Module: EBNF::PEG::Rule

Includes:
Unescape
Defined in:
lib/ebnf/peg/rule.rb

Overview

Behaviior for parsing a PEG rule

Constant Summary

Constants included from Unescape

Unescape::ECHAR, Unescape::ESCAPE_CHAR4, Unescape::ESCAPE_CHAR8, Unescape::ESCAPE_CHARS, Unescape::UCHAR

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from Unescape

unescape, unescape_codepoints, unescape_string

Instance Attribute Details

#parserEBNF::PEG::Parser

Initialized by parser when loading rules. Used for finding rules and invoking elements of the parse process.

Returns:


11
12
13
# File 'lib/ebnf/peg/rule.rb', line 11

def parser
  @parser
end

Instance Method Details

#eat_whitespace(input) ⇒ Object

Eat whitespace between non-terminal rules


268
269
270
271
272
273
274
275
# File 'lib/ebnf/peg/rule.rb', line 268

def eat_whitespace(input)
  if parser.whitespace.is_a?(Regexp)
    # Eat whitespace before a non-terminal
    input.skip(parser.whitespace)
  elsif parser.whitespace.is_a?(Rule)
    parser.whitespace.parse(input) # throw away result
  end
end

#parse(input) ⇒ Hash{Symbol => Object}, :unmatched

If there is are start_production and/or production, they are invoked with a prod_data stack, the input stream and offset. Otherwise, the results are added as an array value to a hash indexed by the rule name.

If matched, the input position is updated and the results returned in a Hash.

  • alt: returns the value of the matched production or :unmatched.
  • diff: returns the value matched, or :unmatched.
  • hex: returns a string composed of the matched hex character, or :unmatched.
  • opt: returns the value matched, or nil if unmatched.
  • plus: returns an array of the values matched for the specified production, or :unmatched, if none are matched. For Terminals, these are concatenated into a single string.
  • range: returns a string composed of the values matched, or :unmatched, if less than min are matched.
  • rept: returns an array of the values matched for the speficied production, or :unmatched, if none are matched. For Terminals, these are concatenated into a single string.
  • seq: returns an array composed of single-entry hashes for each matched production indexed by the production name, or :unmatched if any production fails to match. For Terminals, returns a string created by concatenating these values. Via option in a production or definition, the result can be a single hash with values for each matched production; note that this is not always possible due to the possibility of repeated productions within the sequence.
  • star: returns an array of the values matched for the specified production. For Terminals, these are concatenated into a single string.

Parameters:

  • input (Scanner)

Returns:

  • (Hash{Symbol => Object}, :unmatched)

    A hash with keys for matched component of the expression. Returns :unmatched if the input does not match the production.


35
36
37
38
39
40
41
42
43
44
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
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
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
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
223
224
225
226
227
# File 'lib/ebnf/peg/rule.rb', line 35

def parse(input)
  # Save position and linenumber for backtracking
  pos, lineno = input.pos, input.lineno

  parser.packrat[sym] ||= {}
  if parser.packrat[sym][pos]
    parser.debug("#{sym}(:memo)", lineno: lineno) { "#{parser.packrat[sym][pos].inspect}(@#{pos})"}
    input.pos, input.lineno = parser.packrat[sym][pos][:pos], parser.packrat[sym][pos][:lineno]
    return parser.packrat[sym][pos][:result]
  end

  if terminal?
    # If the terminal is defined with a regular expression,
    # use that to match the input,
    # otherwise,
    if regexp = parser.terminal_regexp(sym)
      term_opts = parser.terminal_options(sym)
      if matched = input.scan(regexp)
        # Optionally map matched
        matched = term_opts.fetch(:map, {}).fetch(matched.downcase, matched)

        # Optionally unescape matched
        matched = unescape(matched) if term_opts[:unescape]
      end

      result = parser.onTerminal(sym, (matched ? matched : :unmatched))

      # Update furthest failure for strings and terminals
      parser.update_furthest_failure(input.pos, input.lineno, sym) if result == :unmatched
      parser.packrat[sym][pos] = {
        pos: input.pos,
        lineno: input.lineno,
        result: result
      }
      return parser.packrat[sym][pos][:result]
    end
  else
    eat_whitespace(input)
  end
  start_options = parser.onStart(sym)
  string_regexp_opts = start_options[:insensitive_strings] ? Regexp::IGNORECASE : 0

  result = case expr.first
  when :alt
    # Return the first expression to match.
    # Result is either :unmatched, or the value of the matching rule
    alt = :unmatched
    expr[1..-1].each do |prod|
      alt = case prod
      when Symbol
        rule = parser.find_rule(prod)
        raise "No rule found for #{prod}" unless rule
        rule.parse(input)
      when String
        s = input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts))
        case start_options[:insensitive_strings]
        when :lower then s && s.downcase
        when :upper then s && s.upcase
        else s
        end || :unmatched
      end
      if alt == :unmatched
        # Update furthest failure for strings and terminals
        parser.update_furthest_failure(input.pos, input.lineno, prod) if prod.is_a?(String) || rule.terminal?
      else
        break
      end
    end
    alt
  when :diff
    # matches any string that matches A but does not match B.
    # (Note, this is only used for Terminal rules, non-terminals will use :not)
    raise "Diff used on non-terminal #{prod}" unless terminal?
    re1, re2 = Regexp.new(translate_codepoints(expr[1])), Regexp.new(translate_codepoints(expr[2]))
    matched = input.scan(re1)
    if !matched || re2.match?(matched)
      # Update furthest failure for terminals
      parser.update_furthest_failure(input.pos, input.lineno, sym)
      :unmatched
    else
      matched
    end
  when :hex
    # Matches the given hex character if expression matches the character whose number (code point) in ISO/IEC 10646 is N. The number of leading zeros in the #xN form is insignificant.
    input.scan(to_regexp) || begin
      # Update furthest failure for terminals
      parser.update_furthest_failure(input.pos, input.lineno, expr.last)
      :unmatched
    end
  when :not
    # matches any string that does not match B.
    res = case prod = expr[1]
    when Symbol
      rule = parser.find_rule(prod)
      raise "No rule found for #{prod}" unless rule
      rule.parse(input)
    when String
      input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts)) || :unmatched
    end
    if res != :unmatched
      # Update furthest failure for terminals
      parser.update_furthest_failure(input.pos, input.lineno, sym) if terminal?
      :unmatched
    else
      nil
    end
  when :opt
    # Result is the matched value or nil
    opt = rept(input, 0, 1, expr[1], string_regexp_opts, **start_options)

    # Update furthest failure for strings and terminals
    parser.update_furthest_failure(input.pos, input.lineno, expr[1]) if terminal?
    opt.first
  when :plus
    # Result is an array of all expressions while they match,
    # at least one must match
    plus = rept(input, 1, '*', expr[1], string_regexp_opts)

    # Update furthest failure for strings and terminals
    parser.update_furthest_failure(input.pos, input.lineno, expr[1]) if terminal?
    plus.is_a?(Array) && terminal? ? plus.join("") : plus
  when :range, :istr
    # Matches the specified character range
    input.scan(to_regexp) || begin
      # Update furthest failure for strings and terminals
      parser.update_furthest_failure(input.pos, input.lineno, expr[1])
      :unmatched
    end
  when :rept
    # Result is an array of all expressions while they match,
    # an empty array of none match
    rept = rept(input, expr[1], expr[2], expr[3], string_regexp_opts)

    # # Update furthest failure for strings and terminals
    parser.update_furthest_failure(input.pos, input.lineno, expr[3]) if terminal?
    rept.is_a?(Array) && terminal? ? rept.join("") : rept
  when :seq
    # Evaluate each expression into an array of hashes where each hash contains a key from the associated production and the value is the parsed value of that production. Returns :unmatched if the input does not match the production. Value ordering is ensured by native Hash ordering.
    seq = expr[1..-1].each_with_object([]) do |prod, accumulator|
      eat_whitespace(input) unless accumulator.empty? || terminal?
      res = case prod
      when Symbol
        rule = parser.find_rule(prod)
        raise "No rule found for #{prod}" unless rule
        rule.parse(input)
      when String
        s = input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts))
        case start_options[:insensitive_strings]
        when :lower then s && s.downcase
        when :upper then s && s.upcase
        else s
        end || :unmatched
      end
      if res == :unmatched
        # Update furthest failure for strings and terminals
        parser.update_furthest_failure(input.pos, input.lineno, prod)
        break :unmatched 
      end
      accumulator << {prod.to_sym => res}
    end
    if seq == :unmatched
      :unmatched
    elsif terminal?
      seq.map(&:values).compact.join("") # Concat values for terminal production
    elsif start_options[:as_hash]
      seq.inject {|memo, h| memo.merge(h)}
    else
      seq
    end
  when :star
    # Result is an array of all expressions while they match,
    # an empty array of none match
    star = rept(input, 0, '*', expr[1], string_regexp_opts)

    # Update furthest failure for strings and terminals
    parser.update_furthest_failure(input.pos, input.lineno, expr[1]) if terminal?
    star.is_a?(Array) && terminal? ? star.join("") : star
  else
    raise "attempt to parse unknown rule type: #{expr.first}"
  end

  if result == :unmatched
    input.pos, input.lineno = pos, lineno
  end

  result = parser.onFinish(result)
  (parser.packrat[sym] ||= {})[pos] = {
    pos: input.pos,
    lineno: input.lineno,
    result: result
  }
  return parser.packrat[sym][pos][:result]
end

#rept(input, min, max, prod, string_regexp_opts, **options) ⇒ :unmatched, Array

Repitition, 0-1, 0-n, 1-n, ...

Note, nil results are removed from the result, but count towards min/max calculations

Parameters:

  • input (Scanner)
  • min (Integer)
  • max (Integer)

    If it is an integer, it stops matching after max entries.

  • prod (Symbol, String)
  • string_regexp_opts (Integer)

Returns:

  • (:unmatched, Array)

241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
# File 'lib/ebnf/peg/rule.rb', line 241

def rept(input, min, max, prod, string_regexp_opts, **options)
  result = []

  case prod
  when Symbol
    rule = parser.find_rule(prod)
    raise "No rule found for #{prod}" unless rule
    while (max == '*' || result.length < max) && (res = rule.parse(input)) != :unmatched
      eat_whitespace(input) unless terminal?
      result << res
    end
  when String
    while (res = input.scan(Regexp.new(Regexp.quote(prod), string_regexp_opts))) && (max == '*' || result.length < max)
      eat_whitespace(input) unless terminal?
      result << case options[:insensitive_strings]
      when :lower then res.downcase
      when :upper then res.upcase
      else res
      end
    end
  end

  result.length < min ? :unmatched : result.compact
end