top: extend multi-byte support to 'Inspection' feature

The previous commit implemented multi-byte support for
the basic top user interaction and display provisions.
This commit completes multi-byte support by addressing
that 'Inspect Other Output' feature (the 'Y' command).

Few people probably exploit this very powerful feature
which allows the perusing of any file or piped output.
And even if nobody uses 'Y', someone will stumble over
it on the help screen and try it out. Assuming top was
not built with INSP_OFFDEMO defined, they'll end up on
the screen our translators have faithfully translated.

Without this patch, such a screen would display with a
bunch of 'unprintable' characters which will then show
in the standard (less-like) way as: '^A', '<C3>', etc.
In other words, those poor screens will be a big mess!

[ this program can even display an executable binary ]
[ while at that same time supporting Find/Find Next. ]
[ imagine, a file with no guarantee of real strings! ]
[ just try a Find using less with such binary files. ]

With this commit, the translated 'Y' demo screens will
now be properly shown, providing no invalid multi-byte
characters have been detected. Should that be the case
then they'll be displayed in that less-like way above.

And, if users go on to fully exploit this 'Y' command,
there is a good chance that a file or pipe might yield
output in a utf-8 multi-byte form. Should that be true
such output will thus be handled appropriately by top.

[ in many respects, this change was more challenging ]
[ than the basic support within the previous commit. ]
[ story of my life: least used = most effort needed. ]

Many thanks to our procps-ng translators which enabled
a proper test of these changed 'Y' command provisions:
. Vietnamese: Trần Ngọc Quân
. Polish: Jakub Bogusz
. German: Mario Blättermann
. French: Frédéric Marchal, Stéphane Aulery

[ and my sincerest apologies too, for my negligence! ]

Reference(s):
https://gitlab.com/procps-ng/procps/issues/68

Signed-off-by: Jim Warner <james.warner@comcast.net>

top/top.c

@@ -710,6 +710,26 @@ static const char *utf8_justify (const char *str, int width, int justr) {
    snprintf(buf, sizeof(buf), justr ? r_fmt : l_fmt, width, width, str, COLPADSTR);
    return buf;
 } // end: utf8_justify
+
+
+        /*
+         * Returns a physical or logical column number given a
+         * multi-byte string and a target column value */
+static int utf8_proper_col (const char *str, int col, int tophysical) {
+    const unsigned char *p = (const unsigned char *)str;
+    int clen, tlen = 0, cnum = 0;
+
+    while (*p) {
+        // -1 represents a decoding error, don't encourage repositioning ...
+        if (0 > (clen = UTF8_tab[*p])) return col;
+        if (tophysical && cnum + 1 > col) break;
+        p += clen;
+        tlen += clen;
+        if (!tophysical && tlen > col) break;
+        ++cnum;
+    }
+    return tophysical ? tlen : cnum;
+} // end: utf8_proper_col
 
 /*######  Misc Color/Display support  ####################################*/
 
@@ -2849,6 +2869,7 @@ static struct I_struc Inspect;
 
 static char   **Insp_p;           // pointers to each line start
 static int      Insp_nl;          // total lines, total Insp_p entries
+static int      Insp_utf8;        // treat Insp_buf as translatable, else raw
 static char    *Insp_buf;         // the results from insp_do_file/pipe
 static size_t   Insp_bufsz;       // allocated size of Insp_buf
 static size_t   Insp_bufrd;       // bytes actually in Insp_buf
@@ -2856,9 +2877,11 @@ static struct I_ent *Insp_sel;    // currently selected Inspect entry
 
         // Our 'make status line' macro
 #define INSP_MKSL(big,txt) { int _sz = big ? Screen_cols : 80; \
-   putp(tg2(0, (Msg_row = 3))); \
+   const char *_p; \
-   PUTT("%s%.*s", Curwin->capclr_hdr, Screen_cols -1 \
+   _sz += utf8_delta(txt); \
-      , fmtmk("%-*.*s%s", _sz, _sz, txt, Cap_clr_eol)); \
+   _p = fmtmk("%-*.*s", _sz, _sz, txt); \
+   PUTT("%s%s%.*s%s", tg2(0, (Msg_row = 3)), Curwin->capclr_hdr \
+      , utf8_embody(_p, Screen_cols), _p, Cap_clr_eol); \
    putp(Caps_off); fflush(stdout); }
 
         // Our 'row length' macro, equivalent to a strlen() call
@@ -2962,7 +2985,7 @@ static void insp_do_pipe (char *fmts, int pid) {
         /*
          * This guy is a *Helper* function serving the following two masters:
          *   insp_find_str() - find the next Insp_sel->fstr match
-         *   insp_make_row() - highlight any Insp_sel->fstr matches in-view
+         *   insp_mkrow_...  - highlight any Insp_sel->fstr matches in-view
          * If Insp_sel->fstr is found in the designated row, he returns the
          * offset from the start of the row, otherwise he returns a huge
          * integer so traditional fencepost usage can be employed. */
@@ -3045,7 +3068,7 @@ static void insp_find_str (int ch, int *col, int *row) {
          * Those will be highlighted with the current windows's capclr_msg,
          * while visible search matches display with capclr_hdr for emphasis.
          * ( we hide ugly plumbing in macros to concentrate on the algorithm ) */
-static inline void insp_make_row (int col, int row) {
+static void insp_mkrow_raw (int col, int row) {
  #define maxSZ ( Screen_cols - (to + 1) )
  #define capNO { if (hicap) { putp(Caps_off); hicap = 0; } }
  #define mkFND { PUTT("%s%.*s%s", Curwin->capclr_hdr, maxSZ, Insp_sel->fstr, Caps_off); \
@@ -3094,7 +3117,77 @@ static inline void insp_make_row (int col, int row) {
  #undef mkCTL
  #undef mkUNP
  #undef mkSTD
-} // end: insp_make_row
+} // end: insp_mkrow_raw
+
+
+        /*
+         * This guy is a *Helper* function responsible for positioning a
+         * single row in the current 'X axis' within a multi-byte string
+         * then displaying the results. Along the way he ensures control
+         * characters will then be displayed in two positions like '^A'.
+         * ( assuming they can even get past those 'gettext' utilities ) */
+static void insp_mkrow_utf8 (int col, int row) {
+ #define maxSZ ( Screen_cols - (to + 1) )
+ #define mkFND { PUTT("%s%.*s%s", Curwin->capclr_hdr, maxSZ, Insp_sel->fstr, Caps_off); \
+    fr += Insp_sel->flen; to += Insp_sel->flen; }
+#ifndef INSP_JUSTNOT
+ #define mkCTL { int x = maxSZ; const char *p = fmtmk("^%c", uch + '@'); \
+    PUTT("%s%.*s%s", Curwin->capclr_msg, x, p, Caps_off); to += 2; }
+#else
+ #define mkCTL { if ((to += 2) <= Screen_cols) \
+    PUTT("%s^%c%s", Curwin->capclr_msg, uch + '@', Caps_off); }
+#endif
+ #define doPUT(buf) if (++to <= Screen_cols) putp(buf);
+   static char buf1[2], buf2[3], buf3[4], buf4[5];
+   char tline[BIGBUFSIZ];
+   int fr, to, ofs;
+
+   col = utf8_proper_col(Insp_p[row], col, 1);
+   if (col < INSP_RLEN(row))
+      memcpy(tline, Insp_p[row] + col, sizeof(tline));
+   else tline[0] = '\n';
+
+   for (fr = 0, to = 0, ofs = 0; to < Screen_cols -1; ) {
+      if (!ofs)
+         ofs = insp_find_ofs(col + fr, row);
+      if (col + fr < ofs) {
+         unsigned char uch = tline[fr++];
+         switch (UTF8_tab[(int)uch]) {
+            case 1:
+               if (uch == '\n')   break;
+               else if (uch < 32) mkCTL
+               else { buf1[0] = uch; doPUT(buf1) }
+               break;
+            case 2:
+               buf2[0] = uch; buf2[1] = tline[fr++];
+               doPUT(buf2)
+               break;
+            case 3:
+               buf3[0] = uch; buf3[1] = tline[fr++]; buf3[2] = tline[fr++];
+               doPUT(buf3)
+               break;
+            case 4:
+               buf4[0] = uch; buf4[1] = tline[fr++]; buf4[2] = tline[fr++]; buf4[3] = tline[fr++];
+               doPUT(buf4)
+               break;
+            default:
+               buf1[0] = ' ';
+               doPUT(buf1)
+               break;
+         }
+      } else {
+         mkFND
+         ofs = 0;
+      }
+      if (col + fr >= INSP_RLEN(row)) break;
+   }
+   putp(Cap_clr_eol);
+
+ #undef maxSZ
+ #undef mkFND
+ #undef mkCTL
+ #undef doPUT
+} // end: insp_mkrow_utf8
 
 
         /*
@@ -3105,6 +3198,7 @@ static inline void insp_make_row (int col, int row) {
          * otherwise being jumpy). */
 static inline void insp_show_pgs (int col, int row, int max) {
    char buf[SMLBUFSIZ];
+   void (*mkrow_func)(int, int);
    int r = snprintf(buf, sizeof(buf), "%d", Insp_nl);
    int c = snprintf(buf, sizeof(buf), "%d", col +Screen_cols);
    int l = row +1, ls = Insp_nl;;
@@ -3118,9 +3212,11 @@ static inline void insp_show_pgs (int col, int row, int max) {
       , (unsigned long)Insp_bufrd);
    INSP_MKSL(0, buf);
 
+   mkrow_func = Insp_utf8 ? insp_mkrow_utf8 : insp_mkrow_raw;
+
    for ( ; max && row < Insp_nl; row++) {
       putp("\n");
-      insp_make_row(col, row);
+      mkrow_func(col, row);
       --max;
    }
 
@@ -3214,7 +3310,13 @@ signify_that:
          case '&':
          case '/':
          case 'n':
+            if (!Insp_utf8)
                insp_find_str(key, &curcol, &curlin);
+            else {
+               int tmpcol = utf8_proper_col(Insp_p[curlin], curcol, 1);
+               insp_find_str(key, &tmpcol, &curlin);
+               curcol = utf8_proper_col(Insp_p[curlin], tmpcol, 0);
+            }
             // must re-hide cursor in case a prompt for a string makes it huge
             putp((Cursor_state = Cap_curs_hide));
             break;
@@ -3300,6 +3402,7 @@ signify_that:
             INSP_BUSY;
             Insp_sel = &Inspect.tab[sel];
             Inspect.tab[sel].func(Inspect.tab[sel].fmts, pid);
+            Insp_utf8 = utf8_delta(Insp_buf);
             key = insp_view_choice(p);
             free(Insp_buf);
             free(Insp_p);

top/top.h

@@ -683,6 +683,7 @@ typedef struct WIN_t {
 //atic int           utf8_delta (const char *str);
 //atic int           utf8_embody (const char *str, int width);
 //atic const char   *utf8_justify (const char *str, int width, int justr);
+//atic int           utf8_proper_col (const char *str, int col, int tophysical);
 /*------  Misc Color/Display support  ------------------------------------*/
 //atic void          capsmk (WIN_t *q);
 //atic void          show_msg (const char *str);
@@ -745,7 +746,8 @@ typedef struct WIN_t {
 //atic void          insp_do_pipe (char *fmts, int pid);
 //atic inline int    insp_find_ofs (int col, int row);
 //atic void          insp_find_str (int ch, int *col, int *row);
-//atic inline void   insp_make_row (int col, int row);
+//atic void          insp_mkrow_raw (int col, int row);
+//atic void          insp_mkrow_utf8 (int col, int row);
 //atic void          insp_show_pgs (int col, int row, int max);
 //atic int           insp_view_choice (proc_t *obj);
 //atic void          inspection_utility (int pid);