Class: Enolib::Parser

Inherits:
Object
  • Object
show all
Defined in:
lib/enolib/parser.rb

Instance Method Summary collapse

Constructor Details

#initialize(context) ⇒ Parser

Returns a new instance of Parser.



5
6
7
8
9
10
11
12
 
# File 'lib/enolib/parser.rb', line 5

def initialize(context)
  @context = context
  @depth = 0
  @index = 0
  @line = 0
  @unresolved_non_section_elements = {}
  @unresolved_sections = {}
end

Instance Method Details

#run ⇒ Object 



14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
 
# File 'lib/enolib/parser.rb', line 14

def run
  if @context.input.empty?
    @context.line_count = 1
    return
  end

  comments = nil
  last_continuable_element = nil
  last_non_section_element = nil
  last_section = @context.document

  while @index < @context.input.length
    match = Grammar::REGEX.match(@context.input, @index)

    unless match && match.begin(0) == @index
      instruction = tokenize_error_context
      raise Errors::Parsing.invalid_line(@context, instruction)
    end

    instruction = {
      index: @index,
      line: @line,
      ranges: {
        line: match.offset(0)
      }
    }

    multiline_field = false

    if match[Grammar::EMPTY_LINE_INDEX]

      instruction[:type] = :empty_line

      if comments
        @context.meta.concat(comments)
        comments = nil
      end

    elsif match[Grammar::ELEMENT_OPERATOR_INDEX]

      if comments
        instruction[:comments] = comments
        comments = nil
      end

      instruction[:key] = match[Grammar::KEY_UNESCAPED_INDEX]

      if instruction[:key]
        instruction[:ranges][:element_operator] = match.offset(Grammar::ELEMENT_OPERATOR_INDEX)
        instruction[:ranges][:key] = match.offset(Grammar::KEY_UNESCAPED_INDEX)
      else
        instruction[:key] = match[Grammar::KEY_ESCAPED_INDEX]
        instruction[:ranges][:element_operator] = match.offset(Grammar::ELEMENT_OPERATOR_INDEX)
        instruction[:ranges][:escape_begin_operator] = match.offset(Grammar::KEY_ESCAPE_BEGIN_OPERATOR_INDEX)
        instruction[:ranges][:escape_end_operator] = match.offset(Grammar::KEY_ESCAPE_END_OPERATOR_INDEX)
        instruction[:ranges][:key] = match.offset(Grammar::KEY_ESCAPED_INDEX)
      end

      value = match[Grammar::FIELD_VALUE_INDEX]

      if value
        instruction[:ranges][:value] = match.offset(Grammar::FIELD_VALUE_INDEX)
        instruction[:type] = :field
        instruction[:value] = value
      else
        instruction[:type] = :empty_element
      end

      instruction[:parent] = last_section
      last_section[:elements].push(instruction)
      last_continuable_element = instruction
      last_non_section_element = instruction

    elsif match[Grammar::LIST_ITEM_OPERATOR_INDEX]

      if comments
        instruction[:comments] = comments
        comments = nil
      end

      instruction[:ranges][:item_operator] = match.offset(Grammar::LIST_ITEM_OPERATOR_INDEX)
      instruction[:type] = :list_item

      value = match[Grammar::LIST_ITEM_VALUE_INDEX]

      if value
        instruction[:ranges][:value] = match.offset(Grammar::LIST_ITEM_VALUE_INDEX)
        instruction[:value] = value
      end

      if !last_non_section_element
        instruction = tokenize_error_context
        raise Errors::Parsing.missing_list_for_list_item(@context, instruction)
      elsif last_non_section_element[:type] == :list
        last_non_section_element[:items].push(instruction)
      elsif last_non_section_element[:type] == :empty_element
        last_non_section_element[:items] = [instruction]
        last_non_section_element[:type] = :list
      else
        instruction = tokenize_error_context
        raise Errors::Parsing.missing_list_for_list_item(@context, instruction)
      end

      instruction[:parent] = last_non_section_element
      last_continuable_element = instruction

    elsif match[Grammar::FIELDSET_ENTRY_OPERATOR_INDEX]

      if comments
        instruction[:comments] = comments
        comments = nil
      end

      instruction[:type] = :fieldset_entry

      instruction[:key] = match[Grammar::KEY_UNESCAPED_INDEX]

      if instruction[:key]
        instruction[:ranges][:key] = match.offset(Grammar::KEY_UNESCAPED_INDEX)
        instruction[:ranges][:entry_operator] = match.offset(Grammar::FIELDSET_ENTRY_OPERATOR_INDEX)
      else
        instruction[:key] = match[Grammar::KEY_ESCAPED_INDEX]
        instruction[:ranges][:entry_operator] = match.offset(Grammar::FIELDSET_ENTRY_OPERATOR_INDEX)
        instruction[:ranges][:escape_begin_operator] = match.offset(Grammar::KEY_ESCAPE_BEGIN_OPERATOR_INDEX)
        instruction[:ranges][:escape_end_operator] = match.offset(Grammar::KEY_ESCAPE_END_OPERATOR_INDEX)
        instruction[:ranges][:key] = match.offset(Grammar::KEY_ESCAPED_INDEX)
      end

      value = match[Grammar::FIELDSET_ENTRY_VALUE_INDEX]

      if value
        instruction[:ranges][:value] = match.offset(Grammar::FIELDSET_ENTRY_VALUE_INDEX)
        instruction[:value] = value
      end

      if !last_non_section_element
        instruction = tokenize_error_context
        raise Errors::Parsing.missing_fieldset_for_fieldset_entry(@context, instruction)
      elsif last_non_section_element[:type] == :fieldset
        last_non_section_element[:entries].push(instruction)
      elsif last_non_section_element[:type] == :empty_element
        last_non_section_element[:entries] = [instruction]
        last_non_section_element[:type] = :fieldset
      else
        instruction = tokenize_error_context
        raise Errors::Parsing.missing_fieldset_for_fieldset_entry(@context, instruction)
      end

      instruction[:parent] = last_non_section_element
      last_continuable_element = instruction

    elsif match[Grammar::SPACED_LINE_CONTINUATION_OPERATOR_INDEX]

      unless last_continuable_element
        instruction = tokenize_error_context
        raise Errors::Parsing.missing_element_for_continuation(@context, instruction)
      end

      instruction[:spaced] = true
      instruction[:ranges][:spaced_line_continuation_operator] = match.offset(Grammar::SPACED_LINE_CONTINUATION_OPERATOR_INDEX)
      instruction[:type] = :continuation

      value = match[Grammar::SPACED_LINE_CONTINUATION_VALUE_INDEX]

      if value
        instruction[:ranges][:value] = match.offset(Grammar::SPACED_LINE_CONTINUATION_VALUE_INDEX)
        instruction[:value] = value
      end

      if last_continuable_element.has_key?(:continuations)
        last_continuable_element[:continuations].push(instruction)
      else
        if last_continuable_element[:type] == :empty_element
          last_continuable_element[:type] = :field
        end

        last_continuable_element[:continuations] = [instruction]
      end

      if comments
        @context.meta.concat(comments)
        comments = nil
      end

    elsif match[Grammar::DIRECT_LINE_CONTINUATION_OPERATOR_INDEX]

      unless last_continuable_element
        instruction = tokenize_error_context
        raise Errors::Parsing.missing_element_for_continuation(@context, instruction)
      end

      instruction[:ranges][:direct_line_continuation_operator] = match.offset(Grammar::DIRECT_LINE_CONTINUATION_OPERATOR_INDEX)
      instruction[:type] = :continuation

      value = match[Grammar::DIRECT_LINE_CONTINUATION_VALUE_INDEX]

      if value
        instruction[:ranges][:value] = match.offset(Grammar::DIRECT_LINE_CONTINUATION_VALUE_INDEX)
        instruction[:value] = value
      end

      if last_continuable_element.has_key?(:continuations)
        last_continuable_element[:continuations].push(instruction)
      else
        if last_continuable_element[:type] == :empty_element
          last_continuable_element[:type] = :field
        end

        last_continuable_element[:continuations] = [instruction]
      end

      if comments
        @context.meta.concat(comments)
        comments = nil
      end

    elsif match[Grammar::SECTION_OPERATOR_INDEX]

      if comments
        instruction[:comments] = comments
        comments = nil
      end

      instruction[:elements] = []
      instruction[:ranges][:section_operator] = match.offset(Grammar::SECTION_OPERATOR_INDEX)
      instruction[:type] = :section

      new_depth = instruction[:ranges][:section_operator][1] - instruction[:ranges][:section_operator][0]

      if new_depth == @depth + 1
        instruction[:parent] = last_section
        @depth = new_depth
      elsif new_depth == @depth
        instruction[:parent] = last_section[:parent]
      elsif new_depth < @depth
        while new_depth < @depth
          last_section = last_section[:parent]
          @depth -= 1
        end

        instruction[:parent] = last_section[:parent]
      else
        instruction = tokenize_error_context
        raise Errors::Parsing.section_hierarchy_layer_skip(@context, instruction, last_section)
      end

      instruction[:parent][:elements].push(instruction)
      last_section = instruction

      instruction[:key] = match[Grammar::SECTION_KEY_UNESCAPED_INDEX]

      if instruction[:key]
        instruction[:ranges][:key] = match.offset(Grammar::SECTION_KEY_UNESCAPED_INDEX)
      else
        instruction[:key] = match[Grammar::SECTION_KEY_ESCAPED_INDEX]
        instruction[:ranges][:escape_begin_operator] = match.offset(Grammar::SECTION_KEY_ESCAPE_BEGIN_OPERATOR_INDEX)
        instruction[:ranges][:escape_end_operator] = match.offset(Grammar::SECTION_KEY_ESCAPE_END_OPERATOR_INDEX)
        instruction[:ranges][:key] = match.offset(Grammar::SECTION_KEY_ESCAPED_INDEX)
      end

      template = match[Grammar::SECTION_TEMPLATE_INDEX]

      if template
        instruction[:ranges][:template] = match.offset(Grammar::SECTION_TEMPLATE_INDEX)
        instruction[:template] = template

        parent = instruction[:parent]
        while parent[:type] != :document
          parent[:deep_resolve] = true
          parent = parent[:parent]
        end

        copy_operator_offset = match.offset(Grammar::SECTION_COPY_OPERATOR_INDEX)

        if copy_operator_offset[1] - copy_operator_offset[0] == 2
          instruction[:deep_copy] = true
          instruction[:ranges][:deep_copy_operator] = copy_operator_offset
        else
          instruction[:ranges][:copy_operator] = copy_operator_offset
        end

        if @unresolved_sections.has_key?(template)
          @unresolved_sections[template][:targets].push(instruction)
        else
          @unresolved_sections[template] = { targets: [instruction] }
        end

        instruction[:copy] = @unresolved_sections[template]
      end

      last_continuable_element = nil
      last_non_section_element = nil

    elsif match[Grammar::MULTILINE_FIELD_OPERATOR_INDEX]

      if comments
        instruction[:comments] = comments
        comments = nil
      end

      operator = match[Grammar::MULTILINE_FIELD_OPERATOR_INDEX]
      key = match[Grammar::MULTILINE_FIELD_KEY_INDEX]

      instruction[:key] = key
      instruction[:parent] = last_section
      instruction[:ranges][:multiline_field_operator] = match.offset(Grammar::MULTILINE_FIELD_OPERATOR_INDEX)
      instruction[:ranges][:key] = match.offset(Grammar::MULTILINE_FIELD_KEY_INDEX)
      instruction[:type] = :multiline_field_begin

      @index = match.end(0)

      last_section[:elements].push(instruction)
      last_continuable_element = nil
      last_non_section_element = instruction

      terminator_regex = /\n[^\S\n]*(#{operator})(?!-)[^\S\n]*(#{Regexp.escape(key)})[^\S\n]*(?=\n|$)/
      terminator_match = terminator_regex.match(@context.input, @index)

      @index += 1  # move past current char (\n) into next line
      @line += 1

      unless terminator_match
        tokenize_error_context
        raise Errors::Parsing.unterminated_multiline_field(@context, instruction)
      end

      end_of_multiline_field_index = terminator_match.begin(0)

      if end_of_multiline_field_index != @index - 1
        instruction[:lines] = []

        loop do
          end_of_line_index = @context.input.index("\n", @index)

          if !end_of_line_index || end_of_line_index >= end_of_multiline_field_index
            last_non_section_element[:lines].push(
              line: @line,
              ranges: {
                line: [@index, end_of_multiline_field_index],
                value: [@index, end_of_multiline_field_index]
              },
              type: :multiline_field_value
            )

            @index = end_of_multiline_field_index + 1
            @line += 1

            break
          else
            last_non_section_element[:lines].push(
              line: @line,
              ranges: {
                line: [@index, end_of_line_index],
                value: [@index, end_of_line_index]
              },
              type: :multiline_field_value
            )

            @index = end_of_line_index + 1
            @line += 1
          end
        end
      end

      instruction = {
        length: terminator_match.end(0),
        line: @line,
        ranges: {
          key: terminator_match.offset(2),
          line: [@index, terminator_match.end(0)],
          multiline_field_operator: terminator_match.offset(1)
        },
        type: :multiline_field_end
      }

      last_non_section_element[:end] = instruction
      last_non_section_element = nil

      @index = terminator_match.end(0) + 1
      @line += 1

      multiline_field = true

    elsif match[Grammar::COMMENT_OPERATOR_INDEX]

      if comments
        comments.push(instruction)
      else
        comments = [instruction]
      end

      instruction[:ranges][:comment_operator] = match.offset(Grammar::COMMENT_OPERATOR_INDEX)
      instruction[:type] = :comment

      comment = match[Grammar::COMMENT_VALUE_INDEX]

      if comment
        instruction[:comment] = comment
        instruction[:ranges][:comment] = match.offset(Grammar::COMMENT_VALUE_INDEX)
      end

    elsif match[Grammar::COPY_OPERATOR_INDEX]

      if comments
        instruction[:comments] = comments
        comments = nil
      end

      template = match[Grammar::TEMPLATE_INDEX]

      instruction[:ranges][:copy_operator] = match.offset(Grammar::COPY_OPERATOR_INDEX)
      instruction[:ranges][:template] = match.offset(Grammar::TEMPLATE_INDEX)
      instruction[:template] = template
      instruction[:type] = :empty_element

      instruction[:key] = match[Grammar::KEY_UNESCAPED_INDEX]

      if instruction[:key]
        instruction[:ranges][:key] = match.offset(Grammar::KEY_UNESCAPED_INDEX)
      else
        instruction[:key] = match[Grammar::KEY_ESCAPED_INDEX]
        instruction[:ranges][:escape_begin_operator] = match.offset(Grammar::KEY_ESCAPE_BEGIN_OPERATOR_INDEX)
        instruction[:ranges][:escape_end_operator] = match.offset(Grammar::KEY_ESCAPE_END_OPERATOR_INDEX)
        instruction[:ranges][:key] = match.offset(Grammar::KEY_ESCAPED_INDEX)
      end

      instruction[:parent] = last_section
      last_section[:elements].push(instruction)
      last_continuable_element = nil
      last_non_section_element = instruction

      if @unresolved_non_section_elements.has_key?(template)
        @unresolved_non_section_elements[template][:targets].push(instruction)
      else
        @unresolved_non_section_elements[template] = { targets: [instruction] }
      end

      instruction[:copy] = @unresolved_non_section_elements[template]
    end

    unless multiline_field
      @index = match.end(0) + 1
      @line += 1
    end
  end

  @context.line_count = @context.input[-1] == "\n" ? @line + 1 : @line
  @context.meta.concat(comments) if comments

  resolve unless @unresolved_non_section_elements.empty? && @unresolved_sections.empty?
end