summaryrefslogtreecommitdiff
path: root/posix/bug-regex20.c
diff options
context:
space:
mode:
authorUlrich Drepper <drepper@redhat.com>2003-11-18 23:40:59 +0000
committerUlrich Drepper <drepper@redhat.com>2003-11-18 23:40:59 +0000
commitad7f28c29d06ddb4506d0d75e089732740b5bd2b (patch)
treede9ee40c2d213a4113e3da2b8cedc3d505386bc1 /posix/bug-regex20.c
parent5146ec9a2c092cb74b5cd0eb8b5e938b46f1631b (diff)
Update.
* posix/regex_internal.h (re_token_type_t): Remove unused ALT, END_OF_RE_TOKEN_T and SUBEXP. Reorder values. Add OP_UTF8_PERIOD and EPSILON_BIT. (IS_EPSILON_NODE): Just test if EPSILON_BIT is set. (ACCEPT_MB_NODE): Return 1 for OP_UTF8_PERIOD as well. * posix/regex_internal.c (create_ci_newstate, create_cd_newstate): Handle OP_UTF8_PERIOD. (re_string_reconstruct): Set valid_len for single byte char searching with no translation and case sensitivity. * posix/regcomp.c (re_compile_fastmap_iter, calc_first): Handle OP_UTF8_PERIOD. (re_compile_internal): Don't call optimize_utf8 if preg->translate != NULL. (optimize_utf8): Remove BACK_SLASH case. Transform OP_PERIOD into OP_UTF8_PERIOD if the searching can be optimized. (parse_bracket_exp): Don't create SIMPLE_BRACKET if it doesn't have any bits set and COMPLEX_BRACKET is used. * posix/regexec.c (transit_state_mb): Fix comment typo. (group_nodes_into_DFAstates, check_node_accept): Handle OP_UTF8_PERIOD. (check_node_accept_bytes): Likewise. Reorder slightly so that re_string_char_size_at and re_string_elem_size_at are called only when needed. * posix/bug-regex20.c (BRE, ERE): Define. (tests): Use them to make lines shorter. Expect . to be optimized. Add lots of new tests. (main): Run (ATM just case sensitive) test with backwards searching as well. 2003-11-18 Jakub Jelinek <jakub@redhat.com>
Diffstat (limited to 'posix/bug-regex20.c')
-rw-r--r--posix/bug-regex20.c229
1 files changed, 163 insertions, 66 deletions
diff --git a/posix/bug-regex20.c b/posix/bug-regex20.c
index 74662e6246..7f5d0310ca 100644
--- a/posix/bug-regex20.c
+++ b/posix/bug-regex20.c
@@ -29,6 +29,9 @@
#define RE_NO_INTERNAL_PROTOTYPES 1
#include "regex_internal.h"
+#define BRE RE_SYNTAX_POSIX_BASIC
+#define ERE RE_SYNTAX_POSIX_EXTENDED
+
static struct
{
int syntax;
@@ -42,71 +45,145 @@ static struct
\xc3\xb6 LATIN SMALL LETTER O WITH DIAERESIS
\xe2\x80\x94 EM DASH */
/* Should be optimized. */
- {RE_SYNTAX_POSIX_BASIC, "foo", "b\xc3\xa4rfoob\xc3\xa4z", 4, 1},
- {RE_SYNTAX_POSIX_BASIC, "b\xc3\xa4z", "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
- {RE_SYNTAX_POSIX_BASIC, "b\xc3\xa4*z", "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
- {RE_SYNTAX_POSIX_BASIC, "b\xc3\xa4*z", "b\xc3\xa4rfoobz", 7, 1},
- {RE_SYNTAX_POSIX_BASIC, "b\xc3\xa4\\+z",
- "b\xc3\xa4rfoob\xc3\xa4\xc3\xa4z", 7, 1},
- {RE_SYNTAX_POSIX_BASIC, "b\xc3\xa4\\?z", "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
- {RE_SYNTAX_POSIX_BASIC, "b\xc3\xa4\\{1,2\\}z",
- "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\|xy*z$", "\xc3\xb6xyyz", 2, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\\\y\\{6\\}z\\+", "x\\yyyyyyzz\xc3\xb6", 0, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\\\y\\{2,36\\}z\\+", "x\\yzz\xc3\xb6", -1, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\\\y\\{,3\\}z\\+", "x\\yyyzz\xc3\xb6", 0, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\|x\xc3\xa4*z$",
- "\xc3\xb6x\xc3\xa4\xc3\xa4z", 2, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\\\\xc3\x84\\{6\\}z\\+",
+ {BRE, "foo", "b\xc3\xa4rfoob\xc3\xa4z", 4, 1},
+ {BRE, "b\xc3\xa4z", "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
+ {BRE, "b\xc3\xa4*z", "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
+ {BRE, "b\xc3\xa4*z", "b\xc3\xa4rfoobz", 7, 1},
+ {BRE, "b\xc3\xa4\\+z", "b\xc3\xa4rfoob\xc3\xa4\xc3\xa4z", 7, 1},
+ {BRE, "b\xc3\xa4\\?z", "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
+ {BRE, "b\xc3\xa4\\{1,2\\}z", "b\xc3\xa4rfoob\xc3\xa4z", 7, 1},
+ {BRE, "^x\\|xy*z$", "\xc3\xb6xyyz", 2, 1},
+ {BRE, "^x\\\\y\\{6\\}z\\+", "x\\yyyyyyzz\xc3\xb6", 0, 1},
+ {BRE, "^x\\\\y\\{2,36\\}z\\+", "x\\yzz\xc3\xb6", -1, 1},
+ {BRE, "^x\\\\y\\{,3\\}z\\+", "x\\yyyzz\xc3\xb6", 0, 1},
+ {BRE, "^x\\|x\xc3\xa4*z$", "\xc3\xb6x\xc3\xa4\xc3\xa4z", 2, 1},
+ {BRE, "^x\\\\\xc3\x84\\{6\\}z\\+",
"x\\\xc3\x84\xc3\x84\xc3\x84\xc3\x84\xc3\x84\xc3\x84zz\xc3\xb6", 0, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\\\\xc3\x84\\{2,36\\}z\\+",
- "x\\\xc3\x84zz\xc3\xb6", -1, 1},
- {RE_SYNTAX_POSIX_BASIC, "^x\\\\\xc3\x84\\{,3\\}z\\+",
+ {BRE, "^x\\\\\xc3\x84\\{2,36\\}z\\+", "x\\\xc3\x84zz\xc3\xb6", -1, 1},
+ {BRE, "^x\\\\\xc3\x84\\{,3\\}z\\+",
"x\\\xc3\x84\xc3\x84\xc3\x84zz\xc3\xb6", 0, 1},
- {RE_SYNTAX_POSIX_BASIC, "x[C]y", "axCy", 1, 1},
- {RE_SYNTAX_POSIX_BASIC, "x[ABC]y", "axCy", 1, 1},
- {RE_SYNTAX_POSIX_BASIC, "\\`x\\|z\\'", "x\xe2\x80\x94", 0, 1},
- {RE_SYNTAX_POSIX_BASIC, "\\(xy\\)z\\1a\\1", "\xe2\x80\x94xyzxyaxy\xc3\x84", 3, 1},
- {RE_SYNTAX_POSIX_BASIC, "xy\\?z", "\xc3\x84xz\xc3\xb6", 2, 1},
- {RE_SYNTAX_POSIX_BASIC, "\\`\xc3\x84\\|z\\'", "\xc3\x84\xe2\x80\x94", 0, 1},
- {RE_SYNTAX_POSIX_BASIC, "\\(x\xc3\x84\\)z\\1\x61\\1",
+ {BRE, "x[C]y", "axCy", 1, 1},
+ {BRE, "x[ABC]y", "axCy", 1, 1},
+ {BRE, "\\`x\\|z\\'", "x\xe2\x80\x94", 0, 1},
+ {BRE, "\\(xy\\)z\\1a\\1", "\xe2\x80\x94xyzxyaxy\xc3\x84", 3, 1},
+ {BRE, "xy\\?z", "\xc3\x84xz\xc3\xb6", 2, 1},
+ {BRE, "\\`\xc3\x84\\|z\\'", "\xc3\x84\xe2\x80\x94", 0, 1},
+ {BRE, "\\(x\xc3\x84\\)z\\1\x61\\1",
"\xe2\x80\x94x\xc3\x84zx\xc3\x84\x61x\xc3\x84\xc3\x96", 3, 1},
- {RE_SYNTAX_POSIX_BASIC, "x\xc3\x96\\?z", "\xc3\x84xz\xc3\xb6", 2, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "foo", "b\xc3\xa4rfoob\xc3\xa4z", 4, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "^x|xy*z$", "\xc3\xb6xyyz", 2, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "^x\\\\y{6}z+", "x\\yyyyyyzz\xc3\xb6", 0, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "^x\\\\y{2,36}z+", "x\\yzz\xc3\xb6", -1, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "^x\\\\y{,3}z+", "x\\yyyzz\xc3\xb6", 0, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "x[C]y", "axCy", 1, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "x[ABC]y", "axCy", 1, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "\\`x|z\\'", "x\xe2\x80\x94", 0, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "(xy)z\\1a\\1", "\xe2\x80\x94xyzxyaxy\xc3\x84", 3, 1},
- {RE_SYNTAX_POSIX_EXTENDED, "xy?z", "\xc3\x84xz\xc3\xb6", 2, 1},
+ {BRE, "x\xc3\x96\\?z", "\xc3\x84xz\xc3\xb6", 2, 1},
+ {BRE, "x.y", "ax\xe2\x80\x94yz", 1, 1},
+ {BRE, "x.*z", "\xc3\x84xz", 2, 1},
+ {BRE, "x.*z", "\xc3\x84x\xe2\x80\x94z", 2, 1},
+ {BRE, "x.*z", "\xc3\x84x\xe2\x80\x94y\xf1\x90\x80\x90z", 2, 1},
+ {BRE, "x.*z", "\xc3\x84x\xe2\x80\x94\xc3\x94\xf1\x90\x80\x90z", 2, 1},
+ {BRE, "x.\\?z", "axz", 1, 1},
+ {BRE, "x.\\?z", "axyz", 1, 1},
+ {BRE, "x.\\?z", "ax\xc3\x84z", 1, 1},
+ {BRE, "x.\\?z", "ax\xe2\x80\x94z", 1, 1},
+ {BRE, "x.\\?z", "ax\xf0\x9d\x80\x80z", 1, 1},
+ {BRE, "x.\\?z", "ax\xf9\x81\x82\x83\x84z", 1, 1},
+ {BRE, "x.\\?z", "ax\xfd\xbf\xbf\xbf\xbf\xbfz", 1, 1},
+ {BRE, ".", "y", 0, 1},
+ {BRE, ".", "\xc3\x84", 0, 1},
+ {BRE, ".", "\xe2\x80\x94", 0, 1},
+ {BRE, ".", "\xf0\x9d\x80\x80", 0, 1},
+ {BRE, ".", "\xf9\x81\x82\x83\x84", 0, 1},
+ {BRE, ".", "\xfd\xbf\xbf\xbf\xbf\xbf", 0, 1},
+ {BRE, "x.\\?z", "axyyz", -1, 1},
+ {BRE, "x.\\?z", "ax\xc3\x84\xc3\x96z", -1, 1},
+ {BRE, "x.\\?z", "ax\xe2\x80\x94\xc3\xa4z", -1, 1},
+ {BRE, "x.\\?z", "ax\xf0\x9d\x80\x80yz", -1, 1},
+ {BRE, "x.\\?z", "ax\xf9\x81\x82\x83\x84\xf0\xf9\x80\x81z", -1, 1},
+ {BRE, "x.\\?z", "ax\xfd\xbf\xbf\xbf\xbf\xbf\xc3\x96z", -1, 1},
+ {BRE, "x.\\+z", "\xe2\x80\x94xz", -1, 1},
+ {BRE, "x.\\+z", "\xe2\x80\x94xyz", 3, 1},
+ {BRE, "x.\\+z", "\xe2\x80\x94x\xc3\x84y\xe2\x80\x94z", 3, 1},
+ {BRE, "x.\\+z", "\xe2\x80\x94x\xe2\x80\x94z", 3, 1},
+ {BRE, "x.\\+z", "\xe2\x80\x94x\xf0\x9d\x80\x80\xc3\x84z", 3, 1},
+ {BRE, "x.\\+z", "\xe2\x80\x94x.~\xe2\x80\x94\xf9\x81\x82\x83\x84z", 3, 1},
+ {BRE, "x.\\+z", "\xe2\x80\x94x\xfd\xbf\xbf\xbf\xbf\xbfz", 3, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94xz", -1, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94x\xc3\x96y\xc3\xa4z", -1, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94xyz", 3, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94x\xc3\x84\xe2\x80\x94z", 3, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94x\xe2\x80\x94z", 3, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94x\xf0\x9d\x80\x80\xc3\x84z", 3, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94x~\xe2\x80\x94z", 3, 1},
+ {BRE, "x.\\{1,2\\}z", "\xe2\x80\x94x\xfd\xbf\xbf\xbf\xbf\xbfz", 3, 1},
+ {BRE, "x\\(.w\\|\xc3\x86\\)\\?z", "axz", 1, 1},
+ {BRE, "x\\(.w\\|\xc3\x86\\)\\?z", "ax\xfd\xbf\xbf\xbf\xbf\xbfwz", 1, 1},
+ {BRE, "x\\(.w\\|\xc3\x86\\)\\?z", "ax\xc3\x86z", 1, 1},
+ {BRE, "x\\(.w\\|\xc3\x86\\)\\?z", "ax\xe2\x80\x96wz", 1, 1},
+ {ERE, "foo", "b\xc3\xa4rfoob\xc3\xa4z", 4, 1},
+ {ERE, "^x|xy*z$", "\xc3\xb6xyyz", 2, 1},
+ {ERE, "^x\\\\y{6}z+", "x\\yyyyyyzz\xc3\xb6", 0, 1},
+ {ERE, "^x\\\\y{2,36}z+", "x\\yzz\xc3\xb6", -1, 1},
+ {ERE, "^x\\\\y{,3}z+", "x\\yyyzz\xc3\xb6", 0, 1},
+ {ERE, "x[C]y", "axCy", 1, 1},
+ {ERE, "x[ABC]y", "axCy", 1, 1},
+ {ERE, "\\`x|z\\'", "x\xe2\x80\x94", 0, 1},
+ {ERE, "(xy)z\\1a\\1", "\xe2\x80\x94xyzxyaxy\xc3\x84", 3, 1},
+ {ERE, "xy?z", "\xc3\x84xz\xc3\xb6", 2, 1},
+ {ERE, "x.y", "ax\xe2\x80\x94yz", 1, 1},
+ {ERE, "x.*z", "\xc3\x84xz", 2, 1},
+ {ERE, "x.*z", "\xc3\x84x\xe2\x80\x94z", 2, 1},
+ {ERE, "x.*z", "\xc3\x84x\xe2\x80\x94y\xf1\x90\x80\x90z", 2, 1},
+ {ERE, "x.*z", "\xc3\x84x\xe2\x80\x94\xc3\x94\xf1\x90\x80\x90z", 2, 1},
+ {ERE, "x.?z", "axz", 1, 1},
+ {ERE, "x.?z", "axyz", 1, 1},
+ {ERE, "x.?z", "ax\xc3\x84z", 1, 1},
+ {ERE, "x.?z", "ax\xe2\x80\x94z", 1, 1},
+ {ERE, "x.?z", "ax\xf0\x9d\x80\x80z", 1, 1},
+ {ERE, "x.?z", "ax\xf9\x81\x82\x83\x84z", 1, 1},
+ {ERE, "x.?z", "ax\xfd\xbf\xbf\xbf\xbf\xbfz", 1, 1},
+ {ERE, "x.?z", "axyyz", -1, 1},
+ {ERE, "x.?z", "ax\xc3\x84\xc3\x96z", -1, 1},
+ {ERE, "x.?z", "ax\xe2\x80\x94\xc3\xa4z", -1, 1},
+ {ERE, "x.?z", "ax\xf0\x9d\x80\x80yz", -1, 1},
+ {ERE, "x.?z", "ax\xf9\x81\x82\x83\x84\xf0\xf9\x80\x81z", -1, 1},
+ {ERE, "x.?z", "ax\xfd\xbf\xbf\xbf\xbf\xbf\xc3\x96z", -1, 1},
+ {ERE, "x.+z", "\xe2\x80\x94xz", -1, 1},
+ {ERE, "x.+z", "\xe2\x80\x94xyz", 3, 1},
+ {ERE, "x.+z", "\xe2\x80\x94x\xc3\x84y\xe2\x80\x94z", 3, 1},
+ {ERE, "x.+z", "\xe2\x80\x94x\xe2\x80\x94z", 3, 1},
+ {ERE, "x.+z", "\xe2\x80\x94x\xf0\x9d\x80\x80\xc3\x84z", 3, 1},
+ {ERE, "x.+z", "\xe2\x80\x94x.~\xe2\x80\x94\xf9\x81\x82\x83\x84z", 3, 1},
+ {ERE, "x.+z", "\xe2\x80\x94x\xfd\xbf\xbf\xbf\xbf\xbfz", 3, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94xz", -1, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94x\xc3\x96y\xc3\xa4z", -1, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94xyz", 3, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94x\xc3\x84\xe2\x80\x94z", 3, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94x\xe2\x80\x94z", 3, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94x\xf0\x9d\x80\x80\xc3\x84z", 3, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94x~\xe2\x80\x94z", 3, 1},
+ {ERE, "x.{1,2}z", "\xe2\x80\x94x\xfd\xbf\xbf\xbf\xbf\xbfz", 3, 1},
+ {ERE, "x(.w|\xc3\x86)?z", "axz", 1, 1},
+ {ERE, "x(.w|\xc3\x86)?z", "ax\xfd\xbf\xbf\xbf\xbf\xbfwz", 1, 1},
+ {ERE, "x(.w|\xc3\x86)?z", "ax\xc3\x86z", 1, 1},
+ {ERE, "x(.w|\xc3\x86)?z", "ax\xe2\x80\x96wz", 1, 1},
/* Should not be optimized. */
- {RE_SYNTAX_POSIX_BASIC, "x.y", "ax\xe2\x80\x94yz", 1, 0},
- {RE_SYNTAX_POSIX_BASIC, "x[\xc3\x84\xc3\xa4]y", "ax\xc3\xa4y", 1, 0},
- {RE_SYNTAX_POSIX_BASIC, "x[A-Z,]y", "axCy", 1, 0},
- {RE_SYNTAX_POSIX_BASIC, "x[^y]z", "ax\xe2\x80\x94z", 1, 0},
- {RE_SYNTAX_POSIX_BASIC, "x[[:alnum:]]z", "ax\xc3\x96z", 1, 0},
- {RE_SYNTAX_POSIX_BASIC, "x[[=A=]]z", "axAz", 1, 0},
- {RE_SYNTAX_POSIX_BASIC, "x[[=\xc3\x84=]]z", "ax\xc3\x84z", 1, 0},
- {RE_SYNTAX_POSIX_BASIC, "\\<g", "\xe2\x80\x94g", 3, 0},
- {RE_SYNTAX_POSIX_BASIC, "\\bg\\b", "\xe2\x80\x94g", 3, 0},
- {RE_SYNTAX_POSIX_BASIC, "\\Bg\\B", "\xc3\xa4g\xc3\xa4", 2, 0},
- {RE_SYNTAX_POSIX_BASIC, "a\\wz", "a\xc3\x84z", 0, 0},
- {RE_SYNTAX_POSIX_BASIC, "x\\Wz", "\xc3\x96x\xe2\x80\x94z", 2, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x.y", "ax\xe2\x80\x94yz", 1, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x[\xc3\x84\xc3\xa4]y", "ax\xc3\xa4y", 1, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x[A-Z,]y", "axCy", 1, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x[^y]z", "ax\xe2\x80\x94z", 1, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x[[:alnum:]]z", "ax\xc3\x96z", 1, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x[[=A=]]z", "axAz", 1, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x[[=\xc3\x84=]]z", "ax\xc3\x84z", 1, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "\\<g", "\xe2\x80\x94g", 3, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "\\bg\\b", "\xe2\x80\x94g", 3, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "\\Bg\\B", "\xc3\xa4g\xc3\xa4", 2, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "a\\wz", "a\xc3\x84z", 0, 0},
- {RE_SYNTAX_POSIX_EXTENDED, "x\\Wz", "\xc3\x96x\xe2\x80\x94z", 2, 0},
+ {BRE, "x[\xc3\x84\xc3\xa4]y", "ax\xc3\xa4y", 1, 0},
+ {BRE, "x[A-Z,]y", "axCy", 1, 0},
+ {BRE, "x[^y]z", "ax\xe2\x80\x94z", 1, 0},
+ {BRE, "x[[:alnum:]]z", "ax\xc3\x96z", 1, 0},
+ {BRE, "x[[=A=]]z", "axAz", 1, 0},
+ {BRE, "x[[=\xc3\x84=]]z", "ax\xc3\x84z", 1, 0},
+ {BRE, "\\<g", "\xe2\x80\x94g", 3, 0},
+ {BRE, "\\bg\\b", "\xe2\x80\x94g", 3, 0},
+ {BRE, "\\Bg\\B", "\xc3\xa4g\xc3\xa4", 2, 0},
+ {BRE, "a\\wz", "a\xc3\x84z", 0, 0},
+ {BRE, "x\\Wz", "\xc3\x96x\xe2\x80\x94z", 2, 0},
+ {ERE, "x[\xc3\x84\xc3\xa4]y", "ax\xc3\xa4y", 1, 0},
+ {ERE, "x[A-Z,]y", "axCy", 1, 0},
+ {ERE, "x[^y]z", "ax\xe2\x80\x94z", 1, 0},
+ {ERE, "x[[:alnum:]]z", "ax\xc3\x96z", 1, 0},
+ {ERE, "x[[=A=]]z", "axAz", 1, 0},
+ {ERE, "x[[=\xc3\x84=]]z", "ax\xc3\x84z", 1, 0},
+ {ERE, "\\<g", "\xe2\x80\x94g", 3, 0},
+ {ERE, "\\bg\\b", "\xe2\x80\x94g", 3, 0},
+ {ERE, "\\Bg\\B", "\xc3\xa4g\xc3\xa4", 2, 0},
+ {ERE, "a\\wz", "a\xc3\x84z", 0, 0},
+ {ERE, "x\\Wz", "\xc3\x96x\xe2\x80\x94z", 2, 0},
};
int
@@ -144,8 +221,8 @@ main (void)
ret = 1;
}
- res = re_search (&regbuf, tests[i].string, strlen (tests[i].string), 0,
- strlen (tests[i].string), NULL);
+ int str_len = strlen (tests[i].string);
+ res = re_search (&regbuf, tests[i].string, str_len, 0, str_len, NULL);
if (res != tests[i].res)
{
printf ("re_search %zd failed: %d\n", i, res);
@@ -153,6 +230,16 @@ main (void)
regfree (&regbuf);
continue;
}
+
+ res = re_search (&regbuf, tests[i].string, str_len, str_len, -str_len,
+ NULL);
+ if (res != tests[i].res)
+ {
+ printf ("backward re_search %zd failed: %d\n", i, res);
+ ret = 1;
+ regfree (&regbuf);
+ continue;
+ }
regfree (&regbuf);
re_set_syntax (tests[i].syntax | RE_ICASE);
@@ -175,15 +262,25 @@ main (void)
ret = 1;
}
- res = re_search (&regbuf, tests[i].string, strlen (tests[i].string), 0,
- strlen (tests[i].string), NULL);
+ res = re_search (&regbuf, tests[i].string, str_len, 0, str_len, NULL);
if (res != tests[i].res)
{
- printf ("re_search %zd failed: %d\n", i, res);
+ printf ("ICASE re_search %zd failed: %d\n", i, res);
ret = 1;
regfree (&regbuf);
continue;
}
+
+ /* XXX: This causes regex segfault. Disable for now.
+ res = re_search (&regbuf, tests[i].string, str_len, str_len, -str_len,
+ NULL);
+ if (res != tests[i].res)
+ {
+ printf ("ICASE backward re_search %zd failed: %d\n", i, res);
+ ret = 1;
+ regfree (&regbuf);
+ continue;
+ } */
regfree (&regbuf);
}