neovim

commit 8ea18119e7bbbf956680266b6e1a69bc5fa4b40d
parent e02ee7410a6d04b32ec38af9f4ffdcf0798a0f0b
Author: zeertzjq <zeertzjq@outlook.com>
Date:   Sun,  9 Mar 2025 08:00:53 +0800

vim-patch:9.1.1184: Unnecessary use of vim_tolower() in vim_strnicmp_asc() (#32792)

Problem:  Unnecessary use of vim_tolower() in vim_strnicmp_asc().
Solution: Use TOLOWER_ASC() instead (zeertzjq).

It was passing *s1 and *s2 to vim_tolower(). When char is signed, which
is the case on most platforms, c < 0x80 is always true, so it already
behaves the same as TOLOWER_ASC().

closes: vim/vim#16826

https://github.com/vim/vim/commit/b7dc5d3b6169efc8aa0b9d86476072877e74bc2c

Use this function for hashy case-insensitive lookup, as it's ASCII-only.

Note that this function doesn't cast TOLOWER_ASC() argument to uint8_t,
so it'll treat a UTF-8 byte as smaller than NUL. It doesn't matter, as
one of the strings being compared is ASCII-only, and its behavior still
leads to consistent ordering.
Diffstat:
M
src/gen/hashy.lua
 | 
4
++--
M
src/nvim/strings.c
 | 
22
++++++++++++++++++++++

2 files changed, 24 insertions(+), 2 deletions(-)
diff --git a/src/gen/hashy.lua b/src/gen/hashy.lua
@@ -129,14 +129,14 @@ function M.hashy_hash(name, strings, access, lower)
     }
   }
   return -1;
-]]):format(lower and 'mb_strnicmp' or 'memcmp', access('i')))
+]]):format(lower and 'vim_strnicmp_asc' or 'memcmp', access('i')))
   else
     put(([[
   if (low < 0 || %s(str, %s, len)) {
     return -1;
   }
   return low;
-]]):format(lower and 'mb_strnicmp' or 'memcmp', access('low')))
+]]):format(lower and 'vim_strnicmp_asc' or 'memcmp', access('low')))
   end
   put '}\n\n'
   return neworder, table.concat(stats)
diff --git a/src/nvim/strings.c b/src/nvim/strings.c
@@ -475,6 +475,28 @@ bool striequal(const char *a, const char *b)
   return (a == NULL && b == NULL) || (a && b && STRICMP(a, b) == 0);
 }
 
+/// Compare two ASCII strings, for length "len", ignoring case, ignoring locale.
+///
+/// @return 0 for match, < 0 for smaller, > 0 for bigger
+int vim_strnicmp_asc(const char *s1, const char *s2, size_t len)
+  FUNC_ATTR_PURE FUNC_ATTR_WARN_UNUSED_RESULT
+{
+  int i = 0;
+  while (len > 0) {
+    i = TOLOWER_ASC(*s1) - TOLOWER_ASC(*s2);
+    if (i != 0) {
+      break;                       // this character is different
+    }
+    if (*s1 == NUL) {
+      break;                       // strings match until NUL
+    }
+    s1++;
+    s2++;
+    len--;
+  }
+  return i;
+}
+
 /// strchr() version which handles multibyte strings
 ///
 /// @param[in]  string  String to search in.