asyncBatchAnnotateFiles filename output concatenates "output-x-to-x.json"

[baslentfert]

Environment details

• OS: windows 10
• Node.js version: v9.2.0
• npm version:6.5.0
• @google-cloud/vision version: ^0.23.0

Steps to reproduce

function processFilename(fileName) {
// Path to PDF file within bucket

//  const gcsSourceUri = `gs://${bucketName}/pdfs/${fileName}`;
let gcsSourceUri = `gs://${bucketName}/${fileName}`;
let gcsDestinationUri = `gs://${bucketName}/${fileName}.json`;

let inputConfig = {
    // Supported mime_types are: 'application/pdf' and 'image/tiff'
    mimeType: 'application/pdf',
    gcsSource: {
        uri: gcsSourceUri,
    },
};
let outputConfig = {
    gcsDestination: {
        uri: gcsDestinationUri,
    },
};
//    let features = [{ type: 'DOCUMENT_TEXT_DETECTION', model: "builtin/latest" }];
let features = [{ type: 'DOCUMENT_TEXT_DETECTION' }];
let request = {
    requests: [{
        inputConfig: inputConfig,
        features: features,
        outputConfig: outputConfig,
    }, ],
};

client
    .asyncBatchAnnotateFiles(request)
    .then(results => {
        const operation = results[0];
        // Get a Promise representation of the final result of the job
        operation
            .promise()
            .then(filesResponse => {

                //                    console.log(JSON.stringify(filesResponse));

                let destinationUri = filesResponse[0].responses[0].outputConfig.gcsDestination.uri;
                console.log('Json saved to: ' + destinationUri);

                //          console.log(filesResponse[0].responses);
            })
            .catch(function(error) {
                console.log(error);
            });
    })
    .catch(function(error) {
        console.log(error);
    });

}

for example the input filename:
aabb.pdf
then the output will be:
aabb.pdf.jsonoutput-1-to-1.json

(if the pdf contained 1 page)

Thanks!

[baslentfert]

i forgot to mention i used
const vision = require('@google-cloud/vision').v1p2beta1;

wehn i use:
const vision = require('@google-cloud/vision').v1;

i still get the extra filename "add on" jsonoutput-1-to-1.json
but i am not shure if it is "jsonoutput-1-to-1.json" of "output-1-to-1.json" that is added to the given filename.

i made a screenshot:
https://www.lentfert.net/google.cloud-example.jpg

in the code above i do not add the extra string "jsonoutput-1-to-1.json":
let gcsSourceUri = gs://${bucketName}/${fileName};
let gcsDestinationUri = gs://${bucketName}/${fileName}.json;

[nnegrey]

Ah, looks like that code needs to be updated.
Should be:

const gcsDestinationUri = `gs://${bucketName}/

And the output-1-to-1.json is expected output.

[nnegrey]

#300

[mickdekkers]

@nnegrey just a heads up, the docs here still state that GcsDestination can represent a single file.

Also, I'm not sure if this is the best place to ask, but what would be the best way to determine the final output location of the JSON file(s)? The AsyncBatchAnnotateFilesResponse only seems to contain the OutputConfig you pass to asyncBatchAnnotateFiles (so just the gs://${bucketName}/, no gs://${bucketName}/output-x-to-x.json). Is scanning the bucket with the Storage API's Bucket.getFiles method the recommended way?

[nnegrey]

Ah. Good catch, let me look into that. I wonder if you have to specify the batch_size as 1 in the OutputConfig to use a filename.

Yea, because it may end up splitting your output to multiple files due to size, so you'll have to check what's created. To simplify that check, It's recommended to use a prefix gs://$bucketName}/prefix/ so that you know only your output will be there. Less searching that way.