mirror of
https://github.com/go-gitea/gitea.git
synced 2026-09-25 06:03:40 +09:00
72243bead7
The bleve path token filter added in https://github.com/go-gitea/gitea/pull/32210 never generated the full path of a file, so searching a file by its path (e.g. `potato/ham`) found nothing. It also gave the path tokens made-up offsets instead of their position in the path. The filter is replaced by a tokenizer that emits the raw path suffixes starting at each segment and word (`potato/ham.md`, `ham.md`). Paths below the root now match too, as do names containing `-` or spaces and dotfiles. An exact file name also ranks above files inside a directory with the same name. --------- Co-authored-by: silverwind <me@silverwind.io> Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
64 lines
1.8 KiB
Go
64 lines
1.8 KiB
Go
// Copyright 2026 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package bleve
|
|
|
|
import (
|
|
"testing"
|
|
"time"
|
|
|
|
"gitea.dev/models/db"
|
|
"gitea.dev/modules/indexer/code/internal"
|
|
inner_bleve "gitea.dev/modules/indexer/internal/bleve"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestBleveIndexerTokenFilter(t *testing.T) {
|
|
dir := t.TempDir()
|
|
indexer := NewIndexer(dir)
|
|
defer indexer.Close()
|
|
|
|
_, err := indexer.Init(t.Context())
|
|
require.NoError(t, err)
|
|
|
|
batch := inner_bleve.NewFlushingBatch(indexer.inner.Indexer, maxBatchSize)
|
|
batch.Index("2", &RepoIndexerData{RepoID: 2, Filename: ".sub-dir/.sub-filename", Content: "mDNS.port2=12345", UpdatedAt: time.Now()})
|
|
batch.Flush()
|
|
|
|
testCases := []struct {
|
|
keyword string
|
|
expectedIDs []int64
|
|
}{
|
|
{keyword: "12345", expectedIDs: []int64{2}},
|
|
{keyword: "DNS", expectedIDs: []int64{}},
|
|
{keyword: "mdns", expectedIDs: []int64{2}},
|
|
{keyword: "port", expectedIDs: []int64{2}},
|
|
{keyword: "port2", expectedIDs: []int64{2}},
|
|
{keyword: ".sub-dir", expectedIDs: []int64{2}},
|
|
{keyword: "sub-file", expectedIDs: []int64{2}}, // prefix matching? not sure whether this behavior is wanted
|
|
{keyword: "filename", expectedIDs: []int64{2}},
|
|
{keyword: "name", expectedIDs: []int64{}},
|
|
}
|
|
|
|
for _, testCase := range testCases {
|
|
t.Run(testCase.keyword, func(t *testing.T) {
|
|
_, results, _, err := indexer.Search(t.Context(), &internal.SearchOptions{
|
|
Paginator: &db.ListOptions{Page: 1, PageSize: 1},
|
|
Keyword: testCase.keyword,
|
|
})
|
|
require.NoError(t, err)
|
|
assert.ElementsMatch(t, testCase.expectedIDs, searchResultIDs(results))
|
|
})
|
|
}
|
|
}
|
|
|
|
func searchResultIDs(result []*internal.SearchResult) []int64 {
|
|
ids := make([]int64, 0, len(result))
|
|
for _, hit := range result {
|
|
ids = append(ids, hit.RepoID)
|
|
}
|
|
return ids
|
|
}
|