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

Split tracker patterns on colon and dot separators

Browse Source 
The pattern-analysis tokenizer split names only on underscore first,
then on dash. A key like "name_done:<uuid>" left the colon glued to
the leading hex group, so the trailing UUID was never recognised as a
single token and instead shredded on dash into short hex anchors. The
derived template kept those anchors fixed, producing a distinct glob
per UUID and preventing any merge.

Treat colon and dot as primary separators alongside underscore so the
embedded UUID is isolated, matched by isUUIDShape, and collapsed to a
wildcard. Extend templateHasFixedAnchor to ignore the new separators
so a separator-only template stays rejected by the anti-overmerge
guard.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-06-08 18:38:45 +02:00
parent 89ee202845
commit 591a051e0a
2 changed files with 74 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
pkg/cookiebanner/pattern_analysis_worker_test.go
View File

@@ -243,6 +243,12 @@ func TestHeuristicTemplate(t *testing.T) {
input: "__a1b2c3d4_e5f6g7h8",
changed: false,
},
{
name: "colon-delimited trailing UUID collapses to wildcard",
input: "letaido.onboarding.invite_done:0a1b2c3d-4e5f-6789-abcd-ef0123456789",
template: "letaido.onboarding.invite_done:*",
changed: true,
},
}
for _, tt := range tests {
@@ -538,6 +544,12 @@ func TestSplitTokens(t *testing.T) {
tokens: []string{"session", "550e8400-e29b-41d4-a716-446655440000", "data"},
seps: []byte{'_', '_'},
},
{
name: "colon and dot separators isolate trailing UUID",
input: "letaido.onboarding.invite_done:0a1b2c3d-4e5f-6789-abcd-ef0123456789",
tokens: []string{"letaido", "onboarding", "invite", "done", "0a1b2c3d-4e5f-6789-abcd-ef0123456789"},
seps: []byte{'.', '.', '_', ':'},
},
}
for _, tt := range tests {
@@ -952,6 +964,26 @@ func TestFindMergeGroups(t *testing.T) {
},
)
t.Run(
"colon-delimited UUID keys merge under heuristic glob",
func(t *testing.T) {
t.Parallel()
patterns := coredata.TrackerPatterns{
makePattern("letaido.onboarding.invite_done:0a1b2c3d-4e5f-6789-abcd-ef0123456789", &oneYear),
makePattern("letaido.onboarding.invite_done:11111111-2222-3333-4444-555555555555", &oneYear),
makePattern("letaido.onboarding.invite_done:aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee", &oneYear),
}
groups := findMergeGroups(patterns, 3)
require.Len(t, groups, 1)
group, ok := groups[mergeGroupKey{categoryID: gid.Nil, trackerType: coredata.TrackerTypeCookie, template: "letaido.onboarding.invite_done:*", durationBucket: durationBucket(&oneYear)}]
require.True(t, ok)
assert.Len(t, group, 3)
},
)
t.Run(
"unrelated double-underscore keys do not merge under anchor-free glob",
func(t *testing.T) {