String encoding utility methods and tests for Unicode, UTF-8, -16 and -32.

utils/string_encoding/Utf16.dart

+// Copyright (c) 2012, the Dart project authors.  Please see the AUTHORS file
+// for details. All rights reserved. Use of this source code is governed by a
+// BSD-style license that can be found in the LICENSE file.
+
+#library("UTF16");

[Søren Gjesse, 2012/02/01 11:25:25]

Maybe utf16?

[dcarlson, 2012/02/01 22:18:46]

Done.

+#import("UnicodeCore.dart");
+#import("Unicode.dart");
+
+/**
+ * Produce a String from a sequence of UTF16 encoded bytes.
+ */
+String decodeFromUtf16(List<int> bytes) {
+  List<int> codeUnits = _utf16ToUtf16CodeUnits(bytes);
+  // TODO is16BitCodeUnit() is used to work around a bug with frog/dartc
+  // (http://code.google.com/p/dart/issues/detail?id=1357). Consider
+  // removing after this issue is resolved.
+  if (is16BitCodeUnit()) {
+    return new String.fromCharCodes(codeUnits);
+  } else {
+    return new String.fromCharCodes(utf16CodeUnitsToCodepoints(codeUnits));
+  }
+}
+
+/**
+ * Produce a String from a sequence of UTF16-BE encoded bytes.
+ */
+String decodeFromUtf16be(List<int> bytes) {
+  List<int> codeUnits = _utf16beToUtf16CodeUnits(bytes);
+  // TODO is16BitCodeUnit() is used to work around a bug with frog/dartc
+  // (http://code.google.com/p/dart/issues/detail?id=1357). Consider
+  // removing after this issue is resolved.
+  if (is16BitCodeUnit()) {
+    return new String.fromCharCodes(codeUnits);
+  } else {
+    return new String.fromCharCodes(utf16CodeUnitsToCodepoints(codeUnits));
+  }
+}
+
+/**
+ * Produce a String from a sequence of UTF16-LE encoded bytes.
+ */
+String decodeFromUtf16le(List<int> bytes) {
+  List<int> codeUnits = _utf16leToUtf16CodeUnits(bytes);
+  // TODO is16BitCodeUnit() is used to work around a bug with frog/dartc
+  // (http://code.google.com/p/dart/issues/detail?id=1357). Consider
+  // removing after this issue is resolved.
+  if (is16BitCodeUnit()) {
+    return new String.fromCharCodes(codeUnits);
+  } else {
+    return new String.fromCharCodes(utf16CodeUnitsToCodepoints(codeUnits));
+  }
+}
+
+/**
+ * Produce a sequence of UTF16 encoded bytes.
+ */
+List<int> encodeAsUtf16(String str, [bool writeBOM = true]) =>
+    encodeAsUtf16be(str, writeBOM);
+
+/**
+ * Produce a sequence of UTF16-BE encoded bytes.
+ */
+List<int> encodeAsUtf16be(String str, [bool writeBOM = false]) {
+  List<int> utf16CodeUnits = _stringToUtf16CodeUnits(str);
+  List<int> encoding = new List<int>(2 * utf16CodeUnits.length + 
+      (writeBOM ? 2 : 0));
+  int i = 0;
+  if (writeBOM) {
+    encoding[i++] = UNICODE_UTF_BOM_HI;
+    encoding[i++] = UNICODE_UTF_BOM_LO;
+  }
+  for (int unit in utf16CodeUnits) {
+    encoding[i++] = (unit & UNICODE_BYTE_ONE_MASK) >> 8;
+    encoding[i++] = unit & UNICODE_BYTE_ZERO_MASK;
+  }
+  return encoding;
+}
+
+/**
+ * Produce a sequence of UTF16-LE encoded bytes.
+ */
+List<int> encodeAsUtf16le(String str, [bool writeBOM = false]) {
+  List<int> utf16CodeUnits = _stringToUtf16CodeUnits(str);
+  List<int> encoding = new List<int>(2 * utf16CodeUnits.length + 
+      (writeBOM ? 2 : 0));
+  int i = 0;
+  if (writeBOM) {
+    encoding[i++] = UNICODE_UTF_BOM_LO;
+    encoding[i++] = UNICODE_UTF_BOM_HI;
+  }
+  for (int unit in utf16CodeUnits) {
+    encoding[i++] = unit & UNICODE_BYTE_ZERO_MASK;
+    encoding[i++] = (unit & UNICODE_BYTE_ONE_MASK) >> 8;
+  }
+  return encoding;
+}
+
+List<int> _stringToUtf16CodeUnits(String str) {
+  List<int> codepoints = <int>[];
+  // TODO is16BitCodeUnit() is used to work around a bug with frog/dartc
+  // (http://code.google.com/p/dart/issues/detail?id=1357). Consider
+  // removing after this issue is resolved.
+  if (is16BitCodeUnit()) {
+    return str.charCodes();
+  } else {
+    return codepointsToUtf16CodeUnits(str.charCodes());
+  }
+}
+
+/**
+ * Convert UTF-16BE encoded bytes to utf16 code units by grouping 1-2 bytes
+ * to produce the code unit (0-(2^16)-1).
+ */
+List<int> _utf16beToUtf16CodeUnits(List<int> utf16beEncodedBytes,
+    [int start = 0, int length = null]) {
+  if (!(start >= 0)) {
+    throw new IllegalArgumentException("start");
+  }
+
+  if (!(length == null || length >= 0)) {
+    throw new IllegalArgumentException("length");
+  }
+
+  int end = length != null ?
+      Math.min(utf16beEncodedBytes.length, start + length) :
+      utf16beEncodedBytes.length;
+
+  List<int> codeUnits = <int>[];
+  int i = start;
+  int lastIndex = end - 1;
+  while (i < lastIndex) {
+    int hi = utf16beEncodedBytes[i++];
+    int lo = utf16beEncodedBytes[i++];
+    codeUnits.add((hi << 8) | lo);
+  }
+  return codeUnits;
+}
+
+/**
+ * Convert UTF-16LE encoded bytes to utf16 code units by grouping 1-2 bytes
+ * to produce the code unit (0-(2^16)-1).
+ */
+List<int> _utf16leToUtf16CodeUnits(List<int> utf16leEncodedBytes,
+    [int start = 0, int length = null]) {
+  if (!(start >= 0)) {
+    throw new IllegalArgumentException("start");
+  }
+
+  if (!(length == null || length >= 0)) {
+    throw new IllegalArgumentException("length");
+  }
+
+  int end = length != null ?
+      Math.min(utf16leEncodedBytes.length, start + length) :
+      utf16leEncodedBytes.length;
+
+  List<int> codeUnits = <int>[];
+  int i = start;
+  int lastIndex = end - 1;
+  while (i < lastIndex) {
+    int lo = utf16leEncodedBytes[i++];
+    int hi = utf16leEncodedBytes[i++];
+    codeUnits.add((hi << 8) | lo);
+  }
+  return codeUnits;
+}
+
+/**
+ * Convert UTF-16 encoded bytes to utf16 code units by grouping 1-2 bytes
+ * to produce the code unit (0-(2^16)-1). Relies on BOM to determine
+ * endian-ness, and defaults to BE.
+ */
+List<int> _utf16ToUtf16CodeUnits(List<int> utf16EncodedBytes,
+    [int start = 0, int length = null]) {
+  if (!(start >= 0)) {
+    throw new IllegalArgumentException("start");
+  }
+
+  if (!(length == null || length >= 0)) {
+    throw new IllegalArgumentException("length");
+  }
+
+  int end = length != null ?
+      Math.min(utf16EncodedBytes.length, start + length) :
+      utf16EncodedBytes.length;
+
+  if ((start + 1 < end) && utf16EncodedBytes[start] == UNICODE_UTF_BOM_HI &&
+      utf16EncodedBytes[start + 1] == UNICODE_UTF_BOM_LO) {
+    return _utf16beToUtf16CodeUnits(utf16EncodedBytes, start + 2,
+        end - (start + 2));
+  } else if ((start + 1 < end) &&
+      utf16EncodedBytes[start] == UNICODE_UTF_BOM_LO &&
+      utf16EncodedBytes[start + 1] == UNICODE_UTF_BOM_HI) {
+    return _utf16leToUtf16CodeUnits(utf16EncodedBytes, start + 2,
+        end - (start + 2));
+  } else {
+    return _utf16beToUtf16CodeUnits(utf16EncodedBytes, start, end - start);
+  }
+}