Merge pull request #22 from apiiro/tomer/file-paths-file

Allow sending the location of a file with a list of files to snap

Makefile

@@ -13,10 +13,10 @@ build-osx:
 ifneq ($(shell uname -s),Darwin)
 	$(error this makefile assumes you're building from mac env)
 endif
-	GO111MODULE=on CGO_ENABLED=0 $(GOCMD) build -o bin/$(BINARY_NAME)-$(shell $(GOCMD) run . --version | cut -d" " -f 3)-osx .
+	GO111MODULE=on CGO_ENABLED=0 GOARCH=amd64 $(GOCMD) build -o bin/$(BINARY_NAME)-$(shell $(GOCMD) run . --version | cut -d" " -f 3)-osx .
 
 build-linux:
-	docker run --rm -v $(shell pwd):/app -w /app golang:1.20-alpine /bin/sh -c "GO111MODULE=on CGO_ENABLED=0 $(GOCMD) build -o bin/$(BINARY_NAME)-$(shell $(GOCMD) run . --version | cut -d" " -f 3)-linux ."
+	docker run --rm -v $(shell pwd):/app -w /app --platform=linux/amd64 golang:1.20-alpine3.18 /bin/sh -c "GO111MODULE=on CGO_ENABLED=0 GOARCH=amd64 $(GOCMD) build -o bin/$(BINARY_NAME)-$(shell $(GOCMD) run . --version | cut -d" " -f 3)-linux ."
 
 clean:
 	rm -rf ./bin

README.md

@@ -6,28 +6,29 @@ Tool to create a git revision snapshot for an existing repository clone.
 
 ```
 NAME:
-   git-snap - 1.17 - Create a git revision snapshot for an existing repository clone. Symbolic link files will be omitted.
+   git-snap - 1.18 - Create a git revision snapshot for an existing repository clone. Symbolic link files will be omitted.
 
 USAGE:
-   git-snap --src value --rev value   --out value          [optional flags]
+   git-snap --src value --rev value   --out value           [optional flags]
 
 OPTIONS:
-   --src value, -s value      path to existing git clone as source directory, may contain no more than .git directory, current git state doesn't affect the command
-   --rev value, -r value      commit-ish Revision
-   --index value, -x value    Create index file listing file paths and their blob IDs
-   --index-only, --xo         Create index only - Don't checkout any files (default: false)
-   --out value, -o value      output directory. will be created if does not exist
-   --include value, -i value  patterns of file paths to include, comma delimited, may contain any glob pattern
-   --exclude value, -e value  patterns of file paths to exclude, comma delimited, may contain any glob pattern
-   --verbose, --vv            verbose logging (default: false)
-   --text-only                include only text files (default: false)
-   --hash-markers             create also hint files mirroring the hash of original files at <path>.hash (default: false)
-   --ignore-case              ignore case when checking path against inclusion patterns (default: false)
-   --max-size value           maximal file size, in MB (default: 6)
-   --no-double-check          disable files discrepancy double check (default: false)
-   --include-noise-dirs       don't filter out noisy directory names in paths (bin, node_modules etc) (default: false)
-   --help, -h                 show help (default: false)
-   --version, -v              print the version (default: false)
+   --src value, -s value                    path to existing git clone as source directory, may contain no more than .git directory, current git state doesn't affect the command
+   --rev value, -r value                    commit-ish Revision
+   --index value, -x value                  Create index file listing file paths and their blob IDs
+   --index-only, --xo                       Create index only - Don't checkout any files (default: false)
+   --out value, -o value                    output directory. will be created if does not exist
+   --include value, -i value                patterns of file paths to include, comma delimited, may contain any glob pattern
+   --exclude value, -e value                patterns of file paths to exclude, comma delimited, may contain any glob pattern
+   --verbose, --vv                          verbose logging (default: false)
+   --text-only                              include only text files (default: false)
+   --hash-markers                           create also hint files mirroring the hash of original files at <path>.hash (default: false)
+   --ignore-case                            ignore case when checking path against inclusion patterns (default: false)
+   --max-size value                         maximal file size, in MB (default: 6)
+   --no-double-check                        disable files discrepancy double check (default: false)
+   --include-noise-dirs                     don't filter out noisy directory names in paths (bin, node_modules etc) (default: false)
+   --paths-file-location value, --pl value  a location of a text file with all the paths to snap (one path per line)
+   --help, -h                               show help (default: false)
+   --version, -v                            print the version (default: false)
    
 EXIT CODES:
   0   Success

git/git.go

@@ -1,6 +1,7 @@
 package git
 
 import (
+	"bufio"
 	"errors"
 	"fmt"
 	"gitsnap/options"
@@ -30,13 +31,20 @@ type repositoryProvider struct {
 	repository      *git.Repository
 	includePatterns []glob.Glob
 	excludePatterns []glob.Glob
+	fileListToSnap  map[string]bool
 	opts            *options.Options
 }
 
 func Snapshot(opts *options.Options) (err error) {
 
 	provider := &repositoryProvider{
-		opts: opts,
+		opts:           opts,
+		fileListToSnap: map[string]bool{},
+	}
+
+	err = loadFilePathsList(opts, provider)
+	if err != nil {
+		return err
 	}
 
 	provider.includePatterns, err = provider.compileGlobs(opts.IncludePatterns, "include")
@@ -106,6 +114,24 @@ func Snapshot(opts *options.Options) (err error) {
 	return nil
 }
 
+func loadFilePathsList(opts *options.Options, provider *repositoryProvider) error {
+	if opts.PathsFileLocation != "" {
+		file, err := os.Open(opts.PathsFileLocation)
+		if err != nil {
+			return fmt.Errorf("failed to read paths file from location: '%v', error: '%v'", opts.PathsFileLocation, err)
+		}
+
+		defer file.Close()
+		scanner := bufio.NewScanner(file)
+
+		for scanner.Scan() {
+			line := scanner.Text()
+			provider.fileListToSnap[line] = true
+		}
+	}
+	return nil
+}
+
 func (provider *repositoryProvider) getCommit(commitish string) (*object.Commit, error) {
 
 	hash, err := provider.repository.ResolveRevision(plumbing.Revision(commitish))
@@ -174,6 +200,11 @@ func (provider *repositoryProvider) dumpFile(repository *git.Repository, name st
 		filePathToCheck = strings.ToLower(filePathToCheck)
 	}
 
+	if !isFileInList(provider, filePathToCheck) {
+		provider.verboseLog("--- skipping '%v' - not matching file list", filePath)
+		return nil, false
+	}
+
 	skip := true
 	hasIncludePatterns := len(provider.includePatterns) > 0
 	if hasIncludePatterns && !matches(filePathToCheck, provider.includePatterns) {
@@ -261,6 +292,11 @@ func (provider *repositoryProvider) dumpFile(repository *git.Repository, name st
 	return nil, true
 }
 
+func isFileInList(provider *repositoryProvider, filePathToCheck string) bool {
+	_, inFileList := provider.fileListToSnap[filePathToCheck]
+	return inFileList || len(provider.fileListToSnap) == 0
+}
+
 func addEntryToIndexFile(indexFile *os.File, name string, entry *object.TreeEntry) error {
 	if indexFile != nil {
 		_, err := indexFile.WriteString(fmt.Sprintf("%v\t%v\t%v\n", name, entry.Hash.String(), entry.Mode.IsFile()))

git/git_test.go

@@ -512,3 +512,43 @@ func (gitSuite *gitTestSuite) TestSnapshotWithIndexPath() {
 	gitSuite.Nil(err)
 	gitSuite.verifyIndexFile(40, indexFilePath)
 }
+
+func (gitSuite *gitTestSuite) TestSnapshotWithPathsFile() {
+	filesDir, err := ioutil.TempDir("", "")
+	if err != nil {
+		panic(err)
+	}
+
+	filePath := filepath.Join(filesDir, "file.txt")
+
+	file, err := os.OpenFile(filePath, os.O_WRONLY|os.O_APPEND|os.O_CREATE, 0644)
+
+	if err != nil {
+		gitSuite.Nil(err)
+		return
+	}
+
+	data := []byte("src/main/java/com/dchealth/VO/DataElementFormat.java")
+	_, err = file.Write(data)
+
+	if err != nil {
+		err = fmt.Errorf("Failed to write paths file: '%v'", err)
+		fmt.Println(err)
+		gitSuite.Nil(err)
+		return
+	}
+
+	file.Close()
+
+	err = Snapshot(&options.Options{
+		ClonePath:         gitSuite.clonePath,
+		Revision:          "2ca742044ba451d00c6854a465fdd4280d9ad1f5",
+		OutputPath:        gitSuite.outputPath,
+		IncludePatterns:   []string{},
+		ExcludePatterns:   []string{},
+		PathsFileLocation: filePath,
+	})
+
+	gitSuite.Nil(err)
+	gitSuite.verifyOutputPath(7, 1, 1696, 1696)
+}

go.mod

@@ -1,6 +1,6 @@
 module gitsnap
 
-go 1.16
+go 1.14
 
 require (
 	github.com/avast/retry-go v3.0.0+incompatible

main.go

@@ -10,7 +10,7 @@ import (
 	"github.com/urfave/cli/v2"
 )
 
-const VERSION = "1.17"
+const VERSION = "1.18"
 
 func main() {
 	cli.AppHelpTemplate =

options/options.go

@@ -99,6 +99,12 @@ var Flags = []cli.Flag{
 		Usage:    "don't filter out noisy directory names in paths (bin, node_modules etc)",
 		Required: false,
 	},
+	&cli.StringFlag{
+		Name:     "paths-file-location",
+		Aliases:  []string{"pl"},
+		Usage:    "a location of a text file with all the paths to snap (one path per line)",
+		Required: false,
+	},
 }
 
 type Options struct {
@@ -116,6 +122,7 @@ type Options struct {
 	MaxFileSizeBytes      int64
 	SkipDoubleCheck       bool
 	IncludeNoiseDirs      bool
+	PathsFileLocation     string
 }
 
 func splitListFlag(flag string) []string {
@@ -162,6 +169,7 @@ func ParseOptions(c *cli.Context) (*Options, error) {
 		IncludeNoiseDirs:      c.Bool("include-noise-dirs"),
 		OptionalIndexFilePath: c.String("index"),
 		IndexOnly:             c.Bool("index-only"),
+		PathsFileLocation:     c.String("paths-file-location"),
 	}
 
 	err := validateDirectory(opts.ClonePath, false)