javascript - 为什么使用 API 上传 Word OfficeJS PDF 文档会保存一个空的 PDF 文档

Question

我使用了 Microsoft 提供的以下 JS 代码来将文档保存为 PDF:

Office.context.document.getFileAsync(Office.FileType.Pdf,
        function(result) {
            if (result.status == "succeeded") {
                var myFile = result.value;
                var sliceCount = myFile.sliceCount;
                var slicesReceived = 0, gotAllSlices = true, docdataSlices = [];
                console.log("File size:" + myFile.size + " #Slices: " + sliceCount);
                // Now, you can call getSliceAsync to download the files,
                // as described in the previous code segment (compressed format).
                // Get the file slices.
                getSliceAsync(myFile, 0, sliceCount, gotAllSlices, docdataSlices, slicesReceived);
                myFile.closeAsync();
            }
            else {
                console.log("Error:", result.error.message);
            }
        }
    );

function getSliceAsync(file, nextSlice, sliceCount, gotAllSlices, docdataSlices, slicesReceived) {
    file.getSliceAsync(nextSlice, function (sliceResult) {
        if (sliceResult.status == "succeeded") {
            if (!gotAllSlices) { // Failed to get all slices, no need to continue.
                return;
            }

            // Got one slice, store it in a temporary array.
            // (Or you can do something else, such as
            // send it to a third-party server.)
            docdataSlices[sliceResult.value.index] = sliceResult.value.data;
            if (++slicesReceived == sliceCount) {
              // All slices have been received.
              file.closeAsync();
              onGotAllSlices(docdataSlices);
            }
            else {
                getSliceAsync(file, ++nextSlice, sliceCount, gotAllSlices, docdataSlices, slicesReceived);
            }
        }
            else {
                gotAllSlices = false;
                file.closeAsync();
                console.log("getSliceAsync Error:", sliceResult.error.message);
            }
    });
}

function onGotAllSlices(docdataSlices) {
    var docdata = [];
    for (var i = 0; i < docdataSlices.length; i++) {
        docdata = docdata.concat(docdataSlices[i]);
    }

    var fileContent = new String();
    for (var j = 0; j < docdata.length; j++) {
        fileContent += String.fromCharCode(docdata[j]);
    }

    console.log('Final PDF content is received and stored in fileContent.');


    send_file_content(fileContent);
}

function send_file_content(word_doc) {
    var formData = new FormData();
    var blob = new Blob([word_doc], { type: "application/pdf"});
    formData.append("file", blob);
    $.ajax({
        type: 'POST',
        url: 'My-upload-URL',
        data: formData,
        processData: false,
        contentType: false
    }).done(function(data) {
        console.log('* Word Document successfully uploaded: ', data.filepath);
    });
}

我很确定服务器端没问题，因为我已经上传了无数的 PDF 文档并且它按预期工作，但是当我通过上面的 JS 代码上传 Word PDF 文档时，我得到了一个服务器端的空白页。如果 word 文档包含 3 页，那么我将在服务器端获得 3 个空白页作为 PDF 文件。

Answer 1

Microsoft 文档 带有charCodeAt 函数，它会破坏数据并生成一个空白的 PDF 文档。

我没有使用那个函数，而是直接在字节数组上使用了 Uint8Array:

var blob = new Blob([new Uint8Array(myFinalByteArray)], { type: 'application/pdf' });

然后使用 FormData 将 Blob 上传到远程服务器。这种方法解决了这个问题。