Expose Tika http status code in errors returned by client methods

tika/tika.go

@@ -29,6 +29,31 @@ import (
 	"golang.org/x/net/context/ctxhttp"
 )
 
+// ClientError is returned by Client's various parse methods and
+// represents an error response from the Tika server. Example usage:
+//
+//    client := tika.NewClient(nil, tikaURL)
+//    s, err := client.Parse(context.Background(), input)
+//    var tikaErr tika.ClientError
+//    if errors.As(err, &tikaErr) {
+//        switch tikaErr.StatusCode {
+//        case http.StatusUnsupportedMediaType, http.StatusUnprocessableEntity:
+//            // Handle content related error
+//        default:
+//            // Handle possibly intermittent http error
+//        }
+//    } else if err != nil {
+//        // Handle non-http error
+//    }
+type ClientError struct {
+	// StatusCode is the HTTP status code returned by the Tika server.
+	StatusCode int
+}
+
+func (e ClientError) Error() string {
+	return fmt.Sprintf("response code %d", e.StatusCode)
+}
+
 // Client represents a connection to a Tika Server.
 type Client struct {
 	// url is the URL of the Tika Server, including the port (if necessary), but
@@ -107,7 +132,7 @@ func (c *Client) call(ctx context.Context, input io.Reader, method, path string,
 	}
 	defer resp.Body.Close()
 	if resp.StatusCode != http.StatusOK {
-		return nil, fmt.Errorf("response code %v", resp.StatusCode)
+		return nil, ClientError{resp.StatusCode}
 	}
 	return ioutil.ReadAll(resp.Body)
 }

tika/tika_test.go

@@ -19,6 +19,7 @@ package tika
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"net/http"
 	"net/http/httptest"
@@ -75,8 +76,9 @@ func TestParse(t *testing.T) {
 
 func TestParseRecursive(t *testing.T) {
 	tests := []struct {
-		response string
-		want     []string
+		response   string
+		want       []string
+		statusCode int
 	}{
 		{
 			response: `[{"X-TIKA:content":"test 1"}]`,
@@ -93,16 +95,34 @@ func TestParseRecursive(t *testing.T) {
 		{
 			response: `[]`,
 		},
+		{
+			statusCode: http.StatusUnprocessableEntity,
+		},
 	}
 	for _, test := range tests {
 		ts := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
-			fmt.Fprint(w, test.response)
+			if test.statusCode != 0 {
+				w.WriteHeader(test.statusCode)
+			} else {
+				fmt.Fprint(w, test.response)
+			}
 		}))
 		defer ts.Close()
 		c := NewClient(nil, ts.URL)
 		got, err := c.ParseRecursive(context.Background(), nil)
 		if err != nil {
-			t.Errorf("ParseRecursive returned an error: %v, want %v", err, test.want)
+			if test.statusCode != 0 {
+				var tikaErr ClientError
+				if errors.As(err, &tikaErr) {
+					if tikaErr.StatusCode != test.statusCode {
+						t.Errorf("ParseRecursive expected status code %d, got %d", test.statusCode, tikaErr.StatusCode)
+					}
+				} else {
+					t.Errorf("ParseRecursive expected TikaError, got %T", err)
+				}
+			} else {
+				t.Errorf("ParseRecursive returned an error: %v, want %v", err, test.want)
+			}
 			continue
 		}
 		if !reflect.DeepEqual(got, test.want) {