diff options
Diffstat (limited to 'scripts')
| -rw-r--r-- | scripts/extract_highlights.go | 120 | ||||
| -rw-r--r-- | scripts/get_external_link_rank.go | 77 | ||||
| -rw-r--r-- | scripts/get_internal_link_graph.go | 101 |
3 files changed, 0 insertions, 298 deletions
diff --git a/scripts/extract_highlights.go b/scripts/extract_highlights.go deleted file mode 100644 index c7253d5f..00000000 --- a/scripts/extract_highlights.go +++ /dev/null @@ -1,120 +0,0 @@ -package main - -import ( - "encoding/json" - "fmt" - "io/fs" - "net/url" - "os" - "path/filepath" - "regexp" - "strings" -) - -type HighlightLink struct { - Text string `json:"text"` - Link string `json:"link"` -} - -type Result struct { - Title string `json:"title"` - URL string `json:"url"` - Highlights []HighlightLink `json:"highlights"` -} - -func main() { - const contentDir = "content" - const outputFile = "data/highlights.json" - - highlightPattern := regexp.MustCompile(`==(.+?)==`) - titlePattern := regexp.MustCompile(`(?m)^title:\s*["']?(.+?)["']?\s*$`) - slugPattern := regexp.MustCompile(`(?m)^slug:\s*["']?(.+?)["']?\s*$`) - - var results []Result - - err := filepath.WalkDir(contentDir, func(path string, d fs.DirEntry, err error) error { - if err != nil { - return err - } - if d.IsDir() || !strings.HasSuffix(d.Name(), ".md") { - return nil - } - - contentBytes, err := os.ReadFile(path) - if err != nil { - return err - } - content := string(contentBytes) - - // Title - title := filepath.Base(path) - if m := titlePattern.FindStringSubmatch(content); len(m) > 1 { - title = m[1] - } - - // Slug and URL - urlPath := "" - if m := slugPattern.FindStringSubmatch(content); len(m) > 1 { - slug := strings.Trim(m[1], "/") - relDir, _ := filepath.Rel(contentDir, filepath.Dir(path)) - relDir = filepath.ToSlash(relDir) - if relDir != "." { - urlPath = fmt.Sprintf("/%s/%s/", relDir, slug) - } else { - urlPath = fmt.Sprintf("/%s/", slug) - } - } else { - rel, _ := filepath.Rel(contentDir, path) - rel = filepath.ToSlash(rel) - urlPath = "/" + strings.TrimSuffix(rel, ".md") + "/" - } - - // Highlights - matches := highlightPattern.FindAllStringSubmatch(content, -1) - if len(matches) == 0 { - return nil - } - - var highlightLinks []HighlightLink - for _, m := range matches { - if len(m) > 1 { - h := m[1] - encoded := url.QueryEscape(h) - link := fmt.Sprintf("%s#:~:text=%s", urlPath, encoded) - highlightLinks = append(highlightLinks, HighlightLink{Text: h, Link: link}) - } - } - - results = append(results, Result{ - Title: title, - URL: urlPath, - Highlights: highlightLinks, - }) - - return nil - }) - - if err != nil { - fmt.Println("❌ Error:", err) - return - } - - // Write JSON - if err := os.MkdirAll(filepath.Dir(outputFile), os.ModePerm); err != nil { - fmt.Println("❌ Error creating output directory:", err) - return - } - - jsonData, err := json.MarshalIndent(results, "", " ") - if err != nil { - fmt.Println("❌ Error encoding JSON:", err) - return - } - - if err := os.WriteFile(outputFile, jsonData, 0644); err != nil { - fmt.Println("❌ Error writing JSON file:", err) - return - } - - fmt.Printf("✔ 提取完成，共 %d 篇文章有高亮，已写入 %s\n", len(results), outputFile) -} diff --git a/scripts/get_external_link_rank.go b/scripts/get_external_link_rank.go deleted file mode 100644 index 4189c191..00000000 --- a/scripts/get_external_link_rank.go +++ /dev/null @@ -1,77 +0,0 @@ -package main - -import ( - "encoding/json" - "fmt" - "io/fs" - "net/url" - "os" - "path/filepath" - "regexp" - "sort" - "strings" -) - -func main() { - externalLinks := countExternalLinks("content") - writeJSON("data/externallinks.json", externalLinks) - fmt.Println("✅ External link rank data generated.") -} - -// countExternalLinks scans markdown files and counts occurrences of each external domain. -func countExternalLinks(root string) [][2]interface{} { - linkRegex := regexp.MustCompile(`https?://[^\s)>"']+`) - counts := make(map[string]int) - - filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error { - if err != nil || d.IsDir() || !strings.HasSuffix(path, ".md") { - return nil - } - data, err := os.ReadFile(path) - if err != nil { - return nil - } - matches := linkRegex.FindAllString(string(data), -1) - for _, match := range matches { - u, err := url.Parse(match) - if err == nil && u.Host != "" { - // skip my domains - if strings.HasSuffix(u.Host, "eltr.ac") || strings.HasSuffix(u.Host, "guhub.cn") { - continue - } - counts[u.Host]++ - } - } - return nil - }) - - // convert map to sorted array (alphabetically by domain) - type kv struct { - Key string - Value int - } - var list []kv - for k, v := range counts { - list = append(list, kv{k, v}) - } - sort.Slice(list, func(i, j int) bool { return list[i].Key < list[j].Key }) - - result := make([][2]interface{}, len(list)) - for i, kv := range list { - result[i] = [2]interface{}{kv.Key, kv.Value} - } - return result -} - -// writeJSON writes the result to file with indentation. -func writeJSON(path string, data interface{}) { - file, err := os.Create(path) - if err != nil { - fmt.Println("Error:", err) - return - } - defer file.Close() - enc := json.NewEncoder(file) - enc.SetIndent("", " ") - enc.Encode(data) -} diff --git a/scripts/get_internal_link_graph.go b/scripts/get_internal_link_graph.go deleted file mode 100644 index 8adf5594..00000000 --- a/scripts/get_internal_link_graph.go +++ /dev/null @@ -1,101 +0,0 @@ -package main - -import ( - "encoding/json" - "fmt" - "io/fs" - "os" - "path/filepath" - "regexp" - "sort" - "strings" -) - -type Node struct { - ID string `json:"id"` - Label string `json:"label"` - URL string `json:"url"` -} - -type Edge struct { - From string `json:"from"` - To string `json:"to"` -} - -func main() { - root := "content" - - nodes := map[string]Node{} - edges := make([]Edge, 0) // non-nil so it becomes [] not null - - err := filepath.WalkDir(root, func(path string, d fs.DirEntry, err error) error { - if err != nil || d.IsDir() || !strings.HasSuffix(strings.ToLower(path), ".md") { - return nil - } - - rel, err := filepath.Rel(root, path) - if err != nil { - return nil - } - rel = filepath.ToSlash(rel) - urlPath := "/" + strings.TrimSuffix(rel, ".md") + "/" - label := strings.TrimSuffix(filepath.Base(path), ".md") - - nodes[urlPath] = Node{ID: urlPath, Label: label, URL: urlPath} - - data, err := os.ReadFile(path) - if err != nil { - return nil - } - content := string(data) - - linkPattern := regexp.MustCompile(`\[[^\]]*\]\((/[^)]+)\)`) - matches := linkPattern.FindAllStringSubmatch(content, -1) - for _, m := range matches { - link := strings.TrimSuffix(m[1], ".md") - if !strings.HasSuffix(link, "/") { - link += "/" - } - edges = append(edges, Edge{From: urlPath, To: link}) - } - - return nil - }) - - if err != nil { - fmt.Println("WalkDir error:", err) - return - } - - nodeKeys := make([]string, 0, len(nodes)) - for k := range nodes { - nodeKeys = append(nodeKeys, k) - } - sort.Strings(nodeKeys) - nodeList := make([]Node, 0, len(nodeKeys)) - for _, k := range nodeKeys { - nodeList = append(nodeList, nodes[k]) - } - - os.MkdirAll("static", os.ModePerm) - output := map[string]interface{}{ - "nodes": nodeList, - "edges": edges, - } - - outfile := "static/link-graph.json" - f, err := os.Create(outfile) - if err != nil { - fmt.Println("create file error:", err) - return - } - defer f.Close() - - enc := json.NewEncoder(f) - enc.SetIndent("", " ") - if err := enc.Encode(output); err != nil { - fmt.Println("json encode error:", err) - } - - fmt.Printf("✅ Link graph written to %s (%d nodes, %d edges)\n", outfile, len(nodeList), len(edges)) -} |