email_signature_parser 0.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/README.md +105 -0
- data/lib/email_signature_parser/data/job_titles/acronyms.yaml +440 -0
- data/lib/email_signature_parser/data/job_titles/titles.yaml +182 -0
- data/lib/email_signature_parser/data/job_titles/titles_es.yaml +417 -0
- data/lib/email_signature_parser/html_text_parser.rb +181 -0
- data/lib/email_signature_parser/parser.rb +885 -0
- data/lib/email_signature_parser/utils.rb +19 -0
- data/lib/email_signature_parser.rb +32 -0
- metadata +233 -0
@@ -0,0 +1,19 @@
|
|
1
|
+
module EmailSignatureParser
|
2
|
+
module Utils
|
3
|
+
|
4
|
+
def self.max_consecutive_digits(text)
|
5
|
+
return 0 if text.nil? || text.empty?
|
6
|
+
|
7
|
+
# Replace gaps of 1-2 non-digit characters between digits with empty string
|
8
|
+
# This effectively makes digits separated by small gaps appear consecutive
|
9
|
+
processed_text = text.gsub(/(\d)[^\da-zA-Z]{1,2}(?=\d)/, '\1')
|
10
|
+
|
11
|
+
# Find all sequences of consecutive digits
|
12
|
+
digit_sequences = processed_text.scan(/\d+/)
|
13
|
+
|
14
|
+
# Return the length of the longest sequence
|
15
|
+
digit_sequences.map(&:length).max || 0
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
# modules
|
3
|
+
#
|
4
|
+
require 'facets/string'
|
5
|
+
require 'mail'
|
6
|
+
require 'ox'
|
7
|
+
require 'ruby_postal/parser'
|
8
|
+
require 'public_suffix'
|
9
|
+
require 'yaml'
|
10
|
+
require 'cgi'
|
11
|
+
|
12
|
+
require_relative "email_signature_parser/parser"
|
13
|
+
require_relative "email_signature_parser/html_text_parser"
|
14
|
+
require_relative "email_signature_parser/utils"
|
15
|
+
|
16
|
+
module EmailSignatureParser
|
17
|
+
def self.from_file(file_path)
|
18
|
+
parser = EmailSignatureParser::Parser.new
|
19
|
+
parser.parse_from_file(file_path)
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.from_html(from, email_body)
|
23
|
+
parser = EmailSignatureParser::Parser.new
|
24
|
+
parser.parse_from_html(from, email_body)
|
25
|
+
end
|
26
|
+
|
27
|
+
def self.from_text(from, email_body)
|
28
|
+
parser = EmailSignatureParser::Parser.new
|
29
|
+
parser.parse_from_text(from, email_body)
|
30
|
+
end
|
31
|
+
|
32
|
+
end
|
metadata
ADDED
@@ -0,0 +1,233 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: email_signature_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Guillermo Molini
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2025-10-15 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: ruby_postal
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.0'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: ox
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '2.14'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '2.14'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: mail
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '2.5'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '2.5'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: public_suffix
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '5.0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '5.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: facets
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '3.1'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '3.1'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: rspec
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '3.0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '3.0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: bundler
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '2.0'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '2.0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: rake
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '13.0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '13.0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: simplecov
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: pry
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - ">="
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
type: :development
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - ">="
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '0'
|
153
|
+
- !ruby/object:Gem::Dependency
|
154
|
+
name: listen
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - "~>"
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: '3.0'
|
160
|
+
type: :development
|
161
|
+
prerelease: false
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - "~>"
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: '3.0'
|
167
|
+
- !ruby/object:Gem::Dependency
|
168
|
+
name: guard
|
169
|
+
requirement: !ruby/object:Gem::Requirement
|
170
|
+
requirements:
|
171
|
+
- - ">="
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: '0'
|
174
|
+
type: :development
|
175
|
+
prerelease: false
|
176
|
+
version_requirements: !ruby/object:Gem::Requirement
|
177
|
+
requirements:
|
178
|
+
- - ">="
|
179
|
+
- !ruby/object:Gem::Version
|
180
|
+
version: '0'
|
181
|
+
- !ruby/object:Gem::Dependency
|
182
|
+
name: json
|
183
|
+
requirement: !ruby/object:Gem::Requirement
|
184
|
+
requirements:
|
185
|
+
- - ">="
|
186
|
+
- !ruby/object:Gem::Version
|
187
|
+
version: '0'
|
188
|
+
type: :development
|
189
|
+
prerelease: false
|
190
|
+
version_requirements: !ruby/object:Gem::Requirement
|
191
|
+
requirements:
|
192
|
+
- - ">="
|
193
|
+
- !ruby/object:Gem::Version
|
194
|
+
version: '0'
|
195
|
+
description: A Ruby library for parsing email signatures.
|
196
|
+
email:
|
197
|
+
- guillermo.molini@gmail.com
|
198
|
+
executables: []
|
199
|
+
extensions: []
|
200
|
+
extra_rdoc_files: []
|
201
|
+
files:
|
202
|
+
- README.md
|
203
|
+
- lib/email_signature_parser.rb
|
204
|
+
- lib/email_signature_parser/data/job_titles/acronyms.yaml
|
205
|
+
- lib/email_signature_parser/data/job_titles/titles.yaml
|
206
|
+
- lib/email_signature_parser/data/job_titles/titles_es.yaml
|
207
|
+
- lib/email_signature_parser/html_text_parser.rb
|
208
|
+
- lib/email_signature_parser/parser.rb
|
209
|
+
- lib/email_signature_parser/utils.rb
|
210
|
+
homepage: https://github.com/GMolini/email_signature_parser
|
211
|
+
licenses:
|
212
|
+
- MIT
|
213
|
+
metadata: {}
|
214
|
+
post_install_message:
|
215
|
+
rdoc_options: []
|
216
|
+
require_paths:
|
217
|
+
- lib
|
218
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
219
|
+
requirements:
|
220
|
+
- - ">="
|
221
|
+
- !ruby/object:Gem::Version
|
222
|
+
version: '3.1'
|
223
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
224
|
+
requirements:
|
225
|
+
- - ">="
|
226
|
+
- !ruby/object:Gem::Version
|
227
|
+
version: '0'
|
228
|
+
requirements: []
|
229
|
+
rubygems_version: 3.4.10
|
230
|
+
signing_key:
|
231
|
+
specification_version: 4
|
232
|
+
summary: Email Signature Parser
|
233
|
+
test_files: []
|