Class: Stamp::Translator

Inherits:
Object
  • Object
show all
Defined in:
lib/stamp/translator.rb

Constant Summary collapse

TIME_ZONE_ABBREVIATIONS =

Full list of time zone abbreviations from http://en.wikipedia.org/wiki/List_of_time_zone_abbreviations

%w{
  ACDT ACST ACT ADT AEDT AEST AFT AKDT AKST AMST AMT ART AST AWDT AWST AZOST AZT
  BDT BIOT BIT BOT BRT BST BTT CAT CCT CDT CEDT CEST CET CHADT CHAST CHOT ChST CHUT
  CIST CIT CKT CLST CLT COST COT CST CT CVT CWST CXT DAVT DDUT DFT EASST EAST EAT
  ECT EDT EEDT EEST EET EGST EGT EIT EST FET FJT FKST FKT FNT GALT GAMT GET GFT
  GILT GIT GMT GST GYT HADT HAEC HAST HKT HMT HOVT HST ICT IDT IOT IRDT IRKT IRST
  IST JST KGT KOST KRAT KST LHST LINT MAGT MART MAWT MDT MET MEST MHT MIST MIT MMT
  MSK MST MUT MVT MYT NCT NDT NFT NPT NST NT NUT NZDT NZST OMST ORAT PDT PET PETT
  PGT PHOT PHT PKT PMDT PMST PONT PST RET ROTT SAKT SAMT SAST SBT SCT SGT SLT SRT
  SST SYOT TAHT THA TFT TJT TKT TLT TMT TOT TVT UCT ULAT UTC UYST UYT UZT VET VLAT
  VOLT VOST VUT WAKT WAST WAT WEDT WEST WET WST YAKT YEKT
}
TIMEZONE_REGEXP = 
/^(#{TIME_ZONE_ABBREVIATIONS.join('|')})$/
MONTHNAMES_REGEXP = 
/^(#{Date::MONTHNAMES.compact.join('|')})$/i
ABBR_MONTHNAMES_REGEXP = 
/^(#{Date::ABBR_MONTHNAMES.compact.join('|')})$/i
DAYNAMES_REGEXP = 
/^(#{Date::DAYNAMES.join('|')})$/i
ABBR_DAYNAMES_REGEXP = 
/^(#{Date::ABBR_DAYNAMES.join('|')})$/i
ONE_DIGIT_REGEXP = 
/^\d{1}$/
TWO_DIGIT_REGEXP = 
/^\d{2}$/
FOUR_DIGIT_REGEXP = 
/^\d{4}$/
TIME_REGEXP = 
/(\d{1,2})(:)(\d{2})(\s*)(:)?(\d{2})?(\s*)?([ap]m)?/i
UTC_OFFSET_REGEXP =

UTC offsets like "+05:00" or "-0500". The lookbehind/lookahead keep date fragments like "12-31-1999" from matching; hours are capped at 14.

/(?<![-\d])[+-](?:0\d|1[0-4]):?[0-5]\d(?!\d)/
MERIDIAN_LOWER_REGEXP = 
/^(a|p)m$/
MERIDIAN_UPPER_REGEXP = 
/^(A|P)M$/
ORDINAL_DAY_REGEXP = 
/^(\d{1,2})(st|nd|rd|th)$/
OBVIOUS_24_HOUR =

Disambiguate based on value

13..23
OBVIOUS_DAY = 
13..31
OBVIOUS_YEAR = 
32..99

Instance Method Summary collapse

Instance Method Details

#build_emitters(tokens) ⇒ Object

Transforms tokens that look like date/time parts to emitter objects.



80
81
82
83
84
 
# File 'lib/stamp/translator.rb', line 80

def build_emitters(tokens)
  tokens.map do |token|
    yield(token) || Emitters::String.new(token)
  end
end

#date_emitter(token) ⇒ Object 



117
118
119
120
121
122
123
124
125
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
 
# File 'lib/stamp/translator.rb', line 117

def date_emitter(token)
  case token
  when MONTHNAMES_REGEXP
    Emitters::Lookup::MONTH

  when ABBR_MONTHNAMES_REGEXP
    Emitters::Lookup::ABBR_MONTH

  when DAYNAMES_REGEXP
    Emitters::Lookup::DAY

  when ABBR_DAYNAMES_REGEXP
    Emitters::Lookup::ABBR_DAY

  when TIMEZONE_REGEXP
    Emitters::Delegate::ZONE

  when FOUR_DIGIT_REGEXP
    Emitters::Delegate::YEAR

  when ORDINAL_DAY_REGEXP
    Emitters::Ordinal::DAY

  when TWO_DIGIT_REGEXP
    case token.to_i
    when OBVIOUS_DAY
      Emitters::TwoDigit::DAY
    when OBVIOUS_YEAR
      Emitters::TwoDigit::YEAR
    else
      Emitters::Ambiguous.new(
        Emitters::TwoDigit::MONTH,
        Emitters::TwoDigit::DAY,
        Emitters::TwoDigit::YEAR)
    end

  when ONE_DIGIT_REGEXP
    Emitters::Ambiguous.new(
      Emitters::Delegate::MONTH,
      Emitters::Delegate::DAY)
  end
end

#time_emitter(token) ⇒ Object 



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/stamp/translator.rb', line 86

def time_emitter(token)
  case token
  when MERIDIAN_LOWER_REGEXP
    Emitters::AmPm::LOWERCASE

  when MERIDIAN_UPPER_REGEXP
    Emitters::AmPm::UPPERCASE

  when TWO_DIGIT_REGEXP
    Emitters::Ambiguous.new(
      two_digit_hour_emitter(token),
      Emitters::TwoDigit::MIN,
      Emitters::TwoDigit::SEC)

  when ONE_DIGIT_REGEXP
    # 12-hour clock without leading zero
    Emitters::TwelveHour::NON_LEADING_ZERO
  end
end

#translate(example) ⇒ Object 



45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
 
# File 'lib/stamp/translator.rb', line 45

def translate(example)
  # extract any substrings that look like UTC offsets, like "+05:00" or
  # "-0500", before the time logic can mistake them for clock times
  before, offset_example, after = example.partition(UTC_OFFSET_REGEXP)
  unless offset_example.empty?
    emitters = Emitters::Composite.new
    emitters << translate(before) unless before.empty?
    emitters << (offset_example.include?(":") ? Emitters::UtcOffset::COLON : Emitters::UtcOffset::PLAIN)
    emitters << translate(after) unless after.empty?
    return emitters
  end

  # extract any substrings that look like times, like "23:59" or "8:37 am"
  before, time_example, after = example.partition(TIME_REGEXP)

  # build emitters from the example date
  emitters = Emitters::Composite.new
  emitters << build_emitters(before.split(/\b/)) do |token|
    date_emitter(token)
  end

  # build emitters from the example time
  unless time_example.empty?
    time_parts = time_example.scan(TIME_REGEXP).first
    emitters << build_emitters(time_parts) do |token|
      time_emitter(token)
    end
  end

  # recursively process any remaining text
  emitters << translate(after) unless after.empty?
  emitters
end

#two_digit_hour_emitter(token) ⇒ Object 



106
107
108
109
110
111
112
113
114
115
 
# File 'lib/stamp/translator.rb', line 106

def two_digit_hour_emitter(token)
  case token.to_i
  when OBVIOUS_24_HOUR
    # 24-hour clock
    Emitters::TwoDigit::HOUR
  else
    # 12-hour clock with leading zero
    Emitters::TwelveHour::LEADING_ZERO
  end
end