Merge pull request #480 from xavierog/handle-utf8-nicks-with-mk_wcwidth

Handle utf8 nicks with mk_wcwidth()

6 files changed, 431 insertions, 9 deletions

diff --git a/src/core/Makefile.am b/src/core/Makefile.am
index fc32e17e..cc200034 100644
--- a/src/core/Makefile.am
+++ b/src/core/Makefile.am
@@ -44,6 +44,7 @@ libcore_a_SOURCES = \
 	settings.c \
 	signals.c \
 	special-vars.c \
+	utf8.c \
 	write-buffer.c
 
 structure_headers = \
diff --git a/src/core/special-vars.c b/src/core/special-vars.c
index 4dcc3d2f..fe6bbed2 100644
--- a/src/core/special-vars.c
+++ b/src/core/special-vars.c
@@ -25,10 +25,7 @@
 #include "settings.h"
 #include "servers.h"
 #include "misc.h"
-
-#define ALIGN_RIGHT 0x01
-#define ALIGN_CUT   0x02
-#define ALIGN_PAD   0x04
+#include "utf8.h"
 
 #define isvarchar(c) \
         (i_isalnum(c) || (c) == '_')
@@ -316,22 +313,28 @@ static int get_alignment_args(char **data, int *align, int *flags, char *pad)
 }
 
 /* return the aligned text */
-static char *get_alignment(const char *text, int align, int flags, char pad)
+char *get_alignment(const char *text, int align, int flags, char pad)
 {
 	GString *str;
 	char *ret;
+	int policy;
+	unsigned int cut_bytes;
 
 	g_return_val_if_fail(text != NULL, NULL);
 
+	policy = string_policy(text);
+
 	str = g_string_new(text);
 
 	/* cut */
-	if ((flags & ALIGN_CUT) && align > 0 && str->len > align)
-		g_string_truncate(str, align);
+	if ((flags & ALIGN_CUT) && align > 0 && string_width(text, policy) > align) {
+		string_chars_for_width(text, policy, align, &cut_bytes);
+		g_string_truncate(str, cut_bytes);
+	}
 
 	/* add pad characters */
 	if (flags & ALIGN_PAD) {
-		while (str->len < align) {
+		while (string_width(str->str, policy) < align) {
 			if (flags & ALIGN_RIGHT)
 				g_string_prepend_c(str, pad);
 			else
@@ -340,7 +343,7 @@ static char *get_alignment(const char *text, int align, int flags, char pad)
 	}
 
 	ret = str->str;
-        g_string_free(str, FALSE);
+	g_string_free(str, FALSE);
 	return ret;
 }
 
diff --git a/src/core/special-vars.h b/src/core/special-vars.h
index 11262dad..300dae0e 100644
--- a/src/core/special-vars.h
+++ b/src/core/special-vars.h
@@ -9,9 +9,16 @@
 #define PARSE_FLAG_ESCAPE_THEME 0x08 /* if any arguments/variables contain { or } chars, escape them with % */
 #define PARSE_FLAG_ONLY_ARGS	0x10 /* expand only arguments ($0 $1 etc.) but no other $variables */
 
+#define ALIGN_RIGHT 0x01
+#define ALIGN_CUT   0x02
+#define ALIGN_PAD   0x04
+
 typedef char* (*SPECIAL_HISTORY_FUNC)
 	(const char *text, void *item, int *free_ret);
 
+/* Cut and/or pad text so it takes exactly "align" characters on the screen */
+char *get_alignment(const char *text, int align, int flags, char pad);
+
 /* Parse and expand text after '$' character. return value has to be
    g_free()'d if `free_ret' is TRUE. */
 char *parse_special(char **cmd, SERVER_REC *server, void *item,
diff --git a/src/core/utf8.c b/src/core/utf8.c
new file mode 100644
index 00000000..29b277e1
--- /dev/null
+++ b/src/core/utf8.c
@@ -0,0 +1,135 @@
+/* utf8.c - Operations on UTF-8 strings.
+ *
+ * Copyright (C) 2002 Timo Sirainen
+ *
+ * Based on GLib code by
+ *
+ * Copyright (C) 1999 Tom Tromey
+ * Copyright (C) 2000 Red Hat, Inc.
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	 See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include "utf8.h"
+#include "module.h"
+#include "wcwidth.c"
+/* Provide is_utf8(): */
+#include "recode.h"
+
+int string_advance(char const **str, int policy)
+{
+	if (policy == TREAT_STRING_AS_UTF8) {
+		gunichar c;
+
+		c = g_utf8_get_char(*str);
+		*str = g_utf8_next_char(*str);
+
+		return unichar_isprint(c) ? mk_wcwidth(c) : 1;
+	} else {
+		/* Assume TREAT_STRING_AS_BYTES: */
+		*str += 1;
+
+		return 1;
+	}
+}
+
+int string_policy(const char *str)
+{
+	if (is_utf8()) {
+		if (str == NULL || g_utf8_validate(str, -1, NULL)) {
+			/* No string provided or valid UTF-8 string: treat as UTF-8: */
+			return TREAT_STRING_AS_UTF8;
+		}
+	}
+	return TREAT_STRING_AS_BYTES;
+}
+
+int string_length(const char *str, int policy)
+{
+	g_return_val_if_fail(str != NULL, 0);
+
+	if (policy == -1) {
+		policy = string_policy(str);
+	}
+
+	if (policy == TREAT_STRING_AS_UTF8) {
+		return g_utf8_strlen(str, -1);
+	}
+	else {
+		/* Assume TREAT_STRING_AS_BYTES: */
+		return strlen(str);
+	}
+}
+
+int string_width(const char *str, int policy)
+{
+	int len;
+
+	g_return_val_if_fail(str != NULL, 0);
+
+	if (policy == -1) {
+		policy = string_policy(str);
+	}
+
+	len = 0;
+	while (*str != '\0') {
+		len += string_advance(&str, policy);
+	}
+	return len;
+}
+
+int string_chars_for_width(const char *str, int policy, unsigned int n, unsigned int *bytes)
+{
+	const char *c, *previous_c;
+	int str_width, char_width, char_count;
+
+	g_return_val_if_fail(str != NULL, -1);
+
+	/* Handle the dummy case where n is 0: */
+	if (n == 0) {
+		if (bytes != NULL) {
+			*bytes = 0;
+		}
+		return 0;
+	}
+
+	if (policy == -1) {
+		policy = string_policy(str);
+	}
+
+	/* Iterate over characters until we reach n: */
+	char_count = 0;
+	str_width = 0;
+	c = str;
+	while (*c != '\0') {
+		previous_c = c;
+		char_width = string_advance(&c, policy);
+		if (str_width + char_width > n) {
+			/* We stepped beyond n, get one step back and stop there: */
+			c = previous_c;
+			break;
+		}
+		++ char_count;
+		str_width += char_width;
+	}
+	/* At this point, we know that char_count characters reach str_width
+	 * columns, which is less than or equal to n. */
+
+	/* Optionally provide the equivalent amount of bytes: */
+	if (bytes != NULL) {
+		*bytes = c - str;
+	}
+	return char_count;
+}
diff --git a/src/core/utf8.h b/src/core/utf8.h
new file mode 100644
index 00000000..5bb53193
--- /dev/null
+++ b/src/core/utf8.h
@@ -0,0 +1,56 @@
+#ifndef __UTF8_H
+#define __UTF8_H
+
+/* XXX I didn't check the encoding range of big5+. This is standard big5. */
+#define is_big5_los(lo) (0x40 <= (lo) && (lo) <= 0x7E) /* standard */
+#define is_big5_lox(lo) (0x80 <= (lo) && (lo) <= 0xFE) /* extended */
+#define is_big5_lo(lo)	((is_big5_los(lo) || is_big5_lox(lo)))
+#define is_big5_hi(hi)  (0x81 <= (hi) && (hi) <= 0xFE)
+#define is_big5(hi,lo) (is_big5_hi(hi) && is_big5_lo(lo))
+
+#include <glib.h>
+typedef guint32 unichar;
+
+/* Returns width for character (0-2). */
+int mk_wcwidth(unichar c);
+
+/* Advance the str pointer one character further; return the number of columns
+ * occupied by the skipped character.
+ */
+int string_advance(char const **str, int policy);
+
+/* TREAT_STRING_AS_BYTES means strings are to be treated using strncpy,
+ * strnlen, etc.
+ * TREAT_STRING_AS_UTF8 means strings are to be treated using g_utf8_*
+ * functions.
+ */
+enum str_policy {
+	TREAT_STRING_AS_BYTES,
+	TREAT_STRING_AS_UTF8
+};
+
+/* Return how the str string ought to be treated: TREAT_STRING_AS_UTF8 if the
+ * terminal handles UTF-8 and if the string appears to be a valid UTF-8 string;
+ * TREAT_STRING_AS_BYTES otherwise.
+ */
+int string_policy(const char *str);
+
+/* Return the length of the str string according to the given policy; if policy
+ * is -1, this function will call string_policy().
+ */
+int string_length(const char *str, int policy);
+/* Return the screen width of the str string according to the given policy; if
+ * policy is -1, this function will call string_policy().
+ */
+int string_width(const char *str, int policy);
+
+/* Return the amount of characters from str it takes to reach n columns, or -1 if
+ * str is NULL. Optionally return the equivalent amount of bytes.
+ * If policy is -1, this function will call string_policy().
+ */
+int string_chars_for_width(const char *str, int policy, unsigned int n, unsigned int *bytes);
+
+#define unichar_isprint(c) (((c) & ~0x80) >= 32)
+#define is_utf8_leading(c) (((c) & 0xc0) != 0x80)
+
+#endif
diff --git a/src/core/wcwidth.c b/src/core/wcwidth.c
new file mode 100644
index 00000000..80d20fa1
--- /dev/null
+++ b/src/core/wcwidth.c
@@ -0,0 +1,220 @@
+/*
+ * 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 -- 2007-05-25 (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
+ */
+
+#include "module.h"
+
+struct interval {
+  int first;
+  int last;
+};
+
+/* auxiliary function for binary search in interval table */
+static int bisearch(unichar ucs, const struct interval *table, int max) {
+  int min = 0;
+  int 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.
+ */
+
+int mk_wcwidth(unichar 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 },
+    { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
+    { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
+    { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
+    { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
+    { 0xE0100, 0xE01EF }
+  };
+
+  /* test for 8-bit control characters */
+  if (ucs == 0)
+    return 0;
+  if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
+    return -1;
+
+  /* binary search in table of non-spacing characters */
+  if (bisearch(ucs, combining,
+	       sizeof(combining) / sizeof(struct interval) - 1))
+    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)));
+}
+
+
+#if 0
+int mk_wcswidth(const unichar *pwcs, size_t n)
+{
+  int w, width = 0;
+
+  for (;*pwcs && n-- > 0; pwcs++)
+    if ((w = mk_wcwidth(*pwcs)) < 0)
+      return -1;
+    else
+      width += w;
+
+  return width;
+}
+#endif