-
Notifications
You must be signed in to change notification settings - Fork 51
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'main' into dependabot/npm_and_yarn/internal/staticanaly…
…sis/parsing/parsing-minor-updates-9fe37212c1
- Loading branch information
Showing
6 changed files
with
88 additions
and
3 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,15 @@ | ||
steps: | ||
- name: gcr.io/google.com/cloudsdktool/cloud-sdk | ||
env: | ||
- 'PROJECT_ID=ossf-malware-analysis' | ||
- 'LOAD_DATASET=testing' # TODO: change after testing is completed | ||
- 'LOAD_TABLE_PREFIX=merge_' | ||
- 'DEST_DATASET=testing' # TODO: change after testing is completed | ||
- 'DEST_TABLE=analysis' | ||
- 'RESULT_BUCKET=gs://ossf-malware-analysis-results' | ||
- 'SCHEMA_FILE=function/loader/dynamic-analysis-schema.json' | ||
entrypoint: '/bin/bash' | ||
args: ['scripts/bq_load.sh'] | ||
timeout: 43200s # 12 hours | ||
options: | ||
logging: CLOUD_LOGGING_ONLY |
File renamed without changes.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,70 @@ | ||
#!/bin/bash | ||
|
||
if [ -z "$PROJECT_ID" ]; then | ||
echo "PROJECT_ID must be set" | ||
exit 1 | ||
fi | ||
|
||
if [ -z "$LOAD_DATASET" ]; then | ||
echo "LOAD_DATASET must be set" | ||
exit 1 | ||
fi | ||
|
||
if [ -z "$LOAD_TABLE_PREFIX" ]; then | ||
echo "LOAD_TABLE_PREFIX must be set" | ||
exit 1 | ||
fi | ||
|
||
if [ -z "$DEST_DATASET" ]; then | ||
echo "DEST_DATASET must be set" | ||
exit 1 | ||
fi | ||
|
||
if [ -z "$DEST_TABLE" ]; then | ||
echo "DEST_TABLE must be set" | ||
exit 1 | ||
fi | ||
|
||
if [ -z "$RESULT_BUCKET" ]; then | ||
echo "RESULT_BUCKET must be set" | ||
exit 1 | ||
fi | ||
|
||
if [ -z "$SCHEMA_FILE" ]; then | ||
echo "SCHEMA_FILE must be set" | ||
exit 1 | ||
fi | ||
|
||
union="" | ||
|
||
for bucket_prefix in `gsutil ls "$RESULT_BUCKET"`; do | ||
prefix=`echo "$bucket_prefix" | sed "s|$RESULT_BUCKET/\([^\]*\)/|\1|g"` | ||
clean_prefix=`echo "$prefix" | tr -c -d "[:alnum:]"` | ||
table_name="$LOAD_TABLE_PREFIX$clean_prefix" | ||
|
||
echo "## Loading $bucket_prefix into \`$PROJECT_ID.$LOAD_DATASET.$table_name\`." | ||
bq load \ | ||
--headless \ | ||
--project_id="$PROJECT_ID" \ | ||
--dataset_id="$LOAD_DATASET" \ | ||
--replace \ | ||
--time_partitioning_type="DAY" \ | ||
--time_partitioning_field="CreatedTimestamp" \ | ||
--source_format="NEWLINE_DELIMITED_JSON" \ | ||
--max_bad_records=10000 \ | ||
"$table_name" "$bucket_prefix*" "$SCHEMA_FILE" | ||
|
||
# Construct a UNION query for joining the prefix shards together | ||
subquery="SELECT * FROM \`$PROJECT_ID.$LOAD_DATASET.$table_name\`" | ||
if [ -n "$union" ]; then | ||
union="$union UNION ALL " | ||
fi | ||
union="$union$subquery" | ||
done | ||
|
||
query="CREATE OR REPLACE TABLE \`$PROJECT_ID.$DEST_DATASET.$DEST_TABLE\` LIKE \`$PROJECT_ID.$LOAD_DATASET.$table_name\` PARTITION BY TIMESTAMP_TRUNC(CreatedTimestamp, DAY) OPTIONS(expiration_timestamp=NULL) AS $union;" | ||
|
||
echo "## Updating \`$PROJECT_ID.$DEST_DATASET.$DEST_TABLE\` from shards." | ||
echo "Executing query: '$query'" | ||
|
||
bq query --headless --nouse_legacy_sql --project_id="$PROJECT_ID" "$query" |