The string_slice inherits from array_slice and is used to refer to a
substring of an array that is memory managed elsewhere without modifying
the underlying array.
For example, this is useful in cases such as when needing to refer to a
substring of an attribute in the syntax tree.
This commit also adds some minimal helper functions for string_slice,
such as a strtok alternative, equality operators, strcmp, and a function
to strip whitespace from the beginning and end of a string_slice.
gcc/ChangeLog:
* vec.cc (string_slice::strtok): New method.
(strcmp): Add implementation for string_slice.
(string_slice::strip): New method.
(test_string_slice_initializers): New test.
(test_string_slice_strtok): Ditto.
(test_string_slice_strcmp): Ditto.
(test_string_slice_equality): Ditto.
(test_string_slice_invalid): Ditto.
(test_string_slice_strip): Ditto.
(vec_cc_tests): Add new tests.
* vec.h (class string_slice): New class.
(strcmp): Add implementation for string_slice.
---
gcc/vec.cc | 210 +++++++++++++++++++++++++++++++++++++++++++++++++++++
gcc/vec.h | 65 +++++++++++++++++
2 files changed, 275 insertions(+)
diff --git a/gcc/vec.cc b/gcc/vec.cc
index 55f5f3dd447..189cb492c7e 100644
--- a/gcc/vec.cc
+++ b/gcc/vec.cc
@@ -176,6 +176,61 @@ dump_vec_loc_statistics (void)
vec_mem_desc.dump (VEC_ORIGIN);
}
+string_slice
+string_slice::tokenize (string_slice *str, string_slice delims)
+{
+ const char *ptr = str->begin ();
+
+ gcc_assert (str->is_valid () && delims.is_valid ());
+
+ for (; ptr < str->end (); ptr++)
+ for (char c : delims)
+ if (*ptr == c)
+ {
+ /* Update the input string to be the remaining string. */
+ const char* str_begin = str->begin ();
+ *str = string_slice (ptr + 1, str->end ());
+ return string_slice (str_begin, ptr);
+ }
+
+ /* If no deliminators between the start and end, return the whole string. */
+ string_slice res = *str;
+ *str = string_slice::invalid ();
+ return res;
+}
+
+int
+strcmp (string_slice str1, string_slice str2)
+{
+ for (unsigned int i = 0; i < str1.size () && i < str2.size (); i++)
+ {
+ if (str1[i] < str2[i])
+ return -1;
+ if (str1[i] > str2[i])
+ return 1;
+ }
+
+ if (str1.size () < str2.size ())
+ return -1;
+ if (str1.size () > str2.size ())
+ return 1;
+ return 0;
+}
+
+string_slice
+string_slice::strip ()
+{
+ const char *start = this->begin ();
+ const char *end = this->end ();
+
+ while (start < end && ISSPACE (*start))
+ start++;
+ while (end > start && ISSPACE (*(end-1)))
+ end--;
+
+ return string_slice (start, end-start);
+}
+
#if CHECKING_P
/* Report qsort comparator CMP consistency check failure with P1, P2, P3 as
witness elements. */
@@ -584,6 +639,154 @@ test_auto_alias ()
ASSERT_EQ (val, 0);
}
+static void
+test_string_slice_initializers ()
+{
+ string_slice str1 = string_slice ();
+ ASSERT_TRUE (str1.is_valid ());
+ ASSERT_EQ (str1.size (), 0);
+
+ string_slice str2 = string_slice ("Test string");
+ ASSERT_TRUE (str2.is_valid ());
+ ASSERT_EQ (str2.size (), 11);
+
+ string_slice str3 = string_slice ("Test string", 4);
+ ASSERT_TRUE (str3.is_valid ());
+ ASSERT_EQ (str3.size (), 4);
+}
+
+static void
+test_string_slice_tokenize ()
+{
+ string_slice test_string_slice = string_slice ("");
+ string_slice test_delims = string_slice (",");
+
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_FALSE (test_string_slice.is_valid ());
+
+ test_string_slice = string_slice (",");
+ test_delims = string_slice (",");
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_FALSE (test_string_slice.is_valid ());
+
+ test_string_slice = string_slice (",test.,.test, , test ");
+ test_delims = string_slice (",.");
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice ("test"));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice ("test"));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (" "));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (" test "));
+ ASSERT_FALSE (test_string_slice.is_valid ());
+
+ const char *test_string
+ = "This is the test string, it \0 is for testing, 123 ,,";
+ test_string_slice = string_slice (test_string, 52);
+ test_delims = string_slice (",\0", 2);
+
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice ("This is the test string"));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (" it "));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (" is for testing"));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (" 123 "));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_EQ (string_slice::tokenize (&test_string_slice, test_delims),
+ string_slice (""));
+ ASSERT_FALSE (test_string_slice.is_valid ());
+}
+
+static void
+test_string_slice_strcmp ()
+{
+ ASSERT_EQ (strcmp (string_slice (), string_slice ()), 0);
+ ASSERT_EQ (strcmp (string_slice ("test"), string_slice ()), 1);
+ ASSERT_EQ (strcmp (string_slice (), string_slice ("test")), -1);
+ ASSERT_EQ (strcmp (string_slice ("test"), string_slice ("test")), 0);
+ ASSERT_EQ (strcmp (string_slice ("a"), string_slice ("b")), -1);
+ ASSERT_EQ (strcmp (string_slice ("b"), string_slice ("a")), 1);
+ ASSERT_EQ (strcmp (string_slice ("ab", 1), string_slice ("a")), 0);
+ ASSERT_EQ (strcmp (string_slice ("ab", 2), string_slice ("a")), 1);
+}
+
+static void
+test_string_slice_equality ()
+{
+ ASSERT_TRUE (string_slice () == string_slice ());
+ ASSERT_FALSE (string_slice ("test") == string_slice ());
+ ASSERT_FALSE ("test" == string_slice ());
+ ASSERT_FALSE (string_slice () == string_slice ("test"));
+ ASSERT_FALSE (string_slice () == "test");
+ ASSERT_TRUE (string_slice ("test") == string_slice ("test"));
+ ASSERT_TRUE ("test" == string_slice ("test"));
+ ASSERT_TRUE (string_slice ("test") == "test");
+ ASSERT_FALSE (string_slice ("a") == string_slice ("b"));
+ ASSERT_FALSE ("a" == string_slice ("b"));
+ ASSERT_FALSE (string_slice ("a") == "b");
+ ASSERT_FALSE (string_slice ("b") == string_slice ("a"));
+ ASSERT_TRUE (string_slice ("ab", 1) == string_slice ("a"));
+ ASSERT_TRUE (string_slice ("ab", 1) == "a");
+ ASSERT_FALSE (string_slice ("ab", 2) == string_slice ("a"));
+ ASSERT_FALSE (string_slice ("ab", 2) == "a");
+}
+
+static void
+test_string_slice_inequality ()
+{
+ ASSERT_FALSE (string_slice () != string_slice ());
+ ASSERT_TRUE (string_slice ("test") != string_slice ());
+ ASSERT_TRUE ("test" != string_slice ());
+ ASSERT_TRUE (string_slice () != string_slice ("test"));
+ ASSERT_TRUE (string_slice () != "test");
+ ASSERT_FALSE (string_slice ("test") != string_slice ("test"));
+ ASSERT_FALSE ("test" != string_slice ("test"));
+ ASSERT_FALSE (string_slice ("test") != "test");
+ ASSERT_TRUE (string_slice ("a") != string_slice ("b"));
+ ASSERT_TRUE ("a" != string_slice ("b"));
+ ASSERT_TRUE (string_slice ("a") != "b");
+ ASSERT_TRUE (string_slice ("b") != string_slice ("a"));
+ ASSERT_FALSE (string_slice ("ab", 1) != string_slice ("a"));
+ ASSERT_FALSE (string_slice ("ab", 1) != "a");
+ ASSERT_TRUE (string_slice ("ab", 2) != string_slice ("a"));
+ ASSERT_TRUE (string_slice ("ab", 2) != "a");
+}
+
+static void
+test_string_slice_invalid ()
+{
+ ASSERT_FALSE (string_slice::invalid ().is_valid ());
+ ASSERT_FALSE (string_slice (NULL, 1).is_valid ());
+ ASSERT_TRUE (string_slice (NULL, (size_t) 0).is_valid ());
+ ASSERT_TRUE (string_slice ("Test", (size_t) 0).is_valid ());
+ ASSERT_TRUE (string_slice ().is_valid ());
+}
+
+static void
+test_string_slice_strip ()
+{
+ ASSERT_EQ (string_slice (" test ").strip (), string_slice ("test"));
+ ASSERT_EQ (string_slice ("\t test string\t \n ").strip (),
+ string_slice ("test string"));
+ ASSERT_EQ (string_slice ("test").strip (), string_slice ("test"));
+ ASSERT_EQ (string_slice ().strip (), string_slice ());
+ ASSERT_EQ (string_slice ("\t \n \t ").strip (), string_slice ());
+}
+
/* Run all of the selftests within this file. */
void
@@ -604,6 +807,13 @@ vec_cc_tests ()
test_reverse ();
test_auto_delete_vec ();
test_auto_alias ();
+ test_string_slice_initializers ();
+ test_string_slice_tokenize ();
+ test_string_slice_strcmp ();
+ test_string_slice_equality ();
+ test_string_slice_inequality ();
+ test_string_slice_invalid ();
+ test_string_slice_strip ();
}
} // namespace selftest
diff --git a/gcc/vec.h b/gcc/vec.h
index 915df06f03e..d709d339d40 100644
--- a/gcc/vec.h
+++ b/gcc/vec.h
@@ -2484,4 +2484,69 @@ make_array_slice (T *base, unsigned int size)
# pragma GCC poison m_vec m_vecpfx m_vecdata
#endif
+/* string_slice inherits from array_slice, specifically to refer to a substring
+ of a character array.
+ It includes some string like helpers. */
+class string_slice : public array_slice<const char>
+{
+public:
+ explicit string_slice () : array_slice<const char> () {}
+ explicit string_slice (const char *str) : array_slice (str, strlen (str)) {}
+ explicit string_slice (const char *str, size_t len) :
+ array_slice (str, len) {}
+ explicit string_slice (const char *start, const char *end) :
+ array_slice (start, end-start) {}
+
+ friend bool operator== (const string_slice &lhs, const string_slice &rhs)
+ {
+ if (!lhs.is_valid () || !rhs.is_valid ())
+ return false;
+ if (lhs.size () != rhs.size ())
+ return false;
+ return memcmp (lhs.begin (), rhs.begin (), lhs.size ()) == 0;
+ }
+
+ friend bool operator== (const char *lhs, const string_slice &rhs)
+ {
+ return string_slice (lhs) == rhs;
+ }
+
+ friend bool operator== (const string_slice &lhs, const char *rhs)
+ {
+ return lhs == string_slice (rhs);
+ }
+
+ friend bool operator!= (const string_slice &lhs, const string_slice &rhs)
+ {
+ return !(lhs == rhs);
+ }
+
+ friend bool operator!= (const char *lhs, const string_slice &rhs)
+ {
+ return !(string_slice (lhs) == rhs);
+ }
+
+ friend bool operator!= (const string_slice &lhs, const char *rhs)
+ {
+ return !(lhs == string_slice (rhs));
+ }
+
+ /* Returns an invalid string_slice. */
+ static string_slice invalid ()
+ {
+ return string_slice (nullptr, ~0U);
+ }
+
+ /* tokenize is used to split a string by some deliminator into
+ strtok_slice's. Similarly to the posix strtok_r.but without modifying the
+ input string, and returning all tokens which may be empty in the case
+ of an empty input string of consecutive deliminators. */
+ static string_slice tokenize (string_slice *str, string_slice delims);
+
+ /* Removes white space from the front and back of the string_slice. */
+ string_slice strip ();
+};
+
+int strcmp (string_slice str1, string_slice str2);
+
#endif // GCC_VEC_H
