Data commit

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

@@ -0,0 +1,2 @@
+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

@@ -0,0 +1,5 @@
+# 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