PythonMutator: propagate source locations

bundle/config/experimental.go

@@ -45,6 +45,12 @@ type PyDABs struct {
 	// These packages are imported to discover resources, resource generators, and mutators.
 	// This list can include namespace packages, which causes the import of nested packages.
 	Import []string `json:"import,omitempty"`
+
+	// LoadLocations is a flag to enable loading Python source locations from the PyDABs.
+	//
+	// Locations are only supported since PyDABs 0.6.0, and because of that,
+	// this flag is disabled by default.
+	LoadLocations bool `json:"load_locations,omitempty"`
 }
 
 type Command string

bundle/config/mutator/python/python_locations.go

@@ -0,0 +1,163 @@
+package python
+
+import (
+	"encoding/json"
+	"fmt"
+	"io"
+	"path/filepath"
+
+	"github.com/databricks/cli/libs/dyn"
+)
+
+const generatedFileName = "__generated_by_pydabs__.yml"
+
+// pythonLocations is data structure for efficient location lookup for a given path
+type pythonLocations struct {
+	// descendants referenced by index, e.g. '.foo'
+	keys map[string]*pythonLocations
+
+	// descendants referenced by key, e.g. '[0]'
+	indexes map[int]*pythonLocations
+
+	// location for the current node if it exists
+	location dyn.Location
+
+	// if true, location is present
+	exists bool
+}
+
+type pythonLocationEntry struct {
+	Path   string `json:"path"`
+	File   string `json:"file"`
+	Line   int    `json:"line"`
+	Column int    `json:"column"`
+}
+
+// mergePythonLocations applies locations from Python mutator into given dyn.Value
+//
+// The primary use-case is to merge locations.json with output.json, so that any
+// validation errors will point to Python source code instead of generated YAML.
+func mergePythonLocations(value dyn.Value, locations *pythonLocations) (dyn.Value, error) {
+	return dyn.Walk(value, func(path dyn.Path, value dyn.Value) (dyn.Value, error) {
+		if newLocation, ok := findPythonLocation(locations, path); ok {
+			var newLocations []dyn.Location
+
+			// the first item in the list is the "last" location used for error reporting
+			newLocations = append(newLocations, newLocation)
+
+			for _, location := range value.Locations() {
+				if filepath.Base(location.File) == generatedFileName {
+					continue
+				}
+
+				// don't add duplicates if location already exists
+				if location == newLocation {
+					continue
+				}
+
+				newLocations = append(newLocations, location)
+			}
+
+			return value.WithLocations(newLocations), nil
+		} else {
+			return value, nil
+		}
+	})
+}
+
+// parsePythonLocations parses locations.json from the Python mutator.
+//
+// locations file is newline-separated JSON objects with pythonLocationEntry structure.
+func parsePythonLocations(input io.Reader) (*pythonLocations, error) {
+	decoder := json.NewDecoder(input)
+	locations := newPythonLocations()
+
+	for decoder.More() {
+		var entry pythonLocationEntry
+
+		err := decoder.Decode(&entry)
+		if err != nil {
+			return nil, fmt.Errorf("failed to parse python location: %s", err)
+		}
+
+		path, err := dyn.NewPathFromString(entry.Path)
+		if err != nil {
+			return nil, fmt.Errorf("failed to parse python location: %s", err)
+		}
+
+		location := dyn.Location{
+			File:   entry.File,
+			Line:   entry.Line,
+			Column: entry.Column,
+		}
+
+		putPythonLocation(locations, path, location)
+	}
+
+	return locations, nil
+}
+
+// putPythonLocation puts the location to the trie for the given path
+func putPythonLocation(trie *pythonLocations, path dyn.Path, location dyn.Location) {
+	var currentNode = trie
+
+	for _, component := range path {
+		if key := component.Key(); key != "" {
+			if _, ok := currentNode.keys[key]; !ok {
+				currentNode.keys[key] = newPythonLocations()
+			}
+
+			currentNode = currentNode.keys[key]
+		} else {
+			index := component.Index()
+			if _, ok := currentNode.indexes[index]; !ok {
+				currentNode.indexes[index] = newPythonLocations()
+			}
+
+			currentNode = currentNode.indexes[index]
+		}
+	}
+
+	currentNode.location = location
+	currentNode.exists = true
+}
+
+// newPythonLocations creates a new trie node
+func newPythonLocations() *pythonLocations {
+	return &pythonLocations{
+		keys:    make(map[string]*pythonLocations),
+		indexes: make(map[int]*pythonLocations),
+	}
+}
+
+// findPythonLocation finds the location or closest ancestor location in the trie for the given path
+// if no ancestor or exact location is found, false is returned.
+func findPythonLocation(locations *pythonLocations, path dyn.Path) (dyn.Location, bool) {
+	var currentNode = locations
+	var lastLocation = locations.location
+	var exists = locations.exists
+
+	for _, component := range path {
+		if key := component.Key(); key != "" {
+			if _, ok := currentNode.keys[key]; !ok {
+				break
+			}
+
+			currentNode = currentNode.keys[key]
+		} else {
+			index := component.Index()
+			if _, ok := currentNode.indexes[index]; !ok {
+				break
+			}
+
+			currentNode = currentNode.indexes[index]
+		}
+
+		if currentNode.exists {
+			lastLocation = currentNode.location
+			exists = true
+		}
+	}
+
+	return lastLocation, exists
+}

bundle/config/mutator/python/python_locations_test.go

@@ -0,0 +1,127 @@
+package python
+
+import (
+	"bytes"
+	"testing"
+
+	"github.com/databricks/cli/libs/dyn"
+	assert "github.com/databricks/cli/libs/dyn/dynassert"
+)
+
+func TestMergeLocations(t *testing.T) {
+	pythonLocation := dyn.Location{File: "foo.py", Line: 1, Column: 1}
+	generatedLocation := dyn.Location{File: generatedFileName, Line: 1, Column: 1}
+	yamlLocation := dyn.Location{File: "foo.yml", Line: 1, Column: 1}
+
+	locations := newPythonLocations()
+	putPythonLocation(locations, dyn.MustPathFromString("foo"), pythonLocation)
+
+	input := dyn.NewValue(
+		map[string]dyn.Value{
+			"foo": dyn.NewValue(
+				map[string]dyn.Value{
+					"bar": dyn.NewValue("baz", []dyn.Location{yamlLocation, pythonLocation}),
+					"baz": dyn.NewValue("baz", []dyn.Location{yamlLocation}),
+					"qux": dyn.NewValue("baz", []dyn.Location{generatedLocation, yamlLocation}),
+				},
+				[]dyn.Location{},
+			),
+			"bar": dyn.NewValue("baz", []dyn.Location{generatedLocation}),
+		},
+		[]dyn.Location{yamlLocation},
+	)
+
+	expected := dyn.NewValue(
+		map[string]dyn.Value{
+			"foo": dyn.NewValue(
+				map[string]dyn.Value{
+					// pythonLocation was present before, we don't duplicate it, only move it to the beginning
+					"bar": dyn.NewValue("baz", []dyn.Location{pythonLocation, yamlLocation}),
+					// pythonLocation is appended to the beginning of the list if absent
+					"baz": dyn.NewValue("baz", []dyn.Location{pythonLocation, yamlLocation}),
+					// generatedLocation is replaced by pythonLocation
+					"qux": dyn.NewValue("baz", []dyn.Location{pythonLocation, yamlLocation}),
+				},
+				[]dyn.Location{pythonLocation},
+			),
+			// if location is unknown, we keep it as-is
+			"bar": dyn.NewValue("baz", []dyn.Location{generatedLocation}),
+		},
+		[]dyn.Location{yamlLocation},
+	)
+
+	actual, err := mergePythonLocations(input, locations)
+
+	assert.NoError(t, err)
+	assert.Equal(t, expected, actual)
+}
+
+func TestFindLocation(t *testing.T) {
+	location0 := dyn.Location{File: "foo.py", Line: 1, Column: 1}
+	location1 := dyn.Location{File: "foo.py", Line: 2, Column: 1}
+
+	locations := newPythonLocations()
+	putPythonLocation(locations, dyn.MustPathFromString("foo"), location0)
+	putPythonLocation(locations, dyn.MustPathFromString("foo.bar"), location1)
+
+	actual, exists := findPythonLocation(locations, dyn.MustPathFromString("foo.bar"))
+
+	assert.True(t, exists)
+	assert.Equal(t, location1, actual)
+}
+
+func TestFindLocation_indexPathComponent(t *testing.T) {
+	location0 := dyn.Location{File: "foo.py", Line: 1, Column: 1}
+	location1 := dyn.Location{File: "foo.py", Line: 2, Column: 1}
+	location2 := dyn.Location{File: "foo.py", Line: 3, Column: 1}
+
+	locations := newPythonLocations()
+	putPythonLocation(locations, dyn.MustPathFromString("foo"), location0)
+	putPythonLocation(locations, dyn.MustPathFromString("foo.bar"), location1)
+	putPythonLocation(locations, dyn.MustPathFromString("foo.bar[0]"), location2)
+
+	actual, exists := findPythonLocation(locations, dyn.MustPathFromString("foo.bar[0]"))
+
+	assert.True(t, exists)
+	assert.Equal(t, location2, actual)
+}
+
+func TestFindLocation_closestAncestorLocation(t *testing.T) {
+	location0 := dyn.Location{File: "foo.py", Line: 1, Column: 1}
+	location1 := dyn.Location{File: "foo.py", Line: 2, Column: 1}
+
+	locations := newPythonLocations()
+	putPythonLocation(locations, dyn.MustPathFromString("foo"), location0)
+	putPythonLocation(locations, dyn.MustPathFromString("foo.bar"), location1)
+
+	actual, exists := findPythonLocation(locations, dyn.MustPathFromString("foo.bar.baz"))
+
+	assert.True(t, exists)
+	assert.Equal(t, location1, actual)
+}
+
+func TestFindLocation_unknownLocation(t *testing.T) {
+	location0 := dyn.Location{File: "foo.py", Line: 1, Column: 1}
+	location1 := dyn.Location{File: "foo.py", Line: 2, Column: 1}
+
+	locations := newPythonLocations()
+	putPythonLocation(locations, dyn.MustPathFromString("foo"), location0)
+	putPythonLocation(locations, dyn.MustPathFromString("foo.bar"), location1)
+
+	_, exists := findPythonLocation(locations, dyn.MustPathFromString("bar"))
+
+	assert.False(t, exists)
+}
+
+func TestParsePythonLocations(t *testing.T) {
+	expected := dyn.Location{File: "foo.py", Line: 1, Column: 2}
+
+	input := `{"path": "foo", "file": "foo.py", "line": 1, "column": 2}`
+	reader := bytes.NewReader([]byte(input))
+	locations, err := parsePythonLocations(reader)
+
+	assert.NoError(t, err)
+
+	assert.True(t, locations.keys["foo"].exists)
+	assert.Equal(t, expected, locations.keys["foo"].location)
+}