Added yaml lexer for yaml file analysis

Dockerfile

@@ -59,7 +59,7 @@ RUN echo 'deb https://package.perforce.com/apt/ubuntu jammy release' > /etc/apt/
 RUN apt-get update && \
     apt-get install --no-install-recommends -y git subversion mercurial cvs cssc bzr rcs rcs-blame helix-p4d \
     unzip inotify-tools python3 python3-pip \
-    python3-venv python3-setuptools openssh-client
+    python3-venv python3-setuptools openssh-client libyaml-dev
 
 # compile and install universal-ctags
 # hadolint ignore=DL3003,DL3008

opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/AnalyzerGuru.java

@@ -109,6 +109,7 @@
 import org.opengrok.indexer.analysis.uue.UuencodeAnalyzerFactory;
 import org.opengrok.indexer.analysis.vb.VBAnalyzerFactory;
 import org.opengrok.indexer.analysis.verilog.VerilogAnalyzerFactory;
+import org.opengrok.indexer.analysis.yaml.YamlAnalyzerFactory;
 import org.opengrok.indexer.configuration.Project;
 import org.opengrok.indexer.configuration.RuntimeEnvironment;
 import org.opengrok.indexer.history.Annotation;
@@ -259,6 +260,7 @@ public class AnalyzerGuru {
                 new IgnorantAnalyzerFactory(),
                 new BZip2AnalyzerFactory(),
                 new XMLAnalyzerFactory(),
+                YamlAnalyzerFactory.DEFAULT_INSTANCE,
                 MandocAnalyzerFactory.DEFAULT_INSTANCE,
                 TroffAnalyzerFactory.DEFAULT_INSTANCE,
                 new ELFAnalyzerFactory(),
@@ -340,15 +342,15 @@ public class AnalyzerGuru {
      * {@link FileAnalyzerFactory} subclasses are revised to target more or
      * different files.
      * @return a value whose lower 32-bits are a static value
-     * 20201003_00
+     * 20230921_00
      * for the current implementation and whose higher-32 bits are non-zero if
      * {@link #addExtension(java.lang.String, AnalyzerFactory)}
      * or
      * {@link #addPrefix(java.lang.String, AnalyzerFactory)}
      * has been called.
      */
     public static long getVersionNo() {
-        final int ver32 = 20201003_00; // Edit comment above too!
+        final int ver32 = 20230921_00; // Edit comment above too!
         long ver = ver32;
         if (customizationHashCode != 0) {
             ver |= (long) customizationHashCode << 32;

opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/yaml/Consts.java

@@ -0,0 +1,49 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * See LICENSE.txt included in this distribution for the specific
+ * language governing permissions and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at LICENSE.txt.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ */
+package org.opengrok.indexer.analysis.yaml;
+
+import java.util.HashSet;
+import java.util.Set;
+
+/**
+ * Holds static hash set containing the Java keywords.
+ */
+public class Consts {
+
+    static final Set<String> kwd = new HashSet<>();
+    static {
+        kwd.add("true");
+        kwd.add("false");
+        kwd.add("null");
+        kwd.add("True");
+        kwd.add("False");
+        kwd.add("Null");
+        kwd.add("TRUE");
+        kwd.add("FALSE");
+        kwd.add("NULL");
+    }
+
+    private Consts() {
+    }
+
+}

opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/yaml/YamlAnalyzer.java

@@ -0,0 +1,81 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * See LICENSE.txt included in this distribution for the specific
+ * language governing permissions and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at LICENSE.txt.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ * Portions Copyright (c) 2023, Gino Augustine <gino.augustine@oracle.com>.
+ */
+package org.opengrok.indexer.analysis.yaml;
+
+import org.opengrok.indexer.analysis.AbstractAnalyzer;
+import org.opengrok.indexer.analysis.AnalyzerFactory;
+import org.opengrok.indexer.analysis.JFlexTokenizer;
+import org.opengrok.indexer.analysis.JFlexXref;
+import org.opengrok.indexer.analysis.plain.AbstractSourceCodeAnalyzer;
+
+import java.io.Reader;
+
+
+/**
+ *
+ * @author Gino Augustine
+ */
+public class YamlAnalyzer extends AbstractSourceCodeAnalyzer {
+
+
+    /**
+     * Creates a new instance of YamlAnalyzer.
+     * @param factory defined instance for the analyzer
+     */
+    protected YamlAnalyzer(AnalyzerFactory factory) {
+        super(factory, () -> new JFlexTokenizer(new YamlSymbolTokenizer(
+                AbstractAnalyzer.DUMMY_READER)));
+    }
+
+    /**
+     * @return {@code "Java"}
+     */
+    @Override
+    public String getCtagsLang() {
+        return "Yaml";
+    }
+
+    /**
+     * Gets a version number to be used to tag processed documents so that
+     * re-analysis can be re-done later if a stored version number is different
+     * from the current implementation.
+     * @return 20230919_00
+     */
+    @Override
+    protected int getSpecializedVersionNo() {
+        return 20230921_00; // Edit comment above too!
+    }
+
+
+    /**
+     * Create an xref for the language supported by this analyzer.
+     *
+     * @param reader the data to produce xref for
+     * @return an xref instance
+     */
+    @Override
+    protected JFlexXref newXref(Reader reader) {
+        return new JFlexXref(new YamlXref(reader));
+    }
+}

opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/yaml/YamlAnalyzerFactory.java

@@ -0,0 +1,51 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * See LICENSE.txt included in this distribution for the specific
+ * language governing permissions and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at LICENSE.txt.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ * Portions Copyright (c) 2023, Gino Augustine <gino.augustine@oracle.com>.
+ */
+package org.opengrok.indexer.analysis.yaml;
+
+import org.opengrok.indexer.analysis.AbstractAnalyzer;
+import org.opengrok.indexer.analysis.FileAnalyzerFactory;
+
+public class YamlAnalyzerFactory extends FileAnalyzerFactory {
+
+    private static final String NAME = "Yaml";
+
+    private static final String[] SUFFIXES = {
+        "YAML",
+        "YML"
+    };
+
+    public static final YamlAnalyzerFactory DEFAULT_INSTANCE =
+            new YamlAnalyzerFactory();
+
+
+    private YamlAnalyzerFactory() {
+        super(null, null, SUFFIXES, null, null, "text/plain",
+                AbstractAnalyzer.Genre.PLAIN, NAME);
+    }
+
+    @Override
+    protected AbstractAnalyzer newAnalyzer() {
+        return new YamlAnalyzer(this);
+    }
+}

opengrok-indexer/src/main/jflex/analysis/yaml/Yaml.lexh

@@ -0,0 +1,28 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").
+ * You may not use this file except in compliance with the License.
+ *
+ * See LICENSE.txt included in this distribution for the specific
+ * language governing permissions and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at LICENSE.txt.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2023, Oracle and/or its affiliates.
+ * Portions Copyright (c) 2023, Gino Augustine <gino.augustine@oracle.com>.
+ */
+
+
+
+Identifier = [a-zA-Z0-9_-]+
+

opengrok-indexer/src/main/jflex/analysis/yaml/YamlSymbolTokenizer.lex

@@ -0,0 +1,85 @@
+/*
+ * CDDL HEADER START
+ *
+ * The contents of this file are subject to the terms of the
+ * Common Development and Distribution License (the "License").  
+ * You may not use this file except in compliance with the License.
+ *
+ * See LICENSE.txt included in this distribution for the specific
+ * language governing permissions and limitations under the License.
+ *
+ * When distributing Covered Code, include this CDDL HEADER in each
+ * file and include the License file at LICENSE.txt.
+ * If applicable, add the following below this CDDL HEADER, with the
+ * fields enclosed by brackets "[]" replaced with your own identifying
+ * information: Portions Copyright [yyyy] [name of copyright owner]
+ *
+ * CDDL HEADER END
+ */
+
+/*
+ * Copyright (c) 2006, 2023, Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2023, Gino Augustine <gino.augustine@oracle.com>.
+ */
+
+/*
+ * Gets YAML symbols - ignores comments, strings, keywords
+ */
+
+package org.opengrok.indexer.analysis.yaml;
+
+import org.opengrok.indexer.analysis.JFlexSymbolMatcher;
+%%
+%public
+%class YamlSymbolTokenizer
+%extends JFlexSymbolMatcher
+%unicode
+%buffer 32766
+%int
+%include ../CommonLexer.lexh
+%include ../Common.lexh
+%include Yaml.lexh
+%char
+
+%state STRING QSTRING SCOMMENT ALIAS_ANCHOR
+
+ANCHOR_ALIAS_START = [-?:]{WhspChar}+[*\&]
+%%
+
+
+<YYINITIAL> {
+
+{ANCHOR_ALIAS_START}     { yybegin(ALIAS_ANCHOR); }
+ \"     { yybegin(STRING); }
+ \'     { yybegin(QSTRING); }
+ "#"   { yybegin(SCOMMENT); }
+}
+
+<ALIAS_ANCHOR> {
+{Identifier} {
+    String id = yytext();
+    onSymbolMatched(id, yychar);
+    return yystate();
+    }
+ [^]    {yybegin(YYINITIAL);}
+}
+
+<STRING> {
+ \\[\"\\]    {}
+ \"     { yybegin(YYINITIAL); }
+}
+
+<QSTRING> {
+ \\[\'\\]    {}
+ \'     { yybegin(YYINITIAL); }
+}
+
+
+<SCOMMENT> {
+{EOL}    { yybegin(YYINITIAL);}
+}
+
+<YYINITIAL, STRING, SCOMMENT, QSTRING> {
+{WhspChar}+    {}
+[^]    {}
+}