mirror of
https://github.com/hanzoai/team.git
synced 2026-09-30 01:57:35 +00:00
JG HeithcockandGitHub
74f5321056
* [MM-63434] Use forked PDF library with parsing depth limit Replace github.com/ledongthuc/pdf with a fork that limits object nesting depth during parsing. Add test coverage. * Reverting incorrect merge that lost the change to msgpack The error was in merge https://github.com/mattermost/mattermost/commit/64bdff88d853e030d6e0f243cf21370a78dde6ae
53 lines
1.4 KiB
Go
53 lines
1.4 KiB
Go
// Copyright (c) 2015-present Mattermost, Inc. All Rights Reserved.
|
|
// See LICENSE.txt for license information.
|
|
|
|
package docextractor
|
|
|
|
import (
|
|
"bytes"
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/require"
|
|
|
|
"github.com/mattermost/mattermost/server/v8/channels/utils/testutils"
|
|
)
|
|
|
|
func TestPdfEmptyFile(t *testing.T) {
|
|
extractor := pdfExtractor{}
|
|
_, err := extractor.Extract("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("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("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("sample-doc.pdf", bytes.NewReader(content), 0)
|
|
require.Error(t, err)
|
|
}
|