Skip to content

feat: 增加 HTTP 页面语言识别 #160

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.

Sign up for GitHub

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

Draft
h3zh1 wants to merge 1 commit into
base: master
Choose a base branch
from
+517 −0
Draft

feat: 增加 HTTP 页面语言识别 #160

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions core/baseline/baseline.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,6 +240,7 @@ func (bl *Baseline) Collect() {
}
}

bl.Extracteds.Merge(pkg.HTTPLanguageExtract(pkg.ExtractHTTPLanguage(bl.Header, bl.Body)))
bl.Hashes = parsers.NewHashes(bl.Raw)
bl.Extracteds.Merge(pkg.ProtonExtract(bl.Raw))
bl.Unique = UniqueHash(bl)
Expand Down
66 changes: 66 additions & 0 deletions core/baseline/http_language_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,66 @@
package baseline

import (
"testing"

"github.com/chainreactors/spray/core/ihttp"
"github.com/chainreactors/spray/pkg"
"github.com/valyala/fasthttp"
)

func TestCollectAddsHTTPLanguageExtract(t *testing.T) {
var fastResp fasthttp.Response
fastResp.SetStatusCode(200)
fastResp.Header.Set("Content-Type", "text/html; charset=utf-8")
fastResp.Header.Set("Content-Language", "en-US")
fastResp.SetBodyString(`<html lang="en"><body>これは日本語のページです。サービス状態を表示します。</body></html>`)

resp := &ihttp.Response{FastResponse: &fastResp}
bl := NewBaseline("https://example.test/", "example.test", resp)
bl.Collect()

var found bool
for _, e := range bl.Extracteds {
if e.Name == "language" {
found = true
if len(e.ExtractResult) != 1 || e.ExtractResult[0] != "ja" {
t.Fatalf("language extract_result = %v, want [ja]", e.ExtractResult)
}
break
}
}
if !found {
t.Fatal("language extract not found in Extracteds")
}
}

func TestCollectAddsHTTPLanguageExtractWithoutFingerEngine(t *testing.T) {
oldEnableAllFingerEngine := pkg.EnableAllFingerEngine
pkg.EnableAllFingerEngine = false
t.Cleanup(func() {
pkg.EnableAllFingerEngine = oldEnableAllFingerEngine
})

var fastResp fasthttp.Response
fastResp.SetStatusCode(200)
fastResp.Header.Set("Content-Type", "text/html; charset=utf-8")
fastResp.SetBodyString(`<html lang="en"><body>This is an English product page and the service is available for you from the web console with your account.</body></html>`)

resp := &ihttp.Response{FastResponse: &fastResp}
bl := NewBaseline("https://example.test/", "example.test", resp)
bl.Collect()

var found bool
for _, e := range bl.Extracteds {
if e.Name == "language" {
found = true
if len(e.ExtractResult) != 1 || e.ExtractResult[0] != "en" {
t.Fatalf("language extract_result = %v, want [en]", e.ExtractResult)
}
break
}
}
if !found {
t.Fatal("language extract not found, want language detection even when finger engine is disabled")
}
}
Loading
Loading