danfickle#549 Fix soft hyphen characters are visible

openhtmltopdf-core/src/main/java/com/openhtmltopdf/extend/TextRenderer.java

@@ -24,9 +24,9 @@
 import com.openhtmltopdf.render.FSFont;
 import com.openhtmltopdf.render.FSFontMetrics;
 import com.openhtmltopdf.render.JustificationInfo;
+import com.openhtmltopdf.util.OpenUtil;
 
 import static com.openhtmltopdf.util.OpenUtil.areAllCharactersPrintable;
-import static com.openhtmltopdf.util.OpenUtil.isCodePointPrintable;
 
 public interface TextRenderer {
 
@@ -43,11 +43,7 @@ static String getEffectivePrintableString(String input) {
         }
 
         StringBuilder effective = new StringBuilder(input.length());
-        for (int i = 0; i < input.length(); i++) {
-            if (isCodePointPrintable(input.codePointAt(i))) {
-                effective.append(input.charAt(i));
-            }
-        }
+        input.codePoints().filter(OpenUtil::isCodePointPrintable).forEach(effective::appendCodePoint);
 
         return effective.toString();
     }

openhtmltopdf-core/src/main/java/com/openhtmltopdf/util/OpenUtil.java

@@ -34,9 +34,9 @@ public static boolean isCodePointPrintable(int codePoint) {
 	 */
 	public static boolean areAllCharactersPrintable(String str) {
 		Objects.requireNonNull(str, "str");
-		return IntStream.range(0, str.length()).allMatch(idx -> isCodePointPrintable(str.codePointAt(idx)));
+		return str.codePoints().allMatch(OpenUtil::isCodePointPrintable);
 	}
-	
+
 	public static Integer parseIntegerOrNull(String possibleInteger) {
 	        try {
 	            return Integer.parseInt(possibleInteger);

openhtmltopdf-core/src/test/java/com/openhtmltopdf/util/OpenUtilTest.java

@@ -0,0 +1,20 @@
+package com.openhtmltopdf.util;
+
+import org.junit.Test;
+
+import static org.hamcrest.CoreMatchers.is;
+import static org.junit.Assert.*;
+
+/**
+ * @author schrader
+ */
+public class OpenUtilTest {
+
+    @Test
+    public void areAllCharactersPrintable() {
+        String text = "abc 123 \uD844\uDCC1";
+        boolean printable = OpenUtil.areAllCharactersPrintable(text);
+        assertThat(printable, is(true));
+    }
+
+}

openhtmltopdf-examples/pom.xml

@@ -23,6 +23,11 @@
     </license>
   </licenses>
 
+  <properties>
+    <jmh.version>1.25.2</jmh.version>
+    <uberjar.name>benchmarks</uberjar.name>
+  </properties>
+
   <dependencies>
     <dependency>
       <groupId>com.openhtmltopdf</groupId>
@@ -115,6 +120,18 @@
         <version>1.13.1</version>
     </dependency>
 
+    <!-- JMH Benchmarks -->
+    <dependency>
+      <groupId>org.openjdk.jmh</groupId>
+      <artifactId>jmh-core</artifactId>
+      <version>${jmh.version}</version>
+    </dependency>
+    <dependency>
+      <groupId>org.openjdk.jmh</groupId>
+      <artifactId>jmh-generator-annprocess</artifactId>
+      <version>${jmh.version}</version>
+    </dependency>
+
     <dependency>
       <groupId>junit</groupId>
       <artifactId>junit</artifactId>
@@ -154,6 +171,51 @@
           </systemProperties>
         </configuration>
       </plugin>
+      <!-- workaround for: 'java.lang.IllegalStateException: endPosTable already set'.
+           see: https://bugs.java.com/bugdatabase/view_bug.do?bug_id=8067747
+           Thrown while compiling JMH classes
+           -->
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-compiler-plugin</artifactId>
+        <version>3.8.1</version>
+      </plugin>
+      <!-- Create an all-in JAR for running JMH benchmarks -->
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-shade-plugin</artifactId>
+        <version>2.2</version>
+        <executions>
+          <execution>
+            <phase>package</phase>
+            <goals>
+              <goal>shade</goal>
+            </goals>
+            <configuration>
+              <finalName>${uberjar.name}</finalName>
+              <transformers>
+                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
+                  <mainClass>org.openjdk.jmh.Main</mainClass>
+                </transformer>
+              </transformers>
+              <filters>
+                <filter>
+                  <!--
+                      Shading signed JARs will fail without this.
+                      http://stackoverflow.com/questions/999489/invalid-signature-file-when-attempting-to-run-a-jar
+                  -->
+                  <artifact>*:*</artifact>
+                  <excludes>
+                    <exclude>META-INF/*.SF</exclude>
+                    <exclude>META-INF/*.DSA</exclude>
+                    <exclude>META-INF/*.RSA</exclude>
+                  </excludes>
+                </filter>
+              </filters>
+            </configuration>
+          </execution>
+        </executions>
+      </plugin>
     </plugins>
     <resources>
       <resource>

openhtmltopdf-examples/src/main/java/com/openhtmltopdf/benchmark/NoopLogger.java

@@ -0,0 +1,31 @@
+package com.openhtmltopdf.benchmark;
+
+import com.openhtmltopdf.util.Diagnostic;
+import com.openhtmltopdf.util.XRLogger;
+
+import java.util.logging.Level;
+
+/**
+ * @author schrader
+ */
+class NoopLogger implements XRLogger {
+    @Override
+    public void log(String where, Level level, String msg) {
+
+    }
+
+    @Override
+    public void log(String where, Level level, String msg, Throwable th) {
+
+    }
+
+    @Override
+    public void setLevel(String logger, Level level) {
+
+    }
+
+    @Override
+    public boolean isLogLevelEnabled(Diagnostic diagnostic) {
+        return false;
+    }
+}

openhtmltopdf-examples/src/main/java/com/openhtmltopdf/benchmark/RenderTextBenchmark.java

@@ -0,0 +1,86 @@
+package com.openhtmltopdf.benchmark;
+
+import com.openhtmltopdf.pdfboxout.PdfRendererBuilder;
+import com.openhtmltopdf.util.XRLog;
+import org.apache.pdfbox.io.IOUtils;
+import org.apache.pdfbox.util.Charsets;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.runner.Runner;
+import org.openjdk.jmh.runner.options.Options;
+import org.openjdk.jmh.runner.options.OptionsBuilder;
+
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.Map;
+import java.util.concurrent.TimeUnit;
+
+/**
+ * @author schrader
+ */
+@BenchmarkMode(Mode.AverageTime)
+@OutputTimeUnit(TimeUnit.MILLISECONDS)
+@State(Scope.Thread)
+public class RenderTextBenchmark {
+
+    public static void main(String[] args) throws Exception {
+        Options opt = new OptionsBuilder()
+                .include(RenderTextBenchmark.class.getSimpleName())
+                .forks(1)
+                .build();
+
+        new Runner(opt).run();
+    }
+
+    private Map<String, String> contents = new HashMap<>();
+
+    @Setup
+    public void setUp() {
+        XRLog.setLoggerImpl(new NoopLogger());
+
+        Arrays.asList(
+                "/benchmark/render-text-plain.html",
+                "/benchmark/render-text-soft-hyphens.html"
+        ).forEach(path -> contents.put(path, readContent(path)));
+    }
+
+    @Benchmark
+    public void renderText_Plain() throws Exception {
+        runRenderer(contents.get("/benchmark/render-text-plain.html"));
+    }
+
+    @Benchmark
+    public void renderText_SoftHyphens() throws Exception {
+        runRenderer(contents.get("/benchmark/render-text-soft-hyphens.html"));
+    }
+
+    private void runRenderer(String html) throws IOException {
+        ByteArrayOutputStream actual = new ByteArrayOutputStream();
+
+        PdfRendererBuilder builder = new PdfRendererBuilder();
+        builder.withHtmlContent(html, null);
+        builder.toStream(actual);
+        builder.useFastMode();
+        builder.testMode(true);
+
+        builder.run();
+    }
+
+    private String readContent(String path) {
+        try (InputStream htmlIs = RenderTextBenchmark.class.getResourceAsStream(path)) {
+            byte[] htmlBytes = IOUtils.toByteArray(htmlIs);
+            return new String(htmlBytes, Charsets.UTF_8);
+        } catch (IOException e) {
+            throw new RuntimeException(e);
+        }
+    }
+
+}

openhtmltopdf-examples/src/main/resources/benchmark/render-text-plain.html

@@ -0,0 +1,11 @@
+<!DOCTYPE html PUBLIC
+        "-//OPENHTMLTOPDF//DOC XHTML Character Entities Only 1.0//EN" "">
+<html>
+<head>
+    <style>
+    </style>
+</head>
+<body>
+    <p>Li Europan lingues es membres del sam familie. Lor separat existentie es un myth. Por scientie, musica, sport etc, litot Europa usa li sam vocabular.</p>
+</body>
+</html>

openhtmltopdf-examples/src/main/resources/benchmark/render-text-soft-hyphens.html

@@ -0,0 +1,11 @@
+<!DOCTYPE html PUBLIC
+        "-//OPENHTMLTOPDF//DOC XHTML Character Entities Only 1.0//EN" "">
+<html>
+<head>
+    <style>
+    </style>
+</head>
+<body>
+    <p>Li Eu­ro­pan lin­gues es mem­bres del sam fa­mi­lie. Lor se­pa­rat exi­sten­tie es un myth. Por sci­en­tie, mu­si­ca, spo­rt etc.</p>
+</body>
+</html>

openhtmltopdf-pdfbox/src/main/java/com/openhtmltopdf/pdfboxout/PdfBoxFastOutputDevice.java

@@ -33,6 +33,7 @@
 import com.openhtmltopdf.extend.OutputDevice;
 import com.openhtmltopdf.extend.OutputDeviceGraphicsDrawer;
 import com.openhtmltopdf.extend.StructureType;
+import com.openhtmltopdf.extend.TextRenderer;
 import com.openhtmltopdf.layout.SharedContext;
 import com.openhtmltopdf.outputdevice.helper.FontResolverHelper;
 import com.openhtmltopdf.pdfboxout.PdfBoxFontResolver.FontDescription;
@@ -395,22 +396,22 @@ private AffineTransform normalizeMatrix(AffineTransform current) {
 
     public void drawString(String s, float x, float y, JustificationInfo info) {
         PDFont firstFont = _font.getFontDescription().get(0).getFont();
-
+
+        String effectiveString = TextRenderer.getEffectivePrintableString(s);
+
         // First check if the string contains printable characters only and
         // will print with the current font entirely.
         try {
-            if (areAllCharactersPrintable(s)) {
-                firstFont.encode(s);
-                // We got here, so all is good.
-                drawStringFast(s, x, y, info, _font.getFontDescription().get(0), _font.getSize2D());
-                return;
-            }
+            firstFont.getStringWidth(effectiveString);
+            // We got here, so all is good.
+            drawStringFast(effectiveString, x, y, info, _font.getFontDescription().get(0), _font.getSize2D());
+            return;
         }
         catch (Exception e) {
             // Fallthrough, we'll have to process the string into font runs.
         }
 
-        List<FontRun> fontRuns = PdfBoxTextRenderer.divideIntoFontRuns(_font, s, _reorderer);
+        List<FontRun> fontRuns = PdfBoxTextRenderer.divideIntoFontRuns(_font, effectiveString, _reorderer);
 
         float xOffset = 0f;
         for (FontRun run : fontRuns) {