#!/usr/bin/env bash
# nc-smat-diff.sh — diff smat (message archive) content across two environments.
# Different from nc-regression which runs route_test; this just samples actual
# stored messages from each env's smatdb and compares them.
#
# Pairing strategy:
#   By default, sample N most-recent messages from each side, then pair by
#   MSH.10 (message control ID) — the standard HL7 unique identifier.
#   Unmatched IDs are reported as A-only / B-only.
#
# Usage:
#   nc-smat-diff.sh <thread> --env-a HCIROOT_A --env-b HCIROOT_B [opts]
#
# Options:
#   --site-a SITE        site on env-A (default $HCISITE)
#   --site-b SITE        site on env-B (default same as --site-a)
#   --limit N            messages to sample per side (default 50)
#   --ignore FIELDS      hl7-diff --ignore list (default "MSH.7")
#   --out DIR            output directory for per-msg diffs + summary
#   --pair-on FIELD      HL7 field to pair messages on (default MSH.10)
#   --include-history    include SmatHistory archives on both sides
#   --after EXPR         only messages after this time (e.g. "3 days ago")
set -o pipefail

NC_SELF="$0"
LIB_DIR="$(cd "$(dirname "$NC_SELF")" && pwd)"
NCM="$LIB_DIR/nc-msgs.sh"
HL7F="$LIB_DIR/hl7-field.sh"
HL7DIFF="$LIB_DIR/hl7-diff.sh"

die() { printf 'nc-smat-diff: %s\n' "$*" >&2; exit 1; }

THREAD=""
ENV_A=""
ENV_B=""
SITE_A="${HCISITE:-}"
SITE_B=""
LIMIT=50
IGNORE="MSH.7"
OUT=""
PAIR_ON="MSH.10"
INC_HIST=0
AFTER=""

while [ $# -gt 0 ]; do
  case "$1" in
    --env-a)            shift; ENV_A="$1" ;;
    --env-b)            shift; ENV_B="$1" ;;
    --site-a)           shift; SITE_A="$1" ;;
    --site-b)           shift; SITE_B="$1" ;;
    --limit)            shift; LIMIT="$1" ;;
    --ignore)           shift; IGNORE="$1" ;;
    --out)              shift; OUT="$1" ;;
    --pair-on)          shift; PAIR_ON="$1" ;;
    --include-history)  INC_HIST=1 ;;
    --after)            shift; AFTER="$1" ;;
    -h|--help)          sed -n '2,22p' "$NC_SELF"; exit 0 ;;
    -*)                 die "unknown flag: $1" ;;
    *)                  [ -z "$THREAD" ] && THREAD="$1" || die "extra arg: $1" ;;
  esac
  shift
done

[ -n "$THREAD" ] || die "missing thread name"
[ -n "$ENV_A" ] && [ -n "$ENV_B" ] || die "--env-a and --env-b required"
[ -n "$SITE_A" ] || die "--site-a required (or set HCISITE)"
[ -z "$SITE_B" ] && SITE_B="$SITE_A"
[ -z "$OUT" ] && OUT=$(mktemp -d)
mkdir -p "$OUT/a" "$OUT/b" "$OUT/diff" 2>/dev/null

dump_side() {
  local hciroot="$1" site="$2" target_dir="$3"
  local nc_args=("$THREAD" --limit "$LIMIT" --format raw)
  [ "$INC_HIST" = "1" ] && nc_args+=(--include-history)
  [ -n "$AFTER" ] && nc_args+=(--after "$AFTER")
  HCISITEDIR="$hciroot/$site" "$NCM" "${nc_args[@]}" > "$target_dir/all.raw" 2>"$target_dir/err"

  # Split into individual messages on 0x1c, and index by pair-on field
  awk -v RS=$'\x1c' -v dir="$target_dir" '
    NF > 0 || $0 != "" {
      n++
      fpath = dir "/msg_" sprintf("%05d", n) ".hl7"
      printf "%s", $0 > fpath
      close(fpath)
    }
  ' "$target_dir/all.raw"

  # Build pair-on-field → file index
  : > "$target_dir/index.tsv"
  for f in "$target_dir"/msg_*.hl7; do
    [ -f "$f" ] || continue
    local key; key=$("$HL7F" "$PAIR_ON" "$f" 2>/dev/null | head -1)
    [ -z "$key" ] && key="(no-$PAIR_ON)"
    printf '%s\t%s\n' "$key" "$f" >> "$target_dir/index.tsv"
  done
}

printf 'nc-smat-diff:\n  thread: %s\n  A: %s/%s\n  B: %s/%s\n  limit: %d  ignore: %s  pair-on: %s\n  out: %s\n\n' \
  "$THREAD" "$ENV_A" "$SITE_A" "$ENV_B" "$SITE_B" "$LIMIT" "$IGNORE" "$PAIR_ON" "$OUT" >&2

dump_side "$ENV_A" "$SITE_A" "$OUT/a"
dump_side "$ENV_B" "$SITE_B" "$OUT/b"

A_COUNT=$(wc -l < "$OUT/a/index.tsv" | tr -d ' ')
B_COUNT=$(wc -l < "$OUT/b/index.tsv" | tr -d ' ')
printf 'A: %d msgs   B: %d msgs\n\n' "$A_COUNT" "$B_COUNT" >&2

# Pair messages by key
sort -k1 "$OUT/a/index.tsv" > "$OUT/a/sorted.tsv"
sort -k1 "$OUT/b/index.tsv" > "$OUT/b/sorted.tsv"
A_KEYS=$(awk -F'\t' '{print $1}' "$OUT/a/sorted.tsv" | sort -u)
B_KEYS=$(awk -F'\t' '{print $1}' "$OUT/b/sorted.tsv" | sort -u)

SUMMARY="$OUT/_summary.md"
{
  printf '# smat diff: thread=%s\n\n' "$THREAD"
  printf '- A: `%s/%s`  (%d messages sampled)\n' "$ENV_A" "$SITE_A" "$A_COUNT"
  printf '- B: `%s/%s`  (%d messages sampled)\n' "$ENV_B" "$SITE_B" "$B_COUNT"
  printf '- pair-on: `%s`\n' "$PAIR_ON"
  printf '- ignore: `%s`\n\n' "$IGNORE"
  printf '## Per-pair diffs\n\n'
  printf '| %s | diffs | report |\n|---|---|---|\n' "$PAIR_ON"
} > "$SUMMARY"

DIFFS_TOTAL=0
A_ONLY=0
B_ONLY=0
PAIRED=0
while IFS= read -r key; do
  [ -z "$key" ] && continue
  a_files=$(grep -F "${key}	" "$OUT/a/sorted.tsv" | awk -F'\t' '{print $2}' | head -1)
  b_files=$(grep -F "${key}	" "$OUT/b/sorted.tsv" | awk -F'\t' '{print $2}' | head -1)
  if [ -z "$a_files" ] && [ -n "$b_files" ]; then
    B_ONLY=$((B_ONLY+1))
    echo "| \`$key\` | (only on B) | — |" >> "$SUMMARY"
  elif [ -z "$b_files" ] && [ -n "$a_files" ]; then
    A_ONLY=$((A_ONLY+1))
    echo "| \`$key\` | (only on A) | — |" >> "$SUMMARY"
  else
    PAIRED=$((PAIRED+1))
    report="$OUT/diff/${key//\//_}.md"
    cnt=$("$HL7DIFF" --ignore "$IGNORE" --format count "$a_files" "$b_files" 2>/dev/null || echo "?")
    {
      printf '# msg %s\n\nA: `%s`\nB: `%s`\n\n' "$key" "$a_files" "$b_files"
      "$HL7DIFF" --ignore "$IGNORE" "$a_files" "$b_files" 2>/dev/null
    } > "$report"
    echo "| \`$key\` | $cnt | [report](./diff/$(basename "$report")) |" >> "$SUMMARY"
    DIFFS_TOTAL=$((DIFFS_TOTAL + ${cnt:-0}))
  fi
done < <(printf '%s\n%s\n' "$A_KEYS" "$B_KEYS" | sort -u)

{
  printf '\n## Summary\n\n'
  printf '- paired (A and B): %d\n' "$PAIRED"
  printf '- A-only: %d\n' "$A_ONLY"
  printf '- B-only: %d\n' "$B_ONLY"
  printf '- total field differences (post-ignore): %d\n' "$DIFFS_TOTAL"
} >> "$SUMMARY"

printf 'done. Summary: %s\n' "$SUMMARY" >&2
echo "$SUMMARY"