apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-04-24 23:56:21 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Fix backfill: replace gh issue list with gh api for pagination

Browse source 
gh issue list does not support --page flag. Switch to gh api with
temp file to handle JSON containing control characters in issue bodies.
This commit is contained in:
BukeLy 2026-03-02 18:28:01 +08:00
parent 30d7de64d4
commit 3d41a730f1
1 changed files with 3 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

16
.github/workflows/backfill-dedupe.yml vendored
View file

@ -37,19 +37,9 @@ jobs:
SINCE=$(date -u -d "$DAYS_BACK days ago" +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u -v-${DAYS_BACK}d +%Y-%m-%dT%H:%M:%SZ) SINCE=$(date -u -d "$DAYS_BACK days ago" +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u -v-${DAYS_BACK}d +%Y-%m-%dT%H:%M:%SZ)
echo "Fetching open issues since $SINCE" echo "Fetching open issues since $SINCE"
# Get open issues with pagination, filter out PRs and already-labeled ones # Get open issues via gh api --paginate, filter out PRs and already-labeled ones
ISSUES="" ISSUES=$(gh api --paginate "repos/$REPO/issues?state=open&per_page=100" \
PAGE=1 --jq "[.[] | select(.pull_request == null) | select(.created_at >= \"$SINCE\") | select([.labels[].name] | index(\"duplicate\") | not)] | .[].number" | xargs)
while true; do
RAW_COUNT=$(gh issue list --repo "$REPO" --state open --limit 100 --page "$PAGE" --json number | jq 'length')
BATCH=$(gh issue list --repo "$REPO" --state open --limit 100 --page "$PAGE" --json number,labels,createdAt \
--jq "[.[] | select(.createdAt >= \"$SINCE\") | select([.labels[].name] | index(\"duplicate\") | not)] | .[].number")
[ -n "$BATCH" ] && ISSUES="$ISSUES $BATCH"
[ "$RAW_COUNT" -lt 100 ] && break
PAGE=$((PAGE + 1))
done
ISSUES=$(echo "$ISSUES" | xargs)
if [ -z "$ISSUES" ]; then if [ -z "$ISSUES" ]; then
echo "No issues to process" echo "No issues to process"