Update contrib/libs/lzma to 5.6.4

commit_hash:509ecf098c2bdb4bf7273b95ff459ee74bd2a6bf

contrib/libs/lzma/NEWS

@@ -2,10 +2,56 @@
 XZ Utils Release Notes
 ======================
 
+5.6.4 (2025-01-23)
+
+    * liblzma: Fix LZMA/LZMA2 encoder on big endian ARM64.
+
+    * xz:
+
+        - Fix --filters= and --filters1= ... --filters9= options
+          parsing. They require an argument, thus "xz --filters lzma2"
+          should work in addition to "xz --filters=lzma2".
+
+        - On the man page, note in the --compress and --decompress
+          options that the default behavior is to delete the input
+          file unless writing to standard output. It was already
+          documented in the DESCRIPTION section but new users in
+          a hurry might miss it.
+
+    * Windows (native builds, not Cygwin): Fix regressions introduced
+      in XZ Utils 5.6.3 which caused non-ASCII characters to display
+      incorrectly. Only builds with translation support were affected
+      (--enable-nls or ENABLE_NLS=ON). The following changes affect
+      builds that have translations enabled:
+
+        - Require UCRT because MSVCRT doesn't support UTF-8
+          locales and thus translations won't be readable on
+          Windows 10 version 1903 and later. (MSVCRT builds
+          are still possible with --disable-nls or ENABLE_NLS=OFF.)
+
+        - Require gettext-runtime >= 0.23.1 because older versions
+          don't autodetect the use of the UTF-8 code page. This
+          resulted in garbled non-ASCII characters even with UCRT.
+
+        - Partially fix alignment issues in xz --verbose --list
+          with translated messages. Chinese (simplified),
+          Chinese (traditional), and Korean column headings
+          are misaligned still because Windows and MinGW-w64
+          don't provide wcwidth() and XZ Utils doesn't include
+          a replacement function either.
+
+    * CMake: Explicitly disable unity builds. This prevents build
+      failures when another project uses XZ Utils via CMake's
+      FetchContent module, and that project enables unity builds.
+
+    * Update Chinese (traditional) and Serbian translations.
+
+
 5.6.3 (2024-10-01)
 
     IMPORTANT: This includes a Windows-specific security fix to
-    the command line tools. liblzma isn't affected by this issue.
+    the command line tools (CVE-2024-47611). liblzma isn't affected
+    by this issue.
 
     * liblzma:
 
@@ -55,6 +101,7 @@ XZ Utils Release Notes
               which can be exploited with malicious filenames to do
               argument injection or directory traversal attacks.
               UTF-8 avoids best-fit mappings and thus fixes the issue.
+              (CVE-2024-47611)
 
               Forcing the process code page to UTF-8 is possible only
               on Windows 10 version 1903 and later. The command line

contrib/libs/lzma/common/sysdefs.h

@@ -23,17 +23,29 @@
 #	include <config.h>
 #endif
 
-// This #define ensures that C99 and POSIX compliant stdio functions are
-// available with MinGW-w64 (both 32-bit and 64-bit). Modern MinGW-w64 adds
-// this automatically, for example, when the compiler is in C99 (or later)
-// mode when building against msvcrt.dll. It still doesn't hurt to be explicit
-// that we always want this and #define this unconditionally.
+// Choose if MinGW-w64's stdio replacement functions should be used.
+// The default has varied slightly in the past so it's clearest to always
+// set it explicitly.
 //
-// With Universal CRT (UCRT) this is less important because UCRT contains
-// C99-compatible stdio functions. It's still nice to #define this as UCRT
-// doesn't support the POSIX thousand separator flag in printf (like "%'u").
-#ifdef __MINGW32__
+// Modern MinGW-w64 enables the replacement functions even with UCRT
+// when _GNU_SOURCE is defined. That's good because UCRT doesn't support
+// the POSIX thousand separator flag in printf (like "%'u"). Otherwise
+// XZ Utils works with the UCRT stdio functions.
+//
+// The replacement functions add over 20 KiB to each executable. For
+// size-optimized builds (HAVE_SMALL), disable the replacements.
+// Then thousand separators aren't shown in xz's messages but this is
+// a minor downside compare to the slower speed of the HAVE_SMALL builds.
+//
+// The legacy MSVCRT is pre-C99 and it's best to always use the stdio
+// replacements functions from MinGW-w64.
+#if defined(__MINGW32__) && !defined(__USE_MINGW_ANSI_STDIO)
 #	define __USE_MINGW_ANSI_STDIO 1
+#	include <_mingw.h>
+#	if defined(_UCRT) && defined(HAVE_SMALL)
+#		undef __USE_MINGW_ANSI_STDIO
+#		define __USE_MINGW_ANSI_STDIO 0
+#	endif
 #endif
 
 // size_t and NULL

contrib/libs/lzma/liblzma/api/lzma/lzma12.h

@@ -461,7 +461,7 @@ typedef struct {
 	 *
 	 * ext_size_low holds the least significant 32 bits of the
 	 * uncompressed size. The most significant 32 bits must be set
-	 * in ext_size_high. The macro lzma_ext_size_set(opt_lzma, u64size)
+	 * in ext_size_high. The macro lzma_set_ext_size(opt_lzma, u64size)
 	 * can be used to set these members.
 	 *
 	 * The 64-bit uncompressed size is split into two uint32_t variables

contrib/libs/lzma/liblzma/api/lzma/version.h

@@ -22,7 +22,7 @@
 #define LZMA_VERSION_MINOR 6
 
 /** \brief Patch version number of the liblzma release. */
-#define LZMA_VERSION_PATCH 3
+#define LZMA_VERSION_PATCH 4
 
 /**
  * \brief Version stability marker

contrib/libs/lzma/liblzma/common/memcmplen.h

@@ -65,8 +65,7 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2,
 			|| (defined(_MSC_VER) && (defined(_M_X64) \
 				|| defined(_M_ARM64) || defined(_M_ARM64EC))))
 	// This is only for x86-64 and ARM64 for now. This might be fine on
-	// other 64-bit processors too. On big endian one should use xor
-	// instead of subtraction and switch to __builtin_clzll().
+	// other 64-bit processors too.
 	//
 	// Reasons to use subtraction instead of xor:
 	//
@@ -82,14 +81,20 @@ lzma_memcmplen(const uint8_t *buf1, const uint8_t *buf2,
 	// version 2023-05-26. https://www.agner.org/optimize/
 #define LZMA_MEMCMPLEN_EXTRA 8
 	while (len < limit) {
+#	ifdef WORDS_BIGENDIAN
+		const uint64_t x = read64ne(buf1 + len) ^ read64ne(buf2 + len);
+#	else
 		const uint64_t x = read64ne(buf1 + len) - read64ne(buf2 + len);
+#	endif
 		if (x != 0) {
 	// MSVC or Intel C compiler on Windows
 #	if defined(_MSC_VER) || defined(__INTEL_COMPILER)
 			unsigned long tmp;
 			_BitScanForward64(&tmp, x);
 			len += (uint32_t)tmp >> 3;
 	// GCC, Clang, or Intel C compiler
+#	elif defined(WORDS_BIGENDIAN)
+			len += (uint32_t)__builtin_clzll(x) >> 3;
 #	else
 			len += (uint32_t)__builtin_ctzll(x) >> 3;
 #	endif

contrib/libs/lzma/liblzma/common/string_conversion.c

@@ -317,6 +317,10 @@ parse_lzma12_preset(const char **const str, const char *str_end,
 		uint32_t *preset)
 {
 	assert(*str < str_end);
+
+	if (!(**str >= '0' && **str <= '9'))
+		return "Unsupported preset";
+
 	*preset = (uint32_t)(**str - '0');
 
 	// NOTE: Remember to update LZMA12_PRESET_STR if this is modified!

contrib/libs/lzma/liblzma/lzma/lzma_decoder.c

@@ -18,7 +18,7 @@
 
 // The macros unroll loops with switch statements.
 // Silence warnings about missing fall-through comments.
-#if TUKLIB_GNUC_REQ(7, 0)
+#if TUKLIB_GNUC_REQ(7, 0) || defined(__clang__)
 #	pragma GCC diagnostic ignored "-Wimplicit-fallthrough"
 #endif
 

contrib/libs/lzma/ya.make

@@ -11,9 +11,9 @@ LICENSE(
 
 LICENSE_TEXTS(.yandex_meta/licenses.list.txt)
 
-VERSION(5.6.3)
+VERSION(5.6.4)
 
-ORIGINAL_SOURCE(https://github.com/tukaani-project/xz/archive/v5.6.3.tar.gz)
+ORIGINAL_SOURCE(https://github.com/tukaani-project/xz/archive/v5.6.4.tar.gz)
 
 ADDINCL(
     GLOBAL contrib/libs/lzma/liblzma/api