GH-79 improved content parser (#164)

pcorless · Dec 29, 2020 · f646649 · f646649
1 parent 475e5ed
commit f646649
Show file tree

Hide file tree

Showing 16 changed files with 2,344 additions and 1,423 deletions.
diff --git a/build.gradle b/build.gradle
@@ -27,7 +27,7 @@ defaultTasks 'taskReport', 'dependencyReport', 'sourcesJar', 'genPomFileForCoreJ
 // Main distribution for os bundle
 distributions {
     os {
-        distributionBaseName.set("icepdf-os")
+        distributionBaseName.set("icepdf")
         version "${VERSION + (RELEASE_TYPE?.trim()? '-' + RELEASE_TYPE:'')}"
         contents {
             duplicatesStrategy = 'exclude'

diff --git a/core/core-awt/src/main/java/org/icepdf/core/pobjects/Form.java b/core/core-awt/src/main/java/org/icepdf/core/pobjects/Form.java
@@ -21,7 +21,6 @@
 import org.icepdf.core.pobjects.graphics.Shapes;
 import org.icepdf.core.util.Library;
 import org.icepdf.core.util.content.ContentParser;
-import org.icepdf.core.util.content.ContentParserFactory;
 
 import java.awt.geom.AffineTransform;
 import java.awt.geom.Rectangle2D;
@@ -185,8 +184,7 @@ public synchronized void init() throws InterruptedException {
         }
         // Build a new content parser for the content streams and apply the
         // content stream of the calling content stream. 
-        ContentParser cp = ContentParserFactory.getInstance()
-                .getContentParser(library, leafResources);
+        ContentParser cp = new ContentParser(library, leafResources);
         cp.setGraphicsState(graphicsState);
         byte[] in = getDecodedStreamBytes();
         if (in != null) {

diff --git a/core/core-awt/src/main/java/org/icepdf/core/pobjects/Page.java b/core/core-awt/src/main/java/org/icepdf/core/pobjects/Page.java
@@ -29,14 +29,13 @@
 import org.icepdf.core.pobjects.graphics.text.WordText;
 import org.icepdf.core.util.*;
 import org.icepdf.core.util.content.ContentParser;
-import org.icepdf.core.util.content.ContentParserFactory;
 
 import java.awt.*;
 import java.awt.geom.*;
 import java.io.IOException;
 import java.io.InputStream;
-import java.util.*;
 import java.util.List;
+import java.util.*;
 import java.util.logging.Level;
 import java.util.logging.Logger;
 
@@ -420,8 +419,7 @@ public synchronized void init() throws InterruptedException {
             notifyPageInitializationStarted();
             if (contents != null) {
                 try {
-                    ContentParser cp = ContentParserFactory.getInstance()
-                            .getContentParser(library, resources);
+                    ContentParser cp = new ContentParser(library, resources);
                     byte[][] streams = new byte[contents.size()][];
                     byte[] stream;
                     for (int i = 0, max = contents.size(); i < max; i++) {
@@ -1603,8 +1601,7 @@ public synchronized PageText getText() throws InterruptedException {
         if (contents != null) {
             try {
 
-                ContentParser cp = ContentParserFactory.getInstance()
-                        .getContentParser(library, resources);
+                ContentParser cp = new ContentParser(library, resources);
                 byte[][] streams = new byte[contents.size()][];
                 for (int i = 0, max = contents.size(); i < max; i++) {
                     streams[i] = contents.get(i).getDecodedStreamBytes();

diff --git a/core/core-awt/src/main/java/org/icepdf/core/pobjects/Stream.java b/core/core-awt/src/main/java/org/icepdf/core/pobjects/Stream.java
@@ -143,6 +143,7 @@ public byte[] getDecodedStreamBytes(int presize) {
         // decompress the stream
         if (compressed) {
             try {
+                // todo, could nio all a little speed up here.
                 ByteArrayInputStream streamInput = new ByteArrayInputStream(rawBytes);
                 long rawStreamLength = rawBytes.length;
                 InputStream input = getDecodedInputStream(streamInput, rawStreamLength);

diff --git a/...core-awt/src/main/java/org/icepdf/core/pobjects/acroform/VariableTextFieldDictionary.java b/...core-awt/src/main/java/org/icepdf/core/pobjects/acroform/VariableTextFieldDictionary.java
@@ -24,7 +24,6 @@
 import org.icepdf.core.util.Library;
 import org.icepdf.core.util.Utils;
 import org.icepdf.core.util.content.ContentParser;
-import org.icepdf.core.util.content.ContentParserFactory;
 
 import java.awt.*;
 import java.util.HashMap;
@@ -136,8 +135,7 @@ public VariableTextFieldDictionary(Library library, HashMap entries) {
             // the font and colour information we need to generate a new content stream
             if (resources != null) {
                 try {
-                    ContentParser cp = ContentParserFactory.getInstance()
-                            .getContentParser(library, resources);
+                    ContentParser cp = new ContentParser(library, resources);
                     cp.parseTextBlocks(new byte[][]{defaultAppearance.getBytes()});
                     GraphicsState gs = cp.getGraphicsState();
                     if (gs != null) {
@@ -178,8 +176,7 @@ public String generateDefaultAppearance(String content, Resources resources) {
             if (resources == null) {
                 resources = library.getCatalog().getInteractiveForm().getResources();
             }
-            ContentParser cp = ContentParserFactory.getInstance()
-                    .getContentParser(library, resources);
+            ContentParser cp = new ContentParser(library, resources);
             // use full parser so we parse the font color.
             cp.parse(new byte[][]{possibleContent.getBytes()}, null);
             GraphicsState gs = cp.getGraphicsState();

diff --git a/core/core-awt/src/main/java/org/icepdf/core/pobjects/annotations/AppearanceState.java b/core/core-awt/src/main/java/org/icepdf/core/pobjects/annotations/AppearanceState.java
@@ -20,7 +20,6 @@
 import org.icepdf.core.pobjects.graphics.Shapes;
 import org.icepdf.core.util.Library;
 import org.icepdf.core.util.content.ContentParser;
-import org.icepdf.core.util.content.ContentParserFactory;
 
 import java.awt.geom.AffineTransform;
 import java.awt.geom.Rectangle2D;
@@ -77,8 +76,7 @@ public AppearanceState(Library library, HashMap entries, Object streamOrDictiona
             matrix = new AffineTransform();
             originalContentStream = new String(stream.getDecodedStreamBytes());
             try {
-                ContentParser cp = ContentParserFactory.getInstance()
-                        .getContentParser(library, resources);
+                ContentParser cp = new ContentParser(library, resources);
                 shapes = cp.parse(new byte[][]{stream.getDecodedStreamBytes()}, null).getShapes();
             } catch (Exception e) {
                 shapes = new Shapes();
@@ -139,8 +137,7 @@ public String getOriginalContentStream() {
 
     public void setContentStream(byte[] contentBytes){
         try {
-            ContentParser cp = ContentParserFactory.getInstance()
-                    .getContentParser(library, resources);
+            ContentParser cp = new ContentParser(library, resources);
             shapes = cp.parse(new byte[][]{contentBytes}, null).getShapes();
         } catch (Exception e) {
             shapes = new Shapes();

diff --git a/core/core-awt/src/main/java/org/icepdf/core/pobjects/annotations/TextAnnotation.java b/core/core-awt/src/main/java/org/icepdf/core/pobjects/annotations/TextAnnotation.java
@@ -19,7 +19,6 @@
 import org.icepdf.core.pobjects.graphics.Shapes;
 import org.icepdf.core.util.Library;
 import org.icepdf.core.util.content.ContentParser;
-import org.icepdf.core.util.content.ContentParserFactory;
 
 import java.awt.*;
 import java.awt.geom.AffineTransform;
@@ -277,7 +276,7 @@ public void resetAppearanceStream(double dx, double dy, AffineTransform pageTran
         // parse the shapes and assign to this instance
         try {
             Resources resources = form.getResources();
-            ContentParser cp = ContentParserFactory.getInstance().getContentParser(library, resources);
+            ContentParser cp = new ContentParser(library, resources);
             shapes = cp.parse(new byte[][]{iconContentString.getBytes()}, null).getShapes();
         } catch (Exception e) {
             shapes = new Shapes();

diff --git a/core/core-awt/src/main/java/org/icepdf/core/pobjects/graphics/TilingPattern.java b/core/core-awt/src/main/java/org/icepdf/core/pobjects/graphics/TilingPattern.java
@@ -24,7 +24,6 @@
 import org.icepdf.core.util.Defs;
 import org.icepdf.core.util.Library;
 import org.icepdf.core.util.content.ContentParser;
-import org.icepdf.core.util.content.ContentParserFactory;
 
 import java.awt.*;
 import java.awt.geom.AffineTransform;
@@ -287,8 +286,7 @@ public synchronized void init(GraphicsState graphicsState) {
 
         // Build a new content parser for the content streams and apply the
         // content stream of the calling content stream.
-        ContentParser cp = ContentParserFactory.getInstance()
-                .getContentParser(library, resources);
+        ContentParser cp = new ContentParser(library, resources);
         cp.setGraphicsState(parentGraphicState);
         try {
             shapes = cp.parse(new byte[][]{getDecodedStreamBytes()}, null).getShapes();

diff --git a/core/core-awt/src/main/java/org/icepdf/core/util/Library.java b/core/core-awt/src/main/java/org/icepdf/core/util/Library.java
@@ -58,7 +58,7 @@ public class Library {
     static {
         try {
             commonPoolThreads =
-                    Defs.intProperty("org.icepdf.core.library.threadPoolSize", 2);
+                    Defs.intProperty("org.icepdf.core.library.threadPoolSize", 4);
             if (commonPoolThreads < 1) {
                 commonPoolThreads = 2;
             }