Sanitise method to get better descriptions and covers

Author: ahobsonsayers

.golangci.yaml

@@ -27,7 +27,7 @@ linters-settings:
 
       - name: var-naming
         arguments:
-          - ["ID", "JSON", "URL"] # Allow List
+          - ["ID", "IDS", "JSON", "URL"] # Allow List
           - [] # Deny List
 
   # https://golangci-lint.run/usage/linters/#stylecheck

go.mod

@@ -9,6 +9,7 @@ require (
 	github.com/go-chi/chi/v5 v5.0.12
 	github.com/go-chi/httplog/v2 v2.0.9
 	github.com/jinzhu/inflection v1.0.0
+	github.com/k3a/html2text v1.2.1
 	github.com/oapi-codegen/nethttp-middleware v1.0.1
 	github.com/oapi-codegen/runtime v1.1.1
 	github.com/stretchr/testify v1.9.0

go.sum

@@ -25,6 +25,8 @@ github.com/go-test/deep v1.0.8 h1:TDsG77qcSprGbC6vTN8OuXp5g+J+b5Pcguhf7Zt61VM=
 github.com/go-test/deep v1.0.8/go.mod h1:5C2ZWiW0ErCdrYzpqxLbTX7MG14M9iiw8DgHncVwcsE=
 github.com/google/uuid v1.5.0 h1:1p67kYwdtXjb0gL0BPiP1Av9wiZPo5A8z2cWkTZ+eyU=
 github.com/google/uuid v1.5.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1 h1:EGx4pi6eqNxGaHF6qqu48+N2wcFQ5qg5FXgOdqsJ5d8=
+github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
 github.com/gorilla/mux v1.8.0 h1:i40aqfkR1h2SlN9hojwV5ZA91wcXFOvkdNIeFDP5koI=
 github.com/gorilla/mux v1.8.0/go.mod h1:DVbg23sWSpFRCP0SfiEN6jmj59UnW/n46BH5rLB71So=
 github.com/invopop/yaml v0.2.0 h1:7zky/qH+O0DwAyoobXUqvVBwgBFRxKoQ/3FjcVpjTMY=
@@ -33,7 +35,11 @@ github.com/jinzhu/inflection v1.0.0 h1:K317FqzuhWc8YvSVlFMCCUb36O/S9MCKRDI7QkRKD
 github.com/jinzhu/inflection v1.0.0/go.mod h1:h+uFLlag+Qp1Va5pdKtLDYj+kHp5pxUVkryuEj+Srlc=
 github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
 github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
+github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
+github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
 github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
+github.com/k3a/html2text v1.2.1 h1:nvnKgBvBR/myqrwfLuiqecUtaK1lB9hGziIJKatNFVY=
+github.com/k3a/html2text v1.2.1/go.mod h1:ieEXykM67iT8lTvEWBh6fhpH4B23kB9OMKPdIBmgUqA=
 github.com/kr/pretty v0.2.1 h1:Fmg33tUaq4/8ym9TJN1x7sLJnHVwhP33CNkpYV/7rwI=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
@@ -52,6 +58,10 @@ github.com/perimeterx/marshmallow v1.1.5 h1:a2LALqQ1BlHM8PZblsDdidgv1mWi1DgC2UmX
 github.com/perimeterx/marshmallow v1.1.5/go.mod h1:dsXbUu8CRzfYP5a87xpp0xq9S3u0Vchtcl8we9tYaXw=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d h1:zE9ykElWQ6/NYmHa3jpm/yHnI4xSofP+UP6SpjHcSeM=
+github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
+github.com/smartystreets/goconvey v1.6.4 h1:fv0U8FUIMPNf1L9lnHLvLhgicrIVChEkdzIKYqbNC9s=
+github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
 github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
@@ -64,14 +74,19 @@ github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsT
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
 github.com/ugorji/go/codec v1.2.11/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/lint v0.0.0-20210508222113-6edffad5e616 h1:VLliZ0d+/avPrXXH+OakdXhpJuEoBZuwh1m2j7U6Iug=
 golang.org/x/lint v0.0.0-20210508222113-6edffad5e616/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
 golang.org/x/mod v0.12.0 h1:rmsUpXtvNzj340zd98LZ4KntptpfRHwpFOHG188oHXc=
 golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.15.0 h1:h48lPFYpsTvQJZF4EKyI4aLHaev3CxivZmv7yZig9pc=
 golang.org/x/sys v0.15.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/tools v0.0.0-20190328211700-ab21143f2384/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
 golang.org/x/tools v0.12.0 h1:YW6HUoUmYBpwSgyaGaZq1fHjrBjX1rlpZ54T6mu2kss=
 golang.org/x/tools v0.12.0/go.mod h1:Sc0INKfu04TlqNoRA1hgpFZbhYXHPr4V5DzpSBTPqQM=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

goodreads/book.go

@@ -3,7 +3,10 @@ package goodreads
 import (
 	"encoding/xml"
 	"math"
+	"regexp"
 	"strings"
+
+	"github.com/k3a/html2text"
 )
 
 type Book struct {
@@ -14,21 +17,29 @@ type Book struct {
 	Genres      Genres          `xml:"popular_shelves"` // The (max) first 5 "genre" shelves
 }
 
+func (b *Book) Sanitise() {
+	b.BestEdition.Sanitise()
+	for _, series := range b.Series {
+		series.Sanitise()
+	}
+}
+
 func (b *Book) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error {
 	type alias Book
-	type unmarshaller struct {
+	var unmarshaller struct {
 		alias
 		Edition
 	}
-
-	var book unmarshaller
-	err := d.DecodeElement(&book, &start)
+	err := d.DecodeElement(&unmarshaller, &start)
 	if err != nil {
 		return err
 	}
 
-	*b = Book(book.alias)
-	b.BestEdition = book.Edition
+	*b = Book(unmarshaller.alias)
+	b.BestEdition = unmarshaller.Edition
+
+	b.Sanitise()
+
 	return nil
 }
 
@@ -72,26 +83,27 @@ type Edition struct {
 	LanguageCode     string  `xml:"language_code"`
 }
 
-// func (e *Edition) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error {
-// 	type alias Edition
-// 	var unmarshaller alias
-// 	err := d.DecodeElement(&unmarshaller, &start)
-// 	if err != nil {
-// 		return err
-// 	}
-// 	*e = Edition(unmarshaller)
+func (e *Edition) Sanitise() {
+	// Description can sometimes be html, so convert to plain text
+	e.Description = html2text.HTML2Text(e.Description)
 
-// 	// Cleanup some fields
-// 	e.Description = html2text.HTML2Text(e.Description)
-
-// 	return nil
-// }
+	// Get largest image by removing anything between the last number and the extensions
+	// For Example:
+	// https://i.gr-assets.com/images/S/compressed.photo.goodreads.com/books/1546071216l/5907._SX98_.jpg"
+	// Should be:
+	// "https://i.gr-assets.com/images/S/compressed.photo.goodreads.com/books/1546071216l/5907.jpg"
+	e.ImageURL = (regexp.MustCompile(`(\d+)\..*?\.(jpe?g)`).ReplaceAllString(e.ImageURL, "$1.$2"))
+}
 
 type SeriesBook struct {
 	Series       Series  `xml:"series"`
 	BookPosition *string `xml:"user_position"`
 }
 
+func (s *SeriesBook) Sanitise() {
+	s.Series.Sanitise()
+}
+
 type Series struct {
 	Id               string `xml:"id"`
 	Title            string `xml:"title"`
@@ -101,18 +113,7 @@ type Series struct {
 	Numbered         bool   `xml:"numbered"`
 }
 
-func (s *Series) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error {
-	type alias Series
-	var unmarshaller alias
-	err := d.DecodeElement(&unmarshaller, &start)
-	if err != nil {
-		return err
-	}
-	*s = Series(unmarshaller)
-
-	// Cleanup some fields
+func (s *Series) Sanitise() {
 	s.Title = strings.TrimSpace(s.Title)
 	s.Description = strings.TrimSpace(s.Description)
-
-	return nil
 }

server/router.go

@@ -50,9 +50,8 @@ func NewRouter() (http.Handler, error) {
 			&oapimiddleware.Options{
 				SilenceServersWarning: true,
 				Options: openapi3filter.Options{
-					AuthenticationFunc: func(ctx context.Context, authInput *openapi3filter.AuthenticationInput) error {
-						// Skip auth
-						return nil
+					AuthenticationFunc: func(_ context.Context, _ *openapi3filter.AuthenticationInput) error {
+						return nil // Do nothing
 					},
 				},
 			},