diff --git a/.gitignore b/.gitignore index 0530eff..860cd15 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,2 @@ borg *.cube -.idea \ No newline at end of file diff --git a/.task/checksum/build b/.task/checksum/build new file mode 100644 index 0000000..d221f2a --- /dev/null +++ b/.task/checksum/build @@ -0,0 +1 @@ +e7a169415ff04b3b388216dc3048d84c diff --git a/README.md b/README.md index a1f734a..ba6d4aa 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,7 @@ # Borg Data Collector -Assimulate all the data!!! \ -No, seriously, what do you need to download? PWA? A GitHub repo, or every repository they have? A website? Build artefacts? Malware? - -That's why I made Borg, to download and contain sets of data into explorable collections, to reuse later; ATM there is only Zuul, erm, Tar, but that’s all I need right now~ Custom rootFS distroless image and, of course, Nanites (sec ops tooling) to come, but if you want to use and work on a Web3 malware analysis, tool, patches welcome (non-sarcasticly). - -Oh, Calling Trekkies, the status messages below, you know they are wrong, don't you? It hurts a little? Good, you, you're the one... \ -Take part in Open Source, make us smirk with amusement and make the CLI crack more smirks. +As the name might sugest; this pkg collects information and stores it in a Cube file or passes it on; +comes as both a cli tool and a usable package for your go project with a clean export only top level interface. ## Borg Status Scratch Pad diff --git a/Taskfile.yml b/Taskfile.yml new file mode 100644 index 0000000..9249a76 --- /dev/null +++ b/Taskfile.yml @@ -0,0 +1,27 @@ +version: '3' + +tasks: + clean: + cmds: + - rm -f borg + build: + cmds: + - task: clean + - GOOS=linux GOARCH=amd64 go build -o borg main.go + sources: + - main.go + - ./pkg/**/*.go + generates: + - borg + run: + cmds: + - task: build + - chmod +x borg + - ./borg + deps: + - build + test-e2e: + cmds: + - task: build + - chmod +x borg + - ./borg --help diff --git a/cmd/collect_github_repo.go b/cmd/collect_github_repo.go index 75b7dff..b4f873d 100644 --- a/cmd/collect_github_repo.go +++ b/cmd/collect_github_repo.go @@ -3,13 +3,9 @@ package cmd import ( "fmt" "os" - "path/filepath" - "strings" "github.com/Snider/Borg/pkg/vcs" - "github.com/Snider/Borg/pkg/github" - "github.com/Snider/Borg/pkg/vcs" "github.com/spf13/cobra" ) @@ -19,90 +15,33 @@ var collectGithubRepoCmd = &cobra.Command{ Short: "Collect a single Git repository", Long: `Collect a single Git repository and store it in a DataNode.`, Args: cobra.ExactArgs(1), -// collectGitCmd represents the collect git command -var collectGitCmd = &cobra.Command{ - Use: "git", - Short: "Collect one or more Git repositories", - Long: `Collect a single Git repository from a URL, or all public repositories from a GitHub user/organization.`, Run: func(cmd *cobra.Command, args []string) { - repoURL, _ := cmd.Flags().GetString("uri") - user, _ := cmd.Flags().GetString("user") - output, _ := cmd.Flags().GetString("output") + repoURL := args[0] + outputFile, _ := cmd.Flags().GetString("output") - if (repoURL == "" && user == "") || (repoURL != "" && user != "") { - fmt.Println("Error: You must specify either --uri or --user, but not both.") - os.Exit(1) + dn, err := vcs.CloneGitRepository(repoURL) + if err != nil { + fmt.Printf("Error cloning repository: %v\n", err) + return } - if user != "" { - // User specified, collect all their repos - fmt.Printf("Fetching public repositories for %s...\n", user) - repos, err := github.GetPublicRepos(user) - if err != nil { - fmt.Printf("Error fetching repositories: %v\n", err) - return - } - fmt.Printf("Found %d repositories. Cloning...\n\n", len(repos)) - - // Ensure output directory exists - err = os.MkdirAll(output, 0755) - if err != nil { - fmt.Printf("Error creating output directory: %v\n", err) - return - } - - for _, repo := range repos { - fmt.Printf("Cloning %s...\n", repo) - dn, err := vcs.CloneGitRepository(repo) - if err != nil { - fmt.Printf(" Error cloning: %v\n", err) - continue - } - - data, err := dn.ToTar() - if err != nil { - fmt.Printf(" Error serializing: %v\n", err) - continue - } - - repoName := strings.TrimSuffix(filepath.Base(repo), ".git") - outputFile := filepath.Join(output, fmt.Sprintf("%s.dat", repoName)) - err = os.WriteFile(outputFile, data, 0644) - if err != nil { - fmt.Printf(" Error writing file: %v\n", err) - continue - } - fmt.Printf(" Successfully saved to %s\n", outputFile) - } - fmt.Println("\nCollection complete.") - - } else { - // Single repository URL specified - dn, err := vcs.CloneGitRepository(repoURL) - if err != nil { - fmt.Printf("Error cloning repository: %v\n", err) - return - } - - data, err := dn.ToTar() - if err != nil { - fmt.Printf("Error serializing DataNode: %v\n", err) - return - } - - err = os.WriteFile(output, data, 0644) - if err != nil { - fmt.Printf("Error writing DataNode to file: %v\n", err) - return - } - fmt.Printf("Repository saved to %s\n", output) + data, err := dn.ToTar() + if err != nil { + fmt.Printf("Error serializing DataNode: %v\n", err) + return } + + err = os.WriteFile(outputFile, data, 0644) + if err != nil { + fmt.Printf("Error writing DataNode to file: %v\n", err) + return + } + + fmt.Printf("Repository saved to %s\n", outputFile) }, } func init() { collectGithubCmd.AddCommand(collectGithubRepoCmd) - collectGithubRepoCmd.Flags().String("uri", "", "URL of the Git repository to collect") - collectGitCmd.Flags().String("user", "", "GitHub user or organization to collect all repositories from") - collectGitCmd.Flags().String("output", "repo.dat", "Output file (for --uri) or directory (for --user)") + collectGithubRepoCmd.PersistentFlags().String("output", "repo.dat", "Output file for the DataNode") } diff --git a/cmd/main_test.go b/cmd/main_test.go new file mode 100644 index 0000000..6ce284f --- /dev/null +++ b/cmd/main_test.go @@ -0,0 +1,26 @@ +package cmd + +import ( + "os" + "os/exec" + "testing" +) + +func TestMain(t *testing.T) { + // This is a bit of a hack, but it's the easiest way to test the main function. + // We're just making sure that the application doesn't crash when it's run. + Execute() +} + +func TestE2E(t *testing.T) { + home, err := os.UserHomeDir() + if err != nil { + t.Fatalf("Failed to get user home directory: %v", err) + } + taskPath := home + "/go/bin/task" + cmd := exec.Command(taskPath, "test-e2e") + output, err := cmd.CombinedOutput() + if err != nil { + t.Fatalf("Failed to run e2e test: %v\n%s", err, output) + } +} diff --git a/cmd/root.go b/cmd/root.go index a95ea23..d409cbe 100644 --- a/cmd/root.go +++ b/cmd/root.go @@ -8,7 +8,7 @@ import ( // rootCmd represents the base command when called without any subcommands var rootCmd = &cobra.Command{ - Use: "github.com/Snider/Borg", + Use: "borg-data-collector", Short: "A tool for collecting and managing data.", Long: `Borg Data Collector is a command-line tool for cloning Git repositories, packaging their contents into a single file, and managing the data within.`, @@ -28,7 +28,7 @@ func init() { // Cobra supports persistent flags, which, if defined here, // will be global for your application. - // rootCmd.PersistentFlags().StringVar(&cfgFile, "config", "", "config file (default is $HOME/.github.com/Snider/Borg.yaml)") + // rootCmd.PersistentFlags().StringVar(&cfgFile, "config", "", "config file (default is $HOME/.borg-data-collector.yaml)") // Cobra also supports local flags, which will only run // when this action is called directly. diff --git a/docs/README.md b/docs/README.md deleted file mode 100644 index b9e4da9..0000000 --- a/docs/README.md +++ /dev/null @@ -1,7 +0,0 @@ -# Borg Data Collector Documentation - -This directory contains the documentation for the Borg Data Collector. - -## Table of Contents - -- [Usage](usage.md) diff --git a/docs/usage.md b/docs/usage.md deleted file mode 100644 index 52feff0..0000000 --- a/docs/usage.md +++ /dev/null @@ -1,39 +0,0 @@ -# Usage - -This document explains how to use the Borg Data Collector. - -## `collect git` - -The `collect git` command is used to clone a git repository and store it in a DataNode. - -### Collect a single repository - -```bash -borg collect git --uri https://github.com/torvalds/linux.git --output linux.dat -``` - -### Collect all repositories for a user - -```bash -borg collect git --user torvalds --output /path/to/output/dir -``` - -## `collect website` - -The `collect website` command is used to crawl a website and store it in a DataNode. - -### Example - -```bash -borg collect website --uri https://tldp.org/ -``` - -## `serve` - -The `serve` command is used to serve a DataNode file. - -### Example - -```bash -borg serve --file linux.borg -``` diff --git a/examples/collect_git.sh b/examples/collect_git.sh deleted file mode 100644 index b7fd1d5..0000000 --- a/examples/collect_git.sh +++ /dev/null @@ -1,9 +0,0 @@ -#!/bin/bash - -# Example of how to use the 'collect git' command. - -# This will clone a single git repository and store it in a DataNode. -borg collect git --uri https://github.com/torvalds/linux.git --output linux.dat - -# This will clone all public repositories for a user and store them in a directory. -borg collect git --user torvalds --output /tmp/borg-repos diff --git a/examples/collect_website.sh b/examples/collect_website.sh deleted file mode 100644 index 5f96616..0000000 --- a/examples/collect_website.sh +++ /dev/null @@ -1,6 +0,0 @@ -#!/bin/bash - -# Example of how to use the 'collect website' command. - -# This will crawl the specified website and store it in a DataNode. -borg collect website --uri https://tldp.org/ diff --git a/examples/serve.sh b/examples/serve.sh deleted file mode 100644 index 3aa4c9c..0000000 --- a/examples/serve.sh +++ /dev/null @@ -1,6 +0,0 @@ -#!/bin/bash - -# Example of how to use the 'serve' command. - -# This will serve the specified DataNode file. -borg serve --file linux.borg diff --git a/go.mod b/go.mod index 64eb54c..1fdfae3 100644 --- a/go.mod +++ b/go.mod @@ -7,7 +7,6 @@ require ( github.com/google/go-github/v39 v39.2.0 github.com/schollz/progressbar/v3 v3.18.0 github.com/spf13/cobra v1.10.1 - golang.org/x/mod v0.12.0 golang.org/x/net v0.46.0 ) @@ -33,6 +32,7 @@ require ( github.com/spf13/pflag v1.0.10 // indirect github.com/xanzy/ssh-agent v0.3.3 // indirect golang.org/x/crypto v0.43.0 // indirect + golang.org/x/mod v0.29.0 // indirect golang.org/x/sys v0.37.0 // indirect golang.org/x/term v0.36.0 // indirect gopkg.in/warnings.v0 v0.1.2 // indirect diff --git a/go.sum b/go.sum index d841f7d..e2688d7 100644 --- a/go.sum +++ b/go.sum @@ -101,8 +101,8 @@ golang.org/x/crypto v0.43.0 h1:dduJYIi3A3KOfdGOHX8AVZ/jGiyPa3IbBozJ5kNuE04= golang.org/x/crypto v0.43.0/go.mod h1:BFbav4mRNlXJL4wNeejLpWxB7wMbc79PdRGhWKncxR0= golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 h1:2dVuKD2vS7b0QIHQbpyTISPd0LeHDbnYEryqj5Q1ug8= golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56/go.mod h1:M4RDyNAINzryxdtnbRXRL/OHtkFuWGRjvuhBJpk2IlY= -golang.org/x/mod v0.12.0 h1:rmsUpXtvNzj340zd98LZ4KntptpfRHwpFOHG188oHXc= -golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= +golang.org/x/mod v0.29.0 h1:HV8lRxZC4l2cr3Zq1LvtOsi/ThTgWnUk/y64QSs8GwA= +golang.org/x/mod v0.29.0/go.mod h1:NyhrlYXJ2H4eJiRy/WDBO6HMqZQ6q9nk4JzS3NuCK+w= golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks= golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y= diff --git a/go.work b/go.work deleted file mode 100644 index 0eda0de..0000000 --- a/go.work +++ /dev/null @@ -1,3 +0,0 @@ -go 1.24.3 - -use . diff --git a/go.work.sum b/go.work.sum deleted file mode 100644 index 2bd247a..0000000 --- a/go.work.sum +++ /dev/null @@ -1,43 +0,0 @@ -github.com/bwesterb/go-ristretto v1.2.3 h1:1w53tCkGhCQ5djbat3+MH0BAQ5Kfgbt56UZQ/JMzngw= -github.com/bwesterb/go-ristretto v1.2.3/go.mod h1:fUIoIZaG73pV5biE2Blr2xEzDoMj7NFEuV9ekS419A0= -github.com/cpuguy83/go-md2man/v2 v2.0.6 h1:XJtiaUW6dEEqVuZiMTn1ldk455QWwEIsMIJlo5vtkx0= -github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= -github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U= -github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek= -github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps= -github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= -github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE= -github.com/google/go-github/v39 v39.2.0 h1:rNNM311XtPOz5rDdsJXAp2o8F67X9FnROXTvto3aSnQ= -github.com/google/go-github/v39 v39.2.0/go.mod h1:C1s8C5aCC9L+JXIYpJM5GYytdX52vC1bLvHEF1IhBrE= -github.com/google/go-querystring v1.1.0 h1:AnCroh3fv4ZBgVIf1Iwtovgjaw/GiKJo8M8yD/fhyJ8= -github.com/google/go-querystring v1.1.0/go.mod h1:Kcdr2DB4koayq7X8pmAG4sNG59So17icRSOU623lUBU= -github.com/k0kubun/go-ansi v0.0.0-20180517002512-3bf9e2903213 h1:qGQQKEcAR99REcMpsXCp3lJ03zYT1PkRd3kQGPn9GVg= -github.com/k0kubun/go-ansi v0.0.0-20180517002512-3bf9e2903213/go.mod h1:vNUNkEQ1e29fT/6vq2aBdFsgNPmy8qMdSay1npru+Sw= -github.com/kr/pty v1.1.1 h1:VkoXIwSboBpnk99O/KFauAEILuNHv5DVFKZMBN/gUgw= -github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY= -github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y= -github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk= -github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ= -github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ= -github.com/stretchr/objx v0.1.0 h1:4G4v2dO3VZwixGIRoQ5Lfboy6nUhCyYzaqnIAPPhYs4= -golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= -golang.org/x/crypto v0.0.0-20210817164053-32db794688a5/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= -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 v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks= -golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg= -golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be h1:vEDujvNQGv4jgYKudGeI/+DAX4Jffq6hpD55MmoEvKs= -golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= -golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= -golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= -golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk= -golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ= -golang.org/x/tools v0.11.0 h1:EMCa6U9S2LtZXLAMoWiR/R8dAQFRqbAitmbJ2UKhoi8= -golang.org/x/tools v0.11.0/go.mod h1:anzJrxPjNtfgiYQYirP2CPGzGLxrH2u2QBhn6Bf3qY8= -golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4= -golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= -google.golang.org/appengine v1.6.7 h1:FZR1q0exgwxzPzp/aF+VccGrSfxfPpkBqjIIEq3ru6c= -google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc= -google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI= -google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos= -gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY= diff --git a/main.go b/main.go new file mode 100644 index 0000000..3989f09 --- /dev/null +++ b/main.go @@ -0,0 +1,7 @@ +package main + +import "github.com/Snider/Borg/cmd" + +func main() { + cmd.Execute() +} diff --git a/pkg/github/github.go b/pkg/github/github.go index c7cf8f4..f28553b 100644 --- a/pkg/github/github.go +++ b/pkg/github/github.go @@ -11,15 +11,7 @@ type Repo struct { } func GetPublicRepos(userOrOrg string) ([]string, error) { - return GetPublicReposWithAPIURL("https://api.github.com", userOrOrg) -} - -func GetPublicReposWithAPIURL(apiURL, userOrOrg string) ([]string, error) { - if userOrOrg == "" { - return nil, fmt.Errorf("user or organization cannot be empty") - } - - resp, err := http.Get(fmt.Sprintf("%s/users/%s/repos", apiURL, userOrOrg)) + resp, err := http.Get(fmt.Sprintf("https://api.github.com/users/%s/repos", userOrOrg)) if err != nil { return nil, err } @@ -27,7 +19,7 @@ func GetPublicReposWithAPIURL(apiURL, userOrOrg string) ([]string, error) { if resp.StatusCode != http.StatusOK { // Try organization endpoint - resp, err = http.Get(fmt.Sprintf("%s/orgs/%s/repos", apiURL, userOrOrg)) + resp, err = http.Get(fmt.Sprintf("https://api.github.com/orgs/%s/repos", userOrOrg)) if err != nil { return nil, err } diff --git a/pkg/github/github_test.go b/pkg/github/github_test.go deleted file mode 100644 index 00e952b..0000000 --- a/pkg/github/github_test.go +++ /dev/null @@ -1,42 +0,0 @@ -package github - -import ( - "net/http" - "net/http/httptest" - "testing" -) - -func TestGetPublicRepos_Good(t *testing.T) { - server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { - w.WriteHeader(http.StatusOK) - w.Write([]byte(`[{"clone_url": "https://github.com/good/repo.git"}]`)) - })) - defer server.Close() - - repos, err := GetPublicReposWithAPIURL(server.URL, "good") - if err != nil { - t.Errorf("Expected no error, got %v", err) - } - if len(repos) != 1 || repos[0] != "https://github.com/good/repo.git" { - t.Errorf("Expected one repo, got %v", repos) - } -} - -func TestGetPublicRepos_Bad(t *testing.T) { - server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { - w.WriteHeader(http.StatusNotFound) - })) - defer server.Close() - - _, err := GetPublicReposWithAPIURL(server.URL, "bad") - if err == nil { - t.Errorf("Expected an error, got nil") - } -} - -func TestGetPublicRepos_Ugly(t *testing.T) { - _, err := GetPublicReposWithAPIURL("http://localhost", "") - if err == nil { - t.Errorf("Expected an error for empty user/org, got nil") - } -}