Sal*_*rio 7 java pdf replace itext
我正在使用iText(5.5.13)库读取.PDF并替换文件中的模式。问题在于没有找到该模式，因为在库读取pdf时出现了一些奇怪的字符。
例如，在句子中：
"This is a test in order to see if the"
当我尝试阅读时变成：
[(This is a )9(te)-3(st)9( in o)-4(rd)15(er )-2(t)9(o)-5( s)8(ee)7( if t)-3(h)3(e )]
因此，如果我尝试查找和替换"test"，则不会"test"在pdf中找到任何单词，也不会替换它
这是我正在使用的代码：
public void processPDF(String src, String dest) {
try {
PdfReader reader = new PdfReader(src);
PdfArray refs = null;
PRIndirectReference reference = null;
int nPages = reader.getNumberOfPages();
for (int i = 1; i <= nPages; i++) {
PdfDictionary dict = reader.getPageN(i);
PdfObject object = dict.getDirectObject(PdfName.CONTENTS);
if (object.isArray()) {
refs = dict.getAsArray(PdfName.CONTENTS);
ArrayList<PdfObject> references = refs.getArrayList();
for (PdfObject r : references) {
reference = (PRIndirectReference) r;
PRStream stream = (PRStream) PdfReader.getPdfObject(reference);
byte[] data = PdfReader.getStreamBytes(stream);
String dd = new String(data, "UTF-8");
dd = dd.replaceAll("@pattern_1234", "trueValue");
dd = dd.replaceAll("test", "tested");
stream.setData(dd.getBytes());
}
}
if (object instanceof PRStream) {
PRStream stream = (PRStream) object;
byte[] data = PdfReader.getStreamBytes(stream);
String dd = new String(data, "UTF-8");
System.out.println("content---->" + dd);
dd = dd.replaceAll("@pattern_1234", "trueValue");
dd = dd.replaceAll("This", "FIRST");
stream.setData(dd.getBytes(StandardCharsets.UTF_8));
}
}
PdfStamper stamper = new PdfStamper(reader, new FileOutputStream(dest));
stamper.close();
reader.close();
}
catch (Exception e) {
}
}
正如评论和答案中已经提到的那样，PDF 不是一种用于文本编辑的格式。它是一种最终格式，有关文本流、布局甚至到 Unicode 的映射的信息是可选的。
因此，即使假设存在有关将字形映射到 Unicode 的可选信息，使用 iText 完成此任务的方法可能看起来有点令人不满意：首先将使用自定义文本提取策略确定相关文本的位置，然后继续删除使用该位置的所有内容的当前内容PdfCleanUpProcessor，最后将替换文本绘制到间隙中。
在这个答案中，我将展示一个帮助类，它允许结合前两个步骤，查找和删除现有文本，优点是确实只删除了文本，而不是任何背景图形等，如在PdfCleanUpProcessor编辑的情况下。助手还返回被移除文本的位置，允许在其上进行替换标记。
辅助类是基于PdfContentStreamEditor在给出这个答案早。不过，请在 github 上使用该类的版本，因为自概念以来，原始类已有所增强。
该SimpleTextRemover辅助类说明了什么是必要适当从PDF删除文本。其实限制在几个方面：
它只替换实际页面内容流中的文本。
为了替换嵌入的 XObject 中的文本，必须以递归方式遍历相应页面的 XObject 资源，并将编辑器应用于它们。
它的“简单”方式与SimpleTextExtractionStrategyis相同：它假定显示说明的文本以阅读顺序出现在内容中。
还可以处理顺序不同且指令必须排序的内容流，这意味着所有传入指令和相关渲染信息必须缓存到页面末尾，而不仅仅是一次几个指令。然后可以对渲染信息进行排序，可以在排序后的渲染信息中识别要移除的部分，可以操纵相关联的指令，并且最终可以存储这些指令。
它不会尝试识别在视觉上表示空白的字形之间的间隙，而实际上根本没有字形。
要识别间隙，必须扩展代码以检查两个连续的字形是否完全紧跟在另一个字形之后，或者是否存在间隙或行跳转。
在计算删除字形的间隙时，它还没有考虑字符和单词的间距。
为了改进这一点，必须改进字形宽度计算。
但是，考虑到您从内容流中摘录的示例，这些限制可能不会妨碍您。
public class SimpleTextRemover extends PdfContentStreamEditor {
public SimpleTextRemover() {
super (new SimpleTextRemoverListener());
((SimpleTextRemoverListener)getRenderListener()).simpleTextRemover = this;
}
/**
* <p>Removes the string to remove from the given page of the
* document in the PDF reader the given PDF stamper works on.</p>
* <p>The result is a list of glyph lists each of which represents
* a match can can be queried for position information.</p>
*/
public List<List<Glyph>> remove(PdfStamper pdfStamper, int pageNum, String toRemove) throws IOException {
if (toRemove.length() == 0)
return Collections.emptyList();
this.toRemove = toRemove;
cachedOperations.clear();
elementNumber = -1;
pendingMatch.clear();
matches.clear();
allMatches.clear();
editPage(pdfStamper, pageNum);
return allMatches;
}
/**
* Adds the given operation to the cached operations and checks
* whether some cached operations can meanwhile be processed and
* written to the result content stream.
*/
@Override
protected void write(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException {
cachedOperations.add(new ArrayList<>(operands));
while (process(processor)) {
cachedOperations.remove(0);
}
}
/**
* Removes any started match and sends all remaining cached
* operations for processing.
*/
@Override
public void finalizeContent() {
pendingMatch.clear();
try {
while (!cachedOperations.isEmpty()) {
if (!process(this)) {
// TODO: Should not happen, so warn
System.err.printf("Failure flushing operation %s; dropping.\n", cachedOperations.get(0));
}
cachedOperations.remove(0);
}
} catch (IOException e) {
throw new ExceptionConverter(e);
}
}
/**
* Tries to process the first cached operation. Returns whether
* it could be processed.
*/
boolean process(PdfContentStreamProcessor processor) throws IOException {
if (cachedOperations.isEmpty())
return false;
List<PdfObject> operands = cachedOperations.get(0);
PdfLiteral operator = (PdfLiteral) operands.get(operands.size() - 1);
String operatorString = operator.toString();
if (TEXT_SHOWING_OPERATORS.contains(operatorString))
return processTextShowingOp(processor, operator, operands);
super.write(processor, operator, operands);
return true;
}
/**
* Tries to processes a text showing operation. Unless a match
* is pending and starts before the end of the argument of this
* instruction, it can be processed. If the instructions contains
* a part of a match, it is transformed to a TJ operation and
* the glyphs in question are replaced by text position adjustments.
* If the original operation had a side effect (jump to next line
* or spacing adjustment), this side effect is explicitly added.
*/
boolean processTextShowingOp(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException {
PdfObject object = operands.get(operands.size() - 2);
boolean isArray = object instanceof PdfArray;
PdfArray array = isArray ? (PdfArray) object : new PdfArray(object);
int elementCount = countStrings(object);
// Currently pending glyph intersects parameter of this operation -> cannot yet process
if (!pendingMatch.isEmpty() && pendingMatch.get(0).elementNumber < processedElements + elementCount)
return false;
// The parameter of this operation is subject to a match -> copy as is
if (matches.size() == 0 || processedElements + elementCount <= matches.get(0).get(0).elementNumber || elementCount == 0) {
super.write(processor, operator, operands);
processedElements += elementCount;
return true;
}
// The parameter of this operation contains glyphs of a match -> manipulate
PdfArray newArray = new PdfArray();
for (int arrayIndex = 0; arrayIndex < array.size(); arrayIndex++) {
PdfObject entry = array.getPdfObject(arrayIndex);
if (!(entry instanceof PdfString)) {
newArray.add(entry);
} else {
PdfString entryString = (PdfString) entry;
byte[] entryBytes = entryString.getBytes();
for (int index = 0; index < entryBytes.length; ) {
List<Glyph> match = matches.size() == 0 ? null : matches.get(0);
Glyph glyph = match == null ? null : match.get(0);
if (glyph == null || processedElements < glyph.elementNumber) {
newArray.add(new PdfString(Arrays.copyOfRange(entryBytes, index, entryBytes.length)));
break;
}
if (index < glyph.index) {
newArray.add(new PdfString(Arrays.copyOfRange(entryBytes, index, glyph.index)));
index = glyph.index;
continue;
}
newArray.add(new PdfNumber(-glyph.width));
index++;
match.remove(0);
if (match.isEmpty())
matches.remove(0);
}
processedElements++;
}
}
writeSideEffect(processor, operator, operands);
writeTJ(processor, newArray);
return true;
}
/**
* Counts the strings in the given argument, itself a string or
* an array containing strings and non-strings.
*/
int countStrings(PdfObject textArgument) {
if (textArgument instanceof PdfArray) {
int result = 0;
for (PdfObject object : (PdfArray)textArgument) {
if (object instanceof PdfString)
result++;
}
return result;
} else
return textArgument instanceof PdfString ? 1 : 0;
}
/**
* Writes side effects of a text showing operation which is going to be
* replaced by a TJ operation. Side effects are line jumps and changes
* of character or word spacing.
*/
void writeSideEffect(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException {
switch (operator.toString()) {
case "\"":
super.write(processor, OPERATOR_Tw, Arrays.asList(operands.get(0), OPERATOR_Tw));
super.write(processor, OPERATOR_Tc, Arrays.asList(operands.get(1), OPERATOR_Tc));
case "'":
super.write(processor, OPERATOR_Tasterisk, Collections.singletonList(OPERATOR_Tasterisk));
}
}
/**
* Writes a TJ operation with the given array unless array is empty.
*/
void writeTJ(PdfContentStreamProcessor processor, PdfArray array) throws IOException {
if (!array.isEmpty()) {
List<PdfObject> operands = Arrays.asList(array, OPERATOR_TJ);
super.write(processor, OPERATOR_TJ, operands);
}
}
/**
* Analyzes the given text render info whether it starts a new match or
* finishes / continues / breaks a pending match. This method is called
* by the {@link SimpleTextRemoverListener} registered as render listener
* of the underlying content stream processor.
*/
void renderText(TextRenderInfo renderInfo) {
elementNumber++;
int index = 0;
for (TextRenderInfo info : renderInfo.getCharacterRenderInfos()) {
int matchPosition = pendingMatch.size();
pendingMatch.add(new Glyph(info, elementNumber, index));
if (!toRemove.substring(matchPosition, matchPosition + info.getText().length()).equals(info.getText())) {
reduceToPartialMatch();
}
if (pendingMatch.size() == toRemove.length()) {
matches.add(new ArrayList<>(pendingMatch));
allMatches.add(new ArrayList<>(pendingMatch));
pendingMatch.clear();
}
index++;
}
}
/**
* Reduces the current pending match to an actual (partial) match
* after the addition of the next glyph has invalidated it as a
* whole match.
*/
void reduceToPartialMatch() {
outer:
while (!pendingMatch.isEmpty()) {
pendingMatch.remove(0);
int index = 0;
for (Glyph glyph : pendingMatch) {
if (!toRemove.substring(index, index + glyph.text.length()).equals(glyph.text)) {
continue outer;
}
index++;
}
break;
}
}
String toRemove = null;
final List<List<PdfObject>> cachedOperations = new LinkedList<>();
int elementNumber = -1;
int processedElements = 0;
final List<Glyph> pendingMatch = new ArrayList<>();
final List<List<Glyph>> matches = new ArrayList<>();
final List<List<Glyph>> allMatches = new ArrayList<>();
/**
* Render listener class used by {@link SimpleTextRemover} as listener
* of its content stream processor ancestor. Essentially it forwards
* {@link TextRenderInfo} events and ignores all else.
*/
static class SimpleTextRemoverListener implements RenderListener {
@Override
public void beginTextBlock() { }
@Override
public void renderText(TextRenderInfo renderInfo) {
simpleTextRemover.renderText(renderInfo);
}
@Override
public void endTextBlock() { }
@Override
public void renderImage(ImageRenderInfo renderInfo) { }
SimpleTextRemover simpleTextRemover = null;
}
/**
* Value class representing a glyph with information on
* the displayed text and its position, the overall number
* of the string argument of a text showing instruction
* it is in and the index at which it can be found therein,
* and the width to use as text position adjustment when
* replacing it. Beware, the width does not yet consider
* character and word spacing!
*/
public static class Glyph {
public Glyph(TextRenderInfo info, int elementNumber, int index) {
text = info.getText();
ascent = info.getAscentLine();
base = info.getBaseline();
descent = info.getDescentLine();
this.elementNumber = elementNumber;
this.index = index;
this.width = info.getFont().getWidth(text);
}
public final String text;
public final LineSegment ascent;
public final LineSegment base;
public final LineSegment descent;
final int elementNumber;
final int index;
final float width;
}
final PdfLiteral OPERATOR_Tasterisk = new PdfLiteral("T*");
final PdfLiteral OPERATOR_Tc = new PdfLiteral("Tc");
final PdfLiteral OPERATOR_Tw = new PdfLiteral("Tw");
final PdfLiteral OPERATOR_Tj = new PdfLiteral("Tj");
final PdfLiteral OPERATOR_TJ = new PdfLiteral("TJ");
final static List<String> TEXT_SHOWING_OPERATORS = Arrays.asList("Tj", "'", "\"", "TJ");
final static Glyph[] EMPTY_GLYPH_ARRAY = new Glyph[0];
}
（SimpleTextRemover帮助类）
你可以这样使用它：
PdfReader pdfReader = new PdfReader(SOURCE);
PdfStamper pdfStamper = new PdfStamper(pdfReader, RESULT_STREAM);
SimpleTextRemover remover = new SimpleTextRemover();
System.out.printf("\ntest.pdf - Test\n");
for (int i = 1; i <= pdfReader.getNumberOfPages(); i++)
{
System.out.printf("Page %d:\n", i);
List<List<Glyph>> matches = remover.remove(pdfStamper, i, "Test");
for (List<Glyph> match : matches) {
Glyph first = match.get(0);
Vector baseStart = first.base.getStartPoint();
Glyph last = match.get(match.size()-1);
Vector baseEnd = last.base.getEndPoint();
System.out.printf(" Match from (%3.1f %3.1f) to (%3.1f %3.1f)\n", baseStart.get(I1), baseStart.get(I2), baseEnd.get(I1), baseEnd.get(I2));
}
}
pdfStamper.close();
（RemovePageTextContent测试testRemoveTestFromTest）
我的测试文件的控制台输出如下：
public class SimpleTextRemover extends PdfContentStreamEditor {
public SimpleTextRemover() {
super (new SimpleTextRemoverListener());
((SimpleTextRemoverListener)getRenderListener()).simpleTextRemover = this;
}
/**
* <p>Removes the string to remove from the given page of the
* document in the PDF reader the given PDF stamper works on.</p>
* <p>The result is a list of glyph lists each of which represents
* a match can can be queried for position information.</p>
*/
public List<List<Glyph>> remove(PdfStamper pdfStamper, int pageNum, String toRemove) throws IOException {
if (toRemove.length() == 0)
return Collections.emptyList();
this.toRemove = toRemove;
cachedOperations.clear();
elementNumber = -1;
pendingMatch.clear();
matches.clear();
allMatches.clear();
editPage(pdfStamper, pageNum);
return allMatches;
}
/**
* Adds the given operation to the cached operations and checks
* whether some cached operations can meanwhile be processed and
* written to the result content stream.
*/
@Override
protected void write(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException {
cachedOperations.add(new ArrayList<>(operands));
while (process(processor)) {
cachedOperations.remove(0);
}
}
/**
* Removes any started match and sends all remaining cached
* operations for processing.
*/
@Override
public void finalizeContent() {
pendingMatch.clear();
try {
while (!cachedOperations.isEmpty()) {
if (!process(this)) {
// TODO: Should not happen, so warn
System.err.printf("Failure flushing operation %s; dropping.\n", cachedOperations.get(0));
}
cachedOperations.remove(0);
}
} catch (IOException e) {
throw new ExceptionConverter(e);
}
}
/**
* Tries to process the first cached operation. Returns whether
* it could be processed.
*/
boolean process(PdfContentStreamProcessor processor) throws IOException {
if (cachedOperations.isEmpty())
return false;
List<PdfObject> operands = cachedOperations.get(0);
PdfLiteral operator = (PdfLiteral) operands.get(operands.size() - 1);
String operatorString = operator.toString();
if (TEXT_SHOWING_OPERATORS.contains(operatorString))
return processTextShowingOp(processor, operator, operands);
super.write(processor, operator, operands);
return true;
}
/**
* Tries to processes a text showing operation. Unless a match
* is pending and starts before the end of the argument of this
* instruction, it can be processed. If the instructions contains
* a part of a match, it is transformed to a TJ operation and
* the glyphs in question are replaced by text position adjustments.
* If the original operation had a side effect (jump to next line
* or spacing adjustment), this side effect is explicitly added.
*/
boolean processTextShowingOp(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException {
PdfObject object = operands.get(operands.size() - 2);
boolean isArray = object instanceof PdfArray;
PdfArray array = isArray ? (PdfArray) object : new PdfArray(object);
int elementCount = countStrings(object);
// Currently pending glyph intersects parameter of this operation -> cannot yet process
if (!pendingMatch.isEmpty() && pendingMatch.get(0).elementNumber < processedElements + elementCount)
return false;
// The parameter of this operation is subject to a match -> copy as is
if (matches.size() == 0 || processedElements + elementCount <= matches.get(0).get(0).elementNumber || elementCount == 0) {
super.write(processor, operator, operands);
processedElements += elementCount;
return true;
}
// The parameter of this operation contains glyphs of a match -> manipulate
PdfArray newArray = new PdfArray();
for (int arrayIndex = 0; arrayIndex < array.size(); arrayIndex++) {
PdfObject entry = array.getPdfObject(arrayIndex);
if (!(entry instanceof PdfString)) {
newArray.add(entry);
} else {
PdfString entryString = (PdfString) entry;
byte[] entryBytes = entryString.getBytes();
for (int index = 0; index < entryBytes.length; ) {
List<Glyph> match = matches.size() == 0 ? null : matches.get(0);
Glyph glyph = match == null ? null : match.get(0);
if (glyph == null || processedElements < glyph.elementNumber) {
newArray.add(new PdfString(Arrays.copyOfRange(entryBytes, index, entryBytes.length)));
break;
}
if (index < glyph.index) {
newArray.add(new PdfString(Arrays.copyOfRange(entryBytes, index, glyph.index)));
index = glyph.index;
continue;
}
newArray.add(new PdfNumber(-glyph.width));
index++;
match.remove(0);
if (match.isEmpty())
matches.remove(0);
}
processedElements++;
}
}
writeSideEffect(processor, operator, operands);
writeTJ(processor, newArray);
return true;
}
/**
* Counts the strings in the given argument, itself a string or
* an array containing strings and non-strings.
*/
int countStrings(PdfObject textArgument) {
if (textArgument instanceof PdfArray) {
int result = 0;
for (PdfObject object : (PdfArray)textArgument) {
if (object instanceof PdfString)
result++;
}
return result;
} else
return textArgument instanceof PdfString ? 1 : 0;
}
/**
* Writes side effects of a text showing operation which is going to be
* replaced by a TJ operation. Side effects are line jumps and changes
* of character or word spacing.
*/
void writeSideEffect(PdfContentStreamProcessor processor, PdfLiteral operator, List<PdfObject> operands) throws IOException {
switch (operator.toString()) {
case "\"":
super.write(processor, OPERATOR_Tw, Arrays.asList(operands.get(0), OPERATOR_Tw));
super.write(processor, OPERATOR_Tc, Arrays.asList(operands.get(1), OPERATOR_Tc));
case "'":
super.write(processor, OPERATOR_Tasterisk, Collections.singletonList(OPERATOR_Tasterisk));
}
}
/**
* Writes a TJ operation with the given array unless array is empty.
*/
void writeTJ(PdfContentStreamProcessor processor, PdfArray array) throws IOException {
if (!array.isEmpty()) {
List<PdfObject> operands = Arrays.asList(array, OPERATOR_TJ);
super.write(processor, OPERATOR_TJ, operands);
}
}
/**
* Analyzes the given text render info whether it starts a new match or
* finishes / continues / breaks a pending match. This method is called
* by the {@link SimpleTextRemoverListener} registered as render listener
* of the underlying content stream processor.
*/
void renderText(TextRenderInfo renderInfo) {
elementNumber++;
int index = 0;
for (TextRenderInfo info : renderInfo.getCharacterRenderInfos()) {
int matchPosition = pendingMatch.size();
pendingMatch.add(new Glyph(info, elementNumber, index));
if (!toRemove.substring(matchPosition, matchPosition + info.getText().length()).equals(info.getText())) {
reduceToPartialMatch();
}
if (pendingMatch.size() == toRemove.length()) {
matches.add(new ArrayList<>(pendingMatch));
allMatches.add(new ArrayList<>(pendingMatch));
pendingMatch.clear();
}
index++;
}
}
/**
* Reduces the current pending match to an actual (partial) match
* after the addition of the next glyph has invalidated it as a
* whole match.
*/
void reduceToPartialMatch() {
outer:
while (!pendingMatch.isEmpty()) {
pendingMatch.remove(0);
int index = 0;
for (Glyph glyph : pendingMatch) {
if (!toRemove.substring(index, index + glyph.text.length()).equals(glyph.text)) {
continue outer;
}
index++;
}
break;
}
}
String toRemove = null;
final List<List<PdfObject>> cachedOperations = new LinkedList<>();
int elementNumber = -1;
int processedElements = 0;
final List<Glyph> pendingMatch = new ArrayList<>();
final List<List<Glyph>> matches = new ArrayList<>();
final List<List<Glyph>> allMatches = new ArrayList<>();
/**
* Render listener class used by {@link SimpleTextRemover} as listener
* of its content stream processor ancestor. Essentially it forwards
* {@link TextRenderInfo} events and ignores all else.
*/
static class SimpleTextRemoverListener implements RenderListener {
@Override
public void beginTextBlock() { }
@Override
public void renderText(TextRenderInfo renderInfo) {
simpleTextRemover.renderText(renderInfo);
}
@Override
public void endTextBlock() { }
@Override
public void renderImage(ImageRenderInfo renderInfo) { }
SimpleTextRemover simpleTextRemover = null;
}
/**
* Value class representing a glyph with information on
* the displayed text and its position, the overall number
* of the string argument of a text showing instruction
* it is in and the index at which it can be found therein,
* and the width to use as text position adjustment when
* replacing it. Beware, the width does not yet consider
* character and word spacing!
*/
public static class Glyph {
public Glyph(TextRenderInfo info, int elementNumber, int index) {
text = info.getText();
ascent = info.getAscentLine();
base = info.getBaseline();
descent = info.getDescentLine();
this.elementNumber = elementNumber;
this.index = index;
this.width = info.getFont().getWidth(text);
}
public final String text;
public final LineSegment ascent;
public final LineSegment base;
public final LineSegment descent;
final int elementNumber;
final int index;
final float width;
}
final PdfLiteral OPERATOR_Tasterisk = new PdfLiteral("T*");
final PdfLiteral OPERATOR_Tc = new PdfLiteral("Tc");
final PdfLiteral OPERATOR_Tw = new PdfLiteral("Tw");
final PdfLiteral OPERATOR_Tj = new PdfLiteral("Tj");
final PdfLiteral OPERATOR_TJ = new PdfLiteral("TJ");
final static List<String> TEXT_SHOWING_OPERATORS = Arrays.asList("Tj", "'", "\"", "TJ");
final static Glyph[] EMPTY_GLYPH_ARRAY = new Glyph[0];
}
以及在输出 PDF 中的这些位置缺少“测试”的出现。
您可以使用它们在相关位置绘制替换文本，而不是输出匹配坐标。
| 归档时间： |
|
| 查看次数： |
381 次 |
| 最近记录： |