|
|
497
|
-
if (string.chars & rd).size > 0
|
498
|
-
rd_to_set = (string.chars & rd).sample
|
499
|
-
else
|
500
|
-
rd_to_set = rd.sample
|
501
|
-
end
|
502
|
-
if ((0...string.length).find_all {|i| string[i, 1] == rd_to_set}).size == 0
|
503
|
-
if positions_to_set.size == 0
|
504
|
-
puts "pattern not valid on StringPattern.generate, not possible to generate a valid string: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
505
|
-
return ''
|
506
|
-
else
|
507
|
-
k = positions_to_set.sample
|
508
|
-
string[k] = rd_to_set
|
509
|
-
positions_to_set.delete(k)
|
510
|
-
end
|
511
|
-
else
|
512
|
-
k = ((0...string.length).find_all {|i| string[i, 1] == rd_to_set}).sample
|
513
|
-
positions_to_set.delete(k)
|
514
|
-
end
|
515
|
-
}
|
516
|
-
end
|
517
|
-
excluded_data.each {|ed|
|
518
|
-
if (string.chars & ed).size > 0
|
519
|
-
(string.chars & ed).each {|s|
|
520
|
-
string.gsub!(s, string_set.sample)
|
521
|
-
}
|
522
|
-
end
|
523
|
-
}
|
524
|
-
|
525
|
-
if expected_errors_left.include?(:value)
|
526
|
-
string_set_not_allowed = all_characters_set - string_set if string_set_not_allowed.size == 0
|
527
|
-
if string_set_not_allowed.size == 0
|
528
|
-
puts "Not possible to generate a non valid string on StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
529
|
-
return ''
|
530
|
-
end
|
531
|
-
(rand(string.size) + 1).times {
|
532
|
-
string[rand(string.size)] = (all_characters_set - string_set).sample
|
533
|
-
}
|
534
|
-
expected_errors_left.delete(:value)
|
535
|
-
end
|
536
|
-
|
537
|
-
if expected_errors_left.include?(:required_data) and required_data.size > 0
|
538
|
-
(rand(required_data.size) + 1).times {
|
539
|
-
chars_to_remove = required_data.sample
|
540
|
-
chars_to_remove.each {|char_to_remove|
|
541
|
-
string.gsub!(char_to_remove, (string_set - chars_to_remove).sample)
|
542
|
-
}
|
543
|
-
}
|
544
|
-
expected_errors_left.delete(:required_data)
|
545
|
-
end
|
546
|
-
|
547
|
-
if expected_errors_left.include?(:excluded_data) and excluded_data.size > 0
|
548
|
-
(rand(string.size) + 1).times {
|
549
|
-
string[rand(string.size)] = excluded_data.sample.sample
|
550
|
-
}
|
551
|
-
expected_errors_left.delete(:excluded_data)
|
552
|
-
end
|
553
|
-
|
554
|
-
if expected_errors_left.include?(:string_set_not_allowed)
|
555
|
-
string_set_not_allowed = all_characters_set - string_set if string_set_not_allowed.size == 0
|
556
|
-
if string_set_not_allowed.size > 0
|
557
|
-
(rand(string.size) + 1).times {
|
558
|
-
string[rand(string.size)] = string_set_not_allowed.sample
|
559
|
-
}
|
560
|
-
expected_errors_left.delete(:string_set_not_allowed)
|
561
|
-
end
|
562
|
-
end
|
563
|
-
elsif (symbol_type == 'W' or symbol_type == 'P' or symbol_type=='w' or symbol_type =='p') and length>0
|
564
|
-
words = []
|
565
|
-
words_short = []
|
566
|
-
if symbol_type == 'W'
|
567
|
-
if @words_camel.empty?
|
568
|
-
require "pathname"
|
569
|
-
require "json"
|
570
|
-
filename = File.join Pathname(File.dirname(__FILE__)), "../data", "english/nouns.json"
|
571
|
-
nouns = JSON.parse(File.read(filename))
|
572
|
-
filename = File.join Pathname(File.dirname(__FILE__)), "../data", "english/adjs.json"
|
573
|
-
adjs = JSON.parse(File.read(filename))
|
574
|
-
nouns = nouns.map(&:to_camel_case)
|
575
|
-
adjs = adjs.map(&:to_camel_case)
|
576
|
-
@words_camel = adjs + nouns
|
577
|
-
@words_camel_short = @words_camel.sample(2000)
|
578
|
-
end
|
579
|
-
words = @words_camel
|
580
|
-
words_short = @words_camel_short
|
581
|
-
elsif symbol_type == 'w'
|
582
|
-
if @words.empty?
|
583
|
-
require "pathname"
|
584
|
-
require "json"
|
585
|
-
filename = File.join Pathname(File.dirname(__FILE__)), "../data", "english/nouns.json"
|
586
|
-
nouns = JSON.parse(File.read(filename))
|
587
|
-
filename = File.join Pathname(File.dirname(__FILE__)), "../data", "english/adjs.json"
|
588
|
-
adjs = JSON.parse(File.read(filename))
|
589
|
-
@words = adjs + nouns
|
590
|
-
@words_short = @words.sample(2000)
|
591
|
-
end
|
592
|
-
words = @words
|
593
|
-
words_short = @words_short
|
594
|
-
elsif symbol_type == 'P'
|
595
|
-
if @palabras_camel.empty?
|
596
|
-
require "pathname"
|
597
|
-
require "json"
|
598
|
-
filename = File.join Pathname(File.dirname(__FILE__)), "../data", "spanish/palabras#{rand(12)}.json"
|
599
|
-
palabras = JSON.parse(File.read(filename))
|
600
|
-
palabras = palabras.map(&:to_camel_case)
|
601
|
-
@palabras_camel = palabras
|
602
|
-
@palabras_camel_short = @palabras_camel.sample(2000)
|
603
|
-
end
|
604
|
-
words = @palabras_camel
|
605
|
-
words_short = @palabras_camel_short
|
606
|
-
elsif symbol_type == 'p'
|
607
|
-
if @palabras.empty?
|
608
|
-
require "pathname"
|
609
|
-
require "json"
|
610
|
-
filename = File.join Pathname(File.dirname(__FILE__)), "../data", "spanish/palabras#{rand(12)}.json"
|
611
|
-
palabras = JSON.parse(File.read(filename))
|
612
|
-
@palabras = palabras
|
613
|
-
@palabras_short = @palabras.sample(2000)
|
614
|
-
end
|
615
|
-
words = @palabras
|
616
|
-
words_short = @palabras_short
|
617
|
-
end
|
618
|
-
|
619
|
-
wordr = ""
|
620
|
-
wordr_array = []
|
621
|
-
tries = 0
|
622
|
-
while wordr.length < min_length
|
623
|
-
tries += 1
|
624
|
-
length = max_length - wordr.length
|
625
|
-
if tries > 1000
|
626
|
-
wordr += 'A'*length
|
627
|
-
break
|
628
|
-
end
|
629
|
-
if symbol_type == 'w' or symbol_type == "p"
|
630
|
-
length = length -1 if wordr_array.size>0
|
631
|
-
res = (words_short.select { |word| word.length <= length && word.length!=length-1 && word.length!=length-2 && word.length!=length-3 }).sample.to_s
|
632
|
-
unless res.to_s==''
|
633
|
-
wordr_array<<res
|
634
|
-
wordr = wordr_array.join(@word_separator)
|
635
|
-
end
|
636
|
-
else
|
637
|
-
wordr += (words_short.select { |word| word.length <= length && word.length!=length-1 && word.length!=length-2 && word.length!=length-3}).sample.to_s
|
638
|
-
end
|
639
|
-
if (tries % 100) == 0
|
640
|
-
words_short = words.sample(2000)
|
641
|
-
end
|
642
|
-
end
|
643
|
-
good_result = true
|
644
|
-
string = wordr
|
645
|
-
|
646
|
-
elsif (symbol_type == '@' or symbol_type == '!@') and length > 0
|
647
|
-
if min_length > 6 and length < 6
|
648
|
-
length = 6
|
649
|
-
end
|
650
|
-
if deny_pattern and
|
651
|
-
(expected_errors.include?(:required_data) or expected_errors.include?(:excluded_data) or
|
652
|
-
expected_errors.include?(:string_set_not_allowed))
|
653
|
-
expected_errors_left.push(:value)
|
654
|
-
expected_errors.push(:value)
|
655
|
-
expected_errors.uniq!
|
656
|
-
expected_errors_left.uniq!
|
657
|
-
end
|
658
|
-
|
659
|
-
expected_errors_left_orig = expected_errors_left.dup
|
660
|
-
tries = 0
|
661
|
-
begin
|
662
|
-
expected_errors_left = expected_errors_left_orig.dup
|
663
|
-
tries += 1
|
664
|
-
string = ''
|
665
|
-
alpha_set = ALPHA_SET_LOWER + ALPHA_SET_CAPITAL
|
666
|
-
string_set = alpha_set + NUMBER_SET + ['.'] + ['_'] + ['-']
|
667
|
-
string_set_not_allowed = all_characters_set - string_set
|
668
|
-
|
669
|
-
extension = '.'
|
670
|
-
at_sign = '@'
|
671
|
-
|
672
|
-
if expected_errors_left.include?(:value)
|
673
|
-
if rand(2) == 1
|
674
|
-
extension = (all_characters_set - ['.']).sample
|
675
|
-
expected_errors_left.delete(:value)
|
676
|
-
expected_errors_left.delete(:required_data)
|
677
|
-
end
|
678
|
-
if rand(2) == 1
|
679
|
-
1.upto(rand(7)) {|i| extension << alpha_set.sample.downcase
|
680
|
-
}
|
681
|
-
(rand(extension.size) + 1).times {
|
682
|
-
extension[rand(extension.size)] = (string_set - alpha_set - ['.']).sample
|
683
|
-
}
|
684
|
-
expected_errors_left.delete(:value)
|
685
|
-
else
|
686
|
-
1.upto(rand(3) + 2) {|i| extension << alpha_set.sample.downcase
|
687
|
-
}
|
688
|
-
end
|
689
|
-
if rand(2) == 1
|
690
|
-
at_sign = (string_set - ['@']).sample
|
691
|
-
expected_errors_left.delete(:value)
|
692
|
-
expected_errors_left.delete(:required_data)
|
693
|
-
end
|
694
|
-
else
|
695
|
-
if length > 6
|
696
|
-
1.upto(rand(3) + 2) {|i| extension << alpha_set.sample.downcase
|
697
|
-
}
|
698
|
-
else
|
699
|
-
1.upto(2) {|i| extension << alpha_set.sample.downcase
|
700
|
-
}
|
701
|
-
end
|
702
|
-
end
|
703
|
-
length_e = length - extension.size - 1
|
704
|
-
length1 = rand(length_e - 1) + 1
|
705
|
-
length2 = length_e - length1
|
706
|
-
1.upto(length1) {|i| string << string_set.sample}
|
707
|
-
|
708
|
-
string << at_sign
|
709
|
-
|
710
|
-
domain = ''
|
711
|
-
domain_set = alpha_set + NUMBER_SET + ['.'] + ['-']
|
712
|
-
1.upto(length2) {|i| domain << domain_set.sample.downcase
|
713
|
-
}
|
714
|
-
|
715
|
-
if expected_errors.include?(:value) and rand(2) == 1 and domain.size > 0
|
716
|
-
(rand(domain.size) + 1).times {
|
717
|
-
domain[rand(domain.size)] = (all_characters_set - domain_set).sample
|
718
|
-
}
|
719
|
-
expected_errors_left.delete(:value)
|
720
|
-
end
|
721
|
-
string << domain << extension
|
722
|
-
|
723
|
-
if expected_errors_left.include?(:value) or expected_errors_left.include?(:string_set_not_allowed)
|
724
|
-
(rand(string.size) + 1).times {
|
725
|
-
string[rand(string.size)] = string_set_not_allowed.sample
|
726
|
-
}
|
727
|
-
expected_errors_left.delete(:value)
|
728
|
-
expected_errors_left.delete(:string_set_not_allowed)
|
729
|
-
end
|
730
|
-
|
731
|
-
error_regular_expression = false
|
732
|
-
|
733
|
-
if deny_pattern and expected_errors.include?(:length)
|
734
|
-
good_result = true #it is already with wrong length
|
735
|
-
else
|
736
|
-
# I'm doing this because many times the regular expression checking hangs with these characters
|
737
|
-
wrong = %w(.. __ -- ._ _. .- -. _- -_ @. @_ @- .@ _@ -@ @@)
|
738
|
-
if !(Regexp.union(*wrong) === string) #don't include any or the wrong strings
|
739
|
-
if string.index('@').to_i > 0 and
|
740
|
-
string[0..(string.index('@') - 1)].scan(/([a-z0-9]+([\+\._\-][a-z0-9]|)*)/i).join == string[0..(string.index('@') - 1)] and
|
741
|
-
string[(string.index('@') + 1)..-1].scan(/([0-9a-z]+([\.-][a-z0-9]|)*)/i).join == string[string[(string.index('@') + 1)..-1]]
|
742
|
-
error_regular_expression = false
|
743
|
-
else
|
744
|
-
error_regular_expression = true
|
745
|
-
end
|
746
|
-
else
|
747
|
-
error_regular_expression = true
|
748
|
-
end
|
749
|
-
|
750
|
-
if expected_errors.size == 0
|
751
|
-
if error_regular_expression
|
752
|
-
good_result = false
|
753
|
-
else
|
754
|
-
good_result = true
|
755
|
-
end
|
756
|
-
elsif expected_errors_left.size == 0 and
|
757
|
-
(expected_errors - [:length, :min_length, :max_length]).size == 0
|
758
|
-
good_result = true
|
759
|
-
elsif expected_errors != [:length]
|
760
|
-
if !error_regular_expression
|
761
|
-
good_result = false
|
762
|
-
elsif expected_errors.include?(:value)
|
763
|
-
good_result = true
|
764
|
-
end
|
765
|
-
end
|
766
|
-
end
|
767
|
-
|
768
|
-
end until good_result or tries > 100
|
769
|
-
unless good_result
|
770
|
-
puts "Not possible to generate an email on StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
771
|
-
return ''
|
772
|
-
end
|
773
|
-
end
|
774
|
-
if @dont_repeat
|
775
|
-
if @cache_values[pattern.to_s].nil?
|
776
|
-
@cache_values[pattern.to_s] = Array.new()
|
777
|
-
@cache_values[pattern.to_s].push(string)
|
778
|
-
good_result = true
|
779
|
-
elsif @cache_values[pattern.to_s].include?(string)
|
780
|
-
good_result = false
|
781
|
-
else
|
782
|
-
@cache_values[pattern.to_s].push(string)
|
783
|
-
good_result = true
|
784
|
-
end
|
785
|
-
end
|
786
|
-
if pattern.kind_of?(Symbol) and patt.unique
|
787
|
-
if @cache_values[pattern.__id__].nil?
|
788
|
-
@cache_values[pattern.__id__] = Array.new()
|
789
|
-
@cache_values[pattern.__id__].push(string)
|
790
|
-
good_result = true
|
791
|
-
elsif @cache_values[pattern.__id__].include?(string)
|
792
|
-
good_result = false
|
793
|
-
else
|
794
|
-
@cache_values[pattern.__id__].push(string)
|
795
|
-
good_result = true
|
796
|
-
end
|
797
|
-
end
|
798
|
-
end until good_result or tries > 10000
|
799
|
-
unless good_result
|
800
|
-
puts "Not possible to generate the string on StringPattern.generate: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
801
|
-
puts "Take in consideration if you are using StringPattern.dont_repeat=true that you don't try to generate more strings that are possible to be generated"
|
802
|
-
return ''
|
803
|
-
end
|
804
|
-
|
805
|
-
return string
|
806
|
-
end
|
807
|
-
|
808
|
-
|
809
|
-
##############################################
|
810
|
-
# This method is defined to validate if the text_to_validate supplied follows the pattern
|
811
|
-
# It works also with array of patterns but in that case will return only true or false
|
812
|
-
# input:
|
813
|
-
# text (String) (synonyms: text_to_validate, validate) -- The text to validate
|
814
|
-
# pattern -- symbol with this info: "length:symbol_type" or "min_length-max_length:symbol_type"
|
815
|
-
# min_length -- minimum length of the string
|
816
|
-
# max_length (optional) -- maximum length of the string. If not provided the result will be with the min_length provided
|
817
|
-
# symbol_type -- the type of the string we want.
|
818
|
-
# expected_errors (Array of symbols) (optional) (synonyms: errors) -- :length, :min_length, :max_length, :value, :required_data, :excluded_data, :string_set_not_allowed
|
819
|
-
# not_expected_errors (Array of symbols) (optional) (synonyms: not_errors, non_expected_errors) -- :length, :min_length, :max_length, :value, :required_data, :excluded_data, :string_set_not_allowed
|
820
|
-
# example:
|
821
|
-
# validate(text: "This text will be validated", pattern: :"10-20:Xn", expected_errors: [:value, :max_length])
|
822
|
-
#
|
823
|
-
# Output:
|
824
|
-
# if expected_errors and not_expected_errors are not supplied: an array with all detected errors
|
825
|
-
# if expected_errors or not_expected_errors supplied: true or false
|
826
|
-
# if array of patterns supplied, it will return true or false
|
827
|
-
###############################################
|
828
|
-
def StringPattern.validate(text: '', pattern: '', expected_errors: [], not_expected_errors: [], **synonyms)
|
829
|
-
text_to_validate = text
|
830
|
-
text_to_validate = synonyms[:text_to_validate] if synonyms.keys.include?(:text_to_validate)
|
831
|
-
text_to_validate = synonyms[:validate] if synonyms.keys.include?(:validate)
|
832
|
-
expected_errors = synonyms[:errors] if synonyms.keys.include?(:errors)
|
833
|
-
not_expected_errors = synonyms[:not_errors] if synonyms.keys.include?(:not_errors)
|
834
|
-
not_expected_errors = synonyms[:non_expected_errors] if synonyms.keys.include?(:non_expected_errors)
|
835
|
-
#:length, :min_length, :max_length, :value, :required_data, :excluded_data, :string_set_not_allowed
|
836
|
-
if (expected_errors.include?(:min_length) or expected_errors.include?(:max_length)) and !expected_errors.include?(:length)
|
837
|
-
expected_errors.push(:length)
|
838
|
-
end
|
839
|
-
if (not_expected_errors.include?(:min_length) or not_expected_errors.include?(:max_length)) and !not_expected_errors.include?(:length)
|
840
|
-
not_expected_errors.push(:length)
|
841
|
-
end
|
842
|
-
if pattern.kind_of?(Array) and pattern.size == 1
|
843
|
-
pattern = pattern[0]
|
844
|
-
elsif pattern.kind_of?(Array) and pattern.size > 1 then
|
845
|
-
total_min_length = 0
|
846
|
-
total_max_length = 0
|
847
|
-
all_errors_collected = Array.new
|
848
|
-
result = true
|
849
|
-
num_patt = 0
|
850
|
-
patterns = Array.new
|
851
|
-
pattern.each {|pat|
|
852
|
-
if (pat.kind_of?(String) and (!StringPattern.optimistic or
|
853
|
-
(StringPattern.optimistic and pat.to_s.scan(/(\d+)-(\d+):(.+)/).size == 0 and pat.to_s.scan(/^!?(\d+):(.+)/).size == 0))) #fixed text
|
854
|
-
symbol_type = ''
|
855
|
-
min_length = max_length = pat.length
|
856
|
-
elsif pat.kind_of?(Symbol) or (pat.kind_of?(String) and StringPattern.optimistic and
|
857
|
-
(pat.to_s.scan(/(\d+)-(\d+):(.+)/).size > 0 or pat.to_s.scan(/^!?(\d+):(.+)/).size > 0))
|
858
|
-
patt = StringPattern.analyze(pat)
|
859
|
-
min_length = patt.min_length
|
860
|
-
max_length = patt.max_length
|
861
|
-
symbol_type = patt.symbol_type
|
862
|
-
else
|
863
|
-
puts "String pattern class not supported (#{pat.class} for #{pat})"
|
864
|
-
end
|
865
|
-
|
866
|
-
patterns.push({pattern: pat, min_length: min_length, max_length: max_length, symbol_type: symbol_type})
|
867
|
-
|
868
|
-
total_min_length += min_length
|
869
|
-
total_max_length += max_length
|
870
|
-
|
871
|
-
if num_patt == (pattern.size - 1) # i am in the last one
|
872
|
-
if text_to_validate.length < total_min_length
|
873
|
-
all_errors_collected.push(:length)
|
874
|
-
all_errors_collected.push(:min_length)
|
875
|
-
end
|
876
|
-
|
877
|
-
if text_to_validate.length > total_max_length
|
878
|
-
all_errors_collected.push(:length)
|
879
|
-
all_errors_collected.push(:max_length)
|
880
|
-
end
|
881
|
-
|
882
|
-
end
|
883
|
-
num_patt += 1
|
884
|
-
|
885
|
-
|
886
|
-
}
|
887
|
-
|
888
|
-
num_patt = 0
|
889
|
-
patterns.each {|patt|
|
890
|
-
|
891
|
-
tmp_result = false
|
892
|
-
(patt[:min_length]..patt[:max_length]).each {|n|
|
893
|
-
res = StringPattern.validate(text: text_to_validate[0..n - 1], pattern: patt[:pattern], not_expected_errors: not_expected_errors)
|
894
|
-
if res.kind_of?(Array)
|
895
|
-
all_errors_collected += res
|
896
|
-
end
|
897
|
-
|
898
|
-
if res.kind_of?(TrueClass) or (res.kind_of?(Array) and res.size == 0) #valid
|
899
|
-
#we pass in the next one the rest of the pattern array list: pattern: pattern[num_patt+1..pattern.size]
|
900
|
-
res = StringPattern.validate(text: text_to_validate[n..text_to_validate.length], pattern: pattern[num_patt + 1..pattern.size], expected_errors: expected_errors, not_expected_errors: not_expected_errors)
|
901
|
-
|
902
|
-
if res.kind_of?(Array)
|
903
|
-
if ((all_errors_collected + res) - expected_errors).size > 0
|
904
|
-
tmp_result = false
|
905
|
-
else
|
906
|
-
all_errors_collected += res
|
907
|
-
tmp_result = true
|
908
|
-
end
|
909
|
-
elsif res.kind_of?(TrueClass) then
|
910
|
-
tmp_result = true
|
911
|
-
end
|
912
|
-
return true if tmp_result
|
913
|
-
end
|
914
|
-
}
|
915
|
-
|
916
|
-
unless tmp_result
|
917
|
-
return false
|
918
|
-
end
|
919
|
-
num_patt += 1
|
920
|
-
}
|
921
|
-
return result
|
922
|
-
end
|
923
|
-
|
924
|
-
if (pattern.kind_of?(String) and (!StringPattern.optimistic or
|
925
|
-
(StringPattern.optimistic and pattern.to_s.scan(/(\d+)-(\d+):(.+)/).size == 0 and pattern.to_s.scan(/^!?(\d+):(.+)/).size == 0))) #fixed text
|
926
|
-
symbol_type = ''
|
927
|
-
min_length = max_length = pattern.length
|
928
|
-
else #symbol
|
929
|
-
patt = StringPattern.analyze(pattern)
|
930
|
-
min_length = patt.min_length
|
931
|
-
max_length = patt.max_length
|
932
|
-
symbol_type = patt.symbol_type
|
933
|
-
|
934
|
-
required_data = patt.required_data
|
935
|
-
excluded_data = patt.excluded_data
|
936
|
-
string_set = patt.string_set
|
937
|
-
all_characters_set = patt.all_characters_set
|
938
|
-
|
939
|
-
required_chars = Array.new
|
940
|
-
required_data.each {|rd|
|
941
|
-
required_chars << rd if rd.size == 1
|
942
|
-
}
|
943
|
-
if (required_chars.flatten & excluded_data.flatten).size > 0
|
944
|
-
puts "pattern argument not valid on StringPattern.validate, a character cannot be required and excluded at the same time: #{pattern.inspect}, expected_errors: #{expected_errors.inspect}"
|
945
|
-
return ''
|
946
|
-
end
|
947
|
-
|
948
|
-
end
|
949
|
-
|
950
|
-
if text_to_validate.nil?
|
951
|
-
return false
|
952
|
-
end
|
953
|
-
detected_errors = Array.new
|
954
|
-
|
955
|
-
if text_to_validate.length < min_length
|
956
|
-
detected_errors.push(:min_length)
|
957
|
-
detected_errors.push(:length)
|
958
|
-
end
|
959
|
-
if text_to_validate.length > max_length
|
960
|
-
detected_errors.push(:max_length)
|
961
|
-
detected_errors.push(:length)
|
962
|
-
end
|
963
|
-
|
964
|
-
if symbol_type == '' #fixed text
|
965
|
-
if pattern.to_s != text.to_s #not equal
|
966
|
-
detected_errors.push(:value)
|
967
|
-
detected_errors.push(:required_data)
|
968
|
-
end
|
969
|
-
else # pattern supplied
|
970
|
-
if symbol_type != '@'
|
971
|
-
if required_data.size > 0
|
972
|
-
required_data.each {|rd|
|
973
|
-
if (text_to_validate.chars & rd).size == 0
|
974
|
-
detected_errors.push(:value)
|
975
|
-
detected_errors.push(:required_data)
|
976
|
-
break
|
977
|
-
end
|
978
|
-
}
|
979
|
-
end
|
980
|
-
if excluded_data.size > 0
|
981
|
-
if (excluded_data & text_to_validate.chars).size > 0
|
982
|
-
detected_errors.push(:value)
|
983
|
-
detected_errors.push(:excluded_data)
|
984
|
-
end
|
985
|
-
end
|
986
|
-
string_set_not_allowed = all_characters_set - string_set
|
987
|
-
text_to_validate.chars.each {|st|
|
988
|
-
if string_set_not_allowed.include?(st)
|
989
|
-
detected_errors.push(:value)
|
990
|
-
detected_errors.push(:string_set_not_allowed)
|
991
|
-
break
|
992
|
-
end
|
993
|
-
}
|
994
|
-
else #symbol_type=="@"
|
995
|
-
string = text_to_validate
|
996
|
-
wrong = %w(.. __ -- ._ _. .- -. _- -_ @. @_ @- .@ _@ -@ @@)
|
997
|
-
if !(Regexp.union(*wrong) === string) #don't include any or the wrong strings
|
998
|
-
if string.index('@').to_i > 0 and
|
999
|
-
string[0..(string.index('@') - 1)].scan(/([a-z0-9]+([\+\._\-][a-z0-9]|)*)/i).join == string[0..(string.index('@') - 1)] and
|
1000
|
-
string[(string.index('@') + 1)..-1].scan(/([0-9a-z]+([\.-][a-z0-9]|)*)/i).join == string[string[(string.index('@') + 1)..-1]]
|
1001
|
-
error_regular_expression = false
|
1002
|
-
else
|
1003
|
-
error_regular_expression = true
|
1004
|
-
end
|
1005
|
-
else
|
1006
|
-
error_regular_expression = true
|
1007
|
-
end
|
1008
|
-
|
1009
|
-
if error_regular_expression
|
1010
|
-
detected_errors.push(:value)
|
1011
|
-
end
|
1012
|
-
|
1013
|
-
end
|
1014
|
-
end
|
1015
|
-
|
1016
|
-
if expected_errors.size == 0 and not_expected_errors.size == 0
|
1017
|
-
return detected_errors
|
1018
|
-
else
|
1019
|
-
if expected_errors & detected_errors == expected_errors
|
1020
|
-
if (not_expected_errors & detected_errors).size > 0
|
1021
|
-
return false
|
1022
|
-
else
|
1023
|
-
return true
|
1024
|
-
end
|
1025
|
-
else
|
1026
|
-
return false
|
1027
|
-
end
|
1028
|
-
end
|
1029
|
-
end
|
1030
|
-
|
1031
59
|
end
|
1032
|
-
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: string_pattern
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 2.
|
4
|
+
version: 2.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Mario Ruiz
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2019-
|
11
|
+
date: 2019-08-12 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: regexp_parser
|