org.dromara.pdf.pdfbox.util

Class TextTokenUtil

java.lang.Object

org.dromara.pdf.pdfbox.util.TextTokenUtil

public class TextTokenUtil
extends Object

文本标记工具

Since:

1.8

Copyright (c) 2020 xsx All Rights Reserved. x-easypdf-pdfbox is licensed under Mulan PSL v2. You can use this software according to the terms and conditions of the Mulan PSL v2. You may obtain a copy of Mulan PSL v2 at: http://license.coscl.org.cn/MulanPSL2 THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE. See the Mulan PSL v2 for more details.

Author:

xsx

Constructor Summary

Constructors

Constructor and Description
TextTokenUtil()

Method Summary

Modifier and Type	Method and Description
static String	getTextForToken(Object token, PDFont font) 获取文本
static String	getTextForTokenInfo(TextTokenInfo info) 获取文本
static Map<org.apache.pdfbox.cos.COSName,PDFont>	initResourceFontMap(org.apache.pdfbox.pdmodel.PDResources resources) 初始化资源字体字典
static List<TextTokenInfo>	initTextTokenInfoListForCharacter(org.apache.commons.logging.Log log, org.apache.pdfbox.pdmodel.PDResources resources, List<Object> tokens, List<ReplaceInfo> replaceList, Map<Character,Integer> replaceIndexMap) 初始化文本标记信息列表
static List<TextTokenInfo>	initTextTokenInfoListForString(org.apache.pdfbox.pdmodel.PDResources resources, List<Object> tokens) 初始化文本标记信息列表
static void	initTextTokenInfoTextValue(org.apache.commons.logging.Log log, TextTokenInfo tokenInfo, Object token, int tokenIndex, List<ReplaceInfo> replaceList, Map<Character,Integer> replaceIndexMap) 初始化文本标记值
static void	joinString(StringBuilder builder, Object token, PDFont font) 拼接字符串
static void	processNotSameLengthReplaceText(PDDocument document, org.apache.pdfbox.pdmodel.PDResources resources, PDFont font, TextTokenInfo info, String replaceText) 处理不同长度替换文本
static void	processReplaceText(PDDocument document, org.apache.pdfbox.pdmodel.PDResources resources, PDFont font, Object token, String value) 处理替换文本
static void	processSameLengthReplaceText(PDDocument document, org.apache.pdfbox.pdmodel.PDResources resources, PDFont font, TextTokenInfo info, String replaceText) 处理相同长度替换文本
static boolean	replaceTextForToken(org.apache.commons.logging.Log log, PDDocument document, org.apache.pdfbox.pdmodel.PDResources resources, List<Object> tokens, List<ReplaceInfo> replaceList, Map<Character,Integer> replaceIndexMap) 替换文本标记
static boolean	replaceTextForToken(org.apache.commons.logging.Log log, PDDocument document, org.apache.pdfbox.pdmodel.PDResources resources, List<Object> tokens, PDFont font, Map<String,String> replaceMap) 替换文本
static boolean	tryReplaceTextForNormal(org.apache.commons.logging.Log log, PDDocument document, org.apache.pdfbox.pdmodel.PDResources resources, List<Object> tokens, PDFont font, Map<String,String> replaceMap) 尝试替换正常文本
static boolean	tryReplaceTextForSpecial(org.apache.commons.logging.Log log, PDDocument document, org.apache.pdfbox.pdmodel.PDResources resources, List<Object> tokens, PDFont font, Map<String,String> replaceMap) 尝试替换特殊文本

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

TextTokenUtil

public TextTokenUtil()

Method Detail

replaceTextForToken

public static boolean replaceTextForToken(org.apache.commons.logging.Log log,
                                          PDDocument document,
                                          org.apache.pdfbox.pdmodel.PDResources resources,
                                          List<Object> tokens,
                                          List<ReplaceInfo> replaceList,
                                          Map<Character,Integer> replaceIndexMap)

替换文本标记

Parameters:

log - 日志

document - 文档

resources - 页面资源

tokens - 标记列表

replaceList - 替换列表

replaceIndexMap - 替换索引字典

replaceTextForToken

public static boolean replaceTextForToken(org.apache.commons.logging.Log log,
                                          PDDocument document,
                                          org.apache.pdfbox.pdmodel.PDResources resources,
                                          List<Object> tokens,
                                          PDFont font,
                                          Map<String,String> replaceMap)

替换文本

Parameters:

log - 日志

document - 文档

resources - 页面资源

tokens - 标记列表

font - 替换字体

replaceMap - 替换字典

Returns:

返回布尔值，true为是，false为否

tryReplaceTextForNormal

public static boolean tryReplaceTextForNormal(org.apache.commons.logging.Log log,
                                              PDDocument document,
                                              org.apache.pdfbox.pdmodel.PDResources resources,
                                              List<Object> tokens,
                                              PDFont font,
                                              Map<String,String> replaceMap)

尝试替换正常文本

Parameters:

log - 日志

document - 文档

resources - 页面资源

tokens - 标记列表

font - 替换字体

replaceMap - 替换字典

Returns:

返回布尔值，true为是，false为否

tryReplaceTextForSpecial

public static boolean tryReplaceTextForSpecial(org.apache.commons.logging.Log log,
                                               PDDocument document,
                                               org.apache.pdfbox.pdmodel.PDResources resources,
                                               List<Object> tokens,
                                               PDFont font,
                                               Map<String,String> replaceMap)

尝试替换特殊文本

Parameters:

log - 日志

document - 文档

resources - 页面资源

tokens - 标记列表

font - 替换字体

replaceMap - 替换字典

Returns:

返回布尔值，true为是，false为否

processSameLengthReplaceText

public static void processSameLengthReplaceText(PDDocument document,
                                                org.apache.pdfbox.pdmodel.PDResources resources,
                                                PDFont font,
                                                TextTokenInfo info,
                                                String replaceText)

处理相同长度替换文本

Parameters:

document - 文档

resources - 页面资源

font - 替换字体

info - 文本标记信息

replaceText - 替换文本

processNotSameLengthReplaceText

public static void processNotSameLengthReplaceText(PDDocument document,
                                                   org.apache.pdfbox.pdmodel.PDResources resources,
                                                   PDFont font,
                                                   TextTokenInfo info,
                                                   String replaceText)

处理不同长度替换文本

Parameters:

document - 文档

resources - 页面资源

font - 替换字体

info - 文本标记信息

replaceText - 替换文本

processReplaceText

public static void processReplaceText(PDDocument document,
                                      org.apache.pdfbox.pdmodel.PDResources resources,
                                      PDFont font,
                                      Object token,
                                      String value)

处理替换文本

Parameters:

document - 文档

resources - 页面资源

font - 替换字体

token - 标记

value - 文本

initTextTokenInfoListForCharacter

public static List<TextTokenInfo> initTextTokenInfoListForCharacter(org.apache.commons.logging.Log log,
                                                                    org.apache.pdfbox.pdmodel.PDResources resources,
                                                                    List<Object> tokens,
                                                                    List<ReplaceInfo> replaceList,
                                                                    Map<Character,Integer> replaceIndexMap)

初始化文本标记信息列表

Parameters:

log - 日志

resources - 页面资源

tokens - 标记列表

replaceList - 替换列表

replaceIndexMap - 替换索引字典

Returns:

返回文本信息列表

initTextTokenInfoListForString

public static List<TextTokenInfo> initTextTokenInfoListForString(org.apache.pdfbox.pdmodel.PDResources resources,
                                                                 List<Object> tokens)

初始化文本标记信息列表

Parameters:

resources - 页面资源

tokens - 标记列表

Returns:

返回文本信息列表

initTextTokenInfoTextValue

public static void initTextTokenInfoTextValue(org.apache.commons.logging.Log log,
                                              TextTokenInfo tokenInfo,
                                              Object token,
                                              int tokenIndex,
                                              List<ReplaceInfo> replaceList,
                                              Map<Character,Integer> replaceIndexMap)

初始化文本标记值

Parameters:

log - 日志

tokenInfo - 标记信息

token - 标记

tokenIndex - 标记索引

replaceList - 替换列表

replaceIndexMap - 替换索引字典

getTextForToken

public static String getTextForToken(Object token,
                                     PDFont font)

获取文本

Parameters:

token - 标记

font - 字体

Returns:

返回文本内容

getTextForTokenInfo

public static String getTextForTokenInfo(TextTokenInfo info)

获取文本

Parameters:

info - 文本标记信息

Returns:

返回文本

initResourceFontMap

public static Map<org.apache.pdfbox.cos.COSName,PDFont> initResourceFontMap(org.apache.pdfbox.pdmodel.PDResources resources)

初始化资源字体字典

Parameters:

resources - 页面资源

Returns:

返回资源字体字典

joinString

public static void joinString(StringBuilder builder,
                              Object token,
                              PDFont font)

拼接字符串

Parameters:

builder - 构建器

token - 标记

font - 字体