aboutsummaryrefslogtreecommitdiff
path: root/gcc/gccspec.c
blob: 746ebf0c420b78f1812c82b0e85c1ec3e9f1f5de (plain)
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
/* Specific flags and argument handling of the C front-end.
   Copyright (C) 1999, 2001, 2003, 2007, 2010 Free Software Foundation, Inc.

This file is part of GCC.

GCC is free software; you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free
Software Foundation; either version 3, or (at your option) any later
version.

GCC is distributed in the hope that it will be useful, but WITHOUT ANY
WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
for more details.

You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING3.  If not see
<http://www.gnu.org/licenses/>.  */

#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "tm.h"
#include "gcc.h"
#include "opts.h"

/* Filter command line before processing by the gcc driver proper.  */
void
lang_specific_driver (struct cl_decoded_option **in_decoded_options ATTRIBUTE_UNUSED,
		      unsigned int *in_decoded_options_count ATTRIBUTE_UNUSED,
		      int *in_added_libraries ATTRIBUTE_UNUSED)
{
  /* Systems which use the NeXT runtime by default should arrange
     for the shared libgcc to be used when -fgnu-runtime is passed
     through specs.  */
#if defined(ENABLE_SHARED_LIBGCC) && ! defined(NEXT_OBJC_RUNTIME)
  unsigned int i;

  /* The new argument list will be contained in this.  */
  struct cl_decoded_option *new_decoded_options;

  /* True if we should add -shared-libgcc to the command-line.  */
  int shared_libgcc = 0;

  /* The total number of arguments with the new stuff.  */
  unsigned int argc;

  /* The argument list.  */
  struct cl_decoded_option *decoded_options;

  argc = *in_decoded_options_count;
  decoded_options = *in_decoded_options;

  for (i = 1; i < argc; i++)
    {
      switch (decoded_options[i].opt_index)
	{
	case OPT_static_libgcc:
	case OPT_static:
	  return;

	case OPT_SPECIAL_input_file:
	  {
	    const char *file = decoded_options[i].arg;
	    int len;

	    /* If the filename ends in .m or .mi, we are compiling
	       ObjC and want to pass -shared-libgcc.  */
	    len = strlen (file);
	    if ((len > 2 && file[len - 2] == '.' && file[len - 1] == 'm')
		||  (len > 3 && file[len - 3] == '.' && file[len - 2] == 'm'
		     && file[len - 1] == 'i'))
	      shared_libgcc = 1;
	  }
	  break;
	}
    }

  if  (shared_libgcc)
    {
      new_decoded_options = XNEWVEC (struct cl_decoded_option, argc + 1);

      i = 0;
      do
	{
	  new_decoded_options[i] = decoded_options[i];
	  i++;
	}
      while (i < argc);

      generate_option (OPT_shared_libgcc, NULL, 1, CL_DRIVER,
		       &new_decoded_options[i++]);

      *in_decoded_options_count = i;
      *in_decoded_options = new_decoded_options;
    }
#endif
}

/* Called before linking.  Returns 0 on success and -1 on failure.  */
int
lang_specific_pre_link (void)
{
  return 0;  /* Not used for C.  */
}

/* Number of extra output files that lang_specific_pre_link may generate.  */
int lang_specific_extra_outfiles = 0;  /* Not used for C.  */
' href='#n394'>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
/* Language lexer for the GNU compiler for the Java(TM) language.
   Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005
   Free Software Foundation, Inc.
   Contributed by Alexandre Petit-Bianco (apbianco@cygnus.com)

This file is part of GCC.

GCC is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.

GCC is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING.  If not, write to
the Free Software Foundation, 51 Franklin Street, Fifth Floor,
Boston, MA 02110-1301, USA. 

Java and all Java-based marks are trademarks or registered trademarks
of Sun Microsystems, Inc. in the United States and other countries.
The Free Software Foundation is independent of Sun Microsystems, Inc.  */

/* It defines java_lex (yylex) that reads a Java ASCII source file
   possibly containing Unicode escape sequence or utf8 encoded
   characters and returns a token for everything found but comments,
   white spaces and line terminators. When necessary, it also fills
   the java_lval (yylval) union. It's implemented to be called by a
   re-entrant parser generated by Bison.

   The lexical analysis conforms to the Java grammar described in "The
   Java(TM) Language Specification. J. Gosling, B. Joy, G. Steele.
   Addison Wesley 1996" (http://java.sun.com/docs/books/jls/html/3.doc.html) */

#include "keyword.h"
#include "flags.h"
#include "chartables.h"
#ifndef JC1_LITE
#include "timevar.h"
#endif

/* Function declarations.  */
static char *java_sprint_unicode (int);
static void java_unicode_2_utf8 (unicode_t);
static void java_lex_error (const char *, int);
#ifndef JC1_LITE
static int do_java_lex (YYSTYPE *);
static int java_lex (YYSTYPE *);
static int java_is_eol (FILE *, int);
static tree build_wfl_node (tree);
#endif
static int java_parse_escape_sequence (void);
static int java_start_char_p (unicode_t);
static int java_part_char_p (unicode_t);
static int java_space_char_p (unicode_t);
static void java_parse_doc_section (int);
static void java_parse_end_comment (int);
static int java_read_char (java_lexer *);
static int java_get_unicode (void);
static int java_peek_unicode (void);
static void java_next_unicode (void);
static int java_read_unicode (java_lexer *, int *);
#ifndef JC1_LITE
static int utf8_cmp (const unsigned char *, int, const char *);
#endif

java_lexer *java_new_lexer (FILE *, const char *);
#ifndef JC1_LITE
static void error_if_numeric_overflow (tree);
#endif

#ifdef HAVE_ICONV
/* This is nonzero if we have initialized `need_byteswap'.  */
static int byteswap_init = 0;

/* Some versions of iconv() (e.g., glibc 2.1.3) will return UCS-2 in
   big-endian order -- not native endian order.  We handle this by
   doing a conversion once at startup and seeing what happens.  This
   flag holds the results of this determination.  */
static int need_byteswap = 0;
#endif

void
java_init_lex (FILE *finput, const char *encoding)
{
#ifndef JC1_LITE
  int java_lang_imported = 0;

  if (!java_lang_id)
    java_lang_id = get_identifier ("java.lang");
  if (!inst_id)
    inst_id = get_identifier ("inst$");
  if (!wpv_id)
    wpv_id = get_identifier ("write_parm_value$");

  if (!java_lang_imported)
    {
      tree node = build_tree_list (build_unknown_wfl (java_lang_id),
				   NULL_TREE);
      read_import_dir (TREE_PURPOSE (node));
      TREE_CHAIN (node) = ctxp->import_demand_list;
      ctxp->import_demand_list = node;
      java_lang_imported = 1;
    }

  if (!wfl_operator)
    {
#ifndef JC1_LITE
#ifdef USE_MAPPED_LOCATION
      wfl_operator = build_expr_wfl (NULL_TREE, input_location);
#else
      wfl_operator = build_expr_wfl (NULL_TREE, ctxp->filename, 0, 0);
#endif
#endif
    }
  if (!label_id)
    label_id = get_identifier ("$L");
  if (!wfl_append) 
    wfl_append = build_unknown_wfl (get_identifier ("append"));
  if (!wfl_string_buffer)
    wfl_string_buffer = 
      build_unknown_wfl (get_identifier (flag_emit_class_files
				      ? "java.lang.StringBuffer"
					 : "gnu.gcj.runtime.StringBuffer"));
  if (!wfl_to_string)
    wfl_to_string = build_unknown_wfl (get_identifier ("toString"));

  CPC_INITIALIZER_LIST (ctxp) = CPC_STATIC_INITIALIZER_LIST (ctxp) =
    CPC_INSTANCE_INITIALIZER_LIST (ctxp) = NULL_TREE;

  memset (ctxp->modifier_ctx, 0, sizeof (ctxp->modifier_ctx));
  ctxp->current_parsed_class = NULL;
  ctxp->package = NULL_TREE;
#endif

#ifndef JC1_LITE
  ctxp->save_location = input_location;
#endif
  ctxp->java_error_flag = 0;
  ctxp->lexer = java_new_lexer (finput, encoding);
}

static char *
java_sprint_unicode (int c)
{
  static char buffer [10];
  if (c < ' ' || c >= 127)
    sprintf (buffer, "\\u%04x", c);
  else
    {
      buffer [0] = c;
      buffer [1] = '\0';
    }
  return buffer;
}

/* Create a new lexer object.  */

java_lexer *
java_new_lexer (FILE *finput, const char *encoding)
{
  java_lexer *lex = XNEW (java_lexer);
  int enc_error = 0;

  lex->finput = finput;
  lex->bs_count = 0;
  lex->unget_value = 0;
  lex->next_unicode = 0;
  lex->avail_unicode = 0;
  lex->next_columns = 1;
  lex->encoding = encoding;
  lex->position.line = 1;
  lex->position.col = 1;
#ifndef JC1_LITE
#ifdef USE_MAPPED_LOCATION
      input_location
	= linemap_line_start (&line_table, 1, 120);
#else
      input_line = 1;
#endif
#endif

#ifdef HAVE_ICONV
  lex->handle = iconv_open ("UCS-2", encoding);
  if (lex->handle != (iconv_t) -1)
    {
      lex->first = -1;
      lex->last = -1;
      lex->out_first = -1;
      lex->out_last = -1;
      lex->read_anything = 0;
      lex->use_fallback = 0;

      /* Work around broken iconv() implementations by doing checking at
	 runtime.  We assume that if the UTF-8 => UCS-2 encoder is broken,
	 then all UCS-2 encoders will be broken.  Perhaps not a valid
	 assumption.  */
      if (! byteswap_init)
	{
	  iconv_t handle;

	  byteswap_init = 1;

	  handle = iconv_open ("UCS-2", "UTF-8");
	  if (handle != (iconv_t) -1)
	    {
	      unicode_t result;
	      unsigned char in[3];
	      char *inp, *outp;
	      size_t inc, outc, r;

	      /* This is the UTF-8 encoding of \ufeff.  */
	      in[0] = 0xef;
	      in[1] = 0xbb;
	      in[2] = 0xbf;

	      inp = (char *) in;
	      inc = 3;
	      outp = (char *) &result;
	      outc = 2;

	      r = iconv (handle, (ICONV_CONST char **) &inp, &inc,
			 &outp, &outc);
	      iconv_close (handle);
	      /* Conversion must be complete for us to use the result.  */
	      if (r != (size_t) -1 && inc == 0 && outc == 0)
		need_byteswap = (result != 0xfeff);
	    }
	}

      lex->byte_swap = need_byteswap;
    }
  else
#endif /* HAVE_ICONV */
    {
      /* If iconv failed, use the internal decoder if the default
	 encoding was requested.  This code is used on platforms where
	 iconv exists but is insufficient for our needs.  For
	 instance, on Solaris 2.5 iconv cannot handle UTF-8 or UCS-2.

	 On Solaris the default encoding, as returned by nl_langinfo(),
	 is `646' (aka ASCII), but the Solaris iconv_open() doesn't
	 understand that.  We work around that by pretending
	 `646' to be the same as UTF-8.   */
      if (strcmp (encoding, DEFAULT_ENCODING) && strcmp (encoding, "646"))
	enc_error = 1;
#ifdef HAVE_ICONV
      else
        {
	  lex->use_fallback = 1;
	  lex->encoding = "UTF-8";
	}
#endif /* HAVE_ICONV */
    }

  if (enc_error)
    fatal_error ("unknown encoding: %qs\nThis might mean that your locale's encoding is not supported\nby your system's iconv(3) implementation.  If you aren't trying\nto use a particular encoding for your input file, try the\n%<--encoding=UTF-8%> option", encoding);

  return lex;
}

void
java_destroy_lexer (java_lexer *lex)
{
#ifdef HAVE_ICONV
  if (! lex->use_fallback)
    iconv_close (lex->handle);
#endif
  free (lex);
}

static int
java_read_char (java_lexer *lex)
{
#ifdef HAVE_ICONV
  if (! lex->use_fallback)
    {
      size_t ir, inbytesleft, in_save, out_count, out_save;
      char *inp, *outp;
      unicode_t result;

      /* If there is data which has already been converted, use it.  */
      if (lex->out_first == -1 || lex->out_first >= lex->out_last)
	{
	  lex->out_first = 0;
	  lex->out_last = 0;

	  while (1)
	    {
	      /* See if we need to read more data.  If FIRST == 0 then
		 the previous conversion attempt ended in the middle of
		 a character at the end of the buffer.  Otherwise we
		 only have to read if the buffer is empty.  */
	      if (lex->first == 0 || lex->first >= lex->last)
		{
		  int r;

		  if (lex->first >= lex->last)
		    {
		      lex->first = 0;
		      lex->last = 0;
		    }
		  if (feof (lex->finput))
		    return UEOF;
		  r = fread (&lex->buffer[lex->last], 1,
			     sizeof (lex->buffer) - lex->last,
			     lex->finput);
		  lex->last += r;
		}

	      inbytesleft = lex->last - lex->first;
	      out_count = sizeof (lex->out_buffer) - lex->out_last;

	      if (inbytesleft == 0)
		{
		  /* We've tried to read and there is nothing left.  */
		  return UEOF;
		}

	      in_save = inbytesleft;
	      out_save = out_count;
	      inp = &lex->buffer[lex->first];
	      outp = (char *) &lex->out_buffer[lex->out_last];
	      ir = iconv (lex->handle, (ICONV_CONST char **) &inp,
			  &inbytesleft, &outp, &out_count);

	      /* If we haven't read any bytes, then look to see if we
		 have read a BOM.  */
	      if (! lex->read_anything && out_save - out_count >= 2)
		{
		  unicode_t uc = * (unicode_t *) &lex->out_buffer[0];
		  if (uc == 0xfeff)
		    {
		      lex->byte_swap = 0;
		      lex->out_first += 2;
		    }
		  else if (uc == 0xfffe)
		    {
		      lex->byte_swap = 1;
		      lex->out_first += 2;
		    }
		  lex->read_anything = 1;
		}

	      if (lex->byte_swap)
		{
		  unsigned int i;
		  for (i = 0; i < out_save - out_count; i += 2)
		    {
		      char t = lex->out_buffer[lex->out_last + i];
		      lex->out_buffer[lex->out_last + i]
			= lex->out_buffer[lex->out_last + i + 1];
		      lex->out_buffer[lex->out_last + i + 1] = t;
		    }
		}

	      lex->first += in_save - inbytesleft;
	      lex->out_last += out_save - out_count;

	      /* If we converted anything at all, move along.  */
	      if (out_count != out_save)
		break;

	      if (ir == (size_t) -1)
		{
		  if (errno == EINVAL)
		    {
		      /* This is ok.  This means that the end of our buffer
			 is in the middle of a character sequence.  We just
			 move the valid part of the buffer to the beginning
			 to force a read.  */
		      memmove (&lex->buffer[0], &lex->buffer[lex->first],
			       lex->last - lex->first);
		      lex->last -= lex->first;
		      lex->first = 0;
		    }
		  else
		    {
		      /* A more serious error.  */
		      char buffer[128];
		      sprintf (buffer,
			       "Unrecognized character for encoding '%s'", 
		               lex->encoding);
		      java_lex_error (buffer, 0);
		      return UEOF;
		    }
		}
	    }
	}

      if (lex->out_first == -1 || lex->out_first >= lex->out_last)
	{
	  /* Don't have any data.  */
	  return UEOF;
	}

      /* Success.  */
      result = * ((unicode_t *) &lex->out_buffer[lex->out_first]);
      lex->out_first += 2;
      return result;
    }
  else
#endif /* HAVE_ICONV */
    {
      int c, c1, c2;
      c = getc (lex->finput);

      if (c == EOF)
	return UEOF;
      if (c < 128)
	return (unicode_t) c;
      else
	{
	  if ((c & 0xe0) == 0xc0)
	    {
	      c1 = getc (lex->finput);
	      if ((c1 & 0xc0) == 0x80)
		{
		  unicode_t r = (unicode_t)(((c & 0x1f) << 6) + (c1 & 0x3f));
		  /* Check for valid 2-byte characters.  We explicitly
		     allow \0 because this encoding is common in the
		     Java world.  */
		  if (r == 0 || (r >= 0x80 && r <= 0x7ff))
		    return r;
		}
	    }
	  else if ((c & 0xf0) == 0xe0)
	    {
	      c1 = getc (lex->finput);
	      if ((c1 & 0xc0) == 0x80)
		{
		  c2 = getc (lex->finput);
		  if ((c2 & 0xc0) == 0x80)
		    {
		      unicode_t r =  (unicode_t)(((c & 0xf) << 12) + 
						 (( c1 & 0x3f) << 6)
						 + (c2 & 0x3f));
		      /* Check for valid 3-byte characters.
			 Don't allow surrogate, \ufffe or \uffff.  */
		      if (IN_RANGE (r, 0x800, 0xffff)
			  && ! IN_RANGE (r, 0xd800, 0xdfff)
			  && r != 0xfffe && r != 0xffff)
			return r;
		    }
		}
	    }

	  /* We simply don't support invalid characters.  We also
	     don't support 4-, 5-, or 6-byte UTF-8 sequences, as these
	     cannot be valid Java characters.  */
	  java_lex_error ("malformed UTF-8 character", 0);
	}
    }

  /* We only get here on error.  */
  return UEOF;
}

static int
java_read_unicode (java_lexer *lex, int *unicode_escape_p)
{
  int c;

  if (lex->unget_value)
    {
      c = lex->unget_value;
      lex->unget_value = 0;
    }
  else
    c = java_read_char (lex);

  *unicode_escape_p = 0;

  if (c != '\\')
    {
      lex->bs_count = 0;
      return c;
    }

  ++lex->bs_count;
  if ((lex->bs_count) % 2 == 1)
    {
      /* Odd number of \ seen.  */
      c = java_read_char (lex);
      if (c == 'u')
        {
	  unicode_t unicode = 0;
	  int shift = 12;

	  /* Recognize any number of `u's in \u.  */
	  while ((c = java_read_char (lex)) == 'u')
	    ;

	  shift = 12;
	  do
	    {
	      if (c == UEOF)
		{
		  java_lex_error ("prematurely terminated \\u sequence", 0);
		  return UEOF;
		}

	      if (hex_p (c))
		unicode |= (unicode_t)(hex_value (c) << shift);
	      else
		{
		  java_lex_error ("non-hex digit in \\u sequence", 0);
		  break;
		}

	      c = java_read_char (lex);
	      shift -= 4;
	    }
	  while (shift >= 0);

	  if (c != UEOF)
	    lex->unget_value = c;

	  lex->bs_count = 0;
	  *unicode_escape_p = 1;
	  return unicode;
	}
      lex->unget_value = c;
    }
  return (unicode_t) '\\';
}

/* Get the next Unicode character (post-Unicode-escape-handling).
   Move the current position to just after returned character. */

static int
java_get_unicode (void)
{
  int next = java_peek_unicode ();
  java_next_unicode ();
  return next;
}

/* Return the next Unicode character (post-Unicode-escape-handling).
   Do not move the current position, which remains just before
   the returned character. */

static int
java_peek_unicode (void)
{
  int unicode_escape_p;
  java_lexer *lex = ctxp->lexer;
  int next;

  if (lex->avail_unicode)
    return lex->next_unicode;

  next = java_read_unicode (lex, &unicode_escape_p);

  if (next == '\r')
    {
      /* We have to read ahead to see if we got \r\n.
	 In that case we return a single line terminator.  */
      int dummy;
      next = java_read_unicode (lex, &dummy);
      if (next != '\n' && next != UEOF)
	lex->unget_value = next;
      /* In either case we must return a newline.  */
      next = '\n';
    }

  lex->next_unicode = next;
  lex->avail_unicode = 1;

  if (next == UEOF)
    {
      lex->next_columns = 0;
      return next;
    }

  if (next == '\n')
    {
      lex->next_columns = 1 - lex->position.col;
    }
  else if (next == '\t')
    {
      int cur_col = lex->position.col;
      lex->next_columns = ((cur_col + 7) & ~7) + 1 - cur_col;
      
    }
  else
    {
      lex->next_columns = 1;
    }
  if (unicode_escape_p)
    lex->next_columns = 6;
  return next;
}

/* Move forward one Unicode character (post-Unicode-escape-handling).
   Only allowed after java_peek_unicode.  The combination java_peek_unicode
   followed by java_next_unicode is equivalent to java_get_unicode.  */

static void java_next_unicode (void)
{
  struct java_lexer *lex = ctxp->lexer;
  lex->position.col += lex->next_columns;
  if (lex->next_unicode == '\n')
    {
      lex->position.line++; 
#ifndef JC1_LITE
#ifdef USE_MAPPED_LOCATION
      input_location
	= linemap_line_start (&line_table, lex->position.line, 120);
#else
      input_line = lex->position.line;
#endif
#endif
    }
  lex->avail_unicode = 0;
}

#if 0
/* The inverse of java_next_unicode.
   Not currently used, but could be if it would be cleaner or faster.
   java_peek_unicode == java_get_unicode + java_unget_unicode.
   java_get_unicode == java_peek_unicode + java_next_unicode.
*/
static void java_unget_unicode ()
{
  struct java_lexer *lex = ctxp->lexer;
  if (lex->avail_unicode)
    fatal_error ("internal error - bad unget");
  lex->avail_unicode = 1;
  lex->position.col -= lex->next_columns;
}
#endif

/* Parse the end of a C style comment.
 * C is the first character following the '/' and '*'.  */
static void
java_parse_end_comment (int c)
{
  for ( ;; c = java_get_unicode ())
    {
      switch (c)
	{
	case UEOF:
	  java_lex_error ("Comment not terminated at end of input", 0);
	  return;
	case '*':
	  switch (c = java_peek_unicode ())
	    {
	    case UEOF:
	      java_lex_error ("Comment not terminated at end of input", 0);
	      return;
	    case '/':
	      java_next_unicode ();
	      return;
	    case '*':	/* Reparse only '*'.  */
	      ;
	    }
	}
    }
}

/* Parse the documentation section. Keywords must be at the beginning
   of a documentation comment line (ignoring white space and any `*'
   character). Parsed keyword(s): @DEPRECATED.  */

static void
java_parse_doc_section (int c)
{
  int last_was_star;

  /* We reset this here, because only the most recent doc comment
     applies to the following declaration.  */
  ctxp->deprecated = 0;

  /* We loop over all the lines of the comment.  We'll eventually exit
     if we hit EOF prematurely, or when we see the comment
     terminator.  */
  while (1)
    {
      /* These first steps need only be done if we're still looking
	 for the deprecated tag.  If we've already seen it, we might
	 as well skip looking for it again.  */
      if (! ctxp->deprecated)
	{
	  /* Skip whitespace and '*'s.  We must also check for the end
	     of the comment here.  */
	  while (JAVA_WHITE_SPACE_P (c) || c == '*')
	    {
	      last_was_star = (c == '*');
	      c = java_get_unicode ();
	      if (last_was_star && c == '/')
		{
		  /* We just saw the comment terminator.  */
		  return;
		}
	    }

	  if (c == UEOF)
	    goto eof;

	  if (c == '@')
	    {
	      const char *deprecated = "@deprecated";
	      int i;

	      for (i = 0; deprecated[i]; ++i)
		{
		  if (c != deprecated[i])
		    break;
		  /* We write the code in this way, with the
		     update at the end, so that after the loop
		     we're left with the next character in C.  */
		  c = java_get_unicode ();
		}

	      if (c == UEOF)
		goto eof;

	      /* @deprecated must be followed by a space or newline.
		 We also allow a '*' in case it appears just before
		 the end of a comment.  In this position only we also
		 must allow any Unicode space character.  */
	      if (c == ' ' || c == '\n' || c == '*' || java_space_char_p (c))
		{
		  if (! deprecated[i])
		    ctxp->deprecated = 1;
		}
	    }
	}

      /* We've examined the relevant content from this line.  Now we
	 skip the remaining characters and start over with the next
	 line.  We also check for end of comment here.  */
      while (c != '\n' && c != UEOF)
	{
	  last_was_star = (c == '*');
	  c = java_get_unicode ();
	  if (last_was_star && c == '/')
	    return;
	}

      if (c == UEOF)
	goto eof;
      /* We have to advance past the \n.  */
      c = java_get_unicode ();
      if (c == UEOF)
	goto eof;
    }

 eof:
  java_lex_error ("Comment not terminated at end of input", 0);
}

/* Return true if C is a valid start character for a Java identifier.
   This is only called if C >= 128 -- smaller values are handled
   inline.  However, this function handles all values anyway.  */
static int
java_start_char_p (unicode_t c)
{
  unsigned int hi = c / 256;
  const char *const page = type_table[hi];
  unsigned long val = (unsigned long) page;
  int flags;

  if ((val & ~ LETTER_MASK) != 0)
    flags = page[c & 255];
  else
    flags = val;

  return flags & LETTER_START;
}

/* Return true if C is a valid part character for a Java identifier.
   This is only called if C >= 128 -- smaller values are handled
   inline.  However, this function handles all values anyway.  */
static int
java_part_char_p (unicode_t c)
{
  unsigned int hi = c / 256;
  const char *const page = type_table[hi];
  unsigned long val = (unsigned long) page;
  int flags;

  if ((val & ~ LETTER_MASK) != 0)
    flags = page[c & 255];
  else
    flags = val;

  return flags & LETTER_PART;
}

/* Return true if C is whitespace.  */
static int
java_space_char_p (unicode_t c)
{
  unsigned int hi = c / 256;
  const char *const page = type_table[hi];
  unsigned long val = (unsigned long) page;
  int flags;

  if ((val & ~ LETTER_MASK) != 0)
    flags = page[c & 255];
  else
    flags = val;

  return flags & LETTER_SPACE;
}

static int
java_parse_escape_sequence (void)
{
  int c;

  switch (c = java_get_unicode ())
    {
    case 'b':
      return (unicode_t)0x8;
    case 't':
      return (unicode_t)0x9;
    case 'n':
      return (unicode_t)0xa;
    case 'f':
      return (unicode_t)0xc;
    case 'r':
      return (unicode_t)0xd;
    case '"':
      return (unicode_t)0x22;
    case '\'':
      return (unicode_t)0x27;
    case '\\':
      return (unicode_t)0x5c;
    case '0': case '1': case '2': case '3': case '4':
    case '5': case '6': case '7':
      {
	int more = 3;
	unicode_t char_lit = 0;

	if (c > '3')
	  {
	    /* According to the grammar, `\477' has a well-defined
	       meaning -- it is `\47' followed by `7'.  */
	    --more;
	  }
	char_lit = 0;
	for (;;)
	  {
	    char_lit = 8 * char_lit + c - '0';
	    if (--more == 0)
	      break;
	    c = java_peek_unicode ();
	    if (! RANGE (c, '0', '7'))
	      break;
	    java_next_unicode ();
	  }

	return char_lit;
      }
    default:
      java_lex_error ("Invalid character in escape sequence", -1);
      return JAVA_CHAR_ERROR;
    }
}

#ifndef JC1_LITE
#define IS_ZERO(X) REAL_VALUES_EQUAL (X, dconst0)

/* Subroutine of java_lex: converts floating-point literals to tree
   nodes.  LITERAL_TOKEN is the input literal, JAVA_LVAL is where to
   store the result.  FFLAG indicates whether the literal was tagged
   with an 'f', indicating it is of type 'float'; NUMBER_BEGINNING
   is the line number on which to report any error.  */

static void java_perform_atof (YYSTYPE *, char *, int, int);

static void
java_perform_atof (YYSTYPE *java_lval, char *literal_token, int fflag,
		   int number_beginning)
{
  REAL_VALUE_TYPE value;
  tree type = (fflag ? FLOAT_TYPE_NODE : DOUBLE_TYPE_NODE);

  SET_REAL_VALUE_ATOF (value,
		       REAL_VALUE_ATOF (literal_token, TYPE_MODE (type)));

  if (REAL_VALUE_ISINF (value) || REAL_VALUE_ISNAN (value))
    {
      JAVA_FLOAT_RANGE_ERROR (fflag ? "float" : "double");
      value = DCONST0;
    }
  else if (IS_ZERO (value))
    {
      /* We check to see if the value is really 0 or if we've found an
	 underflow.  We do this in the most primitive imaginable way.  */
      int really_zero = 1;
      char *p = literal_token;
      if (*p == '-')
	++p;
      while (*p && *p != 'e' && *p != 'E')
	{
	  if (*p != '0' && *p != '.')
	    {
	      really_zero = 0;
	      break;
	    }
	  ++p;
	}
      if (! really_zero)
	{
	  int save_col = ctxp->lexer->position.col;
	  ctxp->lexer->position.col = number_beginning;
	  java_lex_error ("Floating point literal underflow", 0);
	  ctxp->lexer->position.col = save_col;
	}
    }

  SET_LVAL_NODE (build_real (type, value));
}
#endif

static int yylex (YYSTYPE *);

static int
#ifdef JC1_LITE
yylex (YYSTYPE *java_lval)
#else
do_java_lex (YYSTYPE *java_lval)
#endif
{
  int c;
  char *string;

  /* Translation of the Unicode escape in the raw stream of Unicode
     characters. Takes care of line terminator.  */
 step1:
  /* Skip white spaces: SP, TAB and FF or ULT.  */ 
  for (;;)
    {
      c = java_peek_unicode ();
      if (c != '\n' && ! JAVA_WHITE_SPACE_P (c))
	break;
      java_next_unicode ();
    }

  /* Handle EOF here.  */
  if (c == UEOF)	/* Should probably do something here...  */
    return 0;

#ifndef JC1_LITE
#ifdef USE_MAPPED_LOCATION
  LINEMAP_POSITION_FOR_COLUMN (input_location, &line_table,
			       ctxp->lexer->position.col);
#else
  ctxp->lexer->token_start = ctxp->lexer->position;
#endif
#endif

  /* Numeric literals.  */
  if (JAVA_ASCII_DIGIT (c) || (c == '.'))
    {
      /* This section of code is borrowed from gcc/c-lex.c.  */
#define TOTAL_PARTS ((HOST_BITS_PER_WIDE_INT / HOST_BITS_PER_CHAR) * 2 + 2)
      int parts[TOTAL_PARTS];
      HOST_WIDE_INT high, low;
      /* End borrowed section.  */

#define MAX_TOKEN_LEN 256
      char literal_token [MAX_TOKEN_LEN + 1];
      int  literal_index = 0, radix = 10, long_suffix = 0, overflow = 0, bytes;
      int  found_hex_digits = 0, found_non_octal_digits = -1;
      int  i;
#ifndef JC1_LITE
      int  number_beginning = ctxp->lexer->position.col;
      tree value;
#endif
     
      for (i = 0; i < TOTAL_PARTS; i++)
	parts [i] = 0;

      if (c == '0')
	{
	  java_next_unicode ();
	  c = java_peek_unicode ();
	  if (c == 'x' || c == 'X')
	    {
	      radix = 16;
	      java_next_unicode ();
	      c = java_peek_unicode ();
	    }
	  else if (JAVA_ASCII_DIGIT (c))
	    {
	      literal_token [literal_index++] = '0';
	      radix = 8;
	    }
	  else if (c == '.' || c == 'e' || c =='E')
	    {
	      literal_token [literal_index++] = '0';
	      /* Handle C during floating-point parsing.  */
	    }
	  else
	    {
	      /* We have a zero literal: 0, 0{l,L}, 0{f,F}, 0{d,D}.  */
              switch (c)
		{		
		case 'L': case 'l':
		  java_next_unicode ();
		  SET_LVAL_NODE (long_zero_node);
		  return (INT_LIT_TK);
		case 'f': case 'F':
		  java_next_unicode ();
		  SET_LVAL_NODE (float_zero_node);
		  return (FP_LIT_TK);
		case 'd': case 'D':
		  java_next_unicode ();
		  SET_LVAL_NODE (double_zero_node);
		  return (FP_LIT_TK);
		default:
		  SET_LVAL_NODE (integer_zero_node);
		  return (INT_LIT_TK);
		}
	    }
	}

      /* Terminate LITERAL_TOKEN in case we bail out on large tokens.  */
      literal_token [MAX_TOKEN_LEN] = '\0';

      /* Parse the first part of the literal, until we find something
	 which is not a number.  */
      while ((radix == 16 ? JAVA_ASCII_HEXDIGIT (c) : JAVA_ASCII_DIGIT (c))
             && literal_index < MAX_TOKEN_LEN)
	{
	  /* We store in a string (in case it turns out to be a FP) and in
	     PARTS if we have to process a integer literal.  */
	  int numeric = hex_value (c);
	  int count;

	  /* Remember when we find a valid hexadecimal digit.  */
	  if (radix == 16)
	    found_hex_digits = 1;
          /* Remember when we find an invalid octal digit.  */
          else if (radix == 8 && numeric >= 8 && found_non_octal_digits < 0)
	    found_non_octal_digits = literal_index;

	  literal_token [literal_index++] = c;
	  /* This section of code if borrowed from gcc/c-lex.c.  */
	  for (count = 0; count < TOTAL_PARTS; count++)
	    {
	      parts[count] *= radix;
	      if (count)
		{
		  parts[count]   += (parts[count-1] >> HOST_BITS_PER_CHAR);
		  parts[count-1] &= (1 << HOST_BITS_PER_CHAR) - 1;
		}
	      else
		parts[0] += numeric;
	    }
	  if (parts [TOTAL_PARTS-1] != 0)
	    overflow = 1;
	  /* End borrowed section.  */
	  java_next_unicode ();
	  c = java_peek_unicode ();
	}

      /* If we have something from the FP char set but not a digit, parse
	 a FP literal.  */
      if (JAVA_ASCII_FPCHAR (c) && !JAVA_ASCII_DIGIT (c))
	{
	  /* stage==0: seen digits only
	   * stage==1: seen '.'
	   * stage==2: seen 'e' or 'E'.
	   * stage==3: seen '+' or '-' after 'e' or 'E'.
	   * stage==4: seen type suffix ('f'/'F'/'d'/'D')
	   */
	  int stage = 0;
	  int seen_digit = (literal_index ? 1 : 0);
	  int seen_exponent = 0;
	  int fflag = 0;	/* 1 for {f,F}, 0 for {d,D}. FP literal are
				   double unless specified.  */

	  /* It is ok if the radix is 8 because this just means we've
	     seen a leading `0'.  However, radix==16 is invalid.  */
	  if (radix == 16)
	    java_lex_error ("Can't express non-decimal FP literal", 0);
	  radix = 10;

	  for (; literal_index < MAX_TOKEN_LEN;)
	    {
	      if (c == '.')
		{
		  if (stage < 1)
		    {
		      stage = 1;
		      literal_token [literal_index++ ] = c;
		      java_next_unicode ();
		      c = java_peek_unicode ();
		      if (literal_index == 1 && !JAVA_ASCII_DIGIT (c))
			BUILD_OPERATOR (DOT_TK);
		    }
		  else
		    java_lex_error ("Invalid character in FP literal", 0);
		}

	      if ((c == 'e' || c == 'E') && literal_index < MAX_TOKEN_LEN)
		{
		  if (stage < 2)
		    {
		      /* {E,e} must have seen at least a digit.  */
		      if (!seen_digit)
			java_lex_error
                          ("Invalid FP literal, mantissa must have digit", 0);
		      seen_digit = 0;
		      seen_exponent = 1;
		      stage = 2;
		      literal_token [literal_index++] = c;
		      java_next_unicode ();
		      c = java_peek_unicode ();
		    }
		  else
		    java_lex_error ("Invalid character in FP literal", 0);
		}
	      if ( c == 'f' || c == 'F' || c == 'd' || c == 'D')
		{
		  fflag = ((c == 'd') || (c == 'D')) ? 0 : 1;
		  stage = 4;	/* So we fall through.  */
		}

	      if ((c=='-' || c =='+') && stage == 2
                  && literal_index < MAX_TOKEN_LEN)
		{
		  stage = 3;
		  literal_token [literal_index++] = c;
		  java_next_unicode ();
		  c = java_peek_unicode ();
		}

              if (((stage == 0 && JAVA_ASCII_FPCHAR (c))
                   || (stage == 1 && JAVA_ASCII_FPCHAR (c) && !(c == '.'))
                   || (stage == 2 && (JAVA_ASCII_DIGIT (c) || JAVA_FP_PM (c)))
                   || (stage == 3 && JAVA_ASCII_DIGIT (c)))
                  && literal_index < MAX_TOKEN_LEN)
		{
		  if (JAVA_ASCII_DIGIT (c))
		    seen_digit = 1;
                  if (stage == 2)
                    stage = 3;
		  literal_token [literal_index++ ] = c;
		  java_next_unicode ();
		  c = java_peek_unicode ();
		}
	      else if (literal_index < MAX_TOKEN_LEN)
		{
		  if (stage == 4) /* Don't push back fF/dD.  */
		    java_next_unicode ();
		  
		  /* An exponent (if any) must have seen a digit.  */
		  if (seen_exponent && !seen_digit)
		    java_lex_error
                      ("Invalid FP literal, exponent must have digit", 0);

		  literal_token [literal_index] = '\0';

#ifndef JC1_LITE
		  java_perform_atof (java_lval, literal_token,
				     fflag, number_beginning);
#endif
		  return FP_LIT_TK;
		}
	    }
	} /* JAVA_ASCII_FPCHAR (c) */

      /* Here we get back to converting the integral literal.  */
      if (radix == 16 && ! found_hex_digits)
	java_lex_error
	  ("0x must be followed by at least one hexadecimal digit", 0);
      else if (radix == 8 && found_non_octal_digits >= 0)
	{
	  int back = literal_index - found_non_octal_digits;
	  ctxp->lexer->position.col -= back;
	  java_lex_error ("Octal literal contains digit out of range", 0);
	  ctxp->lexer->position.col += back;
	}
      else if (c == 'L' || c == 'l')
	{
	  java_next_unicode ();
	  long_suffix = 1;
	}

      /* This section of code is borrowed from gcc/c-lex.c.  */
      if (!overflow)
	{
	  bytes = GET_TYPE_PRECISION (long_type_node);
	  for (i = bytes; i < TOTAL_PARTS; i++)
	    if (parts [i])
	      {
	        overflow = 1;
		break;
	      }
	}
      high = low = 0;
      for (i = 0; i < HOST_BITS_PER_WIDE_INT / HOST_BITS_PER_CHAR; i++)
	{
	  high |= ((HOST_WIDE_INT) parts[i + (HOST_BITS_PER_WIDE_INT
					      / HOST_BITS_PER_CHAR)]
		   << (i * HOST_BITS_PER_CHAR));
	  low |= (HOST_WIDE_INT) parts[i] << (i * HOST_BITS_PER_CHAR);
	}
      /* End borrowed section.  */

#ifndef JC1_LITE
      /* Range checking.  */
      /* Temporarily set type to unsigned.  */
      value = build_int_cst_wide (long_suffix
				  ? unsigned_long_type_node
				  : unsigned_int_type_node, low, high);
      SET_LVAL_NODE (value);

      /* For base 10 numbers, only values up to the highest value
	 (plus one) can be written.  For instance, only ints up to
	 2147483648 can be written.  The special case of the largest
	 negative value is handled elsewhere.  For other bases, any
	 number can be represented.  */
      if (overflow || (radix == 10
		       && tree_int_cst_lt (long_suffix
					   ? decimal_long_max
					   : decimal_int_max,
					   value)))
	{
	  if (long_suffix)
	    JAVA_RANGE_ERROR ("Numeric overflow for 'long' literal");
	  else
	    JAVA_RANGE_ERROR ("Numeric overflow for 'int' literal");
	}

      /* Sign extend the value.  */
      value = build_int_cst_wide (long_suffix ? long_type_node : int_type_node,
				  low, high);
      value = force_fit_type (value, 0, false, false);

      if (radix != 10)
	{
	  value = copy_node (value);
	  JAVA_NOT_RADIX10_FLAG (value) = 1;
	}
      
      SET_LVAL_NODE (value);
#endif
      return INT_LIT_TK;
    }

  /* We may have an ID here.  */
  if (JAVA_START_CHAR_P (c))
    {
      int ascii_index = 0, all_ascii = 1;

      /* Keyword, boolean literal or null literal.  */
      while (c != UEOF && JAVA_PART_CHAR_P (c))
	{
	  java_unicode_2_utf8 (c);
	  if (c >= 128)
	    all_ascii = 0;
	  java_next_unicode ();
	  ascii_index++;
	  c = java_peek_unicode ();
	}

      obstack_1grow (&temporary_obstack, '\0');
      string = obstack_finish (&temporary_obstack);

      /* If we have something all ascii, we consider a keyword, a boolean
	 literal, a null literal or an all ASCII identifier.  Otherwise,
	 this is an identifier (possibly not respecting formation rule).  */
      if (all_ascii)
	{
	  const struct java_keyword *kw;
	  if ((kw=java_keyword (string, ascii_index)))
	    {
	      switch (kw->token)
		{
		case PUBLIC_TK:       case PROTECTED_TK: case STATIC_TK:
		case ABSTRACT_TK:     case FINAL_TK:     case NATIVE_TK:
		case SYNCHRONIZED_TK: case TRANSIENT_TK: case VOLATILE_TK:
		case PRIVATE_TK:      case STRICT_TK:
		  SET_MODIFIER_CTX (kw->token);
		  return MODIFIER_TK;
		case FLOAT_TK:
		  SET_LVAL_NODE (float_type_node);
		  return FP_TK;
		case DOUBLE_TK:
		  SET_LVAL_NODE (double_type_node);
		  return FP_TK;
		case BOOLEAN_TK:
		  SET_LVAL_NODE (boolean_type_node);
		  return BOOLEAN_TK;
		case BYTE_TK:
		  SET_LVAL_NODE (byte_type_node);
		  return INTEGRAL_TK;
		case SHORT_TK:
		  SET_LVAL_NODE (short_type_node);
		  return INTEGRAL_TK;
		case INT_TK:
		  SET_LVAL_NODE (int_type_node);
		  return INTEGRAL_TK;
		case LONG_TK:
		  SET_LVAL_NODE (long_type_node);
		  return INTEGRAL_TK;
		case CHAR_TK:
		  SET_LVAL_NODE (char_type_node);
		  return INTEGRAL_TK;

		  /* Keyword based literals.  */
		case TRUE_TK:
		case FALSE_TK:
		  SET_LVAL_NODE ((kw->token == TRUE_TK ? 
				  boolean_true_node : boolean_false_node));
		  return BOOL_LIT_TK;
		case NULL_TK:
		  SET_LVAL_NODE (null_pointer_node);
		  return NULL_TK;

		case ASSERT_TK:
		  if (flag_assert)
		    {
		      BUILD_OPERATOR (kw->token);
		      return kw->token;
		    }
		  else
		    break;

		  /* Some keyword we want to retain information on the location
		     they where found.  */
		case CASE_TK:
		case DEFAULT_TK:
		case SUPER_TK:
		case THIS_TK:
		case RETURN_TK:
		case BREAK_TK:
		case CONTINUE_TK:
		case TRY_TK:
		case CATCH_TK:
		case THROW_TK:
		case INSTANCEOF_TK:
		  BUILD_OPERATOR (kw->token);

		default:
		  return kw->token;
		}
	    }
	}

      java_lval->node = BUILD_ID_WFL (GET_IDENTIFIER (string));
      return ID_TK;
    }

  java_next_unicode ();

  /* Character literals.  */
  if (c == '\'')
    {
      int char_lit;
      
      if ((c = java_get_unicode ()) == '\\')
	char_lit = java_parse_escape_sequence ();
      else
	{
	  if (c == '\n' || c == '\'')
	    java_lex_error ("Invalid character literal", 0);
	  char_lit = c;
	}

      c = java_get_unicode ();

      if ((c == '\n') || (c == UEOF))
	java_lex_error ("Character literal not terminated at end of line", 0);
      if (c != '\'')
	java_lex_error ("Syntax error in character literal", 0);

      if (char_lit == JAVA_CHAR_ERROR)
        char_lit = 0;		/* We silently convert it to zero.  */

      SET_LVAL_NODE (build_int_cst (char_type_node, char_lit));
      return CHAR_LIT_TK;
    }

  /* String literals.  */
  if (c == '"')
    {
      int no_error = 1;
      char *string;

      for (;;)
	{
	  c = java_peek_unicode ();
	  if (c == '\n' || c == UEOF) /* ULT.  */
	    {
	      java_lex_error ("String not terminated at end of line", 0);
	      break;
	    }
	  java_next_unicode ();
	  if (c == '"')
	    break;
	  if (c == '\\')
	    c = java_parse_escape_sequence ();
	  if (c == JAVA_CHAR_ERROR)
	    {
	      no_error = 0;
	      c = 0;		/* We silently convert it to zero.  */
	    }
	  java_unicode_2_utf8 (c);
	}

      obstack_1grow (&temporary_obstack, '\0');
      string = obstack_finish (&temporary_obstack);
#ifndef JC1_LITE
      if (!no_error || (c != '"'))
	java_lval->node = error_mark_node; /* FIXME: Requires further
                                              testing.  */
      else
	java_lval->node = build_string (strlen (string), string);
#endif
      obstack_free (&temporary_obstack, string);
      return STRING_LIT_TK;
    }

  switch (c)
    {
    case '/':
      /* Check for comment.  */
      switch (c = java_peek_unicode ())
	{
	case '/':
	  java_next_unicode ();
	  for (;;)
	    {
	      c = java_get_unicode ();
	      if (c == UEOF)
		{
		  /* It is ok to end a `//' comment with EOF, unless
		     we're being pedantic.  */
		  if (pedantic)
		    java_lex_error ("Comment not terminated at end of input",
				    0);
		  return 0;
		}
	      if (c == '\n')	/* ULT */
		goto step1;
	    }
	  break;

	case '*':
	  java_next_unicode ();
	  if ((c = java_get_unicode ()) == '*')
	    {
	      c = java_get_unicode ();
	      if (c == '/')
		{
		  /* Empty documentation comment.  We have to reset
		     the deprecation marker as only the most recent
		     doc comment applies.  */
		  ctxp->deprecated = 0;
		}
	      else
		java_parse_doc_section (c);
	    }
	  else
	    java_parse_end_comment ((c = java_get_unicode ()));
	  goto step1;
	  break;

	case '=':
	  java_next_unicode ();
	  BUILD_OPERATOR2 (DIV_ASSIGN_TK);

	default:
	  BUILD_OPERATOR (DIV_TK);
	}

    case '(':
      BUILD_OPERATOR (OP_TK);
    case ')':
      return CP_TK;
    case '{':
#ifndef JC1_LITE
      java_lval->operator.token = OCB_TK;
      java_lval->operator.location = BUILD_LOCATION();
#ifdef USE_MAPPED_LOCATION
      if (ctxp->ccb_indent == 1)
	ctxp->first_ccb_indent1 = input_location;
#else
      if (ctxp->ccb_indent == 1)
	ctxp->first_ccb_indent1 = input_line;
#endif
#endif
      ctxp->ccb_indent++;
      return OCB_TK;
    case '}':
      ctxp->ccb_indent--;
#ifndef JC1_LITE
      java_lval->operator.token = CCB_TK;
      java_lval->operator.location = BUILD_LOCATION();
#ifdef USE_MAPPED_LOCATION
      if (ctxp->ccb_indent == 1)
        ctxp->last_ccb_indent1 = input_location;
#else
      if (ctxp->ccb_indent == 1)
        ctxp->last_ccb_indent1 = input_line;
#endif
#endif
      return CCB_TK;
    case '[':
      BUILD_OPERATOR (OSB_TK);
    case ']':
      return CSB_TK;
    case ';':
      return SC_TK;
    case ',':
      return C_TK;
    case '.':
      BUILD_OPERATOR (DOT_TK);

      /* Operators.  */
    case '=':
      c = java_peek_unicode ();
      if (c == '=')
	{
	  java_next_unicode ();
	  BUILD_OPERATOR (EQ_TK);
	}
      else
	{
	  /* Equals is used in two different locations. In the 
	     variable_declarator: rule, it has to be seen as '=' as opposed
	     to being seen as an ordinary assignment operator in
	     assignment_operators: rule.  */
	  BUILD_OPERATOR (ASSIGN_TK);
	}
      
    case '>':
      switch ((c = java_peek_unicode ()))
	{
	case '=':
	  java_next_unicode ();
	  BUILD_OPERATOR (GTE_TK);
	case '>':
	  java_next_unicode ();
	  switch ((c = java_peek_unicode ()))
	    {
	    case '>':
	      java_next_unicode ();
	      c = java_peek_unicode ();
	      if (c == '=')
		{
		  java_next_unicode ();
		  BUILD_OPERATOR2 (ZRS_ASSIGN_TK);
		}
	      else
		{
		  BUILD_OPERATOR (ZRS_TK);
		}
	    case '=':
	      java_next_unicode ();
	      BUILD_OPERATOR2 (SRS_ASSIGN_TK);
	    default:
	      BUILD_OPERATOR (SRS_TK);
	    }
	default:
	  BUILD_OPERATOR (GT_TK);
	}
	
    case '<':
      switch ((c = java_peek_unicode ()))
	{
	case '=':
	  java_next_unicode ();
	  BUILD_OPERATOR (LTE_TK);
	case '<':
	  java_next_unicode ();
	  if ((c = java_peek_unicode ()) == '=')
	    {
	      java_next_unicode ();
	      BUILD_OPERATOR2 (LS_ASSIGN_TK);
	    }
	  else
	    {
	      BUILD_OPERATOR (LS_TK);
	    }
	default:
	  BUILD_OPERATOR (LT_TK);
	}

    case '&':
      switch ((c = java_peek_unicode ()))
	{
	case '&':
	  java_next_unicode ();
	  BUILD_OPERATOR (BOOL_AND_TK);
	case '=':
	  java_next_unicode ();
	  BUILD_OPERATOR2 (AND_ASSIGN_TK);
	default:
	  BUILD_OPERATOR (AND_TK);
	}

    case '|':
      switch ((c = java_peek_unicode ()))
	{
	case '|':
	  java_next_unicode ();
	  BUILD_OPERATOR (BOOL_OR_TK);
	case '=':
	  java_next_unicode ();
	  BUILD_OPERATOR2 (OR_ASSIGN_TK);
	default:
	  BUILD_OPERATOR (OR_TK);
	}

    case '+':
      switch ((c = java_peek_unicode ()))
	{
	case '+':
	  java_next_unicode ();
	  BUILD_OPERATOR (INCR_TK);
	case '=':
	  java_next_unicode ();
	  BUILD_OPERATOR2 (PLUS_ASSIGN_TK);
	default:
	  BUILD_OPERATOR (PLUS_TK);
	}

    case '-':
      switch ((c = java_peek_unicode ()))
	{
	case '-':
	  java_next_unicode ();
	  BUILD_OPERATOR (DECR_TK);
	case '=':
	  java_next_unicode ();
	  BUILD_OPERATOR2 (MINUS_ASSIGN_TK);
	default:
	  BUILD_OPERATOR (MINUS_TK);
	}

    case '*':
      if ((c = java_peek_unicode ()) == '=')
	{
	  java_next_unicode ();
	  BUILD_OPERATOR2 (MULT_ASSIGN_TK);
	}
      else
	{
	  BUILD_OPERATOR (MULT_TK);
	}

    case '^':
      if ((c = java_peek_unicode ()) == '=')
	{
	  java_next_unicode ();
	  BUILD_OPERATOR2 (XOR_ASSIGN_TK);
	}
      else
	{
	  BUILD_OPERATOR (XOR_TK);
	}

    case '%':
      if ((c = java_peek_unicode ()) == '=')
	{
	  java_next_unicode ();
	  BUILD_OPERATOR2 (REM_ASSIGN_TK);
	}
      else
	{
	  BUILD_OPERATOR (REM_TK);
	}

    case '!':
      if ((c = java_peek_unicode()) == '=')
	{
	  java_next_unicode ();
	  BUILD_OPERATOR (NEQ_TK);
	}
      else
	{
	  BUILD_OPERATOR (NEG_TK);
	}
	  
    case '?':
      BUILD_OPERATOR (REL_QM_TK);
    case ':':
      BUILD_OPERATOR (REL_CL_TK);
    case '~':
      BUILD_OPERATOR (NOT_TK);
    }
  
  if (c == 0x1a)		/* CTRL-Z.  */
    {
      if ((c = java_peek_unicode ()) == UEOF)
	return 0;		/* Ok here.  */
    }

  /* Everything else is an invalid character in the input.  */
  {
    char lex_error_buffer [128];
    sprintf (lex_error_buffer, "Invalid character '%s' in input", 
	     java_sprint_unicode (c));
    java_lex_error (lex_error_buffer, -1);
  }
  return 0;
}

#ifndef JC1_LITE

/* The exported interface to the lexer.  */
static int
java_lex (YYSTYPE *java_lval)
{
  int r;

  timevar_push (TV_LEX);
  r = do_java_lex (java_lval);
  timevar_pop (TV_LEX);
  return r;
}

/* This is called by the parser to see if an error should be generated
   due to numeric overflow.  This function only handles the particular
   case of the largest negative value, and is only called in the case
   where this value is not preceded by `-'.  */
static void
error_if_numeric_overflow (tree value)
{
  if (TREE_CODE (value) == INTEGER_CST
      && !JAVA_NOT_RADIX10_FLAG (value)
      && tree_int_cst_sgn (value) < 0)
    {
      if (TREE_TYPE (value) == long_type_node)
	java_lex_error ("Numeric overflow for 'long' literal", 0);
      else
	java_lex_error ("Numeric overflow for 'int' literal", 0);
    }
}

#endif /* JC1_LITE */

static void
java_unicode_2_utf8 (unicode_t unicode)
{
  if (RANGE (unicode, 0x01, 0x7f))
    obstack_1grow (&temporary_obstack, (char)unicode);
  else if (RANGE (unicode, 0x80, 0x7ff) || unicode == 0)
    {
      obstack_1grow (&temporary_obstack,
		     (unsigned char)(0xc0 | ((0x7c0 & unicode) >> 6)));
      obstack_1grow (&temporary_obstack,
		     (unsigned char)(0x80 | (unicode & 0x3f)));
    }
  else				/* Range 0x800-0xffff.  */
    {
      obstack_1grow (&temporary_obstack,
		     (unsigned char)(0xe0 | (unicode & 0xf000) >> 12));
      obstack_1grow (&temporary_obstack,
		     (unsigned char)(0x80 | (unicode & 0x0fc0) >> 6));
      obstack_1grow (&temporary_obstack,
		     (unsigned char)(0x80 | (unicode & 0x003f)));
    }
}

#ifndef JC1_LITE
static tree
build_wfl_node (tree node)
{
#ifdef USE_MAPPED_LOCATION
  node = build_expr_wfl (node, input_location);
#else
  node = build_expr_wfl (node, ctxp->filename,
			 ctxp->lexer->token_start.line,
			 ctxp->lexer->token_start.col);
#endif
  /* Prevent java_complete_lhs from short-circuiting node (if constant).  */
  TREE_TYPE (node) = NULL_TREE;
  return node;
}
#endif

static void
java_lex_error (const char *msg ATTRIBUTE_UNUSED, int forward ATTRIBUTE_UNUSED)
{
#ifndef JC1_LITE
  int col = (ctxp->lexer->position.col
	     + forward * ctxp->lexer->next_columns);
#if USE_MAPPED_LOCATION
  source_location save_location = input_location;
  LINEMAP_POSITION_FOR_COLUMN (input_location, &line_table, col);
  
  /* Might be caught in the middle of some error report.  */
  ctxp->java_error_flag = 0;
  java_error (NULL);
  java_error (msg);
  input_location = save_location;
#else
  java_lc save = ctxp->lexer->token_start;
  ctxp->lexer->token_start.line = ctxp->lexer->position.line;
  ctxp->lexer->token_start.col = col;

  /* Might be caught in the middle of some error report.  */
  ctxp->java_error_flag = 0;
  java_error (NULL);
  java_error (msg);
  ctxp->lexer->token_start = save;
#endif
#endif
}

#ifndef JC1_LITE
static int
java_is_eol (FILE *fp, int c)
{
  int next;
  switch (c)
    {
    case '\r':
      next = getc (fp);
      if (next != '\n' && next != EOF)
	ungetc (next, fp);
      return 1;
    case '\n':
      return 1;
    default:
      return 0;
    }  
}
#endif

char *
java_get_line_col (const char *filename ATTRIBUTE_UNUSED,
		   int line ATTRIBUTE_UNUSED, int col ATTRIBUTE_UNUSED)
{
#ifdef JC1_LITE
  return 0;
#else
  /* Dumb implementation. Doesn't try to cache or optimize things.  */
  /* First line of the file is line 1, first column is 1.  */

  /* COL == -1 means, at the CR/LF in LINE.  */
  /* COL == -2 means, at the first non space char in LINE.  */

  FILE *fp;
  int c, ccol, cline = 1;
  int current_line_col = 0;
  int first_non_space = 0;
  char *base;

  if (!(fp = fopen (filename, "r")))
    fatal_error ("can't open %s: %m", filename);

  while (cline != line)
    {
      c = getc (fp);
      if (c == EOF)
	{
	  static const char msg[] = "<<file too short - unexpected EOF>>";
	  obstack_grow (&temporary_obstack, msg, sizeof(msg)-1);
	  goto have_line;
	}
      if (java_is_eol (fp, c))
	cline++;
    }

  /* Gather the chars of the current line in a buffer.  */
  for (;;)
    {
      c = getc (fp);
      if (c < 0 || java_is_eol (fp, c))
	break;
      if (!first_non_space && !JAVA_WHITE_SPACE_P (c))
	first_non_space = current_line_col;
      obstack_1grow (&temporary_obstack, c);
      current_line_col++;
    }
 have_line:

  obstack_1grow (&temporary_obstack, '\n');

  if (col == -1)
    {
      col = current_line_col;
      first_non_space = 0;
    }
  else if (col == -2)
    col = first_non_space;
  else
    first_non_space = 0;

  /* Place the '^' a the right position.  */
  base = obstack_base (&temporary_obstack);
  for (col += 2, ccol = 0; ccol < col; ccol++)
    {
      /* Compute \t when reaching first_non_space.  */
      char c = (first_non_space ?
		(base [ccol] == '\t' ? '\t' : ' ') : ' ');
      obstack_1grow (&temporary_obstack, c);
    }
  obstack_grow0 (&temporary_obstack, "^", 1);

  fclose (fp);
  return obstack_finish (&temporary_obstack);
#endif
}

#ifndef JC1_LITE
static int
utf8_cmp (const unsigned char *str, int length, const char *name)
{
  const unsigned char *limit = str + length;
  int i;

  for (i = 0; name[i]; ++i)
    {
      int ch = UTF8_GET (str, limit);
      if (ch != name[i])
	return ch - name[i];
    }

  return str == limit ? 0 : 1;
}

/* A sorted list of all C++ keywords.  */

static const char *const cxx_keywords[] =
{
  "_Complex",
  "__alignof",
  "__alignof__",
  "__asm",
  "__asm__",
  "__attribute",
  "__attribute__",
  "__builtin_va_arg",
  "__complex",
  "__complex__",
  "__const",
  "__const__",
  "__extension__",
  "__imag",
  "__imag__",
  "__inline",
  "__inline__",
  "__label__",
  "__null",
  "__real",
  "__real__",
  "__restrict",
  "__restrict__",
  "__signed",
  "__signed__",
  "__typeof",
  "__typeof__",
  "__volatile",
  "__volatile__",
  "and",
  "and_eq",
  "asm",
  "auto",
  "bitand",
  "bitor",
  "bool",
  "break",
  "case",
  "catch",
  "char",
  "class",
  "compl",
  "const",
  "const_cast",
  "continue",
  "default",
  "delete",
  "do",
  "double",
  "dynamic_cast",
  "else",
  "enum",
  "explicit",
  "export",
  "extern",
  "false",
  "float",
  "for",
  "friend",
  "goto",
  "if",
  "inline",
  "int",
  "long",
  "mutable",
  "namespace",
  "new",
  "not",
  "not_eq",
  "operator",
  "or",
  "or_eq",
  "private",
  "protected",
  "public",
  "register",
  "reinterpret_cast",
  "return",
  "short",
  "signed",
  "sizeof",
  "static",
  "static_cast",
  "struct",
  "switch",
  "template",
  "this",      
  "throw",
  "true",
  "try",
  "typedef",
  "typeid",
  "typename",
  "typeof",
  "union",
  "unsigned",
  "using",
  "virtual",
  "void",
  "volatile",
  "wchar_t",
  "while",
  "xor",
  "xor_eq"
};

/* Return true if NAME is a C++ keyword.  */

int
cxx_keyword_p (const char *name, int length)
{
  int last = ARRAY_SIZE (cxx_keywords);
  int first = 0;
  int mid = (last + first) / 2;
  int old = -1;

  for (mid = (last + first) / 2;
       mid != old;
       old = mid, mid = (last + first) / 2)
    {
      int kwl = strlen (cxx_keywords[mid]);
      int min_length = kwl > length ? length : kwl;
      int r = utf8_cmp ((const unsigned char *) name, min_length, cxx_keywords[mid]);

      if (r == 0)
	{
	  int i;
	  /* We've found a match if all the remaining characters are `$'.  */
	  for (i = min_length; i < length && name[i] == '$'; ++i)
	    ;
	  if (i == length)
	    return 1;
	  r = 1;
	}

      if (r < 0)
	last = mid;
      else
	first = mid;
    }
  return 0;
}
#endif /* JC1_LITE */