我有一些代码可以接受3个不同的PDF字节数组并将它们合并。这段代码非常有效。(一些人)面临的问题是,每个PDF都被视为一个完整的页面(如果打印出来的话),即使上面只有4英寸的内容,也会在垂直方向上留下7英寸的空白。然后,中间的文档被放入其中,它的末尾可能有也可能没有垂直的空格。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,有没有办法剪辑/删除/擦除每个pdf末尾的垂直空白,使其显示为一个无缝文档?
页眉、正文、页脚
更新2:使用答案:
我已经将@mkl的代码转换为C#,它就在这里。
工具类别:
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
RenderListener类:
更新3:修复了1行代码并且它有效:请参阅代码中的注释
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
收集文件并运行工具的代码:
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));
} // html" target="_blank">foreach of the sets of data
tool.Merge(ms, files);
// Save the file using: ms.GetBuffer()
} // using the memory stream
} // TestMergeDocuments
下面的示例工具是按照工具PdfDenseMergeTool
的思想实现的,OP已经评论为非常接近[他]需要的答案。就像PdfDenseMergeTool
这里的这个工具是用Java实现的 /iText我比C#/iTextSharp更熟悉。由于OP已经将PdfDenseMergeTool
翻译为C#/iTextSharp,在这里翻译这个工具也不应该是太大的问题。
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,即如果有足够的可用空间,则将多个源页面的内容放在单个目标页面上这样做。与早期的工具相比,该工具甚至拆分源页面内容以允许更密集的合并。
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将不完全适合目标页的源页拆分为水平线,该水平线不与文本图示符或位图图形的边界框相交。
工具类别:
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)
此工具使用自定义的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);
(verydenseminging.java)
应用于OP的示例文档
标题。pdf格式
身体pdf格式
Footer.pdf
它生成
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);
(verydenseminging.java)
它生成以下内容:
当心这只是概念证明,并没有考虑所有可能性。E、 g.未正确处理具有非平凡旋转值的源页面或目标页面的情况。因此,它还没有准备好投入生产使用。
当前的iText开发版本(5.5.6版)增强了解析器的功能,同时也增强了信号向量图形。因此,我扩展了PageVerticalAnalyzer来利用它:
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(verydenseminging.java方法testMergeOnlyGraphics)合并这些文件
进入这个:
但请再次注意:这仅仅是概念的证明。尤其是需要改进,实施不正确,因为它包括曲线的html" target="_blank">控制点,这些控制点可能远远超出实际曲线。
隐藏CardView时如何删除空间?我用android和Firebase做了一个应用程序,我在cardviews中显示Firebase的信息,但当信息不正确时,cardview必须消失。重点是cardview消失了,但仍然在布局中使用了空格,我已经在 setVisibility(GONE)视图变得不可见,但仍然占用空间,但对我来说不起作用。 这是我的布局: 这是mview: 我希望你能帮助我。
问题内容: 我有一些服务器端HTML输出,我无法使用纯CSS来处理,本质上DIV有时适用: 要么 要么 要么 当DIV == 我要删除它。 有任何想法吗? 问题答案: 甚至更好(假设使用jQuery): 编辑:其他答案是好的,但OP想要删除空项目,而不是将其隐藏。
问题内容: 我有一堆正在用BeautifulSoup解析的HTML,除了一个小小的障碍外,一切进展顺利。我想将输出保存到单行字符串中,并将以下内容作为当前输出: 理想情况下,我想要 我想摆脱很多多余的空格,但是不一定要使用来删除它,也不能因为需要保留文本而公然删除所有空格。我该怎么做?看起来正则表达式过于矫over似乎是一个足够普遍的问题,但这是唯一的方法吗? 我没有任何标签,因此可以在其中变得更
问题内容: 我有两个JavaScript数组: 我希望输出为: 输出数组应删除重复的单词。 如何在JavaScript中合并两个数组,以使每个数组中的唯一项按插入原始数组中的相同顺序获得? 问题答案: 仅合并数组(不删除重复项) ES5版本使用: ES6版本使用解构 由于没有“内置”方式来删除重复项ECMA-262实际上有这样做的好处),因此我们必须手动进行: 然后,使用它: 这也将保留数组的顺序
问题内容: 我们目前有一个使用的詹金斯管道。每个git分支都执行一个声纳分析,使用该属性创建一个声纳项目 。这是非常有用的,因为在合并每个分支之前都会对其进行分析,当一个分支与master合并并在GIT上消失时,该问题就会出现,该项目将继续在sonarqube上进行,并且需要手动删除。有没有办法自动做到这一点?或其他任何建议? 问题答案: 您可以定义以下方法来执行此工作,然后根据需要或在诸如合并/
问题内容: 尝试删除不为空的文件夹时,出现“访问被拒绝”错误。我尝试使用以下命令:。 删除/删除不为空的文件夹/目录的最有效方法是什么? 问题答案: 标准库参考:shutil.rmtree。 根据设计,在包含只读文件的文件夹树上失败。如果要删除该文件夹而不管它是否包含只读文件,请使用