Add support for setting the DOS codepage.

This closes issue #5.

8 files changed, 326 insertions, 52 deletions

diff --git a/Makefile b/Makefile
index 6a373ed..ea8c8d2 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,20 @@ CC=gcc
 CFLAGS=-O3 -flto -Wall -g -Werror=implicit-function-declaration -Werror=int-conversion
 LDLIBS=-lm
 
-OBJS=cpu.o loader.o main.o dosnames.o dis.o dos.o keyb.o dbg.o timer.o utils.o video.o
+OBJS=\
+ cpu.o\
+ loader.o\
+ main.o\
+ codepage.o\
+ dosnames.o\
+ dis.o\
+ dos.o\
+ keyb.o\
+ dbg.o\
+ timer.o\
+ utils.o\
+ video.o\
+
 
 all: obj emu2
 
@@ -20,16 +33,18 @@ clean:
 	rmdir obj
 
 # Generated with gcc -MM src/*.c
+obj/codepage.o: src/codepage.c src/codepage.h src/dbg.h src/env.h
 obj/cpu.o: src/cpu.c src/cpu.h src/dbg.h src/dis.h src/emu.h
 obj/dbg.o: src/dbg.c src/dbg.h src/env.h
 obj/dis.o: src/dis.c src/dis.h src/emu.h
-obj/dos.o: src/dos.c src/dos.h src/dbg.h src/dosnames.h src/emu.h src/env.h \
- src/keyb.h src/loader.h src/timer.h src/utils.h src/video.h
+obj/dos.o: src/dos.c src/codepage.h src/dos.h src/dbg.h src/dosnames.h \
+ src/emu.h src/env.h src/keyb.h src/loader.h src/timer.h src/utils.h \
+ src/video.h
 obj/dosnames.o: src/dosnames.c src/dbg.h src/dosnames.h src/emu.h src/env.h
-obj/keyb.o: src/keyb.c src/keyb.h src/dbg.h src/emu.h
+obj/keyb.o: src/keyb.c src/keyb.h src/dbg.h src/emu.h src/codepage.h
 obj/loader.o: src/loader.c src/loader.h src/dbg.h src/emu.h
 obj/main.o: src/main.c src/dbg.h src/dos.h src/dosnames.h src/emu.h \
  src/keyb.h src/timer.h src/video.h
 obj/timer.o: src/timer.c src/dbg.h src/timer.h src/emu.h
 obj/utils.o: src/utils.c src/utils.h src/dbg.h
-obj/video.o: src/video.c src/video.h src/dbg.h src/emu.h
+obj/video.o: src/video.c src/video.h src/dbg.h src/emu.h src/codepage.h
diff --git a/src/codepage.c b/src/codepage.c
new file mode 100644
index 0000000..f0c61f8
--- /dev/null
+++ b/src/codepage.c
@@ -0,0 +1,274 @@
+#include "codepage.h"
+#include "dbg.h"
+#include "env.h"
+#include <stdlib.h>
+#include <string.h>
+
+/* List of code-pages */
+struct cp_data
+{
+    const char *names;
+    const uint16_t table[256];
+};
+
+static const struct cp_data cp_data[] = {
+    {
+        "437,CP437,IBM437,US",
+        {
+            0x0020, 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,
+            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}
+    },
+    {
+        "850,CP850,IBM850,Latin1,WEU",
+        {
+            0x0020, 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,
+            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, 0x00f8, 0x00a3, 0x00d8, 0x00d7, 0x0192,
+            0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x00f1, 0x00d1, 0x00aa, 0x00ba,
+            0x00bf, 0x00ae, 0x00ac, 0x00bd, 0x00bc, 0x00a1, 0x00ab, 0x00bb,
+            0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x00c1, 0x00c2, 0x00c0,
+            0x00a9, 0x2563, 0x2551, 0x2557, 0x255d, 0x00a2, 0x00a5, 0x2510,
+            0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x00e3, 0x00c3,
+            0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4,
+            0x00f0, 0x00d0, 0x00ca, 0x00cb, 0x00c8, 0x0131, 0x00cd, 0x00ce,
+            0x00cf, 0x2518, 0x250c, 0x2588, 0x2584, 0x00a6, 0x00cc, 0x2580,
+            0x00d3, 0x00df, 0x00d4, 0x00d2, 0x00f5, 0x00d5, 0x00b5, 0x00fe,
+            0x00de, 0x00da, 0x00db, 0x00d9, 0x00fd, 0x00dd, 0x00af, 0x00b4,
+            0x00ad, 0x00b1, 0x2017, 0x00be, 0x00b6, 0x00a7, 0x00f7, 0x00b8,
+            0x00b0, 0x00a8, 0x00b7, 0x00b9, 0x00b3, 0x00b2, 0x25a0, 0x00a0}
+    },
+    {
+        "852,CP850,IBM852,Latin2,CEU",
+        {
+            0x0020, 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,
+            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, 0x016f, 0x0107, 0x00e7,
+            0x0142, 0x00eb, 0x0150, 0x0151, 0x00ee, 0x0179, 0x00c4, 0x0106,
+            0x00c9, 0x0139, 0x013a, 0x00f4, 0x00f6, 0x013d, 0x013e, 0x015a,
+            0x015b, 0x00d6, 0x00dc, 0x0164, 0x0165, 0x0141, 0x00d7, 0x010d,
+            0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x0104, 0x0105, 0x017d, 0x017e,
+            0x0118, 0x0119, 0x00ac, 0x017a, 0x010c, 0x015f, 0x00ab, 0x00bb,
+            0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0x00c1, 0x00c2, 0x011a,
+            0x015e, 0x2563, 0x2551, 0x2557, 0x255d, 0x017b, 0x017c, 0x2510,
+            0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0x0102, 0x0103,
+            0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256c, 0x00a4,
+            0x0111, 0x0110, 0x010e, 0x00cb, 0x010f, 0x0147, 0x00cd, 0x00ce,
+            0x011b, 0x2518, 0x250c, 0x2588, 0x2584, 0x0162, 0x016e, 0x2580,
+            0x00d3, 0x00df, 0x00d4, 0x0143, 0x0144, 0x0148, 0x0160, 0x0161,
+            0x0154, 0x00da, 0x0155, 0x0170, 0x00fd, 0x00dd, 0x0163, 0x00b4,
+            0x00ad, 0x02dd, 0x02db, 0x02c7, 0x02d8, 0x00a7, 0x00f7, 0x00b8,
+            0x00b0, 0x00a8, 0x02d9, 0x0171, 0x0158, 0x0159, 0x25a0, 0x00a0}
+    },
+    {
+        "Kamenický,KEYBCS2,KAMENICKY,Czech,CZ,SK",
+        {
+            0x0020, 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,
+            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,
+
+            0x010c, 0x00fc, 0x00e9, 0x010f, 0x00e4, 0x010e, 0x0164, 0x010d,
+            0x011b, 0x011a, 0x0139, 0x00cd, 0x013e, 0x013a, 0x00c4, 0x00c1,
+            0x00c9, 0x017e, 0x017d, 0x00f4, 0x00f6, 0x00d3, 0x016f, 0x00da,
+            0x00fd, 0x00d6, 0x00dc, 0x0160, 0x013d, 0x00dd, 0x0158, 0x0165,
+            0x00e1, 0x00ed, 0x00f3, 0x00fa, 0x0148, 0x0147, 0x016e, 0x00d4,
+            0x0161, 0x0159, 0x0155, 0x0154, 0x00bc, 0x00a7, 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, 0x03b2, 0x0393, 0x03c0, 0x03a3, 0x03c3, 0x03bc, 0x03c4,
+            0x03a6, 0x0398, 0x03a9, 0x03b4, 0x221e, 0x2205, 0x03b5, 0x2229,
+            0x2261, 0x00b1, 0x2265, 0x2264, 0x2320, 0x2321, 0x00f7, 0x2248,
+            0x2218, 0x00b7, 0x2219, 0x221a, 0x207f, 0x00b2, 0x25a0, 0x00a0}
+    },
+    {
+        0
+    }
+};
+
+static const uint16_t *cp_table = cp_data[0].table;
+
+static int read_codepage_file(const char *fname)
+{
+    FILE *f = fopen(fname, "r");
+    if(!f)
+        return 0;
+    // Note: this leaks memory, so this function should be called only once.
+    uint16_t *new_table = malloc(sizeof(cp_table[0]) * 256);
+    // Start with a copy of CP437
+    memcpy(new_table, cp_data[0].table, sizeof(cp_table[0]) * 256);
+    // Read all lines in file
+    while(!feof(f))
+    {
+        char line[256];
+        int dcode = 0, ucode = 0;
+        if(1 != fscanf(f, " %255[^\n\r#]%*[^\n\r]\n", line))
+        {
+            // Try to consume comments
+            fscanf(f, "%*[^\n\r]\n");
+            continue;
+        }
+
+        if(line[0] == '#')
+            continue;
+        if(2 == sscanf(line, "%i %i", &dcode, &ucode))
+        {
+            if(dcode < 0 || dcode > 256)
+            {
+                fclose(f);
+                print_error("reading codepage '%s', line '%s', invalid byte value %d\n",
+                            fname, line, dcode);
+            }
+            // Ignore control-codes
+            if(dcode < 32 || dcode == 127)
+                continue;
+            if(ucode < 32 || ucode > 0xFFFF)
+            {
+                fclose(f);
+                print_error("reading codepage '%s', line '%s', invalid unicode value %d\n",
+                            fname, line, ucode);
+            }
+            new_table[dcode] = ucode;
+        }
+    }
+    fclose(f);
+    cp_table = new_table;
+    return 1;
+}
+
+void set_codepage(const char *cp_name)
+{
+    // Search our list of codepages
+    for(const struct cp_data *cp = cp_data; cp->names; cp++)
+    {
+        char *names = strdup(cp->names);
+        for(char *name = strtok(names, ","); name; name = strtok(0, ","))
+        {
+            if(0 == strcasecmp(cp_name, name))
+            {
+                debug(debug_dos, "set_codepage: DOS CP set to '%s'\n", names);
+                cp_table = cp->table;
+                return;
+            }
+        }
+    }
+    if(!read_codepage_file(cp_name))
+        print_error("missing or unknown codepage '%s', use '?' for a list.\n",
+                    cp_name);
+}
+
+static void list_codepages(void)
+{
+    fprintf(stderr, "List of internal codepages:\n");
+    for(const struct cp_data *cp = cp_data; cp->names; cp++)
+        fprintf(stderr, "\t%s\n", cp->names);
+    print_error("select one of the above or a filename with a translation table.\n");
+}
+
+void init_codepage(void)
+{
+    const char *cp = getenv(ENV_CODEPAGE);
+    if(cp && *cp)
+    {
+        if(!strcmp(cp, "?"))
+            list_codepages();
+        set_codepage(cp);
+    }
+}
+
+/* Transforms a DOS char to Unicode */
+int get_unicode(uint8_t cp)
+{
+    return cp_table[cp];
+}
+
+/* Transforms a Unicode code-point to the DOS char */
+int get_dos_char(int uc)
+{
+    // TODO: faster searching
+    for(int i = 0; i < 256; i++)
+        if(uc == cp_table[i])
+            return i;
+    // Assume space is always valid
+    return ' ';
+}
+
diff --git a/src/codepage.h b/src/codepage.h
new file mode 100644
index 0000000..c490ef3
--- /dev/null
+++ b/src/codepage.h
@@ -0,0 +1,18 @@
+#pragma once
+
+#include <stdint.h>
+
+/* Set the current codepage to the given one.
+ * You can pass a number (like "437", or "852"), a short name (like "CP437", or
+ * "IBM850") or a file name with the codepage definition.
+ */
+void set_codepage(const char *cp_name);
+
+/* Set codepage from environmebt variable, if found */
+void init_codepage(void);
+
+/* Transforms a DOS char to Unicode */
+int get_unicode(uint8_t cp);
+
+/* Transforms a Unicode code-point to the DOS char */
+int get_dos_char(int uc);
diff --git a/src/dbg.c b/src/dbg.c
index 8edf305..b7f3ea9 100644
--- a/src/dbg.c
+++ b/src/dbg.c
@@ -29,13 +29,15 @@ void print_usage(void)
            "  %-18s  DOS current working directory, use 'C:\\' if not given.\n"
            "  %-18s  Set unix path as root of drive 'n', by default all drives\n"
            "\t\t      point to the unix working directory.\n"
+           ". %-18s  Set DOS code-page. Set to '?' to show lost of code-pages.\n"
            , prog_name
            , ENV_DBG_NAME
            , ENV_DBG_OPT
            , ENV_PROGNAME
            , ENV_DEF_DRIVE
            , ENV_CWD
-           , ENV_DRIVE "n");
+           , ENV_DRIVE "n"
+           , ENV_CODEPAGE);
     exit(EXIT_SUCCESS);
 }
 
diff --git a/src/dos.c b/src/dos.c
index d0ae656..62cc32d 100644
--- a/src/dos.c
+++ b/src/dos.c
@@ -1,3 +1,4 @@
+#include "codepage.h"
 #include "dos.h"
 #include "dbg.h"
 #include "dosnames.h"
@@ -1861,6 +1862,7 @@ void init_dos(int argc, char **argv)
     memset(environ, 0, sizeof(environ));
 
     init_handles();
+    init_codepage();
     init_nls_data();
 
     // Init INTERRUPT handlers - point to our own handlers
diff --git a/src/env.h b/src/env.h
index e146597..528a2dc 100644
--- a/src/env.h
+++ b/src/env.h
@@ -7,4 +7,4 @@
 #define ENV_DEF_DRIVE "EMU2_DEFAULT_DRIVE"
 #define ENV_CWD       "EMU2_CWD"
 #define ENV_DRIVE     "EMU2_DRIVE_"
-
+#define ENV_CODEPAGE  "EMU2_CODEPAGE"
diff --git a/src/keyb.c b/src/keyb.c
index 7e99a26..abafd8b 100644
--- a/src/keyb.c
+++ b/src/keyb.c
@@ -1,6 +1,7 @@
 #include "keyb.h"
 #include "dbg.h"
 #include "emu.h"
+#include "codepage.h"
 
 #include <errno.h>
 #include <fcntl.h>
@@ -307,15 +308,6 @@ static int get_esc_secuence(void)
     }
 }
 
-static int val_utf(int x)
-{
-    // TODO: recode to dos codepage!
-    if(x < 0x100)
-        return add_scancode(x);
-    else
-        return 0;
-}
-
 static int read_key(void)
 {
     char ch = 0xFF;
@@ -338,7 +330,7 @@ static int read_key(void)
         char ch1 = 0xFF;
         if(read(tty_fd, &ch1, 1) == 0 || (ch1 & 0xC0) != 0x80)
             return 0; // INVALID UTF-8
-        return val_utf(((ch & 0x1F) << 6) | (ch1 & 0x3F));
+        return get_dos_char(((ch & 0x1F) << 6) | (ch1 & 0x3F));
     }
     else if((ch & 0xF0) == 0xE0)
     {
@@ -346,8 +338,8 @@ static int read_key(void)
         if(read(tty_fd, &ch1, 1) == 0 || (ch1 & 0xC0) != 0x80 ||
            read(tty_fd, &ch2, 1) == 0 || (ch2 & 0xC0) != 0x80)
             return -1; // INVALID UTF-8
-        return val_utf(((ch & 0x0F) << 12) | ((ch1 & 0x3F) << 6) |
-                       (ch2 & 0x3F));
+        return get_dos_char(((ch & 0x0F) << 12) | ((ch1 & 0x3F) << 6) |
+                            (ch2 & 0x3F));
     }
     else if((ch & 0xF8) == 0xF0)
     {
@@ -356,8 +348,8 @@ static int read_key(void)
            read(tty_fd, &ch2, 1) == 0 || (ch2 & 0xC0) != 0x80 ||
            read(tty_fd, &ch3, 1) == 0 || (ch3 & 0xC0) != 0x80)
             return -1; // INVALID UTF-8
-        return val_utf(((ch & 0x07) << 18) | ((ch1 & 0x3F) << 12) |
-                       ((ch2 & 0x3F) << 6) | (ch3 & 0x3F));
+        return get_dos_char(((ch & 0x07) << 18) | ((ch1 & 0x3F) << 12) |
+                            ((ch2 & 0x3F) << 6) | (ch3 & 0x3F));
     }
     else
         return 0; // INVALID UTF-8
diff --git a/src/video.c b/src/video.c
index b2eeb41..0f0b844 100644
--- a/src/video.c
+++ b/src/video.c
@@ -1,6 +1,7 @@
 #include "video.h"
 #include "dbg.h"
 #include "emu.h"
+#include "codepage.h"
 
 #include <errno.h>
 #include <fcntl.h>
@@ -171,37 +172,7 @@ static void set_color(uint8_t c)
 // Writes a DOS character to the current terminal position
 static void put_vc(uint8_t c)
 {
-    static const uint16_t trans[0x100] = {
-        0x0020, 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, 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,
-        0x03b2, 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};
-    uint16_t uc = trans[c];
+    uint16_t uc = get_unicode(c);
     if(uc < 128)
         putc(uc, tty_file);
     else if(uc < 0x800)