[feature] support processing of (many) more media types (#3090)

* initial work replacing our media decoding / encoding pipeline with ffprobe + ffmpeg

* specify the video codec to use when generating static image from emoji

* update go-storage library (fixes incompatibility after updating go-iotools)

* maintain image aspect ratio when generating a thumbnail for it

* update readme to show go-ffmpreg

* fix a bunch of media tests, move filesize checking to callers of media manager for more flexibility

* remove extra debug from error message

* fix up incorrect function signatures

* update PutFile to just use regular file copy, as changes are file is on separate partition

* fix remaining tests, remove some unneeded tests now we're working with ffmpeg/ffprobe

* update more tests, add more code comments

* add utilities to generate processed emoji / media outputs

* fix remaining tests

* add test for opus media file, add license header to utility cmds

* limit the number of concurrently available ffmpeg / ffprobe instances

* reduce number of instances

* further reduce number of instances

* fix envparsing test with configuration variables

* update docs and configuration with new media-{local,remote}-max-size variables
This commit is contained in:
kim 2024-07-12 09:39:47 +00:00 committed by GitHub
commit cde2fb6244
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
376 changed files with 8026 additions and 54091 deletions

View file

@ -23,30 +23,42 @@ import (
"net/http"
"net/url"
"codeberg.org/gruf/go-bytesize"
"codeberg.org/gruf/go-iotools"
"github.com/superseriousbusiness/gotosocial/internal/gtserror"
)
func (t *transport) DereferenceMedia(ctx context.Context, iri *url.URL) (io.ReadCloser, int64, error) {
func (t *transport) DereferenceMedia(ctx context.Context, iri *url.URL, maxsz int64) (io.ReadCloser, error) {
// Build IRI just once
iriStr := iri.String()
// Prepare HTTP request to this media's IRI
req, err := http.NewRequestWithContext(ctx, "GET", iriStr, nil)
if err != nil {
return nil, 0, err
return nil, err
}
req.Header.Add("Accept", "*/*") // we don't know what kind of media we're going to get here
// Perform the HTTP request
rsp, err := t.GET(req)
if err != nil {
return nil, 0, err
return nil, err
}
// Check for an expected status code
if rsp.StatusCode != http.StatusOK {
return nil, 0, gtserror.NewFromResponse(rsp)
return nil, gtserror.NewFromResponse(rsp)
}
return rsp.Body, rsp.ContentLength, nil
// Check media within size limit.
if rsp.ContentLength > maxsz {
_ = rsp.Body.Close() // close early.
sz := bytesize.Size(maxsz) // nicer log format
return nil, gtserror.Newf("media body exceeds max size %s", sz)
}
// Update response body with maximum supported media size.
rsp.Body, _, _ = iotools.UpdateReadCloserLimit(rsp.Body, maxsz)
return rsp.Body, nil
}

View file

@ -67,8 +67,8 @@ type Transport interface {
// Dereference fetches the ActivityStreams object located at this IRI with a GET request.
Dereference(ctx context.Context, iri *url.URL) (*http.Response, error)
// DereferenceMedia fetches the given media attachment IRI, returning the reader and filesize.
DereferenceMedia(ctx context.Context, iri *url.URL) (io.ReadCloser, int64, error)
// DereferenceMedia fetches the given media attachment IRI, returning the reader limited to given max.
DereferenceMedia(ctx context.Context, iri *url.URL, maxsz int64) (io.ReadCloser, error)
// DereferenceInstance dereferences remote instance information, first by checking /api/v1/instance, and then by checking /.well-known/nodeinfo.
DereferenceInstance(ctx context.Context, iri *url.URL) (*gtsmodel.Instance, error)