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.
93 lines
2.9 KiB
Go
93 lines
2.9 KiB
Go
// Copyright (c) 2015-present Mattermost, Inc. All Rights Reserved.
|
|
// See LICENSE.txt for license information.
|
|
|
|
package docextractor
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/require"
|
|
|
|
"github.com/hanzoteam/server/server/v8/channels/utils/testutils"
|
|
)
|
|
|
|
func TestPdfEmptyFile(t *testing.T) {
|
|
extractor := pdfExtractor{}
|
|
_, err := extractor.Extract(context.Background(), "test.pdf", bytes.NewReader([]byte{}), 0)
|
|
require.Error(t, err)
|
|
}
|
|
|
|
func TestPdfFile(t *testing.T) {
|
|
extractor := pdfExtractor{}
|
|
contentText := "\nThis is a simple document that contains some text."
|
|
content, err := testutils.ReadTestFile("sample-doc.pdf")
|
|
require.NoError(t, err)
|
|
extractedText, err := extractor.Extract(context.Background(), "sample-doc.pdf", bytes.NewReader(content), 0)
|
|
require.NoError(t, err)
|
|
require.Equal(t, contentText, extractedText)
|
|
}
|
|
|
|
func TestPdfDeeplyNestedObjects(t *testing.T) {
|
|
// Test for MM-63434
|
|
var buf bytes.Buffer
|
|
buf.WriteString("%PDF-1.0\n")
|
|
for range 10_000 {
|
|
buf.WriteString("0\n0\nobj\n")
|
|
}
|
|
buf.WriteString("startxref\n0\n%%EOF\n")
|
|
|
|
extractor := pdfExtractor{}
|
|
text, err := extractor.Extract(context.Background(), "excessive-nests.pdf", bytes.NewReader(buf.Bytes()), 0)
|
|
require.Error(t, err)
|
|
require.Empty(t, text)
|
|
}
|
|
|
|
func TestWrongPdfFile(t *testing.T) {
|
|
extractor := pdfExtractor{}
|
|
content, err := testutils.ReadTestFile("sample-doc.docx")
|
|
require.NoError(t, err)
|
|
_, err = extractor.Extract(context.Background(), "sample-doc.pdf", bytes.NewReader(content), 0)
|
|
require.Error(t, err)
|
|
}
|
|
|
|
func TestPdfCancelledContext(t *testing.T) {
|
|
extractor := pdfExtractor{}
|
|
content, err := testutils.ReadTestFile("sample-doc.pdf")
|
|
require.NoError(t, err)
|
|
|
|
ctx, cancel := context.WithCancel(context.Background())
|
|
cancel()
|
|
|
|
_, err = extractor.Extract(ctx, "sample-doc.pdf", bytes.NewReader(content), 0)
|
|
require.ErrorIs(t, err, context.Canceled)
|
|
}
|
|
|
|
func TestPdfMaxFileSize(t *testing.T) {
|
|
extractor := pdfExtractor{}
|
|
content, err := testutils.ReadTestFile("sample-doc.pdf")
|
|
require.NoError(t, err)
|
|
require.Greater(t, len(content), 16, "fixture must be larger than the tight limit under test")
|
|
|
|
t.Run("a zero limit means unlimited and extracts the content", func(t *testing.T) {
|
|
text, err := extractor.Extract(context.Background(), "sample-doc.pdf", bytes.NewReader(content), 0)
|
|
require.NoError(t, err)
|
|
require.Contains(t, text, "simple")
|
|
})
|
|
|
|
t.Run("a generous limit extracts the content", func(t *testing.T) {
|
|
text, err := extractor.Extract(context.Background(), "sample-doc.pdf", bytes.NewReader(content), 10*1024*1024)
|
|
require.NoError(t, err)
|
|
require.Contains(t, text, "simple")
|
|
})
|
|
|
|
t.Run("a tight limit prevents extraction", func(t *testing.T) {
|
|
// The reader errors once it reads past the limit, so io.Copy to the
|
|
// temp file fails and no text is extracted.
|
|
text, err := extractor.Extract(context.Background(), "sample-doc.pdf", bytes.NewReader(content), 16)
|
|
require.Error(t, err)
|
|
require.Empty(t, text)
|
|
})
|
|
}
|