linux-kernel - [PATCH v2 06/13] vt: use new tables in ucs.c

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250415192212.33949-7-nico@fluxnic.net>
Date: Tue, 15 Apr 2025 15:17:55 -0400
From: Nicolas Pitre <nico@...xnic.net>
To: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
	Jiri Slaby <jirislaby@...nel.org>
Cc: Nicolas Pitre <npitre@...libre.com>,
	linux-serial@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH v2 06/13] vt: use new tables in ucs.c

From: Nicolas Pitre <npitre@...libre.com>

This removes the table from ucs.c and substitutes the generated tables
from ucs_width_table.h providing comprehensive ranges for double-width
and zero-width Unicode code points.

Also implements ucs_is_zero_width() to query the new zero-width table.

Signed-off-by: Nicolas Pitre <npitre@...libre.com>
---
 drivers/tty/vt/ucs.c       | 44 +++++++++++++++++++++-----------------
 include/linux/consolemap.h |  6 +-----
 2 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/tty/vt/ucs.c b/drivers/tty/vt/ucs.c
index 0f6c087158..5e71aa3896 100644
--- a/drivers/tty/vt/ucs.c
+++ b/drivers/tty/vt/ucs.c
@@ -5,22 +5,12 @@
 #include <linux/consolemap.h>
 #include <linux/minmax.h>
 
-/* ucs_is_double_width() is based on the wcwidth() implementation by
- * Markus Kuhn -- 2007-05-26 (Unicode 5.0)
- * Latest version: https://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
- */
-
 struct ucs_interval {
 	u32 first;
 	u32 last;
 };
 
-static const struct ucs_interval ucs_double_width_ranges[] = {
-	{ 0x1100, 0x115F }, { 0x2329, 0x232A }, { 0x2E80, 0x303E },
-	{ 0x3040, 0xA4CF }, { 0xAC00, 0xD7A3 }, { 0xF900, 0xFAFF },
-	{ 0xFE10, 0xFE19 }, { 0xFE30, 0xFE6F }, { 0xFF00, 0xFF60 },
-	{ 0xFFE0, 0xFFE6 }, { 0x20000, 0x2FFFD }, { 0x30000, 0x3FFFD }
-};
+#include "ucs_width_table.h"
 
 static int interval_cmp(const void *key, const void *element)
 {
@@ -34,6 +24,27 @@ static int interval_cmp(const void *key, const void *element)
 	return 0;
 }
 
+static bool cp_in_range(u32 cp, const struct ucs_interval *ranges, size_t size)
+{
+	if (!in_range(cp, ranges[0].first, ranges[size - 1].last))
+		return false;
+
+	return __inline_bsearch(&cp, ranges, size, sizeof(*ranges),
+				interval_cmp) != NULL;
+}
+
+/**
+ * Determine if a Unicode code point is zero-width.
+ *
+ * @param cp: Unicode code point (UCS-4)
+ * Return: true if the character is zero-width, false otherwise
+ */
+bool ucs_is_zero_width(u32 cp)
+{
+	return cp_in_range(cp, ucs_zero_width_ranges,
+			   ARRAY_SIZE(ucs_zero_width_ranges));
+}
+
 /**
  * Determine if a Unicode code point is double-width.
  *
@@ -42,13 +53,6 @@ static int interval_cmp(const void *key, const void *element)
  */
 bool ucs_is_double_width(u32 cp)
 {
-	size_t size = ARRAY_SIZE(ucs_double_width_ranges);
-
-	if (!in_range(cp, ucs_double_width_ranges[0].first,
-			  ucs_double_width_ranges[size - 1].last))
-		return false;
-
-	return __inline_bsearch(&cp, ucs_double_width_ranges, size,
-				sizeof(*ucs_double_width_ranges),
-				interval_cmp) != NULL;
+	return cp_in_range(cp, ucs_double_width_ranges,
+			   ARRAY_SIZE(ucs_double_width_ranges));
 }
diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h
index 7d778752dc..b3a9118666 100644
--- a/include/linux/consolemap.h
+++ b/include/linux/consolemap.h
@@ -29,11 +29,7 @@ u32 conv_8bit_to_uni(unsigned char c);
 int conv_uni_to_8bit(u32 uni);
 void console_map_init(void);
 bool ucs_is_double_width(uint32_t cp);
-static inline bool ucs_is_zero_width(uint32_t cp)
-{
-	/* coming soon */
-	return false;
-}
+bool ucs_is_zero_width(uint32_t cp);
 #else
 static inline u16 inverse_translate(const struct vc_data *conp, u16 glyph,
 		bool use_unicode)
-- 
2.49.0