Java使用IText生产PDF时，中文标点符号出现在行首的问题处理

Java使用IText生成PDF时，中文标点符号出现在行首的问题处理

使用itext 5进行html转成pdf时，标点符号出现在某一行的开头但这种情况下显然不符合中文书写的规则，主要问题出在itext中的DefaultSplitCharacter类，该方法主要用来判断字符是否为可拆分字符。

itext 版本：5.5.13

解决办法：
1、可以通过修改源码的方式，可以参考
如何修改jar包源码以及解决iText生成pdf时中文标点存在行首问题

2、如果不想修改源码，也可以在自己项目中创建与itext中DefaultSplitCharacter相同的包路径，并在该包下重新DefaultSplitCharacter类,能这样处理的原因，与类的加载顺序有关。
在这里插入图片描述

package com.itextpdf.text.pdf;import com.itextpdf.text.SplitCharacter;public class DefaultSplitCharacter implements SplitCharacter {/*** An instance of the default SplitCharacter.*/public static final SplitCharacter DEFAULT = new DefaultSplitCharacter();// line of text cannot start or end with this characterstatic final char u2060 = '\u2060'; // - ZERO WIDTH NO BREAK SPACE// a line of text cannot start with any following characters in// NOT_BEGIN_CHARACTERS[]static final char u30fb = '\u30fb'; // ・ - KATAKANA MIDDLE DOTstatic final char u2022 = '\u2022'; // • - BLACK SMALL CIRCLE (BULLET)static final char uff65 = '\uff65'; // ･ - HALFWIDTH KATAKANA MIDDLE DOTstatic final char u300d = '\u300d'; // 」 - RIGHT CORNER BRACKETstatic final char uff09 = '\uff09'; // ） - FULLWIDTH RIGHT PARENTHESISstatic final char u0021 = '\u0021'; // ! - EXCLAMATION MARKstatic final char u0025 = '\u0025'; // % - PERCENT SIGNstatic final char u0029 = '\u0029'; // ) - RIGHT PARENTHESISstatic final char u002c = '\u002c'; // , - COMMAstatic final char u002e = '\u002e'; // . - FULL STOPstatic final char u003f = '\u003f'; // ? - QUESTION MARKstatic final char u005d = '\u005d'; // ] - RIGHT SQUARE BRACKETstatic final char u007d = '\u007d'; // } - RIGHT CURLYstatic final char uff61 = '\uff61'; // ｡ - HALFWIDTH IDEOGRAPHIC FULL STOPstatic final char uff70 = '\uff70'; // ｰ - HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARKstatic final char uff9e = '\uff9e'; // ﾞ - HALFWIDTH KATAKANA VOICED SOUND MARKstatic final char uff9f = '\uff9f'; // ﾟ - HALFWIDTH KATAKANA SEMI-VOICED SOUND MARKstatic final char u3001 = '\u3001'; // 、 - IDEOGRAPHIC COMMAstatic final char u3002 = '\u3002'; // 。 - IDEOGRAPHIC FULL STOPstatic final char uff0c = '\uff0c'; // ， - FULLWIDTH COMMAstatic final char uff0e = '\uff0e'; // ． - FULLWIDTH FULL STOPstatic final char uff1a = '\uff1a'; // ： - FULLWIDTH COLONstatic final char uff1b = '\uff1b'; // ； - FULLWIDTH SEMICOLONstatic final char uff1f = '\uff1f'; // ？ - FULLWIDTH QUESTION MARKstatic final char uff01 = '\uff01'; // ！ - FULLWIDTH EXCLAMATION MARKstatic final char u309b = '\u309b'; // ゛ - KATAKANA-HIRAGANA VOICED SOUND MARKstatic final char u309c = '\u309c'; // ゜ - KATAKANA-HIRAGANA SEMI-VOICED SOUND MARKstatic final char u30fd = '\u30fd'; // ヽ - KATAKANA ITERATION MARKstatic final char u2019 = '\u2019'; // ’ - RIGHT SINGLE QUOTATION MARKstatic final char u201d = '\u201d'; // ” - RIGHT DOUBLE QUOTATION MARKstatic final char u3015 = '\u3015'; // 〕 - RIGHT TORTOISE SHELL BRACKETstatic final char uff3d = '\uff3d'; // ］ - FULLWIDTH RIGHT SQUARE BRACKETstatic final char uff5d = '\uff5d'; // ｝ - FULLWIDTH RIGHT CURLY BRACKETstatic final char u3009 = '\u3009'; // 〉 - RIGHT ANGLE BRACKETstatic final char u300b = '\u300b'; // 》 - RIGHT DOUBLE ANGLE BRACKETstatic final char u300f = '\u300f'; // 』 - RIGHT WHITE CORNER BRACKETstatic final char u3011 = '\u3011'; // 】 - RIGHT BLACK LENTICULAR BRACKETstatic final char u00b0 = '\u00b0'; // ° - DEGREE SIGNstatic final char u2032 = '\u2032'; // ′ - PRIMEstatic final char u2033 = '\u2033'; // ″ - DOUBLE PRIMEstatic final char[] NOT_BEGIN_CHARACTERS = new char[] { u30fb, u2022, uff65, u300d, uff09, u0021, u0025, u0029,u002c, u002e, u003f, u005d, u007d, uff61, uff70, uff9e, uff9f, u3001, u3002, uff0c, uff0e, uff1a, uff1b,uff1f, uff01, u309b, u309c, u30fd, u2019, u201d, u3015, uff3d, uff5d, u3009, u300b, u300f, u3011, u00b0,u2032, u2033, u2060 };// a line of text cannot end with any following characters in// NOT_ENDING_CHARACTERS[]static final char u0024 = '\u0024'; // $ - DOLLAR SIGNstatic final char u0028 = '\u0028'; // ( - LEFT PARENTHESISstatic final char u005b = '\u005b'; // [ - LEFT SQUARE BRACKETstatic final char u007b = '\u007b'; // { - LEFT CURLY BRACKETstatic final char u00a3 = '\u00a3'; // £ - POUND SIGNstatic final char u00a5 = '\u00a5'; // ¥ - YEN SIGNstatic final char u201c = '\u201c'; // “ - LEFT DOUBLE QUOTATION MARKstatic final char u2018 = '\u2018'; // ‘ - LEFT SINGLE QUOTATION MARKstatic final char u300a = '\u300a'; // 《 - LEFT DOUBLE ANGLE BRACKETstatic final char u3008 = '\u3008'; // 〈 - LEFT ANGLE BRACKETstatic final char u300c = '\u300c'; // 「 - LEFT CORNER BRACKETstatic final char u300e = '\u300e'; // 『 - LEFT WHITE CORNER BRACKETstatic final char u3010 = '\u3010'; // 【 - LEFT BLACK LENTICULAR BRACKETstatic final char u3014 = '\u3014'; // 〔 - LEFT TORTOISE SHELL BRACKETstatic final char uff62 = '\uff62'; // ｢ - HALFWIDTH LEFT CORNER BRACKETstatic final char uff08 = '\uff08'; // （ - FULLWIDTH LEFT PARENTHESISstatic final char uff3b = '\uff3b'; // ［ - FULLWIDTH LEFT SQUARE BRACKETstatic final char uff5b = '\uff5b'; // ｛ - FULLWIDTH LEFT CURLY BRACKETstatic final char uffe5 = '\uffe5'; // ￥ - FULLWIDTH YEN SIGNstatic final char uff04 = '\uff04'; // ＄ - FULLWIDTH DOLLAR SIGNstatic final char[] NOT_ENDING_CHARACTERS = new char[] { u0024, u0028, u005b, u007b, u00a3, u00a5, u201c, u2018,u3008, u300a, u300c, u300e, u3010, u3014, uff62, uff08, uff3b, uff5b, uffe5, uff04, u2060 };@Overridepublic boolean isSplitCharacter(int start, int current, int end, char[] cc, PdfChunk[] ck) {// Note: If you don't add an try/catch and there is an issue with// isSplitCharacter(), iText silently fails and// you have no idea there was a problem.try {char c = getCharacter(current, cc, ck);int next = current + 1;if (next < cc.length) {char charNext = getCharacter(next, cc, ck);for (char not_begin_character : NOT_BEGIN_CHARACTERS) {if (charNext == not_begin_character) {return false;}}}for (char not_ending_character : NOT_ENDING_CHARACTERS) {if (c == not_ending_character) {return false;}}if (c <= ' ' || c == '-' || c == '\u2010') {return true;}if (c < 0x2002)return false;return ((c >= 0x2002 && c <= 0x200b)|| (c >= 0x2e80 && c < 0xd7a0)|| (c >= 0xf900 && c < 0xfb00)|| (c >= 0xfe30 && c < 0xfe50)|| (c >= 0xff61 && c < 0xffa0));} catch (Exception ex) {ex.printStackTrace();}return true;}/*** Returns a character int the array (Note: modified from the iText default* version with the addition null check of '|| ck[Math.min(position, ck.length -* 1)] == null'.** @param position position in the array* @param ck       chunk array* @param cc       the character array that has to be checked* @return the character*/protected char getCharacter(int position, char[] cc, PdfChunk[] ck) {if (ck == null || ck[Math.min(position, ck.length - 1)] == null) {return cc[position];}return (char) ck[Math.min(position, ck.length - 1)].getUnicodeEquivalent(cc[position]);}
}