Build conversion application

Author	Dave Jarvis <email>
Date	2021-06-17 21:14:59 GMT-0700
Commit	5f3aa535e4618f6a76103f493d2a26d1e5b19124
Parent	4dda57c

.gitignore

		-# Ignore Gradle project-specific cache directory
		.gradle
		-
		-# Ignore Gradle build output directory
		-lib/build
		-
		.idea
		gradle
		gradlew*
		+build
		+

README.md

		A Java library to convert straight quotes into curly quotes.

		+# Requirements
		+
		+Download and install OpenJDK 16 or greater.
		+
		+# Download
		+
		+Download the `.jar` file from this repository.
		+
		+# Run
		+
		+Run the software as follows:
		+
		+ java -jar keenquotes.jar < src.txt > dst.txt 2> err.txt
		+
		+Where:
		+
		+* `src.txt` -- Input document file that contains straight quotes.
		+* `dst.txt` -- Output document file that'll contain curled quotes.
		+* `err.txt` -- Error file that will note ambiguous conversion errors.
		+
		+For help, run the software as follows:
		+
		+ java -jar keenquotes.jar -h
		+
		# Software Design

build.gradle

		plugins {
		id 'application'
		+ id 'com.palantir.git-version' version '0.12.3'
		}

		group 'com.whitemagicsoftware'
		-version '1.0'

		repositories {

		main {
		java {
		- srcDirs = ["src/main"]
		+ srcDirs = ["src/main/java"]
		}
		}

		mainClassName = "com.whitemagicsoftware.${applicationName}.KeenQuotes"
		}
		+
		+version = gitVersion()
		+
		+def resourceDir = sourceSets.main.resources.srcDirs[0]
		+final File propertiesFile = file("${resourceDir}/com/whitemagicsoftware/${applicationName}/app.properties")
		+propertiesFile.write("application.version=${version}")

		jar {

		useJUnitPlatform()
		}
		-

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

		"movin",
		"neighborin",
		+ "neighbourin",
		"nothin",
		"notin",

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

		+package com.whitemagicsoftware.keenquotes;
		+
		+import java.util.ArrayList;
		+import java.util.Map;
		+import java.util.function.Consumer;
		+
		+import static com.whitemagicsoftware.keenquotes.TokenType.*;
		+import static java.util.Collections.sort;
		+
		+/**
		+ * Responsible for converting curly quotes to HTML entities throughout a
		+ * text string.
		+ */
		+public class Converter {
		+ private static final Map<TokenType, String> REPLACEMENTS = 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, "″"
		+ );
		+
		+ /**
		+ * Converts straight quotes to curly quotes and primes. Any quotation marks
		+ * that cannot be converted are passed to the {@link Consumer}.
		+ *
		+ * @param text The text to parse.
		+ * @param unresolved Recipient for ambiguous {@link Lexeme}s.
		+ * @return The given text string with as many straight quotes converted to
		+ * curly quotes as is feasible.
		+ */
		+ public static String convert(
		+ final String text, final Consumer<Lexeme> unresolved ) {
		+ final var parser = new Parser( text );
		+ final var tokens = new ArrayList<Token>();
		+
		+ // Parse the tokens and consume all unresolved lexemes.
		+ parser.parse( tokens::add, unresolved );
		+
		+ // The parser may emit tokens in any order.
		+ sort( tokens );
		+
		+ final var result = new StringBuilder( text.length() );
		+ var position = 0;
		+
		+ for( final var token : tokens ) {
		+ if( position <= token.began() ) {
		+ result.append( text, position, token.began() );
		+ result.append( REPLACEMENTS.get( token.getType() ) );
		+ }
		+
		+ position = token.ended();
		+ }
		+
		+ return result.append( text.substring( position ) ).toString();
		+ }
		+}

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

		package com.whitemagicsoftware.keenquotes;

		-import java.util.ArrayList;
		-import java.util.Map;
		-import java.util.function.Consumer;
		+import picocli.CommandLine;

		-import static com.whitemagicsoftware.keenquotes.TokenType.*;
		-import static java.util.Collections.sort;
		+import java.io.BufferedReader;
		+import java.io.IOException;
		+import java.io.InputStream;
		+import java.io.InputStreamReader;
		+import java.util.Properties;
		+
		+import static java.lang.String.format;
		+import static picocli.CommandLine.Help.Ansi.Style.*;
		+import static picocli.CommandLine.Help.ColorScheme;

		/**
		* Responsible for replacing {@link Token} instances with equivalent smart
		* quotes (or straight quotes). This will inform the caller when ambiguous
		* quotes cannot be reliably resolved.
		*/
		public final class KeenQuotes {
		- private static final Map<TokenType, String> REPLACEMENTS = 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, "″"
		- );
		+ private final Settings mSettings = new Settings( this );
		+
		+ private static ColorScheme createColourScheme() {
		+ return new ColorScheme.Builder()
		+ .commands( bold )
		+ .options( fg_blue, bold )
		+ .parameters( fg_blue )
		+ .optionParams( italic )
		+ .errors( fg_red, bold )
		+ .stackTraces( italic )
		+ .build();
		+ }
		+
		+ public void run() {
		+ final StringBuilder sb = new StringBuilder();
		+
		+ try( final BufferedReader reader = open( System.in ) ) {
		+ String line;
		+ final var sep = System.lineSeparator();
		+
		+ while( (line = reader.readLine()) != null ) {
		+ sb.append( line );
		+ sb.append( sep );
		+ }
		+
		+ System.out.println(
		+ Converter.convert( sb.toString(), System.err::println )
		+ );
		+ } catch( final Exception ex ) {
		+ ex.printStackTrace( System.err );
		+ }
		+ }
		+
		+ private Settings getSettings() {
		+ return mSettings;
		+ }

		/**
		- * Converts straight quotes to curly quotes and primes. Any quotation marks
		- * that cannot be converted are passed to the {@link Consumer}.
		+ * Returns the application version number retrieved from the application
		+ * properties file. The properties file is generated at build time, which
		+ * keys off the repository.
		*
		- * @param text The text to parse.
		- * @param unresolved Recipient for ambiguous {@link Lexeme}s.
		- * @return The given text string with as many straight quotes converted to
		- * curly quotes as is feasible.
		+ * @return The application version number.
		+ * @throws RuntimeException An {@link IOException} occurred.
		*/
		- public static String convert(
		- final String text, final Consumer<Lexeme> unresolved ) {
		- final var parser = new Parser( text );
		- final var tokens = new ArrayList<Token>();
		+ private static String getVersion() {
		+ try {
		+ final var properties = loadProperties( "app.properties" );
		+ return properties.getProperty( "application.version" );
		+ } catch( final Exception ex ) {
		+ throw new RuntimeException( ex );
		+ }
		+ }

		- // Parse the tokens and consume all unresolved lexemes.
		- parser.parse( tokens::add, unresolved );
		+ @SuppressWarnings( "SameParameterValue" )
		+ private static Properties loadProperties( final String resource )
		+ throws IOException {
		+ final var properties = new Properties();
		+ properties.load( getResourceAsStream( getResourceName( resource ) ) );
		+ return properties;
		+ }

		- // The parser may emit tokens in any order.
		- sort( tokens );
		+ private static String getResourceName( final String resource ) {
		+ return format( "%s/%s", getPackagePath(), resource );
		+ }

		- final var result = new StringBuilder( text.length() );
		- var position = 0;
		+ private static String getPackagePath() {
		+ return KeenQuotes.class.getPackageName().replace( '.', '/' );
		+ }

		- for( final var token : tokens ) {
		- if( position <= token.began() ) {
		- result.append( text, position, token.began() );
		- result.append( REPLACEMENTS.get( token.getType() ) );
		- }
		+ private static InputStream getResourceAsStream( final String resource ) {
		+ return KeenQuotes.class.getClassLoader().getResourceAsStream( resource );
		+ }

		- position = token.ended();
		- }
		+ @SuppressWarnings( "SameParameterValue" )
		+ private static BufferedReader open( final InputStream in ) {
		+ return new BufferedReader( new InputStreamReader( in ) );
		+ }

		- return result.append( text.substring( position ) ).toString();
		+ public static void main( final String[] args ) {
		+ final var app = new KeenQuotes();
		+ final var parser = new CommandLine( app.getSettings() );
		+ parser.setColorScheme( createColourScheme() );
		+
		+ final var exitCode = parser.execute( args );
		+ final var parseResult = parser.getParseResult();
		+
		+ if( parseResult.isUsageHelpRequested() ) {
		+ System.exit( exitCode );
		+ }
		+ else if( parseResult.isVersionHelpRequested() ) {
		+ System.out.println( getVersion() );
		+ System.exit( exitCode );
		+ }
		}
		}

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

		+/* Copyright 2021 White Magic Software, Ltd. -- All rights reserved. */
		+package com.whitemagicsoftware.keenquotes;
		+
		+import picocli.CommandLine;
		+
		+import java.util.concurrent.Callable;
		+
		+@CommandLine.Command(
		+ name = "KeenQuotes",
		+ mixinStandardHelpOptions = true,
		+ description = "Converts straight quotes to curly quotes."
		+)
		+@SuppressWarnings( {"FieldMayBeFinal", "CanBeFinal"} )
		+public final class Settings implements Callable<Integer> {
		+ /**
		+ * Main executable class.
		+ */
		+ private final KeenQuotes mMain;
		+
		+ /**
		+ * List of unambiguous contractions having leading apostrophes.
		+ */
		+ @CommandLine.Option(
		+ names = {"-ub", "--unamb-began"},
		+ description =
		+ "Contractions to treat as unambiguous (e.g., cause,bout)",
		+ paramLabel = "words"
		+ )
		+ private String[] mUnambiguousBegan;
		+
		+ /**
		+ * List of unambiguous contractions having lagging apostrophes.
		+ */
		+ @CommandLine.Option(
		+ names = {"-ue", "--unamb-ended"},
		+ description =
		+ "Contractions to treat as unambiguous (e.g., frien,thinkin)",
		+ paramLabel = "words"
		+ )
		+ private String[] mUnambiguousEnded;
		+
		+ /**
		+ * List of ambiguous contractions having leading apostrophes.
		+ */
		+ @CommandLine.Option(
		+ names = {"-ab", "--amb-began"},
		+ description =
		+ "Contractions to treat as ambiguous (e.g., sup,kay)",
		+ paramLabel = "words"
		+ )
		+ private String[] mAmbiguousBegan;
		+
		+ /**
		+ * List of ambiguous contractions having lagging apostrophes.
		+ */
		+ @CommandLine.Option(
		+ names = {"-ae", "--amb-ended"},
		+ description =
		+ "Contractions to treat as ambiguous (e.g., gi,o)",
		+ paramLabel = "words"
		+ )
		+ private String[] mAmbiguousEnded;
		+
		+ /**
		+ * Display default values.
		+ */
		+ @CommandLine.Option(
		+ names = {"-l", "--list"},
		+ description = "List all ambiguous and unambiguous contractions"
		+ )
		+ private boolean mDisplayList;
		+
		+ public Settings( final KeenQuotes main ) {
		+ assert main != null;
		+ mMain = main;
		+ }
		+
		+ /**
		+ * Invoked after the command-line arguments are parsed to launch the
		+ * application.
		+ *
		+ * @return Exit level zero.
		+ */
		+ @Override
		+ public Integer call() {
		+ mMain.run();
		+ return 0;
		+ }
		+}

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

		package com.whitemagicsoftware.keenquotes;

		+import org.junit.jupiter.api.Disabled;
		import org.junit.jupiter.api.Test;
		import org.junit.jupiter.params.ParameterizedTest;
		import org.junit.jupiter.params.provider.ValueSource;

		import java.io.BufferedReader;
		import java.io.IOException;
		import java.io.InputStreamReader;
		import java.util.function.Function;

		+import static com.whitemagicsoftware.keenquotes.Converter.convert;
		import static java.lang.System.out;
		import static org.junit.jupiter.api.Assertions.assertEquals;

		*/
		@Test
		- //@Disabled
		+ @Disabled
		public void test_parse_SingleLine_Parsed() {
		- out.println( KeenQuotes.convert(
		+ out.println( convert(
		"\"’Kearney lives on the banks of Killarney—’",
		out::println

		@Test
		public void test_Parse_StraightQuotes_CurlyQuotes() throws IOException {
		- testConverter( text -> KeenQuotes.convert( text, ( lexeme ) -> {} ) );
		+ testConverter( text -> convert( text, ( lexeme ) -> {} ) );
		}

		@ParameterizedTest
		- @ValueSource( strings = {"westrup"} )
		+ @ValueSource( strings = {"habberton"} )
		void test_Parse_Story_Converted( final String filename ) throws IOException {
		final var sb = new StringBuilder( 2 ^ 20 );

		}

		- System.out.println( KeenQuotes.convert( sb.toString(), out::println ) );
		+ System.out.println( convert( sb.toString(), out::println ) );
		}

Delta	286 lines added, 53 lines removed, 233-line increase