Merge branch 'main' of https://github.com/ahobsonsayers/abs-tract

README.md

@@ -100,14 +100,16 @@ and enter the following details:
 ### Goodreads
 
 - Name: **GoodReads**
-- URL: **http://<your_address>:5555/goodreads**
-- Authorization Header Value: **<leave this unset>**
+- URL: `http://<your_address>:5555/goodreads`
+  - e.g. `192.168.1.100:5555/goodreads`
+- Authorization Header Value: **Leave this unset**
 
 ### Kindle
 
 - Name: **Kindle**
-- URL: **http://<your_address>:5555/kindle/<your_region>**
-- Authorization Header Value: **<leave this unset>**
+- URL: `http://<your_address>:5555/kindle/<your_region>`
+  - e.g. `192.168.1.100:5555/kindle/uk`
+- Authorization Header Value: **Leave this unset**
 
 Region can be one of the following:
 
@@ -122,10 +124,6 @@ Region can be one of the following:
 - uk - United Kingdom
 - us - United States
 
-### Setup video walkthrough:
-
-https://github.com/ahobsonsayers/abs-tract/assets/32173585/54437af6-a17c-4458-bb82-479b183171da
-
 ## FAQ
 
 ### Why is Goodreads not returning covers?

go.mod

@@ -3,6 +3,7 @@ module github.com/ahobsonsayers/abs-tract
 go 1.21
 
 require (
+	github.com/adrg/strutil v0.3.1
 	github.com/antchfx/htmlquery v1.3.1
 	github.com/antchfx/xpath v1.3.0
 	github.com/deckarep/golang-set/v2 v2.6.0
@@ -12,7 +13,6 @@ require (
 	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/lithammer/fuzzysearch v1.1.8
 	github.com/oapi-codegen/nethttp-middleware v1.0.1
 	github.com/oapi-codegen/runtime v1.1.1
 	github.com/orsinium-labs/enum v1.4.0

go.sum

@@ -1,4 +1,6 @@
 github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
+github.com/adrg/strutil v0.3.1 h1:OLvSS7CSJO8lBii4YmBt8jiK9QOtB9CzCzwl4Ic/Fz4=
+github.com/adrg/strutil v0.3.1/go.mod h1:8h90y18QLrs11IBffcGX3NW/GFBXCMcNg4M7H6MspPA=
 github.com/antchfx/htmlquery v1.3.1 h1:wm0LxjLMsZhRHfQKKZscDf2COyH4vDYA3wyH+qZ+Ylc=
 github.com/antchfx/htmlquery v1.3.1/go.mod h1:PTj+f1V2zksPlwNt7uVvZPsxpKNa7mlVliCRxLX6Nx8=
 github.com/antchfx/xpath v1.3.0 h1:nTMlzGAK3IJ0bPpME2urTuFL76o4A96iYvoKFHRXJgc=
@@ -52,8 +54,6 @@ github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
-github.com/lithammer/fuzzysearch v1.1.8 h1:/HIuJnjHuXS8bKaiTMeeDlW2/AyIWk2brx1V8LFgLN4=
-github.com/lithammer/fuzzysearch v1.1.8/go.mod h1:IdqeyBClc3FFqSzYq/MXESsS4S0FsZ5ajtkr5xPLts4=
 github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
 github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
 github.com/matryer/is v1.4.1 h1:55ehd8zaGABKLXQUe2awZ99BD/PTc2ls+KV/dXphgEQ=
@@ -84,6 +84,7 @@ github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UV
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 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=
@@ -96,20 +97,17 @@ golang.org/x/exp v0.0.0-20220303212507-bbda1eaf7a17/go.mod h1:lgLbSvA5ygNOMpwM/9
 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 v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
-golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 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/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 v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.19.0 h1:zTwKpTd2XuCqf8huc7Fo2iSy+4RHPd10s4KzeTnVr1c=
 golang.org/x/net v0.19.0/go.mod h1:CfAk/cbD4CthTvqiEl8NpboMuiuOYsAr/7NOjZJtv1U=
 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/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -125,14 +123,12 @@ 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 v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
 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 v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190328211700-ab21143f2384/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
 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=
-golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
 golang.org/x/tools v0.12.0 h1:YW6HUoUmYBpwSgyaGaZq1fHjrBjX1rlpZ54T6mu2kss=
 golang.org/x/tools v0.12.0/go.mod h1:Sc0INKfu04TlqNoRA1hgpFZbhYXHPr4V5DzpSBTPqQM=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

goodreads/book.go

@@ -13,7 +13,9 @@ import (
 )
 
 var (
+	// These are dirty workarounds, but they seem to work
 	alternativeCoverRegex = regexp.MustCompile(`^\s*<i>.*[Aa]lternat(iv)?e cover.*</i>\s*$`)
+	breakTagRegex         = regexp.MustCompile(`<br\s*/?>`)
 	lastBracketRegex      = regexp.MustCompile(`^(.*)(\([^\(\)]*\))([^()]*)$`)
 )
 
@@ -65,7 +67,7 @@ func (b *Book) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error {
 }
 
 type Work struct {
-	Title         string `xml:"original_title"`
+	FullTitle     string `xml:"original_title"`
 	MediaType     string `xml:"media_type"`
 	EditionsCount int    `xml:"books_count"`
 
@@ -81,6 +83,23 @@ type Work struct {
 	RatingDistribution string `xml:"rating_dist"`
 }
 
+// Title is the full title with any subtitle removed.
+// A subtitle is anything after the first : in the full title
+func (w Work) Title() string {
+	titleParts := strings.Split(w.FullTitle, ":")
+	return strings.TrimSpace(titleParts[0])
+}
+
+// Subtitle is the subtle part of the full title.
+// A subtitle is anything after the first : in the full title
+func (w Work) Subtitle() string {
+	colonIdx := strings.Index(w.FullTitle, ":")
+	if colonIdx == -1 {
+		return ""
+	}
+	return strings.TrimSpace(w.FullTitle[colonIdx+1:])
+}
+
 func (w Work) AverageRating() float64 {
 	averageRating := float64(w.RatingsSum) / float64(w.RatingsCount)
 	return math.Round(averageRating*100) / 100 // Round to two decimal places
@@ -89,7 +108,7 @@ func (w Work) AverageRating() float64 {
 type Edition struct {
 	Id               string  `xml:"id"`
 	ISBN             *string `xml:"isbn13"`
-	Title            string  `xml:"title"`
+	FullTitle        string  `xml:"title"`
 	Description      string  `xml:"description"`
 	NumPages         string  `xml:"num_pages"`
 	ImageURL         string  `xml:"image_url"`
@@ -103,11 +122,31 @@ type Edition struct {
 	Language         string  `xml:"language_code"`
 }
 
+// Title is the full title with any subtitle removed.
+// A subtitle is anything after the first : in the full title
+func (e Edition) Title() string {
+	titleParts := strings.Split(e.FullTitle, ":")
+	return strings.TrimSpace(titleParts[0])
+}
+
+// Subtitle is the subtle part of the full title.
+// A subtitle is anything after the first : in the full title
+func (e Edition) Subtitle() string {
+	colonIdx := strings.Index(e.FullTitle, ":")
+	if colonIdx == -1 {
+		return ""
+	}
+	return strings.TrimSpace(e.FullTitle[colonIdx+1:])
+}
+
 func (e *Edition) Sanitise() {
 	// Description can sometimes be html and contain preamble about alternative covers
+	// Break tags need to be specially handled to add new lines as html2text does
+	// not convert them to new lines properly
 	description := strings.TrimSpace(e.Description)
 	description = alternativeCoverRegex.ReplaceAllString(description, "")
-	description = html2text.HTML2Text(description)
+	description = breakTagRegex.ReplaceAllString(description, "\n")
+	description = html2text.HTML2TextWithOptions(description, html2text.WithUnixLineBreaks())
 	e.Description = description
 
 	// Get original cover image by cleaning the ul0

goodreads/goodreads.go

@@ -9,12 +9,9 @@ import (
 	"net/http"
 	"net/url"
 	"regexp"
-	"strconv"
-	"strings"
 	"sync"
 
 	"github.com/ahobsonsayers/abs-tract/utils"
-	"github.com/lithammer/fuzzysearch/fuzzy"
 	"github.com/orsinium-labs/enum"
 	"github.com/samber/lo"
 )
@@ -32,11 +29,6 @@ var (
 		goodreadsUrl: utils.CloneURL(defaultGoodreadsUrl),
 		apiKey:       DefaultAPIKey,
 	}
-
-	bookSearchTypeEnum   = enum.NewBuilder[string, BookSearchType]()
-	BookSearchTypeTitle  = bookSearchTypeEnum.Add(BookSearchType{"title"})
-	BookSearchTypeAuthor = bookSearchTypeEnum.Add(BookSearchType{"author"})
-	BookSearchTypes      = bookSearchTypeEnum.Enum()
 )
 
 type BookSearchType enum.Member[string]
@@ -150,7 +142,7 @@ func (c *Client) GetBooksByIds(ctx context.Context, bookIds []string) ([]Book, e
 	// Only return books whose work have a title
 	validBooks := make([]Book, 0, len(books))
 	for _, book := range books {
-		if book.Work.Title != "" {
+		if book.Work.FullTitle != "" {
 			validBooks = append(validBooks, book)
 		}
 	}
@@ -176,157 +168,3 @@ func (c *Client) GetBookByTitle(ctx context.Context, bookTitle string, bookAutho
 
 	return result.Work, nil
 }
-
-// SearchBooks search for a book by its title and optionally an author (which can give better results)
-// https://www.goodreads.com/api/index#search.books
-func (c *Client) SearchBooks(ctx context.Context, bookTitle string, bookAuthor *string) ([]Book, error) {
-	var bookOverviews []BookOverview
-	var err error
-	if bookAuthor == nil || *bookAuthor == "" {
-		// If author is not set, search for books by title
-		bookOverviews, err = c.searchBooksManyPages(ctx, searchBooksManyPagesInput{
-			Query:      bookTitle,
-			SearchType: BookSearchTypeTitle,
-			Page:       1,
-			NumPages:   5,
-		})
-		if err != nil {
-			return nil, err
-		}
-
-	} else {
-		// If author is set, search for books by author ONLY.
-		// We will then search the authors books for title.
-		// We do NOT search goodreads by title AND author together using the 'all' search type
-		// as goodreads returns awful results, including sometimes none at all.
-		authorBookOverviews, err := c.searchBooksManyPages(ctx, searchBooksManyPagesInput{
-			Query:      *bookAuthor,
-			SearchType: BookSearchTypeAuthor,
-			Page:       1,
-			NumPages:   15,
-		})
-		if err != nil {
-			return nil, err
-		}
-
-		// In author books, find books that (fuzzily) match the title
-		authorBookOverviewMatches := fuzzy.RankFindNormalizedFold(bookTitle, BookTitles(authorBookOverviews))
-
-		// Use matched author books for the book overviews. User order returned by goodreads
-		matchedBookOverviews := make([]BookOverview, 0, len(authorBookOverviewMatches))
-		for _, match := range authorBookOverviewMatches {
-			matchedBookOverviews = append(matchedBookOverviews, authorBookOverviews[match.OriginalIndex])
-		}
-		bookOverviews = matchedBookOverviews
-	}
-
-	// Get book details using their ids
-	bookDetails, err := c.GetBooksByIds(ctx, BookIds(bookOverviews))
-	if err != nil {
-		return nil, err
-	}
-
-	return bookDetails, nil
-}
-
-type searchBooksSinglePageInput struct {
-	Query      string
-	SearchType BookSearchType
-	Page       int
-}
-
-// searchBooksPage searches for books and returns the requested page of results.
-// If Query is not set, no search will be performed and no results will be returned.
-// If search type is unset or invalid, search will fallback to a title search
-// If page is < 1, first page of results is returned.
-func (c *Client) searchBooksSinglePage(ctx context.Context, input searchBooksSinglePageInput) ([]BookOverview, error) {
-	input.Query = strings.TrimSpace(input.Query)
-	if input.Query == "" {
-		return nil, nil
-	}
-	if !BookSearchTypes.Contains(input.SearchType) {
-		// Default to title search
-		input.SearchType = BookSearchTypeTitle
-	}
-	if input.Page < 1 {
-		input.Page = 1
-	}
-
-	queryParams := map[string]string{
-		"q":             input.Query,
-		"search[field]": input.SearchType.Value,
-		"page":          strconv.Itoa(input.Page),
-	}
-	var unmarshaller struct {
-		Books []BookOverview `xml:"search>results>work>best_book"`
-	}
-	err := c.get(ctx, "search/index.xml", queryParams, &unmarshaller)
-	if err != nil {
-		return nil, err
-	}
-
-	// Sanitise the books
-	books := make([]BookOverview, 0, len(unmarshaller.Books))
-	for _, book := range unmarshaller.Books {
-		book.Sanitise()
-		books = append(books, book)
-	}
-
-	return books, nil
-}
-
-type searchBooksManyPagesInput struct {
-	Query      string
-	SearchType BookSearchType
-	Page       int
-	NumPages   int
-}
-
-// searchBooksManyPages searches for books and returns (flattened) results from the request number of pages.
-// Arguments are the same as searchBooks except for NumPages. If NumPages < 1, a single page of results
-// will be returned
-func (c *Client) searchBooksManyPages(ctx context.Context, input searchBooksManyPagesInput) ([]BookOverview, error) {
-	if input.Page < 1 {
-		input.Page = 1
-	}
-	if input.NumPages < 1 {
-		input.NumPages = 1
-	}
-
-	bookPages := make([][]BookOverview, input.NumPages)
-	var errs error
-
-	var wg sync.WaitGroup
-	var bookIdsMutex sync.Mutex
-	var errsMutex sync.Mutex
-
-	// Get 5 pages of books. This should be enough
-	for idx := 0; idx < input.NumPages; idx++ {
-		wg.Add(1)
-
-		go func(idx int) {
-			defer wg.Done()
-
-			pageBooks, err := c.searchBooksSinglePage(
-				ctx, searchBooksSinglePageInput{
-					Query:      input.Query,
-					SearchType: input.SearchType,
-					Page:       input.Page + idx,
-				},
-			)
-			if err != nil {
-				errsMutex.Lock()
-				errs = errors.Join(errs, err)
-				errsMutex.Unlock()
-				return
-			}
-
-			bookIdsMutex.Lock()
-			bookPages[idx] = pageBooks
-			bookIdsMutex.Unlock()
-		}(idx)
-	}
-	wg.Wait()
-
-	return lo.Flatten(bookPages), errs
-}