Skip to content

Commit b831d1c

Browse files
authored
fix: gnore weird transient packages (#4176)
Signed-off-by: Uroš Marolt <uros@marolt.me>
1 parent bba3a14 commit b831d1c

5 files changed

Lines changed: 12 additions & 0 deletions

File tree

services/apps/packages_worker/src/deps-dev/queries/advisoriesSql.ts

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -20,6 +20,7 @@ WITH purl_map AS (
2020
FROM \`bigquery-public-data.deps_dev_v1.PackageVersionsLatest\`
2121
WHERE System IN (${systems})
2222
AND Purl IS NOT NULL
23+
AND Name NOT LIKE '%>%'
2324
GROUP BY System, Name
2425
)
2526
SELECT
@@ -33,5 +34,6 @@ FROM \`bigquery-public-data.deps_dev_v1.AdvisoriesLatest\` a,
3334
UNNEST(a.Packages) AS pkg
3435
LEFT JOIN purl_map pm ON pm.System = pkg.System AND pm.Name = pkg.Name
3536
WHERE pkg.System IN (${systems})
37+
AND pkg.Name NOT LIKE '%>%'
3638
`
3739
}

services/apps/packages_worker/src/deps-dev/queries/dependentCountsSql.ts

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -9,6 +9,7 @@ WITH purl_map AS (
99
FROM \`bigquery-public-data.deps_dev_v1.PackageVersionsLatest\`
1010
WHERE System IN ('NPM', 'GO', 'MAVEN', 'PYPI', 'NUGET', 'CARGO')
1111
AND Purl IS NOT NULL
12+
AND Name NOT LIKE '%>%'
1213
GROUP BY System, Name
1314
)
1415
SELECT

services/apps/packages_worker/src/deps-dev/queries/packageReposSql.ts

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,7 @@ WITH purl_map AS (
55
FROM \`bigquery-public-data.deps_dev_v1.PackageVersionsLatest\`
66
WHERE System IN (${systems})
77
AND Purl IS NOT NULL
8+
AND Name NOT LIKE '%>%'
89
GROUP BY System, Name
910
),
1011
path_computed AS (

services/apps/packages_worker/src/deps-dev/queries/packagesSql.ts

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,7 @@ SELECT
1515
FROM \`bigquery-public-data.deps_dev_v1.PackageVersionsLatest\`
1616
WHERE System IN (${systems})
1717
AND Purl IS NOT NULL
18+
AND Name NOT LIKE '%>%'
1819
QUALIFY ROW_NUMBER() OVER (PARTITION BY System, Name ORDER BY UpstreamPublishedAt DESC) = 1
1920
`
2021
}
@@ -44,6 +45,7 @@ WITH today AS (
4445
AND SnapshotAt < TIMESTAMP(DATE_ADD(DATE '${today}', INTERVAL 1 DAY))
4546
AND System IN (${systems})
4647
AND Purl IS NOT NULL
48+
AND Name NOT LIKE '%>%'
4749
QUALIFY ROW_NUMBER() OVER (PARTITION BY System, Name ORDER BY UpstreamPublishedAt DESC) = 1
4850
),
4951
last_watermark AS (
@@ -53,6 +55,8 @@ last_watermark AS (
5355
WHERE SnapshotAt >= TIMESTAMP('${watermark}')
5456
AND SnapshotAt < TIMESTAMP(DATE_ADD(DATE '${watermark}', INTERVAL 1 DAY))
5557
AND System IN (${systems})
58+
AND Purl IS NOT NULL
59+
AND Name NOT LIKE '%>%'
5660
GROUP BY System, Name
5761
)
5862
SELECT t.* EXCEPT(UpstreamPublishedAt)

services/apps/packages_worker/src/deps-dev/queries/versionsSql.ts

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -11,6 +11,7 @@ SELECT
1111
FROM \`bigquery-public-data.deps_dev_v1.PackageVersionsLatest\`
1212
WHERE System IN (${systems})
1313
AND Purl IS NOT NULL
14+
AND Name NOT LIKE '%>%'
1415
`
1516
}
1617

@@ -34,13 +35,16 @@ WITH today AS (
3435
AND SnapshotAt < TIMESTAMP(DATE_ADD(DATE '${today}', INTERVAL 1 DAY))
3536
AND System IN (${systems})
3637
AND Purl IS NOT NULL
38+
AND Name NOT LIKE '%>%'
3739
),
3840
last_watermark AS (
3941
SELECT System, Name, Version, MAX(UpstreamPublishedAt) AS UpstreamPublishedAt
4042
FROM \`bigquery-public-data.deps_dev_v1.PackageVersions\`
4143
WHERE SnapshotAt >= TIMESTAMP('${watermark}')
4244
AND SnapshotAt < TIMESTAMP(DATE_ADD(DATE '${watermark}', INTERVAL 1 DAY))
4345
AND System IN (${systems})
46+
AND Purl IS NOT NULL
47+
AND Name NOT LIKE '%>%'
4448
GROUP BY System, Name, Version
4549
)
4650
SELECT t.*

0 commit comments

Comments
 (0)