1
2
3
4
5
6
7
8
9
10
11
12
13
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
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
|
#!/usr/local/bin/ruby
# Parse a Ruby source file, building a set of objects
# representing the modules, classes, methods,
# requires, and includes we find (these classes
# are defined in code_objects.rb).
# This file contains stuff stolen outright from:
#
# rtags.rb -
# ruby-lex.rb - ruby lexcal analizer
# ruby-token.rb - ruby tokens
# by Keiju ISHITSUKA (Nippon Rational Inc.)
#
require "tracer"
require "e2mmap"
require "irb/slex"
require "rdoc/code_objects"
require "rdoc/tokenstream"
require "rdoc/markup/simple_markup/preprocess"
require "rdoc/parsers/parserfactory"
$TOKEN_DEBUG = $DEBUG
# Definitions of all tokens involved in the lexical analysis
module RubyToken
EXPR_BEG = :EXPR_BEG
EXPR_MID = :EXPR_MID
EXPR_END = :EXPR_END
EXPR_ARG = :EXPR_ARG
EXPR_FNAME = :EXPR_FNAME
EXPR_DOT = :EXPR_DOT
EXPR_CLASS = :EXPR_CLASS
class Token
NO_TEXT = "??".freeze
attr :text
def initialize(line_no, char_no)
@line_no = line_no
@char_no = char_no
@text = NO_TEXT
end
# Because we're used in contexts that expect to return a token,
# we set the text string and then return ourselves
def set_text(text)
@text = text
self
end
attr_reader :line_no, :char_no, :text
end
class TkNode < Token
attr :node
end
class TkId < Token
def initialize(line_no, char_no, name)
super(line_no, char_no)
@name = name
end
attr :name
end
class TkKW < TkId
end
class TkVal < Token
def initialize(line_no, char_no, value = nil)
super(line_no, char_no)
set_text(value)
end
end
class TkOp < Token
def name
self.class.op_name
end
end
class TkOPASGN < TkOp
def initialize(line_no, char_no, op)
super(line_no, char_no)
op = TkReading2Token[op] unless op.kind_of?(Symbol)
@op = op
end
attr :op
end
class TkUnknownChar < Token
def initialize(line_no, char_no, id)
super(line_no, char_no)
@name = char_no.chr
end
attr :name
end
class TkError < Token
end
def set_token_position(line, char)
@prev_line_no = line
@prev_char_no = char
end
def Token(token, value = nil)
tk = nil
case token
when String, Symbol
source = token.kind_of?(String) ? TkReading2Token : TkSymbol2Token
if (tk = source[token]).nil?
IRB.fail TkReading2TokenNoKey, token
end
tk = Token(tk[0], value)
else
tk = if (token.ancestors & [TkId, TkVal, TkOPASGN, TkUnknownChar]).empty?
token.new(@prev_line_no, @prev_char_no)
else
token.new(@prev_line_no, @prev_char_no, value)
end
end
tk
end
TokenDefinitions = [
[:TkCLASS, TkKW, "class", EXPR_CLASS],
[:TkMODULE, TkKW, "module", EXPR_BEG],
[:TkDEF, TkKW, "def", EXPR_FNAME],
[:TkUNDEF, TkKW, "undef", EXPR_FNAME],
[:TkBEGIN, TkKW, "begin", EXPR_BEG],
[:TkRESCUE, TkKW, "rescue", EXPR_MID],
[:TkENSURE, TkKW, "ensure", EXPR_BEG],
[:TkEND, TkKW, "end", EXPR_END],
[:TkIF, TkKW, "if", EXPR_BEG, :TkIF_MOD],
[:TkUNLESS, TkKW, "unless", EXPR_BEG, :TkUNLESS_MOD],
[:TkTHEN, TkKW, "then", EXPR_BEG],
[:TkELSIF, TkKW, "elsif", EXPR_BEG],
[:TkELSE, TkKW, "else", EXPR_BEG],
[:TkCASE, TkKW, "case", EXPR_BEG],
[:TkWHEN, TkKW, "when", EXPR_BEG],
[:TkWHILE, TkKW, "while", EXPR_BEG, :TkWHILE_MOD],
[:TkUNTIL, TkKW, "until", EXPR_BEG, :TkUNTIL_MOD],
[:TkFOR, TkKW, "for", EXPR_BEG],
[:TkBREAK, TkKW, "break", EXPR_END],
[:TkNEXT, TkKW, "next", EXPR_END],
[:TkREDO, TkKW, "redo", EXPR_END],
[:TkRETRY, TkKW, "retry", EXPR_END],
[:TkIN, TkKW, "in", EXPR_BEG],
[:TkDO, TkKW, "do", EXPR_BEG],
[:TkRETURN, TkKW, "return", EXPR_MID],
[:TkYIELD, TkKW, "yield", EXPR_END],
[:TkSUPER, TkKW, "super", EXPR_END],
[:TkSELF, TkKW, "self", EXPR_END],
[:TkNIL, TkKW, "nil", EXPR_END],
[:TkTRUE, TkKW, "true", EXPR_END],
[:TkFALSE, TkKW, "false", EXPR_END],
[:TkAND, TkKW, "and", EXPR_BEG],
[:TkOR, TkKW, "or", EXPR_BEG],
[:TkNOT, TkKW, "not", EXPR_BEG],
[:TkIF_MOD, TkKW],
[:TkUNLESS_MOD, TkKW],
[:TkWHILE_MOD, TkKW],
[:TkUNTIL_MOD, TkKW],
[:TkALIAS, TkKW, "alias", EXPR_FNAME],
[:TkDEFINED, TkKW, "defined?", EXPR_END],
[:TklBEGIN, TkKW, "BEGIN", EXPR_END],
[:TklEND, TkKW, "END", EXPR_END],
[:Tk__LINE__, TkKW, "__LINE__", EXPR_END],
[:Tk__FILE__, TkKW, "__FILE__", EXPR_END],
[:TkIDENTIFIER, TkId],
[:TkFID, TkId],
[:TkGVAR, TkId],
[:TkIVAR, TkId],
[:TkCONSTANT, TkId],
[:TkINTEGER, TkVal],
[:TkFLOAT, TkVal],
[:TkSTRING, TkVal],
[:TkXSTRING, TkVal],
[:TkREGEXP, TkVal],
[:TkCOMMENT, TkVal],
[:TkDSTRING, TkNode],
[:TkDXSTRING, TkNode],
[:TkDREGEXP, TkNode],
[:TkNTH_REF, TkId],
[:TkBACK_REF, TkId],
[:TkUPLUS, TkOp, "+@"],
[:TkUMINUS, TkOp, "-@"],
[:TkPOW, TkOp, "**"],
[:TkCMP, TkOp, "<=>"],
[:TkEQ, TkOp, "=="],
[:TkEQQ, TkOp, "==="],
[:TkNEQ, TkOp, "!="],
[:TkGEQ, TkOp, ">="],
[:TkLEQ, TkOp, "<="],
[:TkANDOP, TkOp, "&&"],
[:TkOROP, TkOp, "||"],
[:TkMATCH, TkOp, "=~"],
[:TkNMATCH, TkOp, "!~"],
[:TkDOT2, TkOp, ".."],
[:TkDOT3, TkOp, "..."],
[:TkAREF, TkOp, "[]"],
[:TkASET, TkOp, "[]="],
[:TkLSHFT, TkOp, "<<"],
[:TkRSHFT, TkOp, ">>"],
[:TkCOLON2, TkOp],
[:TkCOLON3, TkOp],
# [:OPASGN, TkOp], # +=, -= etc. #
[:TkASSOC, TkOp, "=>"],
[:TkQUESTION, TkOp, "?"], #?
[:TkCOLON, TkOp, ":"], #:
[:TkfLPAREN], # func( #
[:TkfLBRACK], # func[ #
[:TkfLBRACE], # func{ #
[:TkSTAR], # *arg
[:TkAMPER], # &arg #
[:TkSYMBOL, TkId], # :SYMBOL
[:TkSYMBEG, TkId],
[:TkGT, TkOp, ">"],
[:TkLT, TkOp, "<"],
[:TkPLUS, TkOp, "+"],
[:TkMINUS, TkOp, "-"],
[:TkMULT, TkOp, "*"],
[:TkDIV, TkOp, "/"],
[:TkMOD, TkOp, "%"],
[:TkBITOR, TkOp, "|"],
[:TkBITXOR, TkOp, "^"],
[:TkBITAND, TkOp, "&"],
[:TkBITNOT, TkOp, "~"],
[:TkNOTOP, TkOp, "!"],
[:TkBACKQUOTE, TkOp, "`"],
[:TkASSIGN, Token, "="],
[:TkDOT, Token, "."],
[:TkLPAREN, Token, "("], #(exp)
[:TkLBRACK, Token, "["], #[arry]
[:TkLBRACE, Token, "{"], #{hash}
[:TkRPAREN, Token, ")"],
[:TkRBRACK, Token, "]"],
[:TkRBRACE, Token, "}"],
[:TkCOMMA, Token, ","],
[:TkSEMICOLON, Token, ";"],
[:TkRD_COMMENT],
[:TkSPACE],
[:TkNL],
[:TkEND_OF_SCRIPT],
[:TkBACKSLASH, TkUnknownChar, "\\"],
[:TkAT, TkUnknownChar, "@"],
[:TkDOLLAR, TkUnknownChar, "\$"], #"
]
# {reading => token_class}
# {reading => [token_class, *opt]}
TkReading2Token = {}
TkSymbol2Token = {}
def RubyToken.def_token(token_n, super_token = Token, reading = nil, *opts)
token_n = token_n.id2name unless token_n.kind_of?(String)
if RubyToken.const_defined?(token_n)
IRB.fail AlreadyDefinedToken, token_n
end
token_c = Class.new super_token
RubyToken.const_set token_n, token_c
# token_c.inspect
if reading
if TkReading2Token[reading]
IRB.fail TkReading2TokenDuplicateError, token_n, reading
end
if opts.empty?
TkReading2Token[reading] = [token_c]
else
TkReading2Token[reading] = [token_c].concat(opts)
end
end
TkSymbol2Token[token_n.intern] = token_c
if token_c <= TkOp
token_c.class_eval %{
def self.op_name; "#{reading}"; end
}
end
end
for defs in TokenDefinitions
def_token(*defs)
end
NEWLINE_TOKEN = TkNL.new(0,0)
NEWLINE_TOKEN.set_text("\n")
end
# Lexical analyzer for Ruby source
class RubyLex
######################################################################
#
# Read an input stream character by character. We allow for unlimited
# ungetting of characters just read.
#
# We simplify the implementation greatly by reading the entire input
# into a buffer initially, and then simply traversing it using
# pointers.
#
# We also have to allow for the <i>here document diversion</i>. This
# little gem comes about when the lexer encounters a here
# document. At this point we effectively need to split the input
# stream into two parts: one to read the body of the here document,
# the other to read the rest of the input line where the here
# document was initially encountered. For example, we might have
#
# do_something(<<-A, <<-B)
# stuff
# for
# A
# stuff
# for
# B
#
# When the lexer encounters the <<A, it reads until the end of the
# line, and keeps it around for later. It then reads the body of the
# here document. Once complete, it needs to read the rest of the
# original line, but then skip the here document body.
#
class BufferedReader
attr_reader :line_num
def initialize(content)
if /\t/ =~ content
tab_width = Options.instance.tab_width
content = content.split(/\n/).map do |line|
1 while line.gsub!(/\t+/) { ' ' * (tab_width*$&.length - $`.length % tab_width)} && $~ #`
line
end .join("\n")
end
@content = content
@content << "\n" unless @content[-1,1] == "\n"
@size = @content.size
@offset = 0
@hwm = 0
@line_num = 1
@read_back_offset = 0
@last_newline = 0
@newline_pending = false
end
def column
@offset - @last_newline
end
def getc
return nil if @offset >= @size
ch = @content[@offset, 1]
@offset += 1
@hwm = @offset if @hwm < @offset
if @newline_pending
@line_num += 1
@last_newline = @offset - 1
@newline_pending = false
end
if ch == "\n"
@newline_pending = true
end
ch
end
def getc_already_read
getc
end
def ungetc(ch)
raise "unget past beginning of file" if @offset <= 0
@offset -= 1
if @content[@offset] == ?\n
@newline_pending = false
end
end
def get_read
res = @content[@read_back_offset...@offset]
@read_back_offset = @offset
res
end
def peek(at)
pos = @offset + at
if pos >= @size
nil
else
@content[pos, 1]
end
end
def peek_equal(str)
@content[@offset, str.length] == str
end
def divert_read_from(reserve)
@content[@offset, 0] = reserve
@size = @content.size
end
end
# end of nested class BufferedReader
extend Exception2MessageMapper
def_exception(:AlreadyDefinedToken, "Already defined token(%s)")
def_exception(:TkReading2TokenNoKey, "key nothing(key='%s')")
def_exception(:TkSymbol2TokenNoKey, "key nothing(key='%s')")
def_exception(:TkReading2TokenDuplicateError,
"key duplicate(token_n='%s', key='%s')")
def_exception(:SyntaxError, "%s")
include RubyToken
attr_reader :continue
attr_reader :lex_state
def RubyLex.debug?
false
end
def initialize(content)
lex_init
@reader = BufferedReader.new(content)
@exp_line_no = @line_no = 1
@base_char_no = 0
@indent = 0
@ltype = nil
@quoted = nil
@lex_state = EXPR_BEG
@space_seen = false
@continue = false
@line = ""
@skip_space = false
@read_auto_clean_up = false
@exception_on_syntax_error = true
end
attr :skip_space, true
attr :read_auto_clean_up, true
attr :exception_on_syntax_error, true
attr :indent
# io functions
def line_no
@reader.line_num
end
def char_no
@reader.column
end
def get_read
@reader.get_read
end
def getc
@reader.getc
end
def getc_of_rests
@reader.getc_already_read
end
def gets
c = getc or return
l = ""
begin
l.concat c unless c == "\r"
break if c == "\n"
end while c = getc
l
end
def ungetc(c = nil)
@reader.ungetc(c)
end
def peek_equal?(str)
@reader.peek_equal(str)
end
def peek(i = 0)
@reader.peek(i)
end
def lex
until (((tk = token).kind_of?(TkNL) || tk.kind_of?(TkEND_OF_SCRIPT)) &&
!@continue or
tk.nil?)
end
line = get_read
if line == "" and tk.kind_of?(TkEND_OF_SCRIPT) || tk.nil?
nil
else
line
end
end
def token
set_token_position(line_no, char_no)
begin
begin
tk = @OP.match(self)
@space_seen = tk.kind_of?(TkSPACE)
rescue SyntaxError
abort if @exception_on_syntax_error
tk = TkError.new(line_no, char_no)
end
end while @skip_space and tk.kind_of?(TkSPACE)
if @read_auto_clean_up
get_read
end
# throw :eof unless tk
p tk if $DEBUG
tk
end
ENINDENT_CLAUSE = [
"case", "class", "def", "do", "for", "if",
"module", "unless", "until", "while", "begin" #, "when"
]
DEINDENT_CLAUSE = ["end" #, "when"
]
PERCENT_LTYPE = {
"q" => "\'",
"Q" => "\"",
"x" => "\`",
"r" => "\/",
"w" => "]"
}
PERCENT_PAREN = {
"{" => "}",
"[" => "]",
"<" => ">",
"(" => ")"
}
Ltype2Token = {
"\'" => TkSTRING,
"\"" => TkSTRING,
"\`" => TkXSTRING,
"\/" => TkREGEXP,
"]" => TkDSTRING
}
Ltype2Token.default = TkSTRING
DLtype2Token = {
"\"" => TkDSTRING,
"\`" => TkDXSTRING,
"\/" => TkDREGEXP,
}
def lex_init()
@OP = SLex.new
@OP.def_rules("\0", "\004", "\032") do |chars, io|
Token(TkEND_OF_SCRIPT).set_text(chars)
end
@OP.def_rules(" ", "\t", "\f", "\r", "\13") do |chars, io|
@space_seen = TRUE
while (ch = getc) =~ /[ \t\f\r\13]/
chars << ch
end
ungetc
Token(TkSPACE).set_text(chars)
end
@OP.def_rule("#") do
|op, io|
identify_comment
end
@OP.def_rule("=begin", proc{@prev_char_no == 0 && peek(0) =~ /\s/}) do
|op, io|
str = op
@ltype = "="
begin
line = ""
begin
ch = getc
line << ch
end until ch == "\n"
str << line
end until line =~ /^=end/
ungetc
@ltype = nil
if str =~ /\A=begin\s+rdoc/i
str.sub!(/\A=begin.*\n/, '')
str.sub!(/^=end.*/m, '')
Token(TkCOMMENT).set_text(str)
else
Token(TkRD_COMMENT)#.set_text(str)
end
end
@OP.def_rule("\n") do
print "\\n\n" if RubyLex.debug?
case @lex_state
when EXPR_BEG, EXPR_FNAME, EXPR_DOT
@continue = TRUE
else
@continue = FALSE
@lex_state = EXPR_BEG
end
Token(TkNL).set_text("\n")
end
@OP.def_rules("*", "**",
"!", "!=", "!~",
"=", "==", "===",
"=~", "<=>",
"<", "<=",
">", ">=", ">>") do
|op, io|
@lex_state = EXPR_BEG
Token(op).set_text(op)
end
@OP.def_rules("<<") do
|op, io|
tk = nil
if @lex_state != EXPR_END && @lex_state != EXPR_CLASS &&
(@lex_state != EXPR_ARG || @space_seen)
c = peek(0)
if /[-\w_\"\'\`]/ =~ c
tk = identify_here_document
end
end
if !tk
@lex_state = EXPR_BEG
tk = Token(op).set_text(op)
end
tk
end
@OP.def_rules("'", '"') do
|op, io|
identify_string(op)
end
@OP.def_rules("`") do
|op, io|
if @lex_state == EXPR_FNAME
Token(op).set_text(op)
else
identify_string(op)
end
end
@OP.def_rules('?') do
|op, io|
if @lex_state == EXPR_END
@lex_state = EXPR_BEG
Token(TkQUESTION).set_text(op)
else
ch = getc
if @lex_state == EXPR_ARG && ch !~ /\s/
ungetc
@lex_state = EXPR_BEG;
Token(TkQUESTION).set_text(op)
else
str = op
str << ch
if (ch == '\\') #'
str << read_escape
end
@lex_state = EXPR_END
Token(TkINTEGER).set_text(str)
end
end
end
@OP.def_rules("&", "&&", "|", "||") do
|op, io|
@lex_state = EXPR_BEG
Token(op).set_text(op)
end
@OP.def_rules("+=", "-=", "*=", "**=",
"&=", "|=", "^=", "<<=", ">>=", "||=", "&&=") do
|op, io|
@lex_state = EXPR_BEG
op =~ /^(.*)=$/
Token(TkOPASGN, $1).set_text(op)
end
@OP.def_rule("+@", proc{@lex_state == EXPR_FNAME}) do |op, io|
Token(TkUPLUS).set_text(op)
end
@OP.def_rule("-@", proc{@lex_state == EXPR_FNAME}) do |op, io|
Token(TkUMINUS).set_text(op)
end
@OP.def_rules("+", "-") do
|op, io|
catch(:RET) do
if @lex_state == EXPR_ARG
if @space_seen and peek(0) =~ /[0-9]/
throw :RET, identify_number(op)
else
@lex_state = EXPR_BEG
end
elsif @lex_state != EXPR_END and peek(0) =~ /[0-9]/
throw :RET, identify_number(op)
else
@lex_state = EXPR_BEG
end
Token(op).set_text(op)
end
end
@OP.def_rule(".") do
@lex_state = EXPR_BEG
if peek(0) =~ /[0-9]/
ungetc
identify_number("")
else
# for obj.if
@lex_state = EXPR_DOT
Token(TkDOT).set_text(".")
end
end
@OP.def_rules("..", "...") do
|op, io|
@lex_state = EXPR_BEG
Token(op).set_text(op)
end
lex_int2
end
def lex_int2
@OP.def_rules("]", "}", ")") do
|op, io|
@lex_state = EXPR_END
@indent -= 1
Token(op).set_text(op)
end
@OP.def_rule(":") do
if @lex_state == EXPR_END || peek(0) =~ /\s/
@lex_state = EXPR_BEG
tk = Token(TkCOLON)
else
@lex_state = EXPR_FNAME;
tk = Token(TkSYMBEG)
end
tk.set_text(":")
end
@OP.def_rule("::") do
# p @lex_state.id2name, @space_seen
if @lex_state == EXPR_BEG or @lex_state == EXPR_ARG && @space_seen
@lex_state = EXPR_BEG
tk = Token(TkCOLON3)
else
@lex_state = EXPR_DOT
tk = Token(TkCOLON2)
end
tk.set_text("::")
end
@OP.def_rule("/") do
|op, io|
if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
identify_string(op)
elsif peek(0) == '='
getc
@lex_state = EXPR_BEG
Token(TkOPASGN, :/).set_text("/=") #")
elsif @lex_state == EXPR_ARG and @space_seen and peek(0) !~ /\s/
identify_string(op)
else
@lex_state = EXPR_BEG
Token("/").set_text(op)
end
end
@OP.def_rules("^") do
@lex_state = EXPR_BEG
Token("^").set_text("^")
end
# @OP.def_rules("^=") do
# @lex_state = EXPR_BEG
# Token(TkOPASGN, :^)
# end
@OP.def_rules(",", ";") do
|op, io|
@lex_state = EXPR_BEG
Token(op).set_text(op)
end
@OP.def_rule("~") do
@lex_state = EXPR_BEG
Token("~").set_text("~")
end
@OP.def_rule("~@", proc{@lex_state = EXPR_FNAME}) do
@lex_state = EXPR_BEG
Token("~").set_text("~@")
end
@OP.def_rule("(") do
@indent += 1
if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
@lex_state = EXPR_BEG
tk = Token(TkfLPAREN)
else
@lex_state = EXPR_BEG
tk = Token(TkLPAREN)
end
tk.set_text("(")
end
@OP.def_rule("[]", proc{@lex_state == EXPR_FNAME}) do
Token("[]").set_text("[]")
end
@OP.def_rule("[]=", proc{@lex_state == EXPR_FNAME}) do
Token("[]=").set_text("[]=")
end
@OP.def_rule("[") do
@indent += 1
if @lex_state == EXPR_FNAME
t = Token(TkfLBRACK)
else
if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
t = Token(TkLBRACK)
elsif @lex_state == EXPR_ARG && @space_seen
t = Token(TkLBRACK)
else
t = Token(TkfLBRACK)
end
@lex_state = EXPR_BEG
end
t.set_text("[")
end
@OP.def_rule("{") do
@indent += 1
if @lex_state != EXPR_END && @lex_state != EXPR_ARG
t = Token(TkLBRACE)
else
t = Token(TkfLBRACE)
end
@lex_state = EXPR_BEG
t.set_text("{")
end
@OP.def_rule('\\') do #'
if getc == "\n"
@space_seen = true
@continue = true
Token(TkSPACE).set_text("\\\n")
else
ungetc
Token("\\").set_text("\\") #"
end
end
@OP.def_rule('%') do
|op, io|
if @lex_state == EXPR_BEG || @lex_state == EXPR_MID
identify_quotation('%')
elsif peek(0) == '='
getc
Token(TkOPASGN, "%").set_text("%=")
elsif @lex_state == EXPR_ARG and @space_seen and peek(0) !~ /\s/
identify_quotation('%')
else
@lex_state = EXPR_BEG
Token("%").set_text("%")
end
end
@OP.def_rule('$') do #'
identify_gvar
end
@OP.def_rule('@') do
if peek(0) =~ /[@\w_]/
ungetc
identify_identifier
else
Token("@").set_text("@")
end
end
# @OP.def_rule("def", proc{|op, io| /\s/ =~ io.peek(0)}) do
# |op, io|
# @indent += 1
# @lex_state = EXPR_FNAME
# # @lex_state = EXPR_END
# # until @rests[0] == "\n" or @rests[0] == ";"
# # rests.shift
# # end
# end
@OP.def_rule("__END__", proc{@prev_char_no == 0 && peek(0) =~ /[\r\n]/}) do
throw :eof
end
@OP.def_rule("") do
|op, io|
printf "MATCH: start %s: %s\n", op, io.inspect if RubyLex.debug?
if peek(0) =~ /[0-9]/
t = identify_number("")
elsif peek(0) =~ /[\w_]/
t = identify_identifier
end
printf "MATCH: end %s: %s\n", op, io.inspect if RubyLex.debug?
t
end
p @OP if RubyLex.debug?
end
def identify_gvar
@lex_state = EXPR_END
str = "$"
tk = case ch = getc
when /[~_*$?!@\/\\;,=:<>".]/ #"
str << ch
Token(TkGVAR, str)
when "-"
str << "-" << getc
Token(TkGVAR, str)
when "&", "`", "'", "+"
str << ch
Token(TkBACK_REF, str)
when /[1-9]/
str << ch
while (ch = getc) =~ /[0-9]/
str << ch
end
ungetc
Token(TkNTH_REF)
when /\w/
ungetc
ungetc
return identify_identifier
else
ungetc
Token("$")
end
tk.set_text(str)
end
def identify_identifier
token = ""
token.concat getc if peek(0) =~ /[$@]/
token.concat getc if peek(0) == "@"
while (ch = getc) =~ /\w|_/
print ":", ch, ":" if RubyLex.debug?
token.concat ch
end
ungetc
if ch == "!" or ch == "?"
token.concat getc
end
# fix token
# $stderr.puts "identifier - #{token}, state = #@lex_state"
case token
when /^\$/
return Token(TkGVAR, token).set_text(token)
when /^\@/
@lex_state = EXPR_END
return Token(TkIVAR, token).set_text(token)
end
if @lex_state != EXPR_DOT
print token, "\n" if RubyLex.debug?
token_c, *trans = TkReading2Token[token]
if token_c
# reserved word?
if (@lex_state != EXPR_BEG &&
@lex_state != EXPR_FNAME &&
trans[1])
# modifiers
token_c = TkSymbol2Token[trans[1]]
@lex_state = trans[0]
else
if @lex_state != EXPR_FNAME
if ENINDENT_CLAUSE.include?(token)
@indent += 1
elsif DEINDENT_CLAUSE.include?(token)
@indent -= 1
end
@lex_state = trans[0]
else
@lex_state = EXPR_END
end
end
return Token(token_c, token).set_text(token)
end
end
if @lex_state == EXPR_FNAME
@lex_state = EXPR_END
if peek(0) == '='
token.concat getc
end
elsif @lex_state == EXPR_BEG || @lex_state == EXPR_DOT
@lex_state = EXPR_ARG
else
@lex_state = EXPR_END
end
if token[0, 1] =~ /[A-Z]/
return Token(TkCONSTANT, token).set_text(token)
elsif token[token.size - 1, 1] =~ /[!?]/
return Token(TkFID, token).set_text(token)
else
return Token(TkIDENTIFIER, token).set_text(token)
end
end
def identify_here_document
ch = getc
if ch == "-"
ch = getc
indent = true
end
if /['"`]/ =~ ch # '
lt = ch
quoted = ""
while (c = getc) && c != lt
quoted.concat c
end
else
lt = '"'
quoted = ch.dup
while (c = getc) && c =~ /\w/
quoted.concat c
end
ungetc
end
ltback, @ltype = @ltype, lt
reserve = ""
while ch = getc
reserve << ch
if ch == "\\" #"
ch = getc
reserve << ch
elsif ch == "\n"
break
end
end
str = ""
while (l = gets)
l.chomp!
l.strip! if indent
break if l == quoted
str << l.chomp << "\n"
end
@reader.divert_read_from(reserve)
@ltype = ltback
@lex_state = EXPR_END
Token(Ltype2Token[lt], str).set_text(str.dump)
end
def identify_quotation(initial_char)
ch = getc
if lt = PERCENT_LTYPE[ch]
ch = getc
elsif ch =~ /\W/
lt = "\""
else
RubyLex.fail SyntaxError, "unknown type of %string ('#{ch}')"
end
# if ch !~ /\W/
# ungetc
# next
# end
#@ltype = lt
@quoted = ch unless @quoted = PERCENT_PAREN[ch]
identify_string(lt, @quoted, ch, initial_char)
end
def identify_number(start)
str = start.dup
if start == "+" or start == "-" or start == ""
start = getc
str << start
end
@lex_state = EXPR_END
if start == "0"
if peek(0) == "x"
ch = getc
str << ch
match = /[0-9a-f_]/
else
match = /[0-7_]/
end
while ch = getc
if ch !~ match
ungetc
break
else
str << ch
end
end
return Token(TkINTEGER).set_text(str)
end
type = TkINTEGER
allow_point = TRUE
allow_e = TRUE
while ch = getc
case ch
when /[0-9_]/
str << ch
when allow_point && "."
type = TkFLOAT
if peek(0) !~ /[0-9]/
ungetc
break
end
str << ch
allow_point = false
when allow_e && "e", allow_e && "E"
str << ch
type = TkFLOAT
if peek(0) =~ /[+-]/
str << getc
end
allow_e = false
allow_point = false
else
ungetc
break
end
end
Token(type).set_text(str)
end
def identify_string(ltype, quoted = ltype, opener=nil, initial_char = nil)
@ltype = ltype
@quoted = quoted
subtype = nil
str = ""
str << initial_char if initial_char
str << (opener||quoted)
nest = 0
begin
while ch = getc
str << ch
if @quoted == ch
if nest == 0
break
else
nest -= 1
end
elsif opener == ch
nest += 1
elsif @ltype != "'" && @ltype != "]" and ch == "#"
ch = getc
if ch == "{"
subtype = true
str << ch << skip_inner_expression
else
ungetc(ch)
end
elsif ch == '\\' #'
str << read_escape
end
end
if @ltype == "/"
if peek(0) =~ /i|o|n|e|s/
str << getc
end
end
if subtype
Token(DLtype2Token[ltype], str)
else
Token(Ltype2Token[ltype], str)
end.set_text(str)
ensure
@ltype = nil
@quoted = nil
@lex_state = EXPR_END
end
end
def skip_inner_expression
res = ""
nest = 0
while (ch = getc)
res << ch
if ch == '}'
break if nest.zero?
nest -= 1
elsif ch == '{'
nest += 1
end
end
res
end
def identify_comment
@ltype = "#"
comment = "#"
while ch = getc
if ch == "\\"
ch = getc
if ch == "\n"
ch = " "
else
comment << "\\"
end
else
if ch == "\n"
@ltype = nil
ungetc
break
end
end
comment << ch
end
return Token(TkCOMMENT).set_text(comment)
end
def read_escape
res = ""
case ch = getc
when /[0-7]/
ungetc ch
3.times do
case ch = getc
when /[0-7]/
when nil
break
else
ungetc
break
end
res << ch
end
when "x"
res << ch
2.times do
case ch = getc
when /[0-9a-fA-F]/
when nil
break
else
ungetc
break
end
res << ch
end
when "M"
res << ch
if (ch = getc) != '-'
ungetc
else
res << ch
if (ch = getc) == "\\" #"
res << ch
res << read_escape
else
res << ch
end
end
when "C", "c", "^"
res << ch
if ch == "C" and (ch = getc) != "-"
ungetc
else
res << ch
if (ch = getc) == "\\" #"
res << ch
res << read_escape
else
res << ch
end
end
else
res << ch
end
res
end
end
# Extract code elements from a source file, returning a TopLevel
# object containing the constituent file elements.
#
# This file is based on rtags
module RDoc
GENERAL_MODIFIERS = [ 'nodoc' ].freeze
CLASS_MODIFIERS = GENERAL_MODIFIERS
ATTR_MODIFIERS = GENERAL_MODIFIERS
CONSTANT_MODIFIERS = GENERAL_MODIFIERS
METHOD_MODIFIERS = GENERAL_MODIFIERS +
[ 'arg', 'args', 'yield', 'yields', 'notnew', 'not-new', 'not_new', 'doc' ]
class RubyParser
include RubyToken
include TokenStream
extend ParserFactory
parse_files_matching(/\.rbw?$/)
def initialize(top_level, file_name, content, options, stats)
@options = options
@stats = stats
@size = 0
@token_listeners = nil
@input_file_name = file_name
@scanner = RubyLex.new(content)
@scanner.exception_on_syntax_error = false
@top_level = top_level
@progress = $stderr unless options.quiet
end
def scan
@tokens = []
@unget_read = []
@read = []
catch(:eof) do
begin
parse_toplevel_statements(@top_level)
rescue Exception => e
$stderr.puts "\n\n"
$stderr.puts "RDoc failure in #@input_file_name at or around " +
"line #{@scanner.line_no} column #{@scanner.char_no}"
$stderr.puts
$stderr.puts "Before reporting this, could you check that the file"
$stderr.puts "you're documenting compiles cleanly--RDoc is not a"
$stderr.puts "full Ruby parser, and gets confused easily if fed"
$stderr.puts "invalid programs."
$stderr.puts
$stderr.puts "The internal error was:\n\n"
e.set_backtrace(e.backtrace[0,4])
raise
end
end
@top_level
end
private
def warn(msg)
prefix = "\n" + @input_file_name + ":"
if @scanner
prefix << "#{@scanner.line_no}:#{@scanner.char_no}: "
end
$stderr.puts prefix + msg
end
def error(msg)
warn msg
exit(1)
end
def progress(char)
unless @options.quiet
@progress.print(char)
@progress.flush
end
end
def add_token_listener(obj)
@token_listeners ||= []
@token_listeners << obj
end
def remove_token_listener(obj)
@token_listeners.delete(obj)
end
def get_tk
tk = nil
if @tokens.empty?
tk = @scanner.token
@read.push @scanner.get_read
puts "get_tk1 => #{tk.inspect}" if $TOKEN_DEBUG
else
@read.push @unget_read.shift
tk = @tokens.shift
puts "get_tk2 => #{tk.inspect}" if $TOKEN_DEBUG
end
if tk.kind_of?(TkSYMBEG)
set_token_position(tk.line_no, tk.char_no)
tk1 = get_tk
if tk1.kind_of?(TkId) || tk1.kind_of?(TkOp)
tk = Token(TkSYMBOL).set_text(":" + tk1.name)
# remove the identifier we just read (we're about to
# replace it with a symbol)
@token_listeners.each do |obj|
obj.pop_token
end if @token_listeners
else
warn("':' not followed by identified or operator")
tk = tk1
end
end
# inform any listeners of our shiny new token
@token_listeners.each do |obj|
obj.add_token(tk)
end if @token_listeners
tk
end
def peek_tk
unget_tk(tk = get_tk)
tk
end
def unget_tk(tk)
@tokens.unshift tk
@unget_read.unshift @read.pop
# Remove this token from any listeners
@token_listeners.each do |obj|
obj.pop_token
end if @token_listeners
end
def skip_tkspace(skip_nl = true)
tokens = []
while ((tk = get_tk).kind_of?(TkSPACE) ||
(skip_nl && tk.kind_of?(TkNL)))
tokens.push tk
end
unget_tk(tk)
tokens
end
def get_tkread
read = @read.join("")
@read = []
read
end
def peek_read
@read.join('')
end
NORMAL = "::"
SINGLE = "<<"
# Look for the first comment in a file that isn't
# a shebang line.
def collect_first_comment
skip_tkspace
res = ''
first_line = true
tk = get_tk
while tk.kind_of?(TkCOMMENT)
if first_line && tk.text[0,2] == "#!"
skip_tkspace
tk = get_tk
else
res << tk.text << "\n"
tk = get_tk
if tk.kind_of? TkNL
skip_tkspace(false)
tk = get_tk
end
end
first_line = false
end
unget_tk(tk)
res
end
def parse_toplevel_statements(container)
comment = collect_first_comment
look_for_directives_in(container, comment)
container.comment = comment unless comment.empty?
parse_statements(container, NORMAL, nil, comment)
end
def parse_statements(container, single=NORMAL, current_method=nil, comment='')
nest = 1
save_visibility = container.visibility
# if container.kind_of?(TopLevel)
# else
# comment = ''
# end
non_comment_seen = true
while tk = get_tk
keep_comment = false
non_comment_seen = true unless tk.kind_of?(TkCOMMENT)
# $stderr.puts "===== #{tk.inspect}"
# blank_line_seen = true
# while tk.kind_of?(TkNL)
# skip_tkspace(false)
# if peek_tk.kind_of?(TkCOMMENT)
# if blank_line_seen
# comment = ''
# blank_line_seen = false
# end
# tk = get_tk
# comment << tk.text << "\n"
# else
# blank_line_seen = true
# end
# tk = get_tk
# end
case tk
when TkNL
skip_tkspace(true) # Skip blanks and newlines
tk = get_tk
if tk.kind_of?(TkCOMMENT)
if non_comment_seen
comment = ''
non_comment_seen = false
end
while tk.kind_of?(TkCOMMENT)
comment << tk.text << "\n"
tk = get_tk # this is the newline
skip_tkspace(false) # leading spaces
tk = get_tk
end
unless comment.empty?
look_for_directives_in(container, comment)
if container.done_documenting
container.ongoing_visibility = save_visibility
return
end
end
keep_comment = true
else
non_comment_seen = true
end
unget_tk(tk)
keep_comment = true
when TkCLASS
if container.document_children
parse_class(container, single, tk, comment)
else
nest += 1
end
when TkMODULE
if container.document_children
parse_module(container, single, tk, comment)
else
nest += 1
end
when TkDEF
if container.document_self
parse_method(container, single, tk, comment)
else
nest += 1
end
when TkCONSTANT
if container.document_self
parse_constant(container, single, tk, comment)
end
when TkALIAS
if container.document_self
parse_alias(container, single, tk, comment)
end
when TkYIELD
if current_method.nil?
warn("Warning: yield outside of method") if container.document_self
else
parse_yield(container, single, tk, current_method)
end
# Until and While can have a 'do', which shouldn't increas
# the nesting. We can't solve the general case, but we can
# handle most occurrences by ignoring a do at the end of a line
when TkUNTIL, TkWHILE
nest += 1
puts "FOUND #{tk.class} in #{container.name}, nest = #{nest}, " +
"line #{tk.line_no}" if $DEBUG
skip_optional_do_after_expression
when TkCASE, TkDO, TkIF, TkUNLESS, TkBEGIN, TkFOR
nest += 1
puts "Found #{tk.class} in #{container.name}, nest = #{nest}, " +
"line #{tk.line_no}" if $DEBUG
when TkIDENTIFIER
if nest == 1 and current_method.nil?
case tk.name
when "private", "protected", "public",
"private_class_method", "public_class_method"
parse_visibility(container, single, tk)
keep_comment = true
when "attr"
parse_attr(container, single, tk, comment)
when /^attr_(reader|writer|accessor)$/, @options.extra_accessors
parse_attr_accessor(container, single, tk, comment)
when "alias_method"
if container.document_self
parse_alias(container, single, tk, comment)
end
end
end
case tk.name
when "require"
parse_require(container, comment)
when "include"
parse_include(container, comment)
end
when TkEND
nest -= 1
puts "Found 'end' in #{container.name}, nest = #{nest}, line #{tk.line_no}" if $DEBUG
puts "Method = #{current_method.name}" if $DEBUG and current_method
if nest == 0
read_documentation_modifiers(container, CLASS_MODIFIERS)
container.ongoing_visibility = save_visibility
return
end
end
comment = '' unless keep_comment
begin
get_tkread
skip_tkspace(false)
end while peek_tk == TkNL
end
end
def parse_class(container, single, tk, comment, &block)
progress("c")
@stats.num_classes += 1
container, name_t = get_class_or_module(container)
case name_t
when TkCONSTANT
name = name_t.name
superclass = "Object"
if peek_tk.kind_of?(TkLT)
get_tk
skip_tkspace(true)
superclass = get_class_specification
superclass = "<unknown>" if superclass.empty?
end
if single == SINGLE
cls_type = SingleClass
else
cls_type = NormalClass
end
cls = container.add_class(cls_type, name, superclass)
read_documentation_modifiers(cls, CLASS_MODIFIERS)
cls.record_location(@top_level)
parse_statements(cls)
cls.comment = comment
when TkLSHFT
case name = get_class_specification
when "self", container.name
parse_statements(container, SINGLE, &block)
else
other = TopLevel.find_class_named(name)
unless other
# other = @top_level.add_class(NormalClass, name, nil)
# other.record_location(@top_level)
# other.comment = comment
other = NormalClass.new("Dummy", nil)
end
read_documentation_modifiers(other, CLASS_MODIFIERS)
parse_statements(other, SINGLE, &block)
end
else
warn("Expected class name or '<<'. Got #{name_t.class}: #{name_t.text.inspect}")
end
end
def parse_module(container, single, tk, comment)
progress("m")
@stats.num_modules += 1
container, name_t = get_class_or_module(container)
# skip_tkspace
name = name_t.name
mod = container.add_module(NormalModule, name)
mod.record_location(@top_level)
read_documentation_modifiers(mod, CLASS_MODIFIERS)
parse_statements(mod)
mod.comment = comment
end
# Look for the name of a class of module (optionally with a leading :: or
# with :: separated named) and return the ultimate name and container
def get_class_or_module(container)
skip_tkspace
name_t = get_tk
# class ::A -> A is in the top level
if name_t.kind_of?(TkCOLON2)
name_t = get_tk
container = @top_level
end
skip_tkspace(false)
while peek_tk.kind_of?(TkCOLON2)
prev_container = container
container = container.find_module_named(name_t.name)
if !container
# warn("Couldn't find module #{name_t.name}")
container = prev_container.add_module(NormalModule, name_t.name)
end
get_tk
name_t = get_tk
end
return [container, name_t]
end
def parse_constant(container, single, tk, comment)
name = tk.name
skip_tkspace(false)
eq_tk = get_tk
unless eq_tk.kind_of?(TkASSIGN)
unget_tk(eq_tk)
return
end
nest = 0
get_tkread
tk = get_tk
if tk.kind_of? TkGT
unget_tk(tk)
unget_tk(eq_tk)
return
end
loop do
puts("Param: #{tk}, #{@scanner.continue} " +
"#{@scanner.lex_state} #{nest}") if $DEBUG
case tk
when TkSEMICOLON
break
when TkLPAREN, TkfLPAREN
nest += 1
when TkRPAREN
nest -= 1
when TkCOMMENT
if nest <= 0 && @scanner.lex_state == EXPR_END
unget_tk(tk)
break
end
when TkNL
if (@scanner.lex_state == EXPR_END and nest <= 0) || !@scanner.continue
unget_tk(tk)
break
end
end
tk = get_tk
end
res = get_tkread.tr("\n", " ").strip
res = "" if res == ";"
con = Constant.new(name, res, comment)
read_documentation_modifiers(con, CONSTANT_MODIFIERS)
if con.document_self
container.add_constant(con)
end
end
def parse_method(container, single, tk, comment)
progress(".")
@stats.num_methods += 1
line_no = tk.line_no
column = tk.char_no
start_collecting_tokens
add_token(tk)
add_token_listener(self)
@scanner.instance_eval{@lex_state = EXPR_FNAME}
skip_tkspace(false)
name_t = get_tk
back_tk = skip_tkspace
meth = nil
dot = get_tk
if dot.kind_of?(TkDOT) or dot.kind_of?(TkCOLON2)
@scanner.instance_eval{@lex_state = EXPR_FNAME}
skip_tkspace
name_t2 = get_tk
case name_t
when TkSELF
name = name_t2.name
when TkCONSTANT
name = name_t2.name
prev_container = container
container = container.find_module_named(name_t.name)
if !container
warn("Couldn't find #{name_t.name}. Assuming it's a module")
container = prev_container.add_module(NormalModule, name_t.name)
end
else
# warn("Unexpected token '#{name_t2.inspect}'")
# break
skip_method(container)
return
end
meth = AnyMethod.new(get_tkread, name)
meth.singleton = true
else
unget_tk dot
back_tk.reverse_each do
|tk|
unget_tk tk
end
name = name_t.name
meth = AnyMethod.new(get_tkread, name)
meth.singleton = (single == SINGLE)
end
remove_token_listener(self)
meth.start_collecting_tokens
indent = TkSPACE.new(1,1)
indent.set_text(" " * column)
meth.add_tokens([TkCOMMENT.new(line_no,
1,
"# File #{@top_level.file_absolute_name}, line #{line_no}"),
NEWLINE_TOKEN,
indent])
meth.add_tokens(@token_stream)
add_token_listener(meth)
@scanner.instance_eval{@continue = false}
parse_method_parameters(meth)
if meth.document_self
container.add_method(meth)
end
# Having now read the method parameters and documentation modifiers, we
# now know whether we have to rename #initialize to ::new
if name == "initialize" && !meth.singleton
if meth.dont_rename_initialize
meth.visibility = :protected
else
meth.singleton = true
meth.name = "new"
meth.visibility = :public
end
end
parse_statements(container, single, meth)
remove_token_listener(meth)
meth.comment = comment
end
def skip_method(container)
meth = AnyMethod.new("", "anon")
parse_method_parameters(meth)
parse_statements(container, false, meth)
end
# Capture the method's parameters. Along the way,
# look for a comment containing
#
# # yields: ....
#
# and add this as the block_params for the method
def parse_method_parameters(method)
res = parse_method_or_yield_parameters(method)
method.params = res unless method.params
if method.block_params.nil?
skip_tkspace(false)
read_documentation_modifiers(method, METHOD_MODIFIERS)
end
end
def parse_method_or_yield_parameters(method=nil, modifiers=METHOD_MODIFIERS)
skip_tkspace(false)
tk = get_tk
# Little hack going on here. In the statement
# f = 2*(1+yield)
# We see the RPAREN as the next token, so we need
# to exit early. This still won't catch all cases
# (such as "a = yield + 1"
end_token = case tk
when TkLPAREN, TkfLPAREN
TkRPAREN
when TkRPAREN
return ""
else
TkNL
end
nest = 0
loop do
puts("Param: #{tk.inspect}, #{@scanner.continue} " +
"#{@scanner.lex_state} #{nest}") if $DEBUG
case tk
when TkSEMICOLON
break
when TkLBRACE
nest += 1
when TkRBRACE
nest -= 1
break if nest <= 0
when TkLPAREN, TkfLPAREN
nest += 1
when end_token
if end_token == TkRPAREN
nest -= 1
break if @scanner.lex_state == EXPR_END and nest <= 0
else
break unless @scanner.continue
end
when method && method.block_params.nil? && TkCOMMENT
unget_tk(tk)
read_documentation_modifiers(method, modifiers)
end
tk = get_tk
end
res = get_tkread.tr("\n", " ").strip
res = "" if res == ";"
res
end
# while, until, and for have an optional
def skip_optional_do_after_expression
skip_tkspace(false)
tk = get_tk
case tk
when TkLPAREN, TkfLPAREN
end_token = TkRPAREN
else
end_token = TkNL
end
nest = 0
@scanner.instance_eval{@continue = false}
loop do
puts("\nWhile: #{tk}, #{@scanner.continue} " +
"#{@scanner.lex_state} #{nest}") if $DEBUG
case tk
when TkSEMICOLON
break
when TkLPAREN, TkfLPAREN
nest += 1
when TkDO
break if nest.zero?
when end_token
if end_token == TkRPAREN
nest -= 1
break if @scanner.lex_state == EXPR_END and nest.zero?
else
break unless @scanner.continue
end
end
tk = get_tk
end
skip_tkspace(false)
if peek_tk.kind_of? TkDO
get_tk
end
end
# Return a superclass, which can be either a constant
# of an expression
def get_class_specification
tk = get_tk
return "self" if tk.kind_of?(TkSELF)
res = ""
while tk.kind_of?(TkCOLON2) ||
tk.kind_of?(TkCOLON3) ||
tk.kind_of?(TkCONSTANT)
res += tk.text
tk = get_tk
end
unget_tk(tk)
skip_tkspace(false)
get_tkread # empty out read buffer
tk = get_tk
case tk
when TkNL, TkCOMMENT, TkSEMICOLON
unget_tk(tk)
return res
end
res += parse_call_parameters(tk)
res
end
def parse_call_parameters(tk)
end_token = case tk
when TkLPAREN, TkfLPAREN
TkRPAREN
when TkRPAREN
return ""
else
TkNL
end
nest = 0
loop do
puts("Call param: #{tk}, #{@scanner.continue} " +
"#{@scanner.lex_state} #{nest}") if $DEBUG
case tk
when TkSEMICOLON
break
when TkLPAREN, TkfLPAREN
nest += 1
when end_token
if end_token == TkRPAREN
nest -= 1
break if @scanner.lex_state == EXPR_END and nest <= 0
else
break unless @scanner.continue
end
when TkCOMMENT
unget_tk(tk)
break
end
tk = get_tk
end
res = get_tkread.tr("\n", " ").strip
res = "" if res == ";"
res
end
# Parse a constant, which might be qualified by
# one or more class or module names
def get_constant
res = ""
skip_tkspace(false)
tk = get_tk
while tk.kind_of?(TkCOLON2) ||
tk.kind_of?(TkCOLON3) ||
tk.kind_of?(TkCONSTANT)
res += tk.text
tk = get_tk
end
# if res.empty?
# warn("Unexpected token #{tk} in constant")
# end
unget_tk(tk)
res
end
# Get a constant that may be surrounded by parens
def get_constant_with_optional_parens
skip_tkspace(false)
nest = 0
while (tk = peek_tk).kind_of?(TkLPAREN) || tk.kind_of?(TkfLPAREN)
get_tk
skip_tkspace(true)
nest += 1
end
name = get_constant
while nest > 0
skip_tkspace(true)
tk = get_tk
nest -= 1 if tk.kind_of?(TkRPAREN)
end
name
end
# Directives are modifier comments that can appear after class, module,
# or method names. For example
#
# def fred # :yields: a, b
#
# or
#
# class SM # :nodoc:
#
# we return the directive name and any parameters as a two element array
def read_directive(allowed)
tk = get_tk
puts "directive: #{tk.inspect}" if $DEBUG
result = nil
if tk.kind_of?(TkCOMMENT)
if tk.text =~ /\s*:?(\w+):\s*(.*)/
directive = $1.downcase
if allowed.include?(directive)
result = [directive, $2]
end
end
else
unget_tk(tk)
end
result
end
def read_documentation_modifiers(context, allow)
dir = read_directive(allow)
case dir[0]
when "notnew", "not_new", "not-new"
context.dont_rename_initialize = true
when "nodoc"
context.document_self = false
if dir[1].downcase == "all"
context.document_children = false
end
when "doc"
context.document_self = true
context.force_documentation = true
when "yield", "yields"
unless context.params.nil?
context.params.sub!(/(,|)\s*&\w+/,'') # remove parameter &proc
end
context.block_params = dir[1]
when "arg", "args"
context.params = dir[1]
end if dir
end
# Look for directives in a normal comment block:
#
# #-- - don't display comment from this point forward
#
#
# This routine modifies it's parameter
def look_for_directives_in(context, comment)
preprocess = SM::PreProcess.new(@input_file_name,
@options.rdoc_include)
preprocess.handle(comment) do |directive, param|
case directive
when "stopdoc"
context.stop_doc
""
when "startdoc"
context.start_doc
context.force_documentation = true
""
when "enddoc"
context.done_documenting = true
""
when "main"
options = Options.instance
options.main_page = param
""
when "title"
options = Options.instance
options.title = param
""
else
warn "Unrecognized directive '#{directive}'"
break
end
end
remove_private_comments(comment)
end
def remove_private_comments(comment)
comment.gsub!(/^#--.*?^#\+\+/m, '')
comment.sub!(/^#--.*/m, '')
end
def get_symbol_or_name
tk = get_tk
case tk
when TkSYMBOL
tk.text.sub(/^:/, '')
when TkId, TkOp
tk.name
when TkSTRING
tk.text
else
raise "Name or symbol expected (got #{tk})"
end
end
def parse_alias(context, single, tk, comment)
skip_tkspace
if (peek_tk.kind_of? TkLPAREN)
get_tk
skip_tkspace
end
new_name = get_symbol_or_name
@scanner.instance_eval{@lex_state = EXPR_FNAME}
skip_tkspace
if (peek_tk.kind_of? TkCOMMA)
get_tk
skip_tkspace
end
old_name = get_symbol_or_name
al = Alias.new(get_tkread, old_name, new_name, comment)
read_documentation_modifiers(al, ATTR_MODIFIERS)
if al.document_self
context.add_alias(al)
end
end
def parse_yield_parameters
parse_method_or_yield_parameters
end
def parse_yield(context, single, tk, method)
if method.block_params.nil?
get_tkread
@scanner.instance_eval{@continue = false}
method.block_params = parse_yield_parameters
end
end
def parse_require(context, comment)
skip_tkspace_comment
tk = get_tk
if tk.kind_of? TkLPAREN
skip_tkspace_comment
tk = get_tk
end
name = nil
case tk
when TkSTRING
name = tk.text
when TkCONSTANT, TkIDENTIFIER, TkIVAR, TkGVAR
name = tk.name
when TkDSTRING
warn "Skipping require of dynamic string: #{tk.text}"
else
error("Unknown argument type to require: #{tk}")
end
if name
context.add_require(Require.new(name, comment))
end
end
def parse_include(context, comment)
skip_tkspace_comment
name = get_constant_with_optional_parens
unless name.empty?
context.add_include(Include.new(name, comment))
end
end
def get_bool
skip_tkspace
tk = get_tk
case tk
when TkTRUE
true
when TkFALSE, TkNIL
false
else
unget_tk tk
true
end
end
def parse_attr(context, single, tk, comment)
args = parse_symbol_arg(1)
if args.size > 0
name = args[0]
rw = "R"
skip_tkspace(false)
tk = get_tk
if tk.kind_of? TkCOMMA
rw = "RW" if get_bool
else
unget_tk tk
end
att = Attr.new(get_tkread, name, rw, comment)
read_documentation_modifiers(att, ATTR_MODIFIERS)
if att.document_self
context.add_attribute(att)
end
else
error("Missing argument to 'attr'")
end
end
def parse_visibility(container, single, tk)
singleton = (single == SINGLE)
vis = case tk.name
when "private" then :private
when "protected" then :protected
when "public" then :public
when "private_class_method"
singleton = true
:private
when "public_class_method"
singleton = true
:public
else raise "Invalid visibility: #{tk.name}"
end
skip_tkspace_comment(false)
if peek_tk.kind_of? TkNL
# error("Missing argument") if singleton
container.ongoing_visibility = vis
else
args = parse_symbol_arg
container.set_visibility_for(args, vis, singleton)
end
end
def parse_attr_accessor(context, single, tk, comment)
args = parse_symbol_arg
read = get_tkread
rw = "?"
# If nodoc is given, don't document any of them
tmp = CodeObject.new
read_documentation_modifiers(tmp, ATTR_MODIFIERS)
return unless tmp.document_self
case tk.name
when "attr_reader" then rw = "R"
when "attr_writer" then rw = "W"
when "attr_accessor" then rw = "RW"
else
rw = @options.extra_accessor_flags[tk.name]
end
for name in args
att = Attr.new(get_tkread, name, rw, comment)
context.add_attribute(att)
end
end
def skip_tkspace_comment(skip_nl = true)
loop do
skip_tkspace(skip_nl)
return unless peek_tk.kind_of? TkCOMMENT
get_tk
end
end
def parse_symbol_arg(no = nil)
args = []
skip_tkspace_comment
case tk = get_tk
when TkLPAREN
loop do
skip_tkspace_comment
if tk1 = parse_symbol_in_arg
args.push tk1
break if no and args.size >= no
end
skip_tkspace_comment
case tk2 = get_tk
when TkRPAREN
break
when TkCOMMA
else
warn("unexpected token: '#{tk.inspect}'")
break
end
end
else
unget_tk tk
if tk = parse_symbol_in_arg
args.push tk
return args if no and args.size >= no
end
loop do
# skip_tkspace_comment(false)
skip_tkspace(false)
tk1 = get_tk
unless tk1.kind_of?(TkCOMMA)
unget_tk tk1
break
end
skip_tkspace_comment
if tk = parse_symbol_in_arg
args.push tk
break if no and args.size >= no
end
end
end
args
end
def parse_symbol_in_arg
case tk = get_tk
when TkSYMBOL
tk.text.sub(/^:/, '')
when TkSTRING
eval @read[-1]
else
warn("Expected symbol or string, got #{tk.inspect}") if $DEBUG
nil
end
end
end
end
|