[js] Decoding as utf8-c8

Author: pmurias

LICENSE

@@ -220,3 +220,11 @@ NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
 LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
 OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
 WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+Portions Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

src/vm/js/nqp-runtime/codecs.js

@@ -1,9 +1,13 @@
 'use strict';
 
-/* This file contains code borrowed/adapated from iconv-lite */
+/* This file contains code borrowed/adapated from iconv-lite
+ and http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
+ */
 
 const NQPException = require('./nqp-exception.js');
 
+const graphemeBreaker = require('grapheme-breaker');
+
 function isSurrogate(unit) {
   return false;
 }
@@ -112,6 +116,105 @@ const latin1 = new SingleByteCodec('Latin-1', withASCII('€‚ƒ„…†‡ˆ‰Š
 
 const ascii = new SingleByteCodec('ASCII', withASCII(''));
 
+const UTF8_ACCEPT = 0;
+const UTF8_REJECT = 1;
+
+const UTF8_DFA = Buffer.from([
+  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 00..1f
+  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 20..3f
+  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 40..5f
+  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 60..7f
+  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, // 80..9f
+  7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, // a0..bf
+  8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, // c0..df
+  0xa, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x4, 0x3, 0x3, // e0..ef
+  0xb, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, // f0..ff
+  0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4, 0x6, 0x1, 0x1, 0x1, 0x1, // s0..s0
+  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, // s1..s2
+  1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, // s3..s4
+  1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, // s5..s6
+  1, 3, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // s7..s8
+]);
+
+
+class Utf8C8 {
+  constructor() {
+  }
+
+  buildGraphemes(codePoints, chunks) {
+    const graphemes = graphemeBreaker.break(String.fromCodePoint(...codePoints));
+    for (const grapheme of graphemes) {
+      if (grapheme === grapheme.normalize('NFC')) {
+        chunks.push(grapheme);
+      } else {
+        let normalizedPrefix = 0;
+        while (grapheme.slice(0, normalizedPrefix+1).normalize('NFC') === grapheme.slice(0, normalizedPrefix+1)) normalizedPrefix++;
+
+        chunks.push(grapheme.slice(0, normalizedPrefix));
+        const buf = Buffer.from(grapheme.slice(normalizedPrefix), 'utf8');
+        this.reject(buf, 0, buf.length, chunks);
+      }
+    }
+    codePoints.length = 0;
+  }
+
+  toDigit(n) {
+    return n <= 9 ? String.fromCharCode('0'.charCodeAt(0) + n) : String.fromCharCode('A'.charCodeAt(0) + n - 10);
+  }
+
+  reject(buf, start, end, chunks) {
+    for (let i = start; i < end; i++) {
+      chunks.push(
+        '\u{10FFFD}x' + this.toDigit(buf[i] >> 4) + this.toDigit(buf[i] & 0x0F)
+      );
+    }
+  }
+
+  decode(buf) {
+    let state = UTF8_ACCEPT;
+    let codePoint;
+    const codePoints = [];
+
+    const chunks = [];
+
+    let accepted = -1;
+
+    for (let i = 0; i < buf.length; i++) {
+      const byte = buf[i];
+      const type = UTF8_DFA[byte];
+
+      codePoint = (state !== UTF8_ACCEPT) ?
+       (byte & 0x3f) | (codePoint << 6) :
+       (0xff >> type) & (byte);
+
+      state = UTF8_DFA[256 + state*16 + type];
+
+      if (state === UTF8_ACCEPT) {
+        codePoints.push(codePoint);
+        accepted = i;
+      }
+
+      if (state === UTF8_REJECT) {
+        this.buildGraphemes(codePoints, chunks);
+        this.reject(buf, accepted+1, i+1, chunks);
+
+        state = UTF8_ACCEPT;
+        accepted = i;
+      }
+    }
+
+    this.buildGraphemes(codePoints, chunks);
+
+    if (state !== UTF8_ACCEPT) {
+      this.reject(buf, accepted+1, buf.length, chunks);
+    }
+
+    return chunks.join('');
+  }
+}
+
+module.exports['utf8-c8'] = new Utf8C8;
+
 module.exports['windows-1252'] = windows1252;
 module.exports.latin1 = latin1;
 module.exports.ascii = ascii;

src/vm/js/nqp-runtime/core.js

@@ -816,9 +816,8 @@ op.isint = function(value) {
   return (value instanceof NQPInt) ? 1 : 0;
 };
 
-/* HACK - utf8-c is a different encoding than utf8 */
 function renameEncoding(encoding) {
-  return {'utf8-c8': 'utf8', 'utf16': 'utf16le', 'iso-8859-1': 'latin1'}[encoding] || encoding;
+  return {'utf16': 'utf16le', 'iso-8859-1': 'latin1'}[encoding] || encoding;
 }
 exports.renameEncoding = renameEncoding;
 
@@ -923,7 +922,7 @@ function bufferDifference(a, b) {
 
 op.decode = function(buf, encoding) {
   let rawBuffer = toRawBuffer(buf);
-  if (encoding === 'windows-1252') {
+  if (encoding === 'windows-1252' || encoding === 'utf8-c8') {
     return codecs[encoding].decode(rawBuffer);
   } else if (encoding === 'utf8') {
     const decoded = rawBuffer.toString(renameEncoding(encoding));