sqlstream -> pipeclean

xeger · Apr 11, 2023 · 2f90ae3 · 2f90ae3
1 parent dea1148
commit 2f90ae3
Show file tree

Hide file tree

Showing 20 changed files with 44 additions and 44 deletions.
diff --git a/Makefile b/Makefile
@@ -1,18 +1,18 @@
 .PHONY: benchmark bin clean default test
 
 default:
-	cat data/sql/input.sql | ./sqlstream scrub data/models
+	cat data/sql/input.sql | ./pipeclean scrub data/models
 
-bin: bin/sqlstream-darwin-amd64 bin/sqlstream-darwin-arm64
+bin: bin/pipeclean-darwin-amd64 bin/pipeclean-darwin-arm64
 
-bin/sqlstream-darwin-amd64:
-	env GOOS=darwin GOARCH=amd64 go build -o bin/sqlstream-darwin-amd64
+bin/pipeclean-darwin-amd64:
+	env GOOS=darwin GOARCH=amd64 go build -o bin/pipeclean-darwin-amd64
 
-bin/sqlstream-darwin-arm64:
-	env GOOS=darwin GOARCH=amd64 go build -o bin/sqlstream-darwin-arm64
+bin/pipeclean-darwin-arm64:
+	env GOOS=darwin GOARCH=amd64 go build -o bin/pipeclean-darwin-arm64
 
 benchmark:
-	time cat data/sql/benchmark.sql | ./sqlstream scrub data/models > data/sql/benchmark-output.sql
+	time cat data/sql/benchmark.sql | ./pipeclean scrub data/models > data/sql/benchmark-output.sql
 
 clean:
 	rm -Rf bin
@@ -24,16 +24,16 @@ test:
 data: data/models/city.json data/models/givenName.json data/models/sn.json data/models/streetName.json
 
 data/models/city.txt: data/training/city.csv
-	tail -n+2 data/training/city.csv | ./sqlstream train dict > data/models/city.txt
+	tail -n+2 data/training/city.csv | ./pipeclean train dict > data/models/city.txt
 
 data/models/city.json: Makefile data/models/city.txt
-	cat data/models/city.txt | ./sqlstream train markov:words:5 > data/models/city.json
+	cat data/models/city.txt | ./pipeclean train markov:words:5 > data/models/city.json
 
 data/models/givenName.json: Makefile data/training/givenName.csv
-	tail -n+2 data/training/givenName.csv | ./sqlstream train markov:words:3 > data/models/givenName.json
+	tail -n+2 data/training/givenName.csv | ./pipeclean train markov:words:3 > data/models/givenName.json
 
 data/models/sn.json: Makefile data/training/sn.csv
-	tail -n+2 data/training/sn.csv | ./sqlstream train markov:words:3 > data/models/sn.json
+	tail -n+2 data/training/sn.csv | ./pipeclean train markov:words:3 > data/models/sn.json
 
 data/models/streetName.json: Makefile data/training/streetName.csv
-	tail -n+2 data/training/streetName.csv | ./sqlstream train markov:words:5 > data/models/streetName.json
+	tail -n+2 data/training/streetName.csv | ./pipeclean train markov:words:5 > data/models/streetName.json
diff --git a/cmd/generate.go b/cmd/generate.go
@@ -6,7 +6,7 @@ import (
 	"os"
 
 	"github.com/spf13/cobra"
-	"github.com/xeger/sqlstream/nlp"
+	"github.com/xeger/pipeclean/nlp"
 )
 
 // Used for flags.
@@ -24,7 +24,7 @@ func generate(cmd *cobra.Command, args []string) {
 	if len(args) == 1 {
 		modelFile = args[0]
 	} else {
-		fmt.Fprintln(os.Stderr, "Usage: sqlstream generate <modelFile>")
+		fmt.Fprintln(os.Stderr, "Usage: pipeclean generate <modelFile>")
 		os.Exit(1)
 	}
 

diff --git a/cmd/recognize.go b/cmd/recognize.go
@@ -7,7 +7,7 @@ import (
 	"strings"
 
 	"github.com/spf13/cobra"
-	"github.com/xeger/sqlstream/nlp"
+	"github.com/xeger/pipeclean/nlp"
 )
 
 // Used for flags.
@@ -32,7 +32,7 @@ func recognize(cmd *cobra.Command, args []string) {
 	if len(args) == 1 {
 		modelFile = args[0]
 	} else {
-		fmt.Fprintln(os.Stderr, "Usage: sqlstream recognize <modelFile>")
+		fmt.Fprintln(os.Stderr, "Usage: pipeclean recognize <modelFile>")
 		os.Exit(1)
 	}
 

diff --git a/cmd/root.go b/cmd/root.go
@@ -6,7 +6,7 @@ import (
 
 var (
 	rootCmd = &cobra.Command{
-		Use:   "sqlstream",
+		Use:   "pipeclean",
 		Short: "Streaming MySQL Sanitizer",
 		Long: `Masks sensitive text in MySQL dumps.
 Uses a heuristic rule system, applying language models to avoid depending on

diff --git a/cmd/scrub.go b/cmd/scrub.go
@@ -7,10 +7,10 @@ import (
 	"runtime"
 
 	"github.com/spf13/cobra"
-	"github.com/xeger/sqlstream/nlp"
-	"github.com/xeger/sqlstream/scrubbing"
-	"github.com/xeger/sqlstream/scrubbing/json"
-	"github.com/xeger/sqlstream/scrubbing/mysql"
+	"github.com/xeger/pipeclean/nlp"
+	"github.com/xeger/pipeclean/scrubbing"
+	"github.com/xeger/pipeclean/scrubbing/json"
+	"github.com/xeger/pipeclean/scrubbing/mysql"
 )
 
 // Used for flags.

diff --git a/cmd/train.go b/cmd/train.go
@@ -8,7 +8,7 @@ import (
 	"strings"
 
 	"github.com/spf13/cobra"
-	"github.com/xeger/sqlstream/nlp"
+	"github.com/xeger/pipeclean/nlp"
 )
 
 // Used for flags.
@@ -51,11 +51,11 @@ func train(cmd *cobra.Command, args []string) {
 		case "words":
 			markovSep = ""
 		default:
-			fmt.Fprintln(os.Stderr, "Usage: sqlstream train <modelType>[param1:param2:...]")
+			fmt.Fprintln(os.Stderr, "Usage: pipeclean train <modelType>[param1:param2:...]")
 			fmt.Fprintln(os.Stderr, "Examples:")
-			fmt.Fprintln(os.Stderr, "  sqlstream train dict # dictionary-lookup model")
-			fmt.Fprintln(os.Stderr, "  sqlstream train markov:words:5 # markov word model of order 5")
-			fmt.Fprintln(os.Stderr, "  sqlstream train markov:sentences:3 # markov sentence model of order 5")
+			fmt.Fprintln(os.Stderr, "  pipeclean train dict # dictionary-lookup model")
+			fmt.Fprintln(os.Stderr, "  pipeclean train markov:words:5 # markov word model of order 5")
+			fmt.Fprintln(os.Stderr, "  pipeclean train markov:sentences:3 # markov sentence model of order 5")
 			os.Exit(1)
 		}
 

diff --git a/go.mod b/go.mod
@@ -1,4 +1,4 @@
-module github.com/xeger/sqlstream
+module github.com/xeger/pipeclean
 
 go 1.20
 

diff --git a/main.go b/main.go
@@ -1,7 +1,7 @@
 package main
 
 import (
-	"github.com/xeger/sqlstream/cmd"
+	"github.com/xeger/pipeclean/cmd"
 )
 
 func main() {

diff --git a/nlp/clean_test.go b/nlp/clean_test.go
@@ -3,7 +3,7 @@ package nlp_test
 import (
 	"testing"
 
-	"github.com/xeger/sqlstream/nlp"
+	"github.com/xeger/pipeclean/nlp"
 )
 
 func TestClean(t *testing.T) {

diff --git a/nlp/is_test.go b/nlp/is_test.go
@@ -3,7 +3,7 @@ package nlp_test
 import (
 	"testing"
 
-	"github.com/xeger/sqlstream/nlp"
+	"github.com/xeger/pipeclean/nlp"
 )
 
 func TestIsLower(t *testing.T) {

diff --git a/nlp/markov_model.go b/nlp/markov_model.go
@@ -7,7 +7,7 @@ import (
 	"strings"
 
 	"github.com/xeger/gomarkov"
-	"github.com/xeger/sqlstream/rand"
+	"github.com/xeger/pipeclean/rand"
 )
 
 type MarkovModel struct {
@@ -21,7 +21,7 @@ type markovModelJSON struct {
 	Chain     gomarkov.Chain `json:"chain"`
 }
 
-const markovModelTypeID = "github.com/xeger/sqlstream/nlp.MarkovModel"
+const markovModelTypeID = "github.com/xeger/pipeclean/nlp.MarkovModel"
 
 func NewMarkovModel(order int, separator string) *MarkovModel {
 	return &MarkovModel{

diff --git a/nlp/markov_model_test.go b/nlp/markov_model_test.go
@@ -3,7 +3,7 @@ package nlp_test
 import (
 	"testing"
 
-	"github.com/xeger/sqlstream/nlp"
+	"github.com/xeger/pipeclean/nlp"
 )
 
 func TestDeterminism(t *testing.T) {

diff --git a/rand/new_test.go b/rand/new_test.go
@@ -3,7 +3,7 @@ package rand_test
 import (
 	"testing"
 
-	"github.com/xeger/sqlstream/rand"
+	"github.com/xeger/pipeclean/rand"
 )
 
 func TestNewSource(t *testing.T) {

diff --git a/scrubbing/json/scrub.go b/scrubbing/json/scrub.go
@@ -4,7 +4,7 @@ import (
 	"encoding/json"
 	"io"
 
-	"github.com/xeger/sqlstream/scrubbing"
+	"github.com/xeger/pipeclean/scrubbing"
 )
 
 // Scrub sanitizes a single line, which may contain multiple SQL statements.

diff --git a/scrubbing/mysql/mysql_scrubber.go b/scrubbing/mysql/mysql_scrubber.go
@@ -3,7 +3,7 @@ package mysql
 import (
 	"github.com/pingcap/tidb/parser/ast"
 	"github.com/pingcap/tidb/parser/test_driver"
-	"github.com/xeger/sqlstream/scrubbing"
+	"github.com/xeger/pipeclean/scrubbing"
 )
 
 type mysqlScrubber struct {

diff --git a/scrubbing/mysql/scrub.go b/scrubbing/mysql/scrub.go
@@ -5,7 +5,7 @@ import (
 	"fmt"
 
 	"github.com/pingcap/tidb/parser"
-	"github.com/xeger/sqlstream/scrubbing"
+	"github.com/xeger/pipeclean/scrubbing"
 )
 
 func scrub(msc *mysqlScrubber, p *parser.Parser, line string) string {

diff --git a/scrubbing/mysql/scrub_test.go b/scrubbing/mysql/scrub_test.go
@@ -7,8 +7,8 @@ import (
 	"strings"
 	"testing"
 
-	"github.com/xeger/sqlstream/scrubbing"
-	"github.com/xeger/sqlstream/scrubbing/mysql"
+	"github.com/xeger/pipeclean/scrubbing"
+	"github.com/xeger/pipeclean/scrubbing/mysql"
 )
 
 func read(t *testing.T, name string) string {

diff --git a/scrubbing/scrubber.go b/scrubbing/scrubber.go
@@ -8,8 +8,8 @@ import (
 	"regexp"
 	"strings"
 
-	"github.com/xeger/sqlstream/nlp"
-	"github.com/xeger/sqlstream/rand"
+	"github.com/xeger/pipeclean/nlp"
+	"github.com/xeger/pipeclean/rand"
 	"gopkg.in/yaml.v3"
 )
 

diff --git a/scrubbing/scrubber_test.go b/scrubbing/scrubber_test.go
@@ -3,10 +3,10 @@ package scrubbing_test
 import (
 	"testing"
 
-	"github.com/xeger/sqlstream/scrubbing"
+	"github.com/xeger/pipeclean/scrubbing"
 )
 
-const salt = "github.com/xeger/sqlstream/scrubbing"
+const salt = "github.com/xeger/pipeclean/scrubbing"
 
 func scrub(s string) string {
 	return scrubSalted(s, "")

diff --git a/sqlstream b/sqlstream
@@ -1,4 +1,4 @@
 #! /bin/sh
 
-# Convenience wrapper for running sqlstream from source.
+# Convenience wrapper for running pipeclean from source.
 exec go run main.go $@