Skip to content
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

Add support for local file system in HTTP driver. #777

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+75 −6
Open

Add support for local file system in HTTP driver. #777

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
43 changes: 39 additions & 4 deletions pkg/drivers/http/driver.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,7 @@ import (
"io"
"net/http"
"net/url"
"os"

"github.com/gobwas/glob"

Expand Down Expand Up @@ -88,17 +89,51 @@ func (drv *Driver) Name() string {
return drv.options.Name
}

func (drv *Driver) Open(ctx context.Context, params drivers.Params) (drivers.HTMLPage, error) {
func (drv *Driver) readLocalFile(u *url.URL, params drivers.Params) (*http.Response, error) {
req, err := http.NewRequest(http.MethodGet, params.URL, nil)
if err != nil {
return nil, err
}
f, err := os.Open(u.Path)
if err != nil {
return nil, err
}
stat, err := f.Stat()
if err != nil {
f.Close()
return nil, err
}
return &http.Response{
Status: "200 OK",
StatusCode: http.StatusOK,
Proto: "HTTP/1.1",
ProtoMajor: 1,
ProtoMinor: 1,
Header: map[string][]string{},
Body: f,
ContentLength: stat.Size(),
Trailer: map[string][]string{},
Request: req,
}, nil
}

params = drivers.SetDefaultParams(drv.options.Options, params)
func (drv *Driver) Open(ctx context.Context, params drivers.Params) (drivers.HTMLPage, error) {
var resp *http.Response
var err error
u, err := url.Parse(params.URL)
if err == nil && u.Scheme == "file" {
resp, err = drv.readLocalFile(u, params)
} else {
req, reqErr := http.NewRequest(http.MethodGet, params.URL, nil)
if reqErr != nil {
return nil, reqErr
}

drv.makeRequest(ctx, req, params)
params = drivers.SetDefaultParams(drv.options.Options, params)
drv.makeRequest(ctx, req, params)
resp, err = drv.client.Do(req)
}

resp, err := drv.client.Do(req)
if err != nil {
return nil, errors.Wrapf(err, "failed to retrieve a document %s", params.URL)
}
Expand Down
38 changes: 36 additions & 2 deletions pkg/drivers/http/driver_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ import (
"crypto/tls"
"io"
"net/http"
"os"
"path/filepath"
"reflect"
"testing"
"unsafe"
Expand All @@ -17,6 +19,11 @@ import (
"github.com/MontFerret/ferret/pkg/drivers"
)

const (
testInnerText = `феррет`
testHTMLDocument = `<!DOCTYPE html><html><head><meta charset="windows-1251"/></head><body>феррет</body></html>`
)

func Test_newHTTPClientWithTransport(t *testing.T) {
httpTransport := (http.DefaultTransport).(*http.Transport)
httpTransport.TLSClientConfig = &tls.Config{InsecureSkipVerify: true}
Expand Down Expand Up @@ -87,6 +94,33 @@ func Test_newHTTPClient(t *testing.T) {
})
}

func TestDriver_readFromFile(t *testing.T) {
ctx := context.Background()
dir := t.TempDir()
localFile := filepath.Join(dir, "test.html")
if err := os.WriteFile(localFile, []byte(testHTMLDocument), 0644); err != nil {
t.Fatal(err)
}
localFileURL := "file://" + localFile
drv := &Driver{}
page, err := drv.Open(context.Background(), drivers.Params{
URL: localFileURL,
})
if err != nil {
t.Error("cannot read local file, %w", err)
}
if localFileURL != string(page.GetURL()) {
t.Errorf("got: '%s', want: '%s'", page.GetURL(), localFileURL)
}
doc := page.GetMainFrame()
gotInnerText, err := doc.GetElement().GetInnerText(ctx)
if err != nil {
t.Errorf("cannot get inner text of document, %s", err)
} else if testInnerText != gotInnerText {
t.Errorf("got: '%s', want: '%s'", gotInnerText, testInnerText)
}
}

func TestDriver_convertToUTF8(t *testing.T) {
type args struct {
inputData string
Expand All @@ -102,11 +136,11 @@ func TestDriver_convertToUTF8(t *testing.T) {
{
name: "should convert to expected state",
args: args{
inputData: `<!DOCTYPE html><html><head><meta charset="windows-1251"/></head><body>феррет</body></html>`,
inputData: testHTMLDocument,
srcCharset: "windows-1251",
},
wantErr: false,
expected: `<!DOCTYPE html><html><head><meta charset="windows-1251"/></head><body>феррет</body></html>`,
expected: testHTMLDocument,
},
}
for _, tt := range tests {
Expand Down