utils: add regex-split

lib/utils/mu-utils.cc

@@ -39,6 +39,7 @@
 #include <cinttypes>
 #include <charconv>
 #include <limits>
+#include <regex>
 
 #include <glib.h>
 #include <glib/gprintf.h>
@@ -142,8 +143,6 @@ Mu::utf8_flatten(const char* str)
 }
 
 
-
-
 /* turn \0-terminated buf into ascii (which is a utf8 subset); convert
  *   any non-ascii into '.'
  */
@@ -162,7 +161,6 @@ asciify_in_place (char *buf)
 	return buf;
 }
 
-
 static char*
 utf8ify (const char *buf)
 {
@@ -245,7 +243,6 @@ Mu::split(const std::string& str, const std::string& sepa)
 std::vector<std::string>
 Mu::split(const std::string& str, char sepa)
 {
-
 	std::vector<std::string> vec;
 	size_t b = 0, e = 0;
 
@@ -266,6 +263,14 @@ Mu::split(const std::string& str, char sepa)
 	return vec;
 }
 
+std::vector<std::string>
+Mu::split(const std::string& str, const std::regex& sepa_rx)
+{
+	std::sregex_token_iterator it(str.begin(), str.end(), sepa_rx, -1);
+	std::sregex_token_iterator end;
+
+	return {it, end};
+}
 
 std::string
 Mu::join(const std::vector<std::string>& svec, const std::string& sepa)

lib/utils/mu-utils.hh

@@ -33,6 +33,7 @@
 #include <type_traits>
 #include <algorithm>
 #include <numeric>
+#include <regex>
 
 #include "mu-utils-format.hh"
 #include "mu-option.hh"
@@ -85,7 +86,6 @@ std::string remove_ctrl(const std::string& str);
  */
 std::vector<std::string> split(const std::string& str, const std::string& sepa);
 
-
 /**
  * Split a string in parts. As a special case, splitting an empty string
  * yields an empty vector (not a vector with a single empty element)
@@ -97,6 +97,15 @@ std::vector<std::string> split(const std::string& str, const std::string& sepa);
  */
 std::vector<std::string> split(const std::string& str, char sepa);
 
+/**
+ * Split a string in parts
+ *
+ * @param str a string
+ * @param sepa the separator regex
+ *
+ * @return the parts.
+ */
+std::vector<std::string> split(const std::string& str, const std::regex& sepa_rx);
 
 /**
  * Join the strings in svec into a string, separated by sepa

lib/utils/tests/test-utils.cc

@@ -208,7 +208,7 @@ test_split()
 			g_assert_cmpstr(sv1[i].c_str(),==,sv2[i].c_str());
 	};
 
-
+	// string sepa
 	assert_equal_svec(split("axbxc", "x"), {"a", "b", "c"});
 	assert_equal_svec(split("axbxcx", "x"), {"a", "b", "c", ""});
 	assert_equal_svec(split("", "boo"), {});
@@ -216,10 +216,12 @@ test_split()
 	assert_equal_svec(split("abc", ""), {"a", "b", "c"});
 	assert_equal_svec(split("", "boo"), {});
 
-
+	// char sepa
 	assert_equal_svec(split("axbxc", 'x'), {"a", "b", "c"});
 	assert_equal_svec(split("axbxcx", 'x'), {"a", "b", "c", ""});
-	assert_equal_svec(split("", "boo"), {});
+
+	// rx sexp
+	assert_equal_svec(split("axbyc", std::regex("[xy]")), {"a", "b", "c"});
 }
 
 static void