Adding upstream version 5.6.1+really5.4.5.upstream/5.6.1+really5.4.5

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

20 files changed, 2649 insertions, 0 deletions

diff --git a/src/common/common_w32res.rc b/src/common/common_w32res.rc
new file mode 100644
index 0000000..d05d22e
--- /dev/null
+++ b/src/common/common_w32res.rc
@@ -0,0 +1,52 @@
+/*
+ * Author: Lasse Collin
+ *
+ * This file has been put into the public domain.
+ * You can do whatever you want with this file.
+ */
+
+#include <winresrc.h>
+#ifdef HAVE_CONFIG_H
+# include "config.h"
+#endif
+#define LZMA_H_INTERNAL
+#define LZMA_H_INTERNAL_RC
+#include "lzma/version.h"
+
+#ifndef MY_BUILD
+# define MY_BUILD 0
+#endif
+#define MY_VERSION LZMA_VERSION_MAJOR,LZMA_VERSION_MINOR,LZMA_VERSION_PATCH,MY_BUILD
+
+#define MY_FILENAME    MY_NAME MY_SUFFIX
+#define MY_COMPANY     "The Tukaani Project <https://tukaani.org/>"
+#define MY_PRODUCT     PACKAGE_NAME " <" PACKAGE_URL ">"
+
+LANGUAGE LANG_ENGLISH, SUBLANG_ENGLISH_US
+VS_VERSION_INFO VERSIONINFO
+  FILEVERSION MY_VERSION
+  PRODUCTVERSION MY_VERSION
+  FILEFLAGSMASK VS_FFI_FILEFLAGSMASK
+  FILEFLAGS 0
+  FILEOS VOS_NT_WINDOWS32
+  FILETYPE MY_TYPE
+  FILESUBTYPE 0x0L
+BEGIN
+    BLOCK "StringFileInfo"
+    BEGIN
+        BLOCK "040904b0"
+        BEGIN
+            VALUE "CompanyName", MY_COMPANY
+            VALUE "FileDescription", MY_DESC
+            VALUE "FileVersion", LZMA_VERSION_STRING
+            VALUE "InternalName", MY_NAME
+            VALUE "OriginalFilename", MY_FILENAME
+            VALUE "ProductName", MY_PRODUCT
+            VALUE "ProductVersion", LZMA_VERSION_STRING
+        END
+    END
+    BLOCK "VarFileInfo"
+    BEGIN
+        VALUE "Translation", 0x409, 1200
+    END
+END
diff --git a/src/common/mythread.h b/src/common/mythread.h
new file mode 100644
index 0000000..4495e01
--- /dev/null
+++ b/src/common/mythread.h
@@ -0,0 +1,528 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       mythread.h
+/// \brief      Some threading related helper macros and functions
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef MYTHREAD_H
+#define MYTHREAD_H
+
+#include "sysdefs.h"
+
+// If any type of threading is enabled, #define MYTHREAD_ENABLED.
+#if defined(MYTHREAD_POSIX) || defined(MYTHREAD_WIN95) \
+		|| defined(MYTHREAD_VISTA)
+#	define MYTHREAD_ENABLED 1
+#endif
+
+
+#ifdef MYTHREAD_ENABLED
+
+////////////////////////////////////////
+// Shared between all threading types //
+////////////////////////////////////////
+
+// Locks a mutex for a duration of a block.
+//
+// Perform mythread_mutex_lock(&mutex) in the beginning of a block
+// and mythread_mutex_unlock(&mutex) at the end of the block. "break"
+// may be used to unlock the mutex and jump out of the block.
+// mythread_sync blocks may be nested.
+//
+// Example:
+//
+//     mythread_sync(mutex) {
+//         foo();
+//         if (some_error)
+//             break; // Skips bar()
+//         bar();
+//     }
+//
+// At least GCC optimizes the loops completely away so it doesn't slow
+// things down at all compared to plain mythread_mutex_lock(&mutex)
+// and mythread_mutex_unlock(&mutex) calls.
+//
+#define mythread_sync(mutex) mythread_sync_helper1(mutex, __LINE__)
+#define mythread_sync_helper1(mutex, line) mythread_sync_helper2(mutex, line)
+#define mythread_sync_helper2(mutex, line) \
+	for (unsigned int mythread_i_ ## line = 0; \
+			mythread_i_ ## line \
+				? (mythread_mutex_unlock(&(mutex)), 0) \
+				: (mythread_mutex_lock(&(mutex)), 1); \
+			mythread_i_ ## line = 1) \
+		for (unsigned int mythread_j_ ## line = 0; \
+				!mythread_j_ ## line; \
+				mythread_j_ ## line = 1)
+#endif
+
+
+#if !defined(MYTHREAD_ENABLED)
+
+//////////////////
+// No threading //
+//////////////////
+
+// Calls the given function once. This isn't thread safe.
+#define mythread_once(func) \
+do { \
+	static bool once_ = false; \
+	if (!once_) { \
+		func(); \
+		once_ = true; \
+	} \
+} while (0)
+
+
+#if !(defined(_WIN32) && !defined(__CYGWIN__)) && !defined(__wasm__)
+// Use sigprocmask() to set the signal mask in single-threaded programs.
+#include <signal.h>
+
+static inline void
+mythread_sigmask(int how, const sigset_t *restrict set,
+		sigset_t *restrict oset)
+{
+	int ret = sigprocmask(how, set, oset);
+	assert(ret == 0);
+	(void)ret;
+}
+#endif
+
+
+#elif defined(MYTHREAD_POSIX)
+
+////////////////////
+// Using pthreads //
+////////////////////
+
+#include <pthread.h>
+#include <signal.h>
+#include <time.h>
+#include <errno.h>
+
+// If clock_gettime() isn't available, use gettimeofday() from <sys/time.h>
+// as a fallback. gettimeofday() is in SUSv2 and thus is supported on all
+// relevant POSIX systems.
+#ifndef HAVE_CLOCK_GETTIME
+#	include <sys/time.h>
+#endif
+
+#define MYTHREAD_RET_TYPE void *
+#define MYTHREAD_RET_VALUE NULL
+
+typedef pthread_t mythread;
+typedef pthread_mutex_t mythread_mutex;
+
+typedef struct {
+	pthread_cond_t cond;
+#ifdef HAVE_CLOCK_GETTIME
+	// Clock ID (CLOCK_REALTIME or CLOCK_MONOTONIC) associated with
+	// the condition variable.
+	clockid_t clk_id;
+#endif
+} mythread_cond;
+
+typedef struct timespec mythread_condtime;
+
+
+// Calls the given function once in a thread-safe way.
+#define mythread_once(func) \
+	do { \
+		static pthread_once_t once_ = PTHREAD_ONCE_INIT; \
+		pthread_once(&once_, &func); \
+	} while (0)
+
+
+// Use pthread_sigmask() to set the signal mask in multi-threaded programs.
+// Do nothing on OpenVMS since it lacks pthread_sigmask().
+static inline void
+mythread_sigmask(int how, const sigset_t *restrict set,
+		sigset_t *restrict oset)
+{
+#ifdef __VMS
+	(void)how;
+	(void)set;
+	(void)oset;
+#else
+	int ret = pthread_sigmask(how, set, oset);
+	assert(ret == 0);
+	(void)ret;
+#endif
+}
+
+
+// Creates a new thread with all signals blocked. Returns zero on success
+// and non-zero on error.
+static inline int
+mythread_create(mythread *thread, void *(*func)(void *arg), void *arg)
+{
+	sigset_t old;
+	sigset_t all;
+	sigfillset(&all);
+
+	mythread_sigmask(SIG_SETMASK, &all, &old);
+	const int ret = pthread_create(thread, NULL, func, arg);
+	mythread_sigmask(SIG_SETMASK, &old, NULL);
+
+	return ret;
+}
+
+// Joins a thread. Returns zero on success and non-zero on error.
+static inline int
+mythread_join(mythread thread)
+{
+	return pthread_join(thread, NULL);
+}
+
+
+// Initiatlizes a mutex. Returns zero on success and non-zero on error.
+static inline int
+mythread_mutex_init(mythread_mutex *mutex)
+{
+	return pthread_mutex_init(mutex, NULL);
+}
+
+static inline void
+mythread_mutex_destroy(mythread_mutex *mutex)
+{
+	int ret = pthread_mutex_destroy(mutex);
+	assert(ret == 0);
+	(void)ret;
+}
+
+static inline void
+mythread_mutex_lock(mythread_mutex *mutex)
+{
+	int ret = pthread_mutex_lock(mutex);
+	assert(ret == 0);
+	(void)ret;
+}
+
+static inline void
+mythread_mutex_unlock(mythread_mutex *mutex)
+{
+	int ret = pthread_mutex_unlock(mutex);
+	assert(ret == 0);
+	(void)ret;
+}
+
+
+// Initializes a condition variable.
+//
+// Using CLOCK_MONOTONIC instead of the default CLOCK_REALTIME makes the
+// timeout in pthread_cond_timedwait() work correctly also if system time
+// is suddenly changed. Unfortunately CLOCK_MONOTONIC isn't available
+// everywhere while the default CLOCK_REALTIME is, so the default is
+// used if CLOCK_MONOTONIC isn't available.
+//
+// If clock_gettime() isn't available at all, gettimeofday() will be used.
+static inline int
+mythread_cond_init(mythread_cond *mycond)
+{
+#ifdef HAVE_CLOCK_GETTIME
+#	if defined(HAVE_PTHREAD_CONDATTR_SETCLOCK) && \
+		defined(HAVE_CLOCK_MONOTONIC)
+	struct timespec ts;
+	pthread_condattr_t condattr;
+
+	// POSIX doesn't seem to *require* that pthread_condattr_setclock()
+	// will fail if given an unsupported clock ID. Test that
+	// CLOCK_MONOTONIC really is supported using clock_gettime().
+	if (clock_gettime(CLOCK_MONOTONIC, &ts) == 0
+			&& pthread_condattr_init(&condattr) == 0) {
+		int ret = pthread_condattr_setclock(
+				&condattr, CLOCK_MONOTONIC);
+		if (ret == 0)
+			ret = pthread_cond_init(&mycond->cond, &condattr);
+
+		pthread_condattr_destroy(&condattr);
+
+		if (ret == 0) {
+			mycond->clk_id = CLOCK_MONOTONIC;
+			return 0;
+		}
+	}
+
+	// If anything above fails, fall back to the default CLOCK_REALTIME.
+	// POSIX requires that all implementations of clock_gettime() must
+	// support at least CLOCK_REALTIME.
+#	endif
+
+	mycond->clk_id = CLOCK_REALTIME;
+#endif
+
+	return pthread_cond_init(&mycond->cond, NULL);
+}
+
+static inline void
+mythread_cond_destroy(mythread_cond *cond)
+{
+	int ret = pthread_cond_destroy(&cond->cond);
+	assert(ret == 0);
+	(void)ret;
+}
+
+static inline void
+mythread_cond_signal(mythread_cond *cond)
+{
+	int ret = pthread_cond_signal(&cond->cond);
+	assert(ret == 0);
+	(void)ret;
+}
+
+static inline void
+mythread_cond_wait(mythread_cond *cond, mythread_mutex *mutex)
+{
+	int ret = pthread_cond_wait(&cond->cond, mutex);
+	assert(ret == 0);
+	(void)ret;
+}
+
+// Waits on a condition or until a timeout expires. If the timeout expires,
+// non-zero is returned, otherwise zero is returned.
+static inline int
+mythread_cond_timedwait(mythread_cond *cond, mythread_mutex *mutex,
+		const mythread_condtime *condtime)
+{
+	int ret = pthread_cond_timedwait(&cond->cond, mutex, condtime);
+	assert(ret == 0 || ret == ETIMEDOUT);
+	return ret;
+}
+
+// Sets condtime to the absolute time that is timeout_ms milliseconds
+// in the future. The type of the clock to use is taken from cond.
+static inline void
+mythread_condtime_set(mythread_condtime *condtime, const mythread_cond *cond,
+		uint32_t timeout_ms)
+{
+	condtime->tv_sec = (time_t)(timeout_ms / 1000);
+	condtime->tv_nsec = (long)((timeout_ms % 1000) * 1000000);
+
+#ifdef HAVE_CLOCK_GETTIME
+	struct timespec now;
+	int ret = clock_gettime(cond->clk_id, &now);
+	assert(ret == 0);
+	(void)ret;
+
+	condtime->tv_sec += now.tv_sec;
+	condtime->tv_nsec += now.tv_nsec;
+#else
+	(void)cond;
+
+	struct timeval now;
+	gettimeofday(&now, NULL);
+
+	condtime->tv_sec += now.tv_sec;
+	condtime->tv_nsec += now.tv_usec * 1000L;
+#endif
+
+	// tv_nsec must stay in the range [0, 999_999_999].
+	if (condtime->tv_nsec >= 1000000000L) {
+		condtime->tv_nsec -= 1000000000L;
+		++condtime->tv_sec;
+	}
+}
+
+
+#elif defined(MYTHREAD_WIN95) || defined(MYTHREAD_VISTA)
+
+/////////////////////
+// Windows threads //
+/////////////////////
+
+#define WIN32_LEAN_AND_MEAN
+#ifdef MYTHREAD_VISTA
+#	undef _WIN32_WINNT
+#	define _WIN32_WINNT 0x0600
+#endif
+#include <windows.h>
+#include <process.h>
+
+#define MYTHREAD_RET_TYPE unsigned int __stdcall
+#define MYTHREAD_RET_VALUE 0
+
+typedef HANDLE mythread;
+typedef CRITICAL_SECTION mythread_mutex;
+
+#ifdef MYTHREAD_WIN95
+typedef HANDLE mythread_cond;
+#else
+typedef CONDITION_VARIABLE mythread_cond;
+#endif
+
+typedef struct {
+	// Tick count (milliseconds) in the beginning of the timeout.
+	// NOTE: This is 32 bits so it wraps around after 49.7 days.
+	// Multi-day timeouts may not work as expected.
+	DWORD start;
+
+	// Length of the timeout in milliseconds. The timeout expires
+	// when the current tick count minus "start" is equal or greater
+	// than "timeout".
+	DWORD timeout;
+} mythread_condtime;
+
+
+// mythread_once() is only available with Vista threads.
+#ifdef MYTHREAD_VISTA
+#define mythread_once(func) \
+	do { \
+		static INIT_ONCE once_ = INIT_ONCE_STATIC_INIT; \
+		BOOL pending_; \
+		if (!InitOnceBeginInitialize(&once_, 0, &pending_, NULL)) \
+			abort(); \
+		if (pending_) { \
+			func(); \
+			if (!InitOnceComplete(&once_, 0, NULL)) \
+				abort(); \
+		} \
+	} while (0)
+#endif
+
+
+// mythread_sigmask() isn't available on Windows. Even a dummy version would
+// make no sense because the other POSIX signal functions are missing anyway.
+
+
+static inline int
+mythread_create(mythread *thread,
+		unsigned int (__stdcall *func)(void *arg), void *arg)
+{
+	uintptr_t ret = _beginthreadex(NULL, 0, func, arg, 0, NULL);
+	if (ret == 0)
+		return -1;
+
+	*thread = (HANDLE)ret;
+	return 0;
+}
+
+static inline int
+mythread_join(mythread thread)
+{
+	int ret = 0;
+
+	if (WaitForSingleObject(thread, INFINITE) != WAIT_OBJECT_0)
+		ret = -1;
+
+	if (!CloseHandle(thread))
+		ret = -1;
+
+	return ret;
+}
+
+
+static inline int
+mythread_mutex_init(mythread_mutex *mutex)
+{
+	InitializeCriticalSection(mutex);
+	return 0;
+}
+
+static inline void
+mythread_mutex_destroy(mythread_mutex *mutex)
+{
+	DeleteCriticalSection(mutex);
+}
+
+static inline void
+mythread_mutex_lock(mythread_mutex *mutex)
+{
+	EnterCriticalSection(mutex);
+}
+
+static inline void
+mythread_mutex_unlock(mythread_mutex *mutex)
+{
+	LeaveCriticalSection(mutex);
+}
+
+
+static inline int
+mythread_cond_init(mythread_cond *cond)
+{
+#ifdef MYTHREAD_WIN95
+	*cond = CreateEvent(NULL, FALSE, FALSE, NULL);
+	return *cond == NULL ? -1 : 0;
+#else
+	InitializeConditionVariable(cond);
+	return 0;
+#endif
+}
+
+static inline void
+mythread_cond_destroy(mythread_cond *cond)
+{
+#ifdef MYTHREAD_WIN95
+	CloseHandle(*cond);
+#else
+	(void)cond;
+#endif
+}
+
+static inline void
+mythread_cond_signal(mythread_cond *cond)
+{
+#ifdef MYTHREAD_WIN95
+	SetEvent(*cond);
+#else
+	WakeConditionVariable(cond);
+#endif
+}
+
+static inline void
+mythread_cond_wait(mythread_cond *cond, mythread_mutex *mutex)
+{
+#ifdef MYTHREAD_WIN95
+	LeaveCriticalSection(mutex);
+	WaitForSingleObject(*cond, INFINITE);
+	EnterCriticalSection(mutex);
+#else
+	BOOL ret = SleepConditionVariableCS(cond, mutex, INFINITE);
+	assert(ret);
+	(void)ret;
+#endif
+}
+
+static inline int
+mythread_cond_timedwait(mythread_cond *cond, mythread_mutex *mutex,
+		const mythread_condtime *condtime)
+{
+#ifdef MYTHREAD_WIN95
+	LeaveCriticalSection(mutex);
+#endif
+
+	DWORD elapsed = GetTickCount() - condtime->start;
+	DWORD timeout = elapsed >= condtime->timeout
+			? 0 : condtime->timeout - elapsed;
+
+#ifdef MYTHREAD_WIN95
+	DWORD ret = WaitForSingleObject(*cond, timeout);
+	assert(ret == WAIT_OBJECT_0 || ret == WAIT_TIMEOUT);
+
+	EnterCriticalSection(mutex);
+
+	return ret == WAIT_TIMEOUT;
+#else
+	BOOL ret = SleepConditionVariableCS(cond, mutex, timeout);
+	assert(ret || GetLastError() == ERROR_TIMEOUT);
+	return !ret;
+#endif
+}
+
+static inline void
+mythread_condtime_set(mythread_condtime *condtime, const mythread_cond *cond,
+		uint32_t timeout)
+{
+	(void)cond;
+	condtime->start = GetTickCount();
+	condtime->timeout = timeout;
+}
+
+#endif
+
+#endif
diff --git a/src/common/sysdefs.h b/src/common/sysdefs.h
new file mode 100644
index 0000000..f04e45d
--- /dev/null
+++ b/src/common/sysdefs.h
@@ -0,0 +1,197 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       sysdefs.h
+/// \brief      Common includes, definitions, system-specific things etc.
+///
+/// This file is used also by the lzma command line tool, that's why this
+/// file is separate from common.h.
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef LZMA_SYSDEFS_H
+#define LZMA_SYSDEFS_H
+
+//////////////
+// Includes //
+//////////////
+
+#ifdef HAVE_CONFIG_H
+#	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.
+//
+// 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__
+#	define __USE_MINGW_ANSI_STDIO 1
+#endif
+
+// size_t and NULL
+#include <stddef.h>
+
+#ifdef HAVE_INTTYPES_H
+#	include <inttypes.h>
+#endif
+
+// C99 says that inttypes.h always includes stdint.h, but some systems
+// don't do that, and require including stdint.h separately.
+#ifdef HAVE_STDINT_H
+#	include <stdint.h>
+#endif
+
+// Some pre-C99 systems have SIZE_MAX in limits.h instead of stdint.h. The
+// limits are also used to figure out some macros missing from pre-C99 systems.
+#include <limits.h>
+
+// Be more compatible with systems that have non-conforming inttypes.h.
+// We assume that int is 32-bit and that long is either 32-bit or 64-bit.
+// Full Autoconf test could be more correct, but this should work well enough.
+// Note that this duplicates some code from lzma.h, but this is better since
+// we can work without inttypes.h thanks to Autoconf tests.
+#ifndef UINT32_C
+#	if UINT_MAX != 4294967295U
+#		error UINT32_C is not defined and unsigned int is not 32-bit.
+#	endif
+#	define UINT32_C(n) n ## U
+#endif
+#ifndef UINT32_MAX
+#	define UINT32_MAX UINT32_C(4294967295)
+#endif
+#ifndef PRIu32
+#	define PRIu32 "u"
+#endif
+#ifndef PRIx32
+#	define PRIx32 "x"
+#endif
+#ifndef PRIX32
+#	define PRIX32 "X"
+#endif
+
+#if ULONG_MAX == 4294967295UL
+#	ifndef UINT64_C
+#		define UINT64_C(n) n ## ULL
+#	endif
+#	ifndef PRIu64
+#		define PRIu64 "llu"
+#	endif
+#	ifndef PRIx64
+#		define PRIx64 "llx"
+#	endif
+#	ifndef PRIX64
+#		define PRIX64 "llX"
+#	endif
+#else
+#	ifndef UINT64_C
+#		define UINT64_C(n) n ## UL
+#	endif
+#	ifndef PRIu64
+#		define PRIu64 "lu"
+#	endif
+#	ifndef PRIx64
+#		define PRIx64 "lx"
+#	endif
+#	ifndef PRIX64
+#		define PRIX64 "lX"
+#	endif
+#endif
+#ifndef UINT64_MAX
+#	define UINT64_MAX UINT64_C(18446744073709551615)
+#endif
+
+// Incorrect(?) SIZE_MAX:
+//   - Interix headers typedef size_t to unsigned long,
+//     but a few lines later define SIZE_MAX to INT32_MAX.
+//   - SCO OpenServer (x86) headers typedef size_t to unsigned int
+//     but define SIZE_MAX to INT32_MAX.
+#if defined(__INTERIX) || defined(_SCO_DS)
+#	undef SIZE_MAX
+#endif
+
+// The code currently assumes that size_t is either 32-bit or 64-bit.
+#ifndef SIZE_MAX
+#	if SIZEOF_SIZE_T == 4
+#		define SIZE_MAX UINT32_MAX
+#	elif SIZEOF_SIZE_T == 8
+#		define SIZE_MAX UINT64_MAX
+#	else
+#		error size_t is not 32-bit or 64-bit
+#	endif
+#endif
+#if SIZE_MAX != UINT32_MAX && SIZE_MAX != UINT64_MAX
+#	error size_t is not 32-bit or 64-bit
+#endif
+
+#include <stdlib.h>
+#include <assert.h>
+
+// Pre-C99 systems lack stdbool.h. All the code in XZ Utils must be written
+// so that it works with fake bool type, for example:
+//
+//    bool foo = (flags & 0x100) != 0;
+//    bool bar = !!(flags & 0x100);
+//
+// This works with the real C99 bool but breaks with fake bool:
+//
+//    bool baz = (flags & 0x100);
+//
+#ifdef HAVE_STDBOOL_H
+#	include <stdbool.h>
+#else
+#	if ! HAVE__BOOL
+typedef unsigned char _Bool;
+#	endif
+#	define bool _Bool
+#	define false 0
+#	define true 1
+#	define __bool_true_false_are_defined 1
+#endif
+
+#include <string.h>
+
+// As of MSVC 2013, inline and restrict are supported with
+// non-standard keywords.
+#if defined(_WIN32) && defined(_MSC_VER)
+#	ifndef inline
+#		define inline __inline
+#	endif
+#	ifndef restrict
+#		define restrict __restrict
+#	endif
+#endif
+
+////////////
+// Macros //
+////////////
+
+#undef memzero
+#define memzero(s, n) memset(s, 0, n)
+
+// NOTE: Avoid using MIN() and MAX(), because even conditionally defining
+// those macros can cause some portability trouble, since on some systems
+// the system headers insist defining their own versions.
+#define my_min(x, y) ((x) < (y) ? (x) : (y))
+#define my_max(x, y) ((x) > (y) ? (x) : (y))
+
+#ifndef ARRAY_SIZE
+#	define ARRAY_SIZE(array) (sizeof(array) / sizeof((array)[0]))
+#endif
+
+#if defined(__GNUC__) \
+		&& ((__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4)
+#	define lzma_attr_alloc_size(x) __attribute__((__alloc_size__(x)))
+#else
+#	define lzma_attr_alloc_size(x)
+#endif
+
+#endif
diff --git a/src/common/tuklib_common.h b/src/common/tuklib_common.h
new file mode 100644
index 0000000..b1f531e
--- /dev/null
+++ b/src/common/tuklib_common.h
@@ -0,0 +1,71 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_common.h
+/// \brief      Common definitions for tuklib modules
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_COMMON_H
+#define TUKLIB_COMMON_H
+
+// The config file may be replaced by a package-specific file.
+// It should include at least stddef.h, stdbool.h, inttypes.h, and limits.h.
+#include "tuklib_config.h"
+
+// TUKLIB_SYMBOL_PREFIX is prefixed to all symbols exported by
+// the tuklib modules. If you use a tuklib module in a library,
+// you should use TUKLIB_SYMBOL_PREFIX to make sure that there
+// are no symbol conflicts in case someone links your library
+// into application that also uses the same tuklib module.
+#ifndef TUKLIB_SYMBOL_PREFIX
+#	define TUKLIB_SYMBOL_PREFIX
+#endif
+
+#define TUKLIB_CAT_X(a, b) a ## b
+#define TUKLIB_CAT(a, b) TUKLIB_CAT_X(a, b)
+
+#ifndef TUKLIB_SYMBOL
+#	define TUKLIB_SYMBOL(sym) TUKLIB_CAT(TUKLIB_SYMBOL_PREFIX, sym)
+#endif
+
+#ifndef TUKLIB_DECLS_BEGIN
+#	ifdef __cplusplus
+#		define TUKLIB_DECLS_BEGIN extern "C" {
+#	else
+#		define TUKLIB_DECLS_BEGIN
+#	endif
+#endif
+
+#ifndef TUKLIB_DECLS_END
+#	ifdef __cplusplus
+#		define TUKLIB_DECLS_END }
+#	else
+#		define TUKLIB_DECLS_END
+#	endif
+#endif
+
+#if defined(__GNUC__) && defined(__GNUC_MINOR__)
+#	define TUKLIB_GNUC_REQ(major, minor) \
+		((__GNUC__ == (major) && __GNUC_MINOR__ >= (minor)) \
+			|| __GNUC__ > (major))
+#else
+#	define TUKLIB_GNUC_REQ(major, minor) 0
+#endif
+
+#if TUKLIB_GNUC_REQ(2, 5)
+#	define tuklib_attr_noreturn __attribute__((__noreturn__))
+#else
+#	define tuklib_attr_noreturn
+#endif
+
+#if (defined(_WIN32) && !defined(__CYGWIN__)) \
+		|| defined(__OS2__) || defined(__MSDOS__)
+#	define TUKLIB_DOSLIKE 1
+#endif
+
+#endif
diff --git a/src/common/tuklib_config.h b/src/common/tuklib_config.h
new file mode 100644
index 0000000..9d470ba
--- /dev/null
+++ b/src/common/tuklib_config.h
@@ -0,0 +1,10 @@
+// If config.h isn't available, assume that the headers required by
+// tuklib_common.h are available. This is required by crc32_tablegen.c.
+#ifdef HAVE_CONFIG_H
+#	include "sysdefs.h"
+#else
+#	include <stddef.h>
+#	include <stdbool.h>
+#	include <inttypes.h>
+#	include <limits.h>
+#endif
diff --git a/src/common/tuklib_cpucores.c b/src/common/tuklib_cpucores.c
new file mode 100644
index 0000000..bb3f2f7
--- /dev/null
+++ b/src/common/tuklib_cpucores.c
@@ -0,0 +1,109 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_cpucores.c
+/// \brief      Get the number of CPU cores online
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "tuklib_cpucores.h"
+
+#if defined(_WIN32) || defined(__CYGWIN__)
+#	ifndef _WIN32_WINNT
+#		define _WIN32_WINNT 0x0500
+#	endif
+#	include <windows.h>
+
+// glibc >= 2.9
+#elif defined(TUKLIB_CPUCORES_SCHED_GETAFFINITY)
+#	include <sched.h>
+
+// FreeBSD
+#elif defined(TUKLIB_CPUCORES_CPUSET)
+#	include <sys/param.h>
+#	include <sys/cpuset.h>
+
+#elif defined(TUKLIB_CPUCORES_SYSCTL)
+#	ifdef HAVE_SYS_PARAM_H
+#		include <sys/param.h>
+#	endif
+#	include <sys/sysctl.h>
+
+#elif defined(TUKLIB_CPUCORES_SYSCONF)
+#	include <unistd.h>
+
+// HP-UX
+#elif defined(TUKLIB_CPUCORES_PSTAT_GETDYNAMIC)
+#	include <sys/param.h>
+#	include <sys/pstat.h>
+#endif
+
+
+extern uint32_t
+tuklib_cpucores(void)
+{
+	uint32_t ret = 0;
+
+#if defined(_WIN32) || defined(__CYGWIN__)
+	SYSTEM_INFO sysinfo;
+	GetSystemInfo(&sysinfo);
+	ret = sysinfo.dwNumberOfProcessors;
+
+#elif defined(TUKLIB_CPUCORES_SCHED_GETAFFINITY)
+	cpu_set_t cpu_mask;
+	if (sched_getaffinity(0, sizeof(cpu_mask), &cpu_mask) == 0)
+		ret = (uint32_t)CPU_COUNT(&cpu_mask);
+
+#elif defined(TUKLIB_CPUCORES_CPUSET)
+	cpuset_t set;
+	if (cpuset_getaffinity(CPU_LEVEL_WHICH, CPU_WHICH_PID, -1,
+			sizeof(set), &set) == 0) {
+#	ifdef CPU_COUNT
+		ret = (uint32_t)CPU_COUNT(&set);
+#	else
+		for (unsigned i = 0; i < CPU_SETSIZE; ++i)
+			if (CPU_ISSET(i, &set))
+				++ret;
+#	endif
+	}
+
+#elif defined(TUKLIB_CPUCORES_SYSCTL)
+	// On OpenBSD HW_NCPUONLINE tells the number of processor cores that
+	// are online so it is preferred over HW_NCPU which also counts cores
+	// that aren't currently available. The number of cores online is
+	// often less than HW_NCPU because OpenBSD disables simultaneous
+	// multi-threading (SMT) by default.
+#	ifdef HW_NCPUONLINE
+	int name[2] = { CTL_HW, HW_NCPUONLINE };
+#	else
+	int name[2] = { CTL_HW, HW_NCPU };
+#	endif
+	int cpus;
+	size_t cpus_size = sizeof(cpus);
+	if (sysctl(name, 2, &cpus, &cpus_size, NULL, 0) != -1
+			&& cpus_size == sizeof(cpus) && cpus > 0)
+		ret = (uint32_t)cpus;
+
+#elif defined(TUKLIB_CPUCORES_SYSCONF)
+#	ifdef _SC_NPROCESSORS_ONLN
+	// Most systems
+	const long cpus = sysconf(_SC_NPROCESSORS_ONLN);
+#	else
+	// IRIX
+	const long cpus = sysconf(_SC_NPROC_ONLN);
+#	endif
+	if (cpus > 0)
+		ret = (uint32_t)cpus;
+
+#elif defined(TUKLIB_CPUCORES_PSTAT_GETDYNAMIC)
+	struct pst_dynamic pst;
+	if (pstat_getdynamic(&pst, sizeof(pst), 1, 0) != -1)
+		ret = (uint32_t)pst.psd_proc_cnt;
+#endif
+
+	return ret;
+}
diff --git a/src/common/tuklib_cpucores.h b/src/common/tuklib_cpucores.h
new file mode 100644
index 0000000..be1ce1c
--- /dev/null
+++ b/src/common/tuklib_cpucores.h
@@ -0,0 +1,23 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_cpucores.h
+/// \brief      Get the number of CPU cores online
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_CPUCORES_H
+#define TUKLIB_CPUCORES_H
+
+#include "tuklib_common.h"
+TUKLIB_DECLS_BEGIN
+
+#define tuklib_cpucores TUKLIB_SYMBOL(tuklib_cpucores)
+extern uint32_t tuklib_cpucores(void);
+
+TUKLIB_DECLS_END
+#endif
diff --git a/src/common/tuklib_exit.c b/src/common/tuklib_exit.c
new file mode 100644
index 0000000..aa55620
--- /dev/null
+++ b/src/common/tuklib_exit.c
@@ -0,0 +1,58 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_exit.c
+/// \brief      Close stdout and stderr, and exit
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "tuklib_common.h"
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "tuklib_gettext.h"
+#include "tuklib_progname.h"
+#include "tuklib_exit.h"
+
+
+extern void
+tuklib_exit(int status, int err_status, int show_error)
+{
+	if (status != err_status) {
+		// Close stdout. If something goes wrong,
+		// print an error message to stderr.
+		const int ferror_err = ferror(stdout);
+		const int fclose_err = fclose(stdout);
+		if (ferror_err || fclose_err) {
+			status = err_status;
+
+			// If it was fclose() that failed, we have the reason
+			// in errno. If only ferror() indicated an error,
+			// we have no idea what the reason was.
+			if (show_error)
+				fprintf(stderr, "%s: %s: %s\n", progname,
+						_("Writing to standard "
+							"output failed"),
+						fclose_err ? strerror(errno)
+							: _("Unknown error"));
+		}
+	}
+
+	if (status != err_status) {
+		// Close stderr. If something goes wrong, there's
+		// nothing where we could print an error message.
+		// Just set the exit status.
+		const int ferror_err = ferror(stderr);
+		const int fclose_err = fclose(stderr);
+		if (fclose_err || ferror_err)
+			status = err_status;
+	}
+
+	exit(status);
+}
diff --git a/src/common/tuklib_exit.h b/src/common/tuklib_exit.h
new file mode 100644
index 0000000..b11776f
--- /dev/null
+++ b/src/common/tuklib_exit.h
@@ -0,0 +1,25 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_exit.h
+/// \brief      Close stdout and stderr, and exit
+/// \note       Requires tuklib_progname and tuklib_gettext modules
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_EXIT_H
+#define TUKLIB_EXIT_H
+
+#include "tuklib_common.h"
+TUKLIB_DECLS_BEGIN
+
+#define tuklib_exit TUKLIB_SYMBOL(tuklib_exit)
+extern void tuklib_exit(int status, int err_status, int show_error)
+		tuklib_attr_noreturn;
+
+TUKLIB_DECLS_END
+#endif
diff --git a/src/common/tuklib_gettext.h b/src/common/tuklib_gettext.h
new file mode 100644
index 0000000..ff18904
--- /dev/null
+++ b/src/common/tuklib_gettext.h
@@ -0,0 +1,44 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_gettext.h
+/// \brief      Wrapper for gettext and friends
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_GETTEXT_H
+#define TUKLIB_GETTEXT_H
+
+#include "tuklib_common.h"
+#include <locale.h>
+
+#ifndef TUKLIB_GETTEXT
+#	ifdef ENABLE_NLS
+#		define TUKLIB_GETTEXT 1
+#	else
+#		define TUKLIB_GETTEXT 0
+#	endif
+#endif
+
+#if TUKLIB_GETTEXT
+#	include <libintl.h>
+#	define tuklib_gettext_init(package, localedir) \
+		do { \
+			setlocale(LC_ALL, ""); \
+			bindtextdomain(package, localedir); \
+			textdomain(package); \
+		} while (0)
+#	define _(msgid) gettext(msgid)
+#else
+#	define tuklib_gettext_init(package, localedir) \
+		setlocale(LC_ALL, "")
+#	define _(msgid) (msgid)
+#	define ngettext(msgid1, msgid2, n) ((n) == 1 ? (msgid1) : (msgid2))
+#endif
+#define N_(msgid) msgid
+
+#endif
diff --git a/src/common/tuklib_integer.h b/src/common/tuklib_integer.h
new file mode 100644
index 0000000..e22aa8a
--- /dev/null
+++ b/src/common/tuklib_integer.h
@@ -0,0 +1,946 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_integer.h
+/// \brief      Various integer and bit operations
+///
+/// This file provides macros or functions to do some basic integer and bit
+/// operations.
+///
+/// Native endian inline functions (XX = 16, 32, or 64):
+///   - Unaligned native endian reads: readXXne(ptr)
+///   - Unaligned native endian writes: writeXXne(ptr, num)
+///   - Aligned native endian reads: aligned_readXXne(ptr)
+///   - Aligned native endian writes: aligned_writeXXne(ptr, num)
+///
+/// Endianness-converting integer operations (these can be macros!)
+/// (XX = 16, 32, or 64; Y = b or l):
+///   - Byte swapping: bswapXX(num)
+///   - Byte order conversions to/from native (byteswaps if Y isn't
+///     the native endianness): convXXYe(num)
+///   - Unaligned reads: readXXYe(ptr)
+///   - Unaligned writes: writeXXYe(ptr, num)
+///   - Aligned reads: aligned_readXXYe(ptr)
+///   - Aligned writes: aligned_writeXXYe(ptr, num)
+///
+/// Since the above can macros, the arguments should have no side effects
+/// because they may be evaluated more than once.
+///
+/// Bit scan operations for non-zero 32-bit integers (inline functions):
+///   - Bit scan reverse (find highest non-zero bit): bsr32(num)
+///   - Count leading zeros: clz32(num)
+///   - Count trailing zeros: ctz32(num)
+///   - Bit scan forward (simply an alias for ctz32()): bsf32(num)
+///
+/// The above bit scan operations return 0-31. If num is zero,
+/// the result is undefined.
+//
+//  Authors:    Lasse Collin
+//              Joachim Henke
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_INTEGER_H
+#define TUKLIB_INTEGER_H
+
+#include "tuklib_common.h"
+#include <string.h>
+
+// Newer Intel C compilers require immintrin.h for _bit_scan_reverse()
+// and such functions.
+#if defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 1500)
+#	include <immintrin.h>
+// Only include <intrin.h> when it is needed. GCC and Clang can both
+// use __builtin's, so we only need Windows instrincs when using MSVC.
+// GCC and Clang can set _MSC_VER on Windows, so we need to exclude these
+// cases explicitly.
+#elif defined(_MSC_VER) && !TUKLIB_GNUC_REQ(3, 4) && !defined(__clang__)
+#	include <intrin.h>
+#endif
+
+
+///////////////////
+// Byte swapping //
+///////////////////
+
+#if defined(HAVE___BUILTIN_BSWAPXX)
+	// GCC >= 4.8 and Clang
+#	define bswap16(n) __builtin_bswap16(n)
+#	define bswap32(n) __builtin_bswap32(n)
+#	define bswap64(n) __builtin_bswap64(n)
+
+#elif defined(HAVE_BYTESWAP_H)
+	// glibc, uClibc, dietlibc
+#	include <byteswap.h>
+#	ifdef HAVE_BSWAP_16
+#		define bswap16(num) bswap_16(num)
+#	endif
+#	ifdef HAVE_BSWAP_32
+#		define bswap32(num) bswap_32(num)
+#	endif
+#	ifdef HAVE_BSWAP_64
+#		define bswap64(num) bswap_64(num)
+#	endif
+
+#elif defined(HAVE_SYS_ENDIAN_H)
+	// *BSDs and Darwin
+#	include <sys/endian.h>
+
+#elif defined(HAVE_SYS_BYTEORDER_H)
+	// Solaris
+#	include <sys/byteorder.h>
+#	ifdef BSWAP_16
+#		define bswap16(num) BSWAP_16(num)
+#	endif
+#	ifdef BSWAP_32
+#		define bswap32(num) BSWAP_32(num)
+#	endif
+#	ifdef BSWAP_64
+#		define bswap64(num) BSWAP_64(num)
+#	endif
+#	ifdef BE_16
+#		define conv16be(num) BE_16(num)
+#	endif
+#	ifdef BE_32
+#		define conv32be(num) BE_32(num)
+#	endif
+#	ifdef BE_64
+#		define conv64be(num) BE_64(num)
+#	endif
+#	ifdef LE_16
+#		define conv16le(num) LE_16(num)
+#	endif
+#	ifdef LE_32
+#		define conv32le(num) LE_32(num)
+#	endif
+#	ifdef LE_64
+#		define conv64le(num) LE_64(num)
+#	endif
+#endif
+
+#ifndef bswap16
+#	define bswap16(n) (uint16_t)( \
+		  (((n) & 0x00FFU) << 8) \
+		| (((n) & 0xFF00U) >> 8) \
+	)
+#endif
+
+#ifndef bswap32
+#	define bswap32(n) (uint32_t)( \
+		  (((n) & UINT32_C(0x000000FF)) << 24) \
+		| (((n) & UINT32_C(0x0000FF00)) << 8) \
+		| (((n) & UINT32_C(0x00FF0000)) >> 8) \
+		| (((n) & UINT32_C(0xFF000000)) >> 24) \
+	)
+#endif
+
+#ifndef bswap64
+#	define bswap64(n) (uint64_t)( \
+		  (((n) & UINT64_C(0x00000000000000FF)) << 56) \
+		| (((n) & UINT64_C(0x000000000000FF00)) << 40) \
+		| (((n) & UINT64_C(0x0000000000FF0000)) << 24) \
+		| (((n) & UINT64_C(0x00000000FF000000)) << 8) \
+		| (((n) & UINT64_C(0x000000FF00000000)) >> 8) \
+		| (((n) & UINT64_C(0x0000FF0000000000)) >> 24) \
+		| (((n) & UINT64_C(0x00FF000000000000)) >> 40) \
+		| (((n) & UINT64_C(0xFF00000000000000)) >> 56) \
+	)
+#endif
+
+// Define conversion macros using the basic byte swapping macros.
+#ifdef WORDS_BIGENDIAN
+#	ifndef conv16be
+#		define conv16be(num) ((uint16_t)(num))
+#	endif
+#	ifndef conv32be
+#		define conv32be(num) ((uint32_t)(num))
+#	endif
+#	ifndef conv64be
+#		define conv64be(num) ((uint64_t)(num))
+#	endif
+#	ifndef conv16le
+#		define conv16le(num) bswap16(num)
+#	endif
+#	ifndef conv32le
+#		define conv32le(num) bswap32(num)
+#	endif
+#	ifndef conv64le
+#		define conv64le(num) bswap64(num)
+#	endif
+#else
+#	ifndef conv16be
+#		define conv16be(num) bswap16(num)
+#	endif
+#	ifndef conv32be
+#		define conv32be(num) bswap32(num)
+#	endif
+#	ifndef conv64be
+#		define conv64be(num) bswap64(num)
+#	endif
+#	ifndef conv16le
+#		define conv16le(num) ((uint16_t)(num))
+#	endif
+#	ifndef conv32le
+#		define conv32le(num) ((uint32_t)(num))
+#	endif
+#	ifndef conv64le
+#		define conv64le(num) ((uint64_t)(num))
+#	endif
+#endif
+
+
+////////////////////////////////
+// Unaligned reads and writes //
+////////////////////////////////
+
+// No-strict-align archs like x86-64
+// ---------------------------------
+//
+// The traditional way of casting e.g. *(const uint16_t *)uint8_pointer
+// is bad even if the uint8_pointer is properly aligned because this kind
+// of casts break strict aliasing rules and result in undefined behavior.
+// With unaligned pointers it's even worse: compilers may emit vector
+// instructions that require aligned pointers even if non-vector
+// instructions work with unaligned pointers.
+//
+// Using memcpy() is the standard compliant way to do unaligned access.
+// Many modern compilers inline it so there is no function call overhead.
+// For those compilers that don't handle the memcpy() method well, the
+// old casting method (that violates strict aliasing) can be requested at
+// build time. A third method, casting to a packed struct, would also be
+// an option but isn't provided to keep things simpler (it's already a mess).
+// Hopefully this is flexible enough in practice.
+//
+// Some compilers on x86-64 like Clang >= 10 and GCC >= 5.1 detect that
+//
+//     buf[0] | (buf[1] << 8)
+//
+// reads a 16-bit value and can emit a single 16-bit load and produce
+// identical code than with the memcpy() method. In other cases Clang and GCC
+// produce either the same or better code with memcpy(). For example, Clang 9
+// on x86-64 can detect 32-bit load but not 16-bit load.
+//
+// MSVC uses unaligned access with the memcpy() method but emits byte-by-byte
+// code for "buf[0] | (buf[1] << 8)".
+//
+// Conclusion: The memcpy() method is the best choice when unaligned access
+// is supported.
+//
+// Strict-align archs like SPARC
+// -----------------------------
+//
+// GCC versions from around 4.x to to at least 13.2.0 produce worse code
+// from the memcpy() method than from simple byte-by-byte shift-or code
+// when reading a 32-bit integer:
+//
+//     (1) It may be constructed on stack using using four 8-bit loads,
+//         four 8-bit stores to stack, and finally one 32-bit load from stack.
+//
+//     (2) Especially with -Os, an actual memcpy() call may be emitted.
+//
+// This is true on at least on ARM, ARM64, SPARC, SPARC64, MIPS64EL, and
+// RISC-V. Of these, ARM, ARM64, and RISC-V support unaligned access in
+// some processors but not all so this is relevant only in the case when
+// GCC assumes that unaligned is not supported or -mstrict-align or
+// -mno-unaligned-access is used.
+//
+// For Clang it makes little difference. ARM64 with -O2 -mstrict-align
+// was one the very few with a minor difference: the memcpy() version
+// was one instruction longer.
+//
+// Conclusion: At least in case of GCC and Clang, byte-by-byte code is
+// the best choise for strict-align archs to do unaligned access.
+//
+// See also: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111502
+//
+// Thanks to <https://godbolt.org/> it was easy to test different compilers.
+// The following is for little endian targets:
+/*
+#include <stdint.h>
+#include <string.h>
+
+uint32_t bytes16(const uint8_t *b)
+{
+    return (uint32_t)b[0]
+        | ((uint32_t)b[1] << 8);
+}
+
+uint32_t copy16(const uint8_t *b)
+{
+    uint16_t v;
+    memcpy(&v, b, sizeof(v));
+    return v;
+}
+
+uint32_t bytes32(const uint8_t *b)
+{
+    return (uint32_t)b[0]
+        | ((uint32_t)b[1] << 8)
+        | ((uint32_t)b[2] << 16)
+        | ((uint32_t)b[3] << 24);
+}
+
+uint32_t copy32(const uint8_t *b)
+{
+    uint32_t v;
+    memcpy(&v, b, sizeof(v));
+    return v;
+}
+
+void wbytes16(uint8_t *b, uint16_t v)
+{
+    b[0] = (uint8_t)v;
+    b[1] = (uint8_t)(v >> 8);
+}
+
+void wcopy16(uint8_t *b, uint16_t v)
+{
+    memcpy(b, &v, sizeof(v));
+}
+
+void wbytes32(uint8_t *b, uint32_t v)
+{
+    b[0] = (uint8_t)v;
+    b[1] = (uint8_t)(v >> 8);
+    b[2] = (uint8_t)(v >> 16);
+    b[3] = (uint8_t)(v >> 24);
+}
+
+void wcopy32(uint8_t *b, uint32_t v)
+{
+    memcpy(b, &v, sizeof(v));
+}
+*/
+
+
+#ifdef TUKLIB_FAST_UNALIGNED_ACCESS
+
+static inline uint16_t
+read16ne(const uint8_t *buf)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	return *(const uint16_t *)buf;
+#else
+	uint16_t num;
+	memcpy(&num, buf, sizeof(num));
+	return num;
+#endif
+}
+
+
+static inline uint32_t
+read32ne(const uint8_t *buf)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	return *(const uint32_t *)buf;
+#else
+	uint32_t num;
+	memcpy(&num, buf, sizeof(num));
+	return num;
+#endif
+}
+
+
+static inline uint64_t
+read64ne(const uint8_t *buf)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	return *(const uint64_t *)buf;
+#else
+	uint64_t num;
+	memcpy(&num, buf, sizeof(num));
+	return num;
+#endif
+}
+
+
+static inline void
+write16ne(uint8_t *buf, uint16_t num)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	*(uint16_t *)buf = num;
+#else
+	memcpy(buf, &num, sizeof(num));
+#endif
+	return;
+}
+
+
+static inline void
+write32ne(uint8_t *buf, uint32_t num)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	*(uint32_t *)buf = num;
+#else
+	memcpy(buf, &num, sizeof(num));
+#endif
+	return;
+}
+
+
+static inline void
+write64ne(uint8_t *buf, uint64_t num)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	*(uint64_t *)buf = num;
+#else
+	memcpy(buf, &num, sizeof(num));
+#endif
+	return;
+}
+
+
+static inline uint16_t
+read16be(const uint8_t *buf)
+{
+	uint16_t num = read16ne(buf);
+	return conv16be(num);
+}
+
+
+static inline uint16_t
+read16le(const uint8_t *buf)
+{
+	uint16_t num = read16ne(buf);
+	return conv16le(num);
+}
+
+
+static inline uint32_t
+read32be(const uint8_t *buf)
+{
+	uint32_t num = read32ne(buf);
+	return conv32be(num);
+}
+
+
+static inline uint32_t
+read32le(const uint8_t *buf)
+{
+	uint32_t num = read32ne(buf);
+	return conv32le(num);
+}
+
+
+static inline uint64_t
+read64be(const uint8_t *buf)
+{
+	uint64_t num = read64ne(buf);
+	return conv64be(num);
+}
+
+
+static inline uint64_t
+read64le(const uint8_t *buf)
+{
+	uint64_t num = read64ne(buf);
+	return conv64le(num);
+}
+
+
+// NOTE: Possible byte swapping must be done in a macro to allow the compiler
+// to optimize byte swapping of constants when using glibc's or *BSD's
+// byte swapping macros. The actual write is done in an inline function
+// to make type checking of the buf pointer possible.
+#define write16be(buf, num) write16ne(buf, conv16be(num))
+#define write32be(buf, num) write32ne(buf, conv32be(num))
+#define write64be(buf, num) write64ne(buf, conv64be(num))
+#define write16le(buf, num) write16ne(buf, conv16le(num))
+#define write32le(buf, num) write32ne(buf, conv32le(num))
+#define write64le(buf, num) write64ne(buf, conv64le(num))
+
+#else
+
+#ifdef WORDS_BIGENDIAN
+#	define read16ne read16be
+#	define read32ne read32be
+#	define read64ne read64be
+#	define write16ne write16be
+#	define write32ne write32be
+#	define write64ne write64be
+#else
+#	define read16ne read16le
+#	define read32ne read32le
+#	define read64ne read64le
+#	define write16ne write16le
+#	define write32ne write32le
+#	define write64ne write64le
+#endif
+
+
+static inline uint16_t
+read16be(const uint8_t *buf)
+{
+	uint16_t num = ((uint16_t)buf[0] << 8) | (uint16_t)buf[1];
+	return num;
+}
+
+
+static inline uint16_t
+read16le(const uint8_t *buf)
+{
+	uint16_t num = ((uint16_t)buf[0]) | ((uint16_t)buf[1] << 8);
+	return num;
+}
+
+
+static inline uint32_t
+read32be(const uint8_t *buf)
+{
+	uint32_t num = (uint32_t)buf[0] << 24;
+	num |= (uint32_t)buf[1] << 16;
+	num |= (uint32_t)buf[2] << 8;
+	num |= (uint32_t)buf[3];
+	return num;
+}
+
+
+static inline uint32_t
+read32le(const uint8_t *buf)
+{
+	uint32_t num = (uint32_t)buf[0];
+	num |= (uint32_t)buf[1] << 8;
+	num |= (uint32_t)buf[2] << 16;
+	num |= (uint32_t)buf[3] << 24;
+	return num;
+}
+
+
+static inline uint64_t
+read64be(const uint8_t *buf)
+{
+	uint64_t num = (uint64_t)buf[0] << 56;
+	num |= (uint64_t)buf[1] << 48;
+	num |= (uint64_t)buf[2] << 40;
+	num |= (uint64_t)buf[3] << 32;
+	num |= (uint64_t)buf[4] << 24;
+	num |= (uint64_t)buf[5] << 16;
+	num |= (uint64_t)buf[6] << 8;
+	num |= (uint64_t)buf[7];
+	return num;
+}
+
+
+static inline uint64_t
+read64le(const uint8_t *buf)
+{
+	uint64_t num = (uint64_t)buf[0];
+	num |= (uint64_t)buf[1] << 8;
+	num |= (uint64_t)buf[2] << 16;
+	num |= (uint64_t)buf[3] << 24;
+	num |= (uint64_t)buf[4] << 32;
+	num |= (uint64_t)buf[5] << 40;
+	num |= (uint64_t)buf[6] << 48;
+	num |= (uint64_t)buf[7] << 56;
+	return num;
+}
+
+
+static inline void
+write16be(uint8_t *buf, uint16_t num)
+{
+	buf[0] = (uint8_t)(num >> 8);
+	buf[1] = (uint8_t)num;
+	return;
+}
+
+
+static inline void
+write16le(uint8_t *buf, uint16_t num)
+{
+	buf[0] = (uint8_t)num;
+	buf[1] = (uint8_t)(num >> 8);
+	return;
+}
+
+
+static inline void
+write32be(uint8_t *buf, uint32_t num)
+{
+	buf[0] = (uint8_t)(num >> 24);
+	buf[1] = (uint8_t)(num >> 16);
+	buf[2] = (uint8_t)(num >> 8);
+	buf[3] = (uint8_t)num;
+	return;
+}
+
+
+static inline void
+write32le(uint8_t *buf, uint32_t num)
+{
+	buf[0] = (uint8_t)num;
+	buf[1] = (uint8_t)(num >> 8);
+	buf[2] = (uint8_t)(num >> 16);
+	buf[3] = (uint8_t)(num >> 24);
+	return;
+}
+
+
+static inline void
+write64be(uint8_t *buf, uint64_t num)
+{
+	buf[0] = (uint8_t)(num >> 56);
+	buf[1] = (uint8_t)(num >> 48);
+	buf[2] = (uint8_t)(num >> 40);
+	buf[3] = (uint8_t)(num >> 32);
+	buf[4] = (uint8_t)(num >> 24);
+	buf[5] = (uint8_t)(num >> 16);
+	buf[6] = (uint8_t)(num >> 8);
+	buf[7] = (uint8_t)num;
+	return;
+}
+
+
+static inline void
+write64le(uint8_t *buf, uint64_t num)
+{
+	buf[0] = (uint8_t)num;
+	buf[1] = (uint8_t)(num >> 8);
+	buf[2] = (uint8_t)(num >> 16);
+	buf[3] = (uint8_t)(num >> 24);
+	buf[4] = (uint8_t)(num >> 32);
+	buf[5] = (uint8_t)(num >> 40);
+	buf[6] = (uint8_t)(num >> 48);
+	buf[7] = (uint8_t)(num >> 56);
+	return;
+}
+
+#endif
+
+
+//////////////////////////////
+// Aligned reads and writes //
+//////////////////////////////
+
+// Separate functions for aligned reads and writes are provided since on
+// strict-align archs aligned access is much faster than unaligned access.
+//
+// Just like in the unaligned case, memcpy() is needed to avoid
+// strict aliasing violations. However, on archs that don't support
+// unaligned access the compiler cannot know that the pointers given
+// to memcpy() are aligned which results in slow code. As of C11 there is
+// no standard way to tell the compiler that we know that the address is
+// aligned but some compilers have language extensions to do that. With
+// such language extensions the memcpy() method gives excellent results.
+//
+// What to do on a strict-align system when no known language extentensions
+// are available? Falling back to byte-by-byte access would be safe but ruin
+// optimizations that have been made specifically with aligned access in mind.
+// As a compromise, aligned reads will fall back to non-compliant type punning
+// but aligned writes will be byte-by-byte, that is, fast reads are preferred
+// over fast writes. This obviously isn't great but hopefully it's a working
+// compromise for now.
+//
+// __builtin_assume_aligned is support by GCC >= 4.7 and clang >= 3.6.
+#ifdef HAVE___BUILTIN_ASSUME_ALIGNED
+#	define tuklib_memcpy_aligned(dest, src, size) \
+		memcpy(dest, __builtin_assume_aligned(src, size), size)
+#else
+#	define tuklib_memcpy_aligned(dest, src, size) \
+		memcpy(dest, src, size)
+#	ifndef TUKLIB_FAST_UNALIGNED_ACCESS
+#		define TUKLIB_USE_UNSAFE_ALIGNED_READS 1
+#	endif
+#endif
+
+
+static inline uint16_t
+aligned_read16ne(const uint8_t *buf)
+{
+#if defined(TUKLIB_USE_UNSAFE_TYPE_PUNNING) \
+		|| defined(TUKLIB_USE_UNSAFE_ALIGNED_READS)
+	return *(const uint16_t *)buf;
+#else
+	uint16_t num;
+	tuklib_memcpy_aligned(&num, buf, sizeof(num));
+	return num;
+#endif
+}
+
+
+static inline uint32_t
+aligned_read32ne(const uint8_t *buf)
+{
+#if defined(TUKLIB_USE_UNSAFE_TYPE_PUNNING) \
+		|| defined(TUKLIB_USE_UNSAFE_ALIGNED_READS)
+	return *(const uint32_t *)buf;
+#else
+	uint32_t num;
+	tuklib_memcpy_aligned(&num, buf, sizeof(num));
+	return num;
+#endif
+}
+
+
+static inline uint64_t
+aligned_read64ne(const uint8_t *buf)
+{
+#if defined(TUKLIB_USE_UNSAFE_TYPE_PUNNING) \
+		|| defined(TUKLIB_USE_UNSAFE_ALIGNED_READS)
+	return *(const uint64_t *)buf;
+#else
+	uint64_t num;
+	tuklib_memcpy_aligned(&num, buf, sizeof(num));
+	return num;
+#endif
+}
+
+
+static inline void
+aligned_write16ne(uint8_t *buf, uint16_t num)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	*(uint16_t *)buf = num;
+#else
+	tuklib_memcpy_aligned(buf, &num, sizeof(num));
+#endif
+	return;
+}
+
+
+static inline void
+aligned_write32ne(uint8_t *buf, uint32_t num)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	*(uint32_t *)buf = num;
+#else
+	tuklib_memcpy_aligned(buf, &num, sizeof(num));
+#endif
+	return;
+}
+
+
+static inline void
+aligned_write64ne(uint8_t *buf, uint64_t num)
+{
+#ifdef TUKLIB_USE_UNSAFE_TYPE_PUNNING
+	*(uint64_t *)buf = num;
+#else
+	tuklib_memcpy_aligned(buf, &num, sizeof(num));
+#endif
+	return;
+}
+
+
+static inline uint16_t
+aligned_read16be(const uint8_t *buf)
+{
+	uint16_t num = aligned_read16ne(buf);
+	return conv16be(num);
+}
+
+
+static inline uint16_t
+aligned_read16le(const uint8_t *buf)
+{
+	uint16_t num = aligned_read16ne(buf);
+	return conv16le(num);
+}
+
+
+static inline uint32_t
+aligned_read32be(const uint8_t *buf)
+{
+	uint32_t num = aligned_read32ne(buf);
+	return conv32be(num);
+}
+
+
+static inline uint32_t
+aligned_read32le(const uint8_t *buf)
+{
+	uint32_t num = aligned_read32ne(buf);
+	return conv32le(num);
+}
+
+
+static inline uint64_t
+aligned_read64be(const uint8_t *buf)
+{
+	uint64_t num = aligned_read64ne(buf);
+	return conv64be(num);
+}
+
+
+static inline uint64_t
+aligned_read64le(const uint8_t *buf)
+{
+	uint64_t num = aligned_read64ne(buf);
+	return conv64le(num);
+}
+
+
+// These need to be macros like in the unaligned case.
+#define aligned_write16be(buf, num) aligned_write16ne((buf), conv16be(num))
+#define aligned_write16le(buf, num) aligned_write16ne((buf), conv16le(num))
+#define aligned_write32be(buf, num) aligned_write32ne((buf), conv32be(num))
+#define aligned_write32le(buf, num) aligned_write32ne((buf), conv32le(num))
+#define aligned_write64be(buf, num) aligned_write64ne((buf), conv64be(num))
+#define aligned_write64le(buf, num) aligned_write64ne((buf), conv64le(num))
+
+
+////////////////////
+// Bit operations //
+////////////////////
+
+static inline uint32_t
+bsr32(uint32_t n)
+{
+	// Check for ICC first, since it tends to define __GNUC__ too.
+#if defined(__INTEL_COMPILER)
+	return _bit_scan_reverse(n);
+
+#elif (TUKLIB_GNUC_REQ(3, 4) || defined(__clang__)) && UINT_MAX == UINT32_MAX
+	// GCC >= 3.4 has __builtin_clz(), which gives good results on
+	// multiple architectures. On x86, __builtin_clz() ^ 31U becomes
+	// either plain BSR (so the XOR gets optimized away) or LZCNT and
+	// XOR (if -march indicates that SSE4a instructions are supported).
+	return (uint32_t)__builtin_clz(n) ^ 31U;
+
+#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+	uint32_t i;
+	__asm__("bsrl %1, %0" : "=r" (i) : "rm" (n));
+	return i;
+
+#elif defined(_MSC_VER)
+	unsigned long i;
+	_BitScanReverse(&i, n);
+	return i;
+
+#else
+	uint32_t i = 31;
+
+	if ((n & 0xFFFF0000) == 0) {
+		n <<= 16;
+		i = 15;
+	}
+
+	if ((n & 0xFF000000) == 0) {
+		n <<= 8;
+		i -= 8;
+	}
+
+	if ((n & 0xF0000000) == 0) {
+		n <<= 4;
+		i -= 4;
+	}
+
+	if ((n & 0xC0000000) == 0) {
+		n <<= 2;
+		i -= 2;
+	}
+
+	if ((n & 0x80000000) == 0)
+		--i;
+
+	return i;
+#endif
+}
+
+
+static inline uint32_t
+clz32(uint32_t n)
+{
+#if defined(__INTEL_COMPILER)
+	return _bit_scan_reverse(n) ^ 31U;
+
+#elif (TUKLIB_GNUC_REQ(3, 4) || defined(__clang__)) && UINT_MAX == UINT32_MAX
+	return (uint32_t)__builtin_clz(n);
+
+#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+	uint32_t i;
+	__asm__("bsrl %1, %0\n\t"
+		"xorl $31, %0"
+		: "=r" (i) : "rm" (n));
+	return i;
+
+#elif defined(_MSC_VER)
+	unsigned long i;
+	_BitScanReverse(&i, n);
+	return i ^ 31U;
+
+#else
+	uint32_t i = 0;
+
+	if ((n & 0xFFFF0000) == 0) {
+		n <<= 16;
+		i = 16;
+	}
+
+	if ((n & 0xFF000000) == 0) {
+		n <<= 8;
+		i += 8;
+	}
+
+	if ((n & 0xF0000000) == 0) {
+		n <<= 4;
+		i += 4;
+	}
+
+	if ((n & 0xC0000000) == 0) {
+		n <<= 2;
+		i += 2;
+	}
+
+	if ((n & 0x80000000) == 0)
+		++i;
+
+	return i;
+#endif
+}
+
+
+static inline uint32_t
+ctz32(uint32_t n)
+{
+#if defined(__INTEL_COMPILER)
+	return _bit_scan_forward(n);
+
+#elif (TUKLIB_GNUC_REQ(3, 4) || defined(__clang__)) && UINT_MAX >= UINT32_MAX
+	return (uint32_t)__builtin_ctz(n);
+
+#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
+	uint32_t i;
+	__asm__("bsfl %1, %0" : "=r" (i) : "rm" (n));
+	return i;
+
+#elif defined(_MSC_VER)
+	unsigned long i;
+	_BitScanForward(&i, n);
+	return i;
+
+#else
+	uint32_t i = 0;
+
+	if ((n & 0x0000FFFF) == 0) {
+		n >>= 16;
+		i = 16;
+	}
+
+	if ((n & 0x000000FF) == 0) {
+		n >>= 8;
+		i += 8;
+	}
+
+	if ((n & 0x0000000F) == 0) {
+		n >>= 4;
+		i += 4;
+	}
+
+	if ((n & 0x00000003) == 0) {
+		n >>= 2;
+		i += 2;
+	}
+
+	if ((n & 0x00000001) == 0)
+		++i;
+
+	return i;
+#endif
+}
+
+#define bsf32 ctz32
+
+#endif
diff --git a/src/common/tuklib_mbstr.h b/src/common/tuklib_mbstr.h
new file mode 100644
index 0000000..dde9305
--- /dev/null
+++ b/src/common/tuklib_mbstr.h
@@ -0,0 +1,66 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_mbstr.h
+/// \brief      Utility functions for handling multibyte strings
+///
+/// If not enough multibyte string support is available in the C library,
+/// these functions keep working with the assumption that all strings
+/// are in a single-byte character set without combining characters, e.g.
+/// US-ASCII or ISO-8859-*.
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_MBSTR_H
+#define TUKLIB_MBSTR_H
+
+#include "tuklib_common.h"
+TUKLIB_DECLS_BEGIN
+
+#define tuklib_mbstr_width TUKLIB_SYMBOL(tuklib_mbstr_width)
+extern size_t tuklib_mbstr_width(const char *str, size_t *bytes);
+///<
+/// \brief      Get the number of columns needed for the multibyte string
+///
+/// This is somewhat similar to wcswidth() but works on multibyte strings.
+///
+/// \param      str         String whose width is to be calculated. If the
+///                         current locale uses a multibyte character set
+///                         that has shift states, the string must begin
+///                         and end in the initial shift state.
+/// \param      bytes       If this is not NULL, *bytes is set to the
+///                         value returned by strlen(str) (even if an
+///                         error occurs when calculating the width).
+///
+/// \return     On success, the number of columns needed to display the
+///             string e.g. in a terminal emulator is returned. On error,
+///             (size_t)-1 is returned. Possible errors include invalid,
+///             partial, or non-printable multibyte character in str, or
+///             that str doesn't end in the initial shift state.
+
+#define tuklib_mbstr_fw TUKLIB_SYMBOL(tuklib_mbstr_fw)
+extern int tuklib_mbstr_fw(const char *str, int columns_min);
+///<
+/// \brief      Get the field width for printf() e.g. to align table columns
+///
+/// Printing simple tables to a terminal can be done using the field field
+/// feature in the printf() format string, but it works only with single-byte
+/// character sets. To do the same with multibyte strings, tuklib_mbstr_fw()
+/// can be used to calculate appropriate field width.
+///
+/// The behavior of this function is undefined, if
+///   - str is NULL or not terminated with '\0';
+///   - columns_min <= 0; or
+///   - the calculated field width exceeds INT_MAX.
+///
+/// \return     If tuklib_mbstr_width(str, NULL) fails, -1 is returned.
+///             If str needs more columns than columns_min, zero is returned.
+///             Otherwise a positive integer is returned, which can be
+///             used as the field width, e.g. printf("%*s", fw, str).
+
+TUKLIB_DECLS_END
+#endif
diff --git a/src/common/tuklib_mbstr_fw.c b/src/common/tuklib_mbstr_fw.c
new file mode 100644
index 0000000..64c9ad5
--- /dev/null
+++ b/src/common/tuklib_mbstr_fw.c
@@ -0,0 +1,31 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_mbstr_fw.c
+/// \brief      Get the field width for printf() e.g. to align table columns
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "tuklib_mbstr.h"
+
+
+extern int
+tuklib_mbstr_fw(const char *str, int columns_min)
+{
+	size_t len;
+	const size_t width = tuklib_mbstr_width(str, &len);
+	if (width == (size_t)-1)
+		return -1;
+
+	if (width > (size_t)columns_min)
+		return 0;
+
+	if (width < (size_t)columns_min)
+		len += (size_t)columns_min - width;
+
+	return (int)len;
+}
diff --git a/src/common/tuklib_mbstr_width.c b/src/common/tuklib_mbstr_width.c
new file mode 100644
index 0000000..69d159e
--- /dev/null
+++ b/src/common/tuklib_mbstr_width.c
@@ -0,0 +1,65 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_mbstr_width.c
+/// \brief      Calculate width of a multibyte string
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "tuklib_mbstr.h"
+#include <string.h>
+
+#if defined(HAVE_MBRTOWC) && defined(HAVE_WCWIDTH)
+#	include <wchar.h>
+#endif
+
+
+extern size_t
+tuklib_mbstr_width(const char *str, size_t *bytes)
+{
+	const size_t len = strlen(str);
+	if (bytes != NULL)
+		*bytes = len;
+
+#if !(defined(HAVE_MBRTOWC) && defined(HAVE_WCWIDTH))
+	// In single-byte mode, the width of the string is the same
+	// as its length.
+	return len;
+
+#else
+	mbstate_t state;
+	memset(&state, 0, sizeof(state));
+
+	size_t width = 0;
+	size_t i = 0;
+
+	// Convert one multibyte character at a time to wchar_t
+	// and get its width using wcwidth().
+	while (i < len) {
+		wchar_t wc;
+		const size_t ret = mbrtowc(&wc, str + i, len - i, &state);
+		if (ret < 1 || ret > len)
+			return (size_t)-1;
+
+		i += ret;
+
+		const int wc_width = wcwidth(wc);
+		if (wc_width < 0)
+			return (size_t)-1;
+
+		width += (size_t)wc_width;
+	}
+
+	// Require that the string ends in the initial shift state.
+	// This way the caller can be combine the string with other
+	// strings without needing to worry about the shift states.
+	if (!mbsinit(&state))
+		return (size_t)-1;
+
+	return width;
+#endif
+}
diff --git a/src/common/tuklib_open_stdxxx.c b/src/common/tuklib_open_stdxxx.c
new file mode 100644
index 0000000..26702a6
--- /dev/null
+++ b/src/common/tuklib_open_stdxxx.c
@@ -0,0 +1,57 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_open_stdxxx.c
+/// \brief      Make sure that file descriptors 0, 1, and 2 are open
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "tuklib_open_stdxxx.h"
+
+#ifndef TUKLIB_DOSLIKE
+#	include <stdlib.h>
+#	include <errno.h>
+#	include <fcntl.h>
+#	include <unistd.h>
+#endif
+
+
+extern void
+tuklib_open_stdxxx(int err_status)
+{
+#ifdef TUKLIB_DOSLIKE
+	// Do nothing, just silence warnings.
+	(void)err_status;
+
+#else
+	for (int i = 0; i <= 2; ++i) {
+		// We use fcntl() to check if the file descriptor is open.
+		if (fcntl(i, F_GETFD) == -1 && errno == EBADF) {
+			// With stdin, we could use /dev/full so that
+			// writing to stdin would fail. However, /dev/full
+			// is Linux specific, and if the program tries to
+			// write to stdin, there's already a problem anyway.
+			const int fd = open("/dev/null", O_NOCTTY
+					| (i == 0 ? O_WRONLY : O_RDONLY));
+
+			if (fd != i) {
+				if (fd != -1)
+					(void)close(fd);
+
+				// Something went wrong. Exit with the
+				// exit status we were given. Don't try
+				// to print an error message, since stderr
+				// may very well be non-existent. This
+				// error should be extremely rare.
+				exit(err_status);
+			}
+		}
+	}
+#endif
+
+	return;
+}
diff --git a/src/common/tuklib_open_stdxxx.h b/src/common/tuklib_open_stdxxx.h
new file mode 100644
index 0000000..b911616
--- /dev/null
+++ b/src/common/tuklib_open_stdxxx.h
@@ -0,0 +1,23 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_open_stdxxx.h
+/// \brief      Make sure that file descriptors 0, 1, and 2 are open
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_OPEN_STDXXX_H
+#define TUKLIB_OPEN_STDXXX_H
+
+#include "tuklib_common.h"
+TUKLIB_DECLS_BEGIN
+
+#define tuklib_open_stdxx TUKLIB_SYMBOL(tuklib_open_stdxxx)
+extern void tuklib_open_stdxxx(int err_status);
+
+TUKLIB_DECLS_END
+#endif
diff --git a/src/common/tuklib_physmem.c b/src/common/tuklib_physmem.c
new file mode 100644
index 0000000..69f6fd4
--- /dev/null
+++ b/src/common/tuklib_physmem.c
@@ -0,0 +1,234 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_physmem.c
+/// \brief      Get the amount of physical memory
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "tuklib_physmem.h"
+
+// We want to use Windows-specific code on Cygwin, which also has memory
+// information available via sysconf(), but on Cygwin 1.5 and older it
+// gives wrong results (from our point of view).
+#if defined(_WIN32) || defined(__CYGWIN__)
+#	ifndef _WIN32_WINNT
+#		define _WIN32_WINNT 0x0500
+#	endif
+#	include <windows.h>
+
+#elif defined(__OS2__)
+#	define INCL_DOSMISC
+#	include <os2.h>
+
+#elif defined(__DJGPP__)
+#	include <dpmi.h>
+
+#elif defined(__VMS)
+#	include <lib$routines.h>
+#	include <syidef.h>
+#	include <ssdef.h>
+
+#elif defined(AMIGA) || defined(__AROS__)
+#	define __USE_INLINE__
+#	include <proto/exec.h>
+
+#elif defined(__QNX__)
+#	include <sys/syspage.h>
+#	include <string.h>
+
+#elif defined(TUKLIB_PHYSMEM_AIX)
+#	include <sys/systemcfg.h>
+
+#elif defined(TUKLIB_PHYSMEM_SYSCONF)
+#	include <unistd.h>
+
+#elif defined(TUKLIB_PHYSMEM_SYSCTL)
+#	ifdef HAVE_SYS_PARAM_H
+#		include <sys/param.h>
+#	endif
+#	include <sys/sysctl.h>
+
+// Tru64
+#elif defined(TUKLIB_PHYSMEM_GETSYSINFO)
+#	include <sys/sysinfo.h>
+#	include <machine/hal_sysinfo.h>
+
+// HP-UX
+#elif defined(TUKLIB_PHYSMEM_PSTAT_GETSTATIC)
+#	include <sys/param.h>
+#	include <sys/pstat.h>
+
+// IRIX
+#elif defined(TUKLIB_PHYSMEM_GETINVENT_R)
+#	include <invent.h>
+
+// This sysinfo() is Linux-specific.
+#elif defined(TUKLIB_PHYSMEM_SYSINFO)
+#	include <sys/sysinfo.h>
+#endif
+
+
+// With GCC >= 8.1 with -Wextra and Clang >= 13 with -Wcast-function-type
+// will warn about the Windows-specific code.
+#if defined(__has_warning)
+#	if __has_warning("-Wcast-function-type")
+#		define CAN_DISABLE_WCAST_FUNCTION_TYPE 1
+#	endif
+#elif TUKLIB_GNUC_REQ(8,1)
+#	define CAN_DISABLE_WCAST_FUNCTION_TYPE 1
+#endif
+
+
+extern uint64_t
+tuklib_physmem(void)
+{
+	uint64_t ret = 0;
+
+#if defined(_WIN32) || defined(__CYGWIN__)
+	if ((GetVersion() & 0xFF) >= 5) {
+		// Windows 2000 and later have GlobalMemoryStatusEx() which
+		// supports reporting values greater than 4 GiB. To keep the
+		// code working also on older Windows versions, use
+		// GlobalMemoryStatusEx() conditionally.
+		HMODULE kernel32 = GetModuleHandle(TEXT("kernel32.dll"));
+		if (kernel32 != NULL) {
+			typedef BOOL (WINAPI *gmse_type)(LPMEMORYSTATUSEX);
+#ifdef CAN_DISABLE_WCAST_FUNCTION_TYPE
+#	pragma GCC diagnostic push
+#	pragma GCC diagnostic ignored "-Wcast-function-type"
+#endif
+			gmse_type gmse = (gmse_type)GetProcAddress(
+					kernel32, "GlobalMemoryStatusEx");
+#ifdef CAN_DISABLE_WCAST_FUNCTION_TYPE
+#	pragma GCC diagnostic pop
+#endif
+			if (gmse != NULL) {
+				MEMORYSTATUSEX meminfo;
+				meminfo.dwLength = sizeof(meminfo);
+				if (gmse(&meminfo))
+					ret = meminfo.ullTotalPhys;
+			}
+		}
+	}
+
+	if (ret == 0) {
+		// GlobalMemoryStatus() is supported by Windows 95 and later,
+		// so it is fine to link against it unconditionally. Note that
+		// GlobalMemoryStatus() has no return value.
+		MEMORYSTATUS meminfo;
+		meminfo.dwLength = sizeof(meminfo);
+		GlobalMemoryStatus(&meminfo);
+		ret = meminfo.dwTotalPhys;
+	}
+
+#elif defined(__OS2__)
+	unsigned long mem;
+	if (DosQuerySysInfo(QSV_TOTPHYSMEM, QSV_TOTPHYSMEM,
+			&mem, sizeof(mem)) == 0)
+		ret = mem;
+
+#elif defined(__DJGPP__)
+	__dpmi_free_mem_info meminfo;
+	if (__dpmi_get_free_memory_information(&meminfo) == 0
+			&& meminfo.total_number_of_physical_pages
+				!= (unsigned long)-1)
+		ret = (uint64_t)meminfo.total_number_of_physical_pages * 4096;
+
+#elif defined(__VMS)
+	int vms_mem;
+	int val = SYI$_MEMSIZE;
+	if (LIB$GETSYI(&val, &vms_mem, 0, 0, 0, 0) == SS$_NORMAL)
+		ret = (uint64_t)vms_mem * 8192;
+
+#elif defined(AMIGA) || defined(__AROS__)
+	ret = AvailMem(MEMF_TOTAL);
+
+#elif defined(__QNX__)
+	const struct asinfo_entry *entries = SYSPAGE_ENTRY(asinfo);
+	size_t count = SYSPAGE_ENTRY_SIZE(asinfo) / sizeof(struct asinfo_entry);
+	const char *strings = SYSPAGE_ENTRY(strings)->data;
+
+	for (size_t i = 0; i < count; ++i)
+		if (strcmp(strings + entries[i].name, "ram") == 0)
+			ret += entries[i].end - entries[i].start + 1;
+
+#elif defined(TUKLIB_PHYSMEM_AIX)
+	ret = _system_configuration.physmem;
+
+#elif defined(TUKLIB_PHYSMEM_SYSCONF)
+	const long pagesize = sysconf(_SC_PAGESIZE);
+	const long pages = sysconf(_SC_PHYS_PAGES);
+	if (pagesize != -1 && pages != -1)
+		// According to docs, pagesize * pages can overflow.
+		// Simple case is 32-bit box with 4 GiB or more RAM,
+		// which may report exactly 4 GiB of RAM, and "long"
+		// being 32-bit will overflow. Casting to uint64_t
+		// hopefully avoids overflows in the near future.
+		ret = (uint64_t)pagesize * (uint64_t)pages;
+
+#elif defined(TUKLIB_PHYSMEM_SYSCTL)
+	int name[2] = {
+		CTL_HW,
+#ifdef HW_PHYSMEM64
+		HW_PHYSMEM64
+#else
+		HW_PHYSMEM
+#endif
+	};
+	union {
+		uint32_t u32;
+		uint64_t u64;
+	} mem;
+	size_t mem_ptr_size = sizeof(mem.u64);
+	if (sysctl(name, 2, &mem.u64, &mem_ptr_size, NULL, 0) != -1) {
+		// IIRC, 64-bit "return value" is possible on some 64-bit
+		// BSD systems even with HW_PHYSMEM (instead of HW_PHYSMEM64),
+		// so support both.
+		if (mem_ptr_size == sizeof(mem.u64))
+			ret = mem.u64;
+		else if (mem_ptr_size == sizeof(mem.u32))
+			ret = mem.u32;
+	}
+
+#elif defined(TUKLIB_PHYSMEM_GETSYSINFO)
+	// Docs are unclear if "start" is needed, but it doesn't hurt
+	// much to have it.
+	int memkb;
+	int start = 0;
+	if (getsysinfo(GSI_PHYSMEM, (caddr_t)&memkb, sizeof(memkb), &start)
+			!= -1)
+		ret = (uint64_t)memkb * 1024;
+
+#elif defined(TUKLIB_PHYSMEM_PSTAT_GETSTATIC)
+	struct pst_static pst;
+	if (pstat_getstatic(&pst, sizeof(pst), 1, 0) != -1)
+		ret = (uint64_t)pst.physical_memory * (uint64_t)pst.page_size;
+
+#elif defined(TUKLIB_PHYSMEM_GETINVENT_R)
+	inv_state_t *st = NULL;
+	if (setinvent_r(&st) != -1) {
+		inventory_t *i;
+		while ((i = getinvent_r(st)) != NULL) {
+			if (i->inv_class == INV_MEMORY
+					&& i->inv_type == INV_MAIN_MB) {
+				ret = (uint64_t)i->inv_state << 20;
+				break;
+			}
+		}
+
+		endinvent_r(st);
+	}
+
+#elif defined(TUKLIB_PHYSMEM_SYSINFO)
+	struct sysinfo si;
+	if (sysinfo(&si) == 0)
+		ret = (uint64_t)si.totalram * si.mem_unit;
+#endif
+
+	return ret;
+}
diff --git a/src/common/tuklib_physmem.h b/src/common/tuklib_physmem.h
new file mode 100644
index 0000000..09e2a51
--- /dev/null
+++ b/src/common/tuklib_physmem.h
@@ -0,0 +1,28 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_physmem.h
+/// \brief      Get the amount of physical memory
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_PHYSMEM_H
+#define TUKLIB_PHYSMEM_H
+
+#include "tuklib_common.h"
+TUKLIB_DECLS_BEGIN
+
+#define tuklib_physmem TUKLIB_SYMBOL(tuklib_physmem)
+extern uint64_t tuklib_physmem(void);
+///<
+/// \brief      Get the amount of physical memory in bytes
+///
+/// \return     Amount of physical memory in bytes. On error, zero is
+///             returned.
+
+TUKLIB_DECLS_END
+#endif
diff --git a/src/common/tuklib_progname.c b/src/common/tuklib_progname.c
new file mode 100644
index 0000000..e2ef4e5
--- /dev/null
+++ b/src/common/tuklib_progname.c
@@ -0,0 +1,50 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_progname.c
+/// \brief      Program name to be displayed in messages
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#include "tuklib_progname.h"
+#include <string.h>
+
+
+#ifndef HAVE_PROGRAM_INVOCATION_NAME
+char *progname = NULL;
+#endif
+
+
+extern void
+tuklib_progname_init(char **argv)
+{
+#ifdef TUKLIB_DOSLIKE
+	// On these systems, argv[0] always has the full path and .exe
+	// suffix even if the user just types the plain program name.
+	// We modify argv[0] to make it nicer to read.
+
+	// Strip the leading path.
+	char *p = argv[0] + strlen(argv[0]);
+	while (argv[0] < p && p[-1] != '/' && p[-1] != '\\')
+		--p;
+
+	argv[0] = p;
+
+	// Strip the .exe suffix.
+	p = strrchr(p, '.');
+	if (p != NULL)
+		*p = '\0';
+
+	// Make it lowercase.
+	for (p = argv[0]; *p != '\0'; ++p)
+		if (*p >= 'A' && *p <= 'Z')
+			*p = *p - 'A' + 'a';
+#endif
+
+	progname = argv[0];
+	return;
+}
diff --git a/src/common/tuklib_progname.h b/src/common/tuklib_progname.h
new file mode 100644
index 0000000..bb80f25
--- /dev/null
+++ b/src/common/tuklib_progname.h
@@ -0,0 +1,32 @@
+///////////////////////////////////////////////////////////////////////////////
+//
+/// \file       tuklib_progname.h
+/// \brief      Program name to be displayed in messages
+//
+//  Author:     Lasse Collin
+//
+//  This file has been put into the public domain.
+//  You can do whatever you want with this file.
+//
+///////////////////////////////////////////////////////////////////////////////
+
+#ifndef TUKLIB_PROGNAME_H
+#define TUKLIB_PROGNAME_H
+
+#include "tuklib_common.h"
+#include <errno.h>
+
+TUKLIB_DECLS_BEGIN
+
+#ifdef HAVE_PROGRAM_INVOCATION_NAME
+#	define progname program_invocation_name
+#else
+#	define progname TUKLIB_SYMBOL(tuklib_progname)
+	extern char *progname;
+#endif
+
+#define tuklib_progname_init TUKLIB_SYMBOL(tuklib_progname_init)
+extern void tuklib_progname_init(char **argv);
+
+TUKLIB_DECLS_END
+#endif