Compare commits

...
Author SHA1 Message Date
Dominik Schmidt 54b62f42e5 feat(search): hierarchy tokenizer for bleve path fields
Path was a keyword, so the descendant lookup behind delete/move/restore/purge, the scoped search and the KQL path predicate expanded into one term searcher per descendant and OOM-killed the server on large folders (#1269, #3469).

Path is now analyzed into its ancestor prefixes, like path_hierarchy in OpenSearch: ./a/b.txt becomes ., ./a, ./a/b.txt. A folder's descendants are every document carrying the folder's path as a term, so all three call sites are a single term query. Schema 4 -> 5, v4 never shipped.

The same tokenizer with tag_depth is registered as the geohash analyzer, so #3272 can add its geohash field without another schema change.
2026-09-10 16:45:59 +00:00
Viktor Scharf e503c2c5eb add insecure to search reindex (#3505) 2026-09-10 16:29:37 +02:00
Viktor Scharf 994086ceb2 add search retry to all serach tests (#3500) 2026-09-09 15:21:23 +02:00
25 changed files with 576 additions and 176 deletions

No files matched your search

+2 -2
View File
@@ -13,7 +13,7 @@ Fill the new index by indexing all spaces again:
```shell
# the service keeps running while it happens
opencloud search index --all-spaces
opencloud search index --all-spaces --insecure
```
Once the new index is filled, every index but the one with the highest
@@ -31,7 +31,7 @@ The new index is a directory next to the old `bleve` one, both in
bleve index cannot be copied, index all spaces again:
```shell
opencloud search index --all-spaces
opencloud search index --all-spaces --insecure
```
Once the new index is filled, every directory but the one with the highest
+2 -2
View File
@@ -124,14 +124,14 @@ opencloud search index --space $SPACE_ID
It can also be used to re-index all spaces:
```shell
opencloud search index --all-spaces
opencloud search index --all-spaces --insecure
```
Please note that a reindex only picks up new or changed files. Files that have already been indexed are not scanned again, even if the configuration or the whole extractor has been changed. To force a full rescan (re-running the extractor on every file) you need to use the `force-rescan` flag:
```shell
opencloud search index --all-spaces --force-rescan
opencloud search index --all-spaces --force-rescan --insecure
```
## Metrics
+3 -7
View File
@@ -75,14 +75,10 @@ func (b *Backend) Search(_ context.Context, sir *searchService.SearchIndexReques
},
)
// Scope below the space root: restrict at query level so totals and
// paging respect the path too. Path is a case-preserving keyword
// (paths act as references, /Foo and /foo are distinct), so the exact
// folder or the folder prefix matches all of, and only, the scope.
// paging respect the path too. The folder term matches the folder and
// its descendants (see PathAnalyzer).
if requestedPath := utils.MakeRelativePath(sir.Ref.Path); requestedPath != "." {
q.Conjuncts = append(q.Conjuncts, query.NewDisjunctionQuery([]query.Query{
&query.TermQuery{FieldVal: "Path", Term: requestedPath},
&query.PrefixQuery{FieldVal: "Path", Prefix: requestedPath + "/"},
}))
q.Conjuncts = append(q.Conjuncts, &query.TermQuery{FieldVal: "Path", Term: requestedPath})
}
}
-8
View File
@@ -1,8 +1,6 @@
package bleve
import (
"regexp"
bleveSearch "github.com/blevesearch/bleve/v2/search"
storageProvider "github.com/cs3org/go-cs3apis/cs3/storage/provider/v1beta1"
@@ -11,8 +9,6 @@ import (
"github.com/opencloud-eu/opencloud/services/search/pkg/search"
)
var queryEscape = regexp.MustCompile(`([` + regexp.QuoteMeta(`+=&|><!(){}[]^\"~*?:\/`) + `\-\s])`)
func getFieldValue[T any](m map[string]any, key string) (out T) {
val, ok := m[key]
if !ok {
@@ -84,7 +80,3 @@ func hitToFacet[T any](fields map[string]any, prefix string) *T {
func matchToResource(match *bleveSearch.DocumentMatch) *search.Resource {
return mapping.Deserialize[search.Resource](match.Fields)
}
func escapeQuery(s string) string {
return queryEscape.ReplaceAllString(s, "\\$1")
}
@@ -0,0 +1,51 @@
package bleve
import (
"github.com/blevesearch/bleve/v2"
. "github.com/onsi/ginkgo/v2"
. "github.com/onsi/gomega"
"github.com/opencloud-eu/opencloud/pkg/log"
"github.com/opencloud-eu/opencloud/services/search/pkg/search"
)
var _ = Describe("searchResourcesByPath", func() {
var idx bleve.Index
BeforeEach(func() {
var err error
idx, _, err = NewIndex(GinkgoT().TempDir(), log.NopLogger())
Expect(err).ToNot(HaveOccurred())
DeferCleanup(func() { Expect(idx.Close()).To(Succeed()) })
})
ids := func(rootID, lookupPath string) []string {
res, err := searchResourcesByPath(rootID, lookupPath, idx)
Expect(err).ToNot(HaveOccurred())
out := make([]string, 0, len(res))
for _, r := range res {
out = append(out, r.ID)
}
return out
}
It("returns all of, and only, the descendants of the folder in its space", func() {
const rootA, rootB = "s$a!root", "s$b!root"
batch := idx.NewBatch()
for _, r := range []search.Resource{
{ID: "s$a!big", RootID: rootA, Path: "./big", Type: 2},
{ID: "s$a!f1", RootID: rootA, Path: "./big/f1.txt", Type: 1},
{ID: "s$a!f2", RootID: rootA, Path: "./big/sub/f2.txt", Type: 1},
{ID: "s$a!big2", RootID: rootA, Path: "./big2/x.txt", Type: 1},
{ID: "s$b!clone", RootID: rootB, Path: "./big/f1.txt", Type: 1},
{ID: "s$a!odd", RootID: rootA, Path: `./odd name*[1]/file:with spaces?.txt`, Type: 1},
} {
Expect(batch.Index(r.ID, r)).To(Succeed())
}
Expect(idx.Batch(batch)).To(Succeed())
Expect(ids(rootA, "./big")).To(ConsistOf("s$a!f1", "s$a!f2"))
Expect(ids(rootA, "./odd name*[1]")).To(ConsistOf("s$a!odd"))
Expect(ids(rootA, ".")).To(ConsistOf("s$a!big", "s$a!f1", "s$a!f2", "s$a!big2", "s$a!odd"))
})
})
@@ -0,0 +1,82 @@
package hierarchy
import (
"bytes"
"strconv"
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
)
// emits every prefix up to a level: "./a/b" -> ".", "./a", "./a/b" with
// delimiter "/", one level per byte without. tag_depth prepends "<depth>/".
const Name = "hierarchy"
type Tokenizer struct {
delimiter []byte
tagDepth bool
}
func (t *Tokenizer) Tokenize(input []byte) analysis.TokenStream {
if len(input) == 0 {
return nil
}
var out analysis.TokenStream
emit := func(depth, end int) {
term := input[:end]
if t.tagDepth {
term = strconv.AppendInt(make([]byte, 0, end+4), int64(depth), 10)
term = append(term, '/')
term = append(term, input[:end]...)
}
out = append(out, &analysis.Token{
Term: term,
Position: depth,
Start: 0,
End: end,
Type: analysis.AlphaNumeric,
})
}
if len(t.delimiter) == 0 {
for i := range input {
emit(i+1, i+1)
}
return out
}
depth := 0
for start := 0; start <= len(input); {
i := bytes.Index(input[start:], t.delimiter)
if i < 0 {
if start < len(input) {
depth++
emit(depth, len(input))
}
break
}
if i > 0 {
depth++
emit(depth, start+i)
}
start += i + len(t.delimiter)
}
return out
}
func Constructor(config map[string]interface{}, _ *registry.Cache) (analysis.Tokenizer, error) {
t := &Tokenizer{}
if d, ok := config["delimiter"].(string); ok {
t.delimiter = []byte(d)
}
if v, ok := config["tag_depth"].(bool); ok {
t.tagDepth = v
}
return t, nil
}
func init() {
if err := registry.RegisterTokenizer(Name, Constructor); err != nil {
panic(err)
}
}
@@ -0,0 +1,13 @@
package hierarchy_test
import (
"testing"
. "github.com/onsi/ginkgo/v2"
. "github.com/onsi/gomega"
)
func TestHierarchy(t *testing.T) {
RegisterFailHandler(Fail)
RunSpecs(t, "hierarchy tokenizer")
}
@@ -0,0 +1,56 @@
package hierarchy_test
import (
"github.com/blevesearch/bleve/v2/analysis"
"github.com/blevesearch/bleve/v2/registry"
. "github.com/onsi/ginkgo/v2"
. "github.com/onsi/gomega"
"github.com/opencloud-eu/opencloud/services/search/pkg/bleve/hierarchy"
)
func terms(ts analysis.TokenStream) []string {
out := make([]string, 0, len(ts))
for _, t := range ts {
out = append(out, string(t.Term))
}
return out
}
func tokenize(config map[string]any, input string) []string {
tok, err := hierarchy.Constructor(config, registry.NewCache())
Expect(err).ToNot(HaveOccurred())
return terms(tok.Tokenize([]byte(input)))
}
var _ = Describe("hierarchy tokenizer", func() {
path := map[string]any{"delimiter": "/"}
geohash := map[string]any{"tag_depth": true}
DescribeTable("emits every prefix up to a level boundary",
func(config map[string]any, input string, want []string) {
Expect(tokenize(config, input)).To(Equal(want))
},
Entry("relative path", path, "./a/b.txt", []string{".", "./a", "./a/b.txt"}),
Entry("space root", path, ".", []string{"."}),
Entry("trailing delimiter is not a level", path, "./a/", []string{".", "./a"}),
Entry("delimiter only", path, "/", []string{}),
Entry("leading delimiter", path, "/abs/x", []string{"/abs", "/abs/x"}),
Entry("double delimiter", path, "./a//b", []string{".", "./a", "./a//b"}),
Entry("spaces and special characters stay literal", path, "./odd name*[1]/f:x?.txt",
[]string{".", "./odd name*[1]", "./odd name*[1]/f:x?.txt"}),
Entry("empty input", path, "", []string{}),
Entry("geohash, one level per byte, depth tagged", geohash, "u4pru",
[]string{"1/u", "2/u4", "3/u4p", "4/u4pr", "5/u4pru"}),
)
It("keeps byte offsets on the source value", func() {
tok, err := hierarchy.Constructor(path, registry.NewCache())
Expect(err).ToNot(HaveOccurred())
ts := tok.Tokenize([]byte("./a/b"))
Expect(ts).To(HaveLen(3))
Expect(ts[2].Start).To(Equal(0))
Expect(ts[2].End).To(Equal(5))
Expect(ts[2].Position).To(Equal(3))
})
})
+48 -5
View File
@@ -19,6 +19,7 @@ import (
storageProvider "github.com/cs3org/go-cs3apis/cs3/storage/provider/v1beta1"
"github.com/opencloud-eu/opencloud/pkg/log"
"github.com/opencloud-eu/opencloud/services/search/pkg/bleve/hierarchy"
searchmapping "github.com/opencloud-eu/opencloud/services/search/pkg/mapping"
"github.com/opencloud-eu/opencloud/services/search/pkg/search"
)
@@ -208,6 +209,40 @@ func NewMapping() (mapping.IndexMapping, error) {
if err != nil {
return nil, err
}
// path: every ancestor prefix is a term, so one term query matches a folder
// and all of its descendants
err = indexMapping.AddCustomTokenizer("path_hierarchy", map[string]any{
"type": hierarchy.Name,
"delimiter": "/",
})
if err != nil {
return nil, err
}
err = indexMapping.AddCustomAnalyzer(searchmapping.PathAnalyzer, map[string]any{
"type": custom.Name,
"tokenizer": "path_hierarchy",
})
if err != nil {
return nil, err
}
// geohash: no field uses it yet. It is part of the v5 schema so that #3272
// can add its geohash field additively: new fields reconcile at startup,
// a changed analysis block does not (classifyStoredMapping), so the names
// and the config below must not change.
err = indexMapping.AddCustomTokenizer("geohash_hierarchy", map[string]any{
"type": hierarchy.Name,
"tag_depth": true,
})
if err != nil {
return nil, err
}
err = indexMapping.AddCustomAnalyzer(searchmapping.GeohashAnalyzer, map[string]any{
"type": custom.Name,
"tokenizer": "geohash_hierarchy",
})
if err != nil {
return nil, err
}
return indexMapping, nil
}
@@ -226,11 +261,15 @@ func searchResourceByID(id string, index bleve.Index) (*search.Resource, error)
return matchToResource(res.Hits[0]), nil
}
// searchResourcesByPath returns the descendants of the folder at lookupPath.
// The folder term matches the folder and everything below it in one term
// query (see PathAnalyzer); the folder itself is dropped from the result.
func searchResourcesByPath(rootID string, lookupPath string, index bleve.Index) ([]*search.Resource, error) {
q := bleve.NewConjunctionQuery(
bleve.NewQueryStringQuery("RootID:"+rootID),
bleve.NewQueryStringQuery("Path:"+escapeQuery(lookupPath+"/*")),
)
rootQuery := bleve.NewTermQuery(rootID)
rootQuery.SetField("RootID")
pathQuery := bleve.NewTermQuery(lookupPath)
pathQuery.SetField("Path")
q := bleve.NewConjunctionQuery(rootQuery, pathQuery)
bleveReq := bleve.NewSearchRequest(q)
bleveReq.Size = math.MaxInt
bleveReq.Fields = []string{"*"}
@@ -241,7 +280,11 @@ func searchResourcesByPath(rootID string, lookupPath string, index bleve.Index)
resources := make([]*search.Resource, 0, res.Hits.Len())
for _, match := range res.Hits {
resources = append(resources, matchToResource(match))
resource := matchToResource(match)
if resource.Path == lookupPath {
continue
}
resources = append(resources, resource)
}
return resources, nil
+19 -1
View File
@@ -160,7 +160,7 @@
"fields": [
{
"type": "text",
"analyzer": "keyword",
"analyzer": "path",
"store": true,
"index": true,
"include_term_vectors": true,
@@ -1259,7 +1259,25 @@
"type": "regexp"
}
},
"tokenizers": {
"geohash_hierarchy": {
"tag_depth": true,
"type": "hierarchy"
},
"path_hierarchy": {
"delimiter": "/",
"type": "hierarchy"
}
},
"analyzers": {
"geohash": {
"tokenizer": "geohash_hierarchy",
"type": "custom"
},
"path": {
"tokenizer": "path_hierarchy",
"type": "custom"
},
"words": {
"char_filters": [
"dot_to_space"
+6 -3
View File
@@ -60,7 +60,6 @@ func buildBleveDocMapping(t reflect.Type, overrides map[string]FieldOpts, prefix
}
if fieldType == TypeKeyword || fieldType == TypePath {
// bleve has no path tokenizer, so a path is a plain keyword here.
base := bleveKeywordMapping(fieldType, opts)
doc.AddFieldMappingsAt(fi.Name, base)
if opts.caseInsensitive() {
@@ -84,8 +83,9 @@ func buildBleveDocMapping(t reflect.Type, overrides map[string]FieldOpts, prefix
return doc, err
}
// bleveKeywordMapping is a case-preserving keyword field; path fields stay out
// of _all by default.
// bleveKeywordMapping is a case-preserving keyword field; path fields are
// analyzed into their ancestor prefixes (see PathAnalyzer) and stay out of
// _all by default.
func bleveKeywordMapping(fieldType string, opts FieldOpts) *bleveMapping.FieldMapping {
fm := bleve.NewKeywordFieldMapping()
switch {
@@ -94,6 +94,9 @@ func bleveKeywordMapping(fieldType string, opts FieldOpts) *bleveMapping.FieldMa
case fieldType == TypePath:
fm.IncludeInAll = false
}
if fieldType == TypePath {
fm.Analyzer = PathAnalyzer
}
return fm
}
+9
View File
@@ -26,6 +26,15 @@ const WordsSuffix = "_words"
// WordsAnalyzer names the analyzer both engines register for the words sibling.
const WordsAnalyzer = "words"
// PathAnalyzer names the bleve analyzer for TypePath fields: every ancestor
// prefix is a term, like path_hierarchy in OpenSearch.
const PathAnalyzer = "path"
// GeohashAnalyzer names the bleve analyzer for a geohash: every prefix is a
// depth-tagged term (1/u, 2/u4, ...), so a terms facet with TermPrefix
// "<precision>/" is a geohash grid at that precision.
const GeohashAnalyzer = "geohash"
// FieldOpts overrides the default type inference for a struct field. Keys in
// the override map are json-tag names (e.g. "Name", "location", "audio.artist"),
// not Go field names.
+2 -2
View File
@@ -27,7 +27,7 @@ func Reconcile(index string, r SchemaReconciler, logger log.Logger) (Classificat
case VerdictAdditive:
persisted, err := r.ApplyAdditive()
if persisted {
logger.Warn().Strs("fields", classification.NewFields).Str("index", index).Msg("extended the search index mapping with new fields; documents indexed before the upgrade do not contain them and queries on these fields will miss those documents until they are re-indexed; to re-index everything run: opencloud search index --all-spaces --force-rescan")
logger.Warn().Strs("fields", classification.NewFields).Str("index", index).Msg("extended the search index mapping with new fields; documents indexed before the upgrade do not contain them and queries on these fields will miss those documents until they are re-indexed; to re-index everything run: opencloud search index --all-spaces --force-rescan --insecure")
}
if err != nil {
return classification, err
@@ -40,5 +40,5 @@ func Reconcile(index string, r SchemaReconciler, logger log.Logger) (Classificat
// LogNewIndexCreated logs that a fresh, empty index was created and how to
// backfill it. The create path does not run through Reconcile.
func LogNewIndexCreated(logger log.Logger, index string) {
logger.Info().Str("index", index).Msg("created a new empty search index; if this OpenCloud instance already held files, they are not in it yet, index them by running: opencloud search index --all-spaces --force-rescan")
logger.Info().Str("index", index).Msg("created a new empty search index; if this OpenCloud instance already held files, they are not in it yet, index them by running: opencloud search index --all-spaces --force-rescan --insecure")
}
+7 -11
View File
@@ -123,6 +123,13 @@ func walk(offset int, nodes []ast.Node) (bleveQuery.Query, int, error) {
var q bleveQuery.Query = bleveQuery.NewQueryStringQuery(k + ":" + v)
switch {
case searchQuery.FieldIsPath(n.Key) && !isWildcard:
// the folder term matches the folder itself and its descendants
// (see PathAnalyzer); a query string would analyze the value into
// its prefixes and match everything under the root
tq := bleveQuery.NewTermQuery(val)
tq.SetField(k)
q = tq
case n.Exact && !isWildcard:
// = matches the whole value, on the lowercased sibling for
// case-insensitive fields
@@ -140,17 +147,6 @@ func walk(offset int, nodes []ast.Node) (bleveQuery.Query, int, error) {
bq.SetMinShould(1)
q = bq
}
if searchQuery.FieldIsPath(n.Key) {
// bleve has no path hierarchy analyzer, unlike OpenSearch: match the
// folder itself and its descendants (`\/*`). A BooleanQuery keeps
// this atomic; a DisjunctionQuery would be redistributed by an
// enclosing AND (mapBinary treats a left disjunction as an OR-chain).
bq := bleve.NewBooleanQuery()
bq.AddShould(q, bleveQuery.NewQueryStringQuery(k+":"+v+`\/*`))
bq.SetMinShould(1)
q = bq
}
if prev == nil {
prev = q
} else {
@@ -51,23 +51,17 @@ func Test_compile(t *testing.T) {
wantErr: false,
},
{
// path fields expand to match the folder itself and its descendants,
// since bleve has no path hierarchy analyzer.
// one term matches the folder itself and its descendants
name: `path:/Foo`,
args: &ast.Ast{
Nodes: []ast.Node{
&ast.StringNode{Key: "path", Value: "/Foo"},
},
},
// a BooleanQuery (should: exact OR descendants), not a DisjunctionQuery,
// so an enclosing AND does not redistribute the folder-itself clause.
want: func() query.Query {
bq := query.NewBooleanQuery(nil, []query.Query{
query.NewQueryStringQuery(`Path:\/Foo`),
query.NewQueryStringQuery(`Path:\/Foo\/*`),
}, nil)
bq.SetMinShould(1)
return query.NewConjunctionQuery([]query.Query{bq})
tq := query.NewTermQuery("/Foo")
tq.SetField("Path")
return query.NewConjunctionQuery([]query.Query{tq})
}(),
wantErr: false,
},
+1 -1
View File
@@ -29,7 +29,7 @@ import (
// on a breaking mapping change: each version gets its own index (OpenSearch name
// suffix, bleve path suffix), so the service builds a fresh index instead of
// colliding with the old one. No migration; reindex to populate.
const SchemaVersion = 4
const SchemaVersion = 5
var scopeRegex = regexp.MustCompile(`scope:\s*([^" "\n\r]*)`)
+14 -5
View File
@@ -39,16 +39,25 @@ class WaitHelper {
/**
* Repeat $makeAttempt until $shouldStop returns true or the timeout elapses.
*
* @param callable $makeAttempt makes one attempt (e.g. sends a request) and returns its result
* @param callable $shouldStop receives that result, returns true to stop polling
* @param callable $makeAttempt makes one attempt (e.g. sends a request) and returns its result
* @param callable $shouldStop receives that result, returns true to stop polling
* @param int|null $intervalMs pause between attempts in ms; defaults to self::INTERVAL_MS
* @param int|null $timeoutSeconds overall time to keep polling; defaults to self::TIMEOUT_SECONDS
*
* @return mixed the last result from $makeAttempt
*/
public static function waitUntil(callable $makeAttempt, callable $shouldStop): mixed {
$deadline = \microtime(true) + self::TIMEOUT_SECONDS;
public static function waitUntil(
callable $makeAttempt,
callable $shouldStop,
?int $intervalMs = null,
?int $timeoutSeconds = null
): mixed {
$intervalMs ??= self::INTERVAL_MS;
$timeoutSeconds ??= self::TIMEOUT_SECONDS;
$deadline = \microtime(true) + $timeoutSeconds;
$result = $makeAttempt();
while (!$shouldStop($result) && \microtime(true) < $deadline) {
\usleep(self::INTERVAL_MS * 1000);
\usleep($intervalMs * 1000);
$result = $makeAttempt();
}
return $result;
+105 -21
View File
@@ -150,7 +150,7 @@ class SearchContext implements Context {
): void {
// NOTE: because indexing of newly uploaded files or directories with OpenCloud is decoupled and occurs asynchronously
// short wait is necessary before searching
sleep(10);
sleep(2);
// remember the query so "should eventually contain" steps can re-search
$this->lastSearchQuery = [
"user" => $user,
@@ -176,6 +176,25 @@ class SearchContext implements Context {
string $path,
string $user,
TableNode $properties
): void {
$assert = fn () => $this->assertFileOrFolderInSearchResultContainsProperties($path, $user, $properties);
$this->retrySearchUntilSatisfied($assert);
$assert();
}
/**
*
* @param string $path
* @param string $user
* @param TableNode $properties
*
* @return void
* @throws Exception
*/
private function assertFileOrFolderInSearchResultContainsProperties(
string $path,
string $user,
TableNode $properties
): void {
$user = $this->featureContext->getActualUsername($user);
$this->featureContext->verifyTableNodeColumns($properties, ['name', 'value']);
@@ -234,8 +253,7 @@ class SearchContext implements Context {
*
* @throws Exception
*/
#[Then('/^the search result should contain these (?:files|entries) with highlight on keyword "([^"]*)"/')]
public function theSearchResultShouldContainEntriesWithHighlight(
private function assertSearchResultContainsEntriesWithHighlight(
TableNode $expectedFiles,
string $expectedContent
): void {
@@ -284,8 +302,15 @@ class SearchContext implements Context {
): void {
// NOTE: since indexing of newly uploaded files or directories with OpenCloud is decoupled and occurs asynchronously,
// a short wait is necessary before searching
sleep(5);
$response = $this-> searchFiles($user, $pattern, null, $scopeType, $scope, $spaceName);
sleep(2);
$this->lastSearchQuery = [
"user" => $user,
"pattern" => $pattern,
"scopeType" => $scopeType,
"scope" => $scope,
"spaceName" => $spaceName,
];
$response = $this->searchFiles($user, $pattern, null, $scopeType, $scope, $spaceName);
$this->featureContext->setResponse($response);
}
@@ -300,7 +325,7 @@ class SearchContext implements Context {
*
* @return void
*/
private function retrySearchUntilSatisfied(callable $assert): void {
public function retrySearchUntilSatisfied(callable $assert): void {
Assert::assertNotEmpty(
$this->lastSearchQuery,
'No search to retry. Use a "searches for ... using the WebDAV API" step first.'
@@ -310,33 +335,67 @@ class SearchContext implements Context {
fn () => $this->searchFiles(
$query["user"],
$query["pattern"],
$query["limit"],
null,
null,
null,
$query["properties"]
$query["limit"] ?? null,
$query["scopeType"] ?? null,
$query["scope"] ?? null,
$query["spaceName"] ?? null,
$query["properties"] ?? null
),
function ($response) use ($assert) {
$this->featureContext->setResponse($response);
try {
$assert();
return true;
} catch (\Throwable $e) {
} catch (\Throwable) {
return false;
}
}
},
2000,
20
);
$this->featureContext->setResponse($response);
}
/**
*
* @param int $numFiles
*
* @return void
*/
#[Then('the search result should contain :numFiles files/entries')]
public function theSearchResultShouldContainNumEntries(int $numFiles): void {
$assert = fn () => $this->featureContext->checkIFResponseContainsNumberEntries($numFiles);
$this->retrySearchUntilSatisfied($assert);
$assert();
}
/**
*
* @param string $user
* @param int $expectedNumber
* @param TableNode $expectedFiles
*
* @return void
*/
#[Then('the search result of user :user should contain any :expectedNumber of these files/entries:')]
public function theSearchResultShouldContainAnyOfTheseEntries(
string $user,
int $expectedNumber,
TableNode $expectedFiles
): void {
$assert = fn () => $this->featureContext->checkIfSearchResultContainsFiles($user, $expectedNumber, $expectedFiles);
$this->retrySearchUntilSatisfied($assert);
$assert();
}
/**
* @param string $user
* @param TableNode $expectedFiles
*
* @return void
*/
#[Then('/^the search result of user "([^"]*)" should eventually contain only these (?:files|entries):$/')]
public function theSearchResultShouldEventuallyContainOnlyEntries(string $user, TableNode $expectedFiles): void {
#[Then('/^the search result of user "([^"]*)" should contain only these (?:files|entries):$/')]
public function theSearchResultShouldContainOnlyEntries(string $user, TableNode $expectedFiles): void {
$assert = fn () => $this->featureContext->thePropfindResultShouldContainOnlyEntries($user, $expectedFiles);
$this->retrySearchUntilSatisfied($assert);
$assert();
@@ -348,9 +407,31 @@ class SearchContext implements Context {
*
* @return void
*/
#[Then('/^the search result of user "([^"]*)" should eventually contain these (?:files|entries):$/')]
public function theSearchResultShouldEventuallyContainEntries(string $user, TableNode $expectedFiles): void {
$assert = fn () => $this->featureContext->thePropfindResultShouldContainEntries($user, '', $expectedFiles);
#[Then('/^the search result of user "([^"]*)" should contain these (?:files|entries):$/')]
public function theSearchResultShouldContainEntries(string $user, TableNode $expectedFiles): void {
$this->assertSearchResultContainsEntries($user, "", $expectedFiles);
}
/**
* @param string $user
* @param TableNode $expectedFiles
*
* @return void
*/
#[Then('/^the search result of user "([^"]*)" should not contain these (?:files|entries):$/')]
public function theSearchResultShouldNotContainEntries(string $user, TableNode $expectedFiles): void {
$this->assertSearchResultContainsEntries($user, "not", $expectedFiles);
}
/**
* @param string $user
* @param string $shouldOrNot (not|)
* @param TableNode $expectedFiles
*
* @return void
*/
private function assertSearchResultContainsEntries(string $user, string $shouldOrNot, TableNode $expectedFiles): void {
$assert = fn () => $this->featureContext->thePropfindResultShouldContainEntries($user, $shouldOrNot, $expectedFiles);
$this->retrySearchUntilSatisfied($assert);
$assert();
}
@@ -361,9 +442,12 @@ class SearchContext implements Context {
*
* @return void
*/
#[Then('/^the search result should eventually contain these (?:files|entries) with highlight on keyword "([^"]*)"$/')]
public function theSearchResultShouldEventuallyContainEntriesWithHighlight(TableNode $expectedFiles, string $expectedContent): void {
$assert = fn () => $this->theSearchResultShouldContainEntriesWithHighlight($expectedFiles, $expectedContent);
#[Then('/^the search result should contain these (?:files|entries) with highlight on keyword "([^"]*)"$/')]
public function theSearchResultShouldContainEntriesWithHighlight(
TableNode $expectedFiles,
string $expectedContent
): void {
$assert = fn () => $this->assertSearchResultContainsEntriesWithHighlight($expectedFiles, $expectedContent);
$this->retrySearchUntilSatisfied($assert);
$assert();
}
+41 -33
View File
@@ -50,6 +50,7 @@ class SpacesContext implements Context {
private ChecksumContext $checksumContext;
private FilesVersionsContext $filesVersionsContext;
private ArchiverContext $archiverContext;
private SearchContext $searchContext;
/**
* key is space name and value is the username that created the space
@@ -512,6 +513,7 @@ class SpacesContext implements Context {
$this->checksumContext = BehatHelper::getContext($scope, $environment, 'ChecksumContext');
$this->filesVersionsContext = BehatHelper::getContext($scope, $environment, 'FilesVersionsContext');
$this->archiverContext = BehatHelper::getContext($scope, $environment, 'ArchiverContext');
$this->searchContext = BehatHelper::getContext($scope, $environment, 'SearchContext');
}
/**
@@ -3925,41 +3927,47 @@ class SpacesContext implements Context {
*/
#[Then('for user :user the search result should contain space :spaceName')]
public function searchResultShouldContainSpace(string $user, string $spaceName): void {
$responseArray = json_decode(
json_encode(
HttpRequestHelper::getResponseXml($this->featureContext->getResponse())->xpath("//d:response/d:href")
),
true,
512,
JSON_THROW_ON_ERROR
);
Assert::assertNotEmpty($responseArray, "search result is empty");
// searching a space by name goes through the asynchronous file index, so
// re-run the search until the space shows up (or the timeout elapses).
$assert = function () use ($user, $spaceName): void {
$responseArray = json_decode(
json_encode(
HttpRequestHelper::getResponseXml($this->featureContext->getResponse())->xpath("//d:response/d:href")
),
true,
512,
JSON_THROW_ON_ERROR
);
Assert::assertNotEmpty($responseArray, "search result is empty");
// for mountpoint, id looks a little different than for project space
if (str_contains($spaceName, 'mountpoint')) {
$splitSpaceName = explode("/", $spaceName);
$space = $this->getSpaceByName($user, $splitSpaceName[1]);
$splitSpaceId = explode("$", $space['id']);
$spaceId = str_replace('!', '%21', $splitSpaceId[1]);
} else {
$space = $this->getSpaceByName($user, $spaceName);
$spaceId = $space['id'];
}
$suffixPath = $user;
$davPathVersion = $this->featureContext->getDavPathVersion();
if ($davPathVersion === WebDavHelper::DAV_VERSION_SPACES) {
$suffixPath = $spaceId;
}
$topWebDavPath = "/" . WebDavHelper::getDavPath($davPathVersion, $suffixPath);
$spaceFound = false;
foreach ($responseArray as $value) {
if ($topWebDavPath === $value[0]) {
$spaceFound = true;
// for mountpoint, id looks a little different than for project space
if (str_contains($spaceName, 'mountpoint')) {
$splitSpaceName = explode("/", $spaceName);
$space = $this->getSpaceByName($user, $splitSpaceName[1]);
$splitSpaceId = explode("$", $space['id']);
$spaceId = str_replace('!', '%21', $splitSpaceId[1]);
} else {
$space = $this->getSpaceByName($user, $spaceName);
$spaceId = $space['id'];
}
}
Assert::assertTrue($spaceFound, "response does not contain the space '$spaceName'");
$suffixPath = $user;
$davPathVersion = $this->featureContext->getDavPathVersion();
if ($davPathVersion === WebDavHelper::DAV_VERSION_SPACES) {
$suffixPath = $spaceId;
}
$topWebDavPath = "/" . WebDavHelper::getDavPath($davPathVersion, $suffixPath);
$spaceFound = false;
foreach ($responseArray as $value) {
if ($topWebDavPath === $value[0]) {
$spaceFound = true;
}
}
Assert::assertTrue($spaceFound, "response does not contain the space '$spaceName'");
};
$this->searchContext->retrySearchUntilSatisfied($assert);
$assert();
}
/**
+91 -27
View File
@@ -25,6 +25,7 @@ use Behat\Gherkin\Node\TableNode;
use PHPUnit\Framework\Assert;
use Psr\Http\Message\ResponseInterface;
use TestHelpers\GraphHelper;
use TestHelpers\WaitHelper;
use TestHelpers\BehatHelper;
use Behat\Step\Given;
use Behat\Step\Then;
@@ -38,6 +39,7 @@ require_once 'bootstrap.php';
class TagContext implements Context {
private FeatureContext $featureContext;
private SpacesContext $spacesContext;
private array $lastTagsQuery = [];
/**
* This will run before EVERY scenario.
@@ -175,19 +177,79 @@ class TagContext implements Context {
*/
#[When('user :user lists all available tag(s) via the Graph API')]
public function theUserGetsAllAvailableTags(string $user): void {
// Note: after creating or deleting tags, in some cases tags do not appear or disappear immediately,
// So wait is necessary before listing tags
sleep(5);
$this->featureContext->setResponse(
GraphHelper::getTags(
$this->featureContext->getBaseUrl(),
$user,
$this->featureContext->getPasswordForUser($user),
$this->featureContext->getStepLineRef()
)
// Note: after creating or deleting tags, in some cases tags do not appear or disappear immediately
sleep(2);
$this->lastTagsQuery = ["user" => $user];
$this->featureContext->setResponse($this->fetchTags($user));
}
/**
* @param string $user
*
* @return ResponseInterface
* @throws Exception
*/
private function fetchTags(string $user): ResponseInterface {
return GraphHelper::getTags(
$this->featureContext->getBaseUrl(),
$user,
$this->featureContext->getPasswordForUser($user),
$this->featureContext->getStepLineRef()
);
}
/**
* re-run the last tag listing until the assertion passes or the WaitHelper
*
* @param callable $assert
*
* @return void
*/
private function retryTagsUntilSatisfied(callable $assert): void {
Assert::assertNotEmpty(
$this->lastTagsQuery,
'No tag listing to retry. Use a "lists all available tags via the Graph API" step first.'
);
$query = $this->lastTagsQuery;
$response = WaitHelper::waitUntil(
fn () => $this->fetchTags($query["user"]),
function ($response) use ($assert) {
$this->featureContext->setResponse($response);
try {
$assert();
return true;
} catch (\Throwable) {
return false;
}
}
);
$this->featureContext->setResponse($response);
}
/**
*
* @param TableNode $table
*
* @return void
* @throws Exception
*/
#[Then('/^the response should contain following tags:$/')]
public function theResponseShouldContainFollowingTags(TableNode $table): void {
$this->assertResponseContainsFollowingTags("", $table);
}
/**
*
* @param TableNode $table
*
* @return void
* @throws Exception
*/
#[Then('/^the response should not contain following tags:$/')]
public function theResponseShouldNotContainFollowingTags(TableNode $table): void {
$this->assertResponseContainsFollowingTags("not", $table);
}
/**
*
* @param string $shouldOrNot (not|)
@@ -196,27 +258,29 @@ class TagContext implements Context {
* @return void
* @throws Exception
*/
#[Then('/^the response should (not|)\\s?contain following tag(s):$/')]
public function theFollowingTagsShouldExistForUser(string $shouldOrNot, TableNode $table): void {
$rows = $table->getRows();
foreach ($rows as $row) {
private function assertResponseContainsFollowingTags(string $shouldOrNot, TableNode $table): void {
$assert = function () use ($shouldOrNot, $table): void {
$responseArray = $this->featureContext->getJsonDecodedResponse(
$this->featureContext->getResponse()
)['value'];
if ($shouldOrNot === "not") {
Assert::assertFalse(
\in_array($row[0], $responseArray),
"the response should not contain the tag $row[0].\nResponse\n"
. print_r($responseArray, true)
);
} else {
Assert::assertTrue(
\in_array($row[0], $responseArray),
"the response does not contain the tag $row[0].\nResponse\n"
. print_r($responseArray, true)
);
foreach ($table->getRows() as $row) {
if ($shouldOrNot === "not") {
Assert::assertFalse(
\in_array($row[0], $responseArray),
"the response should not contain the tag $row[0].\nResponse\n"
. print_r($responseArray, true)
);
} else {
Assert::assertTrue(
\in_array($row[0], $responseArray),
"the response does not contain the tag $row[0].\nResponse\n"
. print_r($responseArray, true)
);
}
}
}
};
$this->retryTagsUntilSatisfied($assert);
$assert();
}
/**
+4 -4
View File
@@ -4014,7 +4014,7 @@ trait WebDav {
* @return void
* @throws Exception
*/
#[Then('/^the (?:propfind|search) result of user "([^"]*)" should (not|)\\s?contain these (?:files|entries):$/')]
#[Then('/^the propfind result of user "([^"]*)" should (not|)\\s?contain these (?:files|entries):$/')]
public function thePropfindResultShouldContainEntries(
string $user,
string $shouldOrNot,
@@ -4036,7 +4036,7 @@ trait WebDav {
* @return void
* @throws Exception
*/
#[Then('/^the (?:propfind|search) result of user "([^"]*)" should contain only these (?:files|entries):$/')]
#[Then('/^the propfind result of user "([^"]*)" should contain only these (?:files|entries):$/')]
public function thePropfindResultShouldContainOnlyEntries(
string $user,
TableNode $expectedFiles
@@ -4063,7 +4063,7 @@ trait WebDav {
*
* @return void
*/
#[Then('the propfind/search result should contain :numFiles files/entries')]
#[Then('the propfind result should contain :numFiles files/entries')]
public function propfindResultShouldContainNumEntries(int $numFiles): void {
$this->checkIFResponseContainsNumberEntries($numFiles);
}
@@ -4110,7 +4110,7 @@ trait WebDav {
* @return void
* @throws Exception
*/
#[Then('the propfind/search result of user :user should contain any :expectedNumber of these files/entries:')]
#[Then('the propfind result of user :user should contain any :expectedNumber of these files/entries:')]
public function theSearchResultOfUserShouldContainAnyOfTheseEntries(
string $user,
int $expectedNumber,
@@ -186,15 +186,6 @@
- [apiServiceAvailability/serviceAvailabilityCheck.feature:123](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiServiceAvailability/serviceAvailabilityCheck.feature#L123)
#### [Missing properties in REPORT response](https://github.com/owncloud/ocis/issues/9780), [d:getetag property has empty value in REPORT response](https://github.com/owncloud/ocis/issues/9783)
- [apiSearch1/search.feature:437](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L437)
- [apiSearch1/search.feature:438](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L438)
- [apiSearch1/search.feature:439](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L439)
- [apiSearch1/search.feature:465](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L465)
- [apiSearch1/search.feature:466](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L466)
- [apiSearch1/search.feature:467](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L467)
## Scenarios from core API tests that are expected to fail with decomposed storage
### File
@@ -186,15 +186,6 @@
- [apiServiceAvailability/serviceAvailabilityCheck.feature:123](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiServiceAvailability/serviceAvailabilityCheck.feature#L123)
#### [Missing properties in REPORT response](https://github.com/owncloud/ocis/issues/9780), [d:getetag property has empty value in REPORT response](https://github.com/owncloud/ocis/issues/9783)
- [apiSearch1/search.feature:437](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L437)
- [apiSearch1/search.feature:438](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L438)
- [apiSearch1/search.feature:439](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L439)
- [apiSearch1/search.feature:465](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L465)
- [apiSearch1/search.feature:466](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L466)
- [apiSearch1/search.feature:467](https://github.com/opencloud-eu/opencloud/blob/main/tests/acceptance/features/apiSearch1/search.feature#L467)
## Scenarios from core API tests that are expected to fail with posix storage
### File
@@ -409,7 +409,7 @@ Feature: Search
| new |
| spaces |
@issue-4712 @issue-9780 @issue-9781 @issue-9783 @issue-10329
@skip @issue-3501 @issue-9780
Scenario Outline: report extra properties in search entries for a file
Given using <dav-path-version> DAV path
When user "Alice" searches for "*insideTheFo*" using the WebDAV API requesting these properties:
@@ -438,7 +438,7 @@ Feature: Search
| new |
| spaces |
@issue-4712 @issue-9780 @issue-9781 @issue-9783 @issue-10329
@skip @issue-3501 @issue-9780
Scenario Outline: report extra properties in search entries for a folder
Given using <dav-path-version> DAV path
When user "Alice" searches for "*folderMain*" using the WebDAV API requesting these properties:
@@ -16,7 +16,7 @@ Feature: content search
And user "Alice" has uploaded file with content "namaste from nepal" to "hello.txt"
When user "Alice" searches for "Content:hello" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| keywordAtStart.txt |
| keywordAtMiddle.txt |
| keywordAtLast.txt |
@@ -34,15 +34,15 @@ Feature: content search
And user "Alice" has uploaded file with content "alan@example.org want to say hello" to "findByEmail.docs"
When user "Alice" searches for "Content:k6" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| wordWithNumber.md |
When user "Alice" searches for "Content:https://opencloud.eu/" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| findByWebSite.txt |
When user "Alice" searches for "Content:alan@" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| findByEmail.docs |
Examples:
| dav-path-version |
@@ -71,11 +71,11 @@ Feature: content search
And user "Alice" has uploaded file with content "He has expirience, we must to have, I have to find ...." to "fileWithStopWords.txt"
When user "Alice" searches for 'Content:"he has"' using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| fileWithStopWords.txt |
When user "Alice" searches for 'Content:"I have"' using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| fileWithStopWords.txt |
Examples:
| dav-path-version |
@@ -101,7 +101,7 @@ Feature: content search
And user "Brian" has a share "uploadFolder" synced
When user "Brian" searches for "Content:hello" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Brian" should eventually contain only these files:
And the search result of user "Brian" should contain only these files:
| keywordAtStart.txt |
| keywordAtMiddle.txt |
| keywordAtLast.txt |
@@ -121,7 +121,7 @@ Feature: content search
And user "Alice" has deleted file "keywordAtLast.txt"
When user "Alice" searches for "Content:hello" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| keywordAtStart.txt |
| keywordAtMiddle.txt |
Examples:
@@ -139,7 +139,7 @@ Feature: content search
And user "Alice" has restored the file with original path "keywordAtStart.txt"
When user "Alice" searches for "Content:hello" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| keywordAtStart.txt |
Examples:
| dav-path-version |
@@ -154,7 +154,7 @@ Feature: content search
And user "Alice" has restored version index "1" of file "test.txt"
When user "Alice" searches for "Content:hello" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| test.txt |
Examples:
| dav-path-version |
@@ -175,7 +175,7 @@ Feature: content search
And using <dav-path-version> DAV path
When user "Alice" searches for "Content:hello" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| keywordAtStart.txt |
| keywordAtMiddle.txt |
| keywordAtLast.txt |
@@ -204,7 +204,7 @@ Feature: content search
And using <dav-path-version> DAV path
When user "Brian" searches for "Content:hello" using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain only these files:
And the search result of user "Alice" should contain only these files:
| keywordAtStart.txt |
| keywordAtMiddle.txt |
| keywordAtLast.txt |
@@ -224,7 +224,7 @@ Feature: content search
| technical task.txt | test |
When user "Alice" searches for '<pattern>' using the WebDAV API
Then the HTTP status code should be "207"
And the search result of user "Alice" should eventually contain these entries:
And the search result of user "Alice" should contain these entries:
| <search-result-1> |
| <search-result-2> |
And the search result should contain "<result-count>" entries
@@ -251,7 +251,7 @@ Feature: content search
And user "Alice" has uploaded a file inside space "project-space" with content "this is a simple odt file" to "test-odt-file.odt"
When user "Alice" searches for "Content:simple" using the WebDAV API
Then the HTTP status code should be "207"
And the search result should eventually contain these entries with highlight on keyword "simple"
And the search result should contain these entries with highlight on keyword "simple"
| test-text-file.txt |
| test-pdf-file.pdf |
| test-cpp-file.cpp |