[v11,3/3] posix: add test for REG_STARTEND

Message ID ead3a98b18e30df03c3d1efc74812b8ae4889cac.1692534920.git.nabijaczleweli@nabijaczleweli.xyz
State New
Headers
Series [v11,1/3] posix: regcomp(): clear RE_DOT_NOT_NULL |

Checks

Context Check Description
redhat-pt-bot/TryBot-apply_patch success Patch applied to master at the time it was sent
redhat-pt-bot/TryBot-32bit success Build for i686
linaro-tcwg-bot/tcwg_glibc_build--master-arm success Testing passed
linaro-tcwg-bot/tcwg_glibc_build--master-aarch64 success Testing passed
linaro-tcwg-bot/tcwg_glibc_check--master-arm success Testing passed
linaro-tcwg-bot/tcwg_glibc_check--master-aarch64 success Testing passed

Commit Message

Ahelenia Ziemiańska Aug. 20, 2023, 12:38 p.m. UTC
  This test passes on NetBSD, the illumos gate, musl with
https://www.openwall.com/lists/musl/2023/05/14/1,
and now glibc.
It's nothing revolutionary and the behaviour it tests
is largely guaranteed by the 4.4BSD-Lite manual;
nevertheless, it used to fail with
  tst-reg-startend.c: ^a: a^@c: no match$
  tst-reg-startend.c: ^a: a^@c: wanted {1, 2}, got {1, 4}$
  tst-reg-startend.c: ^a: abc: no match$
  tst-reg-startend.c: ^a: abc: wanted {1, 2}, got {1, 4}$
  tst-reg-startend.c: ^a.c$: a^@c: no match$
  tst-reg-startend.c: ^a.c$: abc: no match$
  tst-reg-startend.c: ^a.*c$: a^@c: no match$
  tst-reg-startend.c: ^a.*c$: abc: no match$
  tst-reg-startend.c: ^a[^c]c$: a^@c: no match$
  tst-reg-startend.c: ^a[^c]c$: abc: no match$
  tst-reg-startend.c: ^a..: a^@c: no match$
  tst-reg-startend.c: ^a..: abc: no match$
  tst-reg-startend.c: ..c: a^@c: no match$

Signed-off-by: Ahelenia Ziemiańska <nabijaczleweli@nabijaczleweli.xyz>
---
 posix/Makefile           |   1 +
 posix/tst-reg-startend.c | 142 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 143 insertions(+)
 create mode 100644 posix/tst-reg-startend.c
  

Patch

diff --git a/posix/Makefile b/posix/Makefile
index 3d368b91f6..84baa70c48 100644
--- a/posix/Makefile
+++ b/posix/Makefile
@@ -305,6 +305,7 @@  tests := \
   tst-posix_spawn-setsid \
   tst-preadwrite \
   tst-preadwrite64 \
+  tst-reg-startend \
   tst-regcomp-truncated \
   tst-regex \
   tst-regex2 \
diff --git a/posix/tst-reg-startend.c b/posix/tst-reg-startend.c
new file mode 100644
index 0000000000..854d430676
--- /dev/null
+++ b/posix/tst-reg-startend.c
@@ -0,0 +1,142 @@ 
+/* This is free and unencumbered software released into the public domain.
+
+   Anyone is free to copy, modify, publish, use, compile, sell, or
+   distribute this software, either in source code form or as a compiled
+   binary, for any purpose, commercial or non-commercial, and by any
+   means.
+
+   In jurisdictions that recognize copyright laws, the author or authors
+   of this software dedicate any and all copyright interest in the
+   software to the public domain. We make this dedication for the benefit
+   of the public at large and to the detriment of our heirs and
+   successors. We intend this dedication to be an overt act of
+   relinquishment in perpetuity of all present and future rights to this
+   software under copyright law.
+
+   THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+   EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+   MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+   IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+   OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+   ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+   OTHER DEALINGS IN THE SOFTWARE.  */
+
+
+#include <assert.h>
+#include <locale.h>
+#include <string.h>
+#include <regex.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <support/check.h>
+
+
+static const regmatch_t bound = {1, 4};
+
+
+struct reg_res {
+  const char *regex;
+  regmatch_t result;
+};
+static const struct reg_res reg_res_ac[] = {
+  {"^a",       {1, 2}},
+  {"c$",       {3, 4}},
+  {"^a.c$",    {1, 4}},
+  {"^a.*c$",   {1, 4}},
+  {"^a[^c]c$", {1, 4}},
+  {"^a..",     {1, 4}},
+  {"..c",      {1, 4}},
+  {"[^z]c",    {2, 4}},
+  {}
+};
+static const char *const data_ac[] = {"_a\0cdef", "_abcdef", NULL};
+
+static const struct reg_res reg_res_aa[] = {
+  {"^",             {1, 1}},
+  {"^a",            {1, 2}},
+  {"a$",            {3, 4}},
+  {"^\\(a\\).\\1$", {1, 4}},
+  {"^a[^a]*" ,      {1, 3}},
+  {}
+};
+static const char *const data_aa[] = {"_a\0adef", "_abadef", NULL};
+
+
+static void
+testbunch (const struct reg_res *reg_reses, const char *const *const data)
+{
+#define BASEERR(data)                                      \
+  support_record_failure (),                               \
+    fprintf (stdout, __FILE__ ": %s: ", reg_reses->regex), \
+    fwrite (data + bound.rm_so, 1, bound.rm_eo - bound.rm_so, stdout)
+
+  for (; reg_reses->regex; ++reg_reses)
+    {
+      regex_t rgx;
+      assert (!regcomp (&rgx, reg_reses->regex, 0));
+
+      for (const char *const *dt = data; *dt; ++dt)
+        {
+          regmatch_t match = bound;
+          if (regexec (&rgx, *dt, 1, &match, REG_STARTEND))
+            BASEERR(dt), fputs (": no match\n", stdout);
+
+          if (memcmp(&match, &reg_reses->result, sizeof (regmatch_t)))
+            BASEERR(dt), fprintf (stdout, ": wanted {%d, %d}, got {%d, %d}\n",
+                                  (int)reg_reses->result.rm_so,
+                                  (int)reg_reses->result.rm_eo,
+                                  (int)match.rm_so, (int)match.rm_eo);
+        }
+
+      regfree(&rgx);
+    }
+}
+
+
+struct mb_data_exp {
+  const char *data;
+  bool exp;
+};
+static const struct mb_data_exp mb_data_exp[] = {
+  {"_aaćdef", false},
+  {"_aćdef", true},
+  {}
+};
+
+static void
+testmb (void)
+{
+  regex_t rgx;
+  const struct reg_res reg_reses[] = {{"ać"}};
+  assert (!regcomp (&rgx, reg_reses->regex, 0));
+
+  for (const struct mb_data_exp *de = mb_data_exp; de->data; ++de)
+    {
+      regmatch_t match = bound;
+      if (regexec (&rgx, de->data, 1, &match, REG_STARTEND) == de->exp)
+        BASEERR(de->data), fprintf (stdout, ": %s match\n",
+                                    de->exp ? "no" : "yes");
+
+      if (memcmp(&match, &bound, sizeof (regmatch_t)))
+        BASEERR(de->data), fprintf (stdout, ": wanted {%d, %d}, got {%d, %d}\n",
+                                    (int)bound.rm_so, (int)bound.rm_eo,
+                                    (int)match.rm_so, (int)match.rm_eo);
+    }
+
+  regfree(&rgx);
+}
+
+
+static int
+do_test (void)
+{
+  assert (setlocale (LC_ALL, "C.UTF-8"));
+
+  testbunch (reg_res_ac, data_ac);
+  testbunch (reg_res_aa, data_aa);
+  testmb ();
+  return 0;
+}
+
+
+#include <support/test-driver.c>