JavaDoc, code-style

ascii/src/main/java/io/github/mmm/text/ascii/AsciiConverter.java

@@ -5,21 +5,34 @@
 import io.github.mmm.text.ascii.impl.AsciiConverterImpl;
 
 /**
- * {@link AsciiConverter} converts Unicode to simple 7-bit ASCII characters. It strips diacritic marks and transliterates non-Latin letters and glyphs to ASCII.
- * It is optimized for performance and does not implement perfectly correct transliteration (e.g. it has no state to transliterate a code-point dependening on
- * its predecessors).<br>
- * However, it is very helpful to decode strings for use-cases like indexing and searching or if you want to build a {@link String} to be used for restricted
- * environments (names of files, folders, etc.) where special characters could cause problems.
+ * {@link AsciiConverter} converts Unicode to simple 7-bit ASCII characters. It strips diacritic marks and
+ * transliterates non-Latin letters and glyphs to ASCII. It is optimized for performance and does not implement
+ * perfectly correct transliteration (e.g. it has no state to transliterate a code-point dependening on its
+ * predecessors).<br>
+ * However, it is very helpful to decode strings for use-cases like indexing and searching or if you want to build a
+ * {@link String} to be used for restricted environments (names of files, folders, etc.) where special characters could
+ * cause problems.
  *
  * @since 1.0.0
+ * @see java.text.Normalizer
  */
 public interface AsciiConverter {
 
   /**
    * @param codePoint the {@link String#codePointAt(int) codePoint} to convert.
    * @return the converted ASCII representation of the given {@link String#codePointAt(int) codePoint}.
    */
-  String convert(int codePoint);
+  default String convert(int codePoint) {
+
+    return convert(codePoint, AsciiConverterConfig.of());
+  }
+
+  /**
+   * @param codePoint the {@link String#codePointAt(int) codePoint} to convert.
+   * @param config the {@link AsciiConverterConfig}.
+   * @return the converted ASCII representation of the given {@link String#codePointAt(int) codePoint}.
+   */
+  String convert(int codePoint, AsciiConverterConfig config);
 
   /**
    * @param text the (unicode) {@link CharSequence} to convert.

ascii/src/main/java/io/github/mmm/text/ascii/impl/AsciiBuilder.java

@@ -5,9 +5,9 @@
 /**
  * State for {@link AsciiConverterImpl}.
  *
- * @see CodePointMapping#append(AsciiBuilder, int)
+ * @see CodePointMapping#append(AsciiBuilder, int, CodePointMapping)
  */
-class AsciiBuilder {
+public class AsciiBuilder {
 
   final StringBuilder sb;
 

ascii/src/main/java/io/github/mmm/text/ascii/impl/AsciiConverterConfigImpl.java

@@ -12,6 +12,7 @@
  */
 public final class AsciiConverterConfigImpl implements AsciiConverterConfig {
 
+  /** The default instance. */
   public static final AsciiConverterConfigImpl DEFAULT = new AsciiConverterConfigImpl();
 
   final CaseConversion caseConversion;

ascii/src/main/java/io/github/mmm/text/ascii/impl/AsciiConverterImpl.java

@@ -4,6 +4,7 @@
 
 import java.util.PrimitiveIterator.OfInt;
 
+import io.github.mmm.base.text.CaseConversion;
 import io.github.mmm.text.ascii.AsciiConverter;
 import io.github.mmm.text.ascii.AsciiConverterConfig;
 
@@ -25,13 +26,23 @@ private AsciiConverterImpl() {
   }
 
   @Override
-  public String convert(int codePoint) {
+  public String convert(int codePoint, AsciiConverterConfig config) {
 
     CodePointMapping asc = getAsc(codePoint);
     if (asc == null) {
       return null;
     }
-    return asc.toString();
+    String string;
+    if (config.useLongForms()) {
+      string = asc.asStringLong();
+    } else {
+      string = asc.asString();
+    }
+    CaseConversion cc = config.caseConversion();
+    if (cc != CaseConversion.ORIGINAL_CASE) {
+      string = cc.convert(string);
+    }
+    return string;
   }
 
   private static CodePointMapping getAsc(int codePoint) {
@@ -251,8 +262,10 @@ public String convert(CharSequence text, AsciiConverterConfig config) {
         next = current.append(builder, codePoint, next);
       }
     }
-    // since text is not empty, we entered the while loop, next is the last mapping to process due to buffering.
-    next.append(builder, codePoint, null);
+    if (next != null) {
+      next.append(builder, codePoint, null);
+      // } else { fail(); } // since text is not empty, we entered the while loop, and next can never be null.
+    }
     return builder.getAscii();
   }
 

ascii/src/main/java/io/github/mmm/text/ascii/impl/Char.java

@@ -5,7 +5,7 @@
 /**
  * Implementation of {@link CodePointMapping} for static {@link Character}.
  */
-class Char extends AbstractCodePointMapping {
+public class Char extends AbstractCodePointMapping {
 
   // other non-letters
   static final Char TAB = new Char('\t');

ascii/src/main/java/io/github/mmm/text/ascii/impl/Chars.java

@@ -5,7 +5,7 @@
 /**
  * Implementation of {@link CodePointMapping} for static {@link String}.
  */
-class Chars extends AbstractCodePointMapping {
+public class Chars extends AbstractCodePointMapping {
 
   final String s;
 

ascii/src/main/java/io/github/mmm/text/ascii/impl/CodePointMapping.java

@@ -5,7 +5,7 @@
 /**
  * Interface for the mapping result of a code-point.
  */
-interface CodePointMapping {
+public interface CodePointMapping {
 
   /**
    * @param builder the {@link AsciiBuilder}.
@@ -15,18 +15,30 @@ interface CodePointMapping {
    */
   CodePointMapping append(AsciiBuilder builder, int codePoint, CodePointMapping next);
 
+  /**
+   * @return the {@link #toString() string representation}.
+   */
   String asString();
 
+  /**
+   * @return a longer {@link #toString() string representation} as available (may be the same as {@link #asString()}).
+   */
   default String asStringLong() {
 
     return asString();
   }
 
+  /**
+   * @return the {@link Type}.
+   */
   default Type getType() {
 
     return Type.OTHER;
   }
 
+  /**
+   * {@link Enum} with the available {@link CodePointMapping#getType() type}s for a {@link CodePointMapping}.
+   */
   enum Type {
 
     TEXT,

ascii/src/main/java/io/github/mmm/text/ascii/impl/Factor.java

@@ -5,7 +5,7 @@
 /**
  * Common factors used in physics, etc.
  */
-class Factor extends Fraction {
+public class Factor extends Fraction {
 
   static final Factor TERA = new Factor(1_000_000_000_000L, 1, "T", "tera");
 

ascii/src/main/java/io/github/mmm/text/ascii/impl/Letters.java

@@ -5,25 +5,25 @@
 /**
  * Extends {@link Chars} for multiple latin letters. It typically represents a syllabe or sound (unlike a {@link Word}).
  */
-class Letters extends Chars {
+public class Letters extends Chars {
 
   Letters(String s) {
 
     super(s);
     assert isLetters(s);
   }
 
-  private boolean isLetters(String s) {
+  private boolean isLetters(String string) {
 
-    int len = s.length();
+    int len = string.length();
     if (len < 2) {
-      throw new IllegalArgumentException(s + " - expected at least two letters.");
+      throw new IllegalArgumentException(string + " - expected at least two letters.");
     }
     for (int i = 0; i < len; i++) {
-      int codePoint = s.codePointAt(i);
+      int codePoint = string.codePointAt(i);
       if (!isLatinLetter(codePoint)) {
         throw new IllegalArgumentException(
-            s + " - at index " + i + " illegal code point 0x" + Long.toHexString(codePoint));
+            string + " - at index " + i + " illegal code point 0x" + Long.toHexString(codePoint));
       }
     }
     return true;

ascii/src/main/java/io/github/mmm/text/ascii/impl/Number.java

@@ -5,7 +5,7 @@
 /**
  * {@link CodePointMapping} for a numeric value sign.
  */
-interface Number extends CodePointMapping {
+public interface Number extends CodePointMapping {
 
   /**
    * @return the numerator as {@code long}. The actual value is {@link #getNumerator()}/{@link #getDenominator()}.

ascii/src/main/java/io/github/mmm/text/ascii/impl/StructuredWord.java

@@ -6,7 +6,7 @@
  * Extends {@link Word} for a structured term that has a {@link #asStringLong() long form} where as {@link #asString()}
  * typically is an abbreviation.
  */
-class StructuredWord extends Word {
+public class StructuredWord extends Word {
 
   final String full;
 

ascii/src/main/java/io/github/mmm/text/ascii/impl/Unit.java

@@ -5,7 +5,7 @@
 /**
  * Extends {@link Letters} for a (physical) unit.
  */
-class Unit extends StructuredWord {
+public class Unit extends StructuredWord {
 
   static final Unit ACRE = new Unit("a", "acre");
 

ascii/src/main/java/io/github/mmm/text/ascii/impl/Word.java

@@ -5,7 +5,7 @@
 /**
  * Extends {@link Letters} for a word. Subsequent words will be separated by space.
  */
-class Word extends Chars {
+public class Word extends Chars {
 
   Word(String s) {
 
@@ -18,6 +18,14 @@ public Type getType() {
     return Type.TEXT;
   }
 
+  /**
+   * Default part of {@link #append(AsciiBuilder, int, CodePointMapping)} that can be overridden by sub-classes.
+   *
+   * @param builder the {@link AsciiBuilder}.
+   * @param codePoint the original {@link String#codePointAt(int) code point}.
+   * @param next the next {@link CodePointMapping}.
+   * @return an {@link AsciiState} for stateful processing.
+   */
   protected CodePointMapping doAppend(AsciiBuilder builder, int codePoint, CodePointMapping next) {
 
     return super.append(builder, codePoint, next);

ascii/src/main/java/io/github/mmm/text/ascii/impl/Xxx.java

@@ -14,7 +14,7 @@
  * <li>{@code WD_*} for word</li>
  * </ul>
  */
-abstract class Xxx {
+public abstract class Xxx {
 
   // strings
 

ascii/src/main/java/module-info.java

@@ -4,7 +4,9 @@
  */
 
 /**
- * Conversion from unicode to ASCII (simplified transliteration) and related features.
+ * Conversion from Unicode to ASCII (simplified transliteration) and related features.
+ *
+ * @see io.github.mmm.text.ascii.AsciiConverter
  */
 module io.github.mmm.text.ascii {