-
Notifications
You must be signed in to change notification settings - Fork 69
feat(OpusEncoder): add opus_decode/encode_float binding #193
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull request overview
This PR adds support for floating-point Opus encoding and decoding operations by introducing opus_encode_float and opus_decode_float bindings to the Node.js wrapper.
- Adds
encodeFloatanddecodeFloatmethods to OpusEncoder class - Allocates a new
float*buffer for float operations - Updates documentation with usage examples for float32 operations
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| src/node-opus.h | Adds outFloat member variable and declares EncodeFloat and DecodeFloat methods |
| src/node-opus.cc | Implements float encoding/decoding methods, initializes outFloat buffer in constructor, and registers new methods |
| README.md | Documents the new float32 encoding/decoding API with usage examples |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| if (this->outPcm) delete this->outPcm; | ||
| if (this->outFloat) delete this->outFloat; |
Copilot
AI
Dec 21, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Using delete on an array allocated with new[] is undefined behavior and can cause memory leaks or crashes. Since outFloat is allocated with new float[channels * MAX_FRAME_SIZE] on line 66, it should be deallocated with delete[] instead of delete. The same issue exists with outPcm on line 76.
| if (this->outPcm) delete this->outPcm; | |
| if (this->outFloat) delete this->outFloat; | |
| if (this->outPcm) delete[] this->outPcm; | |
| if (this->outFloat) delete[] this->outFloat; |
| int frameSize = buf.Length() / 4 / this->channels; | ||
|
|
||
| int compressedLength = opus_encode_float(this->encoder, pcm, frameSize, &(this->outOpus[0]), MAX_PACKET_SIZE); | ||
|
|
Copilot
AI
Dec 21, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Missing error handling for the return value of opus_encode_float. According to the Opus API documentation, opus_encode_float can return negative values on error (same error codes as opus_decode_float). This function should check if compressedLength < 0 and throw an appropriate error, similar to how DecodeFloat checks for negative return values on line 243. Without this check, negative error codes could be passed to Buffer::Copy causing undefined behavior.
| if (compressedLength < 0) { | |
| Napi::TypeError::New(env, getDecodeError(compressedLength)).ThrowAsJavaScriptException(); | |
| return env.Null(); | |
| } |
|
I see there are conflicts due to the recent code updates. I'll rebase and fix them shortly. |
|
Sorry, but I just realized it's 3:00 AM here. I'll fix it later. |
2c12350 to
0d687fe
Compare
|
Regarding the remaining points raised by copilot:
I'm ready to push fixes for them. Before I begin, I have some questions; For the two points mentioned above, should I fix the existing bug in this PR while I'm at it? Or would you prefer I only fix my new code and open a separate issue/PR for the existing one? |
Closes #171
Description
This PR adds bindings for
opus_decode_floatandopus_encode_floatto support floating-point operations.