(jena) 01/02: Notes about TurtleJCC

[andy]

This is an automated email from the ASF dual-hosted git repository.

andy pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/jena.git

commit dd70a39a7789bad79ed4d310dfa268a6077c3e73
Author: Andy Seaborne <a...@apache.org>
AuthorDate: Fri Aug 30 10:20:37 2024 +0100

    Notes about TurtleJCC
---
 .../org/apache/jena/riot/lang/extra/TurtleJCC.java    | 19 +++++++++++++++----
 .../jena/riot/lang/extra/TurtleJavaccReaderRIOT.java  |  8 +++++---
 2 files changed, 20 insertions(+), 7 deletions(-)

diff --git 
a/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJCC.java 
b/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJCC.java
index b0218ea6c9..3e6fcdacab 100644
--- a/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJCC.java
+++ b/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJCC.java
@@ -19,15 +19,26 @@
 package org.apache.jena.riot.lang.extra;
 
 import org.apache.jena.riot.*;
+import org.apache.jena.riot.lang.LangTurtle;
 
+/**
+ * This is not the normal Turtle parser.
+ * <p>
+ * This is a separate Turtle parser using JavaCC used as a comparison. The 
JavaCC
+ * grammar reflects the RDF Turtle standard grammar. It also exists so that 
there is
+ * a valid JavaCC grammar that can be used as a basis for other languages.
+ * <p>
+ * It is significantly slower than the RIOT {@link LangTurtle}.
+ */
 public class TurtleJCC {
 
-    // Must be a different content type.
+    // Must be a different content type to the normal parser.
+    // Must have different name and altNames.
     // Must be a different file extension.
     public static Lang TTLJCC = LangBuilder.create("TurtleJavaCC", 
"text/turtle-jcc")
-                                        .addAltNames("ttljcc")
-                                        .addFileExtensions("ttljcc")
-                                        .build();
+                                           .addAltNames("ttljcc")
+                                           .addFileExtensions("ttljcc")
+                                           .build();
     public static ReaderRIOTFactory factory = (lang, profile) -> new 
TurtleJavaccReaderRIOT(profile) ;
 
     public static void register() {
diff --git 
a/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJavaccReaderRIOT.java
 
b/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJavaccReaderRIOT.java
index 0b7065a968..c213423716 100644
--- 
a/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJavaccReaderRIOT.java
+++ 
b/jena-arq/src/main/java/org/apache/jena/riot/lang/extra/TurtleJavaccReaderRIOT.java
@@ -35,10 +35,12 @@ import org.apache.jena.sparql.util.Context;
 
 /**
  * Turtle parser, written using JavaCC.
+ * <p>
  * This is not used normally.
- * It is slower than the RIOT {@link LangTurtle}.
- * It may not be up-to-date but at least in the codebase means it should be 
java-compatible.
- * It exists so that there is a JavaCC grammar that can be used as a basis for 
other languages.
+ * <p>
+ * It is slower than the RIOT {@link LangTurtle} and has not been optimized for
+ * speed. Tokenizing is the bottleneck. It exists so that there is a JavaCC 
grammar
+ * that can be used as a basis for other languages.
  */
 public class TurtleJavaccReaderRIOT implements ReaderRIOT {
     private final ParserProfile profile;