Replace core SBOM-creation API with builder pattern (#1383)

* remove existing cataloging API

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add file cataloging config

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add package cataloging config

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add configs for cross-cutting concerns

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* rename CLI option configs to not require import aliases later

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* update all nested structs for the Catalog struct

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* update Catalog cli options

- add new cataloger selection options (selection and default)
- remove the excludeBinaryOverlapByOwnership
- deprecate "catalogers" flag
- add new javascript configuration

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* migrate relationship capabilities to separate internal package

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* refactor golang cataloger to use configuration options when creating packages

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* create internal object to facilitate reading from and writing to an SBOM

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* create a command-like object (task) to facilitate partial SBOM creation

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add cataloger selection capability

- be able to parse string expressions into a set of resolved actions against sets
- be able to use expressions to select/add/remove tasks to/from the final set of tasks to run

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add package, file, and environment related tasks

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* update existing file catalogers to use nested UI elements

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add CreateSBOMConfig that drives the SBOM creation process

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* capture SBOM creation info as a struct

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add CreateSBOM() function

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* fix tests

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* update docs with SBOM selection help + breaking changes

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* fix multiple override default inputs

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* fix deprecation flag printing to stdout

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* refactor cataloger selection description to separate object

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* address review comments

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* keep expression errors and show specific suggestions only

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* address additional review feedback

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* address more review comments

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* addressed additional PR review feedback

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* fix file selection references

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* remove guess language data generation option

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add tests for coordinatesForSelection

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* rename relationship attributes

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add descriptions to relationships config fields

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* improve documentation around configuration options

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

* add explicit errors around legacy config entries

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>

---------

Signed-off-by: Alex Goodman <wagoodman@users.noreply.github.com>
This commit is contained in:
Alex Goodman
2024-01-12 17:39:13 -05:00
committed by GitHub
parent 1bffc6ef0c
commit b0ab75fd89
126 changed files with 5740 additions and 1841 deletions
+145
View File
@@ -0,0 +1,145 @@
package syft
import (
"context"
"fmt"
"sort"
"time"
"github.com/dustin/go-humanize"
"github.com/scylladb/go-set/strset"
"github.com/wagoodman/go-progress"
"github.com/anchore/syft/internal/bus"
"github.com/anchore/syft/internal/relationship"
"github.com/anchore/syft/internal/sbomsync"
"github.com/anchore/syft/internal/task"
"github.com/anchore/syft/syft/artifact"
"github.com/anchore/syft/syft/event/monitor"
"github.com/anchore/syft/syft/pkg"
"github.com/anchore/syft/syft/sbom"
"github.com/anchore/syft/syft/source"
)
// CreateSBOM creates a software bill-of-materials from the given source. If the CreateSBOMConfig is nil, then
// default options will be used.
func CreateSBOM(ctx context.Context, src source.Source, cfg *CreateSBOMConfig) (*sbom.SBOM, error) {
if cfg == nil {
cfg = DefaultCreateSBOMConfig()
}
if err := cfg.validate(); err != nil {
return nil, fmt.Errorf("invalid configuration: %w", err)
}
srcMetadata := src.Describe()
taskGroups, audit, err := cfg.makeTaskGroups(srcMetadata)
if err != nil {
return nil, err
}
resolver, err := src.FileResolver(cfg.Search.Scope)
if err != nil {
return nil, fmt.Errorf("unable to get file resolver: %w", err)
}
s := sbom.SBOM{
Source: srcMetadata,
Descriptor: sbom.Descriptor{
Name: cfg.ToolName,
Version: cfg.ToolVersion,
Configuration: configurationAuditTrail{
Search: cfg.Search,
Relationships: cfg.Relationships,
DataGeneration: cfg.DataGeneration,
Packages: cfg.Packages,
Files: cfg.Files,
Catalogers: *audit,
ExtraConfigs: cfg.ToolConfiguration,
},
},
Artifacts: sbom.Artifacts{
Packages: pkg.NewCollection(),
},
}
catalogingProgress := monitorCatalogingTask(src.ID(), taskGroups)
packageCatalogingProgress := monitorPackageCatalogingTask(s.Artifacts.Packages)
builder := sbomsync.NewBuilder(&s)
for i := range taskGroups {
err := task.NewTaskExecutor(taskGroups[i], cfg.Parallelism).Execute(ctx, resolver, builder, catalogingProgress)
if err != nil {
// TODO: tie this to the open progress monitors...
return nil, fmt.Errorf("failed to run tasks: %w", err)
}
}
packageCatalogingProgress.SetCompleted()
catalogingProgress.SetCompleted()
relationship.Finalize(builder, cfg.Relationships, src)
return &s, nil
}
func monitorPackageCatalogingTask(pkgs *pkg.Collection) *monitor.CatalogerTaskProgress {
info := monitor.GenericTask{
Title: monitor.Title{
Default: "Packages",
},
ID: monitor.PackageCatalogingTaskID,
HideOnSuccess: false,
ParentID: monitor.TopLevelCatalogingTaskID,
}
prog := bus.StartCatalogerTask(info, -1, "")
go func() {
ticker := time.NewTicker(200 * time.Millisecond)
defer ticker.Stop()
for {
<-ticker.C
count := humanize.Comma(int64(pkgs.PackageCount()))
prog.AtomicStage.Set(fmt.Sprintf("%s packages", count))
if progress.IsCompleted(prog) {
break
}
}
}()
return prog
}
func monitorCatalogingTask(srcID artifact.ID, tasks [][]task.Task) *monitor.CatalogerTaskProgress {
info := monitor.GenericTask{
Title: monitor.Title{
Default: "Catalog contents",
WhileRunning: "Cataloging contents",
OnSuccess: "Cataloged contents",
},
ID: monitor.TopLevelCatalogingTaskID,
Context: string(srcID),
HideOnSuccess: false,
}
var length int64
for _, tg := range tasks {
length += int64(len(tg))
}
return bus.StartCatalogerTask(info, length, "")
}
func formatTaskNames(tasks []task.Task) []string {
set := strset.New()
for _, td := range tasks {
set.Add(td.Name())
}
list := set.List()
sort.Strings(list)
return list
}