Time for an 2014 update…

Task/String-length/ActionScript/string-length-1.as

@@ -0,0 +1,34 @@
+package {
+
+    import flash.display.Sprite;
+    import flash.events.Event;
+    import flash.utils.ByteArray;
+
+    public class StringByteLength extends Sprite {
+
+        public function StringByteLength() {
+            if ( stage ) _init();
+            else addEventListener(Event.ADDED_TO_STAGE, _init);
+        }
+
+        private function _init(e:Event = null):void {
+            var s1:String = "The quick brown fox jumps over the lazy dog";
+            var s2:String = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+            var s3:String = "José";
+
+            var b:ByteArray = new ByteArray();
+            b.writeUTFBytes(s1);
+            trace(b.length);  // 43
+
+            b.clear();
+            b.writeUTFBytes(s2);
+            trace(b.length);  // 28
+
+            b.clear();
+            b.writeUTFBytes(s3);
+            trace(b.length);  // 5
+        }
+
+    }
+
+}

Task/String-length/ActionScript/string-length-2.as

@@ -0,0 +1,4 @@
+var s1:String = "The quick brown fox jumps over the lazy dog";
+var s2:String = "𝔘𝔫𝔦𝔠𝔬𝔡𝔢";
+var s3:String = "José";
+trace(s1.length, s2.length, s3.length);  // 43, 14, 4

Task/String-length/ActionScript/string-length.as

@@ -1 +0,0 @@
-myStrVar.length()

Task/String-length/COBOL/string-length-1.cobol

@@ -0,0 +1 @@
+FUNCTION BYTE-LENGTH(str)

Task/String-length/COBOL/string-length-2.cobol

@@ -0,0 +1 @@
+LENGTH OF str

Task/String-length/COBOL/string-length-3.cobol

@@ -0,0 +1 @@
+FUNCTION LENGTH-AN(str)

Task/String-length/COBOL/string-length-4.cobol

@@ -0,0 +1 @@
+FUNCTION LENGTH(str)

Task/String-length/Clojure/string-length-1.clj

@@ -1,2 +1,8 @@
-(count (.getBytes "Hello, world!")) ; 13 bytes
-(count (.getBytes "π")) ; two bytes
+(def utf-8-octet-length #(-> % (.getBytes "UTF-8") count))
+(map utf-8-octet-length  ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (7 28 14)
+
+(def utf-16-octet-length (comp (partial * 2) count))
+(map utf-16-octet-length ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (10 28 18)
+
+(def code-unit-length count)
+(map code-unit-length    ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 14 9)

Task/String-length/Clojure/string-length-2.clj

@@ -1 +1,2 @@
-(count "Hello, world!")
+(def character-length #(.codePointCount % 0 (count %)))
+(map character-length    ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 7 9)

Task/String-length/Clojure/string-length-3.clj

@@ -0,0 +1,8 @@
+(def grapheme-length
+  #(->> (doto (java.text.BreakIterator/getCharacterInstance)
+          (.setText %))
+        (partial (memfn next))
+        repeatedly
+        (take-while (partial not= java.text.BreakIterator/DONE))
+        count))
+(map grapheme-length     ["møøse" "𝔘𝔫𝔦𝔠𝔬𝔡𝔢" "J\u0332o\u0332s\u0332e\u0301\u0332"]) ; (5 7 4)

Task/String-length/Deja-Vu/string-length-1.djv

@@ -0,0 +1,2 @@
+!. len !encode!utf-8 "møøse"
+!. len !encode!utf-8 "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"

Task/String-length/Deja-Vu/string-length-2.djv

@@ -0,0 +1,2 @@
+!. len "møøse"
+!. len "𝔘𝔫𝔦𝔠𝔬𝔡𝔢"

Task/String-length/Julia/string-length-1.julia

@@ -0,0 +1,2 @@
+sizeof("Hello, world!") # gives 13
+sizeof("Hellö, wørld!") # gives 15

Task/String-length/Julia/string-length-2.julia

@@ -0,0 +1,2 @@
+length("Hello, world!") # gives 13
+length("Hellö, wørld!") # gives 13

Task/String-length/PL-I/string-length.pli

@@ -4,4 +4,4 @@ put skip list ('Byte length=', size(WS));
 
 declare SM graphic (13) initial ('Hello world');
 put ('Character length=', length(SM));
-put skip list ('Byte length=', size(trim(SM));
+put skip list ('Byte length=', size(trim(SM)));

Task/String-length/Python/string-length-1.py

@@ -1,6 +1,2 @@
-#!/bin/env python
-# -*- coding: UTF-8 -*-
-s = u"møøse"
-assert len(s) == 5
-assert len(s.encode('UTF-8')) == 7
-assert len(s.encode('UTF-16')) == 12 # The extra character is probably a leading Unicode byte-order mark (BOM).
+print len('ascii')
+# 5

Task/String-length/Python/string-length-10.py

@@ -0,0 +1,2 @@
+print(len("𝔘𝔫𝔦𝔠𝔬𝔡𝔢"))
+# 7

Task/String-length/Python/string-length-11.py

@@ -0,0 +1,2 @@
+import sys
+sys.maxunicode # 1114111 on a wide build, 65535 on a narrow build

Task/String-length/Python/string-length-12.py

@@ -0,0 +1,4 @@
+print(len('ascii'))
+# 5
+print(len('\u05d0')) # the letter Alef as unicode literal
+# 1

Task/String-length/Python/string-length-13.py

@@ -0,0 +1,2 @@
+print(len(b'\xd7\x90'.decode('utf-8'))) # Alef encoded as utf-8 byte sequence
+# 1

Task/String-length/Python/string-length-14.py

@@ -0,0 +1,2 @@
+print(hex(sys.maxunicode), len(unichr(0x1F4A9)))
+# ('0x10ffff', 1)

Task/String-length/Python/string-length-15.py

@@ -0,0 +1,2 @@
+print(hex(sys.maxunicode), len(unichr(0x1F4A9)))
+# ('0xffff', 2)

Task/String-length/Python/string-length-2.py

@@ -1,6 +1,5 @@
-#!/bin/env python
-# -*- coding: UTF-8 -*-
-s = "møøse"
-assert len(s) == 5
-assert len(s.encode('UTF-8')) == 7
-assert len(s.encode('UTF-16')) == 12 # The extra character is probably a leading Unicode byte-order mark (BOM).
+# The letter Alef
+print len(u'\u05d0'.encode('utf-8'))
+# 2
+print len(u'\u05d0'.encode('iso-8859-8'))
+# 1

Task/String-length/Python/string-length-3.py

@@ -0,0 +1,6 @@
+#!/bin/env python
+# -*- coding: UTF-8 -*-
+s = u"møøse"
+assert len(s) == 5
+assert len(s.encode('UTF-8')) == 7
+assert len(s.encode('UTF-16-BE')) == 10 # There are 3 different UTF-16 encodings: LE and BE are little endian and big endian respectively, the third one (without suffix) adds 2 extra leading bytes: the byte-order mark (BOM).

Task/String-length/Python/string-length-4.py

@@ -0,0 +1,2 @@
+import sys
+sys.maxunicode # 1114111 on a wide build, 65535 on a narrow build

Task/String-length/Python/string-length-5.py

@@ -0,0 +1,8 @@
+print len('ascii')
+# 5
+print len(u'\u05d0') # the letter Alef as unicode literal
+# 1
+print len('\xd7\x90'.decode('utf-8')) # Same encoded as utf-8 string
+# 1
+print hex(sys.maxunicode), len(unichr(0x1F4A9))
+# ('0x10ffff', 1)

Task/String-length/Python/string-length-6.py

@@ -0,0 +1,2 @@
+print hex(sys.maxunicode), len(unichr(0x1F4A9))
+# ('0xffff', 2)

Task/String-length/Python/string-length-7.py

@@ -0,0 +1,2 @@
+print(len(b'Hello, World!'))
+# 13

Task/String-length/Python/string-length-8.py

@@ -0,0 +1,5 @@
+# The letter Alef
+print(len('\u05d0'.encode())) # the default encoding is utf-8 in Python3
+# 2
+print(len('\u05d0'.encode('iso-8859-8')))
+# 1

Task/String-length/Python/string-length-9.py

@@ -0,0 +1,9 @@
+#!/bin/env python
+# -*- coding: UTF-8 -*-
+s = "møøse"
+assert len(s) == 5
+assert len(s.encode('UTF-8')) == 7
+assert len(s.encode('UTF-16-BE')) == 10 # There are 3 different UTF-16 encodings: LE and BE are little endian and big endian respectively, the third one (without suffix) adds 2 extra leading bytes: the byte-order mark (BOM).
+u="𝔘𝔫𝔦𝔠𝔬𝔡𝔢"
+assert len(u.encode()) == 28
+assert len(u.encode('UTF-16-BE')) == 28