mirror of
https://github.com/go-gitea/gitea.git
synced 2026-10-31 21:05:16 +00:00
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>
91 lines
3.6 KiB
Go
91 lines
3.6 KiB
Go
// Copyright 2024 The Gitea Authors. All rights reserved.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
package integration
|
|
|
|
import (
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
"testing"
|
|
|
|
repo_model "gitea.dev/models/repo"
|
|
"gitea.dev/models/unittest"
|
|
"gitea.dev/modules/git"
|
|
"gitea.dev/modules/setting"
|
|
"gitea.dev/modules/test"
|
|
"gitea.dev/routers"
|
|
"gitea.dev/routers/web"
|
|
"gitea.dev/tests"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestRepoDownloadArchive(t *testing.T) {
|
|
defer tests.PrepareTestEnv(t)()
|
|
defer test.MockVariableValue(&setting.EnableGzip, true)()
|
|
defer test.MockVariableValue(&web.GzipMinSize, 10)()
|
|
defer test.MockVariableValue(&testWebRoutes, routers.NormalRoutes())()
|
|
|
|
repo := unittest.AssertExistsAndLoadBean(t, &repo_model.Repository{ID: 1})
|
|
require.NoError(t, git.ForceFastImport(t.Context(), repo.CodeStorageRepo(), []git.FastImportCommit{{
|
|
Ref: "refs/heads/archive-test",
|
|
Files: []git.FastImportFile{
|
|
{Path: "a.txt", Content: "root text file\n"},
|
|
{Path: "aaa.doc", Content: "root document\n"},
|
|
{Path: "x/b.txt", Content: "nested text file\n"},
|
|
{Path: "x/y/a.txt", Content: "deeply nested text file\n"},
|
|
},
|
|
}}))
|
|
|
|
t.Run("NoDuplicateCompression", func(t *testing.T) {
|
|
req := NewRequest(t, "GET", "/user2/repo1/archive/master.zip")
|
|
req.Header.Set("Accept-Encoding", "gzip")
|
|
resp := MakeRequest(t, req, http.StatusOK)
|
|
bs, err := io.ReadAll(resp.Body)
|
|
assert.NoError(t, err)
|
|
assert.Empty(t, resp.Header().Get("Content-Encoding"))
|
|
assert.Len(t, bs, 320)
|
|
})
|
|
|
|
t.Run("Conditional", func(t *testing.T) {
|
|
defer test.MockVariableValue(&setting.Repository.StreamArchives, true)()
|
|
archiveURL := "/user2/repo1/archive/archive-test.tar.gz"
|
|
etag := MakeRequest(t, NewRequest(t, "GET", archiveURL), http.StatusOK).Header().Get("ETag")
|
|
assert.True(t, strings.HasPrefix(etag, `W/"`))
|
|
MakeRequest(t, NewRequest(t, "GET", archiveURL).SetHeader("If-None-Match", etag), http.StatusNotModified)
|
|
MakeRequest(t, NewRequest(t, "GET", archiveURL+"?path=aaa.doc").SetHeader("If-None-Match", etag), http.StatusOK)
|
|
assert.NotEqual(t, etag, MakeRequest(t, NewRequest(t, "GET", "/user2/repo1/archive/master.tar.gz"), http.StatusOK).Header().Get("ETag"))
|
|
|
|
restoreStreaming := test.MockVariableValue(&setting.Repository.StreamArchives, false)
|
|
MakeRequest(t, NewRequest(t, "GET", archiveURL).SetHeader("If-None-Match", etag), http.StatusOK)
|
|
restoreStreaming()
|
|
|
|
defer test.MockVariableValue(&setting.Repository.PrefixArchiveFiles, !setting.Repository.PrefixArchiveFiles)()
|
|
MakeRequest(t, NewRequest(t, "GET", archiveURL).SetHeader("If-None-Match", etag), http.StatusOK)
|
|
})
|
|
|
|
t.Run("SubPath", func(t *testing.T) {
|
|
// When using "archiving and caching" approach, archiving with paths will always use streaming and never be cached
|
|
defer test.MockVariableValue(&setting.Repository.StreamArchives, false)() // this can be removed if there is always streaming mode
|
|
req := NewRequest(t, "GET", "/user2/repo1/archive/archive-test.tar.gz?path=aaa.doc&path=x/y")
|
|
resp := MakeRequest(t, req, http.StatusOK)
|
|
content, err := test.ReadAllTarGzContent(resp.Body)
|
|
require.NoError(t, err)
|
|
assert.Empty(t, content["repo1/a.txt"])
|
|
assert.NotEmpty(t, content["repo1/aaa.doc"])
|
|
assert.Empty(t, content["repo1/x/b.txt"])
|
|
assert.NotEmpty(t, content["repo1/x/y/a.txt"])
|
|
|
|
req = NewRequest(t, "GET", "/user2/repo1/archive/archive-test.tar.gz")
|
|
resp = MakeRequest(t, req, http.StatusOK)
|
|
content, err = test.ReadAllTarGzContent(resp.Body)
|
|
require.NoError(t, err)
|
|
assert.NotEmpty(t, content["repo1/a.txt"])
|
|
assert.NotEmpty(t, content["repo1/aaa.doc"])
|
|
assert.NotEmpty(t, content["repo1/x/b.txt"])
|
|
assert.NotEmpty(t, content["repo1/x/y/a.txt"])
|
|
})
|
|
}
|