Check if URLs are using underscore character

internal/issues/errors/errors.go

@@ -71,4 +71,5 @@ const (
 	ErrorExternalLinkRedirect                    // Pages with external links to redirect URLs
 	ErrorExternalLinkBroken                      // Pages with brooken external links
 	ErrorTimeout                                 // Pages that timed out
+	ErrorUnderscoreURL                           // Pages wich URL has underscore characters
 )

internal/issues/page/reporters.go

@@ -72,5 +72,8 @@ func GetAllReporters() []*models.PageIssueReporter {
 
 		// Add timeout issue reporter
 		NewTimeoutReporter(),
+
+		// Add URL issue reports
+		NewUnderscoreURLReporter(),
 	}
 }

internal/issues/page/url.go

@@ -0,0 +1,24 @@
+package page
+
+import (
+	"net/http"
+	"strings"
+
+	"github.com/stjudewashere/seonaut/internal/issues/errors"
+	"github.com/stjudewashere/seonaut/internal/models"
+
+	"golang.org/x/net/html"
+)
+
+// Returns a report_manager.PageIssueReporter with a callback function that checks
+// if URL has undescore characters.
+func NewUnderscoreURLReporter() *models.PageIssueReporter {
+	c := func(pageReport *models.PageReport, htmlNode *html.Node, header *http.Header) bool {
+		return strings.Contains(pageReport.URL, "_")
+	}
+
+	return &models.PageIssueReporter{
+		ErrorType: errors.ErrorUnderscoreURL,
+		Callback:  c,
+	}
+}

internal/issues/page/url_test.go

@@ -0,0 +1,58 @@
+package page_test
+
+import (
+	"net/http"
+	"testing"
+
+	"github.com/stjudewashere/seonaut/internal/issues/errors"
+	"github.com/stjudewashere/seonaut/internal/issues/page"
+	"github.com/stjudewashere/seonaut/internal/models"
+
+	"golang.org/x/net/html"
+)
+
+// Test the UnderscoreURL reporter with an URL that has not an _ character.
+// The reporter should not report the issue.
+func TestNoUnderscoreURL(t *testing.T) {
+	pageReport := &models.PageReport{
+		URL:        "https://example.com/some-url",
+		Crawled:    true,
+		MediaType:  "text/html",
+		StatusCode: 200,
+		Title:      "not empty description",
+	}
+
+	reporter := page.NewUnderscoreURLReporter()
+	if reporter.ErrorType != errors.ErrorUnderscoreURL {
+		t.Errorf("TestNoIssues: error type is not correct")
+	}
+
+	reportsIssue := reporter.Callback(pageReport, &html.Node{}, &http.Header{})
+
+	if reportsIssue == true {
+		t.Errorf("TestUnderscoreURL: reportsIssue should be false")
+	}
+}
+
+// Test the UnderscoreURL reporter with an URL that has an _ character.
+// The reporter should report the issue.
+func TestUnderscoreURL(t *testing.T) {
+	pageReport := &models.PageReport{
+		URL:        "https://example.com/some_url",
+		Crawled:    true,
+		MediaType:  "text/html",
+		StatusCode: 200,
+		Title:      "not empty description",
+	}
+
+	reporter := page.NewUnderscoreURLReporter()
+	if reporter.ErrorType != errors.ErrorUnderscoreURL {
+		t.Errorf("TestNoIssues: error type is not correct")
+	}
+
+	reportsIssue := reporter.Callback(pageReport, &html.Node{}, &http.Header{})
+
+	if reportsIssue == false {
+		t.Errorf("TestUnderscoreURL: reportsIssue should be true")
+	}
+}

migrations/0054_underscore_url_issue.down.sql

@@ -0,0 +1 @@
+DELETE FROM issue_types WHERE id = 63;

migrations/0054_underscore_url_issue.up.sql

@@ -0,0 +1 @@
+INSERT INTO issue_types (id, type, priority) VALUES(63, "ERROR_UNDERSCORE_URL", 3);

translations/translation.en.yaml

@@ -208,4 +208,7 @@ ERROR_EXTERNAL_LINK_BROKEN: Pages with broken external links
 ERROR_EXTERNAL_LINK_BROKEN_DESC: Broken external links don't impact your site's search engine rankings, but they can frustrate users by leading them to non-existent pages. Fix this by removing or updating the link with the correct URL.
 
 ERROR_TIMEOUT: Timeout
-ERROR_TIMEOUT_DESC: Pages that timed out when our crawler attempted to access them. When this happens, search engine crawlers may fail to access and index the content, suggesting potential server issues or temporary problems hindering visibility in search results.
+ERROR_TIMEOUT_DESC: Pages that timed out when our crawler attempted to access them. When this happens, search engine crawlers may fail to access and index the content, suggesting potential server issues or temporary problems hindering visibility in search results.
+
+ERROR_UNDERSCORE_URL: URLs with underscore characters
+ERROR_UNDERSCORE_URL_DESC: It is usually not recommended to use underscore characters in URLs, as some search engines will ignore them and treat that part as a single word. Use a dash instead as a word separator character.