[libcxx-commits] [libcxx] [libc++][regex] Correctly adjust match prefix for zero-length matches. (PR #94550)

[Konstantin Varlamov via libcxx-commits]

================
@@ -17,102 +17,149 @@
 #include <iterator>
 #include "test_macros.h"
 
-int main(int, char**)
-{
-    {
-        std::regex phone_numbers("\\d{3}-\\d{4}");
-        const char phone_book[] = "555-1234, 555-2345, 555-3456";
-        std::cregex_iterator i(std::begin(phone_book), std::end(phone_book), phone_numbers);
-        std::cregex_iterator i2 = i;
-        assert(i != std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i).size() == 1);
-        assert((*i).position() == 0);
-        assert((*i).str() == "555-1234");
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-        i++;
-        assert(i != std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i).size() == 1);
-        assert((*i).position() == 10);
-        assert((*i).str() == "555-2345");
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-        i++;
-        assert(i != std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i).size() == 1);
-        assert((*i).position() == 20);
-        assert((*i).str() == "555-3456");
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-        i++;
-        assert(i == std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-    }
-    {
-        std::regex phone_numbers("\\d{3}-\\d{4}");
-        const char phone_book[] = "555-1234, 555-2345, 555-3456";
-        std::cregex_iterator i(std::begin(phone_book), std::end(phone_book), phone_numbers);
-        std::cregex_iterator i2 = i;
-        assert(i != std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i).size() == 1);
-        assert((*i).position() == 0);
-        assert((*i).str() == "555-1234");
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-        ++i;
-        assert(i != std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i).size() == 1);
-        assert((*i).position() == 10);
-        assert((*i).str() == "555-2345");
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-        ++i;
-        assert(i != std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i).size() == 1);
-        assert((*i).position() == 20);
-        assert((*i).str() == "555-3456");
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-        ++i;
-        assert(i == std::cregex_iterator());
-        assert(i2!= std::cregex_iterator());
-        assert((*i2).size() == 1);
-        assert((*i2).position() == 0);
-        assert((*i2).str() == "555-1234");
-    }
-    { // https://llvm.org/PR33681
-        std::regex rex(".*");
-        const char foo[] = "foo";
+int main(int, char**) {
+  {
+    std::regex phone_numbers("\\d{3}-\\d{4}");
+    const char phone_book[] = "555-1234, 555-2345, 555-3456";
+    std::cregex_iterator i(std::begin(phone_book), std::end(phone_book), phone_numbers);
+    std::cregex_iterator i2 = i;
+    assert(i != std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i).size() == 1);
+    assert((*i).position() == 0);
+    assert((*i).str() == "555-1234");
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+    i++;
+    assert(i != std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i).size() == 1);
+    assert((*i).position() == 10);
+    assert((*i).str() == "555-2345");
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+    i++;
+    assert(i != std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i).size() == 1);
+    assert((*i).position() == 20);
+    assert((*i).str() == "555-3456");
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+    i++;
+    assert(i == std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+  }
+  {
+    std::regex phone_numbers("\\d{3}-\\d{4}");
+    const char phone_book[] = "555-1234, 555-2345, 555-3456";
+    std::cregex_iterator i(std::begin(phone_book), std::end(phone_book), phone_numbers);
+    std::cregex_iterator i2 = i;
+    assert(i != std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i).size() == 1);
+    assert((*i).position() == 0);
+    assert((*i).str() == "555-1234");
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+    ++i;
+    assert(i != std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i).size() == 1);
+    assert((*i).position() == 10);
+    assert((*i).str() == "555-2345");
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+    ++i;
+    assert(i != std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i).size() == 1);
+    assert((*i).position() == 20);
+    assert((*i).str() == "555-3456");
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+    ++i;
+    assert(i == std::cregex_iterator());
+    assert(i2 != std::cregex_iterator());
+    assert((*i2).size() == 1);
+    assert((*i2).position() == 0);
+    assert((*i2).str() == "555-1234");
+  }
+  { // https://llvm.org/PR33681
+    std::regex rex(".*");
+    const char foo[] = "foo";
     //  The -1 is because we don't want the implicit null from the array.
-        std::cregex_iterator i(std::begin(foo), std::end(foo) - 1, rex);
-        std::cregex_iterator e;
-        assert(i != e);
-        assert((*i).size() == 1);
-        assert((*i).str() == "foo");
-
-        ++i;
-        assert(i != e);
-        assert((*i).size() == 1);
-        assert((*i).str() == "");
-
-        ++i;
-        assert(i == e);
-    }
+    std::cregex_iterator i(std::begin(foo), std::end(foo) - 1, rex);
+    std::cregex_iterator e;
+    assert(i != e);
+    assert((*i).size() == 1);
+    assert((*i).str() == "foo");
+
+    ++i;
+    assert(i != e);
+    assert((*i).size() == 1);
+    assert((*i).str() == "");
+
+    ++i;
+    assert(i == e);
+  }
+
+  {
+    // Check that we correctly adjust the match prefix when dealing with zero-length matches -- this is explicitly
+    // required by the Standard ([re.regiter.incr]: "In all cases in which the call to `regex_search` returns true,
+    // `match.prefix().first` shall be equal to the previous value of `match[0].second`"). For a pattern that matches
+    // empty sequences, there is an implicit zero-length match between every character in a string -- make sure the
+    // prefix of each of these matches (except the first one) is the preceding character.
+
+    auto validate = [](const std::regex& empty_matching_pattern) {
----------------
var-const wrote:

Update: I actually didn't realize we support `<regex>` in the C++03 mode. Would you prefer to change this to a helper function, or to make the test C++11 and above? (perhaps split into a separate file)

https://github.com/llvm/llvm-project/pull/94550