feat: wip! dump links

go.mod

@@ -3,6 +3,7 @@ module github.com/cgi-fr/silo
 go 1.21
 
 require (
+	github.com/dominikbraun/graph v0.23.0
 	github.com/rs/zerolog v1.28.0
 	github.com/stretchr/testify v1.9.0
 )

go.sum

@@ -1,6 +1,8 @@
 github.com/coreos/go-systemd/v22 v22.3.3-0.20220203105225-a9a7ef127534/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dominikbraun/graph v0.23.0 h1:TdZB4pPqCLFxYhdyMFb1TBdFxp8XLcJfTTBQucVPgCo=
+github.com/dominikbraun/graph v0.23.0/go.mod h1:yOjYyogZLY1LSG9E33JWZJiq5k83Qy2C6POAuiViluc=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/mattn/go-colorable v0.1.12 h1:jF+Du6AlPIjs2BiUiQlKOX0rt3SujHxPnksPKZbaA40=
 github.com/mattn/go-colorable v0.1.12/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=

pkg/silo/driven.go

@@ -38,3 +38,8 @@ type Backend interface {
 	ReadLinks() DataLinkReader
 	ReadNodes() DataNodeReader
 }
+
+type DumpWriter interface {
+	Write(node DataNode, uuid string) error
+	Close() error
+}

pkg/silo/driver.go

@@ -21,16 +21,52 @@ import (
 	"errors"
 	"fmt"
 	"io"
+
+	"github.com/dominikbraun/graph"
 )
 
 type Driver struct {
 	backend Backend
+	writer  DumpWriter
 }
 
-func NewDriver(backend Backend) *Driver {
+func NewDriver(backend Backend, writer DumpWriter) *Driver {
 	return &Driver{
 		backend: backend,
+		writer:  writer,
+	}
+}
+
+func (d *Driver) Dump() error {
+	nodes, _ := d.ReadAllNodes()
+	links, _ := d.ReadAllLinks()
+
+	grph := graph.New[string, DataNode](func(n DataNode) string { return n.String() }, graph.Directed())
+
+	for _, node := range nodes {
+		if err := grph.AddVertex(node); err != nil {
+			return fmt.Errorf("%w", err)
+		}
+	}
+
+	for _, link := range links {
+		if err := grph.AddEdge(link.E1.String(), link.E2.String()); err != nil {
+			return fmt.Errorf("%w", err)
+		}
+	}
+
+	result, err := graph.StronglyConnectedComponents[string, DataNode](grph)
+	if err != nil {
+		return fmt.Errorf("%w", err)
+	}
+
+	for i, component := range result {
+		for _, id := range component {
+			println(i, id)
+		}
 	}
+
+	return nil
 }
 
 func (d *Driver) Scan(input DataRowReader) error {
@@ -46,7 +82,7 @@ func (d *Driver) Scan(input DataRowReader) error {
 			break
 		}
 
-		nodes, links := scan(datarow)
+		nodes, links := Scan(datarow)
 
 		for _, node := range nodes {
 			if err := d.backend.StoreNode(node); err != nil {
@@ -64,26 +100,6 @@ func (d *Driver) Scan(input DataRowReader) error {
 	return nil
 }
 
-func scan(datarow DataRow) ([]DataNode, []DataLink) {
-	nodes := []DataNode{}
-	links := []DataLink{}
-
-	for key, value := range datarow {
-		if value != nil {
-			nodes = append(nodes, DataNode{Key: key, Data: value})
-		}
-	}
-
-	// find all pairs in nodes
-	for i := 0; i < len(nodes); i++ {
-		for j := i + 1; j < len(nodes); j++ {
-			links = append(links, DataLink{E1: nodes[i], E2: nodes[j]})
-		}
-	}
-
-	return nodes, links
-}
-
 func (d *Driver) ReadAllNodes() ([]DataNode, error) {
 	nodes := []DataNode{}
 	reader := d.backend.ReadNodes()
@@ -123,3 +139,23 @@ func (d *Driver) ReadAllLinks() ([]DataLink, error) {
 
 	return links, nil
 }
+
+func Scan(datarow DataRow) ([]DataNode, []DataLink) {
+	nodes := []DataNode{}
+	links := []DataLink{}
+
+	for key, value := range datarow {
+		if value != nil {
+			nodes = append(nodes, DataNode{Key: key, Data: value})
+		}
+	}
+
+	// find all pairs in nodes
+	for i := 0; i < len(nodes); i++ {
+		for j := i + 1; j < len(nodes); j++ {
+			links = append(links, DataLink{E1: nodes[i], E2: nodes[j]})
+		}
+	}
+
+	return nodes, links
+}

pkg/silo/driver_test.go

@@ -35,7 +35,7 @@ func TestNominal(t *testing.T) {
 	input := silo.NewDataRowReaderInMemory(rows)
 
 	backend := silo.NewBackendInMemory()
-	driver := silo.NewDriver(backend)
+	driver := silo.NewDriver(backend, nil)
 
 	err := driver.Scan(input)
 	require.NoError(t, err)
@@ -47,4 +47,54 @@ func TestNominal(t *testing.T) {
 	links, err := driver.ReadAllLinks()
 	require.NoError(t, err)
 	assert.Len(t, links, 12)
+
+	require.NoError(t, driver.Dump())
+}
+
+func TestPartialNull(t *testing.T) {
+	t.Parallel()
+
+	rows := []silo.DataRow{
+		{"ID1": 1, "ID2": nil, "ID3": nil, "ID4": "00001"},
+		{"ID1": nil, "ID2": "2", "ID3": 2.0, "ID4": nil},
+	}
+	input := silo.NewDataRowReaderInMemory(rows)
+
+	backend := silo.NewBackendInMemory()
+	driver := silo.NewDriver(backend, nil)
+
+	err := driver.Scan(input)
+	require.NoError(t, err)
+
+	nodes, err := driver.ReadAllNodes()
+	require.NoError(t, err)
+	assert.Len(t, nodes, 4)
+
+	links, err := driver.ReadAllLinks()
+	require.NoError(t, err)
+	assert.Len(t, links, 2)
+}
+
+func TestPartialMissing(t *testing.T) {
+	t.Parallel()
+
+	rows := []silo.DataRow{
+		{"ID1": 1, "ID4": "00001"},
+		{"ID2": "2", "ID3": 2.0},
+	}
+	input := silo.NewDataRowReaderInMemory(rows)
+
+	backend := silo.NewBackendInMemory()
+	driver := silo.NewDriver(backend, nil)
+
+	err := driver.Scan(input)
+	require.NoError(t, err)
+
+	nodes, err := driver.ReadAllNodes()
+	require.NoError(t, err)
+	assert.Len(t, nodes, 4)
+
+	links, err := driver.ReadAllLinks()
+	require.NoError(t, err)
+	assert.Len(t, links, 2)
 }

pkg/silo/graph.go

@@ -0,0 +1,60 @@
+// Copyright (C) 2024 CGI France
+//
+// This file is part of SILO.
+//
+// SILO is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// SILO is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with SILO.  If not, see <http://www.gnu.org/licenses/>.
+
+package silo
+
+import (
+	"encoding/json"
+	"fmt"
+	"strconv"
+	"strings"
+)
+
+func toStringRepresentationBuffered(value any, stringbuffer *strings.Builder) {
+	switch tvalue := value.(type) {
+	case string:
+		stringbuffer.WriteString("string(")
+		stringbuffer.WriteString(tvalue)
+		stringbuffer.WriteByte(')')
+	case bool:
+		stringbuffer.WriteString("bool(")
+		stringbuffer.WriteString(strconv.FormatBool(tvalue))
+		stringbuffer.WriteByte(')')
+	case float64:
+		stringbuffer.WriteString("number(")
+		stringbuffer.WriteString(strconv.FormatFloat(tvalue, 'g', -1, 64))
+		stringbuffer.WriteByte(')')
+	case int, int64, int32, int16, int8, uint, uint64, uint32, uint16, uint8:
+		stringbuffer.WriteString("number(")
+		stringbuffer.WriteString(fmt.Sprint(tvalue))
+		stringbuffer.WriteByte(')')
+	case json.Number:
+		stringbuffer.WriteString("number(")
+		stringbuffer.WriteString(string(tvalue))
+		stringbuffer.WriteByte(')')
+	case []any:
+		stringbuffer.WriteString("slice(")
+
+		for _, value := range tvalue {
+			toStringRepresentationBuffered(value, stringbuffer)
+		}
+
+		stringbuffer.WriteByte(')')
+	case nil:
+		stringbuffer.WriteString("nil(nil)")
+	}
+}

pkg/silo/model.go

@@ -17,6 +17,8 @@
 
 package silo
 
+import "strings"
+
 type DataRow map[string]any
 
 type DataNode struct {
@@ -28,3 +30,15 @@ type DataLink struct {
 	E1 DataNode
 	E2 DataNode
 }
+
+func (n DataNode) String() string {
+	result := &strings.Builder{}
+	result.Grow(512) //nolint:gomnd
+
+	result.WriteString(n.Key)
+	result.WriteRune('=')
+
+	toStringRepresentationBuffered(n.Data, result)
+
+	return result.String()
+}