如何使用iText和XMLWorker(HTML到PDF/a过程)生成有效的PDF/a文件
我目前正在开发一种方法,可以接受HTML输入并将其转换为有效的PDF/a文件。我知道如何使用iText(参考:)以编程方式构造有效的PDF/a文件,但我无法使用HTML作为输入并使用XMLWorker将此输入转换为PDF文件来生成有效的PDF/a文件。我现在遇到的问题是由于PDF/A格式的嵌入式字体要求。我总是遇到这样的例外: 线程“main”com.itextpdf.text.pdf.PdfAConformanceException中的异常:必须嵌入所有字体。这个不是:Helvetica 我试图通过CSS文件强制HTML输入使用哪些字体,并通过XMLWorkerFontProvider类在输出PDF文件中注册要使用的字体,但似乎我做错了什么,因为上面注释的异常总是被抛出 为了让XMLWorker使用通过XMLWorkerFontProvider类注册的字体,我还需要什么?我希望避免在输入中的每个HTML元素中使用默认字体Helvetica 下面是我用于测试的代码: style.css(仅1行): Main.java:如何使用iText和XMLWorker(HTML到PDF/a过程)生成有效的PDF/a文件,pdf,fonts,itext,pdfa,xmlworker,Pdf,Fonts,Itext,Pdfa,Xmlworker,我目前正在开发一种方法,可以接受HTML输入并将其转换为有效的PDF/a文件。我知道如何使用iText(参考:)以编程方式构造有效的PDF/a文件,但我无法使用HTML作为输入并使用XMLWorker将此输入转换为PDF文件来生成有效的PDF/a文件。我现在遇到的问题是由于PDF/A格式的嵌入式字体要求。我总是遇到这样的例外: 线程“main”com.itextpdf.text.pdf.PdfAConformanceException中的异常:必须嵌入所有字体。这个不是:Helvetica 我试
package com.itextpdf;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.Reader;
import java.io.StringReader;
import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.ICC_Profile;
import com.itextpdf.text.pdf.PdfAConformanceLevel;
import com.itextpdf.text.pdf.PdfAWriter;
import com.itextpdf.tool.xml.XMLWorker;
import com.itextpdf.tool.xml.XMLWorkerFontProvider;
import com.itextpdf.tool.xml.XMLWorkerHelper;
import com.itextpdf.tool.xml.css.CssFile;
import com.itextpdf.tool.xml.css.StyleAttrCSSResolver;
import com.itextpdf.tool.xml.html.CssAppliers;
import com.itextpdf.tool.xml.html.CssAppliersImpl;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
import com.itextpdf.tool.xml.pipeline.css.CSSResolver;
import com.itextpdf.tool.xml.pipeline.css.CssResolverPipeline;
import com.itextpdf.tool.xml.pipeline.end.PdfWriterPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;
public class Main {
/**
* @param args
*/
public static void main(String[] args) {
StringBuffer buf = new StringBuffer();
buf.append("<!DOCTYPE html>");
buf.append("<html>");
buf.append("<head>");
buf.append("<title>Test</title>");
buf.append("</head>");
buf.append("<body>");
buf.append("<p>This is a test</p>");
buf.append("</body>");
buf.append("</html>");
OutputStream file = null;
Document document = null;
PdfAWriter writer = null;
try {
file = new FileOutputStream(new File("C:\\Users\\amartin\\Desktop\\Test.pdf"));
document = new Document();
writer = PdfAWriter.getInstance(document, file, PdfAConformanceLevel.PDF_A_1B);
// Create XMP metadata. It's a PDF/A requirement.
writer.createXmpMetadata();
document.open();
// Set output intent. PDF/A requirement.
ICC_Profile icc = ICC_Profile.getInstance(new FileInputStream("./src/main/resources/com/itextpdf/sRGB Color Space Profile.icm"));
writer.setOutputIntents("Custom", "", "http://www.color.org", "sRGB IEC61966-2.1", icc);
// CSS
CSSResolver cssResolver = new StyleAttrCSSResolver();
CssFile cssFile = XMLWorkerHelper.getCSS(new FileInputStream("./css/style.css"));
cssResolver.addCss(cssFile);
XMLWorkerFontProvider fontProvider = new XMLWorkerFontProvider();
fontProvider.register("./fonts/arial.ttf");
fontProvider.register("./fonts/sans-serif.ttf");
fontProvider.addFontSubstitute("lowagie", "garamond");
CssAppliers cssAppliers = new CssAppliersImpl(fontProvider);
HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
// Pipelines
PdfWriterPipeline pdf = new PdfWriterPipeline(document, writer);
HtmlPipeline html = new HtmlPipeline(htmlContext, pdf);
CssResolverPipeline css = new CssResolverPipeline(cssResolver, html);
XMLWorker worker = new XMLWorker(css, true);
XMLParser p = new XMLParser(worker);
Reader reader = new StringReader(buf.toString());
p.parse(reader);
} catch (Exception e) {
e.printStackTrace();
} finally {
if (document != null && document.isOpen())
document.close();
try {
if (file != null)
file.close();
} catch (IOException e) {}
if (writer != null && !writer.isCloseStream())
writer.close();
}
}
}
package com.itextpdf;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.Reader;
import java.io.StringReader;
import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.ICC_Profile;
import com.itextpdf.text.pdf.PdfAConformanceLevel;
import com.itextpdf.text.pdf.PdfAWriter;
import com.itextpdf.tool.xml.XMLWorker;
import com.itextpdf.tool.xml.XMLWorkerHelper;
import com.itextpdf.tool.xml.css.CssFile;
import com.itextpdf.tool.xml.css.StyleAttrCSSResolver;
import com.itextpdf.tool.xml.html.CssAppliers;
import com.itextpdf.tool.xml.html.CssAppliersImpl;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
import com.itextpdf.tool.xml.pipeline.css.CSSResolver;
import com.itextpdf.tool.xml.pipeline.css.CssResolverPipeline;
import com.itextpdf.tool.xml.pipeline.end.PdfWriterPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;
public class Main {
public static void main(String[] args) {
StringBuffer buf = new StringBuffer();
String title = "Test";
// Sample HTML content.
buf.append("<!DOCTYPE html>");
buf.append("<html>");
buf.append("<head>");
buf.append("<title>" + title + "</title>");
buf.append("</head>");
buf.append("<body>");
buf.append("<p>This is a test</p>");
buf.append("</body>");
buf.append("</html>");
OutputStream file = null;
Document document = null;
PdfAWriter writer = null;
try {
file = new FileOutputStream(new File("C:\\Users\\amartin\\Desktop\\Test.pdf"));
document = new Document();
writer = PdfAWriter.getInstance(document, file, PdfAConformanceLevel.PDF_A_1B);
// Avoid discrepances between document title and XMP metadata information.
document.addTitle(title);
// Create XMP metadata. It's a PDF/A requirement.
writer.createXmpMetadata();
document.open();
// Set output intent. PDF/A requirement.
ICC_Profile icc = ICC_Profile.getInstance(new FileInputStream("./src/main/resources/com/itextpdf/sRGB Color Space Profile.icm"));
writer.setOutputIntents("Custom", "", "http://www.color.org", "sRGB IEC61966-2.1", icc);
// CSS stylesheet.
CSSResolver cssResolver = new StyleAttrCSSResolver();
CssFile cssFile = XMLWorkerHelper.getCSS(new FileInputStream("./css/style.css"));
cssResolver.addCss(cssFile);
MyFontProvider fontProvider = new MyFontProvider();
fontProvider.register("./fonts/arial.ttf");
/* DEBUG
System.out.println("Fonts present in " + fontProvider.getClass().getName());
Set<String> registeredFonts = fontProvider.getRegisteredFonts();
for (String font : registeredFonts)
System.out.println(font);
*/
CssAppliers cssAppliers = new CssAppliersImpl(fontProvider);
HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
// Pipelines.
PdfWriterPipeline pdf = new PdfWriterPipeline(document, writer);
HtmlPipeline html = new HtmlPipeline(htmlContext, pdf);
CssResolverPipeline css = new CssResolverPipeline(cssResolver, html);
XMLWorker worker = new XMLWorker(css, true);
XMLParser p = new XMLParser(worker);
Reader reader = new StringReader(buf.toString());
p.parse(reader);
} catch (Exception e) {
e.printStackTrace();
} finally {
if (document != null && document.isOpen())
document.close();
try {
if (file != null)
file.close();
} catch (IOException e) {}
if (writer != null && !writer.isCloseStream())
writer.close();
}
}
}
然后使用相同的参数调用parent.getFont()方法。我看到的唯一输出是:
=fontname:null=编码:Cp1252=嵌入:true=大小:-1.0=样式:-1=基色:null
=fontname:null=编码:Cp1252=嵌入:true=大小:-1.0=样式:-1=基色:null
然后抛出异常,粘贴在此代码之前。根据您发送到
System.out
的反馈,XML Worker似乎没有选择您想要使用的字体系列
请按以下方式指定字体系列:
System.out.println("=fontname: " + fontname + " =encoding: " + encoding + " =embedded : " + embedded + " =size: " + size + " =style: " + style + " =BaseColor: " + color)
font-family: "Arial"
在CSS中使用“字体”可能会奏效,但这很棘手。我认为iText看到的是
normal
,并将其解释为使用默认字体。使此示例正常工作的完整代码如下:
style.css:
* {
font-family: "Arial";
font-style: normal;
}
Main.java:
package com.itextpdf;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.Reader;
import java.io.StringReader;
import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.ICC_Profile;
import com.itextpdf.text.pdf.PdfAConformanceLevel;
import com.itextpdf.text.pdf.PdfAWriter;
import com.itextpdf.tool.xml.XMLWorker;
import com.itextpdf.tool.xml.XMLWorkerFontProvider;
import com.itextpdf.tool.xml.XMLWorkerHelper;
import com.itextpdf.tool.xml.css.CssFile;
import com.itextpdf.tool.xml.css.StyleAttrCSSResolver;
import com.itextpdf.tool.xml.html.CssAppliers;
import com.itextpdf.tool.xml.html.CssAppliersImpl;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
import com.itextpdf.tool.xml.pipeline.css.CSSResolver;
import com.itextpdf.tool.xml.pipeline.css.CssResolverPipeline;
import com.itextpdf.tool.xml.pipeline.end.PdfWriterPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;
public class Main {
/**
* @param args
*/
public static void main(String[] args) {
StringBuffer buf = new StringBuffer();
buf.append("<!DOCTYPE html>");
buf.append("<html>");
buf.append("<head>");
buf.append("<title>Test</title>");
buf.append("</head>");
buf.append("<body>");
buf.append("<p>This is a test</p>");
buf.append("</body>");
buf.append("</html>");
OutputStream file = null;
Document document = null;
PdfAWriter writer = null;
try {
file = new FileOutputStream(new File("C:\\Users\\amartin\\Desktop\\Test.pdf"));
document = new Document();
writer = PdfAWriter.getInstance(document, file, PdfAConformanceLevel.PDF_A_1B);
// Create XMP metadata. It's a PDF/A requirement.
writer.createXmpMetadata();
document.open();
// Set output intent. PDF/A requirement.
ICC_Profile icc = ICC_Profile.getInstance(new FileInputStream("./src/main/resources/com/itextpdf/sRGB Color Space Profile.icm"));
writer.setOutputIntents("Custom", "", "http://www.color.org", "sRGB IEC61966-2.1", icc);
// CSS
CSSResolver cssResolver = new StyleAttrCSSResolver();
CssFile cssFile = XMLWorkerHelper.getCSS(new FileInputStream("./css/style.css"));
cssResolver.addCss(cssFile);
XMLWorkerFontProvider fontProvider = new XMLWorkerFontProvider();
fontProvider.register("./fonts/arial.ttf");
fontProvider.register("./fonts/sans-serif.ttf");
fontProvider.addFontSubstitute("lowagie", "garamond");
CssAppliers cssAppliers = new CssAppliersImpl(fontProvider);
HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
// Pipelines
PdfWriterPipeline pdf = new PdfWriterPipeline(document, writer);
HtmlPipeline html = new HtmlPipeline(htmlContext, pdf);
CssResolverPipeline css = new CssResolverPipeline(cssResolver, html);
XMLWorker worker = new XMLWorker(css, true);
XMLParser p = new XMLParser(worker);
Reader reader = new StringReader(buf.toString());
p.parse(reader);
} catch (Exception e) {
e.printStackTrace();
} finally {
if (document != null && document.isOpen())
document.close();
try {
if (file != null)
file.close();
} catch (IOException e) {}
if (writer != null && !writer.isCloseStream())
writer.close();
}
}
}
package com.itextpdf;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.io.Reader;
import java.io.StringReader;
import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.ICC_Profile;
import com.itextpdf.text.pdf.PdfAConformanceLevel;
import com.itextpdf.text.pdf.PdfAWriter;
import com.itextpdf.tool.xml.XMLWorker;
import com.itextpdf.tool.xml.XMLWorkerHelper;
import com.itextpdf.tool.xml.css.CssFile;
import com.itextpdf.tool.xml.css.StyleAttrCSSResolver;
import com.itextpdf.tool.xml.html.CssAppliers;
import com.itextpdf.tool.xml.html.CssAppliersImpl;
import com.itextpdf.tool.xml.html.Tags;
import com.itextpdf.tool.xml.parser.XMLParser;
import com.itextpdf.tool.xml.pipeline.css.CSSResolver;
import com.itextpdf.tool.xml.pipeline.css.CssResolverPipeline;
import com.itextpdf.tool.xml.pipeline.end.PdfWriterPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipeline;
import com.itextpdf.tool.xml.pipeline.html.HtmlPipelineContext;
public class Main {
public static void main(String[] args) {
StringBuffer buf = new StringBuffer();
String title = "Test";
// Sample HTML content.
buf.append("<!DOCTYPE html>");
buf.append("<html>");
buf.append("<head>");
buf.append("<title>" + title + "</title>");
buf.append("</head>");
buf.append("<body>");
buf.append("<p>This is a test</p>");
buf.append("</body>");
buf.append("</html>");
OutputStream file = null;
Document document = null;
PdfAWriter writer = null;
try {
file = new FileOutputStream(new File("C:\\Users\\amartin\\Desktop\\Test.pdf"));
document = new Document();
writer = PdfAWriter.getInstance(document, file, PdfAConformanceLevel.PDF_A_1B);
// Avoid discrepances between document title and XMP metadata information.
document.addTitle(title);
// Create XMP metadata. It's a PDF/A requirement.
writer.createXmpMetadata();
document.open();
// Set output intent. PDF/A requirement.
ICC_Profile icc = ICC_Profile.getInstance(new FileInputStream("./src/main/resources/com/itextpdf/sRGB Color Space Profile.icm"));
writer.setOutputIntents("Custom", "", "http://www.color.org", "sRGB IEC61966-2.1", icc);
// CSS stylesheet.
CSSResolver cssResolver = new StyleAttrCSSResolver();
CssFile cssFile = XMLWorkerHelper.getCSS(new FileInputStream("./css/style.css"));
cssResolver.addCss(cssFile);
MyFontProvider fontProvider = new MyFontProvider();
fontProvider.register("./fonts/arial.ttf");
/* DEBUG
System.out.println("Fonts present in " + fontProvider.getClass().getName());
Set<String> registeredFonts = fontProvider.getRegisteredFonts();
for (String font : registeredFonts)
System.out.println(font);
*/
CssAppliers cssAppliers = new CssAppliersImpl(fontProvider);
HtmlPipelineContext htmlContext = new HtmlPipelineContext(cssAppliers);
htmlContext.setTagFactory(Tags.getHtmlTagProcessorFactory());
// Pipelines.
PdfWriterPipeline pdf = new PdfWriterPipeline(document, writer);
HtmlPipeline html = new HtmlPipeline(htmlContext, pdf);
CssResolverPipeline css = new CssResolverPipeline(cssResolver, html);
XMLWorker worker = new XMLWorker(css, true);
XMLParser p = new XMLParser(worker);
Reader reader = new StringReader(buf.toString());
p.parse(reader);
} catch (Exception e) {
e.printStackTrace();
} finally {
if (document != null && document.isOpen())
document.close();
try {
if (file != null)
file.close();
} catch (IOException e) {}
if (writer != null && !writer.isCloseStream())
writer.close();
}
}
}
再次感谢你,布鲁诺。我很高兴在这里得到您的帮助:)创建自己的
FontProvider
实现,并将请求的字体写入系统。out
。确保所有这些字体都映射到字体程序。嗨,布鲁诺。我按照你的评论做了,我已经发布了编辑问题的结果。如果您愿意提供一些反馈或建议,我将不胜感激。输出意味着您在CSS中定义的字体没有被XML Worker使用。现在我看看你的CSS,我知道为什么了。试试font-family:“Arial”
而不是使用font
。现在效果很好,布鲁诺。非常感谢你的帮助!你愿意回答这个问题吗?然后我可以把你的答案标记为正确后关闭它?再次,非常感谢:-)你能看一下这个问题吗:我使用了你的代码,但收到错误消息所有字体都必须嵌入。这个不是:Helvetica
。如何在Windows计算机上修复此问题?我正在使用fontProvider.register(“C:\\Windows\\font\\Arial.ttf”)代码>