Merge branch 'open-dev' into open

go.mod

@@ -3,7 +3,7 @@ module github.com/stjudewashere/seonaut
 go 1.23
 
 require (
-	github.com/antchfx/htmlquery v1.3.2
+	github.com/antchfx/htmlquery v1.3.3
 	github.com/go-sql-driver/mysql v1.8.1
 	github.com/golang-migrate/migrate/v4 v4.18.1
 	github.com/google/uuid v1.6.0
@@ -15,15 +15,15 @@ require (
 	github.com/spf13/viper v1.19.0
 	github.com/temoto/robotstxt v1.1.2
 	github.com/turk/go-sitemap v0.0.0-20210912154218-82ad01095e30
-	golang.org/x/crypto v0.27.0
-	golang.org/x/net v0.29.0
-	golang.org/x/text v0.18.0
+	golang.org/x/crypto v0.28.0
+	golang.org/x/net v0.30.0
+	golang.org/x/text v0.19.0
 	gopkg.in/yaml.v3 v3.0.1
 )
 
 require (
 	filippo.io/edwards25519 v1.1.0 // indirect
-	github.com/antchfx/xpath v1.3.1 // indirect
+	github.com/antchfx/xpath v1.3.2 // indirect
 	github.com/aymerick/douceur v0.2.0 // indirect
 	github.com/fsnotify/fsnotify v1.7.0 // indirect
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
@@ -43,7 +43,7 @@ require (
 	github.com/subosito/gotenv v1.6.0 // indirect
 	go.uber.org/atomic v1.11.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
-	golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 // indirect
-	golang.org/x/sys v0.25.0 // indirect
+	golang.org/x/exp v0.0.0-20241009180824-f66d83c29e7c // indirect
+	golang.org/x/sys v0.26.0 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
 )

go.sum

@@ -4,10 +4,10 @@ github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 h1:L/gRVlceqvL25
 github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E=
 github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
 github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
-github.com/antchfx/htmlquery v1.3.2 h1:85YdttVkR1rAY+Oiv/nKI4FCimID+NXhDn82kz3mEvs=
-github.com/antchfx/htmlquery v1.3.2/go.mod h1:1mbkcEgEarAokJiWhTfr4hR06w/q2ZZjnYLrDt6CTUk=
-github.com/antchfx/xpath v1.3.1 h1:PNbFuUqHwWl0xRjvUPjJ95Agbmdj2uzzIwmQKgu4oCk=
-github.com/antchfx/xpath v1.3.1/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs=
+github.com/antchfx/htmlquery v1.3.3 h1:x6tVzrRhVNfECDaVxnZi1mEGrQg3mjE/rxbH2Pe6dNE=
+github.com/antchfx/htmlquery v1.3.3/go.mod h1:WeU3N7/rL6mb6dCwtE30dURBnBieKDC/fR8t6X+cKjU=
+github.com/antchfx/xpath v1.3.2 h1:LNjzlsSjinu3bQpw9hWMY9ocB80oLOWuQqFvO6xt51U=
+github.com/antchfx/xpath v1.3.2/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs=
 github.com/aymerick/douceur v0.2.0 h1:Mv+mAeH1Q+n9Fr+oyamOlAkUNPWPlA8PPGR0QAaYuPk=
 github.com/aymerick/douceur v0.2.0/go.mod h1:wlT5vV2O3h55X9m7iVYN0TBM0NH/MmbLnd30/FjWUq4=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -135,17 +135,17 @@ go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
 go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.27.0 h1:GXm2NjJrPaiv/h1tb2UH8QfgC/hOf/+z0p6PT8o1w7A=
-golang.org/x/crypto v0.27.0/go.mod h1:1Xngt8kV6Dvbssa53Ziq6Eqn0HqbZi5Z6R0ZpwQzt70=
-golang.org/x/exp v0.0.0-20240909161429-701f63a606c0 h1:e66Fs6Z+fZTbFBAxKfP3PALWBtpfqks2bwGcexMxgtk=
-golang.org/x/exp v0.0.0-20240909161429-701f63a606c0/go.mod h1:2TbTHSBQa924w8M6Xs1QcRcFwyucIwBGpK1p2f1YFFY=
+golang.org/x/crypto v0.28.0 h1:GBDwsMXVQi34v5CCYUm2jkJvu4cbtru2U4TN2PSyQnw=
+golang.org/x/crypto v0.28.0/go.mod h1:rmgy+3RHxRZMyY0jjAJShp2zgEdOqj2AO7U0pYmeQ7U=
+golang.org/x/exp v0.0.0-20241009180824-f66d83c29e7c h1:7dEasQXItcW1xKJ2+gg5VOiBnqWrJc+rq0DPKyvvdbY=
+golang.org/x/exp v0.0.0-20241009180824-f66d83c29e7c/go.mod h1:NQtJDoLvd6faHhE7m4T/1IY708gDefGGjR/iUW8yQQ8=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
 golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
-golang.org/x/net v0.29.0 h1:5ORfpBpCs4HzDYoodCDBbwHzdR5UrLBZ3sOnUJmFoHo=
-golang.org/x/net v0.29.0/go.mod h1:gLkgy8jTGERgjzMic6DS9+SP0ajcu6Xu3Orq/SpETg0=
+golang.org/x/net v0.30.0 h1:AcW1SDZMkb8IpzCdQUaIq2sP4sZ4zw+55h6ynffypl4=
+golang.org/x/net v0.30.0/go.mod h1:2wGyMJ5iFasEhkwi13ChkO/t1ECNC4X4eBKkVFyYFlU=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -154,17 +154,17 @@ golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.25.0 h1:r+8e+loiHxRqhXVl6ML1nO3l1+oFoWbnlu2Ehimmi34=
-golang.org/x/sys v0.25.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.26.0 h1:KHjCJyddX0LoSTb3J+vWpupP9p0oznkqVk/IfjymZbo=
+golang.org/x/sys v0.26.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
-golang.org/x/text v0.18.0 h1:XvMDiNzPAl0jr17s6W9lcaIhGUfUORdGCNsuLmPG224=
-golang.org/x/text v0.18.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
+golang.org/x/text v0.19.0 h1:kTxAhCbGbxhK0IwgSKiMO5awPoDQ0RpfiVYBfK860YM=
+golang.org/x/text v0.19.0/go.mod h1:BuEKDfySbSR4drPmRPG/7iBdf8hvFMuRexcpahXilzY=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=

internal/issues/errors/errors.go

@@ -81,4 +81,5 @@ const (
 	ErrorMissingImgElement                       // Pages with Picture missing the img element
 	ErrorMetasInBody                             // Pages with meta tags in the document's body
 	ErrorNosnippet                               // Pages with the nosnippet directive
+	ErrorImgWithoutSize                          // Pages with img elements that have no size attribtues
 )

internal/issues/page/images.go

@@ -133,3 +133,37 @@ func NewMissingImgTagInPictureReporter() *models.PageIssueReporter {
 		Callback:  c,
 	}
 }
+
+// Returns a report_manager.PageIssueReporter with a callback function to check
+// if a page has img elements without width or height attributes.
+func NewImgWithoutSizeReporter() *models.PageIssueReporter {
+	c := func(pageReport *models.PageReport, htmlNode *html.Node, header *http.Header) bool {
+		if !pageReport.Crawled {
+			return false
+		}
+
+		if pageReport.MediaType != "text/html" {
+			return false
+		}
+
+		e := htmlquery.Find(htmlNode, "//img")
+		for _, n := range e {
+			w := htmlquery.SelectAttr(n, "width")
+			if w == "" {
+				return true
+			}
+
+			h := htmlquery.SelectAttr(n, "height")
+			if h == "" {
+				return true
+			}
+		}
+
+		return false
+	}
+
+	return &models.PageIssueReporter{
+		ErrorType: errors.ErrorImgWithoutSize,
+		Callback:  c,
+	}
+}

internal/issues/page/images_test.go

@@ -264,3 +264,110 @@ func TestMissingImgTagInPictureReporterIssues(t *testing.T) {
 		t.Errorf("reportsIssue should be true")
 	}
 }
+
+// Test the NewImgWithoutSizeReporter reporter with a pageReport that the img elements
+// with size attributes. The reporter should not report the issue.
+func TestImgWithoutSizeReporterNoIssues(t *testing.T) {
+	pageReport := &models.PageReport{
+		Crawled:   true,
+		MediaType: "text/html",
+	}
+
+	reporter := page.NewImgWithoutSizeReporter()
+	if reporter.ErrorType != errors.ErrorImgWithoutSize {
+		t.Errorf("error type is not correct")
+	}
+
+	source := `
+	<html>
+		<body>
+			<img src="example.jpg" width="80vw" height="100%">
+			<img src="example-2.jpg" width="400" height="400">
+		</body>
+	</html>
+`
+
+	doc, err := html.Parse(strings.NewReader(source))
+	if err != nil {
+		t.Errorf("error parsing html source")
+	}
+
+	reportsIssue := reporter.Callback(pageReport, doc, &http.Header{})
+
+	if reportsIssue == true {
+		t.Errorf("reportsIssue should be false")
+	}
+}
+
+// Test the NewImgWithoutSizeReporter reporter with a pageReport that the img elements
+// without size attributes. The reporter should report the issue.
+func TestImgWithoutSizeReporterIssues(t *testing.T) {
+	pageReport := &models.PageReport{
+		Crawled:   true,
+		MediaType: "text/html",
+	}
+
+	reporter := page.NewImgWithoutSizeReporter()
+	if reporter.ErrorType != errors.ErrorImgWithoutSize {
+		t.Errorf("error type is not correct")
+	}
+
+	source := `
+	<html>
+		<body>
+			<img src="example.jpg">
+		</body>
+	</html>
+`
+
+	doc, err := html.Parse(strings.NewReader(source))
+	if err != nil {
+		t.Errorf("error parsing html source")
+	}
+
+	reportsIssue := reporter.Callback(pageReport, doc, &http.Header{})
+
+	if reportsIssue == false {
+		t.Errorf("reportsIssue should be true")
+	}
+
+	// Test img only with the height attribute.
+	source = `
+	<html>
+		<body>
+			<img src="example.jpg" height="200">
+		</body>
+	</html>
+`
+
+	doc, err = html.Parse(strings.NewReader(source))
+	if err != nil {
+		t.Errorf("error parsing html source")
+	}
+
+	reportsIssue = reporter.Callback(pageReport, doc, &http.Header{})
+
+	if reportsIssue == false {
+		t.Errorf("reportsIssue should be true")
+	}
+
+	// Test img only with the width attribute.
+	source = `
+		<html>
+			<body>
+				<img src="example.jpg" width="200">
+			</body>
+		</html>
+	`
+
+	doc, err = html.Parse(strings.NewReader(source))
+	if err != nil {
+		t.Errorf("error parsing html source")
+	}
+
+	reportsIssue = reporter.Callback(pageReport, doc, &http.Header{})
+
+	if reportsIssue == false {
+		t.Errorf("reportsIssue should be true")
+	}
+}

internal/issues/page/reporters.go

@@ -50,6 +50,7 @@ func GetAllReporters() []*models.PageIssueReporter {
 		NewLargeImageReporter(),
 		NewNoImageIndexReporter(),
 		NewMissingImgTagInPictureReporter(),
+		NewImgWithoutSizeReporter(),
 
 		// Add language issue reporters
 		NewInvalidLangReporter(),

internal/services/renderer.go

@@ -6,6 +6,8 @@ import (
 	"io"
 	"log"
 	"os"
+	"path/filepath"
+	"strings"
 	"time"
 
 	"gopkg.in/yaml.v3"
@@ -20,6 +22,7 @@ type (
 	Renderer struct {
 		translationMap map[string]interface{}
 		config         *RendererConfig
+		templates      *template.Template
 	}
 )
 
@@ -41,20 +44,22 @@ func NewRenderer(config *RendererConfig) (*Renderer, error) {
 		config:         config,
 	}
 
+	r.templates, err = findAndParseTemplates(config.TemplatesFolder, template.FuncMap{
+		"trans":      r.trans,
+		"total_time": r.totalTime,
+		"add":        r.add,
+		"to_kb":      r.ToKByte,
+	})
+	if err != nil {
+		return nil, fmt.Errorf("renderer initialisation failed: %w", err)
+	}
+
 	return r, nil
 }
 
 // Render a template with the specified PageView data.
 func (r *Renderer) RenderTemplate(w io.Writer, t string, v interface{}) {
-	var templates = template.Must(
-		template.New("").Funcs(template.FuncMap{
-			"trans":      r.trans,
-			"total_time": r.totalTime,
-			"add":        r.add,
-			"to_kb":      r.ToKByte,
-		}).ParseGlob(r.config.TemplatesFolder + "/*.html"))
-
-	err := templates.ExecuteTemplate(w, t+".html", v)
+	err := r.templates.ExecuteTemplate(w, t+".html", v)
 	if err != nil {
 		log.Printf("RenderTemplate: %v\n", err)
 	}
@@ -97,3 +102,35 @@ func (r *Renderer) ToKByte(b int64) string {
 
 	return formatted
 }
+
+// findAndParseTemplates locates and parses all HTML template files in the specified directory.
+// It returns the Template object and an error if any issues occur during parsing.
+func findAndParseTemplates(rootDir string, funcMap template.FuncMap) (*template.Template, error) {
+	cleanRoot := filepath.Clean(rootDir)
+	pfx := len(cleanRoot) + 1
+	root := template.New("")
+
+	err := filepath.Walk(cleanRoot, func(path string, info os.FileInfo, e1 error) error {
+		if !info.IsDir() && strings.HasSuffix(path, ".html") {
+			if e1 != nil {
+				return fmt.Errorf("file walk error: %w", e1)
+			}
+
+			b, e2 := os.ReadFile(path)
+			if e2 != nil {
+				return fmt.Errorf("read file %s error: %w", path, e2)
+			}
+
+			name := path[pfx:]
+			t := root.New(name).Funcs(funcMap)
+			_, e2 = t.Parse(string(b))
+			if e2 != nil {
+				return fmt.Errorf("parse template %s error: %w", name, e2)
+			}
+		}
+
+		return nil
+	})
+
+	return root, err
+}

migrations/0065_img_size.down.sql

@@ -0,0 +1 @@
+DELETE FROM issue_types WHERE id = 73;

migrations/0065_img_size.up.sql

@@ -0,0 +1 @@
+INSERT INTO issue_types (id, type, priority) VALUES(73, "ERROR_IMG_SIZE_ATTR", 3);

translations/translation.en.yaml

@@ -238,4 +238,7 @@ ERROR_METAS_IN_BODY: Pages with meta tags in the document's body
 ERROR_METAS_IN_BODY_DESC: Pages that have meta tags in the document's body. The meta tags must be placed in the head section of the document, otherwise they may get ignored by browsers as well as search engines, causing indexability issues.
 
 ERROR_NOSNIPPET: Pages with the nosnippet directive
-ERROR_NOSNIPPET_DESC: The nosnippet or max-snippet:0 directives tell search engines not to display a text snippet or video preview in the search results. Review these pages to make sure this is the wanted behavior.
+ERROR_NOSNIPPET_DESC: The nosnippet or max-snippet:0 directives tell search engines not to display a text snippet or video preview in the search results. Review these pages to make sure this is the wanted behavior.
+
+ERROR_IMG_SIZE_ATTR: Pages containing images missing size attributes
+ERROR_IMG_SIZE_ATTR_DESC: Not setting the size attributes for images can cause layout shifts as the page loads, which can negatively impact user experience as well as SEO. Make sure your images have the corresponding size attributes in place.