fix(mosaic-tools): roll up Gitea and Woodpecker wrapper fixes (#524)

2026-05-26 20:56:09 +00:00
parent 755df9079e
commit 821e19dcbb
26 changed files with 1173 additions and 174 deletions
--- a/packages/mosaic/framework/tools/git/pr-metadata.sh
+++ b/packages/mosaic/framework/tools/git/pr-metadata.sh
@@ -2,9 +2,10 @@
 # pr-metadata.sh - Get PR metadata as JSON on GitHub or Gitea
 # Usage: pr-metadata.sh -n <pr_number> [-o <output_file>]

-set -e
+set -euo pipefail

 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+# shellcheck source=packages/mosaic/framework/tools/git/detect-platform.sh
 source "$SCRIPT_DIR/detect-platform.sh"

 # Parse arguments
@@ -31,7 +32,7 @@ while [[ $# -gt 0 ]]; do
            exit 0
            ;;
        *)
-            echo "Unknown option: $1"
+            echo "Unknown option: $1" >&2
            exit 1
            ;;
    esac
@@ -42,56 +43,168 @@ if [[ -z "$PR_NUMBER" ]]; then
    exit 1
 fi

+write_metadata() {
+    local metadata="$1"
+    if [[ -n "$OUTPUT_FILE" ]]; then
+        printf '%s\n' "$metadata" > "$OUTPUT_FILE"
+    else
+        printf '%s\n' "$metadata"
+    fi
+}
+
+curl_gitea_pull() {
+    local api_url="$1"
+    local token basic_auth raw_code body_file http_code
+    body_file=$(mktemp)
+
+    token=$(get_gitea_token "$HOST" || true)
+    if [[ -n "$token" ]]; then
+        raw_code=$(curl -sS -w '%{http_code}' -o "$body_file" -H "Authorization: token $token" "$api_url" || true)
+        if [[ "$raw_code" =~ ^2 ]]; then
+            cat "$body_file"
+            rm -f "$body_file"
+            return 0
+        fi
+        http_code="$raw_code"
+    fi
+
+    basic_auth=$(get_gitea_basic_auth "$HOST" || true)
+    if [[ -n "$basic_auth" ]]; then
+        raw_code=$(curl -sS -w '%{http_code}' -o "$body_file" -u "$basic_auth" "$api_url" || true)
+        if [[ "$raw_code" =~ ^2 ]]; then
+            cat "$body_file"
+            rm -f "$body_file"
+            return 0
+        fi
+        http_code="$raw_code"
+    fi
+
+    if [[ -z "${http_code:-}" ]]; then
+        raw_code=$(curl -sS -w '%{http_code}' -o "$body_file" "$api_url" || true)
+        http_code="$raw_code"
+    fi
+
+    python3 - "$http_code" "$body_file" <<'PY' >&2
+import json
+import sys
+
+code, path = sys.argv[1], sys.argv[2]
+try:
+    data = json.load(open(path, encoding="utf-8"))
+    message = data.get("message") or data.get("error") or "unknown API error"
+except Exception:
+    message = open(path, encoding="utf-8", errors="replace").read()[:200] or "empty response"
+print(f"Error: Gitea pull request API request failed with HTTP {code}: {message}")
+PY
+    rm -f "$body_file"
+    return 1
+}
+
 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 "$METADATA"
-    fi
+    write_metadata "$METADATA"
 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
+    HOST=$(get_remote_host) || {
+        echo "Error: Cannot determine host from origin remote URL" >&2
        exit 1
-    fi
+    }

    API_URL="https://${HOST}/api/v1/repos/${OWNER}/${REPO}/pulls/${PR_NUMBER}"
-
-    GITEA_API_TOKEN=$(get_gitea_token "$HOST" || true)
-
-    if [[ -n "$GITEA_API_TOKEN" ]]; then
-        RAW=$(curl -sS -H "Authorization: token $GITEA_API_TOKEN" "$API_URL")
+    if [[ -n "${MOSAIC_GITEA_PR_METADATA_RAW_FILE:-}" ]]; then
+        RAW=$(cat "$MOSAIC_GITEA_PR_METADATA_RAW_FILE")
    else
-        RAW=$(curl -sS "$API_URL")
+        RAW=$(curl_gitea_pull "$API_URL")
    fi

-    # Normalize Gitea response to match our expected schema
-    METADATA=$(echo "$RAW" | python3 -c "
-import json, sys
-data = json.load(sys.stdin)
+    # Normalize Gitea response to match GitHub's expected metadata schema.
+    METADATA=$(printf '%s' "$RAW" | python3 -c "
+import json
+import sys
+
+def first_non_empty(*values):
+    for value in values:
+        if value is None:
+            continue
+        if isinstance(value, str):
+            value = value.strip()
+        if value:
+            return value
+    return ''
+
+def nested(data, *keys):
+    current = data
+    for key in keys:
+        if not isinstance(current, dict):
+            return None
+        current = current.get(key)
+    return current
+
+try:
+    data = json.load(sys.stdin)
+except json.JSONDecodeError as exc:
+    print(f'Error: Gitea API returned non-JSON response: {exc}', file=sys.stderr)
+    sys.exit(1)
+
+if not isinstance(data, dict):
+    print('Error: Gitea API returned an unexpected non-object response', file=sys.stderr)
+    sys.exit(1)
+
+if data.get('message') and not data.get('number'):
+    print(f\"Error: Gitea API error: {data.get('message')}\", file=sys.stderr)
+    sys.exit(1)
+
+head_ref = first_non_empty(
+    nested(data, 'head', 'ref'),
+    nested(data, 'head', 'name'),
+    nested(data, 'head', 'branch'),
+    data.get('head_branch'),
+    data.get('head_ref'),
+    nested(data, 'head', 'label'),
+    data.get('head_label'),
+)
+if isinstance(head_ref, str) and head_ref.startswith('refs/pull/'):
+    head_ref = first_non_empty(
+        nested(data, 'head', 'label'),
+        data.get('head_label'),
+        nested(data, 'head', 'name'),
+        nested(data, 'head', 'branch'),
+        data.get('head_branch'),
+        data.get('head_ref'),
+        head_ref,
+    )
+base_ref = first_non_empty(
+    nested(data, 'base', 'ref'),
+    nested(data, 'base', 'name'),
+    nested(data, 'base', 'branch'),
+    data.get('base_branch'),
+    data.get('base_ref'),
+    data.get('base_label'),
+)
+
+if not head_ref or not base_ref:
+    available = ', '.join(sorted(data.keys()))
+    print(
+        'Error: Unable to resolve non-empty Gitea PR head/base refs '
+        f'(headRefName={head_ref!r}, baseRefName={base_ref!r}; keys={available})',
+        file=sys.stderr,
+    )
+    sys.exit(1)
+
 normalized = {
    'number': data.get('number'),
    'title': data.get('title'),
    'body': data.get('body', ''),
    'state': data.get('state'),
-    'author': data.get('user', {}).get('login', ''),
-    'headRefName': data.get('head', {}).get('ref', ''),
-    'baseRefName': data.get('base', {}).get('ref', ''),
-    '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 '',
+    'author': nested(data, 'user', 'login') or '',
+    'headRefName': head_ref,
+    'baseRefName': base_ref,
+    'labels': [l.get('name', '') for l in data.get('labels', []) if isinstance(l, dict)],
+    'assignees': [a.get('login', '') for a in data.get('assignees', []) if isinstance(a, dict)],
+    'milestone': nested(data, 'milestone', 'title') or '',
    'createdAt': data.get('created_at', ''),
    'updatedAt': data.get('updated_at', ''),
    'url': data.get('html_url', ''),
@@ -102,11 +215,7 @@ normalized = {
 json.dump(normalized, sys.stdout, indent=2)
 ")

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