From 1c9816d3b6653ea915810e883da9dd3e5e2e77b8 Mon Sep 17 00:00:00 2001
From: "Rob Swindell (on Windows 11)" <rob@synchro.net>
Date: Thu, 15 Feb 2024 21:24:53 -0800
Subject: [PATCH] Create utf8_strlcpy() which does a "safe" truncated-string
copy
(doesn't leave a partial UTF-8 sequence at the end of the destination string).
This calls memcpy() for every char, which may not be performant, but I didn't
(yet) do any profiling. Hence, no premature optimization either.
---
src/encode/utf8.c | 22 ++++++++++++++++++++++
src/encode/utf8.h | 3 +++
2 files changed, 25 insertions(+)
diff --git a/src/encode/utf8.c b/src/encode/utf8.c
index 56c5bd710f..20bae23fdd 100644
--- a/src/encode/utf8.c
+++ b/src/encode/utf8.c
@@ -224,6 +224,28 @@ size_t utf8_str_count_width(const char* str, size_t min_width, size_t max_width)
return count;
}
+// Like strlcpy(), but doesn't leave a partial UTF-8 sequence at the end of dst
+size_t utf8_strlcpy(char* dst, const char* src, size_t size)
+{
+ size_t i;
+ int len;
+
+ if (size < 1)
+ return 0;
+
+ for (i = 0; src[i] != '\0'; i += len) {
+ len = utf8_decode_firstbyte(src[i]);
+ if (len < 1)
+ break;
+ if(i + len < size) {
+ memcpy(dst, src + i, len);
+ dst += len;
+ }
+ }
+ *dst = '\0';
+ return i;
+}
+
int cp437_to_utf8_str(const char* str, char* dest, size_t maxlen, unsigned char minval)
{
int retval = 0;
diff --git a/src/encode/utf8.h b/src/encode/utf8.h
index 99e8e50c62..1bfd4fe645 100644
--- a/src/encode/utf8.h
+++ b/src/encode/utf8.h
@@ -44,6 +44,9 @@ size_t utf8_str_total_width(const char*);
// Return the count of chars within the specified width range in UTF-8 string (str)
size_t utf8_str_count_width(const char*, size_t min_width, size_t max_width);
+// Like strlcpy(), but doesn't leave a partial UTF-8 sequence at the end of dst
+size_t utf8_strlcpy(char* dst, const char* src, size_t size);
+
// Normalizes (to ASCII) chars in UTF-8 string 'str', in-place, resulting in string <= original in length
char* utf8_normalize_str(char* str);
--
GitLab