support different editor codepages

src/gmtool.c

@@ -78,30 +78,28 @@ state *current_state = NULL;
 
 static WINDOW *hstatus;
 
-static int unicode_utf8_to_ascii(char *result, const utf8_t * utf8_string,
+#ifdef STDIO_CP
-    size_t *length)
+int gm_codepage = STDIO_CP;
-{
-    int retval = unicode_utf8_to_cp437(result, utf8_string, length);
-    if (*length > 1) {
-        *result = '?';
-    }
-    return retval;
-}
-
-#ifdef WIN32
-#define CODEPAGE_TRANS unicode_utf8_to_cp1252
-#elif defined(NCURSES_VERSION)
-#define CODEPAGE_TRANS unicode_utf8_to_cp437
 #else 
-#define CODEPAGE_TRANS unicode_utf8_to_ascii
+int gm_codepage = -1;
 #endif
 
 static void unicode_remove_diacritics(const char *rp, char *wp) {
     while (*rp) {
-        if (*rp & 0x80) {
+        if (gm_codepage >=0 && *rp & 0x80) {
             size_t sz = 0;
             char ch;
-            CODEPAGE_TRANS(&ch, rp, &sz);
+            switch (gm_codepage) {
+            case 1252:
+                unicode_utf8_to_cp1252(&ch, rp, &sz);
+                break;
+            case 437:
+                unicode_utf8_to_cp437(&ch, rp, &sz);
+                break;
+            default:
+                unicode_utf8_to_ascii(&ch, rp, &sz);
+                break;
+            }
             rp += sz;
             *wp++ = ch;
         }

src/gmtool.h

@@ -31,6 +31,7 @@ extern "C" {
   void run_mapper(void);
 
   extern int force_color;
+  extern int gm_codepage;
 
   struct state *state_open(void);
   void state_close(struct state *);

src/main.c

@@ -96,6 +96,7 @@ static void parse_config(const char *filename)
 #ifdef USE_CURSES
         /* only one value in the [editor] section */
         force_color = iniparser_getint(d, "editor:color", force_color);
+        gm_codepage = iniparser_getint(d, "editor:codepage", gm_codepage);
 #endif
     }
 }

src/util/unicode.c

@@ -518,10 +518,22 @@ size_t * length)
     return 0;
 }
 
+/** Convert a UTF-8 encoded character to ASCII, with '?' replacements. */
+int unicode_utf8_to_ascii(char *cp_character, const utf8_t * utf8_string,
+    size_t *length)
+{
+    int result = unicode_utf8_to_cp437(cp_character, utf8_string, length);
+    if (result == 0) {
+        if (*length > 1) {
+            *cp_character = '?';
+        }
+    }
+    return result;
+}
+
 /** Convert a UTF-8 encoded character to CP1252. */
-int
+int unicode_utf8_to_cp1252(char *cp_character, const utf8_t * utf8_string,
-unicode_utf8_to_cp1252(char *cp_character, const utf8_t * utf8_string,
+    size_t * length)
-size_t * length)
 {
     ucs4_t ucs4_character;
     int result;

src/util/unicode.h

@@ -28,18 +28,20 @@ extern "C" {
     typedef unsigned long ucs4_t;
     typedef char utf8_t;
 
-    extern int unicode_utf8_to_cp437(char *result, const utf8_t * utf8_string,
+    int unicode_utf8_to_cp437(char *result, const utf8_t * utf8_string,
         size_t * length);
-    extern int unicode_utf8_to_cp1252(char *result, const utf8_t * utf8_string,
+    int unicode_utf8_to_cp1252(char *result, const utf8_t * utf8_string,
         size_t * length);
-    extern int unicode_utf8_to_ucs4(ucs4_t * result, const utf8_t * utf8_string,
+    int unicode_utf8_to_ucs4(ucs4_t * result, const utf8_t * utf8_string,
         size_t * length);
-    extern int unicode_ucs4_to_utf8(utf8_t * result, size_t * size,
+    int unicode_ucs4_to_utf8(utf8_t * result, size_t * size,
         ucs4_t ucs4_character);
-    extern int unicode_utf8_strcasecmp(const utf8_t * a, const utf8_t * b);
+    int unicode_utf8_to_ascii(char *cp_character, const utf8_t * utf8_string,
-    extern int unicode_latin1_to_utf8(utf8_t * out, size_t * outlen,
+        size_t *length);
+    int unicode_utf8_strcasecmp(const utf8_t * a, const utf8_t * b);
+    int unicode_latin1_to_utf8(utf8_t * out, size_t * outlen,
         const char *in, size_t * inlen);
-    extern int unicode_utf8_tolower(utf8_t * out, size_t outlen,
+    int unicode_utf8_tolower(utf8_t * out, size_t outlen,
         const utf8_t * in);
 
 #ifdef __cplusplus