Move codePointAt() to separate CodePointSequence class.

test/core/string/code_point_at.wren

@@ -1,38 +0,0 @@
-// Bytes:           11111
-//        012345678901234
-// Chars: sø mé ஃ  thî ng
-var s = "søméஃthîng"
-
-IO.print(s.codePointAt(0)) // expect: 115
-IO.print(s.codePointAt(1)) // expect: 248
-IO.print(s.codePointAt(2)) // expect: -1
-IO.print(s.codePointAt(3)) // expect: 109
-IO.print(s.codePointAt(4)) // expect: 233
-IO.print(s.codePointAt(5)) // expect: -1
-IO.print(s.codePointAt(6)) // expect: 2947
-IO.print(s.codePointAt(7)) // expect: -1
-IO.print(s.codePointAt(8)) // expect: -1
-IO.print(s.codePointAt(9)) // expect: 116
-IO.print(s.codePointAt(10)) // expect: 104
-IO.print(s.codePointAt(11)) // expect: 238
-IO.print(s.codePointAt(12)) // expect: -1
-IO.print(s.codePointAt(13)) // expect: 110
-IO.print(s.codePointAt(14)) // expect: 103
-
-IO.print(s.codePointAt(-15)) // expect: 115
-IO.print(s.codePointAt(-14)) // expect: 248
-IO.print(s.codePointAt(-13)) // expect: -1
-IO.print(s.codePointAt(-12)) // expect: 109
-IO.print(s.codePointAt(-11)) // expect: 233
-IO.print(s.codePointAt(-10)) // expect: -1
-IO.print(s.codePointAt(-9)) // expect: 2947
-IO.print(s.codePointAt(-8)) // expect: -1
-IO.print(s.codePointAt(-7)) // expect: -1
-IO.print(s.codePointAt(-6)) // expect: 116
-IO.print(s.codePointAt(-5)) // expect: 104
-IO.print(s.codePointAt(-4)) // expect: 238
-IO.print(s.codePointAt(-3)) // expect: -1
-IO.print(s.codePointAt(-2)) // expect: 110
-IO.print(s.codePointAt(-1)) // expect: 103
-
-IO.print("\0".codePointAt(0)) // expect: 0

test/core/string/code_point_at_incomplete.wren

@@ -1,8 +0,0 @@
-// The first byte of a two-octet sequence.
-IO.print("\xc0".codePointAt(0)) // expect: -1
-
-// The first byte of a three-octet sequence.
-IO.print("\xe0".codePointAt(0)) // expect: -1
-
-// The first two bytes of a three-octet sequence.
-IO.print("\xe0\xae".codePointAt(0)) // expect: -1

test/core/string/code_point_at_not_int.wren

@@ -1 +0,0 @@
-IO.print("string".codePointAt(12.34)) // expect runtime error: Index must be an integer.

test/core/string/code_point_at_not_num.wren

@@ -1 +0,0 @@
-IO.print("string".codePointAt("not num")) // expect runtime error: Index must be a number.

test/core/string/code_point_at_too_large.wren

@@ -1 +0,0 @@
-IO.print("string".codePointAt(6)) // expect runtime error: Index out of bounds.

test/core/string/code_point_at_too_small.wren

@@ -1 +0,0 @@
-IO.print("string".codePointAt(-7)) // expect runtime error: Index out of bounds.

test/core/string/iterate.wren

@@ -22,3 +22,8 @@ IO.print("a\0b\0c".iterate(1)) // expect: 2
 IO.print("a\0b\0c".iterate(2)) // expect: 3
 IO.print("a\0b\0c".iterate(3)) // expect: 4
 IO.print("a\0b\0c".iterate(4)) // expect: false
+
+// Iterates over invalid UTF-8 one byte at a time.
+IO.print("\xef\xf7".iterate(null)) // expect: 0
+IO.print("\xef\xf7".iterate(0)) // expect: 1
+IO.print("\xef\xf7".iterate(1)) // expect: false

test/core/string/iterator_value.wren

@@ -2,8 +2,8 @@ var s = "abçd"
 IO.print(s.iteratorValue(0)) // expect: a
 IO.print(s.iteratorValue(1)) // expect: b
 IO.print(s.iteratorValue(2)) // expect: ç
-// Iterator value in middle of UTF sequence is an empty string.
-IO.print(s.iteratorValue(3) == "") // expect: true
+// Iterator value in middle of UTF sequence is the unencoded byte.
+IO.print(s.iteratorValue(3) == "\xa7") // expect: true
 IO.print(s.iteratorValue(4)) // expect: d
 
 // 8-bit clean.
@@ -13,3 +13,7 @@ IO.print(t.iteratorValue(1) == "\0") // expect: true
 IO.print(t.iteratorValue(2) == "b") // expect: true
 IO.print(t.iteratorValue(3) == "\0") // expect: true
 IO.print(t.iteratorValue(4) == "c") // expect: true
+
+// Returns single byte strings for invalid UTF-8 sequences.
+IO.print("\xef\xf7".iteratorValue(0) == "\xef") // expect: true
+IO.print("\xef\xf7".iteratorValue(1) == "\xf7") // expect: true

test/core/string/subscript.wren

@@ -27,12 +27,12 @@ IO.print("søméஃthîng"[-1]) // expect: g
 IO.print("søméஃthîng"[-2]) // expect: n
 IO.print("søméஃthîng"[-4]) // expect: î
 
-// If the subscript is in the middle of a UTF-8 sequence, yield an empty string.
-IO.print("søméஃthîng"[2] == "") // expect: true
-IO.print("søméஃthîng"[7] == "") // expect: true
-IO.print("søméஃthîng"[8] == "") // expect: true
-IO.print("søméஃ"[-1] == "") // expect: true
-IO.print("søméஃ"[-2] == "") // expect: true
+// If the subscript is in the middle of a UTF-8 sequence, return the raw byte.
+IO.print("søméஃthîng"[2] == "\xb8") // expect: true
+IO.print("søméஃthîng"[7] == "\xae") // expect: true
+IO.print("søméஃthîng"[8] == "\x83") // expect: true
+IO.print("søméஃ"[-1] == "\x83") // expect: true
+IO.print("søméஃ"[-2] == "\xae") // expect: true
 
 // 8-bit clean.
 IO.print("a\0b\0c"[0] == "a") // expect: true
@@ -40,3 +40,7 @@ IO.print("a\0b\0c"[1] == "\0") // expect: true
 IO.print("a\0b\0c"[2] == "b") // expect: true
 IO.print("a\0b\0c"[3] == "\0") // expect: true
 IO.print("a\0b\0c"[4] == "c") // expect: true
+
+// Returns single byte strings for invalid UTF-8 sequences.
+IO.print("\xef\xf7"[0] == "\xef") // expect: true
+IO.print("\xef\xf7"[1] == "\xf7") // expect: true

test/core/string/subscript_range.wren

@@ -45,3 +45,5 @@ IO.print("søméஃthîng"[3...10]) // expect: méஃt
 IO.print("søméஃthîng"[2..6]) // expect: méஃ
 IO.print("søméஃthîng"[2...6]) // expect: mé
 IO.print("søméஃthîng"[2...7]) // expect: méஃ
+
+// TODO: Strings including invalid UTF-8.