Class: Kaigyo::Tokenizer

Inherits:
Object
  • Object
show all
Defined in:
lib/kaigyo/tokenizer.rb

Constant Summary collapse

WITH = 
'with'
SELECT = 
'select'
FROM = 
'from'
WHERE = 
'where'
GROUP = 
'group'
HAVING = 
'having'
WINDOW = 
'window'
UNION = 
'union'
INTERSECT = 
'intersect'
EXCEPT = 
'except'
ORDER = 
'order'
LIMIT = 
'limit'
OFFSET = 
'offset'
FETCH = 
'fetch'
FOR = 
'for'
BY = 
'by'
LEFT_PAREN = 
'left_paren'
RIGHT_PAREN = 
'right_paren'
INNER = 
'inner'
OUTER = 
'outer'
LEFT = 
'left'
RIGHT = 
'right'
FULL = 
'full'
CROSS = 
'cross'
JOIN = 
'join'
PUNCTUATION = 
'punctuation'
SEMI_COLON = 
'semi_colon'
EQUAL = 
'eaual'
LESS_THAN_EQUAL = 
'less_than_equal'
LESS_THAN = 
'less_than'
GREATER_THAN_EQUAL = 
'greater_than_equal'
GREATER_THAN = 
'greater_than'
BETWEEN = 
'between'
AND = 
'and'
OR = 
'or'
ON = 
'on'
DESC = 
'desc'
ASC = 
'asc'
AS = 
'as'
SUM = 
'sum'
AVG = 
'avg'
IN = 
'in'
LIKE = 
'like'

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(source) ⇒ Tokenizer

Returns a new instance of Tokenizer.



51
52
53
54
55
 
# File 'lib/kaigyo/tokenizer.rb', line 51

def initialize(source)
  @source = source
  @current = 0
  @in_single_quote = false
end

Instance Attribute Details

#current ⇒ Object

Returns the value of attribute current.



4
5
6
 
# File 'lib/kaigyo/tokenizer.rb', line 4

def current
  @current
end

#source ⇒ Object (readonly)

Returns the value of attribute source.



3
4
5
 
# File 'lib/kaigyo/tokenizer.rb', line 3

def source
  @source
end

Instance Method Details

#make_node(token_name, prev_prev_token, prev_token, token) ⇒ Object 



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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
 
# File 'lib/kaigyo/tokenizer.rb', line 141

def make_node(token_name, prev_prev_token, prev_token, token)
  # puts "token_name: #{token_name} prev_prev_token: #{prev_prev_token} prev_token: #{prev_token} token: #{token}"

  case token_name
  when WITH, SELECT, FROM, WHERE, HAVING, LIMIT, OFFSET, WINDOW, UNION, INTERSECT, EXCEPT
    [:clause, token]
  when AND
    if prev_prev_token.downcase == BETWEEN
      [:between_and, token]
    else
      [:and, token]
    end
  when ON
    [:on, token]
  when OR
    [:or, token]
  when BETWEEN
    [:between, token]
  when LIKE
    [:like, token]
  when AS
    [:as, token]
  when IN
    [:in, token]
  when ASC, DESC
    [:order_option, token]
  when JOIN
    if prev_token.downcase == INNER
      [:clause, "#{prev_token} #{token}"]
    elsif prev_prev_token.downcase == LEFT && prev_token.downcase == OUTER
      [:clause, "#{prev_prev_token} #{prev_token} #{token}"]
    elsif prev_token.downcase == LEFT
      [:clause, "#{prev_token} #{token}"]
    elsif prev_prev_token.downcase == RIGHT && prev_token.downcase == OUTER
      [:clause, "#{prev_prev_token} #{prev_token} #{token}"]
    elsif prev_token.downcase == RIGHT
      [:clause, "#{prev_token} #{token}"]
    elsif prev_prev_token.downcase == FULL && prev_token.downcase == OUTER
      [:clause, "#{prev_prev_token} #{prev_token} #{token}"]
    elsif prev_token.downcase == FULL
      [:clause, "#{prev_token} #{token}"]
    elsif prev_token.downcase == CROSS
      [:clause, "#{prev_token} #{token}"]
    else
      [:clause, token]
    end
  when BY
    if prev_token.downcase == GROUP || prev_token.downcase == ORDER
      [:clause, "#{prev_token} #{token}"]
    end
  when INNER, OUTER, LEFT, RIGHT, FULL, CROSS, GROUP, ORDER
    # suppress for duplicate node.
    # cf. GROUP BY, ORDER BY, INNER JOIN
    nil
  when ','
    [:punctuation, token]
  when ';'
    [:semi_colon, token]
  when ')'
    [:right_paren, token]
  when '('
    [:left_paren, token]
  when '<'
    [:less_than, token]
  when '>'
    [:greater_than, token]
  when '<='
    [:less_than_equal, token]
  when '>='
    [:greater_than_equal, token]
  when '='
    [:equal, token]
  when /\'.+\'/
    [:literal, token]
  when AVG, SUM
    [:function, token]
  when /\d+/
    [:number, token]
  else
    [:identifier, token]
  end
end

#next ⇒ Object 



57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
 
# File 'lib/kaigyo/tokenizer.rb', line 57

def next
  return nil if current >= source.length

  token = []

  target = source[current..-1]
  target.chars.each_with_index do |c, i|
    # p "c: #{c} i: #{i} current: #{current}"

    @current += 1

    # begin single quote
    if c == "'" && !@in_single_quote
      @in_single_quote = true
      token << c
      #puts "begin single quote #{token}"
      next
    end

    # in single quote
    if c != "'" && @in_single_quote
      token << c
      #puts "in single quote #{token}"
      next
    end

    # end single quote
    if c == "'" && @in_single_quote
      @in_single_quote = false
      token << c
      #puts "end single quote #{token}"
      break
    end

    case c
    when '(', ')', ','
      token << c

      break
    when ' ', "\n"
      next if token.size.zero?

      break
    when '<', '>'
      token << c
      break if target[i+1] != '='
    when '='
      token << c
      break
    else
      token << c

      case target[i+1]
      when ',', ' ', '(', ')', '=', '<', '>', ';'
        break
      end
    end
  end
  token.join
end

#token_analysis ⇒ Object 



118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
 
# File 'lib/kaigyo/tokenizer.rb', line 118

def token_analysis
  tokens = []
  while token = self.next do
    tokens << token
  end

  result = []
  idx = tokens.size-1

  prev_prev_token = nil
  prev_token = nil

  tokens.each_with_index do |token, i|
    token_name = token.downcase
    node = make_node(token_name, prev_prev_token, prev_token, token)
    result << node if node

    prev_prev_token = prev_token
    prev_token = token
  end
  result
end