java 利用itext将html转为pdf
Java项目需要将html转为pdf，在网上找了几个版本，转出来的效果都不理想：1、样式错乱 2、中文显示问题
最终自己找了个合适的版本：
package com.test;
import java.io.File;
import java.io.FileOutputStream;
import java.io.OutputStream;
import org.xhtmlrenderer.pdf.ITextFontResolver;
import org.xhtmlrenderer.pdf.ITextRenderer;
import com.itextpdf.text.pdf.BaseFont;
public class htmlToPDF {
public static void html2pdf(String htmlFile, String pdfFile) throws Exception {
String url = new File(htmlFile).toURI().toURL().toString();
System.out.println(url);
// step 2
OutputStream os = new FileOutputStream(pdfFile);
ITextRenderer renderer = new ITextRenderer();
renderer.setDocument(url);
// step 3 解决中文支持
ITextFontResolver fontResolver = renderer.getFontResolver();
if ("linux".equals(getCurrentOperatingSystem())) {
fontResolver.addFont("/usr/share/fonts/chiness/simsun.ttc", BaseFont.IDENTITY_H, BaseFont.EMBEDDED);
} else {
fontResolver.addFont("c:/Windows/Fonts/simsun.ttc", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);
}
renderer.layout();
renderer.createPDF(os);
os.close();
System.out.println("create pdf done!!");
}
//判断操作系统
public static String getCurrentOperatingSystem() {
String os = System.getProperty("os.name").toLowerCase();
return os;
}
public static void main(String[] args) {
String htmlFile = "C:/Users/Administrator/Desktop/1535075053000.html";
String pdfFile = "D:/LOGS/dddd.pdf";
try {
htmlToPDF.html2pdf(htmlFile, pdfFile);
} catch (Exception e) {
e.printStackTrace();
}
}
}
以上代码在网络上找到的：参照地址给忘了
上面代码在转pdf的时候遇到：中文不显示，中文不换行
1、中文不展示：代码中指定的字体与html中字体不符；代码中为：simsun.ttc，所以在html的body标签中需添加style="font-family:SimSun;"；其次html的标签一定要标准化，开头：
内部标签一定要闭合，特别是：meta、br、img等
2、中文不换行：参照：http://downpour.iteye.com/blog/509417?page=3#comments
将flying-saucer-core-9.0.3.jar中的org.xhtmlrenderer.layout.Breaker类，添加了2个方法，修改了109行和121行，如下：
/*
* Breaker.java
* Copyright (c) 2004, 2005 Torbj�rn Gannholm,
* Copyright (c) 2005 Wisconsin Court System
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public License
* as published by the Free Software Foundation; either version 2.1
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*
*/
package org.xhtmlrenderer.layout;
import org.xhtmlrenderer.css.constants.IdentValue;
import org.xhtmlrenderer.css.style.CalculatedStyle;
import org.xhtmlrenderer.render.FSFont;
/**
* A utility class that scans the text of a single inline box, looking for the
* next break point.
* @author Torbj�rn Gannholm
*/
public class Breaker {
public static void breakFirstLetter(LayoutContext c, LineBreakContext context,
int avail, CalculatedStyle style) {
FSFont font = style.getFSFont(c);
context.setEnd(getFirstLetterEnd(context.getMaster(), context.getStart()));
context.setWidth(c.getTextRenderer().getWidth(
c.getFontContext(), font, context.getCalculatedSubstring()));
if (context.getWidth() > avail) {
context.setNeedsNewLine(true);
context.setUnbreakable(true);
}
}
private static int getFirstLetterEnd(String text, int start) {
int i = start;
while (i < text.length()) {
char c = text.charAt(i);
int type = Character.getType(c);
if (type == Character.START_PUNCTUATION ||
type == Character.END_PUNCTUATION ||
type == Character.INITIAL_QUOTE_PUNCTUATION ||
type == Character.FINAL_QUOTE_PUNCTUATION ||
type == Character.OTHER_PUNCTUATION) {
i++;
} else {
break;
}
}
if (i < text.length()) {
i++;
}
return i;
}
public static void breakText(LayoutContext c,
LineBreakContext context, int avail, CalculatedStyle style) {
FSFont font = style.getFSFont(c);
IdentValue whitespace = style.getWhitespace();
// ====== handle nowrap
if (whitespace == IdentValue.NOWRAP) {
context.setEnd(context.getLast());
context.setWidth(c.getTextRenderer().getWidth(
c.getFontContext(), font, context.getCalculatedSubstring()));
return;
}
//check if we should break on the next newline
if (whitespace == IdentValue.PRE ||
whitespace == IdentValue.PRE_WRAP ||
whitespace == IdentValue.PRE_LINE) {
int n = context.getStartSubstring().indexOf(WhitespaceStripper.EOL);
if (n > -1) {
context.setEnd(context.getStart() + n + 1);
context.setWidth(c.getTextRenderer().getWidth(
c.getFontContext(), font, context.getCalculatedSubstring()));
context.setNeedsNewLine(true);
context.setEndsOnNL(true);
} else if (whitespace == IdentValue.PRE) {
context.setEnd(context.getLast());
context.setWidth(c.getTextRenderer().getWidth(
c.getFontContext(), font, context.getCalculatedSubstring()));
}
}
//check if we may wrap
if (whitespace == IdentValue.PRE ||
(context.isNeedsNewLine() && context.getWidth() <= avail)) {
return;
}
context.setEndsOnNL(false);
String currentString = context.getStartSubstring();
int left = 0;
// int right = currentString.indexOf(WhitespaceStripper.SPACE, left + 1);
int right = getStrRight(currentString,left);
int lastWrap = 0;
int graphicsLength = 0;
int lastGraphicsLength = 0;
while (right > 0 && graphicsLength <= avail) {
lastGraphicsLength = graphicsLength;
graphicsLength += c.getTextRenderer().getWidth(
c.getFontContext(), font, currentString.substring(left, right));
lastWrap = left;
left = right;
// right = currentString.indexOf(WhitespaceStripper.SPACE, left + 1);
right = getStrRight(currentString,left+1);
}
if (graphicsLength <= avail) {
//try for the last bit too!
lastWrap = left;
lastGraphicsLength = graphicsLength;
graphicsLength += c.getTextRenderer().getWidth(
c.getFontContext(), font, currentString.substring(left));
}
if (graphicsLength <= avail) {
context.setWidth(graphicsLength);
context.setEnd(context.getMaster().length());
//It fit!
return;
}
context.setNeedsNewLine(true);
if (lastWrap != 0) {//found a place to wrap
context.setEnd(context.getStart() + lastWrap);
context.setWidth(lastGraphicsLength);
} else {//unbreakable string
if (left == 0) {
left = currentString.length();
}
context.setEnd(context.getStart() + left);
context.setUnbreakable(true);
if (left == currentString.length()) {
context.setWidth(c.getTextRenderer().getWidth(
c.getFontContext(), font, context.getCalculatedSubstring()));
} else {
context.setWidth(graphicsLength);
}
}
return;
}
private static boolean isChinese(char c) {
Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
|| ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
|| ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
|| ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
return true;
}
return false;
}
private static int getStrRight(String s,int left){
if(left>=s.length())
return -1;
char[] ch = s.toCharArray();
for(int i = left;i至此，终于能正常转换了；