Remove archive directory if empty

internal/archiver/reader.go

@@ -27,6 +27,8 @@ func NewReader(waczPath string) *Reader {
 	}
 }
 
+// ReadArchive reads the archive and returns the contents of the warc record for
+// the specified URL as a string.
 func (s *Reader) ReadArchive(urlStr string) (content string) {
 	wacz, err := zip.OpenReader(s.waczPath)
 	if err != nil {
@@ -73,6 +75,8 @@ func (s *Reader) ReadArchive(urlStr string) (content string) {
 	return string(c)
 }
 
+// getCDXEntry Looks for the specified URL in the index file and returns an IndexEntry if found,
+// otherwise it returns an error.
 func (s *Reader) getCDXEntry(wacz *zip.ReadCloser, urlStr string) (*IndexEntry, error) {
 	file, err := s.getZipFile(wacz, "indexes/index.cdx")
 	if err != nil {
@@ -118,6 +122,7 @@ func (s *Reader) getCDXEntry(wacz *zip.ReadCloser, urlStr string) (*IndexEntry,
 	return &record, nil
 }
 
+// getZipFile returns a *zip.File from a wacz file. If not found it returns an error.
 func (s *Reader) getZipFile(wacz *zip.ReadCloser, waczFile string) (*zip.File, error) {
 	for _, file := range wacz.File {
 		if file.Name == waczFile {
@@ -128,6 +133,8 @@ func (s *Reader) getZipFile(wacz *zip.ReadCloser, waczFile string) (*zip.File, e
 	return nil, errors.New("warc file file not found")
 }
 
+// searchFileSegment searches the target string in WACZ file index using bynary search.
+// It loads the index contents in memory.
 func (s *Reader) searchFileSegment(offset, length int64, target string) (string, error) {
 	file, err := os.Open(s.waczPath)
 	if err != nil {

internal/archiver/writer.go

@@ -233,7 +233,6 @@ func (s *Writer) createIndex() error {
 
 // addPage adds a new page record in the pages.jsonl file.
 func (s *Writer) createPages() error {
-	// Add the pages.jsonl and add the file header
 	pagesWriter, err := s.waczWriter.Create("pages/pages.jsonl")
 	if err != nil {
 		return err

internal/models/archive_record.go

@@ -0,0 +1,6 @@
+package models
+
+type ArchiveRecord struct {
+	Headers string
+	Body    string
+}

internal/routes/resource.go

@@ -92,6 +92,8 @@ func (h *resourceHandler) indexHandler(w http.ResponseWriter, r *http.Request) {
 	h.Renderer.RenderTemplate(w, "resources", pageView)
 }
 
+// archiveHandler the HTTP request for the archive page. It loads the data from the
+// archive and displays the source code of the crawler's response for a specific resource.
 func (h *resourceHandler) archiveHandler(w http.ResponseWriter, r *http.Request) {
 	user, ok := h.CookieSession.GetUser(r.Context())
 	if !ok {
@@ -142,36 +144,22 @@ func (h *resourceHandler) archiveHandler(w http.ResponseWriter, r *http.Request)
 		return
 	}
 
-	archive := h.Container.ArchiveService.ReadArchive(&pv.Project, pageReportView.PageReport.URL)
-
-	var headers, body string
-	index := strings.Index(archive, "\r\n\r\n")
-	if index != -1 {
-		// Split the string into two parts: before and after the first newline
-		headers = archive[:index]
-		body = strings.TrimSpace(archive[index+1:])
-	} else {
-		// If there's no newline, the entire text is the first part
-		headers = archive
-		body = ""
-	}
+	record := h.Container.ArchiveService.ReadArchiveRecord(&pv.Project, pageReportView.PageReport.URL)
 
 	data := &struct {
 		PageReportView *models.PageReportView
 		ProjectView    *models.ProjectView
 		Eid            string
 		Ep             string
 		Tab            string
-		Headers        string
-		Body           string
+		ArchiveRecord  *models.ArchiveRecord
 	}{
 		ProjectView:    pv,
 		PageReportView: pageReportView,
 		Eid:            eid,
 		Ep:             ep,
 		Tab:            tab,
-		Headers:        headers,
-		Body:           body,
+		ArchiveRecord:  record,
 	}
 
 	pageView := &PageView{

internal/services/archiver.go → internal/services/archive.go

@@ -2,8 +2,11 @@ package services
 
 import (
 	"errors"
+	"log"
 	"os"
+	"path/filepath"
 	"strconv"
+	"strings"
 
 	"github.com/stjudewashere/seonaut/internal/archiver"
 	"github.com/stjudewashere/seonaut/internal/models"
@@ -26,11 +29,22 @@ func (s *ArchiveService) GetArchiveWriter(p *models.Project) (*archiver.Writer,
 }
 
 // ReadArchive reads an URLs WACZ record from a project's archive.
-func (s *ArchiveService) ReadArchive(p *models.Project, urlStr string) string {
+func (s *ArchiveService) ReadArchiveRecord(p *models.Project, urlStr string) *models.ArchiveRecord {
 	waczPath := s.getArchiveFile(p)
 	reader := archiver.NewReader(waczPath)
 
-	return reader.ReadArchive(urlStr)
+	content := reader.ReadArchive(urlStr)
+
+	record := &models.ArchiveRecord{}
+	index := strings.Index(content, "\r\n\r\n")
+	if index != -1 {
+		record.Headers = content[:index]
+		record.Body = strings.TrimSpace(content[index+1:])
+	} else {
+		record.Headers = content
+	}
+
+	return record
 }
 
 // ArchiveExists checks if a wacz file exists for the current project.
@@ -50,6 +64,24 @@ func (s *ArchiveService) DeleteArchive(p *models.Project) {
 
 	file := s.getArchiveFile(p)
 	os.Remove(file)
+
+	// Check if the archive directory is empty and remove it.
+	dir := filepath.Dir(file)
+	d, err := os.Open(dir)
+	if err != nil {
+		log.Printf("failed to open archive dir %s: %v", dir, err)
+		return
+	}
+
+	_, err = d.ReadDir(1)
+	if err == nil {
+		return // dir is not empty.
+	}
+
+	err = os.Remove(dir)
+	if err != nil {
+		log.Printf("failed to remove empty archive dir %s: %v", dir, err)
+	}
 }
 
 // GetArchiveFilePath returns the project's wacz file path if it exists,

web/templates/archive.html

@@ -50,12 +50,12 @@
 			<div class="content">
 				<h2>Headers</h2>
 				<p>This block shows the response headers as received by the crawler.</p>
-				<pre class="archive"><code>{{ .Headers }}</code></pre>
+				<pre class="archive"><code>{{ .ArchiveRecord.Headers }}</code></pre>
 
-				{{ if .Body }}
+				{{ if .ArchiveRecord.Body }}
 				<h2>Body</h2>
 				<p>This block shows the response body as received by the crawler.</p>
-				<pre class="archive"><code>{{ .Body }}</code></pre>
+				<pre class="archive"><code>{{ .ArchiveRecord.Body }}</code></pre>
 				{{ end }}
 			</div>
 		</div>