Convert ancient encodings on the game's output.

    Neither old Crawl nor NetHack accept non-ASCII input, so I didn't bother
    implementing that.
    (Adam Borowski <kilobyte@angband.pl>)

git-svn-id: svn://katsu.triplehelix.org/dgamelaunch/trunk@598 db0b04b0-f4d1-0310-9a6d-de3e77497b0e

diff --git a/ttyrec.c b/ttyrec.c
index ad9bd3bfe0a92b55158c781b0498e650e78afe8f..586f26e9a82c26b77dba1a4f2b93f53710de8b9f 100644 (file)
--- a/ttyrec.c
+++ b/ttyrec.c
@@ -62,6 +62,7 @@
 # include <stropts.h>
 #endif
 #include <stdlib.h>
+#include <stdint.h>
 
 #include "ttyrec.h"
 #include "io.h"
@@ -84,6 +85,8 @@ int master;
 struct termios tt;
 struct winsize win;
 
+int ancient_encoding = 0;
+
 void
 ttyrec_id(int game, char *username, char *ttyrec_filename)
 {
@@ -151,6 +154,7 @@ ttyrec_main (int game, char *username, char *ttyrec_path, char* ttyrec_filename)
       snprintf (dirname, 100, "%s%s", ttyrec_path, ttyrec_filename);
   else
       snprintf (dirname, 100, "%s/%s", ttyrec_path, ttyrec_filename);
+  ancient_encoding = myconfig[game]->encoding;
 
   atexit(&remove_ipfile);
   if ((fscript = fopen (dirname, "w")) == NULL)
@@ -258,12 +262,119 @@ game_idle_kill(int signal)
     kill(dgl_parent, SIGHUP);
 }
 
+static unsigned short charset_vt100[128] =
+{
+    0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
+    0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
+    0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
+    0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
+    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
+    0x0028, 0x0029, 0x002a, 0x2192, 0x2190, 0x2191, 0x2193, 0x002f,
+    0x2588, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
+    0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
+    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
+    0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
+    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
+    0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x00a0,
+#if 0
+    0x25c6, 0x2592, 0x2409, 0x240c, 0x240d, 0x240a, 0x00b0, 0x00b1,
+    0x2591, 0x240b, 0x2518, 0x2510, 0x250c, 0x2514, 0x253c, 0xf800,
+    0xf801, 0x2500, 0xf803, 0xf804, 0x251c, 0x2524, 0x2534, 0x252c,
+    0x2502, 0x2264, 0x2265, 0x03c0, 0x2260, 0x00a3, 0x00b7, 0x007f,
+#endif
+    0x2666, 0x2592, 0x2409, 0x240c, 0x240d, 0x240a, 0x00b0, 0x00b1,
+    0x2424, 0x240b, 0x2518, 0x2510, 0x250c, 0x2514, 0x253c, 0x23ba,
+    0x23bb, 0x2500, 0x23bc, 0x23bd, 0x251c, 0x2524, 0x2534, 0x252c,
+    0x2502, 0x2264, 0x2265, 0x03c0, 0x2260, 0x00a3, 0x00b7, 0x0020,
+};
+
+static unsigned short charset_cp437[256] =
+{
+    // Real IBM charset has no control codes, but they are needed by
+    // terminals.
+    0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
+    0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
+    0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
+    0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
+#if 0
+    0x0000, 0x263a, 0x263b, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022,
+    0x25d8, 0x25cb, 0x25d9, 0x2642, 0x2640, 0x266a, 0x266b, 0x263c,
+    0x25b6, 0x25c0, 0x2195, 0x203c, 0x00b6, 0x00a7, 0x25ac, 0x21a8,
+    0x2191, 0x2193, 0x2192, 0x2190, 0x221f, 0x2194, 0x25b2, 0x25bc,
+#endif
+    0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
+    0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
+    0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
+    0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
+    0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
+    0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
+    0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
+    0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
+    0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
+    0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
+    0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
+    0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x2302,
+    0x00c7, 0x00fc, 0x00e9, 0x00e2, 0x00e4, 0x00e0, 0x00e5, 0x00e7,
+    0x00ea, 0x00eb, 0x00e8, 0x00ef, 0x00ee, 0x00ec, 0x00c4, 0x00c5,
+    0x00c9, 0x00e6, 0x00c6, 0x00f4, 0x00f6, 0x00f2, 0x00fb, 0x00f9,
+    0x00ff, 0x00d6, 0x00dc, 0x00a2, 0x00a3, 0x00a5, 0x20a7, 0x0192,
+    0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba,
+    0x00bf, 0x2310, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb,
+    0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x2561, 0x2562, 0x2556,
+    0x2555, 0x2563, 0x2551, 0x2557, 0x255d, 0x255c, 0x255b, 0x2510,
+    0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x255e, 0x255f,
+    0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x2567,
+    0x2568, 0x2564, 0x2565, 0x2559, 0x2558, 0x2552, 0x2553, 0x256b,
+    0x256a, 0x2518, 0x250c, 0x2588, 0x2584, 0x258c, 0x2590, 0x2580,
+    0x03b1, 0x00df, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x00b5, 0x03c4,
+    0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x03c6, 0x03b5, 0x2229,
+    0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248,
+    0x00b0, 0x2219, 0x00b7, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0,
+};
+
+// there must be at least 4 bytes free, NOT CHECKED!
+static int wctoutf8(char *d, uint32_t s)
+{
+    if (s < 0x80)
+    {
+        d[0] = s;
+        return 1;
+    }
+    if (s < 0x800)
+    {
+        d[0] = ( s >>  6)         | 0xc0;
+        d[1] = ( s        & 0x3f) | 0x80;
+        return 2;
+    }
+    if (s < 0x10000)
+    {
+        d[0] = ( s >> 12)         | 0xe0;
+        d[1] = ((s >>  6) & 0x3f) | 0x80;
+        d[2] = ( s        & 0x3f) | 0x80;
+        return 3;
+    }
+    if (s < 0x110000)
+    {
+        d[0] = ( s >> 18)         | 0xf0;
+        d[1] = ((s >> 12) & 0x3f) | 0x80;
+        d[2] = ((s >>  6) & 0x3f) | 0x80;
+        d[3] = ( s        & 0x3f) | 0x80;
+        return 4;
+    }
+    // Invalid char marker (U+FFFD).
+    d[0] = 0xef;
+    d[1] = 0xbf;
+    d[2] = 0xbd;
+    return 3;
+}
+
 void
 dooutput (int max_idle_time)
 {
-  int cc;
+  int cc, i, len;
   time_t tvec, time ();
-  char obuf[BUFSIZ], *ctime ();
+  char obuf[BUFSIZ], ubuf[BUFSIZ*4+2], *ctime (), *out;
+  int galt = 0; // vt100 G switch
 
   setbuf (stdout, NULL);
   (void) close (0);
@@ -281,11 +392,73 @@ dooutput (int max_idle_time)
       if (max_idle_time)
           alarm(max_idle_time);
 
-      h.len = cc;
-      gettimeofday (&h.tv, NULL);
-      (void) write (1, obuf, cc);
-      (void) write_header (fscript, &h);
-      (void) fwrite (obuf, 1, cc, fscript);
+      switch (ancient_encoding)
+      {
+      case 0:  // UTF-8
+      default:
+          h.len = cc;
+          gettimeofday (&h.tv, NULL);
+          (void) write (1, obuf, cc);
+          (void) write_header (fscript, &h);
+          (void) fwrite (obuf, 1, cc, fscript);
+          break;
+      case 1:  // IBM
+          out = ubuf;
+          // Old Crawl emits useless toggles of vt100 mode, even though it
+          // never uses them in this mode.  And they break stuff...
+          for (i = 0; i < cc; i++)
+          {
+              if (galt == 2) // ignore "ESC ( 0", "ESC ( B" and anything such
+              {
+                  galt = 0;
+                  continue;
+              }
+              else if (galt == 1)
+                  if (obuf[i] == '(')
+                  {
+                      galt = 2;
+                      continue;
+                  }
+                  else
+                  {
+                      galt = 0; // false alarm, emit ESC and continue
+                      *out ++ = 27;
+                  }
+              else if (obuf[i] == 27)
+                  {
+                      galt = 1;
+                      continue;
+                  }
+              out += wctoutf8(out, charset_cp437[(unsigned char)obuf[i]]);
+          }
+          h.len = len = out - ubuf;
+          gettimeofday(&h.tv, NULL);
+          write(1, ubuf, len);
+          write_header(fscript, &h);
+          fwrite(ubuf, 1, len, fscript);
+          break;
+      case 2:  // DEC
+          out = ubuf;
+          for (i = 0; i < cc; i++)
+          {
+              if (obuf[i] == 14)
+                  galt = 1;
+              else if (obuf[i] == 15)
+                  galt = 0;
+              else if (obuf[i] & 0x80) // strictly 7-bit
+                  out += wctoutf8(out, 0xFFFD); // or we could assume some other charset
+              else if (galt)
+                  out += wctoutf8(out, charset_vt100[(int)obuf[i]]);
+              else
+                  *out++ = obuf[i];
+          }
+          h.len = len = out - ubuf;
+          gettimeofday(&h.tv, NULL);
+          write(1, ubuf, len);
+          write_header(fscript, &h);
+          fwrite(ubuf, 1, len, fscript);
+          break;
+      }
     }
   done ();
 }