Treat Unicode formatting chars as control chars if -U is set.

Makefile.aut

@@ -22,7 +22,7 @@ DISTFILES_W = \
  defines.wn Makefile.wnm Makefile.wnb \
  configure 
 UNICODE_FILES = \
- compose.uni ubin.uni wide.uni
+ compose.uni fmt.uni ubin.uni wide.uni
 DISTFILES = \
  ${SRC} regexp.c regexp.h \
  COPYING INSTALL LICENSE Makefile.in Makefile.aut NEWS README \
@@ -104,7 +104,9 @@ ${srcdir}/lessecho.man: ${srcdir}/lessecho.nro
  ${NROFF} ${srcdir}/lessecho.nro >${srcdir}/lessecho.man
 
 compose.uni: unicode/UnicodeData.txt
- ./mkutable -f2 Mn Me Cf -- unicode/UnicodeData.txt > $@
+ ./mkutable -f2 Mn Me -- unicode/UnicodeData.txt > $@
+fmt.uni: unicode/UnicodeData.txt
+ ./mkutable -f2 Cf -- unicode/UnicodeData.txt > $@
 ubin.uni: unicode/UnicodeData.txt
  ./mkutable -f2 Cc Cs Co Zl Zp -- unicode/UnicodeData.txt > $@
 wide.uni: unicode/EastAsianWidth.txt

charset.c

@@ -20,6 +20,8 @@
 #include <windows.h>
 #endif
 
+extern int bs_mode;
+
 public int utf_mode = 0;
 
 /*
@@ -739,6 +741,10 @@ DECLARE_RANGE_TABLE_START(wide)
 #include "wide.uni"
 DECLARE_RANGE_TABLE_END(wide)
 
+DECLARE_RANGE_TABLE_START(fmt)
+#include "fmt.uni"
+DECLARE_RANGE_TABLE_END(fmt)
+
 /* comb_table is special pairs, not ranges. */
 static struct wchar_range comb_table[] = {
  {0x0644,0x0622}, {0x0644,0x0623}, {0x0644,0x0625}, {0x0644,0x0627},
@@ -779,7 +785,8 @@ is_in_table(ch, table)
 is_composing_char(ch)
  LWCHAR ch;
 {
- return is_in_table(ch, &compose_table);
+ return is_in_table(ch, &compose_table) ||
+ (bs_mode != BS_CONTROL && is_in_table(ch, &fmt_table));
 }
 
 /*
@@ -789,7 +796,8 @@ is_composing_char(ch)
 is_ubin_char(ch)
  LWCHAR ch;
 {
- int ubin = is_in_table(ch, &ubin_table);
+ int ubin = is_in_table(ch, &ubin_table) ||
+ (bs_mode == BS_CONTROL && is_in_table(ch, &fmt_table));
 #if MSDOS_COMPILER==WIN32C
  if (!ubin && utf_mode == 2 && ch < 0x10000)
  {

fmt.uni

@@ -0,0 +1,19 @@
+/* Generated by "./mkutable -f2 Cf -- unicode/UnicodeData.txt" on Sun Nov 12 16:13:49 PST 2017 */
+ { 0x00ad, 0x00ad }, /* Cf */
+ { 0x0600, 0x0605 }, /* Cf */
+ { 0x061c, 0x061c }, /* Cf */
+ { 0x06dd, 0x06dd }, /* Cf */
+ { 0x070f, 0x070f }, /* Cf */
+ { 0x08e2, 0x08e2 }, /* Cf */
+ { 0x180e, 0x180e }, /* Cf */
+ { 0x200b, 0x200f }, /* Cf */
+ { 0x202a, 0x202e }, /* Cf */
+ { 0x2060, 0x2064 }, /* Cf */
+ { 0x2066, 0x206f }, /* Cf */
+ { 0xfeff, 0xfeff }, /* Cf */
+ { 0xfff9, 0xfffb }, /* Cf */
+ { 0x110bd, 0x110bd }, /* Cf */
+ { 0x1bca0, 0x1bca3 }, /* Cf */
+ { 0x1d173, 0x1d17a }, /* Cf */
+ { 0xe0001, 0xe0001 }, /* Cf */
+ { 0xe0020, 0xe007f }, /* Cf */

less.nro.VER

@@ -829,8 +829,8 @@ Specifies a tags file to be used instead of "tags".
 Causes backspaces and carriage returns to be treated as printable characters;
 that is, they are sent to the terminal when they appear in the input.
 .IP "\-U or \-\-UNDERLINE-SPECIAL"
-Causes backspaces, tabs and carriage returns to be
-treated as control characters;
+Causes backspaces, tabs, carriage returns and "formatting characters"
+(as defined by Unicode) to be treated as control characters;
 that is, they are handled as specified by the \-r option.
 .sp
 By default, if neither \-u nor \-U is given,

version.c

@@ -843,6 +843,8 @@ v524 10/24/17 Fix getcc bug.
 v525 10/24/17 Change M command to mark last displayed line.
 v526 10/25/17 Fix search hilite bug introduced in v517.
 v527 10/30/17 Fix search hilite bug on last page with -a.
+v528 11/3/17 Make second ESC-u clear status column.
+v529 11/12/17 Display Unicode formatting chars in hex if -U is set.
 */
 
-char version[] = "527";
+char version[] = "529";