Add Phase 4 migration scripts for log extraction

- 30-extract-parse-failures.sh: Extracts parse failure events from logs
- 31-extract-purgatory-expiry.sh: Extracts purgatory expiry events from logs
- Both support time range filtering (--since, --until)
- Includes dry-run mode for testing
- Gracefully handles missing logs with dependency notes
- TSV output format for Phase 5 consumption
- Ready for when structured logging is implemented in ngit-grasp

2 files changed, 674 insertions, 0 deletions

diff --git a/docs/how-to/migration-scripts/30-extract-parse-failures.sh b/docs/how-to/migration-scripts/30-extract-parse-failures.sh
new file mode 100755
index 0000000..753fd3e
--- /dev/null
+++ b/docs/how-to/migration-scripts/30-extract-parse-failures.sh
@@ -0,0 +1,328 @@
+#!/usr/bin/env bash
+#
+# 30-extract-parse-failures.sh - Extract parse failure events from systemd logs
+#
+# PHASE 4a of the ngit-relay to ngit-grasp migration analysis pipeline.
+# Extracts structured [PARSE_FAIL] log entries from journalctl.
+#
+# USAGE:
+#   ./30-extract-parse-failures.sh <service-name> <output-dir> [options]
+#
+# EXAMPLES:
+#   # Extract from ngit-grasp service (last 30 days, default)
+#   ./30-extract-parse-failures.sh ngit-grasp.service output/logs
+#
+#   # Extract with custom time range
+#   ./30-extract-parse-failures.sh ngit-grasp.service output/logs --since "2026-01-01"
+#
+#   # Extract from specific time window
+#   ./30-extract-parse-failures.sh ngit-grasp.service output/logs --since "2026-01-15" --until "2026-01-22"
+#
+# OPTIONS:
+#   --since <date>   Start date for log extraction (default: 30 days ago)
+#   --until <date>   End date for log extraction (default: now)
+#   --dry-run        Show what would be extracted without writing files
+#
+# OUTPUT:
+#   <output-dir>/parse-failures.txt
+#
+# OUTPUT FORMAT (TSV):
+#   repo<TAB>npub<TAB>kind<TAB>event_id<TAB>reason
+#
+# EXPECTED LOG FORMAT:
+#   The script looks for structured log entries in this format:
+#
+#   2026-01-22T10:30:45Z ngit-grasp[1234]: [PARSE_FAIL] kind=30618 event_id=abc123... reason="invalid refs format" repo=myrepo npub=npub1...
+#
+#   Required fields: kind, event_id, reason
+#   Optional fields: repo, npub (may not be available if parsing failed early)
+#
+# DEPENDENCY:
+#   This script requires logging improvements in ngit-grasp to emit structured
+#   [PARSE_FAIL] log entries. Until those are implemented, this script will
+#   find no matching entries (which is handled gracefully).
+#
+#   See: docs/how-to/migrate-ngit-relay-to-ngit-grasp.md (Dependencies section)
+#
+#   Expected Rust logging code:
+#     tracing::warn!(
+#         target: "migration",
+#         "[PARSE_FAIL] kind={} event_id={} reason=\"{}\" repo={} npub={}",
+#         event.kind, event.id, reason, identifier, npub
+#     );
+#
+# PREREQUISITES:
+#   - journalctl (systemd)
+#   - grep, awk (standard Unix tools)
+#   - Access to systemd journal (may require sudo or journal group membership)
+#
+# RUNTIME: Depends on log volume, typically < 30 seconds
+#
+# SEE ALSO:
+#   docs/how-to/migrate-ngit-relay-to-ngit-grasp.md - Full migration guide
+#   31-extract-purgatory-expiry.sh - Companion script for purgatory expiry logs
+#
+
+set -euo pipefail
+
+# Colors for output (disabled if not a terminal)
+if [[ -t 1 ]]; then
+    RED='\033[0;31m'
+    GREEN='\033[0;32m'
+    YELLOW='\033[0;33m'
+    BLUE='\033[0;34m'
+    NC='\033[0m'
+else
+    RED=''
+    GREEN=''
+    YELLOW=''
+    BLUE=''
+    NC=''
+fi
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $*" >&2
+}
+
+log_success() {
+    echo -e "${GREEN}[OK]${NC} $*" >&2
+}
+
+log_warn() {
+    echo -e "${YELLOW}[WARN]${NC} $*" >&2
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $*" >&2
+}
+
+usage() {
+    echo "Usage: $0 <service-name> <output-dir> [options]"
+    echo ""
+    echo "Arguments:"
+    echo "  service-name  Systemd service name (e.g., ngit-grasp.service)"
+    echo "  output-dir    Directory to store extracted log data"
+    echo ""
+    echo "Options:"
+    echo "  --since <date>   Start date (default: 30 days ago)"
+    echo "  --until <date>   End date (default: now)"
+    echo "  --dry-run        Show what would be extracted without writing"
+    echo ""
+    echo "Examples:"
+    echo "  $0 ngit-grasp.service output/logs"
+    echo "  $0 ngit-grasp.service output/logs --since '2026-01-01'"
+    echo "  $0 ngit-grasp.service output/logs --since '2026-01-15' --until '2026-01-22'"
+    echo ""
+    echo "Expected log format:"
+    echo "  [PARSE_FAIL] kind=30618 event_id=abc123 reason=\"...\" repo=myrepo npub=npub1..."
+    exit 1
+}
+
+# Parse a single log line and extract fields
+# Input: log line containing [PARSE_FAIL]
+# Output: TSV line: repo<TAB>npub<TAB>kind<TAB>event_id<TAB>reason
+parse_log_line() {
+    local line="$1"
+    
+    # Extract fields using grep -oP (Perl regex) or awk
+    # Fields: kind, event_id, reason, repo (optional), npub (optional)
+    
+    local kind event_id reason repo npub
+    
+    # Extract kind=VALUE
+    kind=$(echo "$line" | grep -oP 'kind=\K[0-9]+' || echo "")
+    
+    # Extract event_id=VALUE (hex string, possibly truncated with ...)
+    event_id=$(echo "$line" | grep -oP 'event_id=\K[a-f0-9]+' || echo "")
+    
+    # Extract reason="VALUE" (quoted string)
+    reason=$(echo "$line" | grep -oP 'reason="\K[^"]*' || echo "")
+    
+    # Extract repo=VALUE (optional, unquoted identifier)
+    repo=$(echo "$line" | grep -oP 'repo=\K[^ ]+' || echo "")
+    
+    # Extract npub=VALUE (optional, npub1... format)
+    npub=$(echo "$line" | grep -oP 'npub=\K[^ ]+' || echo "")
+    
+    # Only output if we have the required fields
+    if [[ -n "$kind" && -n "$event_id" && -n "$reason" ]]; then
+        printf '%s\t%s\t%s\t%s\t%s\n' "$repo" "$npub" "$kind" "$event_id" "$reason"
+    fi
+}
+
+# Main
+main() {
+    if [[ $# -lt 2 ]]; then
+        usage
+    fi
+    
+    local service="$1"
+    local output_dir="$2"
+    shift 2
+    
+    # Default time range: last 30 days
+    local since_date
+    since_date=$(date -d "30 days ago" "+%Y-%m-%d" 2>/dev/null || date -v-30d "+%Y-%m-%d" 2>/dev/null || echo "")
+    local until_date=""
+    local dry_run=false
+    
+    # Parse options
+    while [[ $# -gt 0 ]]; do
+        case "$1" in
+            --since)
+                since_date="$2"
+                shift 2
+                ;;
+            --until)
+                until_date="$2"
+                shift 2
+                ;;
+            --dry-run)
+                dry_run=true
+                shift
+                ;;
+            *)
+                log_error "Unknown option: $1"
+                usage
+                ;;
+        esac
+    done
+    
+    # Validate service name
+    if [[ ! "$service" =~ \.service$ ]]; then
+        service="${service}.service"
+    fi
+    
+    log_info "Extracting parse failures from systemd logs"
+    log_info "Service: $service"
+    log_info "Output: $output_dir"
+    log_info "Time range: ${since_date:-beginning} to ${until_date:-now}"
+    
+    # Check if journalctl is available
+    if ! command -v journalctl &> /dev/null; then
+        log_error "journalctl not found. This script requires systemd."
+        exit 1
+    fi
+    
+    # Build journalctl command
+    local journal_cmd="journalctl -u $service --no-pager -o short-iso"
+    
+    if [[ -n "$since_date" ]]; then
+        journal_cmd="$journal_cmd --since '$since_date'"
+    fi
+    
+    if [[ -n "$until_date" ]]; then
+        journal_cmd="$journal_cmd --until '$until_date'"
+    fi
+    
+    log_info "Running: $journal_cmd | grep '\\[PARSE_FAIL\\]'"
+    
+    if [[ "$dry_run" == true ]]; then
+        log_info "[DRY RUN] Would extract to: $output_dir/parse-failures.txt"
+        
+        # Show sample of what would be extracted
+        log_info "Checking for matching log entries..."
+        local sample_count
+        sample_count=$(eval "$journal_cmd" 2>/dev/null | grep -c '\[PARSE_FAIL\]' || echo "0")
+        sample_count="${sample_count//[^0-9]/}"  # Strip non-numeric characters
+        sample_count="${sample_count:-0}"
+        log_info "Found $sample_count matching log entries"
+        
+        if [[ "$sample_count" -eq 0 ]]; then
+            log_warn "No [PARSE_FAIL] entries found in logs."
+            log_warn "This is expected if ngit-grasp logging improvements are not yet deployed."
+            log_warn "See: docs/how-to/migrate-ngit-relay-to-ngit-grasp.md (Dependencies section)"
+        fi
+        
+        exit 0
+    fi
+    
+    # Create output directory
+    mkdir -p "$output_dir"
+    
+    local output_file="$output_dir/parse-failures.txt"
+    local temp_file
+    temp_file=$(mktemp)
+    
+    # Extract and parse log entries
+    log_info "Extracting log entries..."
+    
+    # Get raw log lines containing [PARSE_FAIL]
+    local raw_lines
+    raw_lines=$(eval "$journal_cmd" 2>/dev/null | grep '\[PARSE_FAIL\]' || true)
+    
+    if [[ -z "$raw_lines" ]]; then
+        log_warn "No [PARSE_FAIL] entries found in logs."
+        log_warn ""
+        log_warn "This is expected if ngit-grasp logging improvements are not yet deployed."
+        log_warn "The structured log format required by this script:"
+        log_warn ""
+        log_warn "  [PARSE_FAIL] kind=30618 event_id=abc123 reason=\"...\" repo=myrepo npub=npub1..."
+        log_warn ""
+        log_warn "See: docs/how-to/migrate-ngit-relay-to-ngit-grasp.md (Dependencies section)"
+        log_warn ""
+        
+        # Create empty output file with header comment
+        {
+            echo "# Parse failures extracted from $service"
+            echo "# Time range: ${since_date:-beginning} to ${until_date:-now}"
+            echo "# Extracted: $(date -Iseconds)"
+            echo "# Format: repo<TAB>npub<TAB>kind<TAB>event_id<TAB>reason"
+            echo "#"
+            echo "# NOTE: No [PARSE_FAIL] entries found."
+            echo "# This is expected if ngit-grasp logging improvements are not yet deployed."
+        } > "$output_file"
+        
+        log_info "Created empty output file: $output_file"
+        exit 0
+    fi
+    
+    # Write header
+    {
+        echo "# Parse failures extracted from $service"
+        echo "# Time range: ${since_date:-beginning} to ${until_date:-now}"
+        echo "# Extracted: $(date -Iseconds)"
+        echo "# Format: repo<TAB>npub<TAB>kind<TAB>event_id<TAB>reason"
+    } > "$output_file"
+    
+    # Parse each line
+    local count=0
+    while IFS= read -r line; do
+        local parsed
+        parsed=$(parse_log_line "$line")
+        if [[ -n "$parsed" ]]; then
+            echo "$parsed" >> "$output_file"
+            ((count++))
+        fi
+    done <<< "$raw_lines"
+    
+    rm -f "$temp_file"
+    
+    # Summary
+    echo ""
+    log_info "=== Extraction Summary ==="
+    log_info "Service: $service"
+    log_info "Time range: ${since_date:-beginning} to ${until_date:-now}"
+    log_success "Extracted $count parse failure entries"
+    echo ""
+    log_info "Output file: $output_file"
+    
+    if [[ $count -gt 0 ]]; then
+        echo ""
+        log_info "Sample entries (first 5):"
+        tail -n +5 "$output_file" | head -5 | while IFS=$'\t' read -r repo npub kind event_id reason; do
+            echo "  kind=$kind repo=$repo reason=\"$reason\""
+        done
+    fi
+    
+    # Breakdown by kind
+    if [[ $count -gt 0 ]]; then
+        echo ""
+        log_info "Breakdown by event kind:"
+        tail -n +5 "$output_file" | awk -F'\t' '{print $3}' | sort | uniq -c | sort -rn | while read -r cnt kind; do
+            echo "  kind $kind: $cnt failures"
+        done
+    fi
+}
+
+main "$@"
diff --git a/docs/how-to/migration-scripts/31-extract-purgatory-expiry.sh b/docs/how-to/migration-scripts/31-extract-purgatory-expiry.sh
new file mode 100755
index 0000000..38b2ca3
--- /dev/null
+++ b/docs/how-to/migration-scripts/31-extract-purgatory-expiry.sh
@@ -0,0 +1,346 @@
+#!/usr/bin/env bash
+#
+# 31-extract-purgatory-expiry.sh - Extract purgatory expiry events from systemd logs
+#
+# PHASE 4b of the ngit-relay to ngit-grasp migration analysis pipeline.
+# Extracts structured [PURGATORY_EXPIRED] log entries from journalctl.
+#
+# USAGE:
+#   ./31-extract-purgatory-expiry.sh <service-name> <output-dir> [options]
+#
+# EXAMPLES:
+#   # Extract from ngit-grasp service (last 30 days, default)
+#   ./31-extract-purgatory-expiry.sh ngit-grasp.service output/logs
+#
+#   # Extract with custom time range
+#   ./31-extract-purgatory-expiry.sh ngit-grasp.service output/logs --since "2026-01-01"
+#
+#   # Extract from specific time window
+#   ./31-extract-purgatory-expiry.sh ngit-grasp.service output/logs --since "2026-01-15" --until "2026-01-22"
+#
+# OPTIONS:
+#   --since <date>   Start date for log extraction (default: 30 days ago)
+#   --until <date>   End date for log extraction (default: now)
+#   --dry-run        Show what would be extracted without writing files
+#
+# OUTPUT:
+#   <output-dir>/purgatory-expired.txt
+#
+# OUTPUT FORMAT (TSV):
+#   repo<TAB>npub<TAB>timestamp<TAB>reason
+#
+# EXPECTED LOG FORMAT:
+#   The script looks for structured log entries in this format:
+#
+#   2026-01-22T10:30:45Z ngit-grasp[1234]: [PURGATORY_EXPIRED] repo=myrepo npub=npub1... reason="clone URL unreachable after 7 days"
+#
+#   Required fields: repo, npub
+#   Optional fields: reason (explains why purgatory expired)
+#
+# BACKGROUND:
+#   "Purgatory" is the state where ngit-grasp has received an announcement event
+#   but cannot yet sync the git data (e.g., clone URL unreachable, git server down).
+#   After a configurable timeout (default 7 days), the repository is marked as
+#   expired and removed from purgatory.
+#
+#   Purgatory expiry during migration analysis indicates repositories that:
+#   - Had valid announcements on the production relay
+#   - Could not be synced to the archive relay
+#   - May need manual intervention or investigation
+#
+# DEPENDENCY:
+#   This script requires logging improvements in ngit-grasp to emit structured
+#   [PURGATORY_EXPIRED] log entries. Until those are implemented, this script
+#   will find no matching entries (which is handled gracefully).
+#
+#   See: docs/how-to/migrate-ngit-relay-to-ngit-grasp.md (Dependencies section)
+#
+#   Expected Rust logging code:
+#     tracing::warn!(
+#         target: "migration",
+#         "[PURGATORY_EXPIRED] repo={} npub={} reason=\"{}\"",
+#         identifier, npub, reason
+#     );
+#
+# PREREQUISITES:
+#   - journalctl (systemd)
+#   - grep, awk (standard Unix tools)
+#   - Access to systemd journal (may require sudo or journal group membership)
+#
+# RUNTIME: Depends on log volume, typically < 30 seconds
+#
+# SEE ALSO:
+#   docs/how-to/migrate-ngit-relay-to-ngit-grasp.md - Full migration guide
+#   30-extract-parse-failures.sh - Companion script for parse failure logs
+#
+
+set -euo pipefail
+
+# Colors for output (disabled if not a terminal)
+if [[ -t 1 ]]; then
+    RED='\033[0;31m'
+    GREEN='\033[0;32m'
+    YELLOW='\033[0;33m'
+    BLUE='\033[0;34m'
+    NC='\033[0m'
+else
+    RED=''
+    GREEN=''
+    YELLOW=''
+    BLUE=''
+    NC=''
+fi
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $*" >&2
+}
+
+log_success() {
+    echo -e "${GREEN}[OK]${NC} $*" >&2
+}
+
+log_warn() {
+    echo -e "${YELLOW}[WARN]${NC} $*" >&2
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $*" >&2
+}
+
+usage() {
+    echo "Usage: $0 <service-name> <output-dir> [options]"
+    echo ""
+    echo "Arguments:"
+    echo "  service-name  Systemd service name (e.g., ngit-grasp.service)"
+    echo "  output-dir    Directory to store extracted log data"
+    echo ""
+    echo "Options:"
+    echo "  --since <date>   Start date (default: 30 days ago)"
+    echo "  --until <date>   End date (default: now)"
+    echo "  --dry-run        Show what would be extracted without writing"
+    echo ""
+    echo "Examples:"
+    echo "  $0 ngit-grasp.service output/logs"
+    echo "  $0 ngit-grasp.service output/logs --since '2026-01-01'"
+    echo "  $0 ngit-grasp.service output/logs --since '2026-01-15' --until '2026-01-22'"
+    echo ""
+    echo "Expected log format:"
+    echo "  [PURGATORY_EXPIRED] repo=myrepo npub=npub1... reason=\"...\""
+    exit 1
+}
+
+# Parse a single log line and extract fields
+# Input: log line containing [PURGATORY_EXPIRED]
+# Output: TSV line: repo<TAB>npub<TAB>timestamp<TAB>reason
+parse_log_line() {
+    local line="$1"
+    
+    # Extract timestamp from the beginning of the log line
+    # Format: 2026-01-22T10:30:45+0000 or similar ISO format
+    local timestamp repo npub reason
+    
+    # Extract ISO timestamp from beginning of line
+    timestamp=$(echo "$line" | grep -oP '^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}' || echo "")
+    
+    # Extract repo=VALUE (unquoted identifier)
+    repo=$(echo "$line" | grep -oP 'repo=\K[^ ]+' || echo "")
+    
+    # Extract npub=VALUE (npub1... format)
+    npub=$(echo "$line" | grep -oP 'npub=\K[^ ]+' || echo "")
+    
+    # Extract reason="VALUE" (quoted string, optional)
+    reason=$(echo "$line" | grep -oP 'reason="\K[^"]*' || echo "")
+    
+    # Only output if we have the required fields
+    if [[ -n "$repo" && -n "$npub" ]]; then
+        printf '%s\t%s\t%s\t%s\n' "$repo" "$npub" "$timestamp" "$reason"
+    fi
+}
+
+# Main
+main() {
+    if [[ $# -lt 2 ]]; then
+        usage
+    fi
+    
+    local service="$1"
+    local output_dir="$2"
+    shift 2
+    
+    # Default time range: last 30 days
+    local since_date
+    since_date=$(date -d "30 days ago" "+%Y-%m-%d" 2>/dev/null || date -v-30d "+%Y-%m-%d" 2>/dev/null || echo "")
+    local until_date=""
+    local dry_run=false
+    
+    # Parse options
+    while [[ $# -gt 0 ]]; do
+        case "$1" in
+            --since)
+                since_date="$2"
+                shift 2
+                ;;
+            --until)
+                until_date="$2"
+                shift 2
+                ;;
+            --dry-run)
+                dry_run=true
+                shift
+                ;;
+            *)
+                log_error "Unknown option: $1"
+                usage
+                ;;
+        esac
+    done
+    
+    # Validate service name
+    if [[ ! "$service" =~ \.service$ ]]; then
+        service="${service}.service"
+    fi
+    
+    log_info "Extracting purgatory expiry events from systemd logs"
+    log_info "Service: $service"
+    log_info "Output: $output_dir"
+    log_info "Time range: ${since_date:-beginning} to ${until_date:-now}"
+    
+    # Check if journalctl is available
+    if ! command -v journalctl &> /dev/null; then
+        log_error "journalctl not found. This script requires systemd."
+        exit 1
+    fi
+    
+    # Build journalctl command
+    local journal_cmd="journalctl -u $service --no-pager -o short-iso"
+    
+    if [[ -n "$since_date" ]]; then
+        journal_cmd="$journal_cmd --since '$since_date'"
+    fi
+    
+    if [[ -n "$until_date" ]]; then
+        journal_cmd="$journal_cmd --until '$until_date'"
+    fi
+    
+    log_info "Running: $journal_cmd | grep '\\[PURGATORY_EXPIRED\\]'"
+    
+    if [[ "$dry_run" == true ]]; then
+        log_info "[DRY RUN] Would extract to: $output_dir/purgatory-expired.txt"
+        
+        # Show sample of what would be extracted
+        log_info "Checking for matching log entries..."
+        local sample_count
+        sample_count=$(eval "$journal_cmd" 2>/dev/null | grep -c '\[PURGATORY_EXPIRED\]' || echo "0")
+        sample_count="${sample_count//[^0-9]/}"  # Strip non-numeric characters
+        sample_count="${sample_count:-0}"
+        log_info "Found $sample_count matching log entries"
+        
+        if [[ "$sample_count" -eq 0 ]]; then
+            log_warn "No [PURGATORY_EXPIRED] entries found in logs."
+            log_warn "This is expected if ngit-grasp logging improvements are not yet deployed."
+            log_warn "See: docs/how-to/migrate-ngit-relay-to-ngit-grasp.md (Dependencies section)"
+        fi
+        
+        exit 0
+    fi
+    
+    # Create output directory
+    mkdir -p "$output_dir"
+    
+    local output_file="$output_dir/purgatory-expired.txt"
+    local temp_file
+    temp_file=$(mktemp)
+    
+    # Extract and parse log entries
+    log_info "Extracting log entries..."
+    
+    # Get raw log lines containing [PURGATORY_EXPIRED]
+    local raw_lines
+    raw_lines=$(eval "$journal_cmd" 2>/dev/null | grep '\[PURGATORY_EXPIRED\]' || true)
+    
+    if [[ -z "$raw_lines" ]]; then
+        log_warn "No [PURGATORY_EXPIRED] entries found in logs."
+        log_warn ""
+        log_warn "This is expected if ngit-grasp logging improvements are not yet deployed."
+        log_warn "The structured log format required by this script:"
+        log_warn ""
+        log_warn "  [PURGATORY_EXPIRED] repo=myrepo npub=npub1... reason=\"...\""
+        log_warn ""
+        log_warn "See: docs/how-to/migrate-ngit-relay-to-ngit-grasp.md (Dependencies section)"
+        log_warn ""
+        
+        # Create empty output file with header comment
+        {
+            echo "# Purgatory expiry events extracted from $service"
+            echo "# Time range: ${since_date:-beginning} to ${until_date:-now}"
+            echo "# Extracted: $(date -Iseconds)"
+            echo "# Format: repo<TAB>npub<TAB>timestamp<TAB>reason"
+            echo "#"
+            echo "# NOTE: No [PURGATORY_EXPIRED] entries found."
+            echo "# This is expected if ngit-grasp logging improvements are not yet deployed."
+        } > "$output_file"
+        
+        log_info "Created empty output file: $output_file"
+        exit 0
+    fi
+    
+    # Write header
+    {
+        echo "# Purgatory expiry events extracted from $service"
+        echo "# Time range: ${since_date:-beginning} to ${until_date:-now}"
+        echo "# Extracted: $(date -Iseconds)"
+        echo "# Format: repo<TAB>npub<TAB>timestamp<TAB>reason"
+    } > "$output_file"
+    
+    # Parse each line
+    local count=0
+    while IFS= read -r line; do
+        local parsed
+        parsed=$(parse_log_line "$line")
+        if [[ -n "$parsed" ]]; then
+            echo "$parsed" >> "$output_file"
+            ((count++))
+        fi
+    done <<< "$raw_lines"
+    
+    rm -f "$temp_file"
+    
+    # Summary
+    echo ""
+    log_info "=== Extraction Summary ==="
+    log_info "Service: $service"
+    log_info "Time range: ${since_date:-beginning} to ${until_date:-now}"
+    log_success "Extracted $count purgatory expiry entries"
+    echo ""
+    log_info "Output file: $output_file"
+    
+    if [[ $count -gt 0 ]]; then
+        echo ""
+        log_info "Sample entries (first 5):"
+        tail -n +5 "$output_file" | head -5 | while IFS=$'\t' read -r repo npub timestamp reason; do
+            echo "  repo=$repo npub=${npub:0:20}... timestamp=$timestamp"
+        done
+    fi
+    
+    # Show unique repos affected
+    if [[ $count -gt 0 ]]; then
+        echo ""
+        local unique_repos
+        unique_repos=$(tail -n +5 "$output_file" | awk -F'\t' '{print $1}' | sort -u | wc -l)
+        log_info "Unique repositories affected: $unique_repos"
+        
+        echo ""
+        log_info "Repositories with purgatory expiry:"
+        tail -n +5 "$output_file" | awk -F'\t' '{print $1}' | sort | uniq -c | sort -rn | head -10 | while read -r cnt repo; do
+            echo "  $repo: $cnt expiry events"
+        done
+        
+        local total_repos
+        total_repos=$(tail -n +5 "$output_file" | awk -F'\t' '{print $1}' | sort -u | wc -l)
+        if [[ $total_repos -gt 10 ]]; then
+            echo "  ... and $((total_repos - 10)) more repositories"
+        fi
+    fi
+}
+
+main "$@"