feat: process HTML on comment text

* feat: client-side katex.js

* docs: add katex attribution

.air.toml

@@ -23,7 +23,7 @@ tmp_dir = "tmp"
   rerun = false
   rerun_delay = 500
   send_interrupt = false
-  stop_on_error = false
+  stop_on_error = true
 
 [color]
   app = ""

.github/workflows/docker-image.yml

@@ -0,0 +1,47 @@
+name: Create and publish a Docker image
+
+# Configures this workflow to run every time a change is pushed to the branch called `release`.
+on:
+    push:
+        branches: ['release']
+
+# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
+env:
+    REGISTRY: ghcr.io
+    IMAGE_NAME: ${{ github.repository }}
+
+# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
+jobs:
+    build-and-push-image:
+        runs-on: ubuntu-latest
+        # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
+        permissions:
+            contents: read
+            packages: write
+            #
+        steps:
+            - name: Checkout repository
+              uses: actions/checkout@v4
+            # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
+            - name: Log in to the Container registry
+              uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
+              with:
+                  registry: ${{ env.REGISTRY }}
+                  username: ${{ github.actor }}
+                  password: ${{ secrets.GITHUB_TOKEN }}
+            # This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
+            - name: Extract metadata (tags, labels) for Docker
+              id: meta
+              uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
+              with:
+                  images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+            # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
+            # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
+            # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
+            - name: Build and push Docker image
+              uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
+              with:
+                  context: .
+                  push: true
+                  tags: ${{ steps.meta.outputs.tags }}
+                  labels: ${{ steps.meta.outputs.labels }}

README.md

@@ -14,26 +14,30 @@ This project is super lightweight by design. The UI is simple and the frontend i
 
 ## Clearnet Instances
 
-| Instance URL                                                                    | Region                          | Notes                                                                                            |
+| Instance URL                                                                              | Region                          | Notes                                                                                            |
-| ------------------------------------------------------------------------------- | ------------------------------- | ------------------------------------------------------------------------------------------------ |
+| ----------------------------------------------------------------------------------------- | ------------------------------- | ------------------------------------------------------------------------------------------------ |
-| [code.whatever.social](https://code.whatever.social)                            | United States & The Netherlands | Operated by [Whatever Social](https://whatever.social) and [http.james](https://httpjames.space) |
+| [code.whatever.social](https://code.whatever.social)                                      | United States & The Netherlands | Operated by [Whatever Social](https://whatever.social) and [http.james](https://httpjames.space) |
-| [ao.vern.cc](https://ao.vern.cc)                                                | United States                   | Operated by [vern.cc](https://vern.cc)                                                           |
+| [ao.vern.cc](https://ao.vern.cc)                                                          | United States                   | Operated by [vern.cc](https://vern.cc)                                                           |
-| [overflow.smnz.de](https://overflow.smnz.de)                                    | Germany                         | Operated by [smnz.de](https://smnz.de)                                                           |
+| [overflow.smnz.de](https://overflow.smnz.de)                                              | Germany                         | Operated by [smnz.de](https://smnz.de)                                                           |
-| [overflow.lunar.icu](https://overflow.lunar.icu)                                | Germany                         | Operated by [lunar.icu](https://lunar.icu/)                                                      |
+| [overflow.lunar.icu](https://overflow.lunar.icu)                                          | Germany                         | Operated by [lunar.icu](https://lunar.icu/)                                                      |
-| [overflow.adminforge.de](https://overflow.adminforge.de/)                       | Germany                         | Operated by [adminForge](https://adminforge.de/)                                                 |
+| [overflow.adminforge.de](https://overflow.adminforge.de/)                                 | Germany                         | Operated by [adminForge](https://adminforge.de/)                                                 |
-| [overflow.hostux.net](https://overflow.hostux.net/)                             | France                          | Operated by [Hostux](https://hostux.net/)                                                        |
+| [overflow.hostux.net](https://overflow.hostux.net/)                                       | France                          | Operated by [Hostux](https://hostux.net/)                                                        |
-| [overflow.projectsegfau.lt](https://overflow.projectsegfau.lt/)                 | United States, France, India    | Operated by [Project Segfault](https://projectsegfau.lt/)                                        |
+| [overflow.projectsegfau.lt](https://overflow.projectsegfau.lt/)                           | United States, France, India    | Operated by [Project Segfault](https://projectsegfau.lt/)                                        |
-| [code.xbdm.fun](https://code.xbdm.fun)                                          | Germany                         | Operated by [xbdm.fun](https://xbdm.fun)                                                         |
+| [code.xbdm.fun](https://code.xbdm.fun)                                                    | Germany                         | Operated by [xbdm.fun](https://xbdm.fun)                                                         |
-| [overflow.fascinated.cc](https://overflow.fascinated.cc/)                       | Germany                         | Operated by [fascinated.cc](https://fascinated.cc/)                                              |
+| [overflow.fascinated.cc](https://overflow.fascinated.cc/)                                 | Germany                         | Operated by [fascinated.cc](https://fascinated.cc/)                                              |
-| [ao.bloatcat.tk](https://ao.bloatcat.tk)                                        | Iceland                         | Operated by [bloatcat.tk](https://bloatcat.tk)                                                   |
+| [ao.bloatcat.tk](https://ao.bloatcat.tk)                                                  | Iceland                         | Operated by [bloatcat.tk](https://bloatcat.tk)                                                   |
-| [anonoverflow.frontendfriendly.xyz](https://anonoverflow.frontendfriendly.xyz/) | United States                   | Operated by [frontendfriendly.xyz](https://frontendfriendly.xyz/)                                |
+| [anonoverflow.frontendfriendly.xyz](https://anonoverflow.frontendfriendly.xyz/)           | United States                   | Operated by [frontendfriendly.xyz](https://frontendfriendly.xyz/)                                |
-| [ao.owo.si](https://ao.owo.si/)                                                 | Germany                         | Operated by [owo.si](https://owo.si/)                                                            |
+| [ao.owo.si](https://ao.owo.si/)                                                           | Germany                         | Operated by [owo.si](https://owo.si/)                                                            |
-| [overflow.datura.network](https://overflow.datura.network/)                     | Germany                         | Operated by [datura.network](https://datura.network)                                             |
+| [overflow.datura.network](https://overflow.datura.network/)                               | Germany                         | Operated by [datura.network](https://datura.network)                                             |
-| [overflow.freedit.eu](overflow.freedit.eu)                                      | United States                   | Operated by [freedit.eu](https://freedit.eu)                                                     |
+| [overflow.freedit.eu](overflow.freedit.eu)                                                | United States                   | Operated by [freedit.eu](https://freedit.eu)                                                     |
-| [ao.ftw.lol](https://ao.ftw.lol)                                                | Germany                         | Operated by [ftw.lol](https://ftw.lol)                                                           |
+| [ao.ftw.lol](https://ao.ftw.lol)                                                          | Germany                         | Operated by [ftw.lol](https://ftw.lol)                                                           |
-| [anonoverflow.hyperreal.coffee](https://anonoverflow.hyperreal.coffee)          | United States                   | Operated by [hyperreal.coffee](https://hyperreal.coffee)                                         |
+| [anonoverflow.hyperreal.coffee](https://anonoverflow.hyperreal.coffee)                    | United States                   | Operated by [hyperreal.coffee](https://hyperreal.coffee)                                         |
-| [a.opnxng.com](a.opnxng.com)                                                    | Singapore                       | Operated by [opnxng.com](https://about.opnxng.com)                                               |
+| [a.opnxng.com](a.opnxng.com)                                                              | Singapore                       | Operated by [opnxng.com](https://about.opnxng.com)                                               |
-| [overflow.sudovanilla.com](https://overflow.sudovanilla.com)                    | United States                   | Operated by [SudoVanilla](https://sudovanilla.com)                                               |
+| [overflow.sudovanilla.com](https://overflow.sudovanilla.com)                              | United States                   | Operated by [SudoVanilla](https://sudovanilla.com)                                               |
+| [anonymousoverflow.privacyfucking.rocks](https://anonymousoverflow.privacyfucking.rocks/) | Germany                         | Operated by [privacyfucking.rocks](https://privacyfucking.rocks)                                 |
+| [exchange.seitan-ayoub.lol](https://exchange.seitan-ayoub.lol)                            | Germany                         | Operated by [Seitan Ayoub](https://seitan-ayoub.lol)                                             |
+| [overflow.r4fo.com](https://overflow.r4fo.com)                                            | The Netherlands                 | Operated by [r4fo.com](https://r4fo.com)                                                         |
+| [overflow.ducks.party](https://overflow.ducks.party)                                      | The Netherlands                 | Operated by [ducks.party](https://ducks.party)                                                   |
 
 ## Other Instances
 

config/version.go

@@ -1,3 +1,3 @@
 package config
 
-var Version = "1.9.0"
+var Version = "1.10.1"

docker-compose.example.yml

@@ -1,14 +1,12 @@
 version: '3'
 
 services:
-  anonymousoverflow:
+    anonymousoverflow:
-    container_name: 'app'
+        container_name: 'app'
-    build:
+        image: 'ghcr.io/httpjamesm/anonymousoverflow:release'
-      context: .
+        environment:
-      network: 'host'
+            - APP_URL=https://domain.com
-    environment:
+            - JWT_SIGNING_SECRET=secret
-      - APP_URL=https://domain.com
+        ports:
-      - JWT_SIGNING_SECRET=secret
+            - '80:8080'
-    ports:
+        restart: 'always'
-      - '80:8080'
-    restart: 'always'

go.mod

@@ -13,6 +13,7 @@ require (
 
 require (
 	github.com/andybalholm/cascadia v1.3.1 // indirect
+	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/dlclark/regexp2 v1.7.0 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect
 	github.com/go-playground/locales v0.14.0 // indirect
@@ -25,6 +26,8 @@ require (
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/pelletier/go-toml/v2 v2.0.6 // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
+	github.com/stretchr/testify v1.9.0 // indirect
 	github.com/ugorji/go/codec v1.2.8 // indirect
 	golang.org/x/crypto v0.4.0 // indirect
 	golang.org/x/net v0.7.0 // indirect
@@ -32,4 +35,5 @@ require (
 	golang.org/x/text v0.7.0 // indirect
 	google.golang.org/protobuf v1.28.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
 )

go.sum

@@ -72,6 +72,8 @@ github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.1 h1:w7B6lhMri9wdJUVmEZPGGhZzrYTPvgJArz7wNPgYKsk=
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
+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 v1.2.8 h1:sgBJS6COt0b/P40VouWKdseidkDgHxYGm0SAglUHfP0=
 github.com/ugorji/go/codec v1.2.8/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZgYf6w6lg=
 golang.org/x/crypto v0.0.0-20211215153901-e495a2d5b3d3/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=

main.go

@@ -51,6 +51,7 @@ func main() {
 	r.POST("/", routes.PostHome)
 
 	r.GET("/a/:id", routes.RedirectShortenedOverflowURL)
+	r.GET("/q/:id", routes.RedirectShortenedOverflowURL)
 
 	r.GET("/questions/:id", func(c *gin.Context) {
 		// redirect user to the question with the title

src/middleware/options.go

@@ -1,6 +1,8 @@
 package middleware
 
-import "github.com/gin-gonic/gin"
+import (
+	"github.com/gin-gonic/gin"
+)
 
 func OptionsMiddleware() gin.HandlerFunc {
 	return func(c *gin.Context) {
@@ -8,23 +10,17 @@ func OptionsMiddleware() gin.HandlerFunc {
 		c.Set("theme", "dark")
 
 		imagesCookie, err := c.Cookie("disable_images")
-		if err != nil {
+		if err == nil {
-			c.Next()
+			if imagesCookie == "true" {
-			return
+				c.Set("disable_images", true)
-		}
+			}
-
-		if imagesCookie == "true" {
-			c.Set("disable_images", true)
 		}
 
 		themeCookie, err := c.Cookie("theme")
-		if err != nil {
+		if err == nil {
-			c.Next()
+			if themeCookie == "light" {
-			return
+				c.Set("theme", "light")
-		}
+			}
-
-		if themeCookie == "light" {
-			c.Set("theme", "light")
 		}
 
 		c.Next()

src/routes/home.go

@@ -40,7 +40,7 @@ func PostHome(c *gin.Context) {
 
 	// validate URL
 	isStackOverflow := strings.HasPrefix(soLink, "https://stackoverflow.com/questions/")
-	isShortenedStackOverflow := strings.HasPrefix(soLink, "https://stackoverflow.com/a/")
+	isShortenedStackOverflow := strings.HasPrefix(soLink, "https://stackoverflow.com/a/") || strings.HasPrefix(soLink, "https://stackoverflow.com/q/")
 	isStackExchange := stackExchangeRegex.MatchString(soLink)
 	if !isStackExchange && !isStackOverflow && !isShortenedStackOverflow {
 		c.HTML(400, "home.html", gin.H{

src/routes/options.go

@@ -30,12 +30,10 @@ func ChangeOptions(c *gin.Context) {
 		if c.MustGet("theme").(string) == "dark" {
 			text = "light"
 		}
+
 		c.SetCookie("theme", text, 60*60*24*365*10, "/", "", false, true)
 		// get redirect url from query
 		redirectUrl := c.Query("redirect_url")
-		if redirectUrl == "" {
-			redirectUrl = os.Getenv("APP_URL")
-		}
 
 		if !strings.HasPrefix(redirectUrl, os.Getenv("APP_URL")) {
 			redirectUrl = os.Getenv("APP_URL")

src/routes/question.go

@@ -29,7 +29,6 @@ var soSortValues = map[string]string{
 }
 
 func ViewQuestion(c *gin.Context) {
-	client := resty.New()
 
 	questionId := c.Param("id")
 	if _, err := strconv.Atoi(questionId); err != nil {
@@ -41,42 +40,24 @@ func ViewQuestion(c *gin.Context) {
 		return
 	}
 
-	questionTitle := c.Param("title")
+	params, err := parseAndValidateParameters(c)
-
+	if err != nil {
-	sortValue := c.Query("sort_by")
+		return
-	if sortValue == "" {
-		sortValue = "votes"
 	}
 
-	soSortValue, ok := soSortValues[sortValue]
-	if !ok {
-		soSortValue = soSortValues["votes"]
-	}
-
-	sub := c.Param("sub")
-
 	domain := "stackoverflow.com"
 
-	if sub != "" {
+	if params.Sub != "" {
-		domain = fmt.Sprintf("%s.stackexchange.com", sub)
+		domain = fmt.Sprintf("%s.stackexchange.com", params.Sub)
 	}
 
-	soLink := fmt.Sprintf("https://%s/questions/%s/%s?answertab=%s", domain, questionId, questionTitle, soSortValue)
+	soLink := fmt.Sprintf("https://%s/questions/%s/%s?answertab=%s", domain, questionId, params.QuestionTitle, params.SoSortValue)
 
-	resp, err := client.R().Get(soLink)
+	resp, err := fetchQuestionData(soLink)
-	if err != nil {
-		c.HTML(500, "home.html", gin.H{
-			"errorMessage": "Unable to fetch question data",
-			"theme":        c.MustGet("theme").(string),
-			"version":      config.Version,
-		})
-		return
-	}
-	defer resp.RawResponse.Body.Close()
 
 	if resp.StatusCode() != 200 {
 		c.HTML(500, "home.html", gin.H{
-			"errorMessage": "Received a non-OK status code",
+			"errorMessage": fmt.Sprintf("Received a non-OK status code %d", resp.StatusCode()),
 			"theme":        c.MustGet("theme").(string),
 			"version":      config.Version,
 		})
@@ -97,181 +78,25 @@ func ViewQuestion(c *gin.Context) {
 		return
 	}
 
-	newFilteredQuestion := types.FilteredQuestion{}
+	newFilteredQuestion, err := extractQuestionData(doc, domain)
-
-	questionTextParent := doc.Find("h1.fs-headline1")
-
-	questionText := questionTextParent.Children().First().Text()
-
-	newFilteredQuestion.Title = questionText
-
-	questionPostLayout := doc.Find("div.post-layout").First()
-
-	questionTags := utils.GetPostTags(questionPostLayout)
-	newFilteredQuestion.Tags = questionTags
-
-	questionBodyParent := doc.Find("div.s-prose")
-
-	questionBodyParentHTML, err := questionBodyParent.Html()
 	if err != nil {
 		c.HTML(500, "home.html", gin.H{
-			"errorMessage": "Unable to parse question body",
+			"errorMessage": "Failed to extract question data",
 			"theme":        c.MustGet("theme").(string),
 			"version":      config.Version,
 		})
 		return
 	}
 
-	newFilteredQuestion.Body = template.HTML(utils.ReplaceImgTags(questionBodyParentHTML))
+	answers, err := extractAnswersData(doc, domain)
-
+	if err != nil {
-	questionBodyText := questionBodyParent.Text()
+		c.HTML(500, "home.html", gin.H{
-
+			"errorMessage": "Failed to extract answer data",
-	// remove all whitespace to create the shortened body desc
+			"theme":        c.MustGet("theme").(string),
-	shortenedBody := strings.TrimSpace(questionBodyText)
+			"version":      config.Version,
-
-	// remove all newlines
-	shortenedBody = strings.ReplaceAll(shortenedBody, "\n", " ")
-
-	// get the first 50 chars
-	shortenedBody = shortenedBody[:50]
-
-	newFilteredQuestion.ShortenedBody = shortenedBody
-
-	comments := utils.FindAndReturnComments(questionBodyParentHTML, domain, questionPostLayout)
-	newFilteredQuestion.Comments = comments
-
-	// parse any code blocks and highlight them
-	answerCodeBlocks := questionCodeBlockRegex.FindAllString(questionBodyParentHTML, -1)
-	for _, codeBlock := range answerCodeBlocks {
-		codeBlock = utils.StripBlockTags(codeBlock)
-
-		// syntax highlight
-		highlightedCodeBlock := utils.HighlightSyntaxViaContent(codeBlock)
-
-		// replace the code block with the highlighted code block
-		questionBodyParentHTML = strings.Replace(questionBodyParentHTML, codeBlock, highlightedCodeBlock, 1)
-	}
-
-	questionCard := doc.Find("div.postcell")
-
-	questionMetadata := questionCard.Find("div.user-info")
-	questionTimestamp := ""
-	questionMetadata.Find("span.relativetime").Each(func(i int, s *goquery.Selection) {
-		// get the second
-		if i == 0 {
-			if s.Text() != "" {
-				// if it's not been edited, it means it's the first
-				questionTimestamp = s.Text()
-				return
-			}
-		}
-
-		// otherwise it's the second element
-		if i == 1 {
-			questionTimestamp = s.Text()
-			return
-		}
-	})
-
-	newFilteredQuestion.Timestamp = questionTimestamp
-
-	userDetails := questionMetadata.Find("div.user-details")
-
-	questionAuthor := ""
-	questionAuthorURL := fmt.Sprintf("https://%s", domain)
-
-	// check if the question has been edited
-	isQuestionEdited := false
-	questionMetadata.Find("a.js-gps-track").Each(func(i int, s *goquery.Selection) {
-		if strings.Contains(s.Text(), "edited") {
-			isQuestionEdited = true
-			return
-		}
-	})
-
-	userDetails.Find("a").Each(func(i int, s *goquery.Selection) {
-		// if question has been edited, the author is the second element.
-
-		if isQuestionEdited {
-			if i == 1 {
-				questionAuthor = s.Text()
-				questionAuthorURL += s.AttrOr("href", "")
-				return
-			}
-		} else {
-			// otherwise it's the first element
-			if i == 0 {
-				questionAuthor = s.Text()
-				questionAuthorURL += s.AttrOr("href", "")
-				return
-			}
-		}
-	})
-
-	newFilteredQuestion.AuthorName = questionAuthor
-	newFilteredQuestion.AuthorURL = questionAuthorURL
-
-	answers := []types.FilteredAnswer{}
-
-	doc.Find("div.answer").Each(func(i int, s *goquery.Selection) {
-
-		newFilteredAnswer := types.FilteredAnswer{}
-
-		postLayout := s.Find("div.post-layout")
-		voteCell := postLayout.Find("div.votecell")
-		answerCell := postLayout.Find("div.answercell")
-		answerBody := answerCell.Find("div.s-prose")
-		answerBodyHTML, _ := answerBody.Html()
-
-		voteCount := html.EscapeString(voteCell.Find("div.js-vote-count").Text())
-
-		newFilteredAnswer.Upvotes = voteCount
-		newFilteredAnswer.IsAccepted = s.HasClass("accepted-answer")
-
-		answerFooter := s.Find("div.mt24")
-
-		answerAuthorURL := fmt.Sprintf("https://%s", domain)
-		answerAuthorName := ""
-		answerTimestamp := ""
-
-		answerFooter.Find("div.post-signature").Each(func(i int, s *goquery.Selection) {
-			answerAuthorDetails := s.Find("div.user-details")
-
-			if answerAuthorDetails.Length() > 0 {
-				questionAuthor := answerAuthorDetails.Find("a").First()
-				answerAuthorName = html.EscapeString(questionAuthor.Text())
-				answerAuthorURL += html.EscapeString(questionAuthor.AttrOr("href", ""))
-			}
-
-			answerTimestamp = html.EscapeString(s.Find("span.relativetime").Text())
 		})
-
+		return
-		answerId, _ := s.Attr("data-answerid")
+	}
-		newFilteredAnswer.ID = answerId
-
-		newFilteredAnswer.AuthorName = answerAuthorName
-		newFilteredAnswer.AuthorURL = answerAuthorURL
-		newFilteredAnswer.Timestamp = answerTimestamp
-
-		// parse any code blocks and highlight them
-		answerCodeBlocks := codeBlockRegex.FindAllString(answerBodyHTML, -1)
-		for _, codeBlock := range answerCodeBlocks {
-			codeBlock = utils.StripBlockTags(codeBlock)
-
-			// syntax highlight
-			highlightedCodeBlock := utils.HighlightSyntaxViaContent(codeBlock)
-
-			// replace the code block with the highlighted code block
-			answerBodyHTML = strings.Replace(answerBodyHTML, codeBlock, highlightedCodeBlock, 1)
-		}
-
-		comments = utils.FindAndReturnComments(answerBodyHTML, domain, postLayout)
-
-		newFilteredAnswer.Comments = comments
-		newFilteredAnswer.Body = template.HTML(utils.ReplaceImgTags(answerBodyHTML))
-
-		answers = append(answers, newFilteredAnswer)
-	})
 
 	imagePolicy := "'self' https:"
 
@@ -284,9 +109,164 @@ func ViewQuestion(c *gin.Context) {
 		"answers":     answers,
 		"imagePolicy": imagePolicy,
 		"theme":       c.MustGet("theme").(string),
-		"currentUrl":  fmt.Sprintf("%s/questions/%s/%s", os.Getenv("APP_URL"), questionId, questionTitle),
+		"currentUrl":  fmt.Sprintf("%s/questions/%s/%s", os.Getenv("APP_URL"), questionId, params.QuestionTitle),
-		"sortValue":   sortValue,
+		"sortValue":   params.SoSortValue,
 		"domain":      domain,
 	})
 
 }
+
+type viewQuestionInputs struct {
+	QuestionID    string
+	QuestionTitle string
+	SoSortValue   string
+	Sub           string
+}
+
+// parseAndValidateParameters consolidates the URL and query parameters into an easily-accessible struct.
+func parseAndValidateParameters(c *gin.Context) (inputs viewQuestionInputs, err error) {
+
+	questionId := c.Param("id")
+	if _, err = strconv.Atoi(questionId); err != nil {
+		c.HTML(400, "home.html", gin.H{
+			"errorMessage": "Invalid question ID",
+			"theme":        c.MustGet("theme").(string),
+			"version":      config.Version,
+		})
+		return
+	}
+
+	inputs.QuestionID = questionId
+
+	sortValue := c.Query("sort_by")
+	if sortValue == "" {
+		sortValue = "votes"
+	}
+
+	soSortValue, ok := soSortValues[sortValue]
+	if !ok {
+		soSortValue = soSortValues["votes"]
+	}
+
+	inputs.SoSortValue = soSortValue
+
+	sub := c.Param("sub")
+
+	inputs.Sub = sub
+
+	return
+}
+
+// fetchQuestionData sends the request to StackOverflow.
+func fetchQuestionData(soLink string) (resp *resty.Response, err error) {
+	client := resty.New()
+	resp, err = client.R().Get(soLink)
+	return
+}
+
+// extractQuestionData parses the HTML document and extracts question data.
+func extractQuestionData(doc *goquery.Document, domain string) (question types.FilteredQuestion, err error) {
+	// Extract the question title.
+	questionTextParent := doc.Find("h1.fs-headline1").First()
+	question.Title = strings.TrimSpace(questionTextParent.Children().First().Text())
+
+	// Extract question tags.
+	questionTags := utils.GetPostTags(doc.Find("div.post-layout").First())
+	question.Tags = questionTags
+
+	// Extract and process the question body.
+	questionBodyParent := doc.Find("div.s-prose").First()
+	questionBodyParentHTML, err := questionBodyParent.Html()
+	if err != nil {
+		return question, err
+	}
+	question.Body = template.HTML(utils.ProcessHTMLBody(questionBodyParentHTML))
+
+	// Extract the shortened body description.
+	shortenedBody := strings.TrimSpace(questionBodyParent.Text())
+	shortenedBody = strings.ReplaceAll(shortenedBody, "\n", " ")
+	if len(shortenedBody) > 50 {
+		shortenedBody = shortenedBody[:50]
+	}
+	question.ShortenedBody = shortenedBody
+
+	// Extract question comments.
+	comments := utils.FindAndReturnComments(questionBodyParentHTML, domain, doc.Find("div.post-layout").First())
+	question.Comments = comments
+
+	// Extract question timestamp and author information.
+	questionCard := doc.Find("div.postcell").First()
+	extractMetadata(questionCard, &question, domain)
+
+	return
+}
+
+// extractMetadata extracts author and timestamp information from a given selection.
+func extractMetadata(selection *goquery.Selection, question *types.FilteredQuestion, domain string) {
+	questionMetadata := selection.Find("div.user-info").First()
+	question.Timestamp = questionMetadata.Find("span.relativetime").First().Text()
+
+	questionAuthorURL := "https://" + domain
+	questionAuthor := selection.Find("div.post-signature.owner div.user-info div.user-details a").First()
+	question.AuthorName = questionAuthor.Text()
+	questionAuthorURL += questionAuthor.AttrOr("href", "")
+	question.AuthorURL = questionAuthorURL
+
+	// Determine if the question has been edited and update author details accordingly.
+	isQuestionEdited := selection.Find("a.js-gps-track").Text() == "edited"
+	if isQuestionEdited {
+		editedAuthor := questionMetadata.Find("a").Last()
+		question.AuthorName = editedAuthor.Text()
+		question.AuthorURL = "https://" + domain + editedAuthor.AttrOr("href", "")
+	}
+}
+
+// extractAnswersData parses the HTML document and extracts answers data.
+func extractAnswersData(doc *goquery.Document, domain string) ([]types.FilteredAnswer, error) {
+	var answers []types.FilteredAnswer
+
+	// Iterate over each answer block.
+	doc.Find("div.answer").Each(func(i int, s *goquery.Selection) {
+		var answer types.FilteredAnswer
+
+		postLayout := s.Find("div.post-layout").First()
+
+		// Extract upvotes.
+		voteCell := postLayout.Find("div.votecell").First()
+		voteCount := html.EscapeString(voteCell.Find("div.js-vote-count").Text())
+		answer.Upvotes = voteCount
+
+		// Check if the answer is accepted.
+		answer.IsAccepted = s.HasClass("accepted-answer")
+
+		// Extract answer body and process it.
+		answerCell := postLayout.Find("div.answercell").First()
+		answerBody := answerCell.Find("div.s-prose").First()
+		answerBodyHTML, _ := answerBody.Html()
+
+		// Process code blocks within the answer.
+		processedAnswerBody := utils.ProcessHTMLBody(answerBodyHTML)
+		answer.Body = template.HTML(html.UnescapeString(processedAnswerBody))
+
+		// Extract author information and timestamp.
+		extractAnswerAuthorInfo(s, &answer, domain)
+
+		answers = append(answers, answer)
+	})
+
+	return answers, nil
+}
+
+// extractAnswerAuthorInfo extracts the author name, URL, and timestamp from an answer block.
+// It directly mutates the answer.
+func extractAnswerAuthorInfo(selection *goquery.Selection, answer *types.FilteredAnswer, domain string) {
+	authorDetails := selection.Find("div.post-signature").Last()
+
+	authorName := html.EscapeString(authorDetails.Find("div.user-details a").First().Text())
+	authorURL := "https://" + domain + authorDetails.Find("div.user-details a").AttrOr("href", "")
+	timestamp := html.EscapeString(authorDetails.Find("span.relativetime").Text())
+
+	answer.AuthorName = authorName
+	answer.AuthorURL = authorURL
+	answer.Timestamp = timestamp
+}

src/utils/comments.go

@@ -50,7 +50,7 @@ func FindAndReturnComments(inHtml, domain string, postLayout *goquery.Selection)
 		commentTimestamp := commentBody.Find("span.relativetime-clean").Text()
 
 		newFilteredComment := types.FilteredComment{
-			Text:       template.HTML(commentCopy),
+			Text:       template.HTML(ProcessHTMLBody(commentCopy)),
 			Timestamp:  commentTimestamp,
 			AuthorName: commentAuthor.Text(),
 			AuthorURL:  commentAuthorURL,

src/utils/links.go

@@ -0,0 +1,45 @@
+package utils
+
+import (
+	"net/url"
+	"regexp"
+	"strings"
+)
+
+// stackOverflowLinkQualifierRegex matches all anchor elements that meet the following conditions:
+// * must be an anchor element
+// * the anchor element must have a pathname beginning with /q or /questions
+// * if there is a host, it must be stackoverflow.com or a subdomain
+var stackOverflowLinkQualifierRegex = regexp.MustCompile(`<a\s[^>]*href="(?:https?://(?:www\.)?(?:\w+\.)*(?:stackoverflow|stackexchange)\.com)?/(?:q|questions)/[^"]*"[^>]*>.*?</a>`)
+
+func ReplaceStackOverflowLinks(html string) string {
+	return stackOverflowLinkQualifierRegex.ReplaceAllStringFunc(html, func(match string) string {
+		// Extract the href attribute value from the anchor tag
+		hrefRegex := regexp.MustCompile(`href="([^"]*)"`)
+		hrefMatch := hrefRegex.FindStringSubmatch(match)
+		if len(hrefMatch) < 2 {
+			return match
+		}
+		href := hrefMatch[1]
+
+		// Parse the URL
+		url, err := url.Parse(href)
+		if err != nil {
+			return match
+		}
+
+		newUrl := url.String()
+
+		// Check if the host is a subdomain
+		parts := strings.Split(url.Host, ".")
+		if len(parts) > 2 {
+			// Prepend the subdomain to the path
+			url.Path = "/exchange/" + parts[0] + url.Path
+		}
+
+		newUrl = url.Path + url.RawQuery + url.Fragment
+
+		// Replace the href attribute value in the anchor tag
+		return strings.Replace(match, hrefMatch[1], newUrl, 1)
+	})
+}

src/utils/links_test.go

@@ -0,0 +1,49 @@
+package utils
+
+import (
+	"fmt"
+	"github.com/stretchr/testify/assert"
+	"strings"
+	"testing"
+)
+
+var sampleInput = `<div class="d-flex fd-column fw-nowrap">
+	<div class="d-flex fw-nowrap">
+		<div class="flex--item wmn0 fl1 lh-lg">
+			<div class="flex--item fl1 lh-lg">
+					<div>
+						<b>This question already has answers here</b>:
+
+					</div>
+			</div>
+		</div>
+	</div>
+			<div class="flex--item mb0 mt4">
+				<a href="/questions/55083952/is-it-possible-to-populate-a-large-set-at-compile-time" dir="ltr">Is it possible to populate a large set at compile time?</a>
+					<span class="question-originals-answer-count">
+						(3 answers)
+					</span>
+			</div>
+			<div class="flex--item mb0 mt4">
+				<a href="https://stackoverflow.com/questions/27221504/how-can-you-make-a-safe-static-singleton-in-rust" dir="ltr">How can you make a safe static singleton in Rust?</a>
+					<span class="question-originals-answer-count">
+						(5 answers)
+					</span>
+			</div>
+			<div class="flex--item mb0 mt4">
+				<a href="https://security.stackexchange.com/questions/25371/brute-force-an-ssh-login-that-has-only-a-4-letter-password" dir="ltr">Brute-force an SSH-login that has only a 4-letter password</a>
+					<span class="question-originals-answer-count">
+						(9 answers)
+					</span>
+			</div>
+		<div class="flex--item mb0 mt8">Closed <span title="2020-01-29 14:28:42Z" class="relativetime">4 years ago</span>.</div>
+</div>`
+
+func TestReplaceStackOverflowLinks(t *testing.T) {
+	replacedLinks := ReplaceStackOverflowLinks(sampleInput)
+
+	fmt.Println(replacedLinks)
+
+	assert.False(t, strings.Contains(replacedLinks, "stackoverflow.com"))
+	assert.False(t, strings.Contains(replacedLinks, "stackexchange.com"))
+}

src/utils/process.go

@@ -0,0 +1,9 @@
+package utils
+
+// ProcessHTMLBody runs HTML through the various preparation functions.
+func ProcessHTMLBody(bodyHTML string) string {
+	highlightedBody := HighlightCodeBlocks(bodyHTML)
+	imageProxiedBody := ReplaceImgTags(highlightedBody)
+	stackOverflowLinksReplacedBody := ReplaceStackOverflowLinks(imageProxiedBody)
+	return stackOverflowLinksReplacedBody
+}

src/utils/syntax.go

@@ -12,7 +12,9 @@ import (
 	"github.com/alecthomas/chroma/styles"
 )
 
-func HighlightSyntaxViaContent(content string) (htmlOut string) {
+// highlightSyntaxViaContent uses Chroma to lex code content and apply the appropriate tokenizer engine.
+// If it can't find one, it defaults to JavaScript syntax highlighting.
+func highlightSyntaxViaContent(content string) (htmlOut string) {
 	content = html.UnescapeString(content)
 
 	fallbackOut := html.EscapeString(content)
@@ -20,9 +22,7 @@ func HighlightSyntaxViaContent(content string) (htmlOut string) {
 	// identify the language
 	lexer := lexers.Analyse(content)
 	if lexer == nil {
-		// unable to identify, so just return the wrapped content
+		lexer = lexers.Get(".js")
-		htmlOut = fallbackOut
-		return
 	}
 
 	style := styles.Get("xcode")
@@ -54,7 +54,9 @@ func HighlightSyntaxViaContent(content string) (htmlOut string) {
 
 var preClassRegex = regexp.MustCompile(`(?s)<pre class=".+">`)
 
-func StripBlockTags(content string) (result string) {
+// stripBlockTags takes an extracted code block from HTML and strips it of its pre and code tags.
+// What's returned is just the code.
+func stripBlockTags(content string) (result string) {
 	// strip all "<code>" tags
 	content = strings.Replace(content, "<code>", "", -1)
 	content = strings.Replace(content, "</code>", "", -1)
@@ -68,3 +70,26 @@ func StripBlockTags(content string) (result string) {
 
 	return
 }
+
+var codeBlockRegex = regexp.MustCompile(`(?s)<pre><code>(.*?)<\/code><\/pre>`)
+
+// HighlightCodeBlocks uses both highlightSyntaxViaContent stripCodeBlocks and returns the newly highlighted code HTML.
+func HighlightCodeBlocks(html string) string {
+	// Replace each code block with the highlighted version
+	highlightedHTML := codeBlockRegex.ReplaceAllStringFunc(html, func(codeBlock string) string {
+		// Extract the code content from the code block
+		codeContent := codeBlockRegex.FindStringSubmatch(codeBlock)[1]
+
+		codeContent = stripBlockTags(codeContent)
+
+		// Highlight the code content
+		highlightedCode := highlightSyntaxViaContent(codeContent)
+
+		// Replace the original code block with the highlighted version
+		highlightedCodeBlock := "<pre>" + highlightedCode + "</pre>"
+
+		return highlightedCodeBlock
+	})
+
+	return highlightedHTML
+}

templates/home.html

@@ -7,7 +7,7 @@
             http-equiv="Content-Security-Policy"
             content="default-src 'none'; style-src 'self'; script-src 'none'; img-src 'self';"
         />
-        <link rel="icon" href="/static/codecircles.png" />
+        <link rel="icon" href="/static/codecircles.webp" />
         <meta
             name="description"
             content="View StackOverflow threads in privacy and without the clutter."
@@ -19,7 +19,7 @@
             <div class="title">
                 <img
                     class="logo"
-                    src="/static/codecircles.png"
+                    src="/static/codecircles.webp"
                     alt="4 circles with alternating colors between green and white"
                 />
                 <h1>AnonymousOverflow</h1>

templates/question.html

@@ -26,7 +26,7 @@
                 <a href="/" class="logo-link">
                     <img
                         class="logo"
-                        src="/static/codecircles.png"
+                        src="/static/codecircles.webp"
                         alt="4 circles with alternating colors between green and white"
                     />
                 </a>

templates/sharedHead.html

@@ -1,4 +1,4 @@
 <meta name="theme-color" content="#8CFFC1" />
-<meta name="og:image" content="/static/codecircles.png" />
+<meta name="og:image" content="/static/codecircles.webp" />
 <meta name="viewport" content="width=device-width, initial-scale=1" />
 <link rel="stylesheet" href="/static/globals.css" />