rohit/probo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Promote glob source and trigger draft on adoption

Browse Source 
The pattern-analysis worker dropped two signals on every run. When
InsertIfNotExists hit a pre-existing glob, the computed bestSource
was discarded by the LoadByBannerIDTypeAndPattern fallback, so the
SCRIPT > EXTENSION > PRE_EXISTING precedence advertised on
bestSource was only ever enforced at first insert. Subsequent
batches with stronger sources could not promote the glob, even
though the page-script-wins rule already lives in detected_trackers
at the row level.

Separately, adoptUncategorisedPatterns returned an adopted bool
that the worker discarded; the function moves detected trackers
from uncategorised exact patterns into categorised globs, which is
a real consent transition, but no draft banner version was created
on adoption-only runs.

Add a focused TrackerPattern.PromoteSource that only updates the
source and updated_at columns. Express the precedence as a pure-Go
shouldPromoteSource helper alongside bestSource so the rule is
unit-testable without a database. The worker now calls
InsertIfNotExists, then on conflict loads, skips when the slot is
held by an exact pattern or a user-recategorised glob, and only
calls PromoteSource when the candidate source ranks above the
existing one.

The skip branch is now documented: adoptUncategorisedPatterns is
the safety net that re-homes uncategorised exacts into the existing
glob via globMatch. Capture its adopted return value and use it
(instead of the previous over-eager consentChanged flag) to gate
ensureDraftVersionForBanner. Merging exacts into a glob in their
own category never changes visitor consent, so the prior flag
produced redundant draft versions on every non-uncategorised merge.

Cover the new pieces with three test layers: pure-unit cases for
shouldPromoteSource (precedence matrix including HTTP/nil collapse
and equal-rank no-write), DB-backed tests for PromoteSource (touch
only source + updated_at, ErrResourceNotFound for missing rows),
and end-to-end worker tests for source promotion on an existing
glob, draft-on-adoption, and the merge-only no-draft case.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-05-26 14:50:39 +02:00
parent bd5c527548
commit 05cbab7258
5 changed files with 957 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

90
pkg/cookiebanner/pattern_analysis_worker.go
View File

@@ -137,18 +137,6 @@ func (h *patternAnalysisHandler) Process(ctx context.Context, banner coredata.Co
func(ctx context.Context, tx pg.Tx) error {
scope := coredata.NewScopeFromObjectID(banner.ID)
var uncategorised coredata.CookieCategory
hasUncategorised := true
if err := uncategorised.LoadUncategorisedByCookieBannerID(ctx, tx, scope, banner.ID); err != nil {
if !errors.Is(err, coredata.ErrResourceNotFound) {
return fmt.Errorf("cannot load uncategorised category: %w", err)
}
hasUncategorised = false
}
var exactPatterns coredata.TrackerPatterns
if err := exactPatterns.LoadAllByCookieBannerID(
ctx,
@@ -163,8 +151,6 @@ func (h *patternAnalysisHandler) Process(ctx context.Context, banner coredata.Co
mergeGroups := findMergeGroups(exactPatterns, patternMergeThreshold)
consentChanged := false
for key, group := range mergeGroups {
var maxAge *int
@@ -203,9 +189,23 @@ func (h *patternAnalysisHandler) Process(ctx context.Context, banner coredata.Co
return fmt.Errorf("cannot load existing glob pattern %q: %w", key.template, err)
}
if globPattern.CookieCategoryID != key.categoryID || globPattern.MatchType != coredata.TrackerPatternMatchTypeGlob {
if globPattern.MatchType != coredata.TrackerPatternMatchTypeGlob || globPattern.CookieCategoryID != key.categoryID {
// The slot is occupied by an exact pattern or
// a user-recategorised glob. Skip the relink
// here so we don't overwrite the user's
// categorisation; the exact patterns in
// `group` will be picked up below by
// adoptUncategorisedPatterns if they live in
// the uncategorised category and globMatch
// the existing glob.
continue
}
if shouldPromoteSource(globPattern.Source, source) {
if err := globPattern.PromoteSource(ctx, tx, scope, *source, now); err != nil {
return fmt.Errorf("cannot promote source on glob pattern %q: %w", key.template, err)
}
}
}
for _, exactPattern := range group {
@@ -219,20 +219,18 @@ func (h *patternAnalysisHandler) Process(ctx context.Context, banner coredata.Co
}
}
if !hasUncategorised || key.categoryID != uncategorised.ID {
consentChanged = true
}
h.logger.InfoCtx(
ctx,
"merged exact patterns into glob pattern",
log.String("template", key.template),
log.Int("count", len(group)),
log.Bool("inserted", inserted),
log.String("banner_id", banner.ID.String()),
)
}
if _, err := h.adoptUncategorisedPatterns(ctx, tx, scope, banner); err != nil {
adopted, err := h.adoptUncategorisedPatterns(ctx, tx, scope, banner)
if err != nil {
return fmt.Errorf("cannot adopt uncategorised patterns: %w", err)
}
@@ -241,7 +239,13 @@ func (h *patternAnalysisHandler) Process(ctx context.Context, banner coredata.Co
return fmt.Errorf("cannot refresh last_matched_at: %w", err)
}
if consentChanged {
// Merging exact patterns into a glob in the same category
// does not change visitor consent for those identifiers
// (findMergeGroups keys on category, so every member of a
// group is already under key.categoryID). Adoption is the
// only operation in this worker that moves trackers
// between categories and therefore changes consent.
if adopted {
if _, err := h.svc.ensureDraftVersionForBanner(ctx, tx, scope, banner.ID); err != nil {
return fmt.Errorf("cannot ensure draft version: %w", err)
}
@@ -633,15 +637,45 @@ func globMatch(pattern, name string) bool {
return true
}
// sourceRank converts a CookieSource into a comparable rank that
// reflects signal strength: SCRIPT > EXTENSION > PRE_EXISTING. HTTP
// and nil collapse into the PRE_EXISTING rank because bestSource
// already normalises them; if a future caller hands us either, the
// ranking still produces a sane "no promotion" outcome against
// PRE_EXISTING/EXTENSION/SCRIPT existing values.
func sourceRank(s *coredata.CookieSource) int {
if s == nil {
return 0
}
switch *s {
case coredata.CookieSourceScript:
return 2
case coredata.CookieSourceExtension:
return 1
default:
return 0
}
}
// shouldPromoteSource reports whether candidate represents a stronger
// signal than existing under the SCRIPT > EXTENSION > PRE_EXISTING
// precedence used across the cookie-banner pipeline. Equal ranks do
// not promote so we avoid pointless writes.
func shouldPromoteSource(existing, candidate *coredata.CookieSource) bool {
return sourceRank(candidate) > sourceRank(existing)
}
// bestSource rolls up the source values of a group of exact patterns
// being merged into a single glob. Precedence is SCRIPT > EXTENSION
// > PRE_EXISTING, mirroring both the upsert SQL's "page-script wins"
// rule and the asymmetric signal strength of each bucket: SCRIPT is
// high-confidence page evidence (a real page tracker), EXTENSION is
// high-confidence extension evidence, and PRE_EXISTING is the
// catch-all that may include extension state injected before SDK
// load. HTTP and nil collapse into PRE_EXISTING here, preserving
// the original two-value rollup behaviour for non-script values.
// > PRE_EXISTING, mirroring both the page-script-wins rule in
// detected_trackers and the asymmetric signal strength of each
// bucket: SCRIPT is high-confidence page evidence (a real page
// tracker), EXTENSION is high-confidence extension evidence, and
// PRE_EXISTING is the catch-all that may include extension state
// injected before SDK load. HTTP and nil collapse into PRE_EXISTING
// here, preserving the original two-value rollup behaviour for
// non-script values.
func bestSource(patterns []*coredata.TrackerPattern) *coredata.CookieSource {
var hasExtension bool