TRegex: add support for byte array string constants in LATIN-1/BYTES …

…mode

regex/src/com.oracle.truffle.regex/src/com/oracle/truffle/regex/tregex/string/Encodings.java

@@ -465,13 +465,13 @@ public boolean isFixedCodePointWidth(CodePointSet set) {
             }
 
             @Override
-            public StringBufferUTF16 createStringBuffer(int capacity) {
-                return new StringBufferUTF16(capacity);
+            public StringBufferLATIN1 createStringBuffer(int capacity) {
+                return new StringBufferLATIN1(capacity);
             }
 
             @Override
             public LoopOptimizationNode extractLoopOptNode(CodePointSet cps) {
-                return new LoopOptIndexOfAnyCharNode(cps.inverseToCharArray(this));
+                return new LoopOptIndexOfAnyByteNode(cps.inverseToByteArray(this));
             }
 
             @Override

regex/src/com.oracle.truffle.regex/src/com/oracle/truffle/regex/tregex/string/StringBufferLATIN1.java

@@ -0,0 +1,85 @@
+/*
+ * Copyright (c) 2020, 2020, Oracle and/or its affiliates. All rights reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * The Universal Permissive License (UPL), Version 1.0
+ *
+ * Subject to the condition set forth below, permission is hereby granted to any
+ * person obtaining a copy of this software, associated documentation and/or
+ * data (collectively the "Software"), free of charge and under any and all
+ * copyright rights in the Software, and any and all patent rights owned or
+ * freely licensable by each licensor hereunder covering either (i) the
+ * unmodified Software as contributed to or provided by such licensor, or (ii)
+ * the Larger Works (as defined below), to deal in both
+ *
+ * (a) the Software, and
+ *
+ * (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+ * one is included with the Software each a "Larger Work" to which the Software
+ * is contributed by such licensors),
+ *
+ * without restriction, including without limitation the rights to copy, create
+ * derivative works of, display, perform, and distribute the Software and make,
+ * use, sell, offer for sale, import, export, have made, and have sold the
+ * Software and the Larger Work(s), and to sublicense the foregoing rights on
+ * either these or other terms.
+ *
+ * This license is subject to the following condition:
+ *
+ * The above copyright notice and either this complete permission notice or at a
+ * minimum a reference to the UPL must 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.
+ */
+package com.oracle.truffle.regex.tregex.string;
+
+import com.oracle.truffle.regex.tregex.buffer.ByteArrayBuffer;
+import com.oracle.truffle.regex.tregex.string.Encodings.Encoding;
+
+public final class StringBufferLATIN1 extends ByteArrayBuffer implements AbstractStringBuffer {
+
+    public StringBufferLATIN1() {
+        this(16);
+    }
+
+    public StringBufferLATIN1(int capacity) {
+        super(capacity);
+    }
+
+    @Override
+    public Encoding getEncoding() {
+        return Encodings.LATIN_1;
+    }
+
+    @Override
+    public void append(int codepoint) {
+        assert codepoint <= Encodings.LATIN_1.getMaxValue();
+        add((byte) codepoint);
+    }
+
+    @Override
+    public void appendOR(int c1, int c2) {
+        assert c1 <= Encodings.LATIN_1.getMaxValue();
+        assert c2 <= Encodings.LATIN_1.getMaxValue();
+        add((byte) (c1 | c2));
+    }
+
+    @Override
+    public void appendXOR(int c1, int c2) {
+        assert c1 <= Encodings.LATIN_1.getMaxValue();
+        assert c2 <= Encodings.LATIN_1.getMaxValue();
+        add((byte) (c1 ^ c2));
+    }
+
+    @Override
+    public StringLATIN1 materialize() {
+        return new StringLATIN1(toArray());
+    }
+}

regex/src/com.oracle.truffle.regex/src/com/oracle/truffle/regex/tregex/string/StringLATIN1.java

@@ -0,0 +1,112 @@
+/*
+ * Copyright (c) 2020, 2020, Oracle and/or its affiliates. All rights reserved.
+ * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+ *
+ * The Universal Permissive License (UPL), Version 1.0
+ *
+ * Subject to the condition set forth below, permission is hereby granted to any
+ * person obtaining a copy of this software, associated documentation and/or
+ * data (collectively the "Software"), free of charge and under any and all
+ * copyright rights in the Software, and any and all patent rights owned or
+ * freely licensable by each licensor hereunder covering either (i) the
+ * unmodified Software as contributed to or provided by such licensor, or (ii)
+ * the Larger Works (as defined below), to deal in both
+ *
+ * (a) the Software, and
+ *
+ * (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+ * one is included with the Software each a "Larger Work" to which the Software
+ * is contributed by such licensors),
+ *
+ * without restriction, including without limitation the rights to copy, create
+ * derivative works of, display, perform, and distribute the Software and make,
+ * use, sell, offer for sale, import, export, have made, and have sold the
+ * Software and the Larger Work(s), and to sublicense the foregoing rights on
+ * either these or other terms.
+ *
+ * This license is subject to the following condition:
+ *
+ * The above copyright notice and either this complete permission notice or at a
+ * minimum a reference to the UPL must 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.
+ */
+package com.oracle.truffle.regex.tregex.string;
+
+import java.util.Arrays;
+
+import com.oracle.truffle.api.CompilerDirectives.CompilationFinal;
+
+public final class StringLATIN1 implements AbstractString {
+
+    @CompilationFinal(dimensions = 1) private final byte[] str;
+
+    public StringLATIN1(byte[] str) {
+        this.str = str;
+    }
+
+    @Override
+    public int encodedLength() {
+        return str.length;
+    }
+
+    @Override
+    public Object content() {
+        return str;
+    }
+
+    @Override
+    public String toString() {
+        return defaultToString();
+    }
+
+    @Override
+    public StringLATIN1 substring(int start, int end) {
+        return new StringLATIN1(Arrays.copyOfRange(str, start, end));
+    }
+
+    @Override
+    public boolean regionMatches(int offset, AbstractString other, int ooffset, int encodedLength) {
+        byte[] o = ((StringLATIN1) other).str;
+        if (offset + encodedLength > str.length || ooffset + encodedLength > o.length) {
+            return false;
+        }
+        for (int i = 0; i < encodedLength; i++) {
+            if (str[offset + i] != o[ooffset + i]) {
+                return false;
+            }
+        }
+        return true;
+    }
+
+    @Override
+    public AbstractStringIterator iterator() {
+        return new StringLATIN1Iterator(str);
+    }
+
+    private static final class StringLATIN1Iterator extends AbstractStringIterator {
+
+        private final byte[] str;
+
+        private StringLATIN1Iterator(byte[] str) {
+            this.str = str;
+        }
+
+        @Override
+        public boolean hasNext() {
+            return i < str.length;
+        }
+
+        @Override
+        public int nextInt() {
+            return Byte.toUnsignedInt(str[i++]);
+        }
+    }
+}

regex/src/com.oracle.truffle.regex/src/com/oracle/truffle/regex/tregex/string/StringUTF32.java

@@ -42,9 +42,11 @@
 
 import java.util.Arrays;
 
+import com.oracle.truffle.api.CompilerDirectives.CompilationFinal;
+
 public final class StringUTF32 implements AbstractString {
 
-    private final int[] str;
+    @CompilationFinal(dimensions = 1) private final int[] str;
 
     public StringUTF32(int[] str) {
         this.str = str;