gpt4 book ai didi

c# - 如何在合并时删除空格

转载 作者:太空狗 更新时间:2023-10-30 00:51:16 26 4
gpt4 key购买 nike

我有一些代码采用 3 个不同的 PDF 字节数组并将它们合并。这段代码效果很好。 (某些人)遇到的问题是每个 PDF 都被认为是整页(如果打印的话),即使上面只有 4 英寸的内容,因此垂直留下 7 英寸的空白。然后中间文档被放入,它的末尾可能有也可能没有垂直空白。然后页脚也会放在自己的页面上。

代码如下:

byte[] Bytes = rv.LocalReport.Render("PDF", null, out MimeType, out Encoding, out Extension, out StreamIDs, out Warnings);
List<byte[]> MergeSets = // This is filled prior to this code

// Append any other pages to this primary letter
if (MergeSets.Count > 0) {
MemoryStream ms = new MemoryStream();
Document document = new Document();
PdfCopy copy = new PdfCopy(document, ms);
document.Open();
PdfImportedPage page;
PdfReader reader = new PdfReader(Bytes); // read the generated primary Letter
int pages = reader.NumberOfPages;

for (int i = 0; i < pages; ) {
page = copy.GetImportedPage(reader, ++i);
copy.AddPage(page);
} // foreach of the pages in the Cover Letter

// Now append the merge sets
foreach (byte[] ba in MergeSets) {
reader = new PdfReader(ba);
pages = reader.NumberOfPages;

for (int i = 0; i < pages; ) {
page = copy.GetImportedPage(reader, ++i);
copy.AddPage(page);
} // foreach of the pages in the current merge set
} // foreach of the sets of data

document.Close();

ServerSaved = SaveGeneratedLetter(ms.GetBuffer(), DateTime.Now.Year, hl.LetterName, SaveName);
} // if there is anything to merge

当我合并每个页面时,有没有一种方法可以剪切/删除/删除每个 pdf 末尾的垂直空白区域,使其显示为一个无缝文档?

UPDATE:Here are some sample .pdf files I am trying to merge.

header , body , footer

UPDATE 2: USING THE ANSWER:

I have converted @mkl's code to C# and here it is.

The tool class:

public class PdfVeryDenseMergeTool {

private Rectangle PageSize;
private float TopMargin;
private float BottomMargin;
private float Gap;
private Document Document = null;
private PdfWriter Writer = null;
private float YPosition = 0;

public PdfVeryDenseMergeTool(Rectangle size, float top, float bottom, float gap) {
this.PageSize = size;
this.TopMargin = top;
this.BottomMargin = bottom;
this.Gap = gap;
} // PdfVeryDenseMergeTool

public void Merge(MemoryStream outputStream, List<PdfReader> inputs) {
try {
this.OpenDocument(outputStream);

foreach (PdfReader reader in inputs) {
this.Merge(reader);
} // foreach of the PDF files to merge
} finally {
this.CloseDocument();
} // try-catch-finally
} // Merge

public void OpenDocument(MemoryStream outputStream) {
this.Document = new Document(PageSize, 36, 36, this.TopMargin, this.BottomMargin);
this.Writer = PdfWriter.GetInstance(Document, outputStream);

this.Document.Open();
this.NewPage();
} // OpenDocument

public void CloseDocument() {
try {
this.Document.Close();
} finally {
this.Document = null;
this.Writer = null;
this.YPosition = 0;
} // try-finally
} // CloseDocument

public void NewPage() {
this.Document.NewPage();
this.YPosition = PageSize.GetTop(this.TopMargin);
} // Merge

public void Merge(PdfReader reader) {
PdfReaderContentParser parser = new PdfReaderContentParser(reader);

for (int pageIndex = 1; pageIndex <= reader.NumberOfPages; pageIndex++) {
this.Merge(reader, parser, pageIndex);
} // foreach of the pages of the current PDF
} // Merge

public void Merge(PdfReader reader, PdfReaderContentParser parser, int pageIndex) {
PdfImportedPage importedPage = Writer.GetImportedPage(reader, pageIndex);
PdfContentByte directContent = Writer.DirectContent;

PageVerticalAnalyzer finder = parser.ProcessContent(pageIndex, new PageVerticalAnalyzer());

if (finder.VerticalFlips.Count < 2)
return;

Rectangle pageSizeToImport = reader.GetPageSize(pageIndex);

int startFlip = finder.VerticalFlips.Count - 1;
bool first = true;

while (startFlip > 0) {
if (!first)
this.NewPage();

float freeSpace = this.YPosition - PageSize.GetBottom(BottomMargin);
int endFlip = startFlip + 1;

while ((endFlip > 1) && (finder.VerticalFlips[startFlip] - finder.VerticalFlips[endFlip - 2] < freeSpace))
endFlip -= 2;

if (endFlip < startFlip) {
float height = finder.VerticalFlips[startFlip] - finder.VerticalFlips[endFlip];

directContent.SaveState();
directContent.Rectangle(0, this.YPosition - height, pageSizeToImport.Width, height);
directContent.Clip();
directContent.NewPath();

this.Writer.DirectContent.AddTemplate(importedPage, 0, this.YPosition - (finder.VerticalFlips[startFlip] - pageSizeToImport.Bottom));

directContent.RestoreState();
this.YPosition -= height + this.Gap;
startFlip = endFlip - 1;
} else if (!first) {
throw new ArgumentException(string.Format("Page {0} content too large", pageIndex));
} // if

first = false;
} // while
} // Merge
} // PdfVeryDenseMergeTool

The RenderListener class:
UPDATE 3: FIXED 1 LINE OF CODE AND IT WORKS: See comment in code

public class PageVerticalAnalyzer : IRenderListener {

public PageVerticalAnalyzer() { }

public List<float> VerticalFlips = new List<float>();

public void AddVerticalUseSection(float from, float to) {
if (to < from) {
float temp = to;
to = from;
from = temp;
}

int i = 0;
int j = 0;

for (i = 0; i < VerticalFlips.Count; i++) {
float flip = VerticalFlips[i];
if (flip < from)
continue;

for (j = i; j < VerticalFlips.Count; j++) {
flip = VerticalFlips[j];
if (flip < to)
continue;
break;
}
break;
} // foreach of the vertical flips

bool fromOutsideInterval = i % 2 == 0;
bool toOutsideInterval = j % 2 == 0;

while (j-- > i)
VerticalFlips.RemoveAt(j); // This was the problem line with just .Remove(j)
if (toOutsideInterval)
VerticalFlips.Insert(i, to);
if (fromOutsideInterval)
VerticalFlips.Insert(i, from);
} // AddVerticalUseSection

public void BeginTextBlock() { /* Do nothing */ }

public void EndTextBlock() { /* Do nothing */ }

public void RenderImage(ImageRenderInfo renderInfo) {
Matrix ctm = renderInfo.GetImageCTM();
List<float> YCoords = new List<float>(4) { 0, 0, 0, 0 };

for (int x = 0; x < 2; x++) {
for (int y = 0; y < 2; y++) {
Vector corner = new Vector(x, y, 1).Cross(ctm);
YCoords[2 * x + y] = corner[Vector.I2];
}
}

YCoords.Sort();
AddVerticalUseSection(YCoords[0], YCoords[3]);
} // RenderImage

public void RenderText(TextRenderInfo renderInfo) {
LineSegment ascentLine = renderInfo.GetAscentLine();
LineSegment descentLine = renderInfo.GetDescentLine();
List<float> YCoords = new List<float>(4) {
ascentLine.GetStartPoint()[Vector.I2],
ascentLine.GetEndPoint()[Vector.I2],
descentLine.GetStartPoint()[Vector.I2],
descentLine.GetEndPoint()[Vector.I2],
};

YCoords.Sort();
AddVerticalUseSection(YCoords[0], YCoords[3]);
} // RenderText
} // PageVericalAnalyzer

Code to gather files and run the tool:

public void TestMergeDocuments() {
PdfVeryDenseMergeTool tool = new PdfVeryDenseMergeTool(iTextSharp.text.PageSize.A4, 18, 18, 10);
List<byte[]> Files = new List<byte[]>();

// Code to load each of the 3 files I need into this byte array list

using (MemoryStream ms = new MemoryStream()) {
List<PdfReader> files = new List<PdfReader>();

foreach (byte[] ba in Files) {
files.Add(new PdfReader(ba));
} // foreach of the sets of data

tool.Merge(ms, files);

// Save the file using: ms.GetBuffer()
} // using the memory stream
} // TestMergeDocuments

最佳答案

以下示例工具是根据来自 this answer 的工具 PdfDenseMergeTool 的想法实现的OP 评论说 非常接近[he] 需要。就像 PdfDenseMergeTool 一样,此工具是在 Java/iText 中实现的,与 C#/iTextSharp 相比,我更熟悉它。作为 OP has already translated PdfDenseMergeTool 到 C#/iTextSharp,在这里翻译这个工具应该也不是什么大问题。

PdfVeryDenseMergeTool

此工具类似于 PdfDenseMergeTool从多个 PdfReader 实例中获取页面的页面内容,并尝试密集合并它们,即将多个源页面的内容放到一个目标页面上(如果有足够的可用空间)。与早期的工具相比,该工具甚至可以拆分源页面内容以实现更密集的合并。

就像其他工具一样,PdfVeryDenseMergeTool 不考虑矢量图形,因为 iText(Sharp) 解析 API 只转发文本和位图图像

PdfVeryDenseMergeTool 在水平线上拆分不完全适合目标页面的源页面,该水平线不与文本字形或位图图形的边界框相交。

工具类:

public class PdfVeryDenseMergeTool
{
public PdfVeryDenseMergeTool(Rectangle size, float top, float bottom, float gap)
{
this.pageSize = size;
this.topMargin = top;
this.bottomMargin = bottom;
this.gap = gap;
}

public void merge(OutputStream outputStream, Iterable<PdfReader> inputs) throws DocumentException, IOException
{
try
{
openDocument(outputStream);
for (PdfReader reader: inputs)
{
merge(reader);
}
}
finally
{
closeDocument();
}
}

void openDocument(OutputStream outputStream) throws DocumentException
{
final Document document = new Document(pageSize, 36, 36, topMargin, bottomMargin);
final PdfWriter writer = PdfWriter.getInstance(document, outputStream);
document.open();
this.document = document;
this.writer = writer;
newPage();
}

void closeDocument()
{
try
{
document.close();
}
finally
{
this.document = null;
this.writer = null;
this.yPosition = 0;
}
}

void newPage()
{
document.newPage();
yPosition = pageSize.getTop(topMargin);
}

void merge(PdfReader reader) throws IOException
{
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
for (int page = 1; page <= reader.getNumberOfPages(); page++)
{
merge(reader, parser, page);
}
}

void merge(PdfReader reader, PdfReaderContentParser parser, int page) throws IOException
{
PdfImportedPage importedPage = writer.getImportedPage(reader, page);
PdfContentByte directContent = writer.getDirectContent();

PageVerticalAnalyzer finder = parser.processContent(page, new PageVerticalAnalyzer());
if (finder.verticalFlips.size() < 2)
return;
Rectangle pageSizeToImport = reader.getPageSize(page);

int startFlip = finder.verticalFlips.size() - 1;
boolean first = true;
while (startFlip > 0)
{
if (!first)
newPage();

float freeSpace = yPosition - pageSize.getBottom(bottomMargin);
int endFlip = startFlip + 1;
while ((endFlip > 1) && (finder.verticalFlips.get(startFlip) - finder.verticalFlips.get(endFlip - 2) < freeSpace))
endFlip -=2;
if (endFlip < startFlip)
{
float height = finder.verticalFlips.get(startFlip) - finder.verticalFlips.get(endFlip);

directContent.saveState();
directContent.rectangle(0, yPosition - height, pageSizeToImport.getWidth(), height);
directContent.clip();
directContent.newPath();

writer.getDirectContent().addTemplate(importedPage, 0, yPosition - (finder.verticalFlips.get(startFlip) - pageSizeToImport.getBottom()));

directContent.restoreState();
yPosition -= height + gap;
startFlip = endFlip - 1;
}
else if (!first)
throw new IllegalArgumentException(String.format("Page %s content sections too large.", page));
first = false;
}
}

Document document = null;
PdfWriter writer = null;
float yPosition = 0;

final Rectangle pageSize;
final float topMargin;
final float bottomMargin;
final float gap;
}

(PdfVeryDenseMergeTool.java)

此工具使用自定义 RenderListener 与 iText 解析器 API 一起使用:

public class PageVerticalAnalyzer implements RenderListener
{
@Override
public void beginTextBlock() { }
@Override
public void endTextBlock() { }

/*
* @see RenderListener#renderText(TextRenderInfo)
*/
@Override
public void renderText(TextRenderInfo renderInfo)
{
LineSegment ascentLine = renderInfo.getAscentLine();
LineSegment descentLine = renderInfo.getDescentLine();
float[] yCoords = new float[]{
ascentLine.getStartPoint().get(Vector.I2),
ascentLine.getEndPoint().get(Vector.I2),
descentLine.getStartPoint().get(Vector.I2),
descentLine.getEndPoint().get(Vector.I2)
};
Arrays.sort(yCoords);
addVerticalUseSection(yCoords[0], yCoords[3]);
}

/*
* @see RenderListener#renderImage(ImageRenderInfo)
*/
@Override
public void renderImage(ImageRenderInfo renderInfo)
{
Matrix ctm = renderInfo.getImageCTM();
float[] yCoords = new float[4];
for (int x=0; x < 2; x++)
for (int y=0; y < 2; y++)
{
Vector corner = new Vector(x, y, 1).cross(ctm);
yCoords[2*x+y] = corner.get(Vector.I2);
}
Arrays.sort(yCoords);
addVerticalUseSection(yCoords[0], yCoords[3]);
}

/**
* This method marks the given interval as used.
*/
void addVerticalUseSection(float from, float to)
{
if (to < from)
{
float temp = to;
to = from;
from = temp;
}

int i=0, j=0;
for (; i<verticalFlips.size(); i++)
{
float flip = verticalFlips.get(i);
if (flip < from)
continue;

for (j=i; j<verticalFlips.size(); j++)
{
flip = verticalFlips.get(j);
if (flip < to)
continue;
break;
}
break;
}
boolean fromOutsideInterval = i%2==0;
boolean toOutsideInterval = j%2==0;

while (j-- > i)
verticalFlips.remove(j);
if (toOutsideInterval)
verticalFlips.add(i, to);
if (fromOutsideInterval)
verticalFlips.add(i, from);
}

final List<Float> verticalFlips = new ArrayList<Float>();
}

(PageVerticalAnalyzer.java)

它是这样使用的:

PdfVeryDenseMergeTool tool = new PdfVeryDenseMergeTool(PageSize.A4, 18, 18, 5);
tool.merge(output, inputs);

(VeryDenseMerging.java)

应用于OP的示例文档

Header.pdf

Header.pdf pages

正文.pdf

Body.pdf pages

Footer.pdf

Footer.pdf pages

它产生

A4 very dense merge result

如果将目标文档页面大小定义为 A5 横向:

PdfVeryDenseMergeTool tool = new PdfVeryDenseMergeTool(new RectangleReadOnly(595,421), 18, 18, 5);
tool.merge(output, inputs);

(VeryDenseMerging.java)

它生成这个:

A5 very dense merge result

当心!这只是概念验证,并未考虑所有可能性。例如。具有重要 Rotate 值的源页面或目标页面的情况未得到正确处理。因此,它还不能用于生产。


当前 (5.5.6 SNAPSHOT) iText 版本的改进

当前的 iText 开发版本 5.5.6 增强了解析器功能,也可以表示矢量图形。因此,我扩展了 PageVerticalAnalyzer 以利用它:

public class PageVerticalAnalyzer implements ExtRenderListener
{
@Override
public void beginTextBlock() { }
@Override
public void endTextBlock() { }
@Override
public void clipPath(int rule) { }
...
static class SubPathSection
{
public SubPathSection(float x, float y, Matrix m)
{
float effectiveY = getTransformedY(x, y, m);
pathFromY = effectiveY;
pathToY = effectiveY;
}

void extendTo(float x, float y, Matrix m)
{
float effectiveY = getTransformedY(x, y, m);
if (effectiveY < pathFromY)
pathFromY = effectiveY;
else if (effectiveY > pathToY)
pathToY = effectiveY;
}

float getTransformedY(float x, float y, Matrix m)
{
return new Vector(x, y, 1).cross(m).get(Vector.I2);
}

float getFromY()
{
return pathFromY;
}

float getToY()
{
return pathToY;
}

private float pathFromY;
private float pathToY;
}

/*
* Beware: The implementation is not correct as it includes the control points of curves
* which may be far outside the actual curve.
*
* @see ExtRenderListener#modifyPath(PathConstructionRenderInfo)
*/
@Override
public void modifyPath(PathConstructionRenderInfo renderInfo)
{
Matrix ctm = renderInfo.getCtm();
List<Float> segmentData = renderInfo.getSegmentData();

switch (renderInfo.getOperation())
{
case PathConstructionRenderInfo.MOVETO:
subPath = null;
case PathConstructionRenderInfo.LINETO:
case PathConstructionRenderInfo.CURVE_123:
case PathConstructionRenderInfo.CURVE_13:
case PathConstructionRenderInfo.CURVE_23:
for (int i = 0; i < segmentData.size()-1; i+=2)
{
if (subPath == null)
{
subPath = new SubPathSection(segmentData.get(i), segmentData.get(i+1), ctm);
path.add(subPath);
}
else
subPath.extendTo(segmentData.get(i), segmentData.get(i+1), ctm);
}
break;
case PathConstructionRenderInfo.RECT:
float x = segmentData.get(0);
float y = segmentData.get(1);
float w = segmentData.get(2);
float h = segmentData.get(3);
SubPathSection section = new SubPathSection(x, y, ctm);
section.extendTo(x+w, y, ctm);
section.extendTo(x, y+h, ctm);
section.extendTo(x+w, y+h, ctm);
path.add(section);
case PathConstructionRenderInfo.CLOSE:
subPath = null;
break;
default:
}
}

/*
* @see ExtRenderListener#renderPath(PathPaintingRenderInfo)
*/
@Override
public Path renderPath(PathPaintingRenderInfo renderInfo)
{
if (renderInfo.getOperation() != PathPaintingRenderInfo.NO_OP)
{
for (SubPathSection section : path)
addVerticalUseSection(section.getFromY(), section.getToY());
}

path.clear();
subPath = null;
return null;
}

List<SubPathSection> path = new ArrayList<SubPathSection>();
SubPathSection subPath = null;
...
}

(PageVerticalAnalyzer.java)

一个简单的测试(VeryDenseMerging.java 方法 testMergeOnlyGraphics)合并这些文件

circlesOnlyA.pdf

circlesOnlyB.pdf

circlesOnlyC.pdf

circlesOnlyD.pdf

进入这个:

circlesOnlyMerge-veryDense.pdf

但再次注意:这仅仅是概念证明。特别是 modifyPath() 需要改进,实现不正确,因为它包含曲线的控制点,可能远离实际曲线。

关于c# - 如何在合并时删除空格,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/28991291/

26 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com