stack/packages/mosaic/framework/tools/git/pr-metadata.sh

#!/bin/bash
# pr-metadata.sh - Get PR metadata as JSON on GitHub or Gitea
# Usage: pr-metadata.sh -n <pr_number> [-o <output_file>]

set -e

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/detect-platform.sh"

# Parse arguments
PR_NUMBER=""
OUTPUT_FILE=""

while [[ $# -gt 0 ]]; do
    case $1 in
        -n|--number)
            PR_NUMBER="$2"
            shift 2
            ;;
        -o|--output)
            OUTPUT_FILE="$2"
            shift 2
            ;;
        -h|--help)
            echo "Usage: pr-metadata.sh -n <pr_number> [-o <output_file>]"
            echo ""
            echo "Options:"
            echo "  -n, --number   PR number (required)"
            echo "  -o, --output   Output file (optional, prints to stdout if omitted)"
            echo "  -h, --help     Show this help"
            exit 0
            ;;
        *)
            echo "Unknown option: $1"
            exit 1
            ;;
    esac
done

if [[ -z "$PR_NUMBER" ]]; then
    echo "Error: PR number is required (-n)" >&2
    exit 1
fi

detect_platform > /dev/null

if [[ "$PLATFORM" == "github" ]]; then
    METADATA=$(gh pr view "$PR_NUMBER" --json number,title,body,state,author,headRefName,baseRefName,files,labels,assignees,milestone,createdAt,updatedAt,url,isDraft)

    if [[ -n "$OUTPUT_FILE" ]]; then
        echo "$METADATA" > "$OUTPUT_FILE"
    else
        echo "$METADATA"
    fi
elif [[ "$PLATFORM" == "gitea" ]]; then
    OWNER=$(get_repo_owner)
    REPO=$(get_repo_name)
    REMOTE_URL=$(git remote get-url origin 2>/dev/null)

    # Extract host from remote URL
    if [[ "$REMOTE_URL" == https://* ]]; then
        HOST=$(echo "$REMOTE_URL" | sed -E 's|https://([^/]+)/.*|\1|')
    elif [[ "$REMOTE_URL" == git@* ]]; then
        HOST=$(echo "$REMOTE_URL" | sed -E 's|git@([^:]+):.*|\1|')
    else
        echo "Error: Cannot determine host from remote URL" >&2
        exit 1
    fi

    API_URL="https://${HOST}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}"

    declare -a TOKEN_CANDIDATES=()
    add_token_candidate() {
        local candidate="$1"
        [[ -z "$candidate" ]] && return 0
        local existing
        for existing in "${TOKEN_CANDIDATES[@]:-}"; do
            [[ "$existing" == "$candidate" ]] && return 0
        done
        TOKEN_CANDIDATES+=("$candidate")
    }

    add_token_candidate "${GITEA_TOKEN:-}"
    add_token_candidate "$(get_gitea_token "$HOST" || true)"

    # Git HTTPS credentials often contain a valid Gitea API token even when a
    # Mosaic credential-source entry is stale. Try them as a fallback before
    # falling back to an unauthenticated request.
    CREDS_FILE="$HOME/.git-credentials"
    if [[ -f "$CREDS_FILE" ]]; then
        while IFS= read -r credential_token; do
            add_token_candidate "$credential_token"
        done < <(grep -F "$HOST" "$CREDS_FILE" 2>/dev/null | sed -n 's#https\?://[^@]*:\([^@/]*\)@.*#\1#p')
    fi

    RAW=""
    HTTP_STATUS=""
    if [[ ${#TOKEN_CANDIDATES[@]} -gt 0 ]]; then
        for GITEA_API_TOKEN in "${TOKEN_CANDIDATES[@]}"; do
            RESPONSE_FILE=$(mktemp)
            HTTP_STATUS=$(curl -sS -o "$RESPONSE_FILE" -w '%{http_code}' -H "Authorization: token $GITEA_API_TOKEN" "$API_URL" || true)
            RAW=$(cat "$RESPONSE_FILE")
            rm -f "$RESPONSE_FILE"
            [[ "$HTTP_STATUS" =~ ^2 ]] && break
        done
    fi

    if [[ ! "$HTTP_STATUS" =~ ^2 ]]; then
        RESPONSE_FILE=$(mktemp)
        HTTP_STATUS=$(curl -sS -o "$RESPONSE_FILE" -w '%{http_code}' "$API_URL" || true)
        RAW=$(cat "$RESPONSE_FILE")
        rm -f "$RESPONSE_FILE"
    fi

    if [[ ! "$HTTP_STATUS" =~ ^2 ]]; then
        ERROR_MESSAGE=$(printf '%s' "$RAW" | python3 -c 'import json, sys
try:
    data=json.load(sys.stdin)
except Exception:
    data={}
print(data.get("message") or data.get("error") or "unknown error")')
        echo "Error: failed to fetch Gitea PR #$PR_NUMBER from $HOST/$OWNER/$REPO (HTTP $HTTP_STATUS): $ERROR_MESSAGE" >&2
        exit 1
    fi

    # Normalize Gitea response to match our expected schema
    METADATA=$(echo "$RAW" | python3 -c "
import json, sys
data = json.load(sys.stdin)
head = data.get('head') or {}
base = data.get('base') or {}
user = data.get('user') or {}
normalized = {
    'number': data.get('number') or data.get('index'),
    'title': data.get('title'),
    'body': data.get('body', ''),
    'state': data.get('state'),
    'author': user.get('login', ''),
    'headRefName': head.get('ref') or head.get('label', '').split(':')[-1],
    'baseRefName': base.get('ref') or base.get('label', '').split(':')[-1],
    'labels': [l.get('name', '') for l in data.get('labels', [])],
    'assignees': [a.get('login', '') for a in data.get('assignees', [])],
    'milestone': data.get('milestone', {}).get('title', '') if data.get('milestone') else '',
    'createdAt': data.get('created_at', ''),
    'updatedAt': data.get('updated_at', ''),
    'url': data.get('html_url') or data.get('url', ''),
    'isDraft': data.get('draft', False),
    'mergeable': data.get('mergeable'),
    'diffUrl': data.get('diff_url', ''),
}
json.dump(normalized, sys.stdout, indent=2)
")

    if [[ -n "$OUTPUT_FILE" ]]; then
        echo "$METADATA" > "$OUTPUT_FILE"
    else
        echo "$METADATA"
    fi
else
    echo "Error: Unknown platform" >&2
    exit 1
fi