Documents4j 문서 포맷 변환기(excel->html)

Documents4j 문서 포맷 변환기(excel->html)

먼저 해당 문서 를 보기전에 아래 사이트를 실습을 해보거나 분석을 꼭 해보시기 바랍니다.

그래야 해당 문서가 이해가 수월 할것으로 예상 됩니다.

http://idlecomputer.tistory.com/248

먼저 기본 로직은 아래와 같습니다.

아래 로직중

1.temp1 은 Documents4j 라이브러리가 만드는 Input 파라 메터 입니다.

2.temp2 은 Documents4j 라이브러리가 만드는 Output 파라 메터 입니다.

3.압축은 7z을 사용하기 때문에 7z이 설치가 되어 있어야 합니다. (VBScript 를 사용할때 해당 경로 적어 줍니다 )

먼저 HTML 을 위해서 오픈 소스 수정이 필요 합니다.

먼저 Maven 프로젝트 소스를 Import 해보면     https://github.com/documents4j/documents4j/releases (소스 다운로드 Site)

먼저 HTML 포멧을 추가 시켜 줘야 합니다.

에서 HTML 부분을 추가해 줍니다

package com.documents4j.api;

import java.io.Serializable;

/**
 * Represents an immutable document MIME type.
 */
public class DocumentType implements Serializable, Comparable {

    public static final DocumentType MS_WORD = new DocumentType(Value.APPLICATION, Value.WORD_ANY);
    public static final DocumentType RTF = new DocumentType(Value.APPLICATION, Value.RTF);
    public static final DocumentType DOCX = new DocumentType(Value.APPLICATION, Value.DOCX);
    public static final DocumentType DOC = new DocumentType(Value.APPLICATION, Value.DOC);
    public static final DocumentType MS_EXCEL = new DocumentType(Value.APPLICATION, Value.EXCEL_ANY);
    public static final DocumentType XLSX = new DocumentType(Value.APPLICATION, Value.XLSX);
    public static final DocumentType XLS = new DocumentType(Value.APPLICATION, Value.XLS);
    public static final DocumentType ODS = new DocumentType(Value.APPLICATION, Value.ODS);
    public static final DocumentType CSV = new DocumentType(Value.TEXT, Value.CSV);
    public static final DocumentType XML = new DocumentType(Value.APPLICATION, Value.XML);
    public static final DocumentType MHTML = new DocumentType(Value.APPLICATION, Value.MHTML);
    public static final DocumentType PDF = new DocumentType(Value.APPLICATION, Value.PDF);
    public static final DocumentType HTML = new DocumentType(Value.APPLICATION, Value.HTML);
    public static final DocumentType PDFA = new DocumentType(Value.APPLICATION, Value.PDFA);
    public static final DocumentType TEXT = new DocumentType(Value.TEXT, Value.PLAIN);
    
    

    private final String type;

    private final String subtype;

    /**
     * Creates a new document type.
     *
     * @param type    The MIME type's type name.
     * @param subtype The MIME type's subtype name.
     */
    public DocumentType(String type, String subtype) {
        if (type == null || subtype == null) {
            throw new NullPointerException("Type elements must not be null");
        }
        this.type = type;
        this.subtype = subtype;
    }

    /**
     * Creates a new document type.
     *
     * @param fullType The MIME type's type name and subtype name, separated by a {@code /}.
     */
    public DocumentType(String fullType) {
        int separator = fullType.indexOf('/');
        if (separator == -1 || fullType.length() == separator + 1) {
            throw new IllegalArgumentException("Not a legal */* document type: " + fullType);
        } else {
            type = fullType.substring(0, separator);
            subtype = fullType.substring(separator + 1);
        }
    }

    public String getType() {
        return type;
    }

    public String getSubtype() {
        return subtype;
    }

    @Override
    public boolean equals(Object other) {
        if (this == other) return true;
        if (other == null || getClass() != other.getClass()) return false;
        DocumentType documentType = (DocumentType) other;
        return subtype.equals(documentType.subtype) && type.equals(documentType.type);
    }

    @Override
    public int hashCode() {
        return 31 * type.hashCode() + subtype.hashCode();
    }

    @Override
    public int compareTo(DocumentType other) {
        return toString().compareTo(other.toString());
    }

    @Override
    public String toString() {
        return type + "/" + subtype;
    }

    /**
     * A holder type for type and subtype names of known {@link com.documents4j.api.DocumentType}s.
     */
    public static class Value {

        public static final String APPLICATION = "application";
        public static final String TEXT = "text";

        public static final String DOC = "msword";
        public static final String DOCX = "vnd.openxmlformats-officedocument.wordprocessingml.document";
        public static final String WORD_ANY = "vnd.com.documents4j.any-msword";

        public static final String XLS = "vnd.ms-excel";
        public static final String XLSX = "vnd.openxmlformats-officedocument.spreadsheetml.sheet";
        public static final String EXCEL_ANY = "vnd.com.documents4j.any-msexcel";
        public static final String ODS = "vnd.oasis.opendocument.spreadsheet";

        public static final String PDF = "pdf";
        public static final String HTML = "htm";

        public static final String PDFA = "vnd.com.documents4j.pdf-a";

        public static final String RTF = "rtf";

        public static final String XML = "xml";
        public static final String MHTML = "x-mimearchive";

        public static final String CSV = "csv";
        public static final String PLAIN = "plain";

        private Value() {
            throw new UnsupportedOperationException();
        }
    }
}

그리고 아래와 같이 소스를 추가해 줍니다.

package com.documents4j.conversion.msoffice;

import com.documents4j.api.DocumentType;

/**
 * An enumeration of MS Excel file
 * format encodings.
 */
enum MicrosoftExcelFormat implements MicrosoftOfficeFormat {

    PDF("999", "pdf", DocumentType.PDF),
    XLSX("51", "xlsx", DocumentType.XLSX),
    XLS("43", "xls", DocumentType.XLS),
    HTML("44", "htm", DocumentType.HTML),
    ODS("60", "ods", DocumentType.ODS),
    CSV("6", "csv", DocumentType.CSV),
    XML("46", "xml", DocumentType.XML),
    TEXT("42", "txt", DocumentType.TEXT);

    private final String value;
    private final DocumentType documentType;
    private final String fileExtension;

    private MicrosoftExcelFormat(String value, String fileExtension, DocumentType documentType) {
        this.value = value;
        this.fileExtension = fileExtension;
        this.documentType = documentType;
    }

    public static MicrosoftExcelFormat of(DocumentType documentType) {
        for (MicrosoftExcelFormat enumeration : MicrosoftExcelFormat.values()) {
            if (enumeration.documentType.equals(documentType)) {
                return enumeration;
            }
        }
        throw new IllegalArgumentException("Unknown document type: " + documentType);
    }

    @Override
    public String getValue() {
        return value;
    }

    @Override
    public String getFileExtension() {
        return fileExtension;
    }
}

위에서 HTML 44 로 설정한 이유는

VBA 에서 html 저장의 상수가 44 이기 때문입니다.

그리고 나서

package com.documents4j.conversion.msoffice;

import com.documents4j.api.DocumentType;
import com.documents4j.conversion.ViableConversion;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.File;
import java.util.concurrent.Semaphore;
import java.util.concurrent.TimeUnit;

import static com.documents4j.api.DocumentType.Value.*;

/**
 * A converter back-end for MS Excel.
 */
@ViableConversion(
        from = {APPLICATION + "/" + XLS,
                APPLICATION + "/" + XLSX,
                APPLICATION + "/" + EXCEL_ANY,
                APPLICATION + "/" + ODS},
        to = {APPLICATION + "/" + PDF,
                APPLICATION + "/" + XLS,
                APPLICATION + "/" + XLSX,
                APPLICATION + "/" + HTML,
                APPLICATION + "/" + ODS,
                TEXT + "/" + CSV,
                TEXT + "/" + PLAIN,
                APPLICATION + "/" + XML})
public class MicrosoftExcelBridge extends AbstractMicrosoftOfficeBridge {

    private static final Logger LOGGER = LoggerFactory.getLogger(MicrosoftExcelBridge.class);

    private static final Object EXCEL_LOCK = new Object();

    /**
     * Other than MS Word, MS Excel does not behave well under stress. Thus, MS Excel must not be asked to convert
     * more than one document at a time.
     */
    private static final Semaphore CONVERSION_LOCK = new Semaphore(1, true);

    public MicrosoftExcelBridge(File baseFolder, long processTimeout, TimeUnit processTimeoutUnit) {
        super(baseFolder, processTimeout, processTimeoutUnit, MicrosoftExcelScript.CONVERSION);
        startUp();
    }

    private void startUp() {
        synchronized (EXCEL_LOCK) {
            tryStart(MicrosoftExcelScript.STARTUP);
            LOGGER.info("From-Microsoft-Excel-Converter was started successfully");
        }
    }

    @Override
    public void shutDown() {
        synchronized (EXCEL_LOCK) {
            tryStop(MicrosoftExcelScript.SHUTDOWN);
            LOGGER.info("From-Microsoft-Excel-Converter was shut down successfully");
        }
    }

    @Override
    protected MicrosoftOfficeTargetNameCorrector targetNameCorrector(File target, String fileExtension) {
        return new MicrosoftExcelTargetNameCorrectorAndLockManager(target, fileExtension, CONVERSION_LOCK, LOGGER);
    }

    @Override
    protected MicrosoftOfficeFormat formatOf(DocumentType documentType) {
        return MicrosoftExcelFormat.of(documentType);
    }

    @Override
    protected MicrosoftOfficeScript getAssertionScript() {
        return MicrosoftExcelScript.ASSERTION;
    }

    @Override
    protected Logger getLogger() {
        return LOGGER;
    }
}

위와 같이 HTML 코드를 추가해 줍니다.

해당 파일에서 실제 VBA 코드를 VBScript 를 작성해 줍니다.

' See http://msdn.microsoft.com/en-us/library/bb243311%28v=office.12%29.aspx
Const WdExportFormatPDF = 17
Const MagicFormatPDF = 999
Const HtmFormat = 44
Dim arguments
Set arguments = WScript.Arguments

Function Zip(Outfile)
  'This script is provided under the Creative Commons license located
  'at http://creativecommons.org/licenses/by-nc/2.5/ . It may not
  'be used for commercial purposes with out the expressed written consent
  'of NateRice.com
	Dim outputfilename
	Dim outputfoldername
	Dim outputzipfile
  Set oFSO = WScript.CreateObject("Scripting.FileSystemObject")
  Set oShell = WScript.CreateObject("Wscript.Shell")

  '--------Find Working Directory--------
  aScriptFilename = Split(Wscript.ScriptFullName, "\")
  sScriptFilename = aScriptFileName(Ubound(aScriptFilename))
  sWorkingDirectory = Replace(Wscript.ScriptFullName, sScriptFilename, "")
  '--------------------------------------

  '-------Ensure we can find 7z.exe------
  If oFSO.FileExists(sWorkingDirectory & "\" & "7z.exe") Then
    s7zLocation = ""
  ElseIf oFSO.FileExists("C:\Program Files\7-Zip\7z.exe") Then
    s7zLocation = "C:\Program Files\7-Zip\"
  Else
    Zip = "Error: Couldn't find 7z.exe"
    Exit Function
  End If
  '--------------------------------------
  outputfilename =   """" & Outfile &".htm" & """"
  outputfoldername = """" & Outfile & ".files" & """"
  outputzipfile = """" &Outfile &".zip" & """"
  oShell.Run """" & s7zLocation & "7z.exe"" a  " & outputzipfile &" " _
  &outputfoldername&" "& outputfilename, 0, True

  
  If oFSO.FileExists(Outfile &".htm") Then
  	oFSO.DeleteFile (Outfile &".htm")
  End IF
  If oFSO.FolderExists(Outfile & ".files") Then 
		oFSO.DeleteFolder(Outfile & ".files")
	END IF
	oFSO.MoveFile Outfile &".zip",Outfile &".htm"
	
  If oFSO.FileExists(Outfile) Then
    Zip = 1
  Else
    Zip = "Error: Archive Creation Failed."
  End If
End Function

' Transforms a file using MS Excel into the given format.
Function ConvertFile( inputFile, outputFile, formatEnumeration )    
  Dim fileSystemObject
  Dim excelApplication
  Dim excelDocument
  
  ' Get the running instance of MS Excel. If Excel is not running, exit the conversion.
  On Error Resume Next
  Set excelApplication = GetObject(, "Excel.Application")
  If Err <> 0 Then
    WScript.Quit -6
  End If
  On Error GoTo 0
  ' Find the source file on the file system.
  Set fileSystemObject = CreateObject("Scripting.FileSystemObject")
  inputFile = fileSystemObject.GetAbsolutePathName(inputFile)

  
  ' Convert the source file only if it exists.
  If fileSystemObject.FileExists(inputFile) Then

    ' Attempt to open the source document.
    On Error Resume Next
    Set excelDocument = excelApplication.Workbooks.Open(inputFile)
    If Err <> 0 Then
        WScript.Quit -2
    End If
    On Error GoTo 0

    ' Convert: See http://msdn2.microsoft.com/en-us/library/bb221597.aspx
    ' Encoding is https://docs.microsoft.com/en-us/dotnet/api/microsoft.office.core.msoencoding?view=office-pia,
    ' ScreenSize is https://docs.microsoft.com/en-us/dotnet/api/microsoft.office.core.msoscreensize?view=office-pia
    On Error Resume Next
    If formatEnumeration = MagicFormatPDF Then
				For Each ws In excelDocument.Worksheets
			    excelApplication.Application.PrintCommunication = False
			    ws.PageSetup.FitToPagesWide = 1
			    ws.PageSetup.FitToPagesTall = 0
			    excelApplication.Application.PrintCommunication = True
       	Next
       	excelDocument.ExportAsFixedFormat xlTypePDF, outputFile, xlQualityStandard, True, True
       	excelDocument.Close False
    ElseIf formatEnumeration = HtmFormat Then     	
    	excelDocument.WebOptions.RelyOnCSS = True
    	excelDocument.WebOptions.OrganizeInFolder = True
    	excelDocument.WebOptions.UseLongFileNames = True
    	excelDocument.WebOptions.DownloadComponents = False
    	excelDocument.WebOptions.RelyOnVML = False
    	excelDocument.WebOptions.AllowPNG = True
    	excelDocument.WebOptions.ScreenSize = 4
    	excelDocument.WebOptions.PixelsPerInch = 96
    	excelDocument.WebOptions.Encoding = 949
    	excelApplication.Application.DefaultWebOptions.SaveHiddenData = True
    	excelApplication.Application.DefaultWebOptions.LoadPictures = True
    	excelApplication.Application.DefaultWebOptions.UpdateLinksOnSave = True
    	excelApplication.Application.DefaultWebOptions.CheckIfOfficeIsHTMLEditor = True
    	excelApplication.Application.DefaultWebOptions.AlwaysSaveInDefaultEncoding = False
    	excelApplication.Application.DefaultWebOptions.SaveNewWebPagesAsWebArchives = True
      excelDocument.SaveAs outputFile, formatEnumeration
      excelDocument.Close False
      Call Zip(outputFile)
    Else 
    	excelDocument.SaveAs outputFile, formatEnumeration
      excelDocument.Close False
    End If

    ' Close the source document.
    
    If Err <> 0 Then
        WScript.Quit -3
    End If
    On Error GoTo 0

    ' Signal that the conversion was successful.
    WScript.Quit 2

  Else

    ' Files does not exist, could not convert
    WScript.Quit -4

  End If

End Function

' Execute the script.
Call ConvertFile( WScript.Arguments.Unnamed.Item(0), WScript.Arguments.Unnamed.Item(1), CInt(WScript.Arguments.Unnamed.Item(2)) )

그리고 나서 Maven Install 을 해주시면

기본 Maven 의 라이브러리 설치 임시 폴더는 c:\user\username\.m2 폴더에 설치가 되고 해당 라이브러리 적용 되게 됩니다.

그리고 나서 stand alone 서버를 mvn package -P extras  로 해주시면 해당 소스가 적용 됩니다.

그리고 나서 테스트 해보면

일단 서버 프로그램 실행 해준뒤에

클라인언트에서

public class Main {
	public static final String SAMPLE_XLSX_FILE_PATH = "./sample-xlsx-file.xlsx";

	public static void main(String[] args) throws InterruptedException, ExecutionException, IOException  {
		// TODO Auto-generated method stub
			File wordFile = new File("TESTDCO.xlsx"), target = new File("test1.zip");
		   
		    
	        RemoteConverter.Builder builder = RemoteConverter.builder()
	        		.baseFolder(new File("test"))
	        		.requestTimeout(3600, TimeUnit.SECONDS)
	        		.baseUri("http://127.0.0.1:9998");
	        IConverter converter = builder.build();
	       
		    Boolean conversion = converter
                    .convert(wordFile).as(DocumentType.MS_EXCEL)
                    .to(target).as(DocumentType.HTML)
                    .execute();
		    System.out.println("test");
		
	}

}

소스로 테스트 해주면

위와 같이 압축 파일을 전송 받게 되며

이렇게 2개의 파일이 압축 되어 있으므로 해당 파일을 웹서버에 올리면

excel이 html 형식으로 보기 좋게 컨버팅 되어 사용 할수 있습니다.