[Patch, regex, libstdc++/69794] Unify special character parsing

[Tim Shen]

I did it wrong in r227289 - I ignored the "\n" special case in grep.
Turns out using code to handle special cases is error prone, so I
turned to use data (_M_grep_spec_char and _M_egrep_spec_char).

Bootstrapped and tested on x86_64-pc-linux-gnu.

Thanks!

-- 
Regards,
Tim Shen

commit 03e651ef56e516f1bc7b0d041d93ef657af54791
Author: Tim Shen <tims...@google.com>
Date:   Sat Feb 13 10:55:38 2016 -0800

        PR libstdc++/69794
        * include/bits/regex_scanner.h: Add different special character
        sets for grep and egrep regex.
        * include/bits/regex_scanner.tcc: Use _M_spec_char more unifiedly.
        * testsuite/28_regex/regression.cc: Add new testcase.

diff --git a/libstdc++-v3/include/bits/regex_scanner.h 
b/libstdc++-v3/include/bits/regex_scanner.h
index bff7366..16071da 100644
--- a/libstdc++-v3/include/bits/regex_scanner.h
+++ b/libstdc++-v3/include/bits/regex_scanner.h
@@ -95,11 +95,19 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
                  : _M_awk_escape_tbl),
     _M_spec_char(_M_is_ecma()
                 ? _M_ecma_spec_char
-                : _M_is_basic()
+                : _M_flags & regex_constants::basic
                 ? _M_basic_spec_char
-                : _M_extended_spec_char),
+                : _M_flags & regex_constants::extended
+                ? _M_extended_spec_char
+                : _M_flags & regex_constants::grep
+                ? _M_grep_spec_char
+                : _M_flags & regex_constants::egrep
+                ? _M_egrep_spec_char
+                : _M_flags & regex_constants::awk
+                ? _M_extended_spec_char
+                : nullptr),
     _M_at_bracket_start(false)
-    { }
+    { __glibcxx_assert(_M_spec_char); }
 
   protected:
     const char*
@@ -177,6 +185,8 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
     const char* _M_ecma_spec_char = "^$\\.*+?()[]{}|";
     const char* _M_basic_spec_char = ".[\\*^$";
     const char* _M_extended_spec_char = ".[\\()*+?{|^$";
+    const char* _M_grep_spec_char = ".[\\*^$\n";
+    const char* _M_egrep_spec_char = ".[\\()*+?{|^$\n";
 
     _StateT                       _M_state;
     _FlagT                        _M_flags;
diff --git a/libstdc++-v3/include/bits/regex_scanner.tcc 
b/libstdc++-v3/include/bits/regex_scanner.tcc
index 920cb14..fedba09 100644
--- a/libstdc++-v3/include/bits/regex_scanner.tcc
+++ b/libstdc++-v3/include/bits/regex_scanner.tcc
@@ -97,9 +97,8 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
     _M_scan_normal()
     {
       auto __c = *_M_current++;
-      const char* __pos;
 
-      if (std::strchr(_M_spec_char, _M_ctype.narrow(__c, '\0')) == nullptr)
+      if (std::strchr(_M_spec_char, _M_ctype.narrow(__c, ' ')) == nullptr)
        {
          _M_token = _S_token_ord_char;
          _M_value.assign(1, __c);
@@ -177,12 +176,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
          _M_state = _S_state_in_brace;
          _M_token = _S_token_interval_begin;
        }
-      else if (((__pos = std::strchr(_M_spec_char, _M_ctype.narrow(__c, '\0')))
-                 != nullptr
-               && *__pos != '\0'
-               && __c != ']'
-               && __c != '}')
-              || (_M_is_grep() && __c == '\n'))
+      else if (__c != ']' && __c != '}')
        {
          auto __it = _M_token_tbl;
          auto __narrowc = _M_ctype.narrow(__c, '\0');
diff --git a/libstdc++-v3/testsuite/28_regex/regression.cc 
b/libstdc++-v3/testsuite/28_regex/regression.cc
index f95bef9..c9a3402 100644
--- a/libstdc++-v3/testsuite/28_regex/regression.cc
+++ b/libstdc++-v3/testsuite/28_regex/regression.cc
@@ -33,10 +33,26 @@ test01()
   regex re("((.)", regex_constants::basic);
 }
 
+void
+test02()
+{
+  bool test __attribute__((unused)) = true;
+
+  std::string re_str
+    {
+      "/abcd" "\n"
+      "/aecf" "\n"
+      "/ghci"
+    };
+  auto rx = std::regex(re_str, std::regex_constants::grep | 
std::regex_constants::icase);
+  VERIFY(std::regex_search("/abcd", rx));
+}
+
 int
 main()
 {
   test01();
+  test02();
   return 0;
 }