mirror of
https://github.com/go-gitea/gitea.git
synced 2026-10-31 03:14:17 +09:00
1ebeade2c1
Code search now matches case-insensitive literal substrings like GitHub, in every script. Word tokenizers can't do this: the ES pattern dropped every non-ASCII word, and the `standard` tokenizer keeps `console.log` as one token. - Elasticsearch indexes positional trigrams, plus 1-2 grams for short terms - Bleve indexes distinct 1-3 grams as a candidate filter and verifies candidates against the content before paging, because phrase queries over trigrams are quadratic in repeated grams - Snippet offsets come from the original content, so `<em>` in sources and width-changing lowercase no longer misplace them - `search_mode=fuzzy` requests behave like Words, the UI never offered fuzzy for code search - The ES code indexer test now runs in CI, it was skipped before There are no UI changes. Both code indexes rebuild after upgrade. Fixes: https://github.com/go-gitea/gitea/issues/40027 Fixes: https://github.com/go-gitea/gitea/issues/16158 Fixes: https://github.com/go-gitea/gitea/issues/21359 --------- Co-authored-by: silverwind <me@silverwind.io> Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
73 lines
2.5 KiB
Go
73 lines
2.5 KiB
Go
// Copyright 2017 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package integration
|
|
|
|
import (
|
|
"net/http"
|
|
"testing"
|
|
|
|
repo_model "gitea.dev/models/repo"
|
|
"gitea.dev/modules/git"
|
|
code_indexer "gitea.dev/modules/indexer/code"
|
|
"gitea.dev/modules/setting"
|
|
"gitea.dev/modules/test"
|
|
"gitea.dev/tests"
|
|
|
|
"github.com/PuerkitoBio/goquery"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func resultFilenames(doc *HTMLDoc) []string {
|
|
filenameSelections := doc.doc.Find(".repository.search").Find(".repo-search-result").Find(".header").Find("span.file")
|
|
result := make([]string, filenameSelections.Length())
|
|
filenameSelections.Each(func(i int, selection *goquery.Selection) {
|
|
result[i] = selection.Text()
|
|
})
|
|
return result
|
|
}
|
|
|
|
func TestSearchRepo(t *testing.T) {
|
|
defer tests.PrepareTestEnv(t)()
|
|
|
|
repo, err := repo_model.GetRepositoryByOwnerAndName(t.Context(), "user2", "repo1")
|
|
assert.NoError(t, err)
|
|
|
|
code_indexer.UpdateRepoIndexer(repo)
|
|
|
|
testSearch(t, "/user2/repo1/search?q=Description&page=1", []string{"README.md"})
|
|
|
|
defer test.MockVariableValue(&setting.Indexer.IncludePatterns, setting.IndexerGlobFromString("**.txt"))()
|
|
defer test.MockVariableValue(&setting.Indexer.ExcludePatterns, setting.IndexerGlobFromString("**/y/**"))()
|
|
|
|
repo, err = repo_model.GetRepositoryByOwnerAndName(t.Context(), "user2", "glob")
|
|
require.NoError(t, err)
|
|
require.NoError(t, git.ForceFastImport(t.Context(), repo.CodeStorageRepo(), []git.FastImportCommit{{
|
|
Ref: "refs/heads/master",
|
|
Files: []git.FastImportFile{
|
|
{Path: "a.txt", Content: "file1 loren ipsum\n"},
|
|
{Path: "aaa.doc", Content: "file2 loren ipsum\n"},
|
|
{Path: "x/b.txt", Content: "file3\n"},
|
|
{Path: "x/y/a.txt", Content: "file4\n"},
|
|
{Path: "x/y/z/a.txt", Content: "file5\n"},
|
|
},
|
|
}}))
|
|
code_indexer.UpdateRepoIndexer(repo)
|
|
|
|
testSearch(t, "/user2/glob/search?q=loren&page=1", []string{"a.txt"})
|
|
testSearch(t, "/user2/glob/search?q=loren&page=1&t=match", []string{"a.txt"})
|
|
testSearch(t, "/user2/glob/search?q=file3&page=1", []string{"x/b.txt"})
|
|
testSearch(t, "/user2/glob/search?q=file3&page=1&t=match", []string{"x/b.txt"})
|
|
testSearch(t, "/user2/glob/search?q=file4&page=1&t=match", []string{})
|
|
testSearch(t, "/user2/glob/search?q=file5&page=1&t=match", []string{})
|
|
}
|
|
|
|
func testSearch(t *testing.T, url string, expected []string) {
|
|
t.Helper()
|
|
req := NewRequest(t, "GET", url)
|
|
resp := MakeRequest(t, req, http.StatusOK)
|
|
filenames := resultFilenames(NewHTMLParser(t, resp.Body))
|
|
assert.Equal(t, expected, filenames, "url=%s", url)
|
|
}
|