Fix parser tests, remove ParserFactory

Author	Dave Jarvis <email>
Date	2022-08-13 15:35:33 GMT-0700
Commit	3cca8ab60c6fd0811689277778b41a4f15cc4b01
Parent	7928edf

src/main/java/com/whitemagicsoftware/keenquotes/Converter.java

		package com.whitemagicsoftware.keenquotes;

		-import com.whitemagicsoftware.keenquotes.ParserFactory.ParserType;
		-
		import java.util.ArrayList;
		import java.util.Map;
		import java.util.function.Consumer;
		import java.util.function.Function;

		import static com.whitemagicsoftware.keenquotes.TokenType.*;
		import static java.util.Collections.sort;
		+import static java.util.Map.*;

		/**
		* Responsible for converting curly quotes to HTML entities throughout a
		* text string.
		*/
		@SuppressWarnings( "unused" )
		public class Converter implements Function<String, String> {
		- public static final Map<TokenType, String> ENTITIES = Map.of(
		- QUOTE_OPENING_SINGLE, "‘",
		- QUOTE_CLOSING_SINGLE, "’",
		- QUOTE_OPENING_DOUBLE, "“",
		- QUOTE_CLOSING_DOUBLE, "”",
		- QUOTE_STRAIGHT_SINGLE, "'",
		- QUOTE_STRAIGHT_DOUBLE, "\"",
		- QUOTE_APOSTROPHE, "'",
		- QUOTE_PRIME_SINGLE, "′",
		- QUOTE_PRIME_DOUBLE, "″"
		+ public static final Map<TokenType, String> ENTITIES = ofEntries(
		+ entry( QUOTE_OPENING_SINGLE, "‘" ),
		+ entry( QUOTE_CLOSING_SINGLE, "’" ),
		+ entry( QUOTE_OPENING_DOUBLE, "“" ),
		+ entry( QUOTE_CLOSING_DOUBLE, "”" ),
		+ entry( QUOTE_STRAIGHT_SINGLE, "'" ),
		+ entry( QUOTE_STRAIGHT_DOUBLE, "\"" ),
		+ entry( QUOTE_APOSTROPHE, "'" ),
		+ entry( QUOTE_PRIME_SINGLE, "′" ),
		+ entry( QUOTE_PRIME_DOUBLE, "″" ),
		+ entry( QUOTE_PRIME_TRIPLE, "‴" ),
		+ entry( QUOTE_PRIME_QUADRUPLE, "&qprime;" )
		);

		/**
		* Used by external applications to initialize the replacement map.
		*/
		- public static final Map<TokenType, String> CHARS = Map.of(
		- QUOTE_OPENING_SINGLE, "‘",
		- QUOTE_CLOSING_SINGLE, "’",
		- QUOTE_OPENING_DOUBLE, "“",
		- QUOTE_CLOSING_DOUBLE, "”",
		- QUOTE_STRAIGHT_SINGLE, "'",
		- QUOTE_STRAIGHT_DOUBLE, "\"",
		- QUOTE_APOSTROPHE, "’",
		- QUOTE_PRIME_SINGLE, "′",
		- QUOTE_PRIME_DOUBLE, "″"
		+ public static final Map<TokenType, String> CHARS = ofEntries(
		+ entry( QUOTE_OPENING_SINGLE, "‘" ),
		+ entry( QUOTE_CLOSING_SINGLE, "’" ),
		+ entry( QUOTE_OPENING_DOUBLE, "“" ),
		+ entry( QUOTE_CLOSING_DOUBLE, "”" ),
		+ entry( QUOTE_STRAIGHT_SINGLE, "'" ),
		+ entry( QUOTE_STRAIGHT_DOUBLE, "\"" ),
		+ entry( QUOTE_APOSTROPHE, "’" ),
		+ entry( QUOTE_PRIME_SINGLE, "′" ),
		+ entry( QUOTE_PRIME_DOUBLE, "″" ),
		+ entry( QUOTE_PRIME_TRIPLE, "‴" ),
		+ entry( QUOTE_PRIME_QUADRUPLE, "⁗" )
		);

		private final Consumer<Lexeme> mUnresolved;
		private final Contractions mContractions;
		private final Map<TokenType, String> mReplacements;
		- private final ParserFactory mFactory;
		+ private final ParserType mParserType;

		/**

		mContractions = c;
		mReplacements = replacements;
		- mFactory = new ParserFactory( parserType );
		+ mParserType = parserType;
		}


		@Override
		public String apply( final String text ) {
		- final var parser = mFactory.createParser( text, mContractions );
		+ final var parser = new Parser( text, mContractions );
		final var tokens = new ArrayList<Token>();

		// Parse the tokens and consume all unresolved lexemes.
		- parser.parse( tokens::add, mUnresolved );
		+ parser.parse( tokens::add, mUnresolved, mParserType.filter() );

		// The parser may emit tokens in any order.

src/main/java/com/whitemagicsoftware/keenquotes/FastCharacterIterator.java

		* </p>
		*/
		-public class FastCharacterIterator {
		+final class FastCharacterIterator {

		private final String mS;

		*/
		public char current() {
		- return hasNext() ? mS.charAt( mPos ) : DONE;
		+ final var pos = mPos;
		+ return pos < mLen ? mS.charAt( pos ) : DONE;
		}


		final var pos = mPos;
		return pos + 1 < mLen ? mS.charAt( pos + 1 ) : DONE;
		- }
		-
		- /**
		- * Answers whether the internal index is less than the string's length,
		- * meaning that calling {@link #next()} followed by {@link #current()} will
		- * succeed.
		- *
		- * @return {@code true} if there are more characters to iterate.
		- */
		- public boolean hasNext() {
		- return mPos < mLen;
		}

src/main/java/com/whitemagicsoftware/keenquotes/KeenQuotes.java

		import java.util.Properties;

		-import static com.whitemagicsoftware.keenquotes.ParserFactory.ParserType.PARSER_PLAIN;
		+import static com.whitemagicsoftware.keenquotes.ParserType.PARSER_PLAIN;
		import static java.lang.String.format;
		import static java.lang.System.*;

src/main/java/com/whitemagicsoftware/keenquotes/Lexer.java

		* Turns text into words, numbers, punctuation, spaces, and more.
		*/
		-public class Lexer {
		+public final class Lexer {
		/**
		* Tokenizes a sequence of characters. The order of comparisons is optimized

		}

		- public static void lex(
		+ private static void lex(
		final FastCharacterIterator i,
		final Consumer<Lexeme> emitter,

src/main/java/com/whitemagicsoftware/keenquotes/Parser.java

		public void parse(
		final Consumer<Token> tokenConsumer,
		- final Consumer<Lexeme> lexemeConsumer ) {
		+ final Consumer<Lexeme> lexemeConsumer,
		+ final Consumer<FastCharacterIterator> filter ) {
		final var lexemes = new CircularFifoQueue<Lexeme>( 3 );


		mClosingDoubleQuotes.clear();
		}
		- });
		+ }, filter);

		// By loop's end, the lexemes list contains tokens for all except the

src/main/java/com/whitemagicsoftware/keenquotes/ParserFactory.java

		-/* Copyright 2021 White Magic Software, Ltd. -- All rights reserved. */
		-package com.whitemagicsoftware.keenquotes;
		-
		-/**
		- * Responsible for creating new {@link Parser} instances based on the
		- * {@link ParserType}. The document content format must be known in advance.
		- */
		-public class ParserFactory {
		- public enum ParserType {
		- PARSER_PLAIN,
		- PARSER_XML
		- }
		-
		- private final ParserType mParserType;
		-
		- public ParserFactory( final ParserType parserType ) {
		- mParserType = parserType;
		- }
		-
		- public Parser createParser(
		- final String text, final Contractions contractions ) {
		-
		- return mParserType == ParserType.PARSER_PLAIN
		- ? new Parser( text, contractions )
		- : new XmlParser( text, contractions );
		- }
		-}

src/main/java/com/whitemagicsoftware/keenquotes/ParserType.java

		+/* Copyright 2022 White Magic Software, Ltd. -- All rights reserved. */
		+package com.whitemagicsoftware.keenquotes;
		+
		+import java.util.function.Consumer;
		+
		+public enum ParserType {
		+ PARSER_PLAIN( filter -> {} ),
		+ PARSER_XML( filter -> new XmlFilter() );
		+
		+ private final Consumer<FastCharacterIterator> mFilter;
		+
		+ ParserType( final Consumer<FastCharacterIterator> filter ) {
		+ mFilter = filter;
		+ }
		+
		+ Consumer<FastCharacterIterator> filter() {
		+ return mFilter;
		+ }
		+}

src/main/java/com/whitemagicsoftware/keenquotes/TokenType.java

		QUOTE_PRIME_SINGLE,
		QUOTE_PRIME_DOUBLE,
		+ QUOTE_PRIME_TRIPLE,
		+ QUOTE_PRIME_QUADRUPLE,
		}

src/main/java/com/whitemagicsoftware/keenquotes/XmlParser.java

		-/* Copyright 2021 White Magic Software, Ltd. -- All rights reserved. */
		-package com.whitemagicsoftware.keenquotes;
		-
		-/**
		- * Turns text into {@link Lexeme}s, allowing XML elements to be ignored.
		- */
		-public final class XmlParser extends Parser {
		- /**
		- * Constructs a new {@link Parser} using the default contraction sets
		- * to help resolve some ambiguous scenarios.
		- *
		- * @param text The prose to parse, containing zero or more quotation
		- * characters.
		- * @param contractions Custom sets of contractions to help resolve
		- */
		- public XmlParser(
		- final String text, final Contractions contractions ) {
		- super( text, contractions );
		- }
		-}

src/test/java/com/whitemagicsoftware/keenquotes/KeenQuotesTest.java

		package com.whitemagicsoftware.keenquotes;

		-import com.whitemagicsoftware.keenquotes.ParserFactory.ParserType;
		import org.junit.jupiter.api.Disabled;
		import org.junit.jupiter.api.Test;

		import java.util.stream.Stream;

		-import static com.whitemagicsoftware.keenquotes.ParserFactory.ParserType.PARSER_PLAIN;
		-import static com.whitemagicsoftware.keenquotes.ParserFactory.ParserType.PARSER_XML;
		+import static com.whitemagicsoftware.keenquotes.ParserType.PARSER_PLAIN;
		+import static com.whitemagicsoftware.keenquotes.ParserType.PARSER_XML;
		import static java.lang.System.out;
		import static org.junit.jupiter.api.Assertions.assertEquals;

src/test/java/com/whitemagicsoftware/keenquotes/ParserTest.java


		parser.parse(
		- ( token ) -> actual.merge( token.getType(), 1, Integer::sum ),
		- ( lexeme ) -> {}
		+ token -> actual.merge( token.getType(), 1, Integer::sum ),
		+ lexeme -> {},
		+ filter -> {}
		);

Delta	64 lines added, 96 lines removed, 32-line decrease