dd: fix ISO-8859-1 case conversion for conv=lcase/ucase

Author: sylvestre

src/uu/dd/src/conversion_tables.rs

@@ -22,8 +22,8 @@ pub const ASCII_UCASE_TO_LCASE: ConversionTable = [
     0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
     0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
     0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
-    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
-    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
+    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
+    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xd7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xdf,
     0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
     0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
 ];
@@ -43,8 +43,8 @@ pub const ASCII_LCASE_TO_UCASE: ConversionTable = [
     0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
     0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
     0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
-    0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
-    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff,
+    0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
+    0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xf7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xff,
 ];
 
 pub const ASCII_TO_EBCDIC: ConversionTable = [

tests/by-util/test_dd.rs

@@ -1945,3 +1945,44 @@ fn test_nocache_eof_fadvise_zero_length() {
         "Expected len=0 at EOF: {strace}"
     );
 }
+
+#[test]
+fn test_iso8859_1_case_conversion() {
+    // Test ISO-8859-1 case conversion for accented characters
+    // É (0xC9) should convert to é (0xE9) with lcase
+    let input = vec![0xC9, 0x0A]; // É\n in ISO-8859-1
+    let expected = vec![0xE9, 0x0A]; // é\n in ISO-8859-1
+    let result = new_ucmd!()
+        .args(&["conv=lcase", "status=none"])
+        .pipe_in(input)
+        .succeeds();
+    assert_eq!(result.stdout(), expected);
+
+    // é (0xE9) should convert to É (0xC9) with ucase
+    let input = vec![0xE9, 0x0A]; // é\n in ISO-8859-1
+    let expected = vec![0xC9, 0x0A]; // É\n in ISO-8859-1
+    let result = new_ucmd!()
+        .args(&["conv=ucase", "status=none"])
+        .pipe_in(input)
+        .succeeds();
+    assert_eq!(result.stdout(), expected);
+
+    // Test multiple ISO-8859-1 characters
+    // À (0xC0), Ç (0xC7) should convert to à (0xE0), ç (0xE7) with lcase
+    let input = vec![0xC0, 0xC7, 0x0A]; // ÀÇ\n
+    let expected = vec![0xE0, 0xE7, 0x0A]; // àç\n
+    let result = new_ucmd!()
+        .args(&["conv=lcase", "status=none"])
+        .pipe_in(input)
+        .succeeds();
+    assert_eq!(result.stdout(), expected);
+
+    // à (0xE0), ç (0xE7) should convert to À (0xC0), Ç (0xC7) with ucase
+    let input = vec![0xE0, 0xE7, 0x0A]; // àç\n
+    let expected = vec![0xC0, 0xC7, 0x0A]; // ÀÇ\n
+    let result = new_ucmd!()
+        .args(&["conv=ucase", "status=none"])
+        .pipe_in(input)
+        .succeeds();
+    assert_eq!(result.stdout(), expected);
+}