Module: Legion::Extensions::Privatecore::Helpers::Patterns

Defined in:
lib/legion/extensions/privatecore/helpers/patterns.rb

Constant Summary collapse

PATTERNS = 
{
  email:           { regex:    /\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b/,
                     category: :contact },
  phone:           { regex:    /\b\d{3}[-.]?\d{3}[-.]?\d{4}\b/,
                     category: :contact },
  ssn:             { regex:    /\b\d{3}-\d{2}-\d{4}\b/,
                     category: :government_id },
  ip:              { regex:    /\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b/,
                     category: :network },
  credit_card:     { regex: /\b(?:\d[ -]*?){13,19}\b/,
                     category: :financial, checksum: :luhn },
  dob:             { regex:    %r{(?:DOB|date of birth)\s*:\s*(\d{1,4}[-/]\d{1,2}[-/]\d{1,4})}i,
                     category: :personal },
  mrn:             { regex:    /(?:MRN|medical record)\s*:\s*(\d{5,15})/i,
                     category: :medical },
  passport:        { regex:    /\b[A-Z]\d{8}\b/,
                     category: :government_id },
  iban:            { regex: /\b[A-Z]{2}\d{2}[A-Z0-9]{11,30}\b/,
                     category: :financial, checksum: :iban },
  drivers_license: { regex:    /\b[A-Z]\d{3}-?\d{4}-?\d{4}\b/,
                     category: :government_id },
  url:             { regex:    %r{https?://[^\s<>"{}|\\^`\[\]]+},
                     category: :network },
  btc_address:     { regex: /\b[13][a-km-zA-HJ-NP-Z1-9]{25,34}\b/,
                     category: :crypto, checksum: :base58check },
  eth_address:     { regex:    /\b0x[0-9a-fA-F]{40}\b/,
                     category: :crypto },
  itin:            { regex:    /\b9\d{2}-[7-9]\d-\d{4}\b/,
                     category: :government_id },
  aadhaar:         { regex: /\b[2-9]\d{3}\s?\d{4}\s?\d{4}\b/,
                     category: :government_id, checksum: :verhoeff },
  api_key:         { regex:    /\b(?:sk|pk|rk)_(?:live|test)_[A-Za-z0-9]{20,}\b/,
                     category: :credential },
  bearer_token:    { regex:    %r{Bearer\s+[A-Za-z0-9\-._~+/]+=*},
                     category: :credential },
  aws_key:         { regex:    /\bAKIA[0-9A-Z]{16}\b/,
                     category: :credential }
}.freeze
CHECKSUM_VALIDATORS = 
{
  luhn:        ->(digits) { luhn_valid?(digits) },
  iban:        ->(text) { iban_valid?(text) },
  verhoeff:    ->(digits) { verhoeff_valid?(digits) },
  base58check: ->(addr) { base58check_valid?(addr) }
}.freeze
VERHOEFF_D = 
[
  [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], [1, 2, 3, 4, 0, 6, 7, 8, 9, 5],
  [2, 3, 4, 0, 1, 7, 8, 9, 5, 6], [3, 4, 0, 1, 2, 8, 9, 5, 6, 7],
  [4, 0, 1, 2, 3, 9, 5, 6, 7, 8], [5, 9, 8, 7, 6, 0, 4, 3, 2, 1],
  [6, 5, 9, 8, 7, 1, 0, 4, 3, 2], [7, 6, 5, 9, 8, 2, 1, 0, 4, 3],
  [8, 7, 6, 5, 9, 3, 2, 1, 0, 4], [9, 8, 7, 6, 5, 4, 3, 2, 1, 0]
].freeze
VERHOEFF_P = 
[
  [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], [1, 5, 7, 6, 2, 8, 3, 0, 9, 4],
  [5, 8, 0, 3, 7, 9, 6, 1, 4, 2], [8, 9, 1, 6, 0, 4, 3, 5, 2, 7],
  [9, 4, 5, 3, 1, 2, 6, 8, 7, 0], [4, 2, 8, 6, 5, 7, 3, 9, 0, 1],
  [2, 7, 9, 3, 8, 0, 6, 4, 1, 5], [7, 0, 4, 6, 9, 1, 3, 2, 5, 8]
].freeze
BASE58_ALPHABET = 
'123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'

Class Method Summary collapse

Class Method Details

.base58check_valid?(address) ⇒ Boolean

Returns:

  • (Boolean) 


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
161
162
163
164
165
166
167
168
169
 
# File 'lib/legion/extensions/privatecore/helpers/patterns.rb', line 134

def base58check_valid?(address)
  return false unless address.match?(/\A[13][a-km-zA-HJ-NP-Z1-9]{25,34}\z/)

  # Decode Base58 to integer
  num = 0
  address.each_char do |char|
    index = BASE58_ALPHABET.index(char)
    return false if index.nil?

    num = (num * 58) + index
  end

  # Convert to variable-length big-endian bytes, then restore
  # leading zero bytes represented by leading '1' characters.
  bytes = []
  while num.positive?
    bytes.unshift(num & 0xff)
    num >>= 8
  end

  leading_ones = address.each_char.take_while { |char| char == '1' }.size
  bytes = ([0] * leading_ones) + bytes

  # Base58Check P2PKH/P2SH addresses decode to:
  # 1 version byte + 20 payload bytes + 4 checksum bytes.
  return false unless bytes.size == 25

  payload  = bytes[0...-4]
  checksum = bytes[-4..]

  # Double SHA-256 of payload; compare first 4 bytes
  require 'digest'
  first_hash  = Digest::SHA256.digest(payload.pack('C*'))
  second_hash = Digest::SHA256.digest(first_hash)
  second_hash.unpack('C*').first(4) == checksum
end

.detect(text, enabled:, validation:) ⇒ Object 



56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
 
# File 'lib/legion/extensions/privatecore/helpers/patterns.rb', line 56

def detect(text, enabled:, validation:)
  return [] unless text.is_a?(String)

  detections = []
  PATTERNS.each do |type, meta|
    next unless enabled.include?(type)

    text.scan(meta[:regex]) do
      md = Regexp.last_match
      capture_index = md.captures.each_index.find { |index| !md[index + 1].nil? }
      match_index = capture_index ? capture_index + 1 : 0
      matched_text = md[match_index]
      next if validation[type] == :checksum && !validate_checksum(type, matched_text)

      detections << {
        type:     type,
        category: meta[:category],
        start:    md.begin(match_index),
        end:      md.end(match_index),
        match:    matched_text
      }
    end
  end
  detections
end

.iban_valid?(iban) ⇒ Boolean

Returns:

  • (Boolean) 


104
105
106
107
108
 
# File 'lib/legion/extensions/privatecore/helpers/patterns.rb', line 104

def iban_valid?(iban)
  rearranged = iban[4..] + iban[0..3]
  numeric = rearranged.chars.map { |c| c.match?(/\d/) ? c : (c.upcase.ord - 55).to_s }.join
  (numeric.to_i % 97) == 1
end

.luhn_valid?(number) ⇒ Boolean

Returns:

  • (Boolean) 


93
94
95
96
97
98
99
100
101
102
 
# File 'lib/legion/extensions/privatecore/helpers/patterns.rb', line 93

def luhn_valid?(number)
  digits = number.chars.map(&:to_i)
  sum = 0
  digits.reverse.each_with_index do |d, i|
    d *= 2 if i.odd?
    d -= 9 if d > 9
    sum += d
  end
  (sum % 10).zero?
end

.validate_checksum(type, match) ⇒ Object 



82
83
84
85
86
87
88
89
90
91
 
# File 'lib/legion/extensions/privatecore/helpers/patterns.rb', line 82

def validate_checksum(type, match)
  meta = PATTERNS[type]
  return true unless meta && meta[:checksum]

  validator = CHECKSUM_VALIDATORS[meta[:checksum]]
  return true unless validator

  cleaned = match.gsub(/[\s-]/, '')
  validator.call(cleaned)
end

.verhoeff_valid?(number) ⇒ Boolean

Returns:

  • (Boolean) 


125
126
127
128
129
130
 
# File 'lib/legion/extensions/privatecore/helpers/patterns.rb', line 125

def verhoeff_valid?(number)
  digits = number.chars.map(&:to_i).reverse
  c = 0
  digits.each_with_index { |d, i| c = VERHOEFF_D[c][VERHOEFF_P[i % 8][d]] }
  c.zero?
end