anbt-sql-formatter 0.0.1 → 0.0.2

Sign up to get free protection for your applications and to get access to all the features.
Files changed (16) hide show
  1. data/bin/anbt-sql-formatter +0 -3
  2. data/lib/anbt-sql-formatter/coarse-tokenizer.rb +1 -3
  3. data/lib/anbt-sql-formatter/exception.rb +0 -2
  4. data/lib/anbt-sql-formatter/formatter.rb +50 -57
  5. data/lib/anbt-sql-formatter/helper.rb +42 -56
  6. data/lib/anbt-sql-formatter/parser.rb +40 -52
  7. data/lib/anbt-sql-formatter/rule.rb +5 -2
  8. data/lib/anbt-sql-formatter/token.rb +1 -10
  9. data/lib/anbt-sql-formatter/version.rb +1 -1
  10. data/test/helper.rb +7 -1
  11. data/test/test_coarse-tokenizer.rb +327 -228
  12. data/test/test_formatter.rb +363 -276
  13. data/test/test_helper.rb +2 -2
  14. data/test/test_parser.rb +302 -213
  15. data/test/test_rule.rb +10 -8
  16. metadata +21 -31
data/lib/anbt-sql-formatter/rule.rb CHANGED
@@ -1,6 +1,6 @@
1
1
  # -*- coding: utf-8 -*-
2
2
 
3
- require "pp"
3
+ require "anbt-sql-formatter/helper"
4
4
 
5
5
  =begin
6
6
  AnbtSqlFormatter: SQL整形ツール. SQL文を決められたルールに従い整形します。
@@ -19,6 +19,9 @@ http://homepage2.nifty.com/igat/igapyon/diary/2005/ig050613.html
19
19
 
20
20
  class AnbtSql
21
21
  class Rule
22
+
23
+ include StringUtil
24
+
22
25
  attr_accessor :keyword, :indent_string, :function_names, :space_after_comma
23
26
  attr_accessor :kw_multi_words
24
27
 
@@ -110,7 +113,7 @@ class AnbtSql
110
113
  end
111
114
 
112
115
  for i in 0...(@function_names.length)
113
- if (@function_names[i].equalsIgnoreCase(name))
116
+ if (equals_ignore_case(@function_names[i], name))
114
117
  return true
115
118
  end
116
119
  end
data/lib/anbt-sql-formatter/token.rb CHANGED
@@ -1,7 +1,5 @@
1
1
  # -*- coding: utf-8 -*-
2
2
 
3
- require "pp"
4
-
5
3
  class AnbtSql
6
4
  class TokenConstants
7
5
 
@@ -56,14 +54,7 @@ class AnbtSql
56
54
  # @return:: バリューオブジェクトの文字列表現。
57
55
  #
58
56
  def to_s
59
- buf = ""
60
- buf << "AbstractAnbtSqlToken["
61
- buf << "_type=" + @_type
62
- buf << ",string=" + @string
63
- buf << ",pos=" + @pos
64
- buf << "]"
65
-
66
- buf
57
+ @string
67
58
  end
68
59
  end
69
60
 
data/lib/anbt-sql-formatter/version.rb CHANGED
@@ -1,7 +1,7 @@
1
1
  module Anbt
2
2
  module Sql
3
3
  module Formatter
4
- VERSION = "0.0.1"
4
+ VERSION = "0.0.2"
5
5
  end
6
6
  end
7
7
  end
data/test/helper.rb CHANGED
@@ -6,7 +6,7 @@ $LOAD_PATH.unshift File.join(File.dirname(__FILE__), "..", "lib")
6
6
  class Helper
7
7
  def Helper.format_tokens(list)
8
8
  list.map{|token|
9
- "<#{token._type}>#{token.string}</>"
9
+ "#{token._type} (#{token.string})"
10
10
  }.join("\n")
11
11
  end
12
12
  end
@@ -15,3 +15,9 @@ end
15
15
  def assert_equals(a,b,c)
16
16
  assert_equal(b,c,a)
17
17
  end
18
+
19
+ def strip_indent(text)
20
+ text.split("\n").map{|line|
21
+ line.sub(/^ */, "")
22
+ }.join("\n")
23
+ end
data/test/test_coarse-tokenizer.rb CHANGED
@@ -9,16 +9,18 @@ class CoarseTokenizer
9
9
  end
10
10
 
11
11
 
12
- def format(tokens)
13
- tokens.map{|t| t.to_s }.join("\n")
14
- end
15
-
16
12
 
17
13
  class TestCoarseTokenizer < Test::Unit::TestCase
18
14
  def setup
19
15
  @tok = CoarseTokenizer.new
20
16
  end
21
17
 
18
+ def _format(tokens)
19
+ tokens.map{|t|
20
+ "#{t._type} (#{t.string})"
21
+ }.join("\n")
22
+ end
23
+
22
24
 
23
25
  def test_shift_to_buf
24
26
  @tok.buf = ""
@@ -62,78 +64,102 @@ class TestCoarseTokenizer < Test::Unit::TestCase
62
64
  def test_tokenize
63
65
  msg = "tokenize - "
64
66
 
65
- assert_equals( msg, (<<EOB
66
- <plain>aa</>
67
- EOB
68
- ).chomp,
69
- format(@tok.tokenize((<<EOB
70
- aa
71
- EOB
72
- ).chomp))
73
- )
67
+ assert_equals(
68
+ msg,
69
+ strip_indent(
70
+ <<-EOB
71
+ plain (aa)
72
+ EOB
73
+ ),
74
+ _format(@tok.tokenize(strip_indent(
75
+ <<-EOB
76
+ aa
77
+ EOB
78
+ )))
79
+ )
74
80
 
75
81
  ########
76
- assert_equals( msg, (<<EOB
77
- <plain>aa </>
78
- <quote_double>"bb"</>
79
- EOB
80
- ).chomp,
81
- format(@tok.tokenize((<<EOB
82
- aa "bb"
83
- EOB
84
- ).chomp))
85
- )
82
+ assert_equals(
83
+ msg,
84
+ strip_indent(
85
+ <<-EOB
86
+ plain (aa )
87
+ quote_double ("bb")
88
+ EOB
89
+ ),
90
+ _format(@tok.tokenize(strip_indent(
91
+ <<-EOB
92
+ aa "bb"
93
+ EOB
94
+ )))
95
+ )
86
96
 
87
97
  ########
88
- assert_equals( msg, (<<EOB
89
- <plain>aa </>
90
- <quote_single>'bb'</>
91
- EOB
92
- ).chomp,
93
- format(@tok.tokenize((<<EOB
94
- aa 'bb'
95
- EOB
96
- ).chomp))
97
- )
98
+ assert_equals(
99
+ msg,
100
+ strip_indent(
101
+ <<-EOB
102
+ plain (aa )
103
+ quote_single ('bb')
104
+ EOB
105
+ ),
106
+ _format(@tok.tokenize(strip_indent(
107
+ <<-EOB
108
+ aa 'bb'
109
+ EOB
110
+ )))
111
+ )
98
112
 
99
113
  ########
100
- assert_equals( msg, (<<EOB
101
- <plain>aa </>
102
- <comment_single>--bb<br></>
103
- <plain>cc</>
104
- EOB
105
- ).chomp,
106
- format(@tok.tokenize((<<EOB
107
- aa --bb
108
- cc
109
- EOB
110
- ).chomp))
111
- )
114
+ assert_equals(
115
+ msg,
116
+ strip_indent(
117
+ <<-EOB
118
+ plain (aa )
119
+ comment_single (--bb\n)
120
+ plain (cc)
121
+ EOB
122
+ ),
123
+ _format(@tok.tokenize(strip_indent(
124
+ <<-EOB
125
+ aa --bb
126
+ cc
127
+ EOB
128
+ )))
129
+ )
112
130
 
113
131
  ########
114
- assert_equals( msg, (<<EOB
115
- <plain>aa </>
116
- <comment_multi>/* bb */</>
117
- <plain> cc</>
118
- EOB
119
- ).chomp,
120
- format(@tok.tokenize((<<EOB
121
- aa /* bb */ cc
122
- EOB
123
- ).chomp))
124
- )
132
+ assert_equals(
133
+ msg,
134
+ strip_indent(
135
+ <<-EOB
136
+ plain (aa )
137
+ comment_multi (/* bb */)
138
+ plain ( cc)
139
+ EOB
140
+ ),
141
+ _format(@tok.tokenize(strip_indent(
142
+ <<-EOB
143
+ aa /* bb */ cc
144
+ EOB
145
+ )))
146
+ )
125
147
 
126
148
  ########
127
- assert_equals( msg + "begin with multiline comment", (<<EOB
128
- <comment_multi>/* bb */</>
129
- <plain> cc</>
130
- EOB
131
- ).chomp,
132
- format(@tok.tokenize((<<EOB
133
- /* bb */ cc
134
- EOB
135
- ).chomp))
136
- )
149
+ assert_equals(
150
+ msg + "begin with multiline comment",
151
+ strip_indent(
152
+ <<-EOB
153
+ comment_multi (/* bb */)
154
+ plain ( cc)
155
+ EOB
156
+ ),
157
+ _format(@tok.tokenize(strip_indent(
158
+ <<-EOB
159
+ /* bb */ cc
160
+ EOB
161
+ )))
162
+ )
137
163
  end
138
164
 
139
165
 
@@ -141,74 +167,99 @@ EOB
141
167
  msg = "string_in_string"
142
168
 
143
169
  ########
144
- assert_equals( msg, (<<EOB
145
- <quote_double>"aa'bb'cc"</>
146
- EOB
147
- ).chomp,
148
- format(@tok.tokenize((<<EOB
149
- "aa'bb'cc"
150
- EOB
151
- ).chomp))
152
- )
170
+ assert_equals(
171
+ msg,
172
+ strip_indent(
173
+ <<-EOB
174
+ quote_double ("aa'bb'cc")
175
+ EOB
176
+ ),
177
+ _format(@tok.tokenize(strip_indent(
178
+ <<-EOB
179
+ "aa'bb'cc"
180
+ EOB
181
+ )))
182
+ )
153
183
 
154
184
  ########
155
- assert_equals( msg, (<<EOB
156
- <quote_single>'aa"bb"cc'</>
157
- EOB
158
- ).chomp,
159
- format(@tok.tokenize((<<EOB
160
- 'aa"bb"cc'
161
- EOB
162
- ).chomp))
163
- )
185
+ assert_equals(
186
+ msg,
187
+ strip_indent(
188
+ <<-EOB
189
+ quote_single ('aa"bb"cc')
190
+ EOB
191
+ ),
192
+ _format(@tok.tokenize(strip_indent(
193
+ <<-EOB
194
+ 'aa"bb"cc'
195
+ EOB
196
+ )))
197
+ )
164
198
  end
165
199
 
166
200
 
167
201
  def test_comment_in_comment
168
202
  msg = "comment_in_comment - "
203
+
169
204
  ########
170
- assert_equals( msg, (<<EOB
171
- <comment_single>--a--b</>
172
- EOB
173
- ).chomp,
174
- format(@tok.tokenize((<<EOB
175
- --a--b
176
- EOB
177
- ).chomp))
178
- )
205
+ assert_equals(
206
+ msg,
207
+ strip_indent(
208
+ <<-EOB
209
+ comment_single (--a--b)
210
+ EOB
211
+ ),
212
+ _format(@tok.tokenize(strip_indent(
213
+ <<-EOB
214
+ --a--b
215
+ EOB
216
+ )))
217
+ )
179
218
 
180
219
  ########
181
- assert_equals( msg, (<<EOB
182
- <comment_single>-- aa /* bb */</>
183
- EOB
184
- ).chomp,
185
- format(@tok.tokenize((<<EOB
186
- -- aa /* bb */
187
- EOB
188
- ).chomp))
189
- )
220
+ assert_equals(
221
+ msg,
222
+ strip_indent(
223
+ <<-EOB
224
+ comment_single (-- aa /* bb */)
225
+ EOB
226
+ ),
227
+ _format(@tok.tokenize(strip_indent(
228
+ <<-EOB
229
+ -- aa /* bb */
230
+ EOB
231
+ )))
232
+ )
190
233
 
191
234
  ########
192
- assert_equals( msg, (<<EOB
193
- <comment_multi>/* aa /* bb */</>
194
- EOB
195
- ).chomp,
196
- format(@tok.tokenize((<<EOB
197
- /* aa /* bb */
198
- EOB
199
- ).chomp))
200
- )
235
+ assert_equals(
236
+ msg,
237
+ strip_indent(
238
+ <<-EOB
239
+ comment_multi (/* aa /* bb */)
240
+ EOB
241
+ ),
242
+ _format(@tok.tokenize(strip_indent(
243
+ <<-EOB
244
+ /* aa /* bb */
245
+ EOB
246
+ )))
247
+ )
201
248
 
202
249
  ########
203
- assert_equals( msg, (<<EOB
204
- <comment_single>-- aa /* bb */</>
205
- EOB
206
- ).chomp,
207
- format(@tok.tokenize((<<EOB
208
- -- aa /* bb */
209
- EOB
210
- ).chomp))
211
- )
250
+ assert_equals(
251
+ msg,
252
+ strip_indent(
253
+ <<-EOB
254
+ comment_multi (/* aa -- bb */)
255
+ EOB
256
+ ),
257
+ _format(@tok.tokenize(strip_indent(
258
+ <<-EOB
259
+ /* aa -- bb */
260
+ EOB
261
+ )))
262
+ )
212
263
  end
213
264
 
214
265
 
@@ -216,48 +267,64 @@ EOB
216
267
  msg = "string_in_comment - "
217
268
 
218
269
  ########
219
- assert_equals( msg, (<<EOB
220
- <comment_single>-- aa "bb" cc</>
221
- EOB
222
- ).chomp,
223
- format(@tok.tokenize((<<EOB
224
- -- aa "bb" cc
225
- EOB
226
- ).chomp))
227
- )
270
+ assert_equals(
271
+ msg,
272
+ strip_indent(
273
+ <<-EOB
274
+ comment_single (-- aa "bb" cc)
275
+ EOB
276
+ ),
277
+ _format(@tok.tokenize(strip_indent(
278
+ <<-EOB
279
+ -- aa "bb" cc
280
+ EOB
281
+ )))
282
+ )
228
283
 
229
284
  ########
230
- assert_equals( msg, (<<EOB
231
- <comment_single>-- aa 'bb' cc</>
232
- EOB
233
- ).chomp,
234
- format(@tok.tokenize((<<EOB
235
- -- aa 'bb' cc
236
- EOB
237
- ).chomp))
238
- )
285
+ assert_equals(
286
+ msg,
287
+ strip_indent(
288
+ <<-EOB
289
+ comment_single (-- aa 'bb' cc)
290
+ EOB
291
+ ),
292
+ _format(@tok.tokenize(strip_indent(
293
+ <<-EOB
294
+ -- aa 'bb' cc
295
+ EOB
296
+ )))
297
+ )
239
298
 
240
299
  ########
241
- assert_equals( msg, (<<EOB
242
- <comment_multi>/* aa "bb" cc */</>
243
- EOB
244
- ).chomp,
245
- format(@tok.tokenize((<<EOB
246
- /* aa "bb" cc */
247
- EOB
248
- ).chomp))
249
- )
300
+ assert_equals(
301
+ msg,
302
+ strip_indent(
303
+ <<-EOB
304
+ comment_multi (/* aa "bb" cc */)
305
+ EOB
306
+ ),
307
+ _format(@tok.tokenize(strip_indent(
308
+ <<-EOB
309
+ /* aa "bb" cc */
310
+ EOB
311
+ )))
312
+ )
250
313
 
251
314
  ########
252
- assert_equals( msg, (<<EOB
253
- <comment_multi>/* aa 'bb' cc */</>
254
- EOB
255
- ).chomp,
256
- format(@tok.tokenize((<<EOB
257
- /* aa 'bb' cc */
258
- EOB
259
- ).chomp))
260
- )
315
+ assert_equals(
316
+ msg,
317
+ strip_indent(
318
+ <<-EOB
319
+ comment_multi (/* aa 'bb' cc */)
320
+ EOB
321
+ ),
322
+ _format(@tok.tokenize(strip_indent(
323
+ <<-EOB
324
+ /* aa 'bb' cc */
325
+ EOB
326
+ )))
327
+ )
261
328
  end
262
329
 
263
330
 
@@ -265,48 +332,64 @@ EOB
265
332
  msg = "comment_in_string - "
266
333
 
267
334
  ########
268
- assert_equals( msg + "comment_single in quote_single", (<<EOB
269
- <quote_single>'aa--bb'</>
270
- EOB
271
- ).chomp,
272
- format(@tok.tokenize((<<EOB
273
- 'aa--bb'
274
- EOB
275
- ).chomp))
276
- )
335
+ assert_equals(
336
+ msg + "comment_single in quote_single",
337
+ strip_indent(
338
+ <<-EOB
339
+ quote_single ('aa--bb')
340
+ EOB
341
+ ),
342
+ _format(@tok.tokenize(strip_indent(
343
+ <<-EOB
344
+ 'aa--bb'
345
+ EOB
346
+ )))
347
+ )
277
348
 
278
349
  ########
279
- assert_equals( msg + "comment_single in quote_double", (<<EOB
280
- <quote_double>"aa--bb"</>
281
- EOB
282
- ).chomp,
283
- format(@tok.tokenize((<<EOB
284
- "aa--bb"
285
- EOB
286
- ).chomp))
287
- )
350
+ assert_equals(
351
+ msg + "comment_single in quote_double",
352
+ strip_indent(
353
+ <<-EOB
354
+ quote_double ("aa--bb")
355
+ EOB
356
+ ),
357
+ _format(@tok.tokenize(strip_indent(
358
+ <<-EOB
359
+ "aa--bb"
360
+ EOB
361
+ )))
362
+ )
288
363
 
289
364
  ########
290
- assert_equals( msg + "comment_multi in quote_double", (<<EOB
291
- <quote_double>"aa /* bb */ cc"</>
292
- EOB
293
- ).chomp,
294
- format(@tok.tokenize((<<EOB
295
- "aa /* bb */ cc"
296
- EOB
297
- ).chomp))
298
- )
365
+ assert_equals(
366
+ msg + "comment_multi in quote_double",
367
+ strip_indent(
368
+ <<-EOB
369
+ quote_double ("aa /* bb */ cc")
370
+ EOB
371
+ ),
372
+ _format(@tok.tokenize(strip_indent(
373
+ <<-EOB
374
+ "aa /* bb */ cc"
375
+ EOB
376
+ )))
377
+ )
299
378
 
300
379
  ########
301
- assert_equals( msg + "comment_multi in quote_double", (<<EOB
302
- <quote_single>'aa /* bb */ cc'</>
303
- EOB
304
- ).chomp,
305
- format(@tok.tokenize((<<EOB
306
- 'aa /* bb */ cc'
307
- EOB
308
- ).chomp))
309
- )
380
+ assert_equals(
381
+ msg + "comment_multi in quote_double",
382
+ strip_indent(
383
+ <<-EOB
384
+ quote_single ('aa /* bb */ cc')
385
+ EOB
386
+ ),
387
+ _format(@tok.tokenize(strip_indent(
388
+ <<-EOB
389
+ 'aa /* bb */ cc'
390
+ EOB
391
+ )))
392
+ )
310
393
  end
311
394
 
312
395
 
@@ -314,47 +397,63 @@ EOB
314
397
  msg = "string_escape"
315
398
 
316
399
  ########
317
- assert_equals( msg, (<<EOB
318
- <quote_double>"_a_\\\\_b_<br>_c_\\'_d_"</>
319
- EOB
320
- ).chomp,
321
- format(@tok.tokenize((<<EOB
322
- "_a_\\\\_b_\n_c_\\'_d_"
323
- EOB
324
- ).chomp))
325
- )
400
+ assert_equals(
401
+ msg,
402
+ strip_indent(
403
+ <<-EOB
404
+ quote_double ("_a_\\\\_b_\n_c_\\'_d_")
405
+ EOB
406
+ ),
407
+ _format(@tok.tokenize(strip_indent(
408
+ <<-EOB
409
+ "_a_\\\\_b_\n_c_\\'_d_"
410
+ EOB
411
+ )))
412
+ )
326
413
 
327
414
  ########
328
- assert_equals( msg, (<<EOB
329
- <quote_single>'_a_\\\\_b_<br>_c_\\'_d_'</>
330
- EOB
331
- ).chomp,
332
- format(@tok.tokenize((<<EOB
333
- '_a_\\\\_b_\n_c_\\'_d_'
334
- EOB
335
- ).chomp))
336
- )
415
+ assert_equals(
416
+ msg,
417
+ strip_indent(
418
+ <<-EOB
419
+ quote_single ('_a_\\\\_b_\n_c_\\'_d_')
420
+ EOB
421
+ ),
422
+ _format(@tok.tokenize(strip_indent(
423
+ <<-EOB
424
+ '_a_\\\\_b_\n_c_\\'_d_'
425
+ EOB
426
+ )))
427
+ )
337
428
 
338
429
  ########
339
- assert_equals( msg, (<<EOB
340
- <quote_double>"_a_""_b_"</>
341
- EOB
342
- ).chomp,
343
- format(@tok.tokenize((<<EOB
344
- "_a_""_b_"
345
- EOB
346
- ).chomp))
347
- )
430
+ assert_equals(
431
+ msg,
432
+ strip_indent(
433
+ <<-EOB
434
+ quote_double ("_a_""_b_")
435
+ EOB
436
+ ),
437
+ _format(@tok.tokenize(strip_indent(
438
+ <<-EOB
439
+ "_a_""_b_"
440
+ EOB
441
+ )))
442
+ )
348
443
 
349
444
  ########
350
- assert_equals( msg, (<<EOB
351
- <quote_single>'_a_''_b_'</>
352
- EOB
353
- ).chomp,
354
- format(@tok.tokenize((<<EOB
355
- '_a_''_b_'
356
- EOB
357
- ).chomp))
358
- )
445
+ assert_equals(
446
+ msg,
447
+ strip_indent(
448
+ <<-EOB
449
+ quote_single ('_a_''_b_')
450
+ EOB
451
+ ),
452
+ _format(@tok.tokenize(strip_indent(
453
+ <<-EOB
454
+ '_a_''_b_'
455
+ EOB
456
+ )))
457
+ )
359
458
  end
360
459
  end