Allow for the exclusion of files from backups (#100)

* Hoist walking of files so it can be used for features other than archive creation

* Add option to ignore files from backup using glob patterns

* Use Regexp instead of glob for exclusion

* Ignore artifacts

* Add teardown to test

* Allow single Re for filtering only

* Add documentation

* Use MatchString on re, add bad input to message in case of error

README.md

@@ -30,6 +30,7 @@ It handles __recurring or one-off backups of Docker volumes__ to a __local direc
   - [Replace deprecated `BACKUP_FROM_SNAPSHOT` usage](#replace-deprecated-backup_from_snapshot-usage)
   - [Using a custom Docker host](#using-a-custom-docker-host)
   - [Run multiple backup schedules in the same container](#run-multiple-backup-schedules-in-the-same-container)
+  - [Define different retention schedules](#define-different-retention-schedules)
 - [Recipes](#recipes)
   - [Backing up to AWS S3](#backing-up-to-aws-s3)
   - [Backing up to Filebase](#backing-up-to-filebase)
@@ -167,6 +168,12 @@ You can populate below template according to your requirements and use it as you
 
 # BACKUP_SOURCES="/other/location"
 
+# When given, all files in BACKUP_SOURCES whose full path matches the given
+# regular expression will be excluded from the archive. Regular Expressions
+# can be used as from the Go standard library https://pkg.go.dev/regexp
+
+# BACKUP_EXCLUDE_REGEXP="\.log$"
+
 ########### BACKUP STORAGE
 
 # The name of the remote bucket that should be used for storing backups. If
@@ -207,9 +214,9 @@ You can populate below template according to your requirements and use it as you
 # AWS_ENDPOINT_PROTO="https"
 
 # Setting this variable to `true` will disable verification of
-# SSL certificates. You shouldn't use this unless you use self-signed
-# certificates for your remote storage backend. This can only be used
-# when AWS_ENDPOINT_PROTO is set to `https`.
+# SSL certificates for AWS_ENDPOINT. You shouldn't use this unless you use
+# self-signed certificates for your remote storage backend. This can only be
+# used when AWS_ENDPOINT_PROTO is set to `https`.
 
 # AWS_ENDPOINT_INSECURE="true"
 
@@ -232,6 +239,12 @@ You can populate below template according to your requirements and use it as you
 
 # WEBDAV_PASSWORD="password"
 
+# Setting this variable to `true` will disable verification of
+# SSL certificates for WEBDAV_URL. You shouldn't use this unless you use
+# self-signed certificates for your remote storage backend.
+
+# WEBDAV_URL_INSECURE="true"
+
 # In addition to storing backups remotely, you can also keep local copies.
 # Pass a container-local path to store your backups if needed. You also need to
 # mount a local folder or Docker volume into that location (`/archive`
@@ -733,6 +746,39 @@ The exact order of schedules that use the same cron expression is not specified.
 In case you need your schedules to overlap, you need to create a dedicated container for each schedule instead.
 When changing the configuration, you currently need to manually restart the container for the changes to take effect.
 
+### Define different retention schedules
+
+If you want to manage backup retention on different schedules, the most straight forward approach is to define a dedicated configuration for retention rule using a different prefix in the `BACKUP_FILENAME` parameter and then run them on different cron schedules.
+
+For example, if you wanted to keep daily backups for 7 days, weekly backups for a month, and retain monthly backups forever, you could create three configuration files and mount them into `/etc/dockervolumebackup.d`:
+
+```ini
+# 01daily.conf
+BACKUP_FILENAME="daily-backup-%Y-%m-%dT%H-%M-%S.tar.gz"
+# run every day at 2am
+BACKUP_CRON_EXPRESSION="0 2 * * *"
+BACKUP_PRUNING_PREFIX="daily-backup-"
+BACKUP_RETENTION_DAYS="7"
+```
+
+```ini
+# 02weekly.conf
+BACKUP_FILENAME="weekly-backup-%Y-%m-%dT%H-%M-%S.tar.gz"
+# run every monday at 3am
+BACKUP_CRON_EXPRESSION="0 3 * * 1"
+BACKUP_PRUNING_PREFIX="weekly-backup-"
+BACKUP_RETENTION_DAYS="31"
+```
+
+```ini
+# 03monthly.conf
+BACKUP_FILENAME="monthly-backup-%Y-%m-%dT%H-%M-%S.tar.gz"
+# run every 1st of a month at 4am
+BACKUP_CRON_EXPRESSION="0 4 1 * *"
+```
+
+Note that while it's possible to define colliding cron schedules for each of these configurations, you might need to adjust the value for `LOCK_TIMEOUT` in case your backups are large and might take longer than an hour.
+
 ## Recipes
 
 This section lists configuration for some real-world use cases that you can mix and match according to your needs.

cmd/backup/archive.go

@@ -11,14 +11,13 @@ import (
 	"compress/gzip"
 	"fmt"
 	"io"
-	"io/fs"
 	"os"
 	"path"
 	"path/filepath"
 	"strings"
 )
 
-func createArchive(inputFilePath, outputFilePath string) error {
+func createArchive(files []string, inputFilePath, outputFilePath string) error {
 	inputFilePath = stripTrailingSlashes(inputFilePath)
 	inputFilePath, outputFilePath, err := makeAbsolute(inputFilePath, outputFilePath)
 	if err != nil {
@@ -28,7 +27,7 @@ func createArchive(inputFilePath, outputFilePath string) error {
 		return fmt.Errorf("createArchive: error creating output file path: %w", err)
 	}
 
-	if err := compress(inputFilePath, outputFilePath, filepath.Dir(inputFilePath)); err != nil {
+	if err := compress(files, outputFilePath, filepath.Dir(inputFilePath)); err != nil {
 		return fmt.Errorf("createArchive: error creating archive: %w", err)
 	}
 
@@ -52,7 +51,7 @@ func makeAbsolute(inputFilePath, outputFilePath string) (string, string, error)
 	return inputFilePath, outputFilePath, err
 }
 
-func compress(inPath, outFilePath, subPath string) error {
+func compress(paths []string, outFilePath, subPath string) error {
 	file, err := os.Create(outFilePath)
 	if err != nil {
 		return fmt.Errorf("compress: error creating out file: %w", err)
@@ -62,14 +61,6 @@ func compress(inPath, outFilePath, subPath string) error {
 	gzipWriter := gzip.NewWriter(file)
 	tarWriter := tar.NewWriter(gzipWriter)
 
-	var paths []string
-	if err := filepath.WalkDir(inPath, func(path string, di fs.DirEntry, err error) error {
-		paths = append(paths, path)
-		return err
-	}); err != nil {
-		return fmt.Errorf("compress: error walking filesystem tree: %w", err)
-	}
-
 	for _, p := range paths {
 		if err := writeTarGz(p, tarWriter, prefix); err != nil {
 			return fmt.Errorf("compress error writing %s to archive: %w", p, err)

cmd/backup/config.go

@@ -3,7 +3,11 @@
 
 package main
 
-import "time"
+import (
+	"fmt"
+	"regexp"
+	"time"
+)
 
 // Config holds all configuration values that are expected to be set
 // by users.
@@ -18,6 +22,7 @@ type Config struct {
 	BackupPruningPrefix        string        `split_words:"true"`
 	BackupStopContainerLabel   string        `split_words:"true" default:"true"`
 	BackupFromSnapshot         bool          `split_words:"true"`
+	BackupExcludeRegexp        RegexpDecoder `split_words:"true"`
 	AwsS3BucketName            string        `split_words:"true"`
 	AwsS3Path                  string        `split_words:"true"`
 	AwsEndpoint                string        `split_words:"true" default:"s3.amazonaws.com"`
@@ -36,6 +41,7 @@ type Config struct {
 	EmailSMTPUsername          string        `envconfig:"EMAIL_SMTP_USERNAME"`
 	EmailSMTPPassword          string        `envconfig:"EMAIL_SMTP_PASSWORD"`
 	WebdavUrl                  string        `split_words:"true"`
+	WebdavUrlInsecure          bool          `split_words:"true"`
 	WebdavPath                 string        `split_words:"true" default:"/"`
 	WebdavUsername             string        `split_words:"true"`
 	WebdavPassword             string        `split_words:"true"`
@@ -43,3 +49,19 @@ type Config struct {
 	ExecForwardOutput          bool          `split_words:"true"`
 	LockTimeout                time.Duration `split_words:"true" default:"60m"`
 }
+
+type RegexpDecoder struct {
+	Re *regexp.Regexp
+}
+
+func (r *RegexpDecoder) Decode(v string) error {
+	if v == "" {
+		return nil
+	}
+	re, err := regexp.Compile(v)
+	if err != nil {
+		return fmt.Errorf("config: error compiling given regexp `%s`: %w", v, err)
+	}
+	*r = RegexpDecoder{Re: re}
+	return nil
+}

cmd/backup/script.go

@@ -9,6 +9,7 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
+	"net/http"
 	"os"
 	"path"
 	"path/filepath"
@@ -146,6 +147,15 @@ func newScript() (*script, error) {
 		} else {
 			webdavClient := gowebdav.NewClient(s.c.WebdavUrl, s.c.WebdavUsername, s.c.WebdavPassword)
 			s.webdavClient = webdavClient
+			if s.c.WebdavUrlInsecure {
+				defaultTransport, ok := http.DefaultTransport.(*http.Transport)
+				if !ok {
+					return nil, errors.New("newScript: unexpected error when asserting type for http.DefaultTransport")
+				}
+				webdavTransport := defaultTransport.Clone()
+				webdavTransport.TLSClientConfig.InsecureSkipVerify = s.c.WebdavUrlInsecure
+				s.webdavClient.SetTransport(webdavTransport)
+			}
 		}
 	}
 
@@ -388,7 +398,28 @@ func (s *script) takeBackup() error {
 		s.logger.Infof("Removed tar file `%s`.", tarFile)
 		return nil
 	})
-	if err := createArchive(backupSources, tarFile); err != nil {
+
+	backupPath, err := filepath.Abs(stripTrailingSlashes(backupSources))
+	if err != nil {
+		return fmt.Errorf("takeBackup: error getting absolute path: %w", err)
+	}
+
+	var filesEligibleForBackup []string
+	if err := filepath.WalkDir(backupPath, func(path string, di fs.DirEntry, err error) error {
+		if err != nil {
+			return err
+		}
+
+		if s.c.BackupExcludeRegexp.Re != nil && s.c.BackupExcludeRegexp.Re.MatchString(path) {
+			return nil
+		}
+		filesEligibleForBackup = append(filesEligibleForBackup, path)
+		return nil
+	}); err != nil {
+		return fmt.Errorf("compress: error walking filesystem tree: %w", err)
+	}
+
+	if err := createArchive(filesEligibleForBackup, backupSources, tarFile); err != nil {
 		return fmt.Errorf("takeBackup: error compressing backup folder: %w", err)
 	}
 
@@ -537,6 +568,7 @@ func (s *script) pruneBackups() error {
 		candidates := s.minioClient.ListObjects(context.Background(), s.c.AwsS3BucketName, minio.ListObjectsOptions{
 			WithMetadata: true,
 			Prefix:       filepath.Join(s.c.AwsS3Path, s.c.BackupPruningPrefix),
+			Recursive:    true,
 		})
 
 		var matches []minio.ObjectInfo

go.mod

@@ -12,7 +12,7 @@ require (
 	github.com/minio/minio-go/v7 v7.0.16
 	github.com/otiai10/copy v1.7.0
 	github.com/sirupsen/logrus v1.8.1
-	github.com/studio-b12/gowebdav v0.0.0-20211109083228-3f8721cd4b6f
+	github.com/studio-b12/gowebdav v0.0.0-20220128162035-c7b1ff8a5e62
 	golang.org/x/crypto v0.0.0-20210817164053-32db794688a5
 	golang.org/x/sync v0.0.0-20210220032951-036812b2e83c
 )

go.sum

@@ -660,6 +660,8 @@ github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd
 github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/studio-b12/gowebdav v0.0.0-20211109083228-3f8721cd4b6f h1:L2NE7BXnSlSLoNYZ0lCwZDjdnYjCNYC71k9ClZUTFTs=
 github.com/studio-b12/gowebdav v0.0.0-20211109083228-3f8721cd4b6f/go.mod h1:bHA7t77X/QFExdeAnDzK6vKM34kEZAcE1OX4MfiwjkE=
+github.com/studio-b12/gowebdav v0.0.0-20220128162035-c7b1ff8a5e62 h1:b2nJXyPCa9HY7giGM+kYcnQ71m14JnGdQabMPmyt++8=
+github.com/studio-b12/gowebdav v0.0.0-20220128162035-c7b1ff8a5e62/go.mod h1:bHA7t77X/QFExdeAnDzK6vKM34kEZAcE1OX4MfiwjkE=
 github.com/subosito/gotenv v1.2.0/go.mod h1:N0PQaV/YGNqwC0u51sEeR/aUtSLEXKX9iv69rRypqCw=
 github.com/syndtr/gocapability v0.0.0-20170704070218-db04d3cc01c8/go.mod h1:hkRG7XYTFWNJGYcbNJQlaLq0fg1yr4J4t/NcTQtrfww=
 github.com/syndtr/gocapability v0.0.0-20180916011248-d98352740cb2/go.mod h1:hkRG7XYTFWNJGYcbNJQlaLq0fg1yr4J4t/NcTQtrfww=

test/compose/docker-compose.yml

@@ -43,6 +43,7 @@ services:
       BACKUP_PRUNING_PREFIX: test
       GPG_PASSPHRASE: 1234secret
       WEBDAV_URL: http://webdav/
+      WEBDAV_URL_INSECURE: 'true'
       WEBDAV_PATH: /my/new/path/
       WEBDAV_USERNAME: test
       WEBDAV_PASSWORD: test

test/ignore/.gitignore

@@ -0,0 +1 @@
+local

test/ignore/docker-compose.yml

@@ -0,0 +1,15 @@
+version: '3.8'
+
+services:
+  backup:
+    image: offen/docker-volume-backup:${TEST_VERSION:-canary}
+    deploy:
+      restart_policy:
+        condition: on-failure
+    environment:
+      BACKUP_FILENAME: test.tar.gz
+      BACKUP_CRON_EXPRESSION: 0 0 5 31 2 ?
+      BACKUP_EXCLUDE_REGEXP: '\.(me|you)$$'
+    volumes:
+      - ./local:/archive
+      - ./sources:/backup/data:ro

test/ignore/run.sh

@@ -0,0 +1,27 @@
+#!/bin/sh
+
+set -e
+
+cd $(dirname $0)
+mkdir -p local
+
+docker-compose up -d
+sleep 5
+docker-compose exec backup backup
+
+docker-compose down --volumes
+
+out=$(mktemp -d)
+sudo tar --same-owner -xvf ./local/test.tar.gz -C "$out"
+
+if [ ! -f "$out/backup/data/me.txt" ]; then
+  echo "[TEST:FAIL] Expected file was not found."
+  exit 1
+fi
+echo "[TEST:PASS] Expected file was found."
+
+if [ -f "$out/backup/data/skip.me" ]; then
+  echo "[TEST:FAIL] Ignored file was found."
+  exit 1
+fi
+echo "[TEST:PASS] Ignored file was not found."