mirror of https://github.com/databricks/cli.git
Compare commits
12 Commits
3d28be5298
...
3ae9ce952b
Author | SHA1 | Date |
---|---|---|
Gleb Kanterov | 3ae9ce952b | |
shreyas-goenka | 984c38e03e | |
Pieter Noordhuis | ade95d9649 | |
Andrew Nester | 592e1111b7 | |
Andrew Nester | fab3e8f168 | |
Ilya Kuznetsov | 756e55fabc | |
Pieter Noordhuis | 886e14910c | |
Gleb Kanterov | 96a6cef0d6 | |
Gleb Kanterov | bfb13afa8e | |
Gleb Kanterov | 43ce278299 | |
Gleb Kanterov | df61375995 | |
Gleb Kanterov | 3438455459 |
23
CHANGELOG.md
23
CHANGELOG.md
|
@ -1,5 +1,28 @@
|
||||||
# Version changelog
|
# Version changelog
|
||||||
|
|
||||||
|
## [Release] Release v0.235.0
|
||||||
|
|
||||||
|
**Note:** the `bundle generate` command now uses the `.<resource-type>.yml`
|
||||||
|
sub-extension for the configuration files it writes. Existing configuration
|
||||||
|
files that do not use this sub-extension are renamed to include it.
|
||||||
|
|
||||||
|
Bundles:
|
||||||
|
* Make `TableName` field part of quality monitor schema ([#1903](https://github.com/databricks/cli/pull/1903)).
|
||||||
|
* Do not prepend paths starting with ~ or variable reference ([#1905](https://github.com/databricks/cli/pull/1905)).
|
||||||
|
* Fix workspace extensions filer accidentally reading notebooks ([#1891](https://github.com/databricks/cli/pull/1891)).
|
||||||
|
* Fix template initialization when running on Databricks ([#1912](https://github.com/databricks/cli/pull/1912)).
|
||||||
|
* Source-linked deployments for bundles in the workspace ([#1884](https://github.com/databricks/cli/pull/1884)).
|
||||||
|
* Added integration test to deploy bundle to /Shared root path ([#1914](https://github.com/databricks/cli/pull/1914)).
|
||||||
|
* Update filenames used by bundle generate to use `.<resource-type>.yml` ([#1901](https://github.com/databricks/cli/pull/1901)).
|
||||||
|
|
||||||
|
Internal:
|
||||||
|
* Extract functionality to detect if the CLI is running on DBR ([#1889](https://github.com/databricks/cli/pull/1889)).
|
||||||
|
* Consolidate test helpers for `io/fs` ([#1906](https://github.com/databricks/cli/pull/1906)).
|
||||||
|
* Use `fs.FS` interface to read template ([#1910](https://github.com/databricks/cli/pull/1910)).
|
||||||
|
* Use `filer.Filer` to write template instantiation ([#1911](https://github.com/databricks/cli/pull/1911)).
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
## [Release] Release v0.234.0
|
## [Release] Release v0.234.0
|
||||||
|
|
||||||
Bundles:
|
Bundles:
|
||||||
|
|
|
@ -45,6 +45,12 @@ type PyDABs struct {
|
||||||
// These packages are imported to discover resources, resource generators, and mutators.
|
// These packages are imported to discover resources, resource generators, and mutators.
|
||||||
// This list can include namespace packages, which causes the import of nested packages.
|
// This list can include namespace packages, which causes the import of nested packages.
|
||||||
Import []string `json:"import,omitempty"`
|
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
|
type Command string
|
||||||
|
|
|
@ -9,6 +9,7 @@ import (
|
||||||
|
|
||||||
"github.com/databricks/cli/bundle"
|
"github.com/databricks/cli/bundle"
|
||||||
"github.com/databricks/cli/bundle/config"
|
"github.com/databricks/cli/bundle/config"
|
||||||
|
"github.com/databricks/cli/libs/dbr"
|
||||||
"github.com/databricks/cli/libs/diag"
|
"github.com/databricks/cli/libs/diag"
|
||||||
"github.com/databricks/cli/libs/dyn"
|
"github.com/databricks/cli/libs/dyn"
|
||||||
"github.com/databricks/cli/libs/textutil"
|
"github.com/databricks/cli/libs/textutil"
|
||||||
|
@ -221,6 +222,15 @@ func (m *applyPresets) Apply(ctx context.Context, b *bundle.Bundle) diag.Diagnos
|
||||||
dashboard.DisplayName = prefix + dashboard.DisplayName
|
dashboard.DisplayName = prefix + dashboard.DisplayName
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if config.IsExplicitlyEnabled((b.Config.Presets.SourceLinkedDeployment)) {
|
||||||
|
isDatabricksWorkspace := dbr.RunsOnRuntime(ctx) && strings.HasPrefix(b.SyncRootPath, "/Workspace/")
|
||||||
|
if !isDatabricksWorkspace {
|
||||||
|
disabled := false
|
||||||
|
b.Config.Presets.SourceLinkedDeployment = &disabled
|
||||||
|
diags = diags.Extend(diag.Warningf("source-linked deployment is available only in the Databricks Workspace"))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
return diags
|
return diags
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -2,12 +2,14 @@ package mutator_test
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
|
"runtime"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
"github.com/databricks/cli/bundle"
|
"github.com/databricks/cli/bundle"
|
||||||
"github.com/databricks/cli/bundle/config"
|
"github.com/databricks/cli/bundle/config"
|
||||||
"github.com/databricks/cli/bundle/config/mutator"
|
"github.com/databricks/cli/bundle/config/mutator"
|
||||||
"github.com/databricks/cli/bundle/config/resources"
|
"github.com/databricks/cli/bundle/config/resources"
|
||||||
|
"github.com/databricks/cli/libs/dbr"
|
||||||
"github.com/databricks/databricks-sdk-go/service/catalog"
|
"github.com/databricks/databricks-sdk-go/service/catalog"
|
||||||
"github.com/databricks/databricks-sdk-go/service/jobs"
|
"github.com/databricks/databricks-sdk-go/service/jobs"
|
||||||
"github.com/stretchr/testify/require"
|
"github.com/stretchr/testify/require"
|
||||||
|
@ -364,3 +366,86 @@ func TestApplyPresetsResourceNotDefined(t *testing.T) {
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestApplyPresetsSourceLinkedDeployment(t *testing.T) {
|
||||||
|
if runtime.GOOS == "windows" {
|
||||||
|
t.Skip("this test is not applicable on Windows because source-linked mode works only in the Databricks Workspace")
|
||||||
|
}
|
||||||
|
|
||||||
|
testContext := context.Background()
|
||||||
|
enabled := true
|
||||||
|
disabled := false
|
||||||
|
workspacePath := "/Workspace/user.name@company.com"
|
||||||
|
|
||||||
|
tests := []struct {
|
||||||
|
bundlePath string
|
||||||
|
ctx context.Context
|
||||||
|
name string
|
||||||
|
initialValue *bool
|
||||||
|
expectedValue *bool
|
||||||
|
expectedWarning string
|
||||||
|
}{
|
||||||
|
{
|
||||||
|
name: "preset enabled, bundle in Workspace, databricks runtime",
|
||||||
|
bundlePath: workspacePath,
|
||||||
|
ctx: dbr.MockRuntime(testContext, true),
|
||||||
|
initialValue: &enabled,
|
||||||
|
expectedValue: &enabled,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "preset enabled, bundle not in Workspace, databricks runtime",
|
||||||
|
bundlePath: "/Users/user.name@company.com",
|
||||||
|
ctx: dbr.MockRuntime(testContext, true),
|
||||||
|
initialValue: &enabled,
|
||||||
|
expectedValue: &disabled,
|
||||||
|
expectedWarning: "source-linked deployment is available only in the Databricks Workspace",
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "preset enabled, bundle in Workspace, not databricks runtime",
|
||||||
|
bundlePath: workspacePath,
|
||||||
|
ctx: dbr.MockRuntime(testContext, false),
|
||||||
|
initialValue: &enabled,
|
||||||
|
expectedValue: &disabled,
|
||||||
|
expectedWarning: "source-linked deployment is available only in the Databricks Workspace",
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "preset disabled, bundle in Workspace, databricks runtime",
|
||||||
|
bundlePath: workspacePath,
|
||||||
|
ctx: dbr.MockRuntime(testContext, true),
|
||||||
|
initialValue: &disabled,
|
||||||
|
expectedValue: &disabled,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
name: "preset nil, bundle in Workspace, databricks runtime",
|
||||||
|
bundlePath: workspacePath,
|
||||||
|
ctx: dbr.MockRuntime(testContext, true),
|
||||||
|
initialValue: nil,
|
||||||
|
expectedValue: nil,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
for _, tt := range tests {
|
||||||
|
t.Run(tt.name, func(t *testing.T) {
|
||||||
|
b := &bundle.Bundle{
|
||||||
|
SyncRootPath: tt.bundlePath,
|
||||||
|
Config: config.Root{
|
||||||
|
Presets: config.Presets{
|
||||||
|
SourceLinkedDeployment: tt.initialValue,
|
||||||
|
},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
diags := bundle.Apply(tt.ctx, b, mutator.ApplyPresets())
|
||||||
|
if diags.HasError() {
|
||||||
|
t.Fatalf("unexpected error: %v", diags)
|
||||||
|
}
|
||||||
|
|
||||||
|
if tt.expectedWarning != "" {
|
||||||
|
require.Equal(t, tt.expectedWarning, diags[0].Summary)
|
||||||
|
}
|
||||||
|
|
||||||
|
require.Equal(t, tt.expectedValue, b.Config.Presets.SourceLinkedDeployment)
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
||||||
|
|
|
@ -6,6 +6,7 @@ import (
|
||||||
|
|
||||||
"github.com/databricks/cli/bundle"
|
"github.com/databricks/cli/bundle"
|
||||||
"github.com/databricks/cli/bundle/config"
|
"github.com/databricks/cli/bundle/config"
|
||||||
|
"github.com/databricks/cli/libs/dbr"
|
||||||
"github.com/databricks/cli/libs/diag"
|
"github.com/databricks/cli/libs/diag"
|
||||||
"github.com/databricks/cli/libs/dyn"
|
"github.com/databricks/cli/libs/dyn"
|
||||||
"github.com/databricks/cli/libs/iamutil"
|
"github.com/databricks/cli/libs/iamutil"
|
||||||
|
@ -57,6 +58,14 @@ func transformDevelopmentMode(ctx context.Context, b *bundle.Bundle) {
|
||||||
t.TriggerPauseStatus = config.Paused
|
t.TriggerPauseStatus = config.Paused
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if !config.IsExplicitlyDisabled(t.SourceLinkedDeployment) {
|
||||||
|
isInWorkspace := strings.HasPrefix(b.SyncRootPath, "/Workspace/")
|
||||||
|
if isInWorkspace && dbr.RunsOnRuntime(ctx) {
|
||||||
|
enabled := true
|
||||||
|
t.SourceLinkedDeployment = &enabled
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
if !config.IsExplicitlyDisabled(t.PipelinesDevelopment) {
|
if !config.IsExplicitlyDisabled(t.PipelinesDevelopment) {
|
||||||
enabled := true
|
enabled := true
|
||||||
t.PipelinesDevelopment = &enabled
|
t.PipelinesDevelopment = &enabled
|
||||||
|
|
|
@ -3,14 +3,17 @@ package mutator
|
||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
"reflect"
|
"reflect"
|
||||||
|
"runtime"
|
||||||
"strings"
|
"strings"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
"github.com/databricks/cli/bundle"
|
"github.com/databricks/cli/bundle"
|
||||||
"github.com/databricks/cli/bundle/config"
|
"github.com/databricks/cli/bundle/config"
|
||||||
"github.com/databricks/cli/bundle/config/resources"
|
"github.com/databricks/cli/bundle/config/resources"
|
||||||
|
"github.com/databricks/cli/libs/dbr"
|
||||||
"github.com/databricks/cli/libs/diag"
|
"github.com/databricks/cli/libs/diag"
|
||||||
"github.com/databricks/cli/libs/tags"
|
"github.com/databricks/cli/libs/tags"
|
||||||
|
"github.com/databricks/cli/libs/vfs"
|
||||||
sdkconfig "github.com/databricks/databricks-sdk-go/config"
|
sdkconfig "github.com/databricks/databricks-sdk-go/config"
|
||||||
"github.com/databricks/databricks-sdk-go/service/catalog"
|
"github.com/databricks/databricks-sdk-go/service/catalog"
|
||||||
"github.com/databricks/databricks-sdk-go/service/compute"
|
"github.com/databricks/databricks-sdk-go/service/compute"
|
||||||
|
@ -140,6 +143,7 @@ func mockBundle(mode config.Mode) *bundle.Bundle {
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
},
|
},
|
||||||
|
SyncRoot: vfs.MustNew("/Users/lennart.kats@databricks.com"),
|
||||||
// Use AWS implementation for testing.
|
// Use AWS implementation for testing.
|
||||||
Tagging: tags.ForCloud(&sdkconfig.Config{
|
Tagging: tags.ForCloud(&sdkconfig.Config{
|
||||||
Host: "https://company.cloud.databricks.com",
|
Host: "https://company.cloud.databricks.com",
|
||||||
|
@ -522,3 +526,32 @@ func TestPipelinesDevelopmentDisabled(t *testing.T) {
|
||||||
|
|
||||||
assert.False(t, b.Config.Resources.Pipelines["pipeline1"].PipelineSpec.Development)
|
assert.False(t, b.Config.Resources.Pipelines["pipeline1"].PipelineSpec.Development)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestSourceLinkedDeploymentEnabled(t *testing.T) {
|
||||||
|
b, diags := processSourceLinkedBundle(t, true)
|
||||||
|
require.NoError(t, diags.Error())
|
||||||
|
assert.True(t, *b.Config.Presets.SourceLinkedDeployment)
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestSourceLinkedDeploymentDisabled(t *testing.T) {
|
||||||
|
b, diags := processSourceLinkedBundle(t, false)
|
||||||
|
require.NoError(t, diags.Error())
|
||||||
|
assert.False(t, *b.Config.Presets.SourceLinkedDeployment)
|
||||||
|
}
|
||||||
|
|
||||||
|
func processSourceLinkedBundle(t *testing.T, presetEnabled bool) (*bundle.Bundle, diag.Diagnostics) {
|
||||||
|
if runtime.GOOS == "windows" {
|
||||||
|
t.Skip("this test is not applicable on Windows because source-linked mode works only in the Databricks Workspace")
|
||||||
|
}
|
||||||
|
|
||||||
|
b := mockBundle(config.Development)
|
||||||
|
|
||||||
|
workspacePath := "/Workspace/lennart@company.com/"
|
||||||
|
b.SyncRootPath = workspacePath
|
||||||
|
b.Config.Presets.SourceLinkedDeployment = &presetEnabled
|
||||||
|
|
||||||
|
ctx := dbr.MockRuntime(context.Background(), true)
|
||||||
|
m := bundle.Seq(ProcessTargetMode(), ApplyPresets())
|
||||||
|
diags := bundle.Apply(ctx, b, m)
|
||||||
|
return b, diags
|
||||||
|
}
|
||||||
|
|
|
@ -9,6 +9,7 @@ import (
|
||||||
"github.com/databricks/cli/libs/dyn"
|
"github.com/databricks/cli/libs/dyn"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
// pythonDiagnostic is a single entry in diagnostics.json
|
||||||
type pythonDiagnostic struct {
|
type pythonDiagnostic struct {
|
||||||
Severity pythonSeverity `json:"severity"`
|
Severity pythonSeverity `json:"severity"`
|
||||||
Summary string `json:"summary"`
|
Summary string `json:"summary"`
|
||||||
|
|
|
@ -0,0 +1,181 @@
|
||||||
|
package python
|
||||||
|
|
||||||
|
import (
|
||||||
|
"encoding/json"
|
||||||
|
"fmt"
|
||||||
|
"io"
|
||||||
|
"path/filepath"
|
||||||
|
|
||||||
|
"github.com/databricks/cli/libs/dyn"
|
||||||
|
)
|
||||||
|
|
||||||
|
// generatedFileName is used as the virtual file name for YAML generated by PyDABs.
|
||||||
|
//
|
||||||
|
// mergePythonLocations replaces dyn.Location with generatedFileName with locations loaded
|
||||||
|
// from locations.json
|
||||||
|
const generatedFileName = "__generated_by_pydabs__.yml"
|
||||||
|
|
||||||
|
// pythonLocations is data structure for efficient location lookup for a given path
|
||||||
|
//
|
||||||
|
// Locations form a tree, and we assign locations of the closest ancestor to each dyn.Value based on its path.
|
||||||
|
// We implement it as a trie (prefix tree) where keys are components of the path. With that, lookups are O(n)
|
||||||
|
// where n is the number of components in the path.
|
||||||
|
//
|
||||||
|
// For example, with locations.json:
|
||||||
|
//
|
||||||
|
// {"path": "resources.jobs.job_0", "file": "src/examples/job_0.py", "line": 3, "column": 5}
|
||||||
|
// {"path": "resources.jobs.job_0.tasks[0].task_key", "file": "src/examples/job_0.py", "line": 10, "column": 5}
|
||||||
|
// {"path": "resources.jobs.job_1", "file": "src/examples/job_1.py", "line": 5, "column": 7}
|
||||||
|
//
|
||||||
|
// - resources.jobs.job_0.tasks[0].task_key is located at job_0.py:10:5
|
||||||
|
//
|
||||||
|
// - resources.jobs.job_0.tasks[0].email_notifications is located at job_0.py:3:5,
|
||||||
|
// because we use the location of the job as the most precise approximation.
|
||||||
|
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
|
||||||
|
}
|
||||||
|
|
||||||
|
// pythonLocationEntry is a single entry in locations.json
|
||||||
|
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) {
|
||||||
|
newLocation, ok := findPythonLocation(locations, path)
|
||||||
|
if !ok {
|
||||||
|
return value, nil
|
||||||
|
}
|
||||||
|
|
||||||
|
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() {
|
||||||
|
// When loaded, dyn.Value created by PyDABs use the virtual file path as their location,
|
||||||
|
// we replace it with newLocation.
|
||||||
|
if filepath.Base(location.File) == generatedFileName {
|
||||||
|
continue
|
||||||
|
}
|
||||||
|
|
||||||
|
newLocations = append(newLocations, location)
|
||||||
|
}
|
||||||
|
|
||||||
|
return value.WithLocations(newLocations), 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
|
||||||
|
}
|
|
@ -0,0 +1,124 @@
|
||||||
|
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{
|
||||||
|
"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 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)
|
||||||
|
}
|
|
@ -7,9 +7,12 @@ import (
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"io"
|
"io"
|
||||||
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
|
||||||
|
"github.com/databricks/cli/bundle/config/mutator/paths"
|
||||||
|
|
||||||
"github.com/databricks/databricks-sdk-go/logger"
|
"github.com/databricks/databricks-sdk-go/logger"
|
||||||
"github.com/fatih/color"
|
"github.com/fatih/color"
|
||||||
|
|
||||||
|
@ -108,7 +111,12 @@ func (m *pythonMutator) Apply(ctx context.Context, b *bundle.Bundle) diag.Diagno
|
||||||
return dyn.InvalidValue, fmt.Errorf("failed to create cache dir: %w", err)
|
return dyn.InvalidValue, fmt.Errorf("failed to create cache dir: %w", err)
|
||||||
}
|
}
|
||||||
|
|
||||||
rightRoot, diags := m.runPythonMutator(ctx, cacheDir, b.BundleRootPath, pythonPath, leftRoot)
|
rightRoot, diags := m.runPythonMutator(ctx, leftRoot, runPythonMutatorOpts{
|
||||||
|
cacheDir: cacheDir,
|
||||||
|
bundleRootPath: b.BundleRootPath,
|
||||||
|
pythonPath: pythonPath,
|
||||||
|
loadLocations: experimental.PyDABs.LoadLocations,
|
||||||
|
})
|
||||||
mutateDiags = diags
|
mutateDiags = diags
|
||||||
if diags.HasError() {
|
if diags.HasError() {
|
||||||
return dyn.InvalidValue, mutateDiagsHasError
|
return dyn.InvalidValue, mutateDiagsHasError
|
||||||
|
@ -152,13 +160,21 @@ func createCacheDir(ctx context.Context) (string, error) {
|
||||||
return os.MkdirTemp("", "-pydabs")
|
return os.MkdirTemp("", "-pydabs")
|
||||||
}
|
}
|
||||||
|
|
||||||
func (m *pythonMutator) runPythonMutator(ctx context.Context, cacheDir string, rootPath string, pythonPath string, root dyn.Value) (dyn.Value, diag.Diagnostics) {
|
type runPythonMutatorOpts struct {
|
||||||
inputPath := filepath.Join(cacheDir, "input.json")
|
cacheDir string
|
||||||
outputPath := filepath.Join(cacheDir, "output.json")
|
bundleRootPath string
|
||||||
diagnosticsPath := filepath.Join(cacheDir, "diagnostics.json")
|
pythonPath string
|
||||||
|
loadLocations bool
|
||||||
|
}
|
||||||
|
|
||||||
|
func (m *pythonMutator) runPythonMutator(ctx context.Context, root dyn.Value, opts runPythonMutatorOpts) (dyn.Value, diag.Diagnostics) {
|
||||||
|
inputPath := filepath.Join(opts.cacheDir, "input.json")
|
||||||
|
outputPath := filepath.Join(opts.cacheDir, "output.json")
|
||||||
|
diagnosticsPath := filepath.Join(opts.cacheDir, "diagnostics.json")
|
||||||
|
locationsPath := filepath.Join(opts.cacheDir, "locations.json")
|
||||||
|
|
||||||
args := []string{
|
args := []string{
|
||||||
pythonPath,
|
opts.pythonPath,
|
||||||
"-m",
|
"-m",
|
||||||
"databricks.bundles.build",
|
"databricks.bundles.build",
|
||||||
"--phase",
|
"--phase",
|
||||||
|
@ -171,6 +187,10 @@ func (m *pythonMutator) runPythonMutator(ctx context.Context, cacheDir string, r
|
||||||
diagnosticsPath,
|
diagnosticsPath,
|
||||||
}
|
}
|
||||||
|
|
||||||
|
if opts.loadLocations {
|
||||||
|
args = append(args, "--locations", locationsPath)
|
||||||
|
}
|
||||||
|
|
||||||
if err := writeInputFile(inputPath, root); err != nil {
|
if err := writeInputFile(inputPath, root); err != nil {
|
||||||
return dyn.InvalidValue, diag.Errorf("failed to write input file: %s", err)
|
return dyn.InvalidValue, diag.Errorf("failed to write input file: %s", err)
|
||||||
}
|
}
|
||||||
|
@ -185,7 +205,7 @@ func (m *pythonMutator) runPythonMutator(ctx context.Context, cacheDir string, r
|
||||||
_, processErr := process.Background(
|
_, processErr := process.Background(
|
||||||
ctx,
|
ctx,
|
||||||
args,
|
args,
|
||||||
process.WithDir(rootPath),
|
process.WithDir(opts.bundleRootPath),
|
||||||
process.WithStderrWriter(stderrWriter),
|
process.WithStderrWriter(stderrWriter),
|
||||||
process.WithStdoutWriter(stdoutWriter),
|
process.WithStdoutWriter(stdoutWriter),
|
||||||
)
|
)
|
||||||
|
@ -221,7 +241,12 @@ func (m *pythonMutator) runPythonMutator(ctx context.Context, cacheDir string, r
|
||||||
return dyn.InvalidValue, diag.Errorf("failed to load diagnostics: %s", pythonDiagnosticsErr)
|
return dyn.InvalidValue, diag.Errorf("failed to load diagnostics: %s", pythonDiagnosticsErr)
|
||||||
}
|
}
|
||||||
|
|
||||||
output, outputDiags := loadOutputFile(rootPath, outputPath)
|
locations, err := loadLocationsFile(locationsPath)
|
||||||
|
if err != nil {
|
||||||
|
return dyn.InvalidValue, diag.Errorf("failed to load locations: %s", err)
|
||||||
|
}
|
||||||
|
|
||||||
|
output, outputDiags := loadOutputFile(opts.bundleRootPath, outputPath, locations)
|
||||||
pythonDiagnostics = pythonDiagnostics.Extend(outputDiags)
|
pythonDiagnostics = pythonDiagnostics.Extend(outputDiags)
|
||||||
|
|
||||||
// we pass through pythonDiagnostic because it contains warnings
|
// we pass through pythonDiagnostic because it contains warnings
|
||||||
|
@ -266,7 +291,21 @@ func writeInputFile(inputPath string, input dyn.Value) error {
|
||||||
return os.WriteFile(inputPath, rootConfigJson, 0600)
|
return os.WriteFile(inputPath, rootConfigJson, 0600)
|
||||||
}
|
}
|
||||||
|
|
||||||
func loadOutputFile(rootPath string, outputPath string) (dyn.Value, diag.Diagnostics) {
|
// loadLocationsFile loads locations.json containing source locations for generated YAML.
|
||||||
|
func loadLocationsFile(locationsPath string) (*pythonLocations, error) {
|
||||||
|
locationsFile, err := os.Open(locationsPath)
|
||||||
|
if errors.Is(err, fs.ErrNotExist) {
|
||||||
|
return newPythonLocations(), nil
|
||||||
|
} else if err != nil {
|
||||||
|
return nil, fmt.Errorf("failed to open locations file: %w", err)
|
||||||
|
}
|
||||||
|
|
||||||
|
defer locationsFile.Close()
|
||||||
|
|
||||||
|
return parsePythonLocations(locationsFile)
|
||||||
|
}
|
||||||
|
|
||||||
|
func loadOutputFile(rootPath string, outputPath string, locations *pythonLocations) (dyn.Value, diag.Diagnostics) {
|
||||||
outputFile, err := os.Open(outputPath)
|
outputFile, err := os.Open(outputPath)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to open output file: %w", err))
|
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to open output file: %w", err))
|
||||||
|
@ -277,12 +316,12 @@ func loadOutputFile(rootPath string, outputPath string) (dyn.Value, diag.Diagnos
|
||||||
// we need absolute path because later parts of pipeline assume all paths are absolute
|
// we need absolute path because later parts of pipeline assume all paths are absolute
|
||||||
// and this file will be used as location to resolve relative paths.
|
// and this file will be used as location to resolve relative paths.
|
||||||
//
|
//
|
||||||
// virtualPath has to stay in rootPath, because locations outside root path are not allowed:
|
// virtualPath has to stay in bundleRootPath, because locations outside root path are not allowed:
|
||||||
//
|
//
|
||||||
// Error: path /var/folders/.../pydabs/dist/*.whl is not contained in bundle root path
|
// Error: path /var/folders/.../pydabs/dist/*.whl is not contained in bundle root path
|
||||||
//
|
//
|
||||||
// for that, we pass virtualPath instead of outputPath as file location
|
// for that, we pass virtualPath instead of outputPath as file location
|
||||||
virtualPath, err := filepath.Abs(filepath.Join(rootPath, "__generated_by_pydabs__.yml"))
|
virtualPath, err := filepath.Abs(filepath.Join(rootPath, generatedFileName))
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to get absolute path: %w", err))
|
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to get absolute path: %w", err))
|
||||||
}
|
}
|
||||||
|
@ -292,7 +331,25 @@ func loadOutputFile(rootPath string, outputPath string) (dyn.Value, diag.Diagnos
|
||||||
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to parse output file: %w", err))
|
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to parse output file: %w", err))
|
||||||
}
|
}
|
||||||
|
|
||||||
return strictNormalize(config.Root{}, generated)
|
// paths are resolved relative to locations of their values, if we change location
|
||||||
|
// we have to update each path, until we simplify that, we don't update locations
|
||||||
|
// for such values, so we don't change how paths are resolved
|
||||||
|
_, err = paths.VisitJobPaths(generated, func(p dyn.Path, kind paths.PathKind, v dyn.Value) (dyn.Value, error) {
|
||||||
|
putPythonLocation(locations, p, v.Location())
|
||||||
|
return v, nil
|
||||||
|
})
|
||||||
|
if err != nil {
|
||||||
|
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to update locations: %w", err))
|
||||||
|
}
|
||||||
|
|
||||||
|
// generated has dyn.Location as if it comes from generated YAML file
|
||||||
|
// earlier we loaded locations.json with source locations in Python code
|
||||||
|
generatedWithLocations, err := mergePythonLocations(generated, locations)
|
||||||
|
if err != nil {
|
||||||
|
return dyn.InvalidValue, diag.FromErr(fmt.Errorf("failed to update locations: %w", err))
|
||||||
|
}
|
||||||
|
|
||||||
|
return strictNormalize(config.Root{}, generatedWithLocations)
|
||||||
}
|
}
|
||||||
|
|
||||||
func strictNormalize(dst any, generated dyn.Value) (dyn.Value, diag.Diagnostics) {
|
func strictNormalize(dst any, generated dyn.Value) (dyn.Value, diag.Diagnostics) {
|
||||||
|
|
|
@ -6,7 +6,6 @@ import (
|
||||||
"os"
|
"os"
|
||||||
"os/exec"
|
"os/exec"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"reflect"
|
|
||||||
"runtime"
|
"runtime"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
|
@ -47,6 +46,7 @@ func TestPythonMutator_load(t *testing.T) {
|
||||||
pydabs:
|
pydabs:
|
||||||
enabled: true
|
enabled: true
|
||||||
venv_path: .venv
|
venv_path: .venv
|
||||||
|
load_locations: true
|
||||||
resources:
|
resources:
|
||||||
jobs:
|
jobs:
|
||||||
job0:
|
job0:
|
||||||
|
@ -65,7 +65,8 @@ func TestPythonMutator_load(t *testing.T) {
|
||||||
"experimental": {
|
"experimental": {
|
||||||
"pydabs": {
|
"pydabs": {
|
||||||
"enabled": true,
|
"enabled": true,
|
||||||
"venv_path": ".venv"
|
"venv_path": ".venv",
|
||||||
|
"load_locations": true
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"resources": {
|
"resources": {
|
||||||
|
@ -80,6 +81,8 @@ func TestPythonMutator_load(t *testing.T) {
|
||||||
}
|
}
|
||||||
}`,
|
}`,
|
||||||
`{"severity": "warning", "summary": "job doesn't have any tasks", "location": {"file": "src/examples/file.py", "line": 10, "column": 5}}`,
|
`{"severity": "warning", "summary": "job doesn't have any tasks", "location": {"file": "src/examples/file.py", "line": 10, "column": 5}}`,
|
||||||
|
`{"path": "resources.jobs.job0", "file": "src/examples/job0.py", "line": 3, "column": 5}
|
||||||
|
{"path": "resources.jobs.job1", "file": "src/examples/job1.py", "line": 5, "column": 7}`,
|
||||||
)
|
)
|
||||||
|
|
||||||
mutator := PythonMutator(PythonMutatorPhaseLoad)
|
mutator := PythonMutator(PythonMutatorPhaseLoad)
|
||||||
|
@ -97,6 +100,25 @@ func TestPythonMutator_load(t *testing.T) {
|
||||||
assert.Equal(t, "job_1", job1.Name)
|
assert.Equal(t, "job_1", job1.Name)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// output of locations.json should be applied to underlying dyn.Value
|
||||||
|
err := b.Config.Mutate(func(v dyn.Value) (dyn.Value, error) {
|
||||||
|
name1, err := dyn.GetByPath(v, dyn.MustPathFromString("resources.jobs.job1.name"))
|
||||||
|
if err != nil {
|
||||||
|
return dyn.InvalidValue, err
|
||||||
|
}
|
||||||
|
|
||||||
|
assert.Equal(t, []dyn.Location{
|
||||||
|
{
|
||||||
|
File: "src/examples/job1.py",
|
||||||
|
Line: 5,
|
||||||
|
Column: 7,
|
||||||
|
},
|
||||||
|
}, name1.Locations())
|
||||||
|
|
||||||
|
return v, nil
|
||||||
|
})
|
||||||
|
assert.NoError(t, err)
|
||||||
|
|
||||||
assert.Equal(t, 1, len(diags))
|
assert.Equal(t, 1, len(diags))
|
||||||
assert.Equal(t, "job doesn't have any tasks", diags[0].Summary)
|
assert.Equal(t, "job doesn't have any tasks", diags[0].Summary)
|
||||||
assert.Equal(t, []dyn.Location{
|
assert.Equal(t, []dyn.Location{
|
||||||
|
@ -106,7 +128,6 @@ func TestPythonMutator_load(t *testing.T) {
|
||||||
Column: 5,
|
Column: 5,
|
||||||
},
|
},
|
||||||
}, diags[0].Locations)
|
}, diags[0].Locations)
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
func TestPythonMutator_load_disallowed(t *testing.T) {
|
func TestPythonMutator_load_disallowed(t *testing.T) {
|
||||||
|
@ -146,7 +167,7 @@ func TestPythonMutator_load_disallowed(t *testing.T) {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}`, "")
|
}`, "", "")
|
||||||
|
|
||||||
mutator := PythonMutator(PythonMutatorPhaseLoad)
|
mutator := PythonMutator(PythonMutatorPhaseLoad)
|
||||||
diag := bundle.Apply(ctx, b, mutator)
|
diag := bundle.Apply(ctx, b, mutator)
|
||||||
|
@ -191,7 +212,7 @@ func TestPythonMutator_init(t *testing.T) {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}`, "")
|
}`, "", "")
|
||||||
|
|
||||||
mutator := PythonMutator(PythonMutatorPhaseInit)
|
mutator := PythonMutator(PythonMutatorPhaseInit)
|
||||||
diag := bundle.Apply(ctx, b, mutator)
|
diag := bundle.Apply(ctx, b, mutator)
|
||||||
|
@ -252,7 +273,7 @@ func TestPythonMutator_badOutput(t *testing.T) {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}`, "")
|
}`, "", "")
|
||||||
|
|
||||||
mutator := PythonMutator(PythonMutatorPhaseLoad)
|
mutator := PythonMutator(PythonMutatorPhaseLoad)
|
||||||
diag := bundle.Apply(ctx, b, mutator)
|
diag := bundle.Apply(ctx, b, mutator)
|
||||||
|
@ -588,7 +609,7 @@ or activate the environment before running CLI commands:
|
||||||
assert.Equal(t, expected, out)
|
assert.Equal(t, expected, out)
|
||||||
}
|
}
|
||||||
|
|
||||||
func withProcessStub(t *testing.T, args []string, output string, diagnostics string) context.Context {
|
func withProcessStub(t *testing.T, args []string, output string, diagnostics string, locations string) context.Context {
|
||||||
ctx := context.Background()
|
ctx := context.Background()
|
||||||
ctx, stub := process.WithStub(ctx)
|
ctx, stub := process.WithStub(ctx)
|
||||||
|
|
||||||
|
@ -600,32 +621,51 @@ func withProcessStub(t *testing.T, args []string, output string, diagnostics str
|
||||||
|
|
||||||
inputPath := filepath.Join(cacheDir, "input.json")
|
inputPath := filepath.Join(cacheDir, "input.json")
|
||||||
outputPath := filepath.Join(cacheDir, "output.json")
|
outputPath := filepath.Join(cacheDir, "output.json")
|
||||||
|
locationsPath := filepath.Join(cacheDir, "locations.json")
|
||||||
diagnosticsPath := filepath.Join(cacheDir, "diagnostics.json")
|
diagnosticsPath := filepath.Join(cacheDir, "diagnostics.json")
|
||||||
|
|
||||||
args = append(args, "--input", inputPath)
|
|
||||||
args = append(args, "--output", outputPath)
|
|
||||||
args = append(args, "--diagnostics", diagnosticsPath)
|
|
||||||
|
|
||||||
stub.WithCallback(func(actual *exec.Cmd) error {
|
stub.WithCallback(func(actual *exec.Cmd) error {
|
||||||
_, err := os.Stat(inputPath)
|
_, err := os.Stat(inputPath)
|
||||||
assert.NoError(t, err)
|
assert.NoError(t, err)
|
||||||
|
|
||||||
if reflect.DeepEqual(actual.Args, args) {
|
actualInputPath := getArg(actual.Args, "--input")
|
||||||
err := os.WriteFile(outputPath, []byte(output), 0600)
|
actualOutputPath := getArg(actual.Args, "--output")
|
||||||
|
actualDiagnosticsPath := getArg(actual.Args, "--diagnostics")
|
||||||
|
actualLocationsPath := getArg(actual.Args, "--locations")
|
||||||
|
|
||||||
|
require.Equal(t, inputPath, actualInputPath)
|
||||||
|
require.Equal(t, outputPath, actualOutputPath)
|
||||||
|
require.Equal(t, diagnosticsPath, actualDiagnosticsPath)
|
||||||
|
|
||||||
|
// locations is an optional argument
|
||||||
|
if locations != "" {
|
||||||
|
require.Equal(t, locationsPath, actualLocationsPath)
|
||||||
|
|
||||||
|
err = os.WriteFile(locationsPath, []byte(locations), 0600)
|
||||||
|
require.NoError(t, err)
|
||||||
|
}
|
||||||
|
|
||||||
|
err = os.WriteFile(outputPath, []byte(output), 0600)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
err = os.WriteFile(diagnosticsPath, []byte(diagnostics), 0600)
|
err = os.WriteFile(diagnosticsPath, []byte(diagnostics), 0600)
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
return nil
|
return nil
|
||||||
} else {
|
|
||||||
return fmt.Errorf("unexpected command: %v", actual.Args)
|
|
||||||
}
|
|
||||||
})
|
})
|
||||||
|
|
||||||
return ctx
|
return ctx
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func getArg(args []string, name string) string {
|
||||||
|
for i := 0; i < len(args); i++ {
|
||||||
|
if args[i] == name {
|
||||||
|
return args[i+1]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return ""
|
||||||
|
}
|
||||||
|
|
||||||
func loadYaml(name string, content string) *bundle.Bundle {
|
func loadYaml(name string, content string) *bundle.Bundle {
|
||||||
v, diag := config.LoadFromBytes(name, []byte(content))
|
v, diag := config.LoadFromBytes(name, []byte(content))
|
||||||
|
|
||||||
|
|
|
@ -11,6 +11,7 @@ import (
|
||||||
"strings"
|
"strings"
|
||||||
|
|
||||||
"github.com/databricks/cli/bundle"
|
"github.com/databricks/cli/bundle"
|
||||||
|
"github.com/databricks/cli/bundle/config"
|
||||||
"github.com/databricks/cli/libs/diag"
|
"github.com/databricks/cli/libs/diag"
|
||||||
"github.com/databricks/cli/libs/dyn"
|
"github.com/databricks/cli/libs/dyn"
|
||||||
"github.com/databricks/cli/libs/notebook"
|
"github.com/databricks/cli/libs/notebook"
|
||||||
|
@ -103,8 +104,13 @@ func (t *translateContext) rewritePath(
|
||||||
return fmt.Errorf("path %s is not contained in sync root path", localPath)
|
return fmt.Errorf("path %s is not contained in sync root path", localPath)
|
||||||
}
|
}
|
||||||
|
|
||||||
// Prefix remote path with its remote root path.
|
var workspacePath string
|
||||||
remotePath := path.Join(t.b.Config.Workspace.FilePath, filepath.ToSlash(localRelPath))
|
if config.IsExplicitlyEnabled(t.b.Config.Presets.SourceLinkedDeployment) {
|
||||||
|
workspacePath = t.b.SyncRootPath
|
||||||
|
} else {
|
||||||
|
workspacePath = t.b.Config.Workspace.FilePath
|
||||||
|
}
|
||||||
|
remotePath := path.Join(workspacePath, filepath.ToSlash(localRelPath))
|
||||||
|
|
||||||
// Convert local path into workspace path via specified function.
|
// Convert local path into workspace path via specified function.
|
||||||
interp, err := fn(*p, localPath, localRelPath, remotePath)
|
interp, err := fn(*p, localPath, localRelPath, remotePath)
|
||||||
|
|
|
@ -4,6 +4,7 @@ import (
|
||||||
"context"
|
"context"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
"runtime"
|
||||||
"strings"
|
"strings"
|
||||||
"testing"
|
"testing"
|
||||||
|
|
||||||
|
@ -787,3 +788,163 @@ func TestTranslatePathWithComplexVariables(t *testing.T) {
|
||||||
b.Config.Resources.Jobs["job"].Tasks[0].Libraries[0].Whl,
|
b.Config.Resources.Jobs["job"].Tasks[0].Libraries[0].Whl,
|
||||||
)
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestTranslatePathsWithSourceLinkedDeployment(t *testing.T) {
|
||||||
|
if runtime.GOOS == "windows" {
|
||||||
|
t.Skip("this test is not applicable on Windows because source-linked mode works only in the Databricks Workspace")
|
||||||
|
}
|
||||||
|
|
||||||
|
dir := t.TempDir()
|
||||||
|
touchNotebookFile(t, filepath.Join(dir, "my_job_notebook.py"))
|
||||||
|
touchNotebookFile(t, filepath.Join(dir, "my_pipeline_notebook.py"))
|
||||||
|
touchEmptyFile(t, filepath.Join(dir, "my_python_file.py"))
|
||||||
|
touchEmptyFile(t, filepath.Join(dir, "dist", "task.jar"))
|
||||||
|
touchEmptyFile(t, filepath.Join(dir, "requirements.txt"))
|
||||||
|
|
||||||
|
enabled := true
|
||||||
|
b := &bundle.Bundle{
|
||||||
|
SyncRootPath: dir,
|
||||||
|
SyncRoot: vfs.MustNew(dir),
|
||||||
|
Config: config.Root{
|
||||||
|
Workspace: config.Workspace{
|
||||||
|
FilePath: "/bundle",
|
||||||
|
},
|
||||||
|
Resources: config.Resources{
|
||||||
|
Jobs: map[string]*resources.Job{
|
||||||
|
"job": {
|
||||||
|
JobSettings: &jobs.JobSettings{
|
||||||
|
Tasks: []jobs.Task{
|
||||||
|
{
|
||||||
|
NotebookTask: &jobs.NotebookTask{
|
||||||
|
NotebookPath: "my_job_notebook.py",
|
||||||
|
},
|
||||||
|
Libraries: []compute.Library{
|
||||||
|
{Whl: "./dist/task.whl"},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
NotebookTask: &jobs.NotebookTask{
|
||||||
|
NotebookPath: "/Users/jane.doe@databricks.com/absolute_remote.py",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
NotebookTask: &jobs.NotebookTask{
|
||||||
|
NotebookPath: "my_job_notebook.py",
|
||||||
|
},
|
||||||
|
Libraries: []compute.Library{
|
||||||
|
{Requirements: "requirements.txt"},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
SparkPythonTask: &jobs.SparkPythonTask{
|
||||||
|
PythonFile: "my_python_file.py",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
SparkJarTask: &jobs.SparkJarTask{
|
||||||
|
MainClassName: "HelloWorld",
|
||||||
|
},
|
||||||
|
Libraries: []compute.Library{
|
||||||
|
{Jar: "./dist/task.jar"},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
SparkJarTask: &jobs.SparkJarTask{
|
||||||
|
MainClassName: "HelloWorldRemote",
|
||||||
|
},
|
||||||
|
Libraries: []compute.Library{
|
||||||
|
{Jar: "dbfs:/bundle/dist/task_remote.jar"},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
Pipelines: map[string]*resources.Pipeline{
|
||||||
|
"pipeline": {
|
||||||
|
PipelineSpec: &pipelines.PipelineSpec{
|
||||||
|
Libraries: []pipelines.PipelineLibrary{
|
||||||
|
{
|
||||||
|
Notebook: &pipelines.NotebookLibrary{
|
||||||
|
Path: "my_pipeline_notebook.py",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
Notebook: &pipelines.NotebookLibrary{
|
||||||
|
Path: "/Users/jane.doe@databricks.com/absolute_remote.py",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
File: &pipelines.FileLibrary{
|
||||||
|
Path: "my_python_file.py",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
Presets: config.Presets{
|
||||||
|
SourceLinkedDeployment: &enabled,
|
||||||
|
},
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
bundletest.SetLocation(b, ".", []dyn.Location{{File: filepath.Join(dir, "resource.yml")}})
|
||||||
|
diags := bundle.Apply(context.Background(), b, mutator.TranslatePaths())
|
||||||
|
require.NoError(t, diags.Error())
|
||||||
|
|
||||||
|
// updated to source path
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
filepath.Join(dir, "my_job_notebook"),
|
||||||
|
b.Config.Resources.Jobs["job"].Tasks[0].NotebookTask.NotebookPath,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
filepath.Join(dir, "requirements.txt"),
|
||||||
|
b.Config.Resources.Jobs["job"].Tasks[2].Libraries[0].Requirements,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
filepath.Join(dir, "my_python_file.py"),
|
||||||
|
b.Config.Resources.Jobs["job"].Tasks[3].SparkPythonTask.PythonFile,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
filepath.Join(dir, "my_pipeline_notebook"),
|
||||||
|
b.Config.Resources.Pipelines["pipeline"].Libraries[0].Notebook.Path,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
filepath.Join(dir, "my_python_file.py"),
|
||||||
|
b.Config.Resources.Pipelines["pipeline"].Libraries[2].File.Path,
|
||||||
|
)
|
||||||
|
|
||||||
|
// left as is
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
filepath.Join("dist", "task.whl"),
|
||||||
|
b.Config.Resources.Jobs["job"].Tasks[0].Libraries[0].Whl,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
"/Users/jane.doe@databricks.com/absolute_remote.py",
|
||||||
|
b.Config.Resources.Jobs["job"].Tasks[1].NotebookTask.NotebookPath,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
filepath.Join("dist", "task.jar"),
|
||||||
|
b.Config.Resources.Jobs["job"].Tasks[4].Libraries[0].Jar,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
"dbfs:/bundle/dist/task_remote.jar",
|
||||||
|
b.Config.Resources.Jobs["job"].Tasks[5].Libraries[0].Jar,
|
||||||
|
)
|
||||||
|
assert.Equal(
|
||||||
|
t,
|
||||||
|
"/Users/jane.doe@databricks.com/absolute_remote.py",
|
||||||
|
b.Config.Resources.Pipelines["pipeline"].Libraries[1].Notebook.Path,
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
|
@ -17,6 +17,11 @@ type Presets struct {
|
||||||
// JobsMaxConcurrentRuns is the default value for the max concurrent runs of jobs.
|
// JobsMaxConcurrentRuns is the default value for the max concurrent runs of jobs.
|
||||||
JobsMaxConcurrentRuns int `json:"jobs_max_concurrent_runs,omitempty"`
|
JobsMaxConcurrentRuns int `json:"jobs_max_concurrent_runs,omitempty"`
|
||||||
|
|
||||||
|
// SourceLinkedDeployment indicates whether source-linked deployment is enabled. Works only in Databricks Workspace
|
||||||
|
// When set to true, resources created during deployment will point to source files in the workspace instead of their workspace copies.
|
||||||
|
// File synchronization to ${workspace.file_path} is skipped.
|
||||||
|
SourceLinkedDeployment *bool `json:"source_linked_deployment,omitempty"`
|
||||||
|
|
||||||
// Tags to add to all resources.
|
// Tags to add to all resources.
|
||||||
Tags map[string]string `json:"tags,omitempty"`
|
Tags map[string]string `json:"tags,omitempty"`
|
||||||
}
|
}
|
||||||
|
|
|
@ -7,6 +7,7 @@ import (
|
||||||
"io/fs"
|
"io/fs"
|
||||||
|
|
||||||
"github.com/databricks/cli/bundle"
|
"github.com/databricks/cli/bundle"
|
||||||
|
"github.com/databricks/cli/bundle/config"
|
||||||
"github.com/databricks/cli/bundle/permissions"
|
"github.com/databricks/cli/bundle/permissions"
|
||||||
"github.com/databricks/cli/libs/cmdio"
|
"github.com/databricks/cli/libs/cmdio"
|
||||||
"github.com/databricks/cli/libs/diag"
|
"github.com/databricks/cli/libs/diag"
|
||||||
|
@ -23,6 +24,11 @@ func (m *upload) Name() string {
|
||||||
}
|
}
|
||||||
|
|
||||||
func (m *upload) Apply(ctx context.Context, b *bundle.Bundle) diag.Diagnostics {
|
func (m *upload) Apply(ctx context.Context, b *bundle.Bundle) diag.Diagnostics {
|
||||||
|
if config.IsExplicitlyEnabled(b.Config.Presets.SourceLinkedDeployment) {
|
||||||
|
cmdio.LogString(ctx, "Source-linked deployment is enabled. Deployed resources reference the source files in your working tree instead of separate copies.")
|
||||||
|
return nil
|
||||||
|
}
|
||||||
|
|
||||||
cmdio.LogString(ctx, fmt.Sprintf("Uploading bundle files to %s...", b.Config.Workspace.FilePath))
|
cmdio.LogString(ctx, fmt.Sprintf("Uploading bundle files to %s...", b.Config.Workspace.FilePath))
|
||||||
opts, err := GetSyncOptions(ctx, bundle.ReadOnly(b))
|
opts, err := GetSyncOptions(ctx, bundle.ReadOnly(b))
|
||||||
if err != nil {
|
if err != nil {
|
||||||
|
|
|
@ -6,6 +6,7 @@ import (
|
||||||
"strings"
|
"strings"
|
||||||
|
|
||||||
"github.com/databricks/cli/bundle"
|
"github.com/databricks/cli/bundle"
|
||||||
|
"github.com/databricks/cli/bundle/config"
|
||||||
"github.com/databricks/cli/bundle/libraries"
|
"github.com/databricks/cli/bundle/libraries"
|
||||||
"github.com/databricks/cli/libs/diag"
|
"github.com/databricks/cli/libs/diag"
|
||||||
"github.com/databricks/cli/libs/log"
|
"github.com/databricks/cli/libs/log"
|
||||||
|
@ -22,6 +23,9 @@ func WrapperWarning() bundle.Mutator {
|
||||||
|
|
||||||
func (m *wrapperWarning) Apply(ctx context.Context, b *bundle.Bundle) diag.Diagnostics {
|
func (m *wrapperWarning) Apply(ctx context.Context, b *bundle.Bundle) diag.Diagnostics {
|
||||||
if isPythonWheelWrapperOn(b) {
|
if isPythonWheelWrapperOn(b) {
|
||||||
|
if config.IsExplicitlyEnabled(b.Config.Presets.SourceLinkedDeployment) {
|
||||||
|
return diag.Warningf("Python wheel notebook wrapper is not available when using source-linked deployment mode. You can disable this mode by setting 'presets.source_linked_deployment: false'")
|
||||||
|
}
|
||||||
return nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -3,8 +3,10 @@ package generate
|
||||||
import (
|
import (
|
||||||
"bytes"
|
"bytes"
|
||||||
"context"
|
"context"
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"io"
|
"io"
|
||||||
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
"testing"
|
"testing"
|
||||||
|
@ -90,7 +92,7 @@ func TestGeneratePipelineCommand(t *testing.T) {
|
||||||
err := cmd.RunE(cmd, []string{})
|
err := cmd.RunE(cmd, []string{})
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
data, err := os.ReadFile(filepath.Join(configDir, "test_pipeline.yml"))
|
data, err := os.ReadFile(filepath.Join(configDir, "test_pipeline.pipeline.yml"))
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
require.Equal(t, fmt.Sprintf(`resources:
|
require.Equal(t, fmt.Sprintf(`resources:
|
||||||
pipelines:
|
pipelines:
|
||||||
|
@ -186,7 +188,123 @@ func TestGenerateJobCommand(t *testing.T) {
|
||||||
err := cmd.RunE(cmd, []string{})
|
err := cmd.RunE(cmd, []string{})
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
data, err := os.ReadFile(filepath.Join(configDir, "test_job.yml"))
|
data, err := os.ReadFile(filepath.Join(configDir, "test_job.job.yml"))
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
require.Equal(t, fmt.Sprintf(`resources:
|
||||||
|
jobs:
|
||||||
|
test_job:
|
||||||
|
name: test-job
|
||||||
|
job_clusters:
|
||||||
|
- new_cluster:
|
||||||
|
custom_tags:
|
||||||
|
"Tag1": "24X7-1234"
|
||||||
|
- new_cluster:
|
||||||
|
spark_conf:
|
||||||
|
"spark.databricks.delta.preview.enabled": "true"
|
||||||
|
tasks:
|
||||||
|
- task_key: notebook_task
|
||||||
|
notebook_task:
|
||||||
|
notebook_path: %s
|
||||||
|
parameters:
|
||||||
|
- name: empty
|
||||||
|
default: ""
|
||||||
|
`, filepath.Join("..", "src", "notebook.py")), string(data))
|
||||||
|
|
||||||
|
data, err = os.ReadFile(filepath.Join(srcDir, "notebook.py"))
|
||||||
|
require.NoError(t, err)
|
||||||
|
require.Equal(t, "# Databricks notebook source\nNotebook content", string(data))
|
||||||
|
}
|
||||||
|
|
||||||
|
func touchEmptyFile(t *testing.T, path string) {
|
||||||
|
err := os.MkdirAll(filepath.Dir(path), 0700)
|
||||||
|
require.NoError(t, err)
|
||||||
|
f, err := os.Create(path)
|
||||||
|
require.NoError(t, err)
|
||||||
|
f.Close()
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestGenerateJobCommandOldFileRename(t *testing.T) {
|
||||||
|
cmd := NewGenerateJobCommand()
|
||||||
|
|
||||||
|
root := t.TempDir()
|
||||||
|
b := &bundle.Bundle{
|
||||||
|
BundleRootPath: root,
|
||||||
|
}
|
||||||
|
|
||||||
|
m := mocks.NewMockWorkspaceClient(t)
|
||||||
|
b.SetWorkpaceClient(m.WorkspaceClient)
|
||||||
|
|
||||||
|
jobsApi := m.GetMockJobsAPI()
|
||||||
|
jobsApi.EXPECT().Get(mock.Anything, jobs.GetJobRequest{JobId: 1234}).Return(&jobs.Job{
|
||||||
|
Settings: &jobs.JobSettings{
|
||||||
|
Name: "test-job",
|
||||||
|
JobClusters: []jobs.JobCluster{
|
||||||
|
{NewCluster: compute.ClusterSpec{
|
||||||
|
CustomTags: map[string]string{
|
||||||
|
"Tag1": "24X7-1234",
|
||||||
|
},
|
||||||
|
}},
|
||||||
|
{NewCluster: compute.ClusterSpec{
|
||||||
|
SparkConf: map[string]string{
|
||||||
|
"spark.databricks.delta.preview.enabled": "true",
|
||||||
|
},
|
||||||
|
}},
|
||||||
|
},
|
||||||
|
Tasks: []jobs.Task{
|
||||||
|
{
|
||||||
|
TaskKey: "notebook_task",
|
||||||
|
NotebookTask: &jobs.NotebookTask{
|
||||||
|
NotebookPath: "/test/notebook",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
Parameters: []jobs.JobParameterDefinition{
|
||||||
|
{
|
||||||
|
Name: "empty",
|
||||||
|
Default: "",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
},
|
||||||
|
}, nil)
|
||||||
|
|
||||||
|
workspaceApi := m.GetMockWorkspaceAPI()
|
||||||
|
workspaceApi.EXPECT().GetStatusByPath(mock.Anything, "/test/notebook").Return(&workspace.ObjectInfo{
|
||||||
|
ObjectType: workspace.ObjectTypeNotebook,
|
||||||
|
Language: workspace.LanguagePython,
|
||||||
|
Path: "/test/notebook",
|
||||||
|
}, nil)
|
||||||
|
|
||||||
|
notebookContent := io.NopCloser(bytes.NewBufferString("# Databricks notebook source\nNotebook content"))
|
||||||
|
workspaceApi.EXPECT().Download(mock.Anything, "/test/notebook", mock.Anything).Return(notebookContent, nil)
|
||||||
|
|
||||||
|
cmd.SetContext(bundle.Context(context.Background(), b))
|
||||||
|
cmd.Flag("existing-job-id").Value.Set("1234")
|
||||||
|
|
||||||
|
configDir := filepath.Join(root, "resources")
|
||||||
|
cmd.Flag("config-dir").Value.Set(configDir)
|
||||||
|
|
||||||
|
srcDir := filepath.Join(root, "src")
|
||||||
|
cmd.Flag("source-dir").Value.Set(srcDir)
|
||||||
|
|
||||||
|
var key string
|
||||||
|
cmd.Flags().StringVar(&key, "key", "test_job", "")
|
||||||
|
|
||||||
|
// Create an old generated file first
|
||||||
|
oldFilename := filepath.Join(configDir, "test_job.yml")
|
||||||
|
touchEmptyFile(t, oldFilename)
|
||||||
|
|
||||||
|
// Having an existing files require --force flag to regenerate them
|
||||||
|
cmd.Flag("force").Value.Set("true")
|
||||||
|
|
||||||
|
err := cmd.RunE(cmd, []string{})
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
// Make sure file do not exists after the run
|
||||||
|
_, err = os.Stat(oldFilename)
|
||||||
|
require.True(t, errors.Is(err, fs.ErrNotExist))
|
||||||
|
|
||||||
|
data, err := os.ReadFile(filepath.Join(configDir, "test_job.job.yml"))
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
require.Equal(t, fmt.Sprintf(`resources:
|
require.Equal(t, fmt.Sprintf(`resources:
|
||||||
|
|
|
@ -1,7 +1,9 @@
|
||||||
package generate
|
package generate
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
|
||||||
|
@ -83,7 +85,17 @@ func NewGenerateJobCommand() *cobra.Command {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
filename := filepath.Join(configDir, fmt.Sprintf("%s.yml", jobKey))
|
oldFilename := filepath.Join(configDir, fmt.Sprintf("%s.yml", jobKey))
|
||||||
|
filename := filepath.Join(configDir, fmt.Sprintf("%s.job.yml", jobKey))
|
||||||
|
|
||||||
|
// User might continuously run generate command to update their bundle jobs with any changes made in Databricks UI.
|
||||||
|
// Due to changing in the generated file names, we need to first rename existing resource file to the new name.
|
||||||
|
// Otherwise users can end up with duplicated resources.
|
||||||
|
err = os.Rename(oldFilename, filename)
|
||||||
|
if err != nil && !errors.Is(err, fs.ErrNotExist) {
|
||||||
|
return fmt.Errorf("failed to rename file %s. DABs uses the resource type as a sub-extension for generated content, please rename it to %s, err: %w", oldFilename, filename, err)
|
||||||
|
}
|
||||||
|
|
||||||
saver := yamlsaver.NewSaverWithStyle(map[string]yaml.Style{
|
saver := yamlsaver.NewSaverWithStyle(map[string]yaml.Style{
|
||||||
// Including all JobSettings and nested fields which are map[string]string type
|
// Including all JobSettings and nested fields which are map[string]string type
|
||||||
"spark_conf": yaml.DoubleQuotedStyle,
|
"spark_conf": yaml.DoubleQuotedStyle,
|
||||||
|
|
|
@ -1,7 +1,9 @@
|
||||||
package generate
|
package generate
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
|
"io/fs"
|
||||||
"os"
|
"os"
|
||||||
"path/filepath"
|
"path/filepath"
|
||||||
|
|
||||||
|
@ -83,7 +85,17 @@ func NewGeneratePipelineCommand() *cobra.Command {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
filename := filepath.Join(configDir, fmt.Sprintf("%s.yml", pipelineKey))
|
oldFilename := filepath.Join(configDir, fmt.Sprintf("%s.yml", pipelineKey))
|
||||||
|
filename := filepath.Join(configDir, fmt.Sprintf("%s.pipeline.yml", pipelineKey))
|
||||||
|
|
||||||
|
// User might continuously run generate command to update their bundle jobs with any changes made in Databricks UI.
|
||||||
|
// Due to changing in the generated file names, we need to first rename existing resource file to the new name.
|
||||||
|
// Otherwise users can end up with duplicated resources.
|
||||||
|
err = os.Rename(oldFilename, filename)
|
||||||
|
if err != nil && !errors.Is(err, fs.ErrNotExist) {
|
||||||
|
return fmt.Errorf("failed to rename file %s. DABs uses the resource type as a sub-extension for generated content, please rename it to %s, err: %w", oldFilename, filename, err)
|
||||||
|
}
|
||||||
|
|
||||||
saver := yamlsaver.NewSaverWithStyle(
|
saver := yamlsaver.NewSaverWithStyle(
|
||||||
// Including all PipelineSpec and nested fields which are map[string]string type
|
// Including all PipelineSpec and nested fields which are map[string]string type
|
||||||
map[string]yaml.Style{
|
map[string]yaml.Style{
|
||||||
|
|
|
@ -1,6 +1,7 @@
|
||||||
package bundle
|
package bundle
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"context"
|
||||||
"errors"
|
"errors"
|
||||||
"fmt"
|
"fmt"
|
||||||
"io/fs"
|
"io/fs"
|
||||||
|
@ -11,6 +12,8 @@ import (
|
||||||
|
|
||||||
"github.com/databricks/cli/cmd/root"
|
"github.com/databricks/cli/cmd/root"
|
||||||
"github.com/databricks/cli/libs/cmdio"
|
"github.com/databricks/cli/libs/cmdio"
|
||||||
|
"github.com/databricks/cli/libs/dbr"
|
||||||
|
"github.com/databricks/cli/libs/filer"
|
||||||
"github.com/databricks/cli/libs/git"
|
"github.com/databricks/cli/libs/git"
|
||||||
"github.com/databricks/cli/libs/template"
|
"github.com/databricks/cli/libs/template"
|
||||||
"github.com/spf13/cobra"
|
"github.com/spf13/cobra"
|
||||||
|
@ -147,6 +150,26 @@ func repoName(url string) string {
|
||||||
return parts[len(parts)-1]
|
return parts[len(parts)-1]
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func constructOutputFiler(ctx context.Context, outputDir string) (filer.Filer, error) {
|
||||||
|
outputDir, err := filepath.Abs(outputDir)
|
||||||
|
if err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
|
||||||
|
// If the CLI is running on DBR and we're writing to the workspace file system,
|
||||||
|
// use the extension-aware workspace filesystem filer to instantiate the template.
|
||||||
|
//
|
||||||
|
// It is not possible to write notebooks through the workspace filesystem's FUSE mount.
|
||||||
|
// Therefore this is the only way we can initialize templates that contain notebooks
|
||||||
|
// when running the CLI on DBR and initializing a template to the workspace.
|
||||||
|
//
|
||||||
|
if strings.HasPrefix(outputDir, "/Workspace/") && dbr.RunsOnRuntime(ctx) {
|
||||||
|
return filer.NewWorkspaceFilesExtensionsClient(root.WorkspaceClient(ctx), outputDir)
|
||||||
|
}
|
||||||
|
|
||||||
|
return filer.NewLocalClient(outputDir)
|
||||||
|
}
|
||||||
|
|
||||||
func newInitCommand() *cobra.Command {
|
func newInitCommand() *cobra.Command {
|
||||||
cmd := &cobra.Command{
|
cmd := &cobra.Command{
|
||||||
Use: "init [TEMPLATE_PATH]",
|
Use: "init [TEMPLATE_PATH]",
|
||||||
|
@ -201,6 +224,11 @@ See https://docs.databricks.com/en/dev-tools/bundles/templates.html for more inf
|
||||||
templatePath = getNativeTemplateByDescription(description)
|
templatePath = getNativeTemplateByDescription(description)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
outputFiler, err := constructOutputFiler(ctx, outputDir)
|
||||||
|
if err != nil {
|
||||||
|
return err
|
||||||
|
}
|
||||||
|
|
||||||
if templatePath == customTemplate {
|
if templatePath == customTemplate {
|
||||||
cmdio.LogString(ctx, "Please specify a path or Git repository to use a custom template.")
|
cmdio.LogString(ctx, "Please specify a path or Git repository to use a custom template.")
|
||||||
cmdio.LogString(ctx, "See https://docs.databricks.com/en/dev-tools/bundles/templates.html to learn more about custom templates.")
|
cmdio.LogString(ctx, "See https://docs.databricks.com/en/dev-tools/bundles/templates.html to learn more about custom templates.")
|
||||||
|
@ -230,7 +258,7 @@ See https://docs.databricks.com/en/dev-tools/bundles/templates.html for more inf
|
||||||
|
|
||||||
// skip downloading the repo because input arg is not a URL. We assume
|
// skip downloading the repo because input arg is not a URL. We assume
|
||||||
// it's a path on the local file system in that case
|
// it's a path on the local file system in that case
|
||||||
return template.Materialize(ctx, configFile, templateFS, outputDir)
|
return template.Materialize(ctx, configFile, templateFS, outputFiler)
|
||||||
}
|
}
|
||||||
|
|
||||||
// Create a temporary directory with the name of the repository. The '*'
|
// Create a temporary directory with the name of the repository. The '*'
|
||||||
|
@ -255,7 +283,7 @@ See https://docs.databricks.com/en/dev-tools/bundles/templates.html for more inf
|
||||||
// Clean up downloaded repository once the template is materialized.
|
// Clean up downloaded repository once the template is materialized.
|
||||||
defer os.RemoveAll(repoDir)
|
defer os.RemoveAll(repoDir)
|
||||||
templateFS := os.DirFS(filepath.Join(repoDir, templateDir))
|
templateFS := os.DirFS(filepath.Join(repoDir, templateDir))
|
||||||
return template.Materialize(ctx, configFile, templateFS, outputDir)
|
return template.Materialize(ctx, configFile, templateFS, outputFiler)
|
||||||
}
|
}
|
||||||
return cmd
|
return cmd
|
||||||
}
|
}
|
||||||
|
|
|
@ -166,7 +166,7 @@ func TestAccGenerateAndBind(t *testing.T) {
|
||||||
_, err = os.Stat(filepath.Join(bundleRoot, "src", "test.py"))
|
_, err = os.Stat(filepath.Join(bundleRoot, "src", "test.py"))
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
matches, err := filepath.Glob(filepath.Join(bundleRoot, "resources", "test_job_key.yml"))
|
matches, err := filepath.Glob(filepath.Join(bundleRoot, "resources", "test_job_key.job.yml"))
|
||||||
require.NoError(t, err)
|
require.NoError(t, err)
|
||||||
|
|
||||||
require.Len(t, matches, 1)
|
require.Len(t, matches, 1)
|
||||||
|
|
|
@ -11,6 +11,11 @@
|
||||||
"node_type_id": {
|
"node_type_id": {
|
||||||
"type": "string",
|
"type": "string",
|
||||||
"description": "Node type id for job cluster"
|
"description": "Node type id for job cluster"
|
||||||
|
},
|
||||||
|
"root_path": {
|
||||||
|
"type": "string",
|
||||||
|
"description": "Root path to deploy bundle to",
|
||||||
|
"default": ""
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -2,7 +2,11 @@ bundle:
|
||||||
name: basic
|
name: basic
|
||||||
|
|
||||||
workspace:
|
workspace:
|
||||||
|
{{ if .root_path }}
|
||||||
|
root_path: "{{.root_path}}/.bundle/{{.unique_id}}"
|
||||||
|
{{ else }}
|
||||||
root_path: "~/.bundle/{{.unique_id}}"
|
root_path: "~/.bundle/{{.unique_id}}"
|
||||||
|
{{ end }}
|
||||||
|
|
||||||
resources:
|
resources:
|
||||||
jobs:
|
jobs:
|
||||||
|
|
|
@ -1,2 +0,0 @@
|
||||||
bundle:
|
|
||||||
name: abc
|
|
|
@ -1,5 +1,8 @@
|
||||||
bundle:
|
bundle:
|
||||||
name: "bundle-playground"
|
name: recreate-pipeline
|
||||||
|
|
||||||
|
workspace:
|
||||||
|
root_path: "~/.bundle/{{.unique_id}}"
|
||||||
|
|
||||||
variables:
|
variables:
|
||||||
catalog:
|
catalog:
|
||||||
|
|
|
@ -1,5 +1,8 @@
|
||||||
bundle:
|
bundle:
|
||||||
name: "bundle-playground"
|
name: uc-schema
|
||||||
|
|
||||||
|
workspace:
|
||||||
|
root_path: "~/.bundle/{{.unique_id}}"
|
||||||
|
|
||||||
resources:
|
resources:
|
||||||
pipelines:
|
pipelines:
|
||||||
|
|
|
@ -0,0 +1,38 @@
|
||||||
|
package bundle
|
||||||
|
|
||||||
|
import (
|
||||||
|
"fmt"
|
||||||
|
"testing"
|
||||||
|
|
||||||
|
"github.com/databricks/cli/internal"
|
||||||
|
"github.com/databricks/cli/internal/acc"
|
||||||
|
"github.com/databricks/cli/libs/env"
|
||||||
|
"github.com/google/uuid"
|
||||||
|
"github.com/stretchr/testify/require"
|
||||||
|
)
|
||||||
|
|
||||||
|
func TestAccDeployBasicToSharedWorkspacePath(t *testing.T) {
|
||||||
|
ctx, wt := acc.WorkspaceTest(t)
|
||||||
|
|
||||||
|
nodeTypeId := internal.GetNodeTypeId(env.Get(ctx, "CLOUD_ENV"))
|
||||||
|
uniqueId := uuid.New().String()
|
||||||
|
|
||||||
|
currentUser, err := wt.W.CurrentUser.Me(ctx)
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
bundleRoot, err := initTestTemplate(t, ctx, "basic", map[string]any{
|
||||||
|
"unique_id": uniqueId,
|
||||||
|
"node_type_id": nodeTypeId,
|
||||||
|
"spark_version": defaultSparkVersion,
|
||||||
|
"root_path": fmt.Sprintf("/Shared/%s", currentUser.UserName),
|
||||||
|
})
|
||||||
|
require.NoError(t, err)
|
||||||
|
|
||||||
|
t.Cleanup(func() {
|
||||||
|
err = destroyBundle(wt.T, ctx, bundleRoot)
|
||||||
|
require.NoError(wt.T, err)
|
||||||
|
})
|
||||||
|
|
||||||
|
err = deployBundle(wt.T, ctx, bundleRoot)
|
||||||
|
require.NoError(wt.T, err)
|
||||||
|
}
|
|
@ -16,6 +16,7 @@ import (
|
||||||
"github.com/databricks/cli/internal"
|
"github.com/databricks/cli/internal"
|
||||||
"github.com/databricks/cli/libs/cmdio"
|
"github.com/databricks/cli/libs/cmdio"
|
||||||
"github.com/databricks/cli/libs/env"
|
"github.com/databricks/cli/libs/env"
|
||||||
|
"github.com/databricks/cli/libs/filer"
|
||||||
"github.com/databricks/cli/libs/flags"
|
"github.com/databricks/cli/libs/flags"
|
||||||
"github.com/databricks/cli/libs/template"
|
"github.com/databricks/cli/libs/template"
|
||||||
"github.com/databricks/cli/libs/vfs"
|
"github.com/databricks/cli/libs/vfs"
|
||||||
|
@ -42,7 +43,9 @@ func initTestTemplateWithBundleRoot(t *testing.T, ctx context.Context, templateN
|
||||||
cmd := cmdio.NewIO(flags.OutputJSON, strings.NewReader(""), os.Stdout, os.Stderr, "", "bundles")
|
cmd := cmdio.NewIO(flags.OutputJSON, strings.NewReader(""), os.Stdout, os.Stderr, "", "bundles")
|
||||||
ctx = cmdio.InContext(ctx, cmd)
|
ctx = cmdio.InContext(ctx, cmd)
|
||||||
|
|
||||||
err = template.Materialize(ctx, configFilePath, os.DirFS(templateRoot), bundleRoot)
|
out, err := filer.NewLocalClient(bundleRoot)
|
||||||
|
require.NoError(t, err)
|
||||||
|
err = template.Materialize(ctx, configFilePath, os.DirFS(templateRoot), out)
|
||||||
return bundleRoot, err
|
return bundleRoot, err
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -21,8 +21,8 @@ const schemaFileName = "databricks_template_schema.json"
|
||||||
// ctx: context containing a cmdio object. This is used to prompt the user
|
// ctx: context containing a cmdio object. This is used to prompt the user
|
||||||
// configFilePath: file path containing user defined config values
|
// configFilePath: file path containing user defined config values
|
||||||
// templateFS: root of the template definition
|
// templateFS: root of the template definition
|
||||||
// outputDir: root of directory where to initialize the template
|
// outputFiler: filer to use for writing the initialized template
|
||||||
func Materialize(ctx context.Context, configFilePath string, templateFS fs.FS, outputDir string) error {
|
func Materialize(ctx context.Context, configFilePath string, templateFS fs.FS, outputFiler filer.Filer) error {
|
||||||
if _, err := fs.Stat(templateFS, schemaFileName); errors.Is(err, fs.ErrNotExist) {
|
if _, err := fs.Stat(templateFS, schemaFileName); errors.Is(err, fs.ErrNotExist) {
|
||||||
return fmt.Errorf("not a bundle template: expected to find a template schema file at %s", schemaFileName)
|
return fmt.Errorf("not a bundle template: expected to find a template schema file at %s", schemaFileName)
|
||||||
}
|
}
|
||||||
|
@ -73,12 +73,7 @@ func Materialize(ctx context.Context, configFilePath string, templateFS fs.FS, o
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
||||||
out, err := filer.NewLocalClient(outputDir)
|
err = r.persistToDisk(ctx, outputFiler)
|
||||||
if err != nil {
|
|
||||||
return err
|
|
||||||
}
|
|
||||||
|
|
||||||
err = r.persistToDisk(ctx, out)
|
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return err
|
return err
|
||||||
}
|
}
|
||||||
|
|
|
@ -19,6 +19,6 @@ func TestMaterializeForNonTemplateDirectory(t *testing.T) {
|
||||||
ctx := root.SetWorkspaceClient(context.Background(), w)
|
ctx := root.SetWorkspaceClient(context.Background(), w)
|
||||||
|
|
||||||
// Try to materialize a non-template directory.
|
// Try to materialize a non-template directory.
|
||||||
err = Materialize(ctx, "", os.DirFS(tmpDir), "")
|
err = Materialize(ctx, "", os.DirFS(tmpDir), nil)
|
||||||
assert.EqualError(t, err, fmt.Sprintf("not a bundle template: expected to find a template schema file at %s", schemaFileName))
|
assert.EqualError(t, err, fmt.Sprintf("not a bundle template: expected to find a template schema file at %s", schemaFileName))
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue