pdf.js/src/display/metadata.js
Jonas Jenwald cc3a6563ee Move the Metadata parsing to the worker-thread
The only reason, as far as I can tell, for parsing the Metadata on the main-thread is how it was originally implemented. When Metadata support was first implemented, it utilized the [`DOMParser`](https://developer.mozilla.org/en-US/docs/Web/API/DOMParser) which isn't available in workers.
Today, with the custom XML-parser being used, that's no longer an issue and it seems reasonable to move the Metadata parsing to the worker-thread[1], since that's where all parsing should happen (for performance reasons).

Based on these changes, we'll be able to reduce the now unnecessary duplication of the XML-parser (and related code) in both of the *built* `pdf.js`/`pdf.worker.js` files.

Finally, this patch changes the `_repair` method to use "Array + join" rather than string concatenation.

---
[1] This needed the previous patch, to enable sending of `Map`s between threads with workers disabled.
2021-02-17 13:12:01 +01:00

42 lines
1.0 KiB
JavaScript

/* Copyright 2012 Mozilla Foundation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import { objectFromEntries } from "../shared/util.js";
class Metadata {
constructor({ parsedData, rawData }) {
this._metadataMap = parsedData;
this._data = rawData;
}
getRaw() {
return this._data;
}
get(name) {
return this._metadataMap.get(name) ?? null;
}
getAll() {
return objectFromEntries(this._metadataMap);
}
has(name) {
return this._metadataMap.has(name);
}
}
export { Metadata };