Question posted in
Some documentation to get you started can be found here.

How to convert .docx to .txt or get text from docx file in android? – Apache

I am downloading .docx file from OneDrive using OneDrive sdk. It downloading successful but I need to convert it in .txt format and I can’t do it.

Does anyone have an idea how to convert or get a text from .docx file in android?

I can get InputStream of .docx file.

here is the code to download a file from OneDrive

InputStream inputStream = iOneDriveClient.getDrive().getItems(fileID).getContent().buildRequest().get();
OutputStream out = new FileOutputStream(mPath);
int read;
byte[] bytes = new byte[1024];
while ((read = inputStream.read(bytes)) != -1) {
    out.write(bytes, 0, read);
}
out.flush();
out.close();
inputStream.close();

this code is already in doInBackground

EDIT

I have added Apache POI library but I can not compile it

I am getting conflicts on lots of files

here is my build.gradle

apply plugin: 'com.android.application'
apply plugin: 'io.fabric'

android {
    compileSdkVersion myCompileSdkVersion
    compileOptions.encoding = 'windows-1251'

    defaultConfig {
        applicationId "com.my.app"
        versionCode 8
        versionName "1.0.5"

        minSdkVersion myMinSdkVersion
        targetSdkVersion myTargetSdkVersion
        vectorDrawables.useSupportLibrary = true

        multiDexEnabled true
        testInstrumentationRunner "androidx.test.runner.AndroidJUnitRunner"

        ndk {
            moduleName "app"
            abiFilters "armeabi-v7a"/*, "x86"*/

        }
    }

    // Specifies one flavor dimension.
    flavorDimensions "common"
    productFlavors {
        live {
            dimension "common"
            buildConfigField 'boolean', 'IS_CUSOTM_APP', 'false'
        }

        custom {
            dimension "common"
            buildConfigField 'boolean', 'IS_CUSOTM_APP', 'true'
        }
    }

    sourceSets.main {
        res.srcDirs = ['src/main/res']
        jni.srcDirs = []
        jniLibs.srcDirs = ['src/main/jni']

    }

    task ndkBuild(type: Exec, description: 'Compile JNI source via NDK') {
        def ndkDir = android.ndkDirectory
        commandLine "$ndkDir/ndk-build",
                'NDK_PROJECT_PATH=build/intermediates/ndk',
                'NDK_LIBS_OUT=src/main/jniLibs',
                'APP_BUILD_SCRIPT=src/main/jni/Android.mk',
                'NDK_APPLICATION_MK=src/main/jni/Application.mk'
    }

    tasks.withType(JavaCompile) {
        compileTask -> compileTask.dependsOn ndkBuild
    }

    buildTypes {
        release {
            minifyEnabled false
            proguardFiles getDefaultProguardFile('proguard-android.txt'), 'proguard-rules.pro'

            lintOptions {
                checkReleaseBuilds false
                // Or, if you prefer, you can continue to check for errors in release builds,
                // but continue the build even when errors are found:
                abortOnError false
                //disable 'MissingTranslation'

                checkReleaseBuilds false
                // Or, if you prefer, you can continue to check for errors in release builds,
                // but continue the build even when errors are found:
                abortOnError false
            }
            debug {
                debuggable = true
                jniDebuggable true

            }
            signingConfig signingConfigs.config
        }
    }

    dexOptions {
        preDexLibraries false
        javaMaxHeapSize "4g"
    }

    packagingOptions {
        exclude 'META-INF/DEPENDENCIES'
        exclude 'META-INF/NOTICE'
        exclude 'META-INF/LICENSE'
        exclude 'META-INF/LICENSE.txt'
        exclude 'META-INF/NOTICE.txt'
    }

    configurations.all {
        resolutionStrategy.force 'com.google.code.findbugs:jsr305:1.3.9'
    }


    externalNativeBuild {

        // Encapsulates your CMake build configurations.
        ndkBuild {
            // Provides a relative path to your to the Android.mk build script.
            path "src/main/jni/Android.mk"
        }
    }

    dataBinding {
        enabled = true
    }


    compileOptions {
        sourceCompatibility JavaVersion.VERSION_1_8
        targetCompatibility JavaVersion.VERSION_1_8
    }
}

dependencies {
    implementation 'androidx.constraintlayout:constraintlayout:1.1.3'

    implementation 'com.google.android.material:material:1.0.0-rc01'

    implementation "commons-io:commons-io:2.4"
    implementation "org.apache.commons:commons-lang3:3.5"

    implementation 'com.jakewharton:butterknife:10.1.0'
    annotationProcessor 'com.jakewharton:butterknife-compiler:10.1.0'
    implementation "com.google.code.gson:gson:2.8.0"

    implementation fileTree(include: ['*.jar'], dir: 'libs')

    implementation('com.google.api-client:google-api-client-android:1.28.0') {
        exclude group: 'org.apache.httpcomponents'
    }

    implementation('com.google.apis:google-api-services-drive:v3-rev136-1.25.0') {
        exclude group: 'org.apache.httpcomponents'
    }

    implementation 'androidx.multidex:multidex:2.0.1'
    //main libs
    implementation 'androidx.cardview:cardview:1.0.0'

    //google
    implementation 'com.google.android.gms:play-services-drive:17.0.0'
    implementation 'com.google.android.gms:play-services-auth:17.0.0'
    implementation 'com.google.firebase:firebase-core:17.0.0'
    implementation 'com.google.code.gson:gson:2.8.5'
    implementation 'com.crashlytics.sdk.android:crashlytics:2.10.1'
    implementation 'com.google.android.exoplayer:exoplayer-core:2.10.0'

    //for M+ permission handling
    implementation 'pub.devrel:easypermissions:1.2.0'

    //for downloading zip
    implementation 'com.mani:ThinDownloadManager:1.4.0'

    //for bottomseet dialog
    implementation 'com.orhanobut:dialogplus:1.11@aar'

    //for crash report
    implementation 'me.drakeet.library:crashwoodpecker:2.1.1'
    testImplementation 'junit:junit:4.13-beta-2'

    // bouncy castle
    implementation 'org.bouncycastle:bcprov-jdk15on:1.61'

    //for speech to text
    implementation 'net.gotev:speech:1.3.1'

    // Add Dagger dependencies
    implementation 'com.google.dagger:dagger:2.16'
    annotationProcessor 'com.google.dagger:dagger-compiler:2.16'

    // Add Dagger Android dependencies
    implementation 'com.google.dagger:dagger-android:2.16'
    implementation 'com.google.dagger:dagger-android-support:2.16'
    // if you use the support libraries
    annotationProcessor 'com.google.dagger:dagger-android-processor:2.16'

    // Add RXAndroid
    implementation 'io.reactivex.rxjava2:rxandroid:2.1.1'
    implementation 'io.reactivex.rxjava2:rxjava:2.2.6'
    implementation 'com.squareup.okhttp3:logging-interceptor:3.9.0'

    // LiveData Support
    implementation 'androidx.lifecycle:lifecycle-extensions:2.0.0'
    annotationProcessor 'androidx.lifecycle:lifecycle-compiler:2.0.0'

    //Retrofit for API Call
    implementation 'com.squareup.retrofit2:retrofit:2.3.0'
    implementation 'com.squareup.retrofit2:converter-gson:2.3.0'
    implementation 'com.squareup.retrofit2:adapter-rxjava2:2.3.0'

    implementation 'id.zelory:compressor:2.1.0'
    implementation 'androidx.exifinterface:exifinterface:1.1.0-beta01'

    //one drive
    implementation('com.onedrive.sdk:onedrive-sdk-android:1.3+') {
        transitive = false
    }

    // Include supported authentication methods for your application
    implementation 'com.microsoft.services.msa:msa-auth:0.8.+'
    implementation 'com.microsoft.aad:adal:1.1.+'

    implementation 'org.apache.tika:tika-parsers:1.21'
}
apply plugin: 'com.google.gms.google-services'
apply from: "../artifacts.gradle"

conflicts error is

Duplicate class com.fasterxml.jackson.core.Base64Variant found in modules docx4j-6.1.1-SNAPSHOT-shaded.jar (docx4j-6.1.1-SNAPSHOT-shaded.jar) and jackson-core-2.9.6.jar (com.fasterxml.jackson.core:jackson-core:2.9.6)

Tags:

2

Answers


  1. 0

    You can use Apache POI

    From Docs:

    For .doc files from Word 97 – Word 2003, in scratchpad there is org.apache.poi.hwpf.extractor.WordExtractor, which will return text for your document.

    Here is an example from Docs:

    FileInputStream fis = new FileInputStream(inputFile);
POIFSFileSystem fileSystem = new POIFSFileSystem(fis);
// Firstly, get an extractor for the Workbook
POIOLE2TextExtractor oleTextExtractor = 
   ExtractorFactory.createExtractor(fileSystem);
// Then a List of extractors for any embedded Excel, Word, PowerPoint
// or Visio objects embedded into it.
POITextExtractor[] embeddedExtractors =
   ExtractorFactory.getEmbededDocsTextExtractors(oleTextExtractor);
for (POITextExtractor textExtractor : embeddedExtractors) {
   // If the embedded object was an Excel spreadsheet.
   if (textExtractor instanceof ExcelExtractor) {
      ExcelExtractor excelExtractor = (ExcelExtractor) textExtractor;
      System.out.println(excelExtractor.getText());
   }
   // A Word Document
   else if (textExtractor instanceof WordExtractor) {
      WordExtractor wordExtractor = (WordExtractor) textExtractor;
      String[] paragraphText = wordExtractor.getParagraphText();
      for (String paragraph : paragraphText) {
         System.out.println(paragraph);
      }
      // Display the document's header and footer text
      System.out.println("Footer text: " + wordExtractor.getFooterText());
      System.out.println("Header text: " + wordExtractor.getHeaderText());
   }
   // PowerPoint Presentation.
   else if (textExtractor instanceof PowerPointExtractor) {
      PowerPointExtractor powerPointExtractor =
         (PowerPointExtractor) textExtractor;
      System.out.println("Text: " + powerPointExtractor.getText());
      System.out.println("Notes: " + powerPointExtractor.getNotes());
   }

}
    Login or Signup to reply.
  2. 0

    After trying to work with Apache POI library to extract Text from .docx, I wasted my whole weekend. But could not believe how easy it was with Mammoth library.

    Add it to dependency

    implementation 'org.zwobble.mammoth:mammoth:1.4.2'

    here is code in on result activity

     if (resultCode == Activity.RESULT_OK) {
                val converter = DocumentConverter()
                val uri = data?.data;
                val result: Result<String>? = converter.extractRawText(contentResolver.openInputStream(uri!!))
                val text_extracted = result!!.getValue()
                Log.e("Docx etracted TeXT:", text_extracted)
                select.text= text_extracted
            }

    hope it helped

    Login or Signup to reply.
Please signup or login to give your own answer.

Back To Top
Search