From f19e75b60646781a818359414750a1b11583a198 Mon Sep 17 00:00:00 2001
From: frosch <frosch@openttd.org>
Date: Tue, 1 Apr 2025 18:21:03 +0200
Subject: [PATCH] Codechange: Use Utf8View in Utf8StringLength.

---
 src/string.cpp     | 19 +++----------------
 src/string_func.h  |  3 +--
 src/tests/utf8.cpp | 12 ++++++++++++
 src/textbuf.cpp    |  2 +-
 4 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/src/string.cpp b/src/string.cpp
index 6eec0604f6..3224a96a7a 100644
--- a/src/string.cpp
+++ b/src/string.cpp
@@ -389,23 +389,10 @@ bool StrContainsIgnoreCase(const std::string_view str, const std::string_view va
  * @param s The string to get the length for.
  * @return The length of the string in characters.
  */
-size_t Utf8StringLength(const char *s)
+size_t Utf8StringLength(std::string_view str)
 {
-	size_t len = 0;
-	const char *t = s;
-	while (Utf8Consume(&t) != 0) len++;
-	return len;
-}
-
-/**
- * Get the length of an UTF-8 encoded string in number of characters
- * and thus not the number of bytes that the encoded string contains.
- * @param s The string to get the length for.
- * @return The length of the string in characters.
- */
-size_t Utf8StringLength(const std::string &str)
-{
-	return Utf8StringLength(str.c_str());
+	Utf8View view(str);
+	return std::distance(view.begin(), view.end());
 }
 
 bool strtolower(std::string &str, std::string::size_type offs)
diff --git a/src/string_func.h b/src/string_func.h
index 68fd80b45f..7a37952a6e 100644
--- a/src/string_func.h
+++ b/src/string_func.h
@@ -174,8 +174,7 @@ inline std::string::iterator Utf8PrevChar(std::string::iterator &s)
 	return cur;
 }
 
-size_t Utf8StringLength(const char *s);
-size_t Utf8StringLength(const std::string &str);
+size_t Utf8StringLength(std::string_view str);
 
 /**
  * Is the given character a lead surrogate code point?
diff --git a/src/tests/utf8.cpp b/src/tests/utf8.cpp
index c8ff3a191a..1429fd6283 100644
--- a/src/tests/utf8.cpp
+++ b/src/tests/utf8.cpp
@@ -95,6 +95,8 @@ TEST_CASE("Utf8View - iterate")
 	auto it = begin;
 	CHECK(it == begin);
 	CHECK(it.GetByteOffset() == 0);
+	CHECK(std::distance(begin, it) == 0);
+	CHECK(std::distance(it, end) == 5);
 	CHECK(*it == 0x1234);
 	CHECK(it == view.GetIterAtByte(0));
 	CHECK(it == view.GetIterAtByte(1));
@@ -103,20 +105,28 @@ TEST_CASE("Utf8View - iterate")
 	CHECK(begin < it);
 	CHECK(it < end);
 	CHECK(it.GetByteOffset() == 3);
+	CHECK(std::distance(begin, it) == 1);
+	CHECK(std::distance(it, end) == 4);
 	CHECK(*it == 'a');
 	CHECK(it == view.GetIterAtByte(3));
 	++it;
 	CHECK(it.GetByteOffset() == 4);
+	CHECK(std::distance(begin, it) == 2);
+	CHECK(std::distance(it, end) == 3);
 	CHECK(*it == 0);
 	CHECK(it == view.GetIterAtByte(4));
 	++it;
 	CHECK(it.GetByteOffset() == 5);
+	CHECK(std::distance(begin, it) == 3);
+	CHECK(std::distance(it, end) == 2);
 	CHECK(*it == 'b');
 	CHECK(it == view.GetIterAtByte(5));
 	++it;
 	CHECK(begin < it);
 	CHECK(it < end);
 	CHECK(it.GetByteOffset() == 6);
+	CHECK(std::distance(begin, it) == 4);
+	CHECK(std::distance(it, end) == 1);
 	CHECK(*it == 0x00012345);
 	CHECK(it == view.GetIterAtByte(6));
 	CHECK(it == view.GetIterAtByte(7));
@@ -125,6 +135,8 @@ TEST_CASE("Utf8View - iterate")
 	++it;
 	CHECK(begin < it);
 	CHECK(it.GetByteOffset() == 10);
+	CHECK(std::distance(begin, it) == 5);
+	CHECK(std::distance(it, end) == 0);
 	CHECK(it == end);
 	CHECK(it == view.GetIterAtByte(10));
 	--it;
diff --git a/src/textbuf.cpp b/src/textbuf.cpp
index eae281cb89..f41023b966 100644
--- a/src/textbuf.cpp
+++ b/src/textbuf.cpp
@@ -444,7 +444,7 @@ void Textbuf::Assign(const std::string_view text)
  */
 void Textbuf::UpdateSize()
 {
-	this->chars = static_cast<uint16_t>(Utf8StringLength(this->buf.c_str()) + 1); // terminating zero
+	this->chars = static_cast<uint16_t>(Utf8StringLength(this->buf) + 1); // terminating zero
 	assert(this->buf.size() < this->max_bytes);
 	assert(this->chars <= this->max_chars);