refactor(java): commons-lang C-classes (#134)

Java/commons-lang-CharEncoding_93/Dockerfile

@@ -0,0 +1,18 @@
+FROM ghcr.io/kupl/starlab-benchmarks/java-base:commons-lang
+
+ENV TZ=Asia/Seoul
+
+COPY ./metadata.json .
+COPY ./npe.json .
+COPY ./buggy.java /tmp/buggy.java
+RUN export BUGGY_PATH=$(cat metadata.json | jq -r ".npe.filepath") \
+    && export BUGGY_LINE=$(cat metadata.json | jq -r ".npe.line") \
+    && export BUGGY_MTHD=$(cat metadata.json | jq -r ".npe.npe_method") \
+    && mv /tmp/buggy.java $BUGGY_PATH \
+    && echo "[{\"filepath\": \"$BUGGY_PATH\", \"line\": $BUGGY_LINE, \"method_name\": \"$BUGGY_MTHD\"}]" | jq . > traces.json
+
+RUN git init . && git add -A
+
+RUN $(cat metadata.json | jq -r ".buildCommand")
+
+RUN $(cat metadata.json | jq -r ".testCommand"); if [ $? -eq 0 ]; then exit 1; fi

Java/commons-lang-CharEncoding_93/buggy.java

@@ -0,0 +1,114 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.commons.lang3;
+
+import java.nio.charset.Charset;
+import java.nio.charset.IllegalCharsetNameException;
+
+/**
+ * <p>Character encoding names required of every implementation of the Java platform.</p>
+ *
+ * <p>According to <a href="http://docs.oracle.com/javase/1.3/docs/api/java/lang/package-summary.html#charenc">JRE character
+ * encoding names</a>:</p>
+ *
+ * <p><cite>Every implementation of the Java platform is required to support the following character encodings.
+ * Consult the release documentation for your implementation to see if any other encodings are supported.
+ * </cite></p>
+ *
+ * @see <a href="http://docs.oracle.com/javase/6/docs/technotes/guides/intl/encoding.doc.html">JRE character encoding names</a>
+ * @since 2.1
+ */
+public class CharEncoding {
+
+    /**
+     * <p>ISO Latin Alphabet #1, also known as ISO-LATIN-1.</p>
+     *
+     * <p>Every implementation of the Java platform is required to support this character encoding.</p>
+     */
+    public static final String ISO_8859_1 = "ISO-8859-1";
+
+    /**
+     * <p>Seven-bit ASCII, also known as ISO646-US, also known as the Basic Latin block
+     * of the Unicode character set.</p>
+     *
+     * <p>Every implementation of the Java platform is required to support this character encoding.</p>
+     */
+    public static final String US_ASCII = "US-ASCII";
+
+    /**
+     * <p>Sixteen-bit Unicode Transformation Format, byte order specified by a mandatory initial
+     * byte-order mark (either order accepted on input, big-endian used on output).</p>
+     *
+     * <p>Every implementation of the Java platform is required to support this character encoding.</p>
+     */
+    public static final String UTF_16 = "UTF-16";
+
+    /**
+     * <p>Sixteen-bit Unicode Transformation Format, big-endian byte order.</p>
+     *
+     * <p>Every implementation of the Java platform is required to support this character encoding.</p>
+     */
+    public static final String UTF_16BE = "UTF-16BE";
+
+    /**
+     * <p>Sixteen-bit Unicode Transformation Format, little-endian byte order.</p>
+     *
+     * <p>Every implementation of the Java platform is required to support this character encoding.</p>
+     */
+    public static final String UTF_16LE = "UTF-16LE";
+
+    /**
+     * <p>Eight-bit Unicode Transformation Format.</p>
+     *
+     * <p>Every implementation of the Java platform is required to support this character encoding.</p>
+     */
+    public static final String UTF_8 = "UTF-8";
+
+    /**
+     * <p>Returns whether the named charset is supported.</p>
+     *
+     * <p>This is similar to <a
+     * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html#isSupported%28java.lang.String%29">
+     * java.nio.charset.Charset.isSupported(String)</a> but handles more formats</p>
+     *
+     * @param name  the name of the requested charset; may be either a canonical name or an alias, null returns false
+     * @return {@code true} if the charset is available in the current Java virtual machine
+     */
+/**
+ * <p>Returns whether the named charset is supported.</p>
+ *
+ * <p>This is similar to <a
+ * href="http://docs.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html#isSupported%28java.lang.String%29">
+ * java.nio.charset.Charset.isSupported(String)</a> but handles more formats</p>
+ *
+ * @param name
+ * 		the name of the requested charset; may be either a canonical name or an alias, null returns false
+ * @return {@code true} if the charset is available in the current Java virtual machine
+ */
+public static boolean isSupported(final java.lang.String name) {
+    {
+        try {
+            return java.nio.charset.Charset.isSupported(/* NPEX_NULL_EXP */
+            name);
+        } catch (final java.nio.charset.IllegalCharsetNameException ex) {
+            return false;
+        }
+    }
+}
+
+}

Java/commons-lang-CharEncoding_93/metadata.json

@@ -0,0 +1,21 @@
+{
+  "language": "java",
+  "id": "commons-lang-CharEncoding_93",
+  "buggyPath": ".",
+  "referencePath": null,
+  "buildCommand": "mvn package -V -B -Denforcer.skip=true -Dcheckstyle.skip=true -Dcobertura.skip=true -Drat.skip=true -Dlicense.skip=true -Dfindbugs.skip=true -Dgpg.skip=true -Dskip.npm=true -Dskip.gulp=true -Dskip.bower=true -Drat.numUnapprovedLicenses=100 -DskipTests=true -DskipITs=true -Dtest=None -DfailIfNoTests=false",
+  "testCommand": "mvn test -V -B -Denforcer.skip=true -Dcheckstyle.skip=true -Dcobertura.skip=true -Drat.skip=true -Dlicense.skip=true -Dfindbugs.skip=true -Dgpg.skip=true -Dskip.npm=true -Dskip.gulp=true -Dskip.bower=true -Drat.numUnapprovedLicenses=100",
+  "categories": [
+    "safety",
+    "npe"
+  ],
+  "npe": {
+    "filepath": "src/main/java/org/apache/commons/lang3/CharEncoding.java",
+    "line": 107,
+    "npe_method": "isSupported",
+    "deref_field": "name",
+    "npe_class": "CharEncoding",
+    "repo": "commons-lang",
+    "bug_id": "CharEncoding_93"
+  }
+}

Java/commons-lang-CharEncoding_93/npe.json

@@ -0,0 +1,7 @@
+{
+    "filepath": "src/main/java/org/apache/commons/lang3/CharEncoding.java",
+    "line": 107,
+    "npe_method": "isSupported",
+    "deref_field": "name",
+    "npe_class": "CharEncoding"
+}

Java/commons-lang-CharSequenceTranslator_55/Dockerfile

@@ -0,0 +1,18 @@
+FROM ghcr.io/kupl/starlab-benchmarks/java-base:commons-lang
+
+ENV TZ=Asia/Seoul
+
+COPY ./metadata.json .
+COPY ./npe.json .
+COPY ./buggy.java /tmp/buggy.java
+RUN export BUGGY_PATH=$(cat metadata.json | jq -r ".npe.filepath") \
+    && export BUGGY_LINE=$(cat metadata.json | jq -r ".npe.line") \
+    && export BUGGY_MTHD=$(cat metadata.json | jq -r ".npe.npe_method") \
+    && mv /tmp/buggy.java $BUGGY_PATH \
+    && echo "[{\"filepath\": \"$BUGGY_PATH\", \"line\": $BUGGY_LINE, \"method_name\": \"$BUGGY_MTHD\"}]" | jq . > traces.json
+
+RUN git init . && git add -A
+
+RUN $(cat metadata.json | jq -r ".buildCommand")
+
+RUN $(cat metadata.json | jq -r ".testCommand"); if [ $? -eq 0 ]; then exit 1; fi

Java/commons-lang-CharSequenceTranslator_55/buggy.java

@@ -0,0 +1,142 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ * 
+ *      http://www.apache.org/licenses/LICENSE-2.0
+ * 
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.commons.lang3.text.translate;
+
+import java.io.IOException;
+import java.io.StringWriter;
+import java.io.Writer;
+import java.util.Locale;
+
+/**
+ * An API for translating text. 
+ * Its core use is to escape and unescape text. Because escaping and unescaping 
+ * is completely contextual, the API does not present two separate signatures.
+ * 
+ * @since 3.0
+ */
+public abstract class CharSequenceTranslator {
+
+    static final char[] HEX_DIGITS = new char[] {'0','1','2','3','4','5','6','7','8','9','A','B','C','D','E','F'};
+
+    /**
+     * Translate a set of codepoints, represented by an int index into a CharSequence, 
+     * into another set of codepoints. The number of codepoints consumed must be returned, 
+     * and the only IOExceptions thrown must be from interacting with the Writer so that 
+     * the top level API may reliably ignore StringWriter IOExceptions. 
+     *
+     * @param input CharSequence that is being translated
+     * @param index int representing the current point of translation
+     * @param out Writer to translate the text to
+     * @return int count of codepoints consumed
+     * @throws IOException if and only if the Writer produces an IOException
+     */
+    public abstract int translate(CharSequence input, int index, Writer out) throws IOException;
+
+    /**
+     * Helper for non-Writer usage. 
+     * @param input CharSequence to be translated
+     * @return String output of translation
+     */
+/**
+ * Helper for non-Writer usage.
+ *
+ * @param input
+ * 		CharSequence to be translated
+ * @return String output of translation
+ */
+public final java.lang.String translate(final java.lang.CharSequence input) {
+    {
+        try {
+            final java.io.StringWriter writer = new java.io.StringWriter(/* NPEX_NULL_EXP */
+            input.length() * 2);
+            translate(input, writer);
+            return writer.toString();
+        } catch (final java.io.IOException ioe) {
+            // this should never ever happen while writing to a StringWriter
+            throw new java.lang.RuntimeException(ioe);
+        }
+    }
+}
+
+    /**
+     * Translate an input onto a Writer. This is intentionally final as its algorithm is 
+     * tightly coupled with the abstract method of this class. 
+     *
+     * @param input CharSequence that is being translated
+     * @param out Writer to translate the text to
+     * @throws IOException if and only if the Writer produces an IOException
+     */
+    public final void translate(final CharSequence input, final Writer out) throws IOException {
+        if (out == null) {
+            throw new IllegalArgumentException("The Writer must not be null");
+        }
+        if (input == null) {
+            return;
+        }
+        int pos = 0;
+        final int len = input.length();
+        while (pos < len) {
+            final int consumed = translate(input, pos, out);
+            if (consumed == 0) {
+                // inlined implementation of Character.toChars(Character.codePointAt(input, pos))
+                // avoids allocating temp char arrays and duplicate checks
+                char c1 = input.charAt(pos);
+                out.write(c1);
+                pos++;
+                if (Character.isHighSurrogate(c1) && pos < len) {
+                    char c2 = input.charAt(pos);
+                    if (Character.isLowSurrogate(c2)) {
+                      out.write(c2);
+                      pos++;
+                    }
+                }
+                continue;
+            }
+            // contract with translators is that they have to understand codepoints
+            // and they just took care of a surrogate pair
+            for (int pt = 0; pt < consumed; pt++) {
+                pos += Character.charCount(Character.codePointAt(input, pos));
+            }
+        }
+    }
+
+    /**
+     * Helper method to create a merger of this translator with another set of 
+     * translators. Useful in customizing the standard functionality.
+     *
+     * @param translators CharSequenceTranslator array of translators to merge with this one
+     * @return CharSequenceTranslator merging this translator with the others
+     */
+    public final CharSequenceTranslator with(final CharSequenceTranslator... translators) {
+        final CharSequenceTranslator[] newArray = new CharSequenceTranslator[translators.length + 1];
+        newArray[0] = this;
+        System.arraycopy(translators, 0, newArray, 1, translators.length);
+        return new AggregateTranslator(newArray);
+    }
+
+    /**
+     * <p>Returns an upper case hexadecimal <code>String</code> for the given
+     * character.</p>
+     *
+     * @param codepoint The codepoint to convert.
+     * @return An upper case hexadecimal <code>String</code>
+     */
+    public static String hex(final int codepoint) {
+        return Integer.toHexString(codepoint).toUpperCase(Locale.ENGLISH);
+    }
+
+}

Java/commons-lang-CharSequenceTranslator_55/metadata.json

@@ -0,0 +1,21 @@
+{
+  "language": "java",
+  "id": "commons-lang-CharSequenceTranslator_55",
+  "buggyPath": ".",
+  "referencePath": null,
+  "buildCommand": "mvn package -V -B -Denforcer.skip=true -Dcheckstyle.skip=true -Dcobertura.skip=true -Drat.skip=true -Dlicense.skip=true -Dfindbugs.skip=true -Dgpg.skip=true -Dskip.npm=true -Dskip.gulp=true -Dskip.bower=true -Drat.numUnapprovedLicenses=100 -DskipTests=true -DskipITs=true -Dtest=None -DfailIfNoTests=false",
+  "testCommand": "mvn test -V -B -Denforcer.skip=true -Dcheckstyle.skip=true -Dcobertura.skip=true -Drat.skip=true -Dlicense.skip=true -Dfindbugs.skip=true -Dgpg.skip=true -Dskip.npm=true -Dskip.gulp=true -Dskip.bower=true -Drat.numUnapprovedLicenses=100",
+  "categories": [
+    "safety",
+    "npe"
+  ],
+  "npe": {
+    "filepath": "src/main/java/org/apache/commons/lang3/text/translate/CharSequenceTranslator.java",
+    "line": 65,
+    "npe_method": "translate",
+    "deref_field": "input",
+    "npe_class": "CharSequenceTranslator",
+    "repo": "commons-lang",
+    "bug_id": "CharSequenceTranslator_55"
+  }
+}

Java/commons-lang-CharSequenceTranslator_55/npe.json

@@ -0,0 +1,7 @@
+{
+    "filepath": "src/main/java/org/apache/commons/lang3/text/translate/CharSequenceTranslator.java",
+    "line": 65,
+    "npe_method": "translate",
+    "deref_field": "input",
+    "npe_class": "CharSequenceTranslator"
+}

Java/commons-lang-CharSequenceTranslator_77/Dockerfile

@@ -0,0 +1,18 @@
+FROM ghcr.io/kupl/starlab-benchmarks/java-base:commons-lang
+
+ENV TZ=Asia/Seoul
+
+COPY ./metadata.json .
+COPY ./npe.json .
+COPY ./buggy.java /tmp/buggy.java
+RUN export BUGGY_PATH=$(cat metadata.json | jq -r ".npe.filepath") \
+    && export BUGGY_LINE=$(cat metadata.json | jq -r ".npe.line") \
+    && export BUGGY_MTHD=$(cat metadata.json | jq -r ".npe.npe_method") \
+    && mv /tmp/buggy.java $BUGGY_PATH \
+    && echo "[{\"filepath\": \"$BUGGY_PATH\", \"line\": $BUGGY_LINE, \"method_name\": \"$BUGGY_MTHD\"}]" | jq . > traces.json
+
+RUN git init . && git add -A
+
+RUN $(cat metadata.json | jq -r ".buildCommand")
+
+RUN $(cat metadata.json | jq -r ".testCommand"); if [ $? -eq 0 ]; then exit 1; fi