libbb: better unicode width support. Hopefully fixes bug 839.

Also opens up a possibility to make other unicode stuff smaller
and more correct later. but:

function                                             old     new   delta
static.combining                                       -     516    +516
bb_wcwidth                                             -     328    +328
unicode_cut_nchars                                     -     141    +141
mbstowc_internal                                       -      93     +93
in_table                                               -      78     +78
cal_main                                             899     961     +62
static.combining0x10000                                -      40     +40
unicode_strlen                                         -      31     +31
bb_mbstrlen                                           31       -     -31
bb_mbstowcs                                          173     102     -71
------------------------------------------------------------------------------
(add/remove: 7/1 grow/shrink: 1/1 up/down: 1289/-102)        Total: 1187 bytes

Uses code of Markus Kuhn, which is in public domain:
http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
"Permission to use, copy, modify, and distribute this software
 for any purpose and without fee is hereby granted. The author
 disclaims all warranties with regard to this software."

Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>

coreutils/cal.c

@@ -16,8 +16,8 @@
  *
  * Major size reduction... over 50% (>1.5k) on i386.
  */
-
 #include "libbb.h"
+#include "unicode.h"
 
 /* We often use "unsigned" intead of "int", it's easier to div on most CPUs */
 
@@ -83,9 +83,16 @@ int cal_main(int argc UNUSED_PARAM, char **argv)
 	time_t now;
 	unsigned month, year, flags, i;
 	char *month_names[12];
-	char day_headings[28];	/* 28 for julian, 21 for nonjulian */
+	/* normal heading: */
+	/* "Su Mo Tu We Th Fr Sa" */
+	/* -j heading: */
+	/* " Su  Mo  Tu  We  Th  Fr  Sa" */
+	char day_headings[ENABLE_FEATURE_ASSUME_UNICODE ? 28 * 6 : 28];
+	IF_FEATURE_ASSUME_UNICODE(char *hp = day_headings;)
 	char buf[40];
 
+	init_unicode();
+
 	flags = getopt32(argv, "jy");
 	/* This sets julian = flags & 1: */
 	option_mask32 &= 1;
@@ -122,15 +129,24 @@ int cal_main(int argc UNUSED_PARAM, char **argv)
 
 		if (i < 7) {
 			zero_tm.tm_wday = i;
-//FIXME: unicode
-//Bug 839:
-//testcase with doublewidth Japanese chars: "LANG=zh_TW.utf8 cal"
-//perhaps use wc[s]width() to probe terminal width
 			/* abbreviated weekday name according to locale */
 			strftime(buf, sizeof(buf), "%a", &zero_tm);
+#if ENABLE_FEATURE_ASSUME_UNICODE
+			if (julian)
+				*hp++ = ' ';
+			{
+				char *two_wchars = unicode_cut_nchars(2, buf);
+				strcpy(hp, two_wchars);
+				free(two_wchars);
+			}
+			hp += strlen(hp);
+			*hp++ = ' ';
+#else
 			strncpy(day_headings + i * (3+julian) + julian, buf, 2);
+#endif
 		}
 	} while (++i < 12);
+	IF_FEATURE_ASSUME_UNICODE(hp[-1] = '\0';)
 
 	if (month) {
 		unsigned row, len, days[MAXDAYS];

coreutils/df.c

@@ -178,7 +178,7 @@ int df_main(int argc UNUSED_PARAM, char **argv)
 #endif
 
 #if ENABLE_FEATURE_ASSUME_UNICODE
-			dev_len = bb_mbstrlen(device);
+			dev_len = unicode_strlen(device);
 			if (dev_len > 20) {
 				printf("%s\n%20s", device, "");
 			} else {

coreutils/expand.c

@@ -49,7 +49,7 @@ static void expand(FILE *file, unsigned tab_size, unsigned opt)
 				unsigned len;
 				*ptr = '\0';
 # if ENABLE_FEATURE_ASSUME_UNICODE
-				len = bb_mbstrlen(ptr_strbeg);
+				len = unicode_strlen(ptr_strbeg);
 # else
 				len = ptr - ptr_strbeg;
 # endif
@@ -105,7 +105,7 @@ static void unexpand(FILE *file, unsigned tab_size, unsigned opt)
 				char c;
 				c = ptr[n];
 				ptr[n] = '\0';
-				len = bb_mbstrlen(ptr);
+				len = unicode_strlen(ptr);
 				ptr[n] = c;
 			}
 # else

coreutils/ls.c

@@ -550,7 +550,7 @@ static void showfiles(struct dnode **dn, unsigned nfiles)
 	} else {
 		/* find the longest file name, use that as the column width */
 		for (i = 0; dn[i]; i++) {
-			int len = bb_mbstrlen(dn[i]->name);
+			int len = unicode_strlen(dn[i]->name);
 			if (column_width < len)
 				column_width = len;
 		}
@@ -742,7 +742,7 @@ static int print_name(const char *name)
 {
 	if (option_mask32 & OPT_Q) {
 #if ENABLE_FEATURE_ASSUME_UNICODE
-		unsigned len = 2 + bb_mbstrlen(name);
+		unsigned len = 2 + unicode_strlen(name);
 #else
 		unsigned len = 2;
 #endif
@@ -762,7 +762,7 @@ static int print_name(const char *name)
 	/* No -Q: */
 #if ENABLE_FEATURE_ASSUME_UNICODE
 	fputs(name, stdout);
-	return bb_mbstrlen(name);
+	return unicode_strlen(name);
 #else
 	return printf("%s", name);
 #endif

include/unicode.h

@@ -13,13 +13,16 @@ enum {
 
 #if !ENABLE_FEATURE_ASSUME_UNICODE
 
-# define bb_mbstrlen(string) strlen(string)
+# define unicode_strlen(string) strlen(string)
+# define unicode_scrlen(string) TODO
 # define unicode_status UNICODE_OFF
 # define init_unicode() ((void)0)
 
 #else
 
-size_t bb_mbstrlen(const char *string) FAST_FUNC;
+size_t FAST_FUNC unicode_strlen(const char *string);
+char* FAST_FUNC unicode_cut_nchars(unsigned width, const char *src);
+unsigned FAST_FUNC unicode_padding_to_width(unsigned width, const char *src);
 
 # if ENABLE_LOCALE_SUPPORT
 
@@ -30,7 +33,7 @@ void init_unicode(void) FAST_FUNC;
 
 # else
 
-/* Crude "locale support" which knows only C and Unicode locales */
+/* Homegrown Unicode support. It knows only C and Unicode locales. */
 
 #  if !ENABLE_FEATURE_CHECK_UNICODE_IN_ENV
 #   define unicode_status UNICODE_ON
@@ -52,6 +55,7 @@ void init_unicode(void) FAST_FUNC;
 #  define iswspace  bb_iswspace
 #  define iswalnum  bb_iswalnum
 #  define iswpunct  bb_iswpunct
+#  define wcwidth   bb_wcwidth
 
 typedef int32_t wint_t;
 typedef struct {
@@ -68,27 +72,6 @@ int iswpunct(wint_t wc) FAST_FUNC;
 
 # endif /* !LOCALE_SUPPORT */
 
-
-# if 0 /* TODO: better support for printfing Unicode fields: */
-
-/* equivalent to printf("%-20.20s", str) */
-char unicode_buffer[20 * MB_CUR_MAX];
-printf("%s", unicode_exact(20, str, unicode_buffer);
-/* no need to free() anything */
-
-/* equivalent to printf("%-20s", str) */
-char *malloced = unicode_minimum(20, str);
-printf("%s", malloced);
-free(malloced); /* ugh */
-
-/* equivalent to printf("%-20s", str), better one */
-printf("%s%*s", str, unicode_pad_to_width(str, 20), "");
-/* equivalent to printf("%20s", str) */
-printf("%*s%s", unicode_pad_to_width(str, 20), "", str);
-
-# endif
-
-
 #endif /* FEATURE_ASSUME_UNICODE */
 
 #endif

libbb/lineedit.c

@@ -878,7 +878,7 @@ static void showfiles(void)
 
 	/* find the longest file name - use that as the column width */
 	for (row = 0; row < nrows; row++) {
-		l = bb_mbstrlen(matches[row]);
+		l = unicode_strlen(matches[row]);
 		if (column_width < l)
 			column_width = l;
 	}
@@ -898,7 +898,7 @@ static void showfiles(void)
 
 		for (nc = 1; nc < ncols && n+nrows < nfiles; n += nrows, nc++) {
 			printf("%s%-*s", matches[n],
-				(int)(column_width - bb_mbstrlen(matches[n])), ""
+				(int)(column_width - unicode_strlen(matches[n])), ""
 			);
 		}
 		puts(matches[n]);

libbb/unicode.c

@@ -9,22 +9,19 @@
 #include "libbb.h"
 #include "unicode.h"
 
-/* If it's not a constant... */
+/* If it's not #defined as a constant in unicode.h... */
 #ifndef unicode_status
 uint8_t unicode_status;
 #endif
 
-size_t FAST_FUNC bb_mbstrlen(const char *string)
+/* This file is compiled only if FEATURE_ASSUME_UNICODE is on.
-{
+ * We check other options and decide whether to use libc support
-	size_t width = mbstowcs(NULL, string, INT_MAX);
+ * via locale, or use our own logic:
-	if (width == (size_t)-1L)
+ */
-		return strlen(string);
-	return width;
-}
 
 #if ENABLE_LOCALE_SUPPORT
 
-/* Unicode support using libc */
+/* Unicode support using libc locale support. */
 
 void FAST_FUNC init_unicode(void)
 {
@@ -34,12 +31,12 @@ void FAST_FUNC init_unicode(void)
 	if (unicode_status != UNICODE_UNKNOWN)
 		return;
 
-	unicode_status = bb_mbstrlen(unicode_0x394) == 1 ? UNICODE_ON : UNICODE_OFF;
+	unicode_status = unicode_strlen(unicode_0x394) == 1 ? UNICODE_ON : UNICODE_OFF;
 }
 
 #else
 
-/* Crude "locale support" which knows only C and Unicode locales */
+/* Homegrown Unicode support. It knows only C and Unicode locales. */
 
 # if ENABLE_FEATURE_CHECK_UNICODE_IN_ENV
 void FAST_FUNC init_unicode(void)
@@ -93,7 +90,6 @@ static size_t wcrtomb_internal(char *s, wchar_t wc)
 	s[0] = wc | (uint8_t)(0x3f00 >> n);
 	return n;
 }
-
 size_t FAST_FUNC wcrtomb(char *s, wchar_t wc, mbstate_t *ps UNUSED_PARAM)
 {
 	if (unicode_status != UNICODE_ON) {
@@ -103,7 +99,6 @@ size_t FAST_FUNC wcrtomb(char *s, wchar_t wc, mbstate_t *ps UNUSED_PARAM)
 
 	return wcrtomb_internal(s, wc);
 }
-
 size_t FAST_FUNC wcstombs(char *dest, const wchar_t *src, size_t n)
 {
 	size_t org_n = n;
@@ -144,6 +139,51 @@ size_t FAST_FUNC wcstombs(char *dest, const wchar_t *src, size_t n)
 	return org_n - n;
 }
 
+static const char *mbstowc_internal(wchar_t *res, const char *src)
+{
+	int bytes;
+	unsigned c = (unsigned char) *src++;
+
+	if (c <= 0x7f) {
+		*res = c;
+		return src;
+	}
+
+	/* 80-7FF -> 110yyyxx 10xxxxxx */
+	/* 800-FFFF -> 1110yyyy 10yyyyxx 10xxxxxx */
+	/* 10000-1FFFFF -> 11110zzz 10zzyyyy 10yyyyxx 10xxxxxx */
+	/* 200000-3FFFFFF -> 111110tt 10zzzzzz 10zzyyyy 10yyyyxx 10xxxxxx */
+	/* 4000000-FFFFFFFF -> 111111tt 10tttttt 10zzzzzz 10zzyyyy 10yyyyxx 10xxxxxx */
+	bytes = 0;
+	do {
+		c <<= 1;
+		bytes++;
+	} while ((c & 0x80) && bytes < 6);
+	if (bytes == 1)
+		return NULL;
+	c = (uint8_t)(c) >> bytes;
+
+	while (--bytes) {
+		unsigned ch = (unsigned char) *src++;
+		if ((ch & 0xc0) != 0x80) {
+			return NULL;
+		}
+		c = (c << 6) + (ch & 0x3f);
+	}
+
+	/* TODO */
+	/* Need to check that c isn't produced by overlong encoding */
+	/* Example: 11000000 10000000 converts to NUL */
+	/* 11110000 10000000 10000100 10000000 converts to 0x100 */
+	/* correct encoding: 11000100 10000000 */
+	if (c <= 0x7f) { /* crude check */
+		return NULL;
+		//or maybe 0xfffd; /* replacement character */
+	}
+
+	*res = c;
+	return src;
+}
 size_t FAST_FUNC mbstowcs(wchar_t *dest, const char *src, size_t n)
 {
 	size_t org_n = n;
@@ -162,58 +202,20 @@ size_t FAST_FUNC mbstowcs(wchar_t *dest, const char *src, size_t n)
 	}
 
 	while (n) {
-		int bytes;
+		wchar_t wc;
-		unsigned c = (unsigned char) *src++;
+		const char *rc = mbstowc_internal(dest ? dest : &wc, src);
-
+		if (rc == NULL) /* error */
-		if (c <= 0x7f) {
-			if (dest)
-				*dest++ = c;
-			if (c == '\0')
-				break;
-			n--;
-			continue;
-		}
-
-		/* 80-7FF -> 110yyyxx 10xxxxxx */
-		/* 800-FFFF -> 1110yyyy 10yyyyxx 10xxxxxx */
-		/* 10000-1FFFFF -> 11110zzz 10zzyyyy 10yyyyxx 10xxxxxx */
-		/* 200000-3FFFFFF -> 111110tt 10zzzzzz 10zzyyyy 10yyyyxx 10xxxxxx */
-		/* 4000000-FFFFFFFF -> 111111tt 10tttttt 10zzzzzz 10zzyyyy 10yyyyxx 10xxxxxx */
-		bytes = 0;
-		do {
-			c <<= 1;
-			bytes++;
-		} while ((c & 0x80) && bytes < 6);
-		if (bytes == 1)
 			return (size_t) -1L;
-		c = (uint8_t)(c) >> bytes;
-
-		while (--bytes) {
-			unsigned ch = (unsigned char) *src++;
-			if ((ch & 0xc0) != 0x80) {
-				return (size_t) -1L;
-			}
-			c = (c << 6) + (ch & 0x3f);
-		}
-
-		/* TODO */
-		/* Need to check that c isn't produced by overlong encoding */
-		/* Example: 11000000 10000000 converts to NUL */
-		/* 11110000 10000000 10000100 10000000 converts to 0x100 */
-		/* correct encoding: 11000100 10000000 */
-		if (c <= 0x7f) { /* crude check */
-			return (size_t) -1L;
-			//or maybe: c = 0xfffd; /* replacement character */
-		}
-
 		if (dest)
-			*dest++ = c;
+			dest++;
 		n--;
 	}
 
 	return org_n - n;
 }
 
+#include "unicode_wcwidth.c"
+
 int FAST_FUNC iswspace(wint_t wc)
 {
 	return (unsigned)wc <= 0x7f && isspace(wc);
@@ -229,4 +231,98 @@ int FAST_FUNC iswpunct(wint_t wc)
 	return (unsigned)wc <= 0x7f && ispunct(wc);
 }
 
+#endif /* Homegrown Unicode support */
+
+
+/* The rest is mostly same for libc and for "homegrown" support */
+
+size_t FAST_FUNC unicode_strlen(const char *string)
+{
+	size_t width = mbstowcs(NULL, string, INT_MAX);
+	if (width == (size_t)-1L)
+		return strlen(string);
+	return width;
+}
+
+char* FAST_FUNC unicode_cut_nchars(unsigned width, const char *src)
+{
+	char *dst;
+	unsigned dst_len;
+
+	if (unicode_status != UNICODE_ON)
+		return xasprintf("%-*.*s", width, width, src);
+
+	dst = NULL;
+	dst_len = 0;
+	while (1) {
+		int w;
+		wchar_t wc;
+
+		dst = xrealloc(dst, dst_len + 2 * MB_CUR_MAX);
+#if ENABLE_LOCALE_SUPPORT
+		{
+			mbstate_t mbst = { 0 };
+			ssize_t rc = mbsrtowcs(&wc, &src, 1, &mbst);
+			if (rc <= 0) /* error, or end-of-string */
+				break;
+		}
+#else
+		src = mbstowc_internal(&wc, src);
+		if (!src || wc == 0) /* error, or end-of-string */
+			break;
 #endif
+		w = wcwidth(wc);
+		if (w < 0) /* non-printable wchar */
+			break;
+		width -= w;
+		if ((int)width < 0) { /* string is longer than width */
+			width += w;
+			while (width) {
+				dst[dst_len++] = ' ';
+				width--;
+			}
+			break;
+		}
+#if ENABLE_LOCALE_SUPPORT
+		{
+			mbstate_t mbst = { 0 };
+			dst_len += wcrtomb(&dst[dst_len], wc, &mbst);
+		}
+#else
+		dst_len += wcrtomb_internal(&dst[dst_len], wc);
+#endif
+	}
+	dst[dst_len] = '\0';
+	return dst;
+}
+
+unsigned FAST_FUNC unicode_padding_to_width(unsigned width, const char *src)
+{
+	if (unicode_status != UNICODE_ON) {
+		return width - strnlen(src, width);
+	}
+
+	while (1) {
+		int w;
+		wchar_t wc;
+
+#if ENABLE_LOCALE_SUPPORT
+		{
+			mbstate_t mbst = { 0 };
+			ssize_t rc = mbsrtowcs(&wc, &src, 1, &mbst);
+			if (rc <= 0) /* error, or end-of-string */
+				return width;
+		}
+#else
+		src = mbstowc_internal(&wc, src);
+		if (!src || wc == 0) /* error, or end-of-string */
+			return width;
+#endif
+		w = wcwidth(wc);
+		if (w < 0) /* non-printable wchar */
+			return width;
+		width -= w;
+		if ((int)width <= 0) /* string is longer than width */
+			return 0;
+	}
+}

libbb/unicode_wcwidth.c

@@ -0,0 +1,217 @@
+/*
+ * This is an implementation of wcwidth() and wcswidth() (defined in
+ * IEEE Std 1002.1-2001) for Unicode.
+ *
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
+ * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
+ *
+ * In fixed-width output devices, Latin characters all occupy a single
+ * "cell" position of equal width, whereas ideographic CJK characters
+ * occupy two such cells. Interoperability between terminal-line
+ * applications and (teletype-style) character terminals using the
+ * UTF-8 encoding requires agreement on which character should advance
+ * the cursor by how many cell positions. No established formal
+ * standards exist at present on which Unicode character shall occupy
+ * how many cell positions on character terminals. These routines are
+ * a first attempt of defining such behavior based on simple rules
+ * applied to data provided by the Unicode Consortium.
+ *
+ * For some graphical characters, the Unicode standard explicitly
+ * defines a character-cell width via the definition of the East Asian
+ * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
+ * In all these cases, there is no ambiguity about which width a
+ * terminal shall use. For characters in the East Asian Ambiguous (A)
+ * class, the width choice depends purely on a preference of backward
+ * compatibility with either historic CJK or Western practice.
+ * Choosing single-width for these characters is easy to justify as
+ * the appropriate long-term solution, as the CJK practice of
+ * displaying these characters as double-width comes from historic
+ * implementation simplicity (8-bit encoded characters were displayed
+ * single-width and 16-bit ones double-width, even for Greek,
+ * Cyrillic, etc.) and not any typographic considerations.
+ *
+ * Much less clear is the choice of width for the Not East Asian
+ * (Neutral) class. Existing practice does not dictate a width for any
+ * of these characters. It would nevertheless make sense
+ * typographically to allocate two character cells to characters such
+ * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
+ * represented adequately with a single-width glyph. The following
+ * routines at present merely assign a single-cell width to all
+ * neutral characters, in the interest of simplicity. This is not
+ * entirely satisfactory and should be reconsidered before
+ * establishing a formal standard in this area. At the moment, the
+ * decision which Not East Asian (Neutral) characters should be
+ * represented by double-width glyphs cannot yet be answered by
+ * applying a simple rule from the Unicode database content. Setting
+ * up a proper standard for the behavior of UTF-8 character terminals
+ * will require a careful analysis not only of each Unicode character,
+ * but also of each presentation form, something the author of these
+ * routines has avoided to do so far.
+ *
+ * http://www.unicode.org/unicode/reports/tr11/
+ *
+ * Markus Kuhn -- 2007-05-26 (Unicode 5.0)
+ *
+ * Permission to use, copy, modify, and distribute this software
+ * for any purpose and without fee is hereby granted. The author
+ * disclaims all warranties with regard to this software.
+ *
+ * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
+ */
+
+struct interval {
+	uint16_t first;
+	uint16_t last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int in_table(unsigned ucs, const struct interval *table, unsigned max)
+{
+	unsigned min = 0;
+	unsigned mid;
+
+	if (ucs < table[0].first || ucs > table[max].last)
+		return 0;
+
+	while (max >= min) {
+		mid = (min + max) / 2;
+		if (ucs > table[mid].last)
+    			min = mid + 1;
+		else if (ucs < table[mid].first)
+    			max = mid - 1;
+		else
+    			return 1;
+	}
+	return 0;
+}
+
+
+/* The following two functions define the column width of an ISO 10646
+ * character as follows:
+ *
+ *    - The null character (U+0000) has a column width of 0.
+ *
+ *    - Other C0/C1 control characters and DEL will lead to a return
+ *      value of -1.
+ *
+ *    - Non-spacing and enclosing combining characters (general
+ *      category code Mn or Me in the Unicode database) have a
+ *      column width of 0.
+ *
+ *    - SOFT HYPHEN (U+00AD) has a column width of 1.
+ *
+ *    - Other format characters (general category code Cf in the Unicode
+ *      database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
+ *
+ *    - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
+ *      have a column width of 0.
+ *
+ *    - Spacing characters in the East Asian Wide (W) or East Asian
+ *      Full-width (F) category as defined in Unicode Technical
+ *      Report #11 have a column width of 2.
+ *
+ *    - All remaining characters (including all printable
+ *      ISO 8859-1 and WGL4 characters, Unicode control characters,
+ *      etc.) have a column width of 1.
+ *
+ * This implementation assumes that wchar_t characters are encoded
+ * in ISO 10646.
+ */
+static int wcwidth(unsigned ucs)
+{
+	/* sorted list of non-overlapping intervals of non-spacing characters */
+	/* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
+	static const struct interval combining[] = {
+		{ 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
+		{ 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
+		{ 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
+		{ 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
+		{ 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
+		{ 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
+		{ 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
+		{ 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
+		{ 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
+		{ 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
+		{ 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
+		{ 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
+		{ 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
+		{ 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
+		{ 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C },
+		{ 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D },
+		{ 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 },
+		{ 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 },
+		{ 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC },
+		{ 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
+		{ 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D },
+		{ 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 },
+		{ 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E },
+		{ 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC },
+		{ 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 },
+		{ 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E },
+		{ 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 },
+		{ 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 },
+		{ 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 },
+		{ 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F },
+		{ 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
+		{ 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
+		{ 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
+		{ 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
+		{ 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
+		{ 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
+		{ 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
+		{ 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
+		{ 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
+		{ 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
+		{ 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
+		{ 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
+		{ 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }
+	};
+	static const struct interval combining0x10000[] = {
+		{ 0x0A01, 0x0A03 }, { 0x0A05, 0x0A06 }, { 0x0A0C, 0x0A0F },
+		{ 0x0A38, 0x0A3A }, { 0x0A3F, 0x0A3F }, { 0xD167, 0xD169 },
+		{ 0xD173, 0xD182 }, { 0xD185, 0xD18B }, { 0xD1AA, 0xD1AD },
+		{ 0xD242, 0xD244 }
+	};
+
+	if (ucs == 0)
+		return 0;
+	/* test for 8-bit control characters (00-1f, 80-9f, 7f) */
+	if ((ucs & ~0x80) < 0x20 || ucs == 0x7f)
+		return -1;
+	if (ucs < 0x0300) /* optimization */
+		return 1;
+
+	/* binary search in table of non-spacing characters */
+	if (in_table(ucs, combining, ARRAY_SIZE(combining) - 1))
+		return 0;
+
+	if (ucs < 0x1100) /* optimization */
+		return 1;
+
+	/* binary search in table of non-spacing characters, cont. */
+	if (in_table(ucs ^ 0x10000, combining0x10000, ARRAY_SIZE(combining0x10000) - 1))
+		return 0;
+	if (ucs == 0xE0001
+	 || (ucs >= 0xE0020 && ucs <= 0xE007F)
+	 || (ucs >= 0xE0100 && ucs <= 0xE01EF)
+	) {
+		return 0;
+	}
+
+	/* if we arrive here, ucs is not a combining or C0/C1 control character */
+
+	return 1 +
+		(  (/*ucs >= 0x1100 &&*/ ucs <= 0x115f) /* Hangul Jamo init. consonants */
+		|| ucs == 0x2329
+		|| ucs == 0x232a
+		|| (ucs >= 0x2e80 && ucs <= 0xa4cf && ucs != 0x303f) /* CJK ... Yi */
+		|| (ucs >= 0xac00 && ucs <= 0xd7a3) /* Hangul Syllables */
+		|| (ucs >= 0xf900 && ucs <= 0xfaff) /* CJK Compatibility Ideographs */
+		|| (ucs >= 0xfe10 && ucs <= 0xfe19) /* Vertical forms */
+		|| (ucs >= 0xfe30 && ucs <= 0xfe6f) /* CJK Compatibility Forms */
+		|| (ucs >= 0xff00 && ucs <= 0xff60) /* Fullwidth Forms */
+		|| (ucs >= 0xffe0 && ucs <= 0xffe6)
+		|| (ucs >= 0x20000 && ucs <= 0x2fffd)
+		|| (ucs >= 0x30000 && ucs <= 0x3fffd)
+		);
+}

modutils/lsmod.c

@@ -64,7 +64,7 @@ int lsmod_main(int argc UNUSED_PARAM, char **argv UNUSED_PARAM)
 			} else
 				token[3] = (char *) "";
 # if ENABLE_FEATURE_ASSUME_UNICODE
-			name_len = bb_mbstrlen(token[0]);
+			name_len = unicode_strlen(token[0]);
 			name_len = (name_len > 19) ? 0 : 19 - name_len;
 			printf("%s%*s %8s %2s %s\n", token[0], name_len, "", token[1], token[2], token[3]);
 # else
@@ -78,7 +78,7 @@ int lsmod_main(int argc UNUSED_PARAM, char **argv UNUSED_PARAM)
 			// so trimming the trailing char is just what we need!
 			token[3][strlen(token[3])-1] = '\0';
 # if ENABLE_FEATURE_ASSUME_UNICODE
-			name_len = bb_mbstrlen(token[0]);
+			name_len = unicode_strlen(token[0]);
 			name_len = (name_len > 19) ? 0 : 19 - name_len;
 			printf("%s%*s %8s %2s %s\n", token[0], name_len, "", token[1], token[2], token[3]);
 # else

networking/udhcp/dumpleases.c

@@ -72,7 +72,7 @@ int dumpleases_main(int argc UNUSED_PARAM, char **argv)
 		/* lease.hostname is char[20] and is always NUL terminated */
 #if ENABLE_FEATURE_ASSUME_UNICODE
 		printf(" %-16s%s%*s", inet_ntoa(addr), lease.hostname,
-			20 - (int)bb_mbstrlen(lease.hostname), "");
+			20 - (int)unicode_strlen(lease.hostname), "");
 #else
 		printf(" %-16s%-20s", inet_ntoa(addr), lease.hostname);
 #endif