From ed448815b4e9881494d3ef561ec84ef694ea4b11 Mon Sep 17 00:00:00 2001 From: Gleb Kanterov Date: Mon, 2 Sep 2024 11:49:30 +0200 Subject: [PATCH] PythonMutator: explain missing package error (#1736) ## Changes Explain the error when the `databricks-pydabs` package is not installed or the Python environment isn't correctly activated. Example output: ``` Error: python mutator process failed: ".venv/bin/python3 -m databricks.bundles.build --phase load --input .../input.json --output .../output.json --diagnostics .../diagnostics.json: exit status 1", use --debug to enable logging .../.venv/bin/python3: Error while finding module specification for 'databricks.bundles.build' (ModuleNotFoundError: No module named 'databricks') Explanation: 'databricks-pydabs' library is not installed in the Python environment. If using Python wheels, ensure that 'databricks-pydabs' is included in the dependencies, and that the wheel is installed in the Python environment: $ .venv/bin/pip install -e . If using a virtual environment, ensure it is specified as the venv_path property in databricks.yml, or activate the environment before running CLI commands: experimental: pydabs: venv_path: .venv ``` ## Tests Unit tests --- .../config/mutator/python/python_mutator.go | 49 +++++++++++++++++-- .../mutator/python/python_mutator_test.go | 24 +++++++++ 2 files changed, 70 insertions(+), 3 deletions(-) diff --git a/bundle/config/mutator/python/python_mutator.go b/bundle/config/mutator/python/python_mutator.go index bf30f070..fbf3b7e0 100644 --- a/bundle/config/mutator/python/python_mutator.go +++ b/bundle/config/mutator/python/python_mutator.go @@ -1,15 +1,21 @@ package python import ( + "bytes" "context" "encoding/json" "errors" "fmt" + "io" "os" "path/filepath" - "github.com/databricks/cli/libs/python" "github.com/databricks/databricks-sdk-go/logger" + "github.com/fatih/color" + + "strings" + + "github.com/databricks/cli/libs/python" "github.com/databricks/cli/bundle/env" @@ -169,7 +175,11 @@ func (m *pythonMutator) runPythonMutator(ctx context.Context, cacheDir string, r return dyn.InvalidValue, diag.Errorf("failed to write input file: %s", err) } - stderrWriter := newLogWriter(ctx, "stderr: ") + stderrBuf := bytes.Buffer{} + stderrWriter := io.MultiWriter( + newLogWriter(ctx, "stderr: "), + &stderrBuf, + ) stdoutWriter := newLogWriter(ctx, "stdout: ") _, processErr := process.Background( @@ -197,7 +207,13 @@ func (m *pythonMutator) runPythonMutator(ctx context.Context, cacheDir string, r // process can fail without reporting errors in diagnostics file or creating it, for instance, // venv doesn't have PyDABs library installed if processErr != nil { - return dyn.InvalidValue, diag.Errorf("python mutator process failed: %sw, use --debug to enable logging", processErr) + diagnostic := diag.Diagnostic{ + Severity: diag.Error, + Summary: fmt.Sprintf("python mutator process failed: %q, use --debug to enable logging", processErr), + Detail: explainProcessErr(stderrBuf.String()), + } + + return dyn.InvalidValue, diag.Diagnostics{diagnostic} } // or we can fail to read diagnostics file, that should always be created @@ -212,6 +228,33 @@ func (m *pythonMutator) runPythonMutator(ctx context.Context, cacheDir string, r return output, pythonDiagnostics } +const installExplanation = `If using Python wheels, ensure that 'databricks-pydabs' is included in the dependencies, +and that the wheel is installed in the Python environment: + + $ .venv/bin/pip install -e . + +If using a virtual environment, ensure it is specified as the venv_path property in databricks.yml, +or activate the environment before running CLI commands: + + experimental: + pydabs: + venv_path: .venv +` + +// explainProcessErr provides additional explanation for common errors. +// It's meant to be the best effort, and not all errors are covered. +// Output should be used only used for error reporting. +func explainProcessErr(stderr string) string { + // implemented in cpython/Lib/runpy.py and portable across Python 3.x, including pypy + if strings.Contains(stderr, "Error while finding module specification for 'databricks.bundles.build'") { + summary := color.CyanString("Explanation: ") + "'databricks-pydabs' library is not installed in the Python environment.\n" + + return stderr + "\n" + summary + "\n" + installExplanation + } + + return stderr +} + func writeInputFile(inputPath string, input dyn.Value) error { // we need to marshal dyn.Value instead of bundle.Config to JSON to support // non-string fields assigned with bundle variables diff --git a/bundle/config/mutator/python/python_mutator_test.go b/bundle/config/mutator/python/python_mutator_test.go index 26350d88..bf12b249 100644 --- a/bundle/config/mutator/python/python_mutator_test.go +++ b/bundle/config/mutator/python/python_mutator_test.go @@ -564,6 +564,30 @@ func TestStrictNormalize(t *testing.T) { assert.True(t, strictDiags.HasError()) } +func TestExplainProcessErr(t *testing.T) { + stderr := "/home/test/.venv/bin/python3: Error while finding module specification for 'databricks.bundles.build' (ModuleNotFoundError: No module named 'databricks')\n" + expected := `/home/test/.venv/bin/python3: Error while finding module specification for 'databricks.bundles.build' (ModuleNotFoundError: No module named 'databricks') + +Explanation: 'databricks-pydabs' library is not installed in the Python environment. + +If using Python wheels, ensure that 'databricks-pydabs' is included in the dependencies, +and that the wheel is installed in the Python environment: + + $ .venv/bin/pip install -e . + +If using a virtual environment, ensure it is specified as the venv_path property in databricks.yml, +or activate the environment before running CLI commands: + + experimental: + pydabs: + venv_path: .venv +` + + out := explainProcessErr(stderr) + + assert.Equal(t, expected, out) +} + func withProcessStub(t *testing.T, args []string, output string, diagnostics string) context.Context { ctx := context.Background() ctx, stub := process.WithStub(ctx)