More unicode to come

FossilOrigin-Name: ff529030371279eaac4d47324b6387112e0e6ca1d83db09af19f9182771b87fc

2 files changed, 72 insertions, 23 deletions

diff --git a/src/c_subst.c b/src/c_subst.c
index cc9823c..31c2cde 100644
--- a/src/c_subst.c
+++ b/src/c_subst.c
@@ -208,11 +208,37 @@ c_unicode_subst(char filename[])
 
 	p = (unsigned char*)filename;
 	while (*p != 0x00) {
+		if (*p == 0xc2) {
+			if (*(p + 1) == 0xb9) {
+				*p = '1';
+				memmove(
+					p + 1,
+					p + 2,
+					(strlen((const char*)p + 2) + 1) * sizeof(char)
+				);
+				c_unicode_subst(filename);
+			}
+			if (*(p + 1) == 0xb2) {
+				*p = '2';
+				memmove(
+					p + 1,
+					p + 2,
+					(strlen((const char*)p + 2) + 1) * sizeof(char)
+				);
+				c_unicode_subst(filename);
+			}
+			if (*(p + 1) == 0xb3) {
+				*p = '3';
+				memmove(
+					p + 1,
+					p + 2,
+					(strlen((const char*)p + 2) + 1) * sizeof(char)
+				);
+				c_unicode_subst(filename);
+			}
+		}
 		if (*p == 0xc3) {
-			if (
-				u_isucharset((unsigned char)*(p + 1), C_CHARSET_A_MAJ) == TRUE ||
-				u_isucharset((unsigned char)*(p + 1), C_CHARSET_A_MIN) == TRUE
-			) {
+			if (u_isucharset((unsigned char)*(p + 1), C_CHARSET_A) == TRUE) {
 				*p = 'a';
 				memmove(
 					p + 1,
@@ -221,10 +247,7 @@ c_unicode_subst(char filename[])
 				);
 				c_unicode_subst(filename);
 			}
-			if (
-				u_isucharset((unsigned char)*(p + 1), C_CHARSET_O_MAJ) == TRUE ||
-				u_isucharset((unsigned char)*(p + 1), C_CHARSET_O_MIN) == TRUE
-			) {
+			if (u_isucharset((unsigned char)*(p + 1), C_CHARSET_O) == TRUE) {
 				*p = 'o';
 				memmove(
 					p + 1,
@@ -246,26 +269,42 @@ c_unicode_subst(char filename[])
 					(strlen((const char*)p + 2) + 1) * sizeof(char)
 				);
 				c_unicode_subst(filename);
-			}		
-			if (*(p + 1) == 0x72) {
-				*p = '2';
+			}
+			if (u_isucharset((unsigned char)*(p + 1), C_CHARSET_DH) == TRUE) {
+				*p = 'd';
+				*(p + 1) = 'h';
+				c_unicode_subst(filename);
+			}
+			if (u_isucharset((unsigned char)*(p + 1), C_CHARSET_C) == TRUE) {
+				*p = 'c';
 				memmove(
 					p + 1,
 					p + 2,
 					(strlen((const char*)p + 2) + 1) * sizeof(char)
 				);
 				c_unicode_subst(filename);
-			}		
-			if (*(p + 1) == 0x73) {
-				*p = '3';
+			}
+			if (u_isucharset((unsigned char)*(p + 1), C_CHARSET_E) == TRUE) {
+				*p = 'e';
+				memmove(
+					p + 1,
+					p + 2,
+					(strlen((const char*)p + 2) + 1) * sizeof(char)
+				);
+				c_unicode_subst(filename);
+			}
+			if (u_isucharset((unsigned char)*(p + 1), C_CHARSET_U) == TRUE) {
+				*p = 'u';
 				memmove(
 					p + 1,
 					p + 2,
 					(strlen((const char*)p + 2) + 1) * sizeof(char)
 				);
 				c_unicode_subst(filename);
-			}		
-			if (*(p + 1) == 0x75) {
+			}
+		}
+		if (*p == 0xce) {
+			if (*(p + 1) == 0xbc) {
 				*p = 'u';
 				memmove(
 					p + 1,
@@ -273,7 +312,7 @@ c_unicode_subst(char filename[])
 					(strlen((const char*)p + 2) + 1) * sizeof(char)
 				);
 				c_unicode_subst(filename);
-			}		
+			}
 		}
 		p++;
 	}
diff --git a/src/c_subst.h b/src/c_subst.h
index 1a64621..e698632 100644
--- a/src/c_subst.h
+++ b/src/c_subst.h
@@ -51,12 +51,22 @@
 #include "c_unixize.h"
 
 #define C_CHARSET_VALID	"_-."
-#define C_CHARSET_A_MAJ	"\x80\x81\x82\x83\x84\x85"
-#define C_CHARSET_A_MIN	"\xa0\xa1\xa2\xa3\xa4\xa5"
-#define C_CHARSET_O_MAJ	"\x92\x93\x94\x95\x96\x98"
-#define C_CHARSET_O_MIN	"\xb2\xb3\xb4\xb5\xb6\xb8"
-#define C_CHARSET_AE	"\x86\xa6"
-#define C_CHARSET_N		"\x91\xb1"
+#define C_CHARSET_A \
+	"\x80\x81\x82\x83\x84\x85\xa0\xa1\xa2\xa3\xa4\xa5"
+#define C_CHARSET_O \
+	"\x92\x93\x94\x95\x96\x98\xb2\xb3\xb4\xb5\xb6\xb8"
+#define C_CHARSET_AE \
+	"\x86\xa6"
+#define C_CHARSET_N \
+	"\x91\xb1"
+#define C_CHARSET_DH \
+	"\x90\xb0"
+#define C_CHARSET_C \
+	"\x87\xa7"
+#define C_CHARSET_E \
+	"\x88\x89\x8a\x8b\xa8\xa9\xaa\xab"
+#define C_CHARSET_U \
+	"\x99\x9a\x9b\x9c\xb9\xba\xbb\xbc"
 
 struct lfiles_s* c_subst_filenames(struct lfiles_s*, const bool_t,
 	const bool_t, const unsigned char);