diff options
| author | Tom Tromey <tromey@redhat.com> | 2003-01-28 18:47:52 +0000 |
|---|---|---|
| committer | Tom Tromey <tromey@gcc.gnu.org> | 2003-01-28 18:47:52 +0000 |
| commit | 82b22c42f92a4fe76e4cd83ba9ab3cce5ccf6dc3 (patch) | |
| tree | c39ef1d10cdd0034ca01bb377913fcd770b6873b /gcc | |
| parent | bffcd064da34369768a4b20dbbcbd1211e55032d (diff) | |
| download | gcc-82b22c42f92a4fe76e4cd83ba9ab3cce5ccf6dc3.zip gcc-82b22c42f92a4fe76e4cd83ba9ab3cce5ccf6dc3.tar.gz gcc-82b22c42f92a4fe76e4cd83ba9ab3cce5ccf6dc3.tar.bz2 | |
lex.c (java_lex): Don't include UEOF as part of token.
* lex.c (java_lex): Don't include UEOF as part of token.
(java_read_unicode): Error if \u sequence prematurely terminated.
From-SVN: r61993
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/java/ChangeLog | 5 | ||||
| -rw-r--r-- | gcc/java/lex.c | 37 |
2 files changed, 28 insertions, 14 deletions
diff --git a/gcc/java/ChangeLog b/gcc/java/ChangeLog index ed7106b..042b7db 100644 --- a/gcc/java/ChangeLog +++ b/gcc/java/ChangeLog @@ -1,3 +1,8 @@ +2003-01-28 Tom Tromey <tromey@redhat.com> + + * lex.c (java_lex): Don't include UEOF as part of token. + (java_read_unicode): Error if \u sequence prematurely terminated. + 2003-01-27 Tom Tromey <tromey@redhat.com> * parse.y (java_check_regular_methods): Check for construct after diff --git a/gcc/java/lex.c b/gcc/java/lex.c index 0aded3f..370217e 100644 --- a/gcc/java/lex.c +++ b/gcc/java/lex.c @@ -542,23 +542,31 @@ java_read_unicode (java_lexer *lex, int *unicode_escape_p) while ((c = java_read_char (lex)) == 'u') ; - /* Unget the most recent character as it is not a `u'. */ - if (c == UEOF) - return UEOF; - lex->unget_value = c; - - /* Next should be 4 hex digits, otherwise it's an error. - The hex value is converted into the unicode, pushed into - the Unicode stream. */ - for (shift = 12; shift >= 0; shift -= 4) + shift = 12; + do { - if ((c = java_read_char (lex)) == UEOF) - return UEOF; + 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 Unicode escape sequence", 0); + { + 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; @@ -1514,7 +1522,7 @@ java_lex (YYSTYPE *java_lval) /* Keyword, boolean literal or null literal. */ for (first_unicode = c, all_ascii = 1, ascii_index = 0; - JAVA_PART_CHAR_P (c); c = java_get_unicode ()) + c != UEOF && JAVA_PART_CHAR_P (c); c = java_get_unicode ()) { java_unicode_2_utf8 (c); if (all_ascii && c >= 128) @@ -1524,7 +1532,8 @@ java_lex (YYSTYPE *java_lval) obstack_1grow (&temporary_obstack, '\0'); string = obstack_finish (&temporary_obstack); - java_unget_unicode (); + if (c != UEOF) + java_unget_unicode (); /* If we have something all ascii, we consider a keyword, a boolean literal, a null literal or an all ASCII identifier. Otherwise, |