crm_formatter 1.0.7.pre.rc.1 → 2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -2
- data/.rspec_status +7 -0
- data/.rubocop.yml +10 -0
- data/.rubocop_todo.yml +188 -0
- data/CODE_OF_CONDUCT.md +74 -0
- data/Gemfile +8 -0
- data/LICENSE.txt +21 -0
- data/README.md +202 -145
- data/Rakefile +75 -5
- data/bin/console +15 -0
- data/bin/setup +8 -0
- data/crm_formatter.gemspec +59 -13
- data/lib/crm_formatter.rb +46 -3
- data/lib/crm_formatter/address.rb +143 -122
- data/lib/crm_formatter/{extensions.csv → csv/extensions.csv} +0 -0
- data/lib/crm_formatter/csv/seed.csv +2 -0
- data/lib/crm_formatter/phone.rb +28 -20
- data/lib/crm_formatter/version.rb +4 -2
- data/lib/crm_formatter/web.rb +115 -248
- data/lib/crm_formatter/wrap.rb +54 -0
- data/menu.rb +3 -1
- data/non_utf8_examples.txt +40 -0
- data/result.txt +964 -0
- data/rubocop.json +1 -0
- metadata +211 -16
- data/bin/crm_formatter +0 -4
- data/gem_notes_crm_formatter.txt +0 -138
- data/lib/crm_formatter/helpers.rb +0 -23
File without changes
|
data/lib/crm_formatter/phone.rb
CHANGED
@@ -1,38 +1,46 @@
|
|
1
|
-
|
2
|
-
class Phone
|
1
|
+
# frozen_string_literal: false
|
3
2
|
|
4
|
-
|
3
|
+
module CrmFormatter
|
4
|
+
class Phone
|
5
|
+
## Checks every phone number in table to verify that it meets phone criteria, then calls format_phone method to wrap Valid results. Otherwise destroys Invalid phone fields and associations.
|
5
6
|
|
6
|
-
# Call:
|
7
|
+
# Call: Wrap.new.validate_phone(phone)
|
7
8
|
def validate_phone(phone)
|
8
|
-
phone_hsh = {
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
end
|
9
|
+
phone_hsh = { phone_status: nil, phone: phone, phone_f: nil }
|
10
|
+
return phone_hsh unless phone.present?
|
11
|
+
phone = phone&.gsub(/\s/, ' ')&.strip
|
12
|
+
reg = Regexp.new('[(]?[0-9]{3}[ ]?[)-.]?[ ]?[0-9]{3}[ ]?[-. ][ ]?[0-9]{4}')
|
13
|
+
phone = nil if phone.first == '0' || phone.include?('(0') || !reg.match(phone)
|
14
|
+
phone_hsh[:phone_f] = format_phone(phone) if phone.present?
|
15
|
+
phone_hsh = check_phone_status(phone_hsh)
|
16
16
|
phone_hsh
|
17
17
|
end
|
18
18
|
|
19
|
+
####### COMPARE ORIGINAL AND FORMATTED PHONE ######
|
20
|
+
def check_phone_status(hsh)
|
21
|
+
phone = hsh[:phone]
|
22
|
+
phone_f = hsh[:phone_f]
|
23
|
+
status = 'invalid'
|
24
|
+
status = phone != phone_f ? 'formatted' : 'unchanged' if phone && phone_f
|
25
|
+
hsh[:phone_status] = status if status.present?
|
26
|
+
hsh
|
27
|
+
end
|
28
|
+
|
19
29
|
#################################
|
20
30
|
## FORMATS PHONE AS: (000) 000-0000
|
21
31
|
## Assumes phone is legitimate, then formats. Not designed to detect Valid phone number.
|
22
32
|
|
23
|
-
# Call:
|
33
|
+
# Call: Wrap.new.format_phone(phone)
|
24
34
|
def format_phone(phone)
|
25
|
-
regex = Regexp.new(
|
26
|
-
if !phone.blank? && (phone !=
|
27
|
-
phone_stripped = phone.gsub(/[^0-9]/,
|
28
|
-
|
29
|
-
|
35
|
+
regex = Regexp.new('[A-Z]+[a-z]+')
|
36
|
+
if !phone.blank? && (phone != 'N/A' || phone != '0') && !regex.match(phone)
|
37
|
+
phone_stripped = phone.gsub(/[^0-9]/, '')
|
38
|
+
phone_step2 = phone_stripped && phone_stripped[0] == '1' ? phone_stripped[1..-1] : phone_stripped
|
30
39
|
final_phone = !(phone_step2 && phone_step2.length < 10) ? "(#{phone_step2[0..2]}) #{(phone_step2[3..5])}-#{(phone_step2[6..9])}" : phone
|
31
40
|
else
|
32
41
|
final_phone = nil
|
33
42
|
end
|
34
|
-
|
43
|
+
final_phone
|
35
44
|
end
|
36
|
-
|
37
45
|
end
|
38
46
|
end
|
data/lib/crm_formatter/web.rb
CHANGED
@@ -1,64 +1,59 @@
|
|
1
|
+
# frozen_string_literal: false
|
2
|
+
|
3
|
+
# require 'rubygems'
|
4
|
+
# require 'active_support'
|
1
5
|
require 'csv'
|
2
6
|
|
3
|
-
|
7
|
+
# StartCrm.run_webs
|
8
|
+
module CrmFormatter
|
4
9
|
class Web
|
5
|
-
|
6
|
-
def initialize(args={})
|
7
|
-
@empty_oa = args.empty?
|
8
|
-
@pos_urls = args.fetch(:pos_urls, [])
|
9
|
-
@neg_urls = args.fetch(:neg_urls, [])
|
10
|
-
@pos_links = args.fetch(:pos_links, [])
|
11
|
-
@neg_links = args.fetch(:neg_links, [])
|
12
|
-
@pos_hrefs = args.fetch(:pos_hrefs, [])
|
13
|
-
@neg_hrefs = args.fetch(:neg_hrefs, [])
|
14
|
-
@pos_exts = args.fetch(:pos_exts, [])
|
15
|
-
@neg_exts = args.fetch(:neg_exts, [])
|
16
|
-
@min_length = args.fetch(:min_length, 2)
|
17
|
-
@max_length = args.fetch(:max_length, 100)
|
18
|
-
end
|
19
|
-
|
20
|
-
def banned_symbols
|
21
|
-
banned_symbols = ["!", "$", "%", "'", "(", ")", "*", "+", ",", "<", ">", "@", "[", "]", "^", "{", "}", "~"]
|
22
|
-
end
|
23
|
-
|
24
|
-
##Call: StartCrm.run_webs
|
25
10
|
def format_url(url)
|
26
11
|
prep_result = prep_for_uri(url)
|
27
12
|
url_hash = prep_result[:url_hash]
|
28
13
|
url = prep_result[:url]
|
29
|
-
url = nil if
|
30
|
-
|
31
|
-
if url
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
14
|
+
url = nil if errors?(url_hash)
|
15
|
+
|
16
|
+
if url&.present?
|
17
|
+
url = normalize_url(url)
|
18
|
+
ext_result = validate_extension(url_hash, url)
|
19
|
+
url_hash = ext_result[:url_hash]
|
20
|
+
url = ext_result[:url]
|
21
|
+
(url = nil if errors?(url_hash)) if url.present?
|
36
22
|
end
|
37
23
|
|
38
|
-
url_hash
|
39
|
-
url_hash =
|
24
|
+
url_hash = consolidate_negs(url_hash)
|
25
|
+
url_hash[:url_f] = url
|
26
|
+
url_hash = extract_path(url_hash) if url.present?
|
27
|
+
url_hash = check_web_status(url_hash)
|
40
28
|
url_hash
|
41
29
|
end
|
42
30
|
|
31
|
+
### COMPARE ORIGINAL AND FORMATTED URL ###
|
32
|
+
def check_web_status(hsh)
|
33
|
+
status = 'invalid' if hsh[:web_neg]&.include?('error')
|
43
34
|
|
44
|
-
|
45
|
-
|
46
|
-
if formatted.present?
|
47
|
-
url_hash[:is_reformatted] = url_hash[:url_path] != formatted
|
35
|
+
if hsh[:url] && hsh[:url_f] && status.nil?
|
36
|
+
status = hsh[:url] != hsh[:url_f] ? 'formatted' : 'unchanged'
|
48
37
|
end
|
49
|
-
|
38
|
+
|
39
|
+
hsh[:web_status] = status if status.present?
|
40
|
+
hsh
|
50
41
|
end
|
51
42
|
|
43
|
+
def consolidate_negs(hsh)
|
44
|
+
neg = hsh[:web_neg].join(', ')
|
45
|
+
hsh[:web_neg] = neg.present? ? neg : nil
|
46
|
+
hsh
|
47
|
+
end
|
52
48
|
|
53
|
-
def
|
54
|
-
errors = url_hash[:
|
49
|
+
def errors?(url_hash)
|
50
|
+
errors = url_hash[:web_neg].map { |web_neg| web_neg.include?('error') }
|
55
51
|
errors.any?
|
56
52
|
end
|
57
53
|
|
58
|
-
|
59
|
-
##Call: StartCrm.run_webs
|
60
54
|
def prep_for_uri(url)
|
61
|
-
url_hash = {
|
55
|
+
url_hash = { web_status: nil, url: url, url_f: nil, url_path: nil, web_neg: [] }
|
56
|
+
|
62
57
|
begin
|
63
58
|
url = url&.split('|')&.first
|
64
59
|
url = url&.split('\\')&.first
|
@@ -74,236 +69,108 @@ module CRMFormatter
|
|
74
69
|
url = url[0..-2] if url.present? && url[-1] == '/'
|
75
70
|
end
|
76
71
|
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
url_hash
|
81
|
-
url_hash =
|
82
|
-
else
|
83
|
-
url_hash[:neg] << "error: syntax"
|
84
|
-
url_hash[:formatted_url] = url
|
72
|
+
banned_symbols = ['!', '$', '%', "'", '(', ')', '*', '+', ',', '<', '>', '@', '[', ']', '^', '{', '}', '~']
|
73
|
+
url = nil if url.present? && banned_symbols.any? { |symb| url&.include?(symb) }
|
74
|
+
unless url.present?
|
75
|
+
url_hash[:web_neg] << 'error: syntax'
|
76
|
+
url_hash[:url_f] = url
|
85
77
|
end
|
86
|
-
|
87
|
-
|
88
|
-
url_hash[:neg] << "error: #{e}"
|
89
|
-
url = nil
|
90
|
-
url_hash
|
91
|
-
end
|
92
|
-
|
93
|
-
prep_result = { url_hash: url_hash, url: url }
|
94
|
-
end
|
95
|
-
|
96
|
-
|
97
|
-
##Call: StartCrm.run_webs
|
98
|
-
def run_uri(url_hash, url)
|
99
|
-
begin
|
100
|
-
uri = URI(url)
|
101
|
-
host_parts = uri.host&.split(".")
|
102
|
-
|
103
|
-
url_hash = compare_criteria(url_hash, host_parts, 'pos_exts', 'equal') if !@empty_oa
|
104
|
-
url_hash = compare_criteria(url_hash, host_parts, 'neg_exts', 'equal') if !@empty_oa
|
105
|
-
|
106
|
-
host = uri.host
|
107
|
-
scheme = uri.scheme
|
108
|
-
url = "#{scheme}://#{host}" if host.present? && scheme.present?
|
109
|
-
url = "http://#{url}" if url[0..3] != "http"
|
110
|
-
url = url.gsub("//", "//www.") if !url.include?("www.")
|
111
|
-
samp_url = convert_to_scheme_host(url)
|
112
|
-
|
113
|
-
url = convert_to_scheme_host(url) if url.present?
|
114
|
-
url_extens_result = check_url_extens(url_hash, url)
|
115
|
-
url_hash = url_extens_result[:url_hash]
|
116
|
-
url = url_extens_result[:url]
|
117
|
-
|
118
|
-
rescue Exception => e
|
119
|
-
url_hash[:neg] << "error: #{e}"
|
78
|
+
rescue StandardError => error
|
79
|
+
url_hash[:web_neg] << "error: #{error}"
|
120
80
|
url = nil
|
121
81
|
url_hash
|
122
82
|
end
|
123
|
-
|
124
|
-
|
125
|
-
end
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
|
146
|
-
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
|
155
|
-
|
156
|
-
|
157
|
-
|
158
|
-
|
159
|
-
|
160
|
-
if criteria_list.present?
|
161
|
-
if target.is_a?(::String)
|
162
|
-
tars = target.split(', ')
|
163
|
-
else
|
164
|
-
tars = target
|
165
|
-
end
|
166
|
-
|
167
|
-
pn_matches = tars.map do |tar|
|
168
|
-
if criteria_list.present?
|
169
|
-
if include_or_equal == 'include'
|
170
|
-
criteria_list.select { |el| el if tar.include?(el) }.join(', ')
|
171
|
-
elsif include_or_equal == 'equal'
|
172
|
-
criteria_list.select { |el| el if tar == el }.join(', ')
|
173
|
-
end
|
174
|
-
end
|
175
|
-
end
|
176
|
-
|
177
|
-
pn_match = pn_matches&.uniq&.sort&.join(', ')
|
178
|
-
if pn_match.present?
|
179
|
-
if list_name.include?('neg')
|
180
|
-
hash[:neg] << "#{list_name}: #{pn_match}"
|
181
|
-
else
|
182
|
-
hash[:pos] << "#{list_name}: #{pn_match}"
|
183
|
-
end
|
184
|
-
end
|
185
|
-
end
|
186
|
-
|
83
|
+
hsh = { url_hash: url_hash, url: url }
|
84
|
+
hsh
|
85
|
+
end
|
86
|
+
|
87
|
+
def normalize_url(url)
|
88
|
+
return unless url.present?
|
89
|
+
uri = URI(url)
|
90
|
+
scheme = uri&.scheme
|
91
|
+
host = uri&.host
|
92
|
+
url = "#{scheme}://#{host}" if host.present? && scheme.present?
|
93
|
+
url = "http://#{url}" if url[0..3] != 'http'
|
94
|
+
|
95
|
+
return unless url.present?
|
96
|
+
url.gsub!('//', '//www.') unless url.include?('www.')
|
97
|
+
url
|
98
|
+
end
|
99
|
+
|
100
|
+
# Source: http://www.iana.org/domains/root/db
|
101
|
+
# Text: http://data.iana.org/TLD/tlds-alpha-by-domain.txt
|
102
|
+
def validate_extension(url_hash, url)
|
103
|
+
return unless url.present?
|
104
|
+
uri_parts = URI(url).host&.split('.')
|
105
|
+
url_exts = uri_parts[2..-1]
|
106
|
+
|
107
|
+
### Finds Errors
|
108
|
+
if url_exts.empty? ## Missing ext.
|
109
|
+
err_msg = 'error: ext.none'
|
110
|
+
else ## Has ext(s), but need to verify validity and count.
|
111
|
+
file_path = './lib/crm_formatter/csv/extensions.csv'
|
112
|
+
iana_list = CSV.read(file_path).flatten
|
113
|
+
matched_exts = iana_list & url_exts
|
114
|
+
|
115
|
+
if matched_exts.empty? ## Has ext, but not valid.
|
116
|
+
err_msg = "error: ext.invalid [#{url_exts.join(', ')}]"
|
117
|
+
elsif matched_exts.count > 1 ## Has too many valid exts, Limit 1.
|
118
|
+
err_msg = "error: ext.valid > 1 [#{matched_exts.join(', ')}]"
|
187
119
|
end
|
188
120
|
end
|
189
|
-
|
190
|
-
hash
|
191
|
-
end
|
192
|
-
|
193
|
-
###### Supporting Methods Below #######
|
194
|
-
|
195
|
-
def extract_link(url_path)
|
196
|
-
url_hash = format_url(url_path)
|
197
|
-
url = url_hash[:formatted_url]
|
198
|
-
link = url_path
|
199
|
-
link_hsh = {url_path: url_path, url: url, link: nil }
|
200
|
-
if url.present? && link.present? && link.length > @min_length
|
201
|
-
url = strip_down_url(url)
|
202
|
-
link = strip_down_url(link)
|
203
|
-
link&.gsub!(url, '')
|
204
|
-
link = link&.split('.net')&.last
|
205
|
-
link = link&.split('.com')&.last
|
206
|
-
link = link&.split('.org')&.last
|
207
|
-
link = "/#{link.split("/").reject(&:empty?).join("/")}" if link.present?
|
208
|
-
link_hsh[:link] = link if link.present? && link.length > @min_length
|
209
|
-
end
|
210
|
-
link_hsh
|
211
|
-
end
|
212
121
|
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
url = url.split('://')
|
219
|
-
url = url[-1]
|
220
|
-
return url
|
122
|
+
if err_msg
|
123
|
+
url_hash[:web_neg] << err_msg
|
124
|
+
url = nil
|
125
|
+
url_hash[:url_f] = nil
|
126
|
+
return { url_hash: url_hash, url: url }
|
221
127
|
end
|
222
|
-
end
|
223
|
-
|
224
128
|
|
225
|
-
|
226
|
-
|
227
|
-
if
|
228
|
-
|
229
|
-
|
230
|
-
flags << "below #{@min_length}" if link.length < @min_length
|
231
|
-
flags << "over #{@max_length}" if link.length > @max_length
|
232
|
-
flags = flags.flatten.compact
|
233
|
-
flags.any? ? valid_link = nil : valid_link = link
|
234
|
-
link_hsh[:valid_link] = valid_link
|
235
|
-
link_hsh[:flags] = flags.join(', ')
|
129
|
+
### Only Non-Errors Get Here ###
|
130
|
+
## Has one valid ext, but need to check if original url exts were > 1. Replace if so.
|
131
|
+
if url_exts.count > matched_exts.count
|
132
|
+
inv_ext = (url_exts - matched_exts).join
|
133
|
+
url = url.gsub(".#{inv_ext}", '')
|
236
134
|
end
|
237
|
-
link_hsh
|
238
|
-
end
|
239
|
-
|
240
|
-
|
241
|
-
def remove_invalid_hrefs(href)
|
242
|
-
href_hsh = {href: href, valid_href: nil, flags: nil }
|
243
|
-
if href.present?
|
244
|
-
@neg_hrefs += get_symbs
|
245
|
-
href = href.split('|').join(' ')
|
246
|
-
href = href.split('/').join(' ')
|
247
|
-
href&.gsub!("(", ' ')
|
248
|
-
href&.gsub!(")", ' ')
|
249
|
-
href&.gsub!("[", ' ')
|
250
|
-
href&.gsub!("]", ' ')
|
251
|
-
href&.gsub!(",", ' ')
|
252
|
-
href&.gsub!("'", ' ')
|
253
135
|
|
254
|
-
|
255
|
-
|
256
|
-
invalid_text = Regexp.new(/[0-9]/)
|
257
|
-
flags << invalid_text&.match(href)
|
258
|
-
href = href&.downcase
|
259
|
-
href = href&.strip
|
260
|
-
|
261
|
-
flags << @neg_hrefs.select { |red| href&.include?(red) }
|
262
|
-
flags = flags.flatten.compact.uniq
|
263
|
-
href_hsh[:valid_href] = href unless flags.any?
|
264
|
-
href_hsh[:flags] = flags.join(', ')
|
265
|
-
end
|
266
|
-
href_hsh
|
136
|
+
ext_result = { url_hash: url_hash, url: url }
|
137
|
+
ext_result
|
267
138
|
end
|
268
139
|
|
140
|
+
###### Supporting Methods Below #######
|
269
141
|
|
270
|
-
def
|
271
|
-
|
272
|
-
|
273
|
-
|
274
|
-
|
275
|
-
|
276
|
-
return url
|
142
|
+
def extract_path(url_hash)
|
143
|
+
path_parts = url_hash[:url_f].split('//').last.split('/')[1..-1]
|
144
|
+
path = "/#{path_parts.join('/')}"
|
145
|
+
if path&.length > 2
|
146
|
+
url_hash[:url_path] = path
|
147
|
+
url_hash[:url_f] = url_hash[:url_f].gsub(url_hash[:url_path], '')
|
277
148
|
end
|
149
|
+
url_hash
|
278
150
|
end
|
279
151
|
|
280
|
-
|
281
|
-
#CALL: Formatter.new.remove_ww3(url)
|
152
|
+
# CALL: Wrap.new.remove_ww3(url)
|
282
153
|
def remove_ww3(url)
|
283
|
-
|
284
|
-
|
285
|
-
|
286
|
-
|
154
|
+
return unless url.present?
|
155
|
+
url.split('.').map { |part| url.gsub!(part, 'www') if part.scan(/ww[0-9]/).any? }
|
156
|
+
url&.gsub!('www.www', 'www')
|
157
|
+
url
|
287
158
|
end
|
288
159
|
|
289
|
-
|
290
160
|
# For rare cases w/ urls with mistaken double slash twice.
|
291
161
|
def remove_slashes(url)
|
292
|
-
|
293
|
-
|
294
|
-
|
295
|
-
|
296
|
-
|
297
|
-
|
298
|
-
|
299
|
-
|
300
|
-
#
|
301
|
-
#
|
302
|
-
#
|
303
|
-
#
|
304
|
-
# extensions = CSV.read(file_path)
|
162
|
+
return url unless url.present? && url.include?('//')
|
163
|
+
parts = url.split('//')
|
164
|
+
return parts[0..1].join if parts.length > 2
|
165
|
+
url
|
166
|
+
end
|
167
|
+
|
168
|
+
# def strip_down_url(url)
|
169
|
+
# return unless url.present?
|
170
|
+
# url = url.downcase.strip
|
171
|
+
# url = url.gsub('www.', '')
|
172
|
+
# url = url.split('://')
|
173
|
+
# url[-1]
|
305
174
|
# end
|
306
|
-
|
307
|
-
|
308
175
|
end
|
309
176
|
end
|