mirror of
https://github.com/hanzoai/team.git
synced 2026-09-30 01:57:35 +00:00
zeekay
8feb24ea1f
The server module named github.com/hanzoai/team/server/v8 — a path that resolves to the retired workspace's repository, not this one — while server/public still published github.com/mattermost/mattermost/server/public. Both are github.com/hanzoteam/server/... now, which is where this code actually lives. That second half is what made the binary unbootable. Upstream's public path stayed claimed by upstream, mattermost-plugin-ai imported it, and the build linked public/model twice; public/plugin's gob.Register then ran twice under one name and panicked at init, before main. Reverting the rename traded the brand for a working binary. Rebranding the plugin alongside it needs no such trade: the agents fork is github.com/hanzoteam/agents/v2 against our public module, so no module named mattermost/mattermost is in the graph at all. Measured: `go list -deps ./cmd/mattermost` names exactly one public/model, and it is ours.
73 lines
1.6 KiB
Go
73 lines
1.6 KiB
Go
// Copyright (c) 2015-present Mattermost, Inc. All Rights Reserved.
|
|
// See LICENSE.txt for license information.
|
|
|
|
package docextractor
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"os"
|
|
"path"
|
|
"strings"
|
|
|
|
"github.com/mattermost/pdf"
|
|
|
|
"github.com/hanzoteam/server/server/v8/channels/utils"
|
|
)
|
|
|
|
type pdfExtractor struct{}
|
|
|
|
func (pe *pdfExtractor) Name() string {
|
|
return "pdfExtractor"
|
|
}
|
|
|
|
func (pe *pdfExtractor) Match(filename string) bool {
|
|
supportedExtensions := map[string]bool{
|
|
"pdf": true,
|
|
}
|
|
extension := strings.TrimPrefix(path.Ext(filename), ".")
|
|
return supportedExtensions[extension]
|
|
}
|
|
|
|
func (pe *pdfExtractor) Extract(ctx context.Context, filename string, r io.ReadSeeker, maxFileSize int64) (out string, outErr error) {
|
|
defer func() {
|
|
if r := recover(); r != nil {
|
|
out = ""
|
|
outErr = errors.New("error extracting pdf text")
|
|
}
|
|
}()
|
|
f, err := os.CreateTemp(os.TempDir(), "pdflib")
|
|
if err != nil {
|
|
return "", fmt.Errorf("error creating temporary file: %v", err)
|
|
}
|
|
defer f.Close()
|
|
defer os.Remove(f.Name())
|
|
|
|
// Bound how much data is copied to disk so a small upload cannot expand
|
|
// into an unbounded amount of temporary storage.
|
|
var src io.Reader = r
|
|
if maxFileSize > 0 {
|
|
src = utils.NewLimitedReaderWithError(r, maxFileSize)
|
|
}
|
|
size, err := io.Copy(f, src)
|
|
if err != nil {
|
|
return "", fmt.Errorf("error copying data into temporary file: %v", err)
|
|
}
|
|
|
|
reader, err := pdf.NewReader(f, size)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
|
|
var buf bytes.Buffer
|
|
b, err := reader.GetPlainText(ctx)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
buf.ReadFrom(b)
|
|
return buf.String(), nil
|
|
}
|