How to parse form using PDFium, obtaining values of text fields, button statuses etc ?
I tried this code, but FPDFTextObj_GetText returns empty string.
ScopedFPDFTextPage pTextPage (FPDFText_LoadPage(Page));
for (int i = 0;i < FPDFPage_CountObjects(Page); i++)
{
FPDF_PAGEOBJECT pageObj = FPDFPage_GetObject(Page, i);
auto pageObjType = FPDFPageObj_GetType(pageObj);
if (pageObjType == FPDF_PAGEOBJ_TEXT)
{
auto size = FPDFTextObj_GetText(pageObj, pTextPage.get(), nullptr, 0);
std::vector<FPDF_WCHAR> buffer = GetFPDFWideStringBuffer(size);
size = FPDFTextObj_GetText(pageObj, pTextPage.get(), buffer.data(), size);
}
else if (pageObjType == FPDF_PAGEOBJ_FORM)
{
for (int j = 0; j < FPDFFormObj_CountObjects(pageObj); j++)
{
auto formObj = FPDFFormObj_GetObject(pageObj, j);
auto formObjType = FPDFPageObj_GetType(formObj);
if (formObjType == FPDF_PAGEOBJ_TEXT)
{
auto size = FPDFTextObj_GetText(pageObj, pTextPage.get(), nullptr, 0);
std::vector<FPDF_WCHAR> buffer = GetFPDFWideStringBuffer(size);
size = FPDFTextObj_GetText(pageObj, pTextPage.get(), buffer.data(), size);
}
}
}
}
Related
Using a legacy IF field code:
enter image description here
and content controls:
private static byte[] mergingDocxFileWithXml(File file, File fileXml) {WordprocessingMLPackage wordMLPackage = WordprocessingMLPackage.load(file)
MainDocumentPart mainDocumentPart = wordMLPackage.getMainDocumentPart()
ArrayList<String> datas
List<Object> contentControls = ContentControl.getAllContentControl(mainDocumentPart)
List<String> arrayListXpathToBoucle = new ArrayList<>()
for (Object contenControl : contentControls) {
ContentControl cControl = new ContentControl(contenControl)
String xPath = cControl.getXPath()
String title = cControl.getTitle()
if (xPath != null) {
datas = XmlPath.getXmlDataFrom(fileXml, xPath)
}
switch (title) {
case "DateDuJour":
cControl.setValue(getDateDay())
break
case "checkbox":
String checkValue = new String(Character.toChars(0x2612))
if (datas[0] != "1") {
checkValue = new String(Character.toChars(0x2610))
}
cControl.setValue(checkValue)
break
case "Boucle_Ligne":
xPath = cControl.getTag()
int indexBoucleContent = getIndexContentBoucle(wordMLPackage.mainDocumentPart.getContent(), xPath)
NodeList nodeList = XmlPath.getNodeListXmlFile(fileXml, xPath)
List<String> dataXpath = getAllXpathForBoucle(contentControls, xPath)
for (int i = 0; i < dataXpath.stream().count(); i++) {
arrayListXpathToBoucle.add(dataXpath.get(i))
}
int totalNode = nodeList.getLength()
for (int j = 0; j < totalNode; j++) {
wordMLPackage = mapingDataNode(j, cControl, contentControls, fileXml, dataXpath, wordMLPackage, indexBoucleContent, null, 0)
}
wordMLPackage.mainDocumentPart.getContent().remove(indexBoucleContent)
break;
case "Boucle_Colonne":
xPath = cControl.getTag()
NodeList nodeList = XmlPath.getNodeListXmlFile(fileXml, xPath)
List<String> dataXpath = getAllXpathForBoucle(contentControls, xPath)
int totalNode = nodeList.getLength()
for (int i = 0; i < dataXpath.stream().count(); i++) {
arrayListXpathToBoucle.add(dataXpath.get(i))
}
String boucleValue = ""
for (int i = 0; i < totalNode; i++) {
datas = XmlPath.getXmlDataFrom(fileXml, dataXpath.get(0))
boucleValue += datas.get(i) + ", "
}
boucleValue = boucleValue.substring(0, boucleValue.length() - 2)
addValueInContentControl(contentControls, dataXpath.get(0), 0, boucleValue, null, wordMLPackage)
break
case "Boucle_Ligne_Table":
xPath = cControl.getTag()
NodeList nodeList = XmlPath.getNodeListXmlFile(fileXml, xPath)
int indexBoucleContent = getIndexContentBoucle(wordMLPackage.mainDocumentPart.getContent(), xPath)
List<String> dataXpath = getAllXpathForBoucle(contentControls, xPath)
int totalNode = nodeList.getLength()
for (int i = 0; i < dataXpath.stream().count(); i++) {
arrayListXpathToBoucle.add(dataXpath.get(i))
}
int nodeIndex = 0
Tbl arraysBoucle = getArraysBoucle(wordMLPackage, indexBoucleContent)
Tr trContent
for (int i = 0; i < totalNode; i++) {
nodeIndex = i + 1
if (arraysBoucle.getContent().stream().count() > 1) {
trContent = WoeDocx4jFunction.getTr(arraysBoucle.getContent().get(1))
} else {
trContent = WoeDocx4jFunction.getTr(arraysBoucle.getContent().get(0))
}
wordMLPackage = mapingDataNode(i, cControl, contentControls, fileXml, dataXpath, wordMLPackage, indexBoucleContent, trContent, nodeIndex)
}
int lastIndexTr = wordMLPackage.getMainDocumentPart().getContent().get(indexBoucleContent).sdtContent.content.get(1).value.content.stream().count()
wordMLPackage.getMainDocumentPart().getContent().get(indexBoucleContent).sdtContent.content.get(1).value.content.remove(lastIndexTr - 1)
break
case "IMAGE":
datas = XmlPath.getXmlDataFrom(fileXml, xPath)
byte[] imageByte = base64ToImage(datas.get(0))
Inline inlineImage = newImage(wordMLPackage, imageByte)
cControl.setValue(null, inlineImage)
break
default:
String xpathBoucle = arrayListXpathToBoucle.find { it.startsWith(xPath) }
if (xpathBoucle != xPath) {
addValueInContentControl(contentControls, xPath, 0, "", fileXml,wordMLPackage)
}
break
}
}
ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
wordMLPackage= mergingFieldWordMlPackage(wordMLPackage)
FieldUpdater updater = new FieldUpdater(wordMLPackage)
updater.update(true);
wordMLPackage.save(outputStream);
return outputStream.toByteArray();
}
Docx4j's legacy field processing does not parse IF fields: http://webapp.docx4java.org/OnlineDemo/ecma376/WordML/IF.html
If you need to do that, you'll need to write code to do the parsing.
An alternative would be to use OpenDoPE conditional content controls. With one of these, the content of the SDT is included only if the associated XPath evaluates to true.
This is a function if the endValueFixed is equal for example 12.0 I want to print the number without zero so I want it to be 12.
void calculateIncrease() {
setState(() {
primerResult = (startingValue * percentage) / 100;
endValue = startingValue + primerResult;
endValueFixe`enter code here`d = roundDouble(endValue, 2);
});
}
This may be an overkill but it works exactly as you wish:
void main() {
// This is your double value
final end = 98.04;
String intPart = "";
String doublePart = "";
int j = 0;
for (int i = 0; i < end.toString().length; i++) {
if (end.toString()[i] != '.') {
intPart += end.toString()[i];
} else {
j = i + 1;
break;
}
}
for (int l = j; l < end.toString().length; l++) {
doublePart += end.toString()[l];
}
if (doublePart[0] == "0" && doublePart[1] != "0") {
print(end);
} else {
print(end.toString());
}
}
You may use this code as a function and send whatever value to end.
if (endValueFixed==12) {
print('${endValueFixed.toInt()}');
}
conditionally cast it to an int and print it then :)
I'm creating a Gmail script that includes 5 variables, one of which is a due date. I just want it to populate as MM/DD/YYYY, however, it is currently populating as Thu Sep 13 2018 00:00:00 GMT-0400 (EDT).
Is there a way I can do that? I've pasted my code below for your reference. Any assistance is much appreciated.
function getRowsData(sheet, range, columnHeadersRowIndex) {
columnHeadersRowIndex = columnHeadersRowIndex || range.getRowIndex() - 1;
var numColumns = range.getEndColumn() - range.getColumn() + 1;
var headersRange = sheet.getRange(columnHeadersRowIndex, range.getColumn(), 1, numColumns);
var headers = headersRange.getValues()[0];
return getObjects(range.getValues(), normalizeHeaders(headers));
}
function getObjects(data, keys) {
var objects = [];
for (var i = 0; i < data.length; ++i) {
var object = {};
var hasData = false;
for (var j = 0; j < data[i].length; ++j) {
var cellData = data[i][j];
if (isCellEmpty(cellData)) {
continue;
}
object[keys[j]] = cellData;
hasData = true;
}
if (hasData) {
objects.push(object);
}
}
return objects;
}
function normalizeHeaders(headers) {
var keys = [];
for (var i = 0; i < headers.length; ++i) {
var key = normalizeHeader(headers[i]);
if (key.length > 0) {
keys.push(key);
}
}
return keys;
}
function normalizeHeader(header) {
var key = "";
var upperCase = false;
for (var i = 0; i < header.length; ++i) {
var letter = header[i];
if (letter == " " && key.length > 0) {
upperCase = true;
continue;
}
if (!isAlnum(letter)) {
continue;
}
if (key.length == 0 && isDigit(letter)) {
continue;
}
if (upperCase) {
upperCase = false;
key += letter.toUpperCase();
} else {
key += letter.toLowerCase();
}
}
return key;
}
function isCellEmpty(cellData) {
return typeof(cellData) == "string" && cellData == "";
}
function isAlnum(char) {
return char >= 'A' && char <= 'Z' ||
char >= 'a' && char <= 'z' ||
isDigit(char);
}
function isDigit(char) {
return char >= '0' && char <= '9';
I am currently linear referencing a set of roads. Using IMSegmatation2.SetMsAsDistance2 works fine for single-part polylines but for multi-part polylines I want to set the M values as the length along the polyline to the point, not the shortest distance between the point and the start point of the polyline. The SetMsAsDistance2 function sets the Measures on parallel lines as equal. I want them to be different.
Apart from setting an M value for each polyline vertex does anyone know of a method that sets the M as the length along the polyline?
The solution is to use the IMSegmentation3.SetAndInterpolateMsBetween function.
Note that the solution assumes that the geometries that make up the feature are in the right order. It assigns measures geometry-by-geometry.
The code for this is:
public static void measuresAdd_NonDuplicating(ref IFeature pFeat, bool bHasZ, bool bIgnoreGaps, out string sError)
{
// Add non-duplicating measures to the feature
sError = "";
IMSegmentation3 pSeg;
IGeometryCollection pGeomColl;
//IGeometryCollection pNewGeomColl; // Use if geometries are to be re-ordered.
IGeometry pGeom;
IPolyline4 pPoly;
IQueryFilter pQ;
IMAware pMAware;
IZAware pZAware;
double dStartMeasure;
double dToMeasure;
double dMeasure;
double dLen;
try
{
if (pFeat.ShapeCopy.IsEmpty == false)
{
pGeomColl = (IGeometryCollection)new PolylineClass();
pGeomColl = (IGeometryCollection)pFeat.ShapeCopy;
if (pGeomColl.GeometryCount == 1)
{
// Single line geometry. Duplication not an issue.
pMAware = (IMAware)pFeat.ShapeCopy;
pMAware.MAware = true;
pSeg = (IMSegmentation3)pMAware;
pPoly = geometryToPolyline((IGeometry)pFeat.ShapeCopy, out sError);
if (sError.Length > 0)
{
sError = "measuresAdd_NonDuplicating\r\n" + sError;
return;
}
pSeg.SetMsAsDistance2(pPoly.FromPoint, 1, 0, bIgnoreGaps);
pFeat.Shape = (IGeometry)pSeg;
pFeat.Store();
}
else
{
// For re-ordering geometries. Not currently used.
//pNewGeomColl = (IGeometryCollection)new Polyline();
//IZAware pZawareNew = (IZAware)pNewGeomColl;
//pZawareNew.ZAware = bHasZ;
//IMAware pMAwareNew = (IMAware)pNewGeomColl;
//pMAwareNew.MAware = true;
dStartMeasure = 0;
dMeasure = 0;
// MultiGeometry. Place them in order and set the measures on each part increasing.
// Currently assumes the existing order is correct.
for (int i = 0; i < pGeomColl.GeometryCount; i++)
{
pGeom = pGeomColl.Geometry[i];
pPoly = geometryToPolyline(pGeom, out sError);
if (sError.Length > 0)
{
sError = "measuresAdd_NonDuplicating\r\n" + sError;
return;
}
// Measure Values
dStartMeasure = dMeasure;
if (i > 0) dStartMeasure += 0.01;
dLen = pPoly.Length;
dToMeasure = dMeasure + dLen;
// Set Measures
pMAware = (IMAware)pPoly;
pMAware.MAware = true;
pZAware = (IZAware)pPoly;
pZAware.ZAware = bHasZ;
pSeg = (IMSegmentation3)pPoly;
pSeg.SetAndInterpolateMsBetween(dStartMeasure, dToMeasure);
// If geometries are re-ordered into a connecting network
//IGeometryCollection pXGeomColl = new PolylineClass();
//pMAware = (IMAware)pXGeomColl;
//pMAware.MAware = true;
//pZAware = (IZAware)pXGeomColl;
//pZAware.ZAware = bHasZ;
//pXGeomColl = (IGeometryCollection)pPoly;
//for (int j = 0; j < pXGeomColl.GeometryCount; j++)
// pNewGeomColl.AddGeometry(pXGeomColl.Geometry[j]);
dMeasure += dLen;
}
pFeat.Shape = (IGeometry)pGeomColl;
}
}
}
catch (Exception ex)
{
System.Diagnostics.StackTrace pStack = new System.Diagnostics.StackTrace(ex, true);
System.Diagnostics.StackFrame pFrame = pStack.GetFrame(pStack.FrameCount - 1);
int iLineNo = pFrame.GetFileLineNumber();
sError = "ERROR: measuresAdd_NonDuplicating; Line: " + iLineNo + "\n" + ex.ToString();
}
}
hallo i have this sniped code like this:
public static void Put_CSVtoSQL_Adhesion()
{
bool IsFirst = true;
DataTable dt = new DataTable();
string line = null;
int i = 0;
try
{
string fileName = Path.Combine(HttpContext.Current.Server.MapPath(UploadDirectory), TheFileName);
using (StreamReader sr = File.OpenText(fileName))
{
while ((line = sr.ReadLine()) != null)
{
string[] data = line.Split(';');
if (data.Length > 0)
{
if (i == 0)
{
foreach (var item in data)
{
dt.Columns.Add(new DataColumn());
}
i++;
}
DataRow row = dt.NewRow();
row.ItemArray = data;
// Pour enlever la tete
if (!IsFirst) dt.Rows.Add(row);
IsFirst = false;
}
}
}
using (var connectionWrapper = new Connexion())
{
var connectedConnection = connectionWrapper.GetConnected();
using (SqlBulkCopy copy = new SqlBulkCopy(connectionWrapper.conn))
{
int CountColl = dt.Columns.Count;
copy.ColumnMappings.Add(0, 1);
copy.ColumnMappings.Add(1, 2);
copy.ColumnMappings.Add(2, 3);
copy.ColumnMappings.Add(3, 4);
copy.ColumnMappings.Add(4, 5);
copy.DestinationTableName = "cotisation";
copy.WriteToServer(dt);
}
}
}
catch (Exception excThrown)
{
throw new Exception(excThrown.Message);
}
}
this code work well, but now i have more than 60 column, should i type manualy from 1 to 60 column or there are another methode ?
copy.ColumnMappings.Add(0, 1);
copy.ColumnMappings.Add(1, 2);
copy.ColumnMappings.Add(2, 3);
copy.ColumnMappings.Add(3, 4);
copy.ColumnMappings.Add(4, 5);
...until 60 column ?
the column is all the same i just shifted 1 column, because the first one is autoincremented column as an ID
Write a loop?
for (int i = 0; i < dt.Columns.Count - 1; i++)
{
copy.ColumnMappings.Add(i, i + 1);
}