gherkin 2.2.5-x86-mswin32

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (132) hide show
  1. data/.gitattributes +2 -0
  2. data/.gitignore +11 -0
  3. data/.mailmap +2 -0
  4. data/.rspec +1 -0
  5. data/.rvmrc +1 -0
  6. data/Gemfile +5 -0
  7. data/History.txt +306 -0
  8. data/LICENSE +20 -0
  9. data/README.rdoc +59 -0
  10. data/Rakefile +16 -0
  11. data/VERSION +1 -0
  12. data/bin/gherkin +5 -0
  13. data/build_native_gems.sh +8 -0
  14. data/cucumber.yml +3 -0
  15. data/features/escaped_pipes.feature +8 -0
  16. data/features/feature_parser.feature +237 -0
  17. data/features/json_formatter.feature +278 -0
  18. data/features/json_parser.feature +318 -0
  19. data/features/native_lexer.feature +19 -0
  20. data/features/parser_with_native_lexer.feature +205 -0
  21. data/features/pretty_formatter.feature +15 -0
  22. data/features/step_definitions/eyeball_steps.rb +3 -0
  23. data/features/step_definitions/gherkin_steps.rb +29 -0
  24. data/features/step_definitions/json_formatter_steps.rb +28 -0
  25. data/features/step_definitions/json_parser_steps.rb +20 -0
  26. data/features/step_definitions/pretty_formatter_steps.rb +82 -0
  27. data/features/steps_parser.feature +46 -0
  28. data/features/support/env.rb +38 -0
  29. data/gherkin.gemspec +59 -0
  30. data/ikvm/.gitignore +3 -0
  31. data/java/.gitignore +2 -0
  32. data/java/src/main/java/gherkin/lexer/i18n/.gitignore +1 -0
  33. data/java/src/main/resources/gherkin/.gitignore +1 -0
  34. data/lib/.gitignore +4 -0
  35. data/lib/gherkin.rb +2 -0
  36. data/lib/gherkin/c_lexer.rb +17 -0
  37. data/lib/gherkin/cli/main.rb +33 -0
  38. data/lib/gherkin/formatter/argument.rb +28 -0
  39. data/lib/gherkin/formatter/colors.rb +119 -0
  40. data/lib/gherkin/formatter/escaping.rb +15 -0
  41. data/lib/gherkin/formatter/filter_formatter.rb +136 -0
  42. data/lib/gherkin/formatter/json_formatter.rb +72 -0
  43. data/lib/gherkin/formatter/line_filter.rb +26 -0
  44. data/lib/gherkin/formatter/model.rb +231 -0
  45. data/lib/gherkin/formatter/monochrome_format.rb +9 -0
  46. data/lib/gherkin/formatter/pretty_formatter.rb +174 -0
  47. data/lib/gherkin/formatter/regexp_filter.rb +21 -0
  48. data/lib/gherkin/formatter/tag_count_formatter.rb +47 -0
  49. data/lib/gherkin/formatter/tag_filter.rb +19 -0
  50. data/lib/gherkin/i18n.rb +180 -0
  51. data/lib/gherkin/i18n.yml +601 -0
  52. data/lib/gherkin/json_parser.rb +88 -0
  53. data/lib/gherkin/lexer/i18n_lexer.rb +47 -0
  54. data/lib/gherkin/listener/event.rb +45 -0
  55. data/lib/gherkin/listener/formatter_listener.rb +113 -0
  56. data/lib/gherkin/native.rb +7 -0
  57. data/lib/gherkin/native/ikvm.rb +55 -0
  58. data/lib/gherkin/native/java.rb +55 -0
  59. data/lib/gherkin/native/null.rb +9 -0
  60. data/lib/gherkin/parser/meta.txt +5 -0
  61. data/lib/gherkin/parser/parser.rb +164 -0
  62. data/lib/gherkin/parser/root.txt +11 -0
  63. data/lib/gherkin/parser/steps.txt +4 -0
  64. data/lib/gherkin/rb_lexer.rb +8 -0
  65. data/lib/gherkin/rb_lexer/.gitignore +1 -0
  66. data/lib/gherkin/rb_lexer/README.rdoc +8 -0
  67. data/lib/gherkin/rubify.rb +24 -0
  68. data/lib/gherkin/tag_expression.rb +62 -0
  69. data/lib/gherkin/tools.rb +8 -0
  70. data/lib/gherkin/tools/files.rb +34 -0
  71. data/lib/gherkin/tools/reformat.rb +20 -0
  72. data/lib/gherkin/tools/stats.rb +20 -0
  73. data/lib/gherkin/tools/stats_listener.rb +60 -0
  74. data/lib/gherkin/version.rb +3 -0
  75. data/ragel/i18n/.gitignore +1 -0
  76. data/ragel/lexer.c.rl.erb +459 -0
  77. data/ragel/lexer.java.rl.erb +224 -0
  78. data/ragel/lexer.rb.rl.erb +179 -0
  79. data/ragel/lexer_common.rl.erb +50 -0
  80. data/spec/gherkin/c_lexer_spec.rb +21 -0
  81. data/spec/gherkin/fixtures/1.feature +8 -0
  82. data/spec/gherkin/fixtures/comments_in_table.feature +9 -0
  83. data/spec/gherkin/fixtures/complex.feature +45 -0
  84. data/spec/gherkin/fixtures/complex.json +143 -0
  85. data/spec/gherkin/fixtures/complex_for_filtering.feature +60 -0
  86. data/spec/gherkin/fixtures/complex_with_tags.feature +61 -0
  87. data/spec/gherkin/fixtures/dos_line_endings.feature +45 -0
  88. data/spec/gherkin/fixtures/hantu_pisang.feature +35 -0
  89. data/spec/gherkin/fixtures/i18n_fr.feature +14 -0
  90. data/spec/gherkin/fixtures/i18n_no.feature +7 -0
  91. data/spec/gherkin/fixtures/i18n_zh-CN.feature +9 -0
  92. data/spec/gherkin/fixtures/scenario_outline_with_tags.feature +13 -0
  93. data/spec/gherkin/fixtures/scenario_without_steps.feature +5 -0
  94. data/spec/gherkin/fixtures/simple_with_comments.feature +7 -0
  95. data/spec/gherkin/fixtures/simple_with_tags.feature +11 -0
  96. data/spec/gherkin/fixtures/with_bom.feature +3 -0
  97. data/spec/gherkin/formatter/argument_spec.rb +28 -0
  98. data/spec/gherkin/formatter/colors_spec.rb +18 -0
  99. data/spec/gherkin/formatter/filter_formatter_spec.rb +165 -0
  100. data/spec/gherkin/formatter/model_spec.rb +15 -0
  101. data/spec/gherkin/formatter/pretty_formatter_spec.rb +140 -0
  102. data/spec/gherkin/formatter/spaces.feature +9 -0
  103. data/spec/gherkin/formatter/tabs.feature +9 -0
  104. data/spec/gherkin/formatter/tag_count_formatter_spec.rb +30 -0
  105. data/spec/gherkin/i18n_spec.rb +149 -0
  106. data/spec/gherkin/java_lexer_spec.rb +20 -0
  107. data/spec/gherkin/json.rb +5 -0
  108. data/spec/gherkin/json_parser_spec.rb +67 -0
  109. data/spec/gherkin/lexer/i18n_lexer_spec.rb +43 -0
  110. data/spec/gherkin/output_stream_string_io.rb +24 -0
  111. data/spec/gherkin/parser/parser_spec.rb +16 -0
  112. data/spec/gherkin/rb_lexer_spec.rb +19 -0
  113. data/spec/gherkin/sexp_recorder.rb +56 -0
  114. data/spec/gherkin/shared/lexer_group.rb +592 -0
  115. data/spec/gherkin/shared/py_string_group.rb +153 -0
  116. data/spec/gherkin/shared/row_group.rb +120 -0
  117. data/spec/gherkin/shared/tags_group.rb +54 -0
  118. data/spec/gherkin/tag_expression_spec.rb +137 -0
  119. data/spec/spec_helper.rb +68 -0
  120. data/tasks/bench.rake +184 -0
  121. data/tasks/bench/feature_builder.rb +49 -0
  122. data/tasks/bench/generated/.gitignore +1 -0
  123. data/tasks/bench/null_listener.rb +4 -0
  124. data/tasks/compile.rake +102 -0
  125. data/tasks/cucumber.rake +18 -0
  126. data/tasks/gems.rake +42 -0
  127. data/tasks/ikvm.rake +54 -0
  128. data/tasks/ragel_task.rb +70 -0
  129. data/tasks/rdoc.rake +9 -0
  130. data/tasks/release.rake +30 -0
  131. data/tasks/rspec.rake +8 -0
  132. metadata +447 -0
@@ -0,0 +1,11 @@
1
+ | | feature | background | scenario | scenario_outline | examples | step | row | py_string | eof | comment | tag |
2
+ | root | feature | E | E | E | E | E | E | E | eof | push(meta) | push(meta) |
3
+ | feature | E | background | scenario | scenario_outline | E | E | E | E | eof | push(meta) | push(meta) |
4
+ | step | E | E | scenario | scenario_outline | E | step | step | step | eof | push(meta) | push(meta) |
5
+ | outline_step | E | E | scenario | scenario_outline | examples | outline_step | outline_step | outline_step | eof | push(meta) | push(meta) |
6
+ | background | E | E | scenario | scenario_outline | E | step | E | E | eof | push(meta) | push(meta) |
7
+ | scenario | E | E | scenario | scenario_outline | E | step | E | E | eof | push(meta) | push(meta) |
8
+ | scenario_outline | E | E | E | E | E | outline_step | E | E | eof | push(meta) | push(meta) |
9
+ | examples | E | E | E | E | E | E | examples_table | E | eof | push(meta) | push(meta) |
10
+ | examples_table | E | E | scenario | scenario_outline | examples | E | examples_table | E | eof | push(meta) | push(meta) |
11
+ | eof | E | E | E | E | E | E | E | E | E | E | E |
@@ -0,0 +1,4 @@
1
+ | | feature | background | scenario | scenario_outline | examples | step | row | py_string | eof | comment | tag |
2
+ | steps | E | E | E | E | E | step | E | E | eof | E | E |
3
+ | step | E | E | E | E | E | step | step | steps | eof | E | E |
4
+ | eof | E | E | E | E | E | E | E | E | E | E | E |
@@ -0,0 +1,8 @@
1
+ module Gherkin
2
+ module RbLexer
3
+ def self.[](i18n_underscored_iso_code)
4
+ require "gherkin/rb_lexer/#{i18n_underscored_iso_code}"
5
+ const_get(i18n_underscored_iso_code.capitalize)
6
+ end
7
+ end
8
+ end
@@ -0,0 +1 @@
1
+ *.rb
@@ -0,0 +1,8 @@
1
+ = Lexers
2
+
3
+ Gherkin support lexing of lots of natural languages, defined by gherkin/i18n.yml
4
+ The lexers are generated with the following command:
5
+
6
+ rake ragel:i18n
7
+
8
+ You have to run this command if you modify gherkin/i18n.yml
@@ -0,0 +1,24 @@
1
+ module Gherkin
2
+ module Rubify
3
+ if defined?(JRUBY_VERSION)
4
+ # Translate Java objects to Ruby.
5
+ # This is especially important to convert java.util.List coming
6
+ # from Java and back to a Ruby Array.
7
+ def rubify(o)
8
+ case(o)
9
+ when Java.java.util.Collection, Array
10
+ o.map{|e| rubify(e)}
11
+ when Java.gherkin.formatter.model.PyString
12
+ require 'gherkin/formatter/model'
13
+ Formatter::Model::PyString.new(o.value, o.line)
14
+ else
15
+ o
16
+ end
17
+ end
18
+ else
19
+ def rubify(o)
20
+ o
21
+ end
22
+ end
23
+ end
24
+ end
@@ -0,0 +1,62 @@
1
+ require 'gherkin/native'
2
+
3
+ module Gherkin
4
+ class TagExpression
5
+ native_impl('gherkin')
6
+
7
+ attr_reader :limits
8
+
9
+ def initialize(tag_expressions)
10
+ @ands = []
11
+ @limits = {}
12
+ tag_expressions.each do |expr|
13
+ add(expr.strip.split(/\s*,\s*/))
14
+ end
15
+ end
16
+
17
+ def empty?
18
+ @ands.empty?
19
+ end
20
+
21
+ def eval(tags)
22
+ return true if @ands.flatten.empty?
23
+ vars = Hash[*tags.map{|tag| [tag, true]}.flatten]
24
+ !!Kernel.eval(ruby_expression)
25
+ end
26
+
27
+ private
28
+
29
+ def add(tags_with_negation_and_limits)
30
+ negatives, positives = tags_with_negation_and_limits.partition{|tag| tag =~ /^~/}
31
+ @ands << (store_and_extract_limits(negatives, true) + store_and_extract_limits(positives, false))
32
+ end
33
+
34
+ def store_and_extract_limits(tags_with_negation_and_limits, negated)
35
+ tags_with_negation = []
36
+ tags_with_negation_and_limits.each do |tag_with_negation_and_limit|
37
+ tag_with_negation, limit = tag_with_negation_and_limit.split(':')
38
+ tags_with_negation << tag_with_negation
39
+ if limit
40
+ tag_without_negation = negated ? tag_with_negation[1..-1] : tag_with_negation
41
+ if @limits[tag_without_negation] && @limits[tag_without_negation] != limit.to_i
42
+ raise "Inconsistent tag limits for #{tag_without_negation}: #{@limits[tag_without_negation]} and #{limit.to_i}"
43
+ end
44
+ @limits[tag_without_negation] = limit.to_i
45
+ end
46
+ end
47
+ tags_with_negation
48
+ end
49
+
50
+ def ruby_expression
51
+ "(" + @ands.map do |ors|
52
+ ors.map do |tag|
53
+ if tag =~ /^~(.*)/
54
+ "!vars['#{$1}']"
55
+ else
56
+ "vars['#{tag}']"
57
+ end
58
+ end.join("||")
59
+ end.join(")&&(") + ")"
60
+ end
61
+ end
62
+ end
@@ -0,0 +1,8 @@
1
+ module Gherkin
2
+ module Tools
3
+ SUB_COMMANDS = %w(stats reformat)
4
+ SUB_COMMANDS.each do |cmd|
5
+ autoload cmd.capitalize.to_sym, "gherkin/tools/#{cmd}"
6
+ end
7
+ end
8
+ end
@@ -0,0 +1,34 @@
1
+ require 'gherkin'
2
+
3
+ module Gherkin
4
+ module Tools
5
+ # Base class for file based operations
6
+ class Files
7
+ include Enumerable
8
+
9
+ def initialize(paths)
10
+ raise "Please specify one or more paths" if paths.empty?
11
+ @paths = paths
12
+ end
13
+
14
+ def each(&proc)
15
+ globs = @paths.map do |path|
16
+ raise "#{path} does not exist" unless File.exist?(path)
17
+ File.directory?(path) ? File.join(path, '**', '*.feature') : path
18
+ end
19
+
20
+ Dir[*globs].uniq.sort.each(&proc)
21
+ end
22
+
23
+ def parse(file, formatter)
24
+ parser = Gherkin::Parser::Parser.new(formatter, true, "root")
25
+ begin
26
+ parser.parse(IO.read(file), file, 0)
27
+ rescue => e
28
+ e.message << " (#{file})"
29
+ raise e
30
+ end
31
+ end
32
+ end
33
+ end
34
+ end
@@ -0,0 +1,20 @@
1
+ require 'stringio'
2
+ require 'gherkin/tools/files'
3
+ require 'gherkin/formatter/pretty_formatter'
4
+ require 'gherkin/listener/formatter_listener'
5
+
6
+ module Gherkin
7
+ module Tools
8
+ class Reformat < Files
9
+ def run
10
+ each do |file|
11
+ io = defined?(JRUBY_VERSION) ? Java.java.io.StringWriter.new : StringIO.new
12
+ formatter = Formatter::PrettyFormatter.new(io, true)
13
+ parse(file, formatter)
14
+ string = defined?(JRUBY_VERSION) ? io.getBuffer.toString : io.string
15
+ File.open(file, 'w') {|io| io.write(string)}
16
+ end
17
+ end
18
+ end
19
+ end
20
+ end
@@ -0,0 +1,20 @@
1
+ require 'gherkin'
2
+ require 'gherkin/tools/files'
3
+ require 'gherkin/tools/stats_listener'
4
+
5
+ module Gherkin
6
+ module Tools
7
+ class Stats < Files
8
+ def run
9
+ formatter = StatsFormatter.new
10
+ each do |f|
11
+ parser = Gherkin::Parser::Parser.new(formatter, true)
12
+ parser.parse(IO.read(f), f, 0)
13
+ end
14
+ puts "Features: #{listener.features}"
15
+ puts "Scenarios: #{listener.scenarios}"
16
+ puts "Steps: #{listener.steps}"
17
+ end
18
+ end
19
+ end
20
+ end
@@ -0,0 +1,60 @@
1
+ require 'gherkin/native'
2
+
3
+ # encoding: utf-8
4
+ module Gherkin
5
+ module Tools
6
+ class StatsListener
7
+ implements 'gherkin.Listener'
8
+
9
+ attr_reader :features, :scenarios, :steps
10
+
11
+ def initialize
12
+ @features = 0
13
+ @scenarios = 0
14
+ @steps = 0
15
+ end
16
+
17
+ def location(uri)
18
+ end
19
+
20
+ def tag(name, line)
21
+ end
22
+
23
+ def comment(content, line)
24
+ end
25
+
26
+ def feature(keyword, name, description, line)
27
+ @features += 1
28
+ end
29
+
30
+ def background(keyword, name, description, line)
31
+ end
32
+
33
+ def scenario(keyword, name, description, line)
34
+ @scenarios += 1
35
+ end
36
+
37
+ def scenario_outline(keyword, name, description, line)
38
+ end
39
+
40
+ def examples(keyword, name, description, line)
41
+ end
42
+
43
+ def step(keyword, name, line)
44
+ @steps += 1
45
+ end
46
+
47
+ def row(row, line)
48
+ end
49
+
50
+ def py_string(string, line)
51
+ end
52
+
53
+ def syntax_error(state, event, legal_events, uri, line)
54
+ end
55
+
56
+ def eof
57
+ end
58
+ end
59
+ end
60
+ end
@@ -0,0 +1,3 @@
1
+ module Gherkin
2
+ VERSION = IO.read(File.dirname(__FILE__) + '/../../VERSION').strip
3
+ end
@@ -0,0 +1 @@
1
+ *.rl
@@ -0,0 +1,459 @@
1
+ #include <assert.h>
2
+ #include <ruby.h>
3
+
4
+ #if defined(_WIN32)
5
+ #include <stddef.h>
6
+ #endif
7
+
8
+ #ifdef HAVE_RUBY_RE_H
9
+ #include <ruby/re.h>
10
+ #else
11
+ #include <re.h>
12
+ #endif
13
+
14
+ #ifdef HAVE_RUBY_ENCODING_H
15
+ #include <ruby/encoding.h>
16
+ #define ENCODED_STR_NEW(ptr, len) \
17
+ rb_enc_str_new(ptr, len, rb_utf8_encoding())
18
+ #else
19
+ #define ENCODED_STR_NEW(ptr, len) \
20
+ rb_str_new(ptr, len)
21
+ #endif
22
+
23
+ #define LF_FLAG 0
24
+ #define CRLF_FLAG 1
25
+ #define LF "\n"
26
+ #define CRLF "\r\n"
27
+
28
+ #ifndef RSTRING_PTR
29
+ #define RSTRING_PTR(s) (RSTRING(s)->ptr)
30
+ #endif
31
+
32
+ #ifndef RSTRING_LEN
33
+ #define RSTRING_LEN(s) (RSTRING(s)->len)
34
+ #endif
35
+
36
+ #define DATA_GET(FROM, TYPE, NAME) \
37
+ Data_Get_Struct(FROM, TYPE, NAME); \
38
+ if (NAME == NULL) { \
39
+ rb_raise(rb_eArgError, "NULL found for " # NAME " when it shouldn't be."); \
40
+ }
41
+
42
+ typedef struct lexer_state {
43
+ int content_len;
44
+ int line_number;
45
+ int current_line;
46
+ int start_col;
47
+ int eol;
48
+ size_t mark;
49
+ size_t keyword_start;
50
+ size_t keyword_end;
51
+ size_t next_keyword_start;
52
+ size_t content_start;
53
+ size_t content_end;
54
+ size_t query_start;
55
+ size_t last_newline;
56
+ size_t final_newline;
57
+ } lexer_state;
58
+
59
+ static VALUE mGherkin;
60
+ static VALUE mGherkinLexer;
61
+ static VALUE mCLexer;
62
+ static VALUE cI18nLexer;
63
+ static VALUE rb_eGherkinLexingError;
64
+
65
+ #define LEN(AT, P) (P - data - lexer->AT)
66
+ #define MARK(M, P) (lexer->M = (P) - data)
67
+ #define PTR_TO(P) (data + lexer->P)
68
+
69
+ #define STORE_KW_END_CON(EVENT) \
70
+ store_multiline_kw_con(listener, # EVENT, \
71
+ PTR_TO(keyword_start), LEN(keyword_start, PTR_TO(keyword_end - 1)), \
72
+ PTR_TO(content_start), LEN(content_start, PTR_TO(content_end)), \
73
+ lexer->current_line, lexer->eol); \
74
+ if (lexer->content_end != 0) { \
75
+ p = PTR_TO(content_end - 1); \
76
+ } \
77
+ lexer->content_end = 0
78
+
79
+ #define STORE_ATTR(ATTR) \
80
+ store_attr(listener, # ATTR, \
81
+ PTR_TO(content_start), LEN(content_start, p), \
82
+ lexer->line_number)
83
+
84
+ %%{
85
+ machine lexer;
86
+
87
+ action begin_content {
88
+ MARK(content_start, p);
89
+ lexer->current_line = lexer->line_number;
90
+ }
91
+
92
+ action begin_pystring_content {
93
+ MARK(content_start, p);
94
+ }
95
+
96
+ action start_pystring {
97
+ lexer->current_line = lexer->line_number;
98
+ lexer->start_col = p - data - lexer->last_newline;
99
+ }
100
+
101
+ action store_pystring_content {
102
+ int len = LEN(content_start, PTR_TO(final_newline));
103
+
104
+ if (len < 0) len = 0;
105
+
106
+ store_pystring_content(listener, lexer->start_col, PTR_TO(content_start), len, lexer->current_line);
107
+ }
108
+
109
+ action store_feature_content {
110
+ STORE_KW_END_CON(feature);
111
+ }
112
+
113
+ action store_background_content {
114
+ STORE_KW_END_CON(background);
115
+ }
116
+
117
+ action store_scenario_content {
118
+ STORE_KW_END_CON(scenario);
119
+ }
120
+
121
+ action store_scenario_outline_content {
122
+ STORE_KW_END_CON(scenario_outline);
123
+ }
124
+
125
+ action store_examples_content {
126
+ STORE_KW_END_CON(examples);
127
+ }
128
+
129
+ action store_step_content {
130
+ store_kw_con(listener, "step",
131
+ PTR_TO(keyword_start), LEN(keyword_start, PTR_TO(keyword_end)),
132
+ PTR_TO(content_start), LEN(content_start, p),
133
+ lexer->current_line);
134
+ }
135
+
136
+ action store_comment_content {
137
+ STORE_ATTR(comment);
138
+ lexer->mark = 0;
139
+ }
140
+
141
+ action store_tag_content {
142
+ STORE_ATTR(tag);
143
+ lexer->mark = 0;
144
+ }
145
+
146
+ action inc_line_number {
147
+ lexer->line_number += 1;
148
+ MARK(final_newline, p);
149
+ }
150
+
151
+ action last_newline {
152
+ MARK(last_newline, p + 1);
153
+ }
154
+
155
+ action start_keyword {
156
+ if (lexer->mark == 0) {
157
+ MARK(mark, p);
158
+ }
159
+ }
160
+
161
+ action end_keyword {
162
+ MARK(keyword_end, p);
163
+ MARK(keyword_start, PTR_TO(mark));
164
+ MARK(content_start, p + 1);
165
+ lexer->mark = 0;
166
+ }
167
+
168
+ action next_keyword_start {
169
+ MARK(content_end, p);
170
+ }
171
+
172
+ action start_row {
173
+ p = p - 1;
174
+ lexer->current_line = lexer->line_number;
175
+ current_row = rb_ary_new();
176
+ }
177
+
178
+ action begin_cell_content {
179
+ MARK(content_start, p);
180
+ }
181
+
182
+ action store_cell_content {
183
+ VALUE con = ENCODED_STR_NEW(PTR_TO(content_start), LEN(content_start, p));
184
+ rb_funcall(con, rb_intern("strip!"), 0);
185
+ VALUE re_pipe = rb_reg_regcomp(rb_str_new2("\\\\\\|"));
186
+ VALUE re_backslash = rb_reg_regcomp(rb_str_new2("\\\\\\\\"));
187
+ rb_funcall(con, rb_intern("gsub!"), 2, re_pipe, rb_str_new2("|"));
188
+ rb_funcall(con, rb_intern("gsub!"), 2, re_backslash, rb_str_new2("\\"));
189
+
190
+ rb_ary_push(current_row, con);
191
+ }
192
+
193
+ action store_row {
194
+ rb_funcall(listener, rb_intern("row"), 2, current_row, INT2FIX(lexer->current_line));
195
+ }
196
+
197
+ action end_feature {
198
+ if (cs < lexer_first_final) {
199
+ if (raise_lexer_error != NULL) {
200
+ size_t count = 0;
201
+ VALUE newstr_val;
202
+ char *newstr;
203
+ int newstr_count = 0;
204
+ size_t len;
205
+ const char *buff;
206
+ if (lexer->last_newline != 0) {
207
+ len = LEN(last_newline, eof);
208
+ buff = PTR_TO(last_newline);
209
+ } else {
210
+ len = strlen(data);
211
+ buff = data;
212
+ }
213
+
214
+ // Allocate as a ruby string so that it gets cleaned up by GC
215
+ newstr_val = rb_str_new(buff, len);
216
+ newstr = RSTRING_PTR(newstr_val);
217
+
218
+ for (count = 0; count < len; count++) {
219
+ if(buff[count] == 10) {
220
+ newstr[newstr_count] = '\0'; // terminate new string at first newline found
221
+ break;
222
+ } else {
223
+ if (buff[count] == '%') {
224
+ newstr[newstr_count++] = buff[count];
225
+ newstr[newstr_count] = buff[count];
226
+ } else {
227
+ newstr[newstr_count] = buff[count];
228
+ }
229
+ }
230
+ newstr_count++;
231
+ }
232
+
233
+ int line = lexer->line_number;
234
+ lexer_init(lexer); // Re-initialize so we can scan again with the same lexer
235
+ raise_lexer_error(newstr, line);
236
+ }
237
+ } else {
238
+ rb_funcall(listener, rb_intern("eof"), 0);
239
+ }
240
+ }
241
+
242
+ include lexer_common "lexer_common.<%= @i18n.underscored_iso_code %>.rl";
243
+
244
+ }%%
245
+
246
+ /** Data **/
247
+ %% write data;
248
+
249
+ static VALUE
250
+ strip_i(VALUE str, VALUE ary)
251
+ {
252
+ rb_funcall(str, rb_intern("strip!"), 0);
253
+ rb_ary_push(ary, str);
254
+
255
+ return Qnil;
256
+ }
257
+
258
+ static VALUE
259
+ multiline_strip(VALUE text)
260
+ {
261
+ VALUE map = rb_ary_new();
262
+ VALUE split = rb_str_split(text, "\n");
263
+
264
+ rb_iterate(rb_each, split, strip_i, map);
265
+
266
+ return split;
267
+ }
268
+
269
+ static void
270
+ store_kw_con(VALUE listener, const char * event_name,
271
+ const char * keyword_at, size_t keyword_length,
272
+ const char * at, size_t length,
273
+ int current_line)
274
+ {
275
+ VALUE con = Qnil, kw = Qnil;
276
+ kw = ENCODED_STR_NEW(keyword_at, keyword_length);
277
+ con = ENCODED_STR_NEW(at, length);
278
+ rb_funcall(con, rb_intern("strip!"), 0);
279
+ rb_funcall(listener, rb_intern(event_name), 3, kw, con, INT2FIX(current_line));
280
+ }
281
+
282
+ static void
283
+ store_multiline_kw_con(VALUE listener, const char * event_name,
284
+ const char * keyword_at, size_t keyword_length,
285
+ const char * at, size_t length,
286
+ int current_line, int eol)
287
+ {
288
+ VALUE con = Qnil, kw = Qnil, name = Qnil, desc = Qnil;
289
+
290
+ kw = ENCODED_STR_NEW(keyword_at, keyword_length);
291
+ con = ENCODED_STR_NEW(at, length);
292
+
293
+ VALUE split = multiline_strip(con);
294
+
295
+ name = rb_funcall(split, rb_intern("shift"), 0);
296
+ desc = rb_ary_join(split, rb_str_new2( \
297
+ eol == CRLF_FLAG ? CRLF : LF ));
298
+
299
+ if( name == Qnil )
300
+ {
301
+ name = rb_str_new2("");
302
+ }
303
+ if( rb_funcall(desc, rb_intern("size"), 0) == 0)
304
+ {
305
+ desc = rb_str_new2("");
306
+ }
307
+ rb_funcall(name, rb_intern("strip!"), 0);
308
+ rb_funcall(desc, rb_intern("strip!"), 0);
309
+ rb_funcall(listener, rb_intern(event_name), 4, kw, name, desc, INT2FIX(current_line));
310
+ }
311
+
312
+ static void
313
+ store_attr(VALUE listener, const char * attr_type,
314
+ const char * at, size_t length,
315
+ int line)
316
+ {
317
+ VALUE val = ENCODED_STR_NEW(at, length);
318
+ rb_funcall(listener, rb_intern(attr_type), 2, val, INT2FIX(line));
319
+ }
320
+
321
+ static void
322
+ store_pystring_content(VALUE listener,
323
+ int start_col,
324
+ const char *at, size_t length,
325
+ int current_line)
326
+ {
327
+ VALUE con = ENCODED_STR_NEW(at, length);
328
+ // Gherkin will crash gracefully if the string representation of start_col pushes the pattern past 32 characters
329
+ char pat[32];
330
+ snprintf(pat, 32, "^[\t ]{0,%d}", start_col);
331
+ VALUE re = rb_reg_regcomp(rb_str_new2(pat));
332
+ VALUE re2 = rb_reg_regcomp(rb_str_new2("\r\\Z"));
333
+ VALUE unescape_escaped_quotes = rb_reg_regcomp(rb_str_new2("\\\\\"\\\\\"\\\\\""));
334
+ rb_funcall(con, rb_intern("gsub!"), 2, re, rb_str_new2(""));
335
+ rb_funcall(con, rb_intern("sub!"), 2, re2, rb_str_new2(""));
336
+ rb_funcall(con, rb_intern("gsub!"), 2, unescape_escaped_quotes, rb_str_new2("\"\"\""));
337
+ rb_funcall(listener, rb_intern("py_string"), 2, con, INT2FIX(current_line));
338
+ }
339
+
340
+ static void
341
+ raise_lexer_error(const char * at, int line)
342
+ {
343
+ rb_raise(rb_eGherkinLexingError, "Lexing error on line %d: '%s'. See http://wiki.github.com/aslakhellesoy/gherkin/lexingerror for more information.", line, at);
344
+ }
345
+
346
+ static int
347
+ count_char(char char_to_count, char *str) {
348
+
349
+ int count = 0;
350
+ int i = 0;
351
+ while(str[i] != '\0') {
352
+ if(str[i] == char_to_count) {
353
+ count++;
354
+ }
355
+ i++;
356
+ }
357
+ return count;
358
+ }
359
+
360
+ static void lexer_init(lexer_state *lexer) {
361
+ lexer->content_start = 0;
362
+ lexer->content_end = 0;
363
+ lexer->content_len = 0;
364
+ lexer->mark = 0;
365
+ lexer->keyword_start = 0;
366
+ lexer->keyword_end = 0;
367
+ lexer->next_keyword_start = 0;
368
+ lexer->line_number = 1;
369
+ lexer->last_newline = 0;
370
+ lexer->final_newline = 0;
371
+ lexer->start_col = 0;
372
+ lexer->eol = LF_FLAG;
373
+ }
374
+
375
+ static VALUE CLexer_alloc(VALUE klass)
376
+ {
377
+ VALUE obj;
378
+ lexer_state *lxr = ALLOC(lexer_state);
379
+ lexer_init(lxr);
380
+
381
+ obj = Data_Wrap_Struct(klass, NULL, -1, lxr);
382
+
383
+ return obj;
384
+ }
385
+
386
+ static VALUE CLexer_init(VALUE self, VALUE listener)
387
+ {
388
+ rb_iv_set(self, "@listener", listener);
389
+
390
+ lexer_state *lxr = NULL;
391
+ DATA_GET(self, lexer_state, lxr);
392
+ lexer_init(lxr);
393
+
394
+ return self;
395
+ }
396
+
397
+ static VALUE CLexer_scan(VALUE self, VALUE input)
398
+ {
399
+ VALUE listener = rb_iv_get(self, "@listener");
400
+
401
+ lexer_state *lexer = NULL;
402
+ DATA_GET(self, lexer_state, lexer);
403
+
404
+ VALUE input_copy = rb_str_dup(input);
405
+
406
+ rb_str_append(input_copy, rb_str_new2("\n%_FEATURE_END_%"));
407
+ char *data = RSTRING_PTR(input_copy);
408
+ size_t len = RSTRING_LEN(input_copy);
409
+
410
+ if (count_char('\r', data) > (count_char('\n', data) / 2)) {
411
+ lexer->eol = CRLF_FLAG;
412
+ }
413
+
414
+ if (len == 0) {
415
+ rb_raise(rb_eGherkinLexingError, "No content to lex.");
416
+ } else {
417
+
418
+ const char *p, *pe, *eof;
419
+ int cs = 0;
420
+
421
+ VALUE current_row = Qnil;
422
+
423
+ p = data;
424
+ pe = data + len;
425
+ eof = pe;
426
+
427
+ assert(*pe == '\0' && "pointer does not end on NULL");
428
+
429
+ %% write init;
430
+ %% write exec;
431
+
432
+ assert(p <= pe && "data overflow after parsing execute");
433
+ assert(lexer->content_start <= len && "content starts after data end");
434
+ assert(lexer->mark < len && "mark is after data end");
435
+
436
+ // Reset lexer by re-initializing the whole thing
437
+ lexer_init(lexer);
438
+
439
+ if (cs == lexer_error) {
440
+ rb_raise(rb_eGherkinLexingError, "Invalid format, lexing fails.");
441
+ } else {
442
+ return Qtrue;
443
+ }
444
+ }
445
+ }
446
+
447
+ void Init_gherkin_lexer_<%= @i18n.underscored_iso_code %>()
448
+ {
449
+ mGherkin = rb_define_module("Gherkin");
450
+ mGherkinLexer = rb_define_module_under(mGherkin, "Lexer");
451
+ rb_eGherkinLexingError = rb_const_get(mGherkinLexer, rb_intern("LexingError"));
452
+
453
+ mCLexer = rb_define_module_under(mGherkin, "CLexer");
454
+ cI18nLexer = rb_define_class_under(mCLexer, "<%= @i18n.underscored_iso_code.capitalize %>", rb_cObject);
455
+ rb_define_alloc_func(cI18nLexer, CLexer_alloc);
456
+ rb_define_method(cI18nLexer, "initialize", CLexer_init, 1);
457
+ rb_define_method(cI18nLexer, "scan", CLexer_scan, 1);
458
+ }
459
+