Merge pull request #282 from metanorma/pdf_a

PDF/A-3A validation fix

Makefile

@@ -6,7 +6,7 @@ SHELL ?= /bin/bash
 endif
 
 #JAR_VERSION := $(shell mvn -q -Dexec.executable="echo" -Dexec.args='$${project.version}' --non-recursive exec:exec -DforceStdout)
-JAR_VERSION := 1.99
+JAR_VERSION := 2.00
 JAR_FILE := mn2pdf-$(JAR_VERSION).jar
 
 all: target/$(JAR_FILE)

README.adoc

@@ -17,14 +17,14 @@ You will need the Java Development Kit (JDK) version 8, Update 241 (8u241) or hi
 
 [source,sh]
 ----
-java -Xss5m -Xmx2048m -jar target/mn2pdf-1.99.jar --xml-file <XML-FileName> --xsl-file <XSLT-FileName> --pdf-file <Output-PDF-FileName> [--syntax-highlight]
+java -Xss5m -Xmx2048m -jar target/mn2pdf-2.00.jar --xml-file <XML-FileName> --xsl-file <XSLT-FileName> --pdf-file <Output-PDF-FileName> [--syntax-highlight]
 ----
 
 e.g.
 
 [source,sh]
 ----
-java -Xss5m -Xmx2048m -jar target/mn2pdf-1.99.jar --xml-file tests/G.191.xml --xsl-file tests/itu.recommendation.xsl --pdf-file tests/G.191.pdf
+java -Xss5m -Xmx2048m -jar target/mn2pdf-2.00.jar --xml-file tests/G.191.xml --xsl-file tests/itu.recommendation.xsl --pdf-file tests/G.191.pdf
 ----
 
 === PDF encryption features
@@ -100,7 +100,7 @@ Update version in `pom.xml`, e.g.:
 ----
 <groupId>org.metanorma.fop</groupId>
 <artifactId>mn2pdf</artifactId>
-<version>1.99</version>
+<version>2.00</version>
 <name>Metanorma XML to PDF converter</name>
 ----
 
@@ -111,8 +111,8 @@ Tag the same version in Git:
 
 [source,xml]
 ----
-git tag v1.99
-git push origin v1.99
+git tag v2.00
+git push origin v2.00
 ----
 
 Then the corresponding GitHub release will be automatically created at:

pom.xml

@@ -5,7 +5,7 @@
  <modelVersion>4.0.0</modelVersion>
  <groupId>org.metanorma.fop</groupId>
  <artifactId>mn2pdf</artifactId>
- <version>1.99</version>
+ <version>2.00</version>
  <name>Metanorma XML to PDF converter</name>
  <packaging>jar</packaging>
  <url>https://www.metanorma.org</url>
@@ -96,25 +96,35 @@
  <goals>
  <goal>shade</goal>
  </goals>
- <configuration>
- <transformers>
- <transformer
- implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
- <resource>META-INF/services/org.apache.xmlgraphics.image.loader.spi.ImagePreloader</resource>
- </transformer>
- <transformer
- implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
- <transformer
- implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
- <manifestEntries>
- <Main-Class>org.metanorma.fop.mn2pdf</Main-Class>
- <Implementation-Version>${project.version}</Implementation-Version>
- </manifestEntries>
- </transformer>
- </transformers>
- </configuration>
  </execution>
  </executions>
+ <configuration>
+ <transformers>
+ <transformer
+ implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
+ <resource>META-INF/services/org.apache.xmlgraphics.image.loader.spi.ImagePreloader</resource>
+ </transformer>
+ <transformer
+ implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
+ <transformer
+ implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
+ <manifestEntries>
+ <Main-Class>org.metanorma.fop.mn2pdf</Main-Class>
+ <Implementation-Version>${project.version}</Implementation-Version>
+ </manifestEntries>
+ </transformer>
+ </transformers>
+ <filters>
+ <filter>
+ <artifact>*:*</artifact>
+ <excludes>
+ <exclude>META-INF/*.SF</exclude>
+ <exclude>META-INF/*.DSA</exclude>
+ <exclude>META-INF/*.RSA</exclude>
+ </excludes>
+ </filter>
+ </filters>
+ </configuration>
  </plugin>
  <plugin>
  <groupId>org.apache.maven.plugins</groupId>
@@ -282,5 +292,15 @@
  <artifactId>webp-imageio</artifactId>
  <version>0.1.6</version>
  </dependency>
+ <dependency>
+ <groupId>org.verapdf</groupId>
+ <artifactId>validation-model</artifactId>
+ <version>1.26.1</version>
+ </dependency>
+ <dependency>
+ <groupId>org.verapdf</groupId>
+ <artifactId>validation-model-jakarta</artifactId>
+ <version>1.26.1</version>
+ </dependency>
  </dependencies>
 </project>

src/main/java/org/metanorma/fop/PDFConformanceChecker.java

@@ -0,0 +1,13 @@
+package org.metanorma.fop;
+
+import static org.metanorma.Constants.PDF_A_MODE;
+
+public class PDFConformanceChecker {
+
+ public static boolean hasException(String msg) {
+ if (msg != null) {
+ return msg.contains("PDFConformanceException") && (msg.contains("PDF/UA-1") || msg.contains(PDF_A_MODE));
+ }
+ return false;
+ }
+}

src/main/java/org/metanorma/fop/PDFGenerator.java

@@ -490,6 +490,11 @@ private void convertmn2pdf(fontConfig fontcfg, XSLTconverter xsltConverter, File
  logger.info(WARNING_NONPDFUA);
  }
 
+ // validate PDF by veraPDF
+ VeraPDFValidator veraPDFValidator = new VeraPDFValidator();
+ veraPDFValidator.validate(pdf);
+
+
  fontcfg.printMessages();
 
  } catch (Exception e) {
@@ -580,6 +585,13 @@ private void runFOP (fontConfig fontcfg, Source src, File pdf) throws IOExceptio
  FOUserAgent foUserAgent = fopFactory.newFOUserAgent();
  // configure foUserAgent
  foUserAgent.setProducer("Ribose Metanorma mn2pdf version " + Util.getAppVersion());
+
+ if (encryptionParams.isEmpty()) {
+ foUserAgent.getRendererOptions().put("pdf-a-mode", PDF_A_MODE);
+ } else {
+ logger.severe("PDF/A doesn't allow encrypted PDFs. PDF will be generated in non-PDF/A mode.");
+ }
+
  setEncryptionParams(foUserAgent);
 
  //Adding a simple logging listener that writes to stdout and stderr 
@@ -641,8 +653,7 @@ private void runFOP (fontConfig fontcfg, Source src, File pdf) throws IOExceptio
  }
 
  } catch (Exception e) {
- String excstr=e.toString();
- if (excstr.contains("PDFConformanceException") && excstr.contains("PDF/UA-1") && !PDFUA_error) { // excstr.contains("all fonts, even the base 14 fonts, have to be embedded")
+ if (PDFConformanceChecker.hasException(e.toString()) && !PDFUA_error) { // excstr.contains("all fonts, even the base 14 fonts, have to be embedded")
  //System.err.println(e.toString());
  logger.severe(e.toString());
  PDFUA_error = true;
@@ -1053,8 +1064,7 @@ public void error(TransformerException exc)
 
  public void fatalError(TransformerException exc)
  throws TransformerException {
- String excstr=exc.toString();
- if (excstr.contains("PDFConformanceException") && excstr.contains("PDF/UA-1") && !PDFUA_error) { // excstr.contains("all fonts, even the base 14 fonts, have to be embedded")
+ if (PDFConformanceChecker.hasException(exc.toString()) && !PDFUA_error) { // excstr.contains("all fonts, even the base 14 fonts, have to be embedded")
  //System.err.println(exc.toString());
  logger.severe(exc.toString());
  PDFUA_error = true;

src/main/java/org/metanorma/fop/Util.java

@@ -573,6 +573,13 @@ public static int getStringWidth(String text, String fontName) {
  return stringWidth;
  }
 
+ public static float getStringWidthByFontSize(String text, String fontName, int fontSize) {
+ float stringWidth = 0.0f;
+ Font font = new Font(fontName, Font.PLAIN, fontSize);
+ stringWidth = SVGUtilities.getStringWidth(text, font);
+ return stringWidth;
+ }
+
  public static String saveFileToDisk(String filename, String content) {
  try {
  Files.createDirectories(tmpfilepath);

src/main/java/org/metanorma/fop/VeraPDFValidator.java

@@ -0,0 +1,55 @@
+package org.metanorma.fop;
+
+import org.metanorma.utils.LoggerHelper;
+import org.verapdf.core.EncryptedPdfException;
+import org.verapdf.core.ModelParsingException;
+import org.verapdf.core.ValidationException;
+import org.verapdf.gf.foundry.VeraGreenfieldFoundryProvider;
+import org.verapdf.pdfa.Foundries;
+import org.verapdf.pdfa.PDFAParser;
+import org.verapdf.pdfa.results.ValidationResult;
+import org.verapdf.pdfa.PDFAValidator;
+import org.verapdf.pdfa.flavours.PDFAFlavour;
+import org.verapdf.report.HTMLReport;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.logging.Logger;
+
+import static org.metanorma.Constants.PDF_A_MODE;
+
+public class VeraPDFValidator {
+
+ protected static final Logger logger = Logger.getLogger(LoggerHelper.LOGGER_NAME);
+
+ // see https://docs.verapdf.org/develop/
+ public void validate(File filePDF) {
+ VeraGreenfieldFoundryProvider.initialise();
+ String sPDFAmode = PDF_A_MODE.substring(PDF_A_MODE.indexOf("-"));
+ PDFAFlavour flavour = PDFAFlavour.fromString(sPDFAmode);
+ try (PDFAParser parser = Foundries.defaultInstance().createParser(new FileInputStream(filePDF), flavour)) {
+ PDFAValidator validator = Foundries.defaultInstance().createValidator(flavour, false);
+ ValidationResult result = validator.validate(parser);
+
+ if (result.isCompliant()) {
+ // File is a valid PDF/A PDF_A_MODE
+ return;
+ } else {
+ // it isn't
+ logger.severe("PDF isn't valid " + PDF_A_MODE + ":");
+ String veraPDFresult = result.toString();
+ veraPDFresult = veraPDFresult.replaceAll("(TestAssertion )","\n$1")
+ .replaceAll("\\s(message=)","\n$1")
+ .replaceAll("\\s(location=)","\n$1");
+ logger.severe(veraPDFresult);
+ //HTMLReport.writeHTMLReport()
+ }
+ } catch (IOException | ValidationException | ModelParsingException | EncryptedPdfException exception) {
+ // Exception during validation
+ logger.severe(exception.toString());
+ }
+ return;
+ }
+
+}

src/main/java/org/metanorma/fop/annotations/Annotation.java

@@ -269,6 +269,8 @@ public void process(File pdf, String xmlReview) throws IOException {
 
  PDAnnotation pdfannot = PDAnnotation.createAnnotation(fdfannot.getCOSObject());
 
+ pdfannot.constructAppearances(); // requires for PDF/A
+
  if (map_pdfannots.get(page) == null) {
  map_pdfannots.put(page, new ArrayList<PDAnnotation>());
  }

src/main/resources/xfdf_simple.xsl

@@ -93,7 +93,7 @@
  <text>
  <xsl:attribute name="color"><xsl:value-of select="$color_annotation"/></xsl:attribute>
  <xsl:attribute name="opacity"><xsl:value-of select="$opacity_popup"/></xsl:attribute>
- <xsl:attribute name="flags">nozoom,norotate</xsl:attribute>
+ <xsl:attribute name="flags">print,nozoom,norotate</xsl:attribute>
  <xsl:attribute name="date"><xsl:value-of select="$date"/></xsl:attribute>
  <xsl:attribute name="page"><xsl:value-of select="$page - 1"/></xsl:attribute>
  <xsl:attribute name="rect"><xsl:value-of select="concat($element_from/@x,',',$element_from/@y)"/></xsl:attribute>