More docs, check 'docs/std'.

1 files changed, 106 insertions, 0 deletions

diff --git a/std/string.zc b/std/string.zc
index 02ae6b9..3f96053 100644
--- a/std/string.zc
+++ b/std/string.zc
@@ -139,4 +139,110 @@ impl String {
     fn free(self) {
         self.vec.free();
     }
+
+    fn _utf8_seq_len(first_byte: char) -> usize {
+        var b = (int)first_byte;
+        if ((b & 0x80) == 0) { return 1; }
+        if ((b & 0xE0) == 0xC0) { return 2; }
+        if ((b & 0xF0) == 0xE0) { return 3; }
+        if ((b & 0xF8) == 0xF0) { return 4; }
+        return 1; // Fallback
+    }
+
+    fn utf8_len(self) -> usize {
+        var count: usize = 0;
+        var i: usize = 0;
+        var len = self.length();
+        while i < len {
+            var c = self.vec.get(i);
+            i = i + String::_utf8_seq_len(c);
+            count = count + 1;
+        }
+        return count;
+    }
+
+    fn utf8_at(self, idx: usize) -> String {
+        var count: usize = 0;
+        var i: usize = 0;
+        var len = self.length();
+        while i < len {
+            var c = self.vec.get(i);
+            var seq = String::_utf8_seq_len(c);
+            
+            if (count == idx) {
+                return self.substring(i, seq);
+            }
+            
+            i = i + seq;
+            count = count + 1;
+        }
+        return String::new("");
+    }
+
+    fn utf8_substr(self, start_idx: usize, num_chars: usize) -> String {
+        if (num_chars == 0) { return String::new(""); }
+
+        var byte_start: usize = 0;
+        var byte_len: usize = 0;
+        
+        var count: usize = 0;
+        var i: usize = 0;
+        var len = self.length();
+        var found_start = false;
+        
+        while i < len {
+            // Check if we reached the start char
+            if (!found_start && count == start_idx) {
+                byte_start = i;
+                found_start = true;
+                // Reset count to track chars collected
+                count = 0; 
+            } else if (!found_start) {
+                 // Still seeking start
+                 var c = self.vec.get(i);
+                 i = i + String::_utf8_seq_len(c);
+                 count = count + 1;
+                 continue;
+            }
+            
+            // If we are here, we are collecting chars
+            if (count < num_chars) {
+                var c = self.vec.get(i);
+                var seq = String::_utf8_seq_len(c);
+                byte_len = byte_len + seq;
+                i = i + seq;
+                count = count + 1;
+            } else {
+                break;
+            }
+        }
+        
+        if (!found_start) { return String::new(""); }
+        
+        return self.substring(byte_start, byte_len);
+    }
+    fn split(self, delim: char) -> Vec<String> {
+        var parts = Vec<String>::new();
+        var len = self.length();
+        if (len == 0) { return parts; }
+
+        var start: usize = 0;
+        var i: usize = 0;
+        
+        while i < len {
+            if (self.vec.get(i) == delim) {
+                // Found delimiter
+                parts.push(self.substring(start, i - start));
+                start = i + 1;
+            }
+            i = i + 1;
+        }
+        
+        // Push last segment
+        if (start <= len) {
+            parts.push(self.substring(start, len - start));
+        }
+        
+        return parts;
+    }
 }
\ No newline at end of file