Fix casing issues

- Fix "README" matching.
- Review to[Lower,Upper]Case w.r.t. Locale. All
  reviewed cases except Locale.English in
Repository were not dependent on either US,
English, or Default locale; and would be properly
specified as ROOT. Fixes #1768 for Turkish.
- Use String toLowerCase and not Character
  toLowerCase in PathTokenizer for
context-sensitive and 1:M character mappings.

Author: idodeclare

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

@@ -866,8 +866,7 @@ public static FileAnalyzerFactory find(String file) {
 
             // Try matching the prefix.
             if (dotpos > 0) {
-                factory
-                        = pre.get(path.substring(0, dotpos).toUpperCase(Locale.getDefault()));
+                factory = pre.get(path.substring(0, dotpos).toUpperCase(Locale.ROOT));
                 if (factory != null) {
                     if (LOGGER.isLoggable(Level.FINER)) {
                         LOGGER.log(Level.FINER, "{0}: chosen by prefix: {1}",
@@ -881,8 +880,7 @@ public static FileAnalyzerFactory find(String file) {
             // Now try matching the suffix. We kind of consider this order (first
             // prefix then suffix) to be workable although for sure there can be
             // cases when this does not work.
-            factory
-                    = ext.get(path.substring(dotpos + 1).toUpperCase(Locale.getDefault()));
+            factory = ext.get(path.substring(dotpos + 1).toUpperCase(Locale.ROOT));
             if (factory != null) {
                 if (LOGGER.isLoggable(Level.FINER)) {
                     LOGGER.log(Level.FINER, "{0}: chosen by suffix: {1}",
@@ -894,7 +892,7 @@ public static FileAnalyzerFactory find(String file) {
         }
 
         // file doesn't have any of the prefix or extensions we know, try full match
-        return FILE_NAMES.get(path.toUpperCase(Locale.getDefault()));
+        return FILE_NAMES.get(path.toUpperCase(Locale.ROOT));
     }
 
     /**

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

@@ -28,6 +28,7 @@
 import java.io.Reader;
 import java.io.StringReader;
 import java.io.Writer;
+import java.util.Locale;
 import java.util.logging.Level;
 import java.util.logging.Logger;
 
@@ -230,14 +231,14 @@ protected FileAnalyzer(FileAnalyzerFactory factory,
      * @return Normalized name of the analyzer.
      */
     public String getFileTypeName() {
-        String name = this.getClass().getSimpleName().toLowerCase();
+        String name = this.getClass().getSimpleName().toLowerCase(Locale.ROOT);
         String suffix = "analyzer";
 
         if (name.endsWith(suffix)) {
             return name.substring(0, name.length() - suffix.length());
         }
 
-        return name.toLowerCase();
+        return name;
     }
 
     /**

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

@@ -23,6 +23,7 @@
 
 package org.opengrok.indexer.analysis;
 
+import java.util.Locale;
 import java.util.Set;
 import java.util.regex.Pattern;
 import org.opengrok.indexer.util.StringUtils;
@@ -449,7 +450,7 @@ protected boolean onFilteredSymbolMatched(String str, int start,
         Set<String> keywords, boolean caseSensitive) {
 
         if (keywords != null) {
-            String check = caseSensitive ? str : str.toLowerCase();
+            String check = caseSensitive ? str : str.toLowerCase(Locale.ROOT);
             if (keywords.contains(check)) {
                 onKeywordMatched(str, start);
                 return false;

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

@@ -20,7 +20,7 @@
 /*
  * Copyright (c) 2009, 2018, Oracle and/or its affiliates. All rights reserved.
  * Portions Copyright 2011 Jens Elkner.
- * Portions Copyright (c) 2017, Chris Fraire <[email protected]>.
+ * Portions Copyright (c) 2017-2018, Chris Fraire <[email protected]>.
  */
 
 package org.opengrok.indexer.analysis;
@@ -30,6 +30,7 @@
 import java.util.Comparator;
 import java.util.HashMap;
 import java.util.List;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Set;
 import java.util.SortedSet;
@@ -252,7 +253,7 @@ public static boolean writeSymbol(Writer out, Definitions defs,
         String[] strs = new String[1];
         strs[0] = "";
 
-        String check = caseSensitive ? symbol : symbol.toLowerCase();
+        String check = caseSensitive ? symbol : symbol.toLowerCase(Locale.ROOT);
         if (isKeyword || (keywords != null && keywords.contains( check ))) {
             // This is a keyword, so we don't create a link.
             out.append("<b>");

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

@@ -19,11 +19,13 @@
 
 /*
  * Copyright (c) 2005, 2018, Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2018, Chris Fraire <[email protected]>.
  */
 package org.opengrok.indexer.analysis;
 
 import java.io.IOException;
 import java.util.Arrays;
+import java.util.Locale;
 import org.apache.lucene.analysis.Tokenizer;
 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
 import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
@@ -90,14 +92,24 @@ public final boolean incrementToken() throws IOException {
             if (i >= buf.length) {
                 buf = Arrays.copyOf(buf, buf.length * 2);
             }
-            buf[i++] = Character.toLowerCase((char) c);
+            /**
+             * "In general, String.toLowerCase(Locale) should be used to map
+             * characters to lowercase. String case mapping methods have several
+             * benefits over Character case mapping methods. String case mapping
+             * methods can perform locale-sensitive mappings, context-sensitive
+             * mappings, and 1:M character mappings, whereas the Character case
+             * mapping methods cannot." See below.
+             */
+            buf[i++] = (char)c;
             c = input.read();
             charsRead++;
         } while (c != delimiter && c != cdot && !Character.isWhitespace(c) && c != -1);
         if (c == cdot) {
             dot = true;
         }
-        termAtt.copyBuffer(buf, 0, i);
+        String bufLcase = String.valueOf(buf, 0, i).toLowerCase(Locale.ROOT);
+        i = bufLcase.length();
+        termAtt.append(bufLcase);
         termAtt.setLength(i);
         offsetAtt.setOffset(correctOffset(startPosition), correctOffset(startPosition + i));
         startPosition = startPosition + i + 1;

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

@@ -19,6 +19,7 @@
 
 /*
  * Copyright (c) 2007, 2018, Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2018, Chris Fraire <[email protected]>.
  */
 package org.opengrok.indexer.analysis.sql;
 
@@ -58,7 +59,7 @@ private static void populateKeywordSet(Set<String> set, String file)
             Consts.class.getResourceAsStream(file), StandardCharsets.UTF_8))) {
             while ((line = reader.readLine()) != null) {
                 line=line.trim();
-                lline = line.toLowerCase(Locale.US);
+                lline = line.toLowerCase(Locale.ROOT);
                 if (line.charAt(0) != '#') {
                     set.add(line);
                     set.add(lline);

opengrok-indexer/src/main/java/org/opengrok/indexer/analysis/sql/PLSQLConsts.java

@@ -19,6 +19,7 @@
 
 /*
  * Copyright (c) 2007, 2018, Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2018, Chris Fraire <[email protected]>.
  */
 package org.opengrok.indexer.analysis.sql;
 
@@ -59,7 +60,7 @@ private static void populateKeywordSet(Set<String> set, String file)
             Consts.class.getResourceAsStream(file), StandardCharsets.UTF_8))) {
             while ((line = reader.readLine()) != null) {
                 line=line.trim();
-                lline = line.toLowerCase(Locale.US);
+                lline = line.toLowerCase(Locale.ROOT);
                 if (line.charAt(0) != '#') {
                     set.add(line);
                     set.add(lline);

opengrok-indexer/src/main/java/org/opengrok/indexer/authorization/AuthControlFlag.java

@@ -19,10 +19,12 @@
 
 /*
  * Copyright (c) 2017, 2018 Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2018, Chris Fraire <[email protected]>.
  */
 package org.opengrok.indexer.authorization;
 
 import java.util.Arrays;
+import java.util.Locale;
 import java.util.stream.Collectors;
 
 /**
@@ -87,7 +89,7 @@ public boolean isSufficient() {
      */
     public static AuthControlFlag get(String flag) throws IllegalArgumentException {
         try {
-            return AuthControlFlag.valueOf(flag.toUpperCase());
+            return AuthControlFlag.valueOf(flag.toUpperCase(Locale.ROOT));
         } catch (IllegalArgumentException ex) {
             // flag does not exist -> add some more info about which flags do exist
             throw new IllegalArgumentException(

opengrok-indexer/src/main/java/org/opengrok/indexer/authorization/AuthorizationEntity.java

@@ -19,10 +19,12 @@
 
 /*
  * Copyright (c) 2017, 2018 Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2018, Chris Fraire <[email protected]>.
  */
 package org.opengrok.indexer.authorization;
 
 import java.io.Serializable;
+import java.util.Locale;
 import java.util.Map;
 import java.util.Map.Entry;
 import java.util.Set;
@@ -565,7 +567,9 @@ protected String colorToString(String colorElement) {
      */
     protected String infoToString(String prefix) {
         StringBuilder builder = new StringBuilder(40);
-        builder.append(" ").append(getFlag().toString().toUpperCase()).append(" '").append(getName()).append("'");
+        String flup = getFlag().toString().toUpperCase(Locale.ROOT);
+        String nm = getName();
+        builder.append(" ").append(flup).append(" '").append(nm).append("'");
         return builder.toString();
     }
 

opengrok-indexer/src/main/java/org/opengrok/indexer/authorization/AuthorizationPlugin.java

@@ -19,9 +19,11 @@
 
 /*
  * Copyright (c) 2017, 2018 Oracle and/or its affiliates. All rights reserved.
+ * Portions Copyright (c) 2018, Chris Fraire <[email protected]>.
  */
 package org.opengrok.indexer.authorization;
 
+import java.util.Locale;
 import java.util.Map;
 import java.util.TreeMap;
 import java.util.logging.Level;
@@ -104,7 +106,7 @@ public synchronized void load(Map<String, Object> parameters) {
             setFailed();
             LOGGER.log(Level.INFO, "[{0}] Plugin \"{1}\" {2} and is {3}.",
                     new Object[]{
-                        getFlag().toString().toUpperCase(),
+                        getFlag().toString().toUpperCase(Locale.ROOT),
                         getName(),
                         hasPlugin() ? "found" : "not found",
                         isWorking() ? "working" : "failed"});
@@ -125,7 +127,7 @@ public synchronized void load(Map<String, Object> parameters) {
 
         LOGGER.log(Level.INFO, "[{0}] Plugin \"{1}\" {2} and is {3}.",
                 new Object[]{
-                    getFlag().toString().toUpperCase(),
+                    getFlag().toString().toUpperCase(Locale.ROOT),
                     getName(),
                     hasPlugin() ? "found" : "not found",
                     isWorking() ? "working" : "failed"});