knotserver: add handler to retrieve retrieve repo language percentage

flake.nix

···
     inherit (gitignore.lib) gitignoreSource;
   in {
     overlays.default = final: prev: let
-      goModHash = "sha256-SfyLSQa3g30PXCi/VQOm0cz372B6YdXE7xfBlhgCGec=";
+      goModHash = "sha256-EooM036KFlO4Zot5vDLX+HFU2GfjCtjVEfF7t+d4Avk=";
       buildCmdPackage = name:
         final.buildGoModule {
           pname = name;

go.mod

···
 	github.com/dustin/go-humanize v1.0.1
 	github.com/gliderlabs/ssh v0.3.8
 	github.com/go-chi/chi/v5 v5.2.0
-	github.com/go-git/go-git/v5 v5.0.0-00010101000000-000000000000
+	github.com/go-enry/go-enry/v2 v2.9.2
+	github.com/go-git/go-git/v5 v5.14.0
 	github.com/google/uuid v1.6.0
 	github.com/gorilla/sessions v1.4.0
 	github.com/haileyok/atproto-oauth-golang v0.0.2
···
 	github.com/dlclark/regexp2 v1.11.5 // indirect
 	github.com/emirpasic/gods v1.18.1 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
+	github.com/go-enry/go-oniguruma v1.2.1 // indirect
 	github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 // indirect
 	github.com/go-git/go-billy/v5 v5.6.2 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect

go.sum

···
 github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU=
 github.com/go-chi/chi/v5 v5.2.0 h1:Aj1EtB0qR2Rdo2dG4O94RIU35w2lvQSj6BRA4+qwFL0=
 github.com/go-chi/chi/v5 v5.2.0/go.mod h1:DslCQbL2OYiznFReuXYUmQ2hGd1aDpCnlMNITLSKoi8=
+github.com/go-enry/go-enry/v2 v2.9.2 h1:giOQAtCgBX08kosrX818DCQJTCNtKwoPBGu0qb6nKTY=
+github.com/go-enry/go-enry/v2 v2.9.2/go.mod h1:9yrj4ES1YrbNb1Wb7/PWYr2bpaCXUGRt0uafN0ISyG8=
+github.com/go-enry/go-oniguruma v1.2.1 h1:k8aAMuJfMrqm/56SG2lV9Cfti6tC4x8673aHCcBk+eo=
+github.com/go-enry/go-oniguruma v1.2.1/go.mod h1:bWDhYP+S6xZQgiRL7wlTScFYBe023B6ilRZbCAD5Hf4=
 github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376 h1:+zs/tPmkDkHx3U66DAb0lQFJrpS6731Oaa12ikc+DiI=
 github.com/go-git/gcfg v1.5.1-0.20230307220236-3a3c6141e376/go.mod h1:an3vInlBmSxCcxctByoQdvwPiA7DTK7jaaFDBTtu0ic=
 github.com/go-git/go-billy/v5 v5.6.2 h1:6Q86EsPXMa7c3YZ3aLAQsMA0VlWmy43r6FHqa/UNbRM=
···
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 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 v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
 github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=

knotserver/git/git.go

···
 	return c, nil
 }
 
+func (g *GitRepo) FileContentN(path string, cap int64) ([]byte, error) {
+	buf := []byte{}
+
+	c, err := g.r.CommitObject(g.h)
+	if err != nil {
+		return nil, fmt.Errorf("commit object: %w", err)
+	}
+
+	tree, err := c.Tree()
+	if err != nil {
+		return nil, fmt.Errorf("file tree: %w", err)
+	}
+
+	file, err := tree.File(path)
+	if err != nil {
+		return nil, err
+	}
+
+	isbin, _ := file.IsBinary()
+
+	if !isbin {
+		reader, err := file.Reader()
+		if err != nil {
+			return nil, err
+		}
+		bufReader := io.LimitReader(reader, cap)
+		_, err = bufReader.Read(buf)
+		if err != nil {
+			return nil, err
+		}
+		return buf, nil
+	} else {
+		return nil, ErrBinaryFile
+	}
+}
+
 func (g *GitRepo) FileContent(path string) (string, error) {
 	c, err := g.r.CommitObject(g.h)
 	if err != nil {

knotserver/handler.go

···
 	r.Route("/repo", func(r chi.Router) {
 		r.Use(h.VerifySignature)
 		r.Put("/new", h.NewRepo)
+		r.Get("/languages/{branch}", h.RepoLanguages)
 		r.Delete("/", h.RemoveRepo)
 		r.Route("/fork", func(r chi.Router) {
 			r.Post("/", h.RepoFork)

knotserver/routes.go

···
 	"net/http"
 	"net/url"
 	"os"
+	"path"
 	"path/filepath"
 	"strconv"
 	"strings"
···
 	securejoin "github.com/cyphar/filepath-securejoin"
 	"github.com/gliderlabs/ssh"
 	"github.com/go-chi/chi/v5"
+	"github.com/go-enry/go-enry/v2"
 	gogit "github.com/go-git/go-git/v5"
 	"github.com/go-git/go-git/v5/plumbing"
 	"github.com/go-git/go-git/v5/plumbing/object"
···
 
 	w.Header().Set("Content-Type", "application/json")
 	json.NewEncoder(w).Encode(types.AncestorCheckResponse{Status: status})
+}
+
+func (h *Handle) RepoLanguages(w http.ResponseWriter, r *http.Request) {
+	l := h.l.With("handler", "RepoForkSync")
+
+	data := struct {
+		Did    string `json:"did"`
+		Source string `json:"source"`
+		Name   string `json:"name,omitempty"`
+	}{}
+
+	if err := json.NewDecoder(r.Body).Decode(&data); err != nil {
+		writeError(w, "invalid request body", http.StatusBadRequest)
+		return
+	}
+
+	did := data.Did
+	source := data.Source
+
+	if did == "" || source == "" {
+		l.Error("invalid request body, empty did or name")
+		w.WriteHeader(http.StatusBadRequest)
+		return
+	}
+
+	var name string
+	if data.Name != "" {
+		name = data.Name
+	} else {
+		name = filepath.Base(source)
+	}
+
+	branch := chi.URLParam(r, "branch")
+	branch, _ = url.PathUnescape(branch)
+
+	relativeRepoPath := filepath.Join(did, name)
+	repoPath, _ := securejoin.SecureJoin(h.c.Repo.ScanPath, relativeRepoPath)
+
+	gr, err := git.Open(repoPath, branch)
+	if err != nil {
+		log.Println(err)
+		notFound(w)
+		return
+	}
+
+	languageFileCount := make(map[string]int)
+	languagePercentage := make(map[string]float64)
+
+	err = recurseEntireTree(gr, func(absPath string) {
+		lang, safe := enry.GetLanguageByExtension(absPath)
+		if len(lang) == 0 || !safe {
+			content, _ := gr.FileContentN(absPath, 1024)
+			if !safe {
+				lang = enry.GetLanguage(absPath, content)
+			} else {
+				lang, _ = enry.GetLanguageByContent(absPath, content)
+				if len(lang) == 0 {
+					return
+				}
+			}
+		}
+
+		v, ok := languageFileCount[lang]
+		if ok {
+			languageFileCount[lang] = v + 1
+		} else {
+			languageFileCount[lang] = 1
+		}
+	}, "")
+	if err != nil {
+		log.Println(err)
+		writeError(w, err.Error(), http.StatusNoContent)
+		return
+	}
+
+	for path, fileCount := range languageFileCount {
+		percentage := float64(fileCount) / float64(len(languageFileCount)) * 100.0
+		languagePercentage[path] = percentage
+	}
+
+	w.Header().Set("Content-Type", "application/json")
+	json.NewEncoder(w).Encode(types.RepoLanguageResponse{Languages: languagePercentage})
+}
+
+func recurseEntireTree(git *git.GitRepo, callback func(absPath string), filePath string) error {
+	files, err := git.FileTree(filePath)
+	if err != nil {
+		log.Println(err)
+		return err
+	}
+
+	for _, file := range files {
+		absPath := path.Join(filePath, file.Name)
+		if !file.IsFile {
+			return recurseEntireTree(git, callback, absPath)
+		}
+		callback(absPath)
+	}
+
+	return nil
 }
 
 func (h *Handle) RepoForkSync(w http.ResponseWriter, r *http.Request) {

types/repo.go

···
 type AncestorCheckResponse struct {
 	Status ForkStatus `json:"status"`
 }
+
+type RepoLanguageResponse struct {
+	// Language: Percentage
+	Languages map[string]float64 `json:"languages"`
+}

types/tree.go

···
 
 // A nicer git tree representation.
 type NiceTree struct {
+	// Relative path
 	Name      string `json:"name"`
 	Mode      string `json:"mode"`
 	Size      int64  `json:"size"`