fileop: handle multibyte host filenames, e.g. UTF-8

Handle host filenames with multibyte encoding, like UTF-8.

1 files changed, 45 insertions, 35 deletions

diff --git a/tools/fileop.c b/tools/fileop.c
index 2417423..e597f4a 100644
--- a/tools/fileop.c
+++ b/tools/fileop.c
@@ -6,6 +6,7 @@
 #include <unistd.h>
 #include <inttypes.h>
 #include <stdbool.h>
+#include <wchar.h>
 
 #ifndef O_TEXT
 # define O_TEXT	0
@@ -95,32 +96,50 @@ static void do_closeall(int fd)
     send_reply(fd, 0);
 }
 
-/* XXX: This assumes Latin-1; Unicode requires more sophistication */
-static const char my_tolower[256] =
-  "\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017"
-  "\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037"
-  " !\"#$%&'()*+,-./0123456789:;<=>?"
-  "\351abcdefghijklmnopqrstuvwxyz\344\366\345\374_"
-  "\351abcdefghijklmnopqrstuvwxyz\344\366\345\374\377"
-  "\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217"
-  "\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237"
-  "\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257"
-  "\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277"
-  "\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317"
-  "\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337"
-  "\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357"
-  "\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377";
+static void unmangle_filename(char *out, const unsigned char *in)
+{
+  static const wchar_t my_tolower[256] =
+    L"\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017"
+    L"\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037"
+    L" !\"#¤%&'()*+,-./0123456789:;<=>?"
+    L"éabcdefghijklmnopqrstuvwxyzäöåü_"
+    L"éabcdefghijklmnopqrstuvwxyzäöåü\377"
+    L"\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217"
+    L"\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237"
+    L"\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257"
+    L"\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277"
+    L"\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317"
+    L"\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337"
+    L"\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357"
+    L"\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377";
+  int i;
+
+  wctomb(NULL, 0);
+
+  for (i = 0; i < 8; i++) {
+    if (*in != ' ')
+      out += wctomb(out, my_tolower[*in]);
+    in++;
+  }
+
+  if (memcmp(in, "   ", 3) && memcmp(in, "Ufd", 3)) {
+    out += wctomb(out, L'.');
+    for (i = 0; i < 3; i++) {
+      if (*in != ' ')
+	out += wctomb(out, my_tolower[*in]);
+      in++;
+    }
+  }
+
+  *out = '\0';
+}
 
 static void do_open(int fd, uint16_t ix, char *name)
 {
-  int i;
-  bool nodot;
-  struct file_data *fm;
   int err;
+  struct file_data *fm;
   static const char *modes[6] = {"r+t", "r+b", "w+t", "w+b", "rt", "rb" };
-  char path[16], *p;
-
-  name[11] = '\0';
+  char path[64];
 
   if (!fileops) {
     send_reply(fd, 128+42);	/* Skivan ej klar */
@@ -129,24 +148,13 @@ static void do_open(int fd, uint16_t ix, char *name)
 
   do_close(-1, ix);
 
-  nodot = true;
-  p = path;
-  for (i = 0; i < 11; i++) {
-    if (name[i] != ' ') {
-      if (i >= 8 && nodot) {
-	*p++ = '.';
-	nodot = false;
-      }
-      *p++ = my_tolower[(unsigned char)name[i]];
-    }
-  }
+  unmangle_filename(path, (const unsigned char *)name);
   
-  if (p == path) {
+  if (!path[0]) {
     /* Empty filename */
     send_reply(fd, 128+21);	/* File not found */
     return;
   }
-  *p = '\0';
 
   fm = calloc(1, sizeof(struct file_info *));
   if (!fm) {
@@ -161,6 +169,7 @@ static void do_open(int fd, uint16_t ix, char *name)
   if (!fm->f) {
     free(fm);
     switch (errno) {
+#if 0				/* Enable this? */
     case EACCES:
       err = 128+39;
       break;
@@ -171,11 +180,12 @@ static void do_open(int fd, uint16_t ix, char *name)
     case ENOTDIR:
       err = 128+48;
       break;
+#endif
     default:
       err = 128+21;
       break;
     }
-    send_reply(fd, 128+21);
+    send_reply(fd, err);
     return;
   }