Bugfix: --last does not count correctly when 2-byte or more characters exist

The last parameter does not take into consideration UTF-8 widths.
Redesign counting to accommodate the 2-byte, 3-byte, and 4-byte character widths.

diff --git a/level_3/byte_dump/c/byte_dump.c b/level_3/byte_dump/c/byte_dump.c
index ac446a15018c69e7983e7675cb56554a6ed645a8..65a723e9beeae9c4a84feebff0690827194f5706 100644 (file)
--- a/level_3/byte_dump/c/byte_dump.c
+++ b/level_3/byte_dump/c/byte_dump.c
@@ -58,6 +58,12 @@ extern "C" {
 
     printf("%c%c", f_string_eol, f_string_eol);
 
+    printf("  When ");
+    fl_color_print(f_standard_output, data.context.notable, data.context.reset, "--%s", byte_dump_long_last);
+    printf(" is used, any UTF-8 sequences will still be printed in full should any part is found within the requested range.");
+
+    printf("%c%c", f_string_eol, f_string_eol);
+
     return f_none;
   }
 #endif // _di_byte_dump_print_help_

diff --git a/level_3/byte_dump/c/private-byte_dump.c b/level_3/byte_dump/c/private-byte_dump.c
index 3f30db114bb40fa2810650ca889af4eaa85bb924..3b5eb04187572001b87b54629f8fb5c143c4f3cc 100644 (file)
--- a/level_3/byte_dump/c/private-byte_dump.c
+++ b/level_3/byte_dump/c/private-byte_dump.c
@@ -77,10 +77,6 @@ extern "C" {
         }
         // Process the UTF-8 character.
         else if (width_utf > 1) {
-          position++;
-
-          if (data.last > 0 && position > data.last) break;
-
           continue;
         }
       }
@@ -103,13 +99,7 @@ extern "C" {
         // UTF-8 character fragments must have a width of 1 (and ASCII characters can only be the first character in a sequence).
         if (width_current == 1) {
           // Grab the next UTF-8 character fragment if the entire sequence is not collected yet.
-          if (width_count < width_utf) {
-            position++;
-
-            if (data.last > 0 && position > data.last) break;
-
-            continue;
-          }
+          if (width_count < width_utf) continue;
         }
         else {
           found_invalid_utf = f_true;
@@ -145,12 +135,20 @@ extern "C" {
             }
           }
         }
+
+        if (data.last) {
+          position += width_utf;
+
+          if (position >= data.last) break;
+        }
       }
+      else if (data.last) {
+        position++;
 
-      width_utf = -1;
-      position++;
+        if (position >= data.last) break;
+      }
 
-      if (data.last > 0 && position > data.last) break;
+      width_utf = -1;
     } // while
 
     // Print placeholders to fill out the remaining line and then optionally print the text block.