8000 Enhanced search logic of board listall, core search and lib search by silvanocerza · Pull Request #1222 · arduino/arduino-cli · GitHub
[go: up one dir, main page]

Skip to content

Enhanced search logic of board listall, core search and lib search #1222

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Mar 16, 2021
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading< 8000 /span>
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Remove fuzzy logic from lib search command
  • Loading branch information
silvanocerza committed Mar 15, 2021
commit 249fd5a91bb6b9c1407ba2171e84db7887a167ca
55 changes: 22 additions & 33 deletions commands/lib/search.go
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,9 @@ import (

"github.com/arduino/arduino-cli/arduino/libraries/librariesindex"
"github.com/arduino/arduino-cli/arduino/libraries/librariesmanager"
"github.com/arduino/arduino-cli/arduino/utils"
"github.com/arduino/arduino-cli/commands"
rpc "github.com/arduino/arduino-cli/rpc/commands"
"github.com/lithammer/fuzzysearch/fuzzy"
semver "go.bug.st/relaxed-semver"
)

Expand All @@ -43,44 +43,33 @@ func searchLibrary(req *rpc.LibrarySearchReq, lm *librariesmanager.LibrariesMana
res := []*rpc.SearchedLibrary{}
status := rpc.LibrarySearchStatus_success

// If the query is empty all libraries are returned
if strings.Trim(query, " ") == "" {
for _, lib := range lm.Index.Libraries {
res = append(res, indexLibraryToRPCSearchLibrary(lib))
searchArgs := strings.Split(strings.Trim(query, " "), " ")

match := func(toTest []string) (bool, error) {
if len(searchArgs) == 0 {
return true, nil
}
return &rpc.LibrarySearchResp{Libraries: res, Status: status}, nil
}

// maximumSearchDistance is the maximum Levenshtein distance accepted when using fuzzy search.
// This value is completely arbitrary and picked randomly.
maximumSearchDistance := 150
// Use a lower distance for shorter query or the user might be flooded with unrelated results
if len(query) <= 4 {
maximumSearchDistance = 40
for _, t := range toTest {
matches, err := utils.Match(t, searchArgs)
if err != nil {
return false, err
}
if matches {
return matches, nil
}
}
return false, nil
}

// Removes some chars from query strings to enhance results
cleanQuery := strings.Map(func(r rune) rune {
switch r {
case '_':
case '-':
case ' ':
return -1
}
return r
}, query)
for _, lib := range lm.Index.Libraries {
// Use both uncleaned and cleaned query
for _, q := range []string{query, cleanQuery} {
toTest := []string{lib.Name, lib.Latest.Paragraph, lib.Latest.Sentence}
for _, rank := range fuzzy.RankFindNormalizedFold(q, toTest) {
if rank.Distance < maximumSearchDistance {
res = append(res, indexLibraryToRPCSearchLibrary(lib))
goto nextLib
}
}
toTest := []string{lib.Name, lib.Latest.Paragraph, lib.Latest.Sentence}
if ok, err := match(toTest); err != nil {
return nil, err
} else if !ok {
continue
}
nextLib:
res = append(res, indexLibraryToRPCSearchLibrary(lib))
}

return &rpc.LibrarySearchResp{Libraries: res, Status: status}, nil
Expand Down
2 changes: 1 addition & 1 deletion commands/lib/search_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ func TestSearchLibrarySimilar(t *testing.T) {

req := &rpc.LibrarySearchReq{
Instance: &rpc.Instance{Id: 1},
Query: "ardino",
Query: "arduino",
}

resp, err := searchLibrary(req, lm)
Expand Down
41 changes: 15 additions & 26 deletions test/test_lib.py
Original file line number Diff line number Diff line change
Expand Up @@ -414,7 +414,7 @@ def test_lib_ops_caseinsensitive(run_command):


def test_search(run_command):
assert run_command("lib update-index")
assert run_command("update")

result = run_command("lib search --names")
assert result.ok
Expand All @@ -433,29 +433,6 @@ def test_search(run_command):
result = run_command("lib search --names")
assert result.ok

# Search for a specific target
result = run_command("lib search --names ArduinoJson --format json")
assert result.ok
libs_json = json.loads(result.stdout)
assert len(libs_json.get("libraries")) >= 1


def test_search_paragraph(run_command):
"""
Search for a string that's only present in the `paragraph` field
within the index file.
"""
assert run_command("lib update-index")
result = run_command('lib search "A simple and efficient JSON library" --names --format json')
assert result.ok
data = json.loads(result.stdout)
libraries = [l["name"] for l in data["libraries"]]
assert "ArduinoJson" in libraries


def test_lib_search_fuzzy(run_command):
run_command("update")

def run_search(search_args, expected_libraries):
res = run_command(f"lib searc 9EE0 h --names --format json {search_args}")
assert res.ok
Expand All @@ -468,7 +445,6 @@ def run_search(search_args, expected_libraries):
run_search("Arduino mkr iot carrier", ["Arduino_MKRIoTCarrier"])
run_search("mkr iot carrier", ["Arduino_MKRIoTCarrier"])
run_search("mkriotcarrier", ["Arduino_MKRIoTCarrier"])
run_search("Arduinomkriotcarrier", ["Arduino_MKRIoTCarrier"])

run_search(
"dht",
Expand All @@ -481,10 +457,23 @@ def run_search(search_args, expected_libraries):
run_search("sensor dht", [])

run_search("arduino json", ["ArduinoJson", "Arduino_JSON"])
run_search("arduinojson", ["ArduinoJson", "Arduino_JSON"])
run_search("arduinojson", ["ArduinoJson"])
run_search("json", ["ArduinoJson", "Arduino_JSON"])


def test_search_paragraph(run_command):
"""
Search for a string that's only present in the `paragraph` field
within the index file.
"""
assert run_command("lib update-index")
result = run_command('lib search "A simple and efficient JSON library" --names --format json')
assert result.ok
data = json.loads(result.stdout)
libraries = [l["name"] for l in data["libraries"]]
assert "ArduinoJson" in libraries


def test_lib_list_with_updatable_flag(run_command):
# Init the environment explicitly
run_command("lib update-index")
Expand Down
0