feat: extract set_fields rule forces Int fields on gff_json merge targets (#40)
test / test (push) Successful in 1m27s
build-binaries / build-binaries (push) Successful in 2m22s
build-image / publish (push) Successful in 15s

Adds a `set_fields` option to `extract.merge.gff_json` rules: forces existing Int fields to a fixed value on every extract, applied after preserve_fields/merge_lists so the forced value always wins. Fields absent from the document stay absent. Rule targets can now be globs (e.g. `areas/*.are.json`).

Motivation: sow-module area weather chances must stay 0 (scripted regional weather owns weather); this makes the extract pipeline enforce it instead of a post-extract script.

Covered by `TestExtractSetsConfiguredGFFJSONFields`; `make check` passes.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Reviewed-on: #40
Co-authored-by: vickydotbat <vickydotbat@tutamail.com>
Co-committed-by: vickydotbat <vickydotbat@tutamail.com>
This commit was merged in pull request #40.
This commit is contained in:
2026-07-14 16:36:40 +00:00
committed by archvillainette
parent 5ebef57160
commit 4ee28fee4f
3 changed files with 148 additions and 14 deletions
+36 -14
View File
@@ -350,26 +350,48 @@ func mergeExtractedGFFJSON(p *project.Project, target string, extracted *gff.Doc
}
raw, err := os.ReadFile(target)
if err != nil {
if errors.Is(err, os.ErrNotExist) {
return nil
}
if err != nil && !errors.Is(err, os.ErrNotExist) {
return fmt.Errorf("read existing source %s: %w", target, err)
}
var existing gff.Document
if err := json.Unmarshal(raw, &existing); err != nil {
return fmt.Errorf("parse existing source %s: %w", target, err)
if err == nil {
var existing gff.Document
if err := json.Unmarshal(raw, &existing); err != nil {
return fmt.Errorf("parse existing source %s: %w", target, err)
}
for _, label := range rule.PreserveFields {
if field, ok := gffField(existing.Root, label); ok {
setGFFField(&extracted.Root, field)
}
}
for _, listRule := range rule.MergeLists {
if err := mergeGFFListByKey(&extracted.Root, existing.Root, listRule); err != nil {
return err
}
}
}
for _, label := range rule.PreserveFields {
if field, ok := gffField(existing.Root, label); ok {
setGFFField(&extracted.Root, field)
// set_fields runs last so a forced value also wins over preserve_fields.
for _, setRule := range rule.SetFields {
if err := setGFFIntField(&extracted.Root, setRule); err != nil {
return fmt.Errorf("set_fields on %s: %w", target, err)
}
}
for _, listRule := range rule.MergeLists {
if err := mergeGFFListByKey(&extracted.Root, existing.Root, listRule); err != nil {
return err
return nil
}
// setGFFIntField forces an existing Int field to a fixed value; a field the
// document does not have is left absent rather than invented.
func setGFFIntField(s *gff.Struct, rule project.ExtractSetFieldRule) error {
for index, field := range s.Fields {
if field.Label != rule.Field {
continue
}
if _, ok := field.Value.(gff.IntValue); !ok {
return fmt.Errorf("field %q is %s, not Int", rule.Field, field.Type)
}
s.Fields[index].Value = gff.IntValue(rule.Value)
return nil
}
return nil
}
@@ -384,7 +406,7 @@ func extractGFFJSONMergeRule(p *project.Project, target string) (project.Extract
return project.ExtractGFFJSONMergeRule{}, false, nil
}
for _, rule := range p.EffectiveConfig().Extract.Merge.GFFJSON {
if rule.Target == rel {
if rule.Target == rel || matchPathPattern(rel, rule.Target) {
return rule, true, nil
}
}