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.
70 lines
1.8 KiB
Go
70 lines
1.8 KiB
Go
// Copyright (c) 2015-present Mattermost, Inc. All Rights Reserved.
|
|
// See LICENSE.txt for license information.
|
|
|
|
package docextractor
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"io"
|
|
"path"
|
|
"strings"
|
|
|
|
"code.sajari.com/docconv/v2"
|
|
|
|
"github.com/hanzoteam/server/server/v8/channels/utils"
|
|
)
|
|
|
|
type documentExtractor struct{}
|
|
|
|
var doconvConverterByExtensions = map[string]func(io.Reader) (string, map[string]string, error){
|
|
"doc": docconv.ConvertDoc,
|
|
"docx": docconv.ConvertDocx,
|
|
"pptx": docconv.ConvertPptx,
|
|
"odt": docconv.ConvertODT,
|
|
"html": func(r io.Reader) (string, map[string]string, error) { return docconv.ConvertHTML(r, true) },
|
|
// Temporarily disabled to avoid crashes on malicious .pages files
|
|
// "pages": docconv.ConvertPages,
|
|
"rtf": docconv.ConvertRTF,
|
|
"pdf": docconv.ConvertPDF,
|
|
}
|
|
|
|
func (de *documentExtractor) Name() string {
|
|
return "documentExtractor"
|
|
}
|
|
|
|
func (de *documentExtractor) Match(filename string) bool {
|
|
extension := strings.TrimPrefix(path.Ext(filename), ".")
|
|
_, ok := doconvConverterByExtensions[extension]
|
|
return ok
|
|
}
|
|
|
|
func (de *documentExtractor) Extract(_ 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 document text")
|
|
}
|
|
}()
|
|
|
|
extension := strings.TrimPrefix(path.Ext(filename), ".")
|
|
converter, ok := doconvConverterByExtensions[extension]
|
|
if !ok {
|
|
return "", errors.New("unknown converter")
|
|
}
|
|
|
|
// Bound how much data the converter is allowed to read so a small upload
|
|
// cannot expand into an unbounded amount of in-memory work.
|
|
var reader io.Reader = r
|
|
if maxFileSize > 0 {
|
|
reader = utils.NewLimitedReaderWithError(r, maxFileSize)
|
|
}
|
|
|
|
text, _, err := converter(reader)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
|
|
return text, nil
|
|
}
|