erp/.claude/skills/arcodange-email-ingest/scripts/email-list.sh

#!/usr/bin/env bash
# List candidate supplier-invoice emails from the books@ Zoho mailbox.
#
# Usage:
#   email-list.sh [--folder PATH]      # default: /Inbox/books (the books@ alias-filtered folder)
#                 [--limit N]          # default: 30
#                 [--candidates-only]  # filter by subject pattern OR attachment
#                 [--all-folders]      # scan every folder (slow, lots of API calls)
#
# Output: table with mid, date, from, subject, hasAttachment.
# A "candidate" is a message whose subject matches a supplier-like pattern
# (facture/invoice/receipt/reçu/payment/paiement/abonnement/order/commande)
# OR which has an attachment.

set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ZOHO_CURL="${SCRIPT_DIR}/zoho-curl.sh"

FOLDER="/Inbox/books"
LIMIT=30
CANDIDATES_ONLY=0
ALL_FOLDERS=0
while [[ $# -gt 0 ]]; do
  case "$1" in
    --folder)           FOLDER="$2"; shift 2 ;;
    --limit)            LIMIT="$2"; shift 2 ;;
    --candidates-only)  CANDIDATES_ONLY=1; shift ;;
    --all-folders)      ALL_FOLDERS=1; shift ;;
    -h|--help)          sed -n '2,12p' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
    *) echo "email-list.sh: unknown arg: $1" >&2; exit 2 ;;
  esac
done

WORK="$(mktemp -d -t emailist.XXXXXX)"
trap 'rm -rf "${WORK}"' EXIT

# 1. Discover accountId
"${ZOHO_CURL}" /accounts > "${WORK}/accounts.json"
AID=$(python3 -c "import json,sys; d=json.load(open(sys.argv[1])); print((d.get('data') or [{}])[0].get('accountId',''))" "${WORK}/accounts.json")
[[ -z "${AID}" ]] && { echo "email-list.sh: no accountId in /accounts response" >&2; exit 1; }

# 2. Resolve folder path → folderId
"${ZOHO_CURL}" "/accounts/${AID}/folders" > "${WORK}/folders.json"

# Build list of (folderId, path) tuples to scan
if [[ "${ALL_FOLDERS}" == "1" ]]; then
  FOLDER_IDS=$(python3 -c "
import json, sys
d = json.load(open(sys.argv[1]))
for f in (d.get('data') or []):
    fid = f.get('folderId'); path = f.get('path') or f.get('folderName','-')
    # Skip noisy system folders
    if path in ('/Drafts','/Templates','/Snoozed','/Sent','/Spam','/Trash','/Outbox'): continue
    print(f\"{fid}|{path}\")" "${WORK}/folders.json")
else
  FOLDER_IDS=$(python3 -c "
import json, sys
d = json.load(open(sys.argv[1]))
target = sys.argv[2]
for f in (d.get('data') or []):
    if f.get('path') == target:
        print(f\"{f.get('folderId')}|{f.get('path')}\")
        break" "${WORK}/folders.json" "${FOLDER}")
  if [[ -z "${FOLDER_IDS}" ]]; then
    echo "email-list.sh: folder '${FOLDER}' not found. Available:" >&2
    python3 -c "import json,sys; [print(f'  {f.get(\"path\",\"-\")}') for f in json.load(open(sys.argv[1])).get('data',[])]" "${WORK}/folders.json" >&2
    exit 2
  fi
fi

# 3. Fetch messages per folder
mkdir -p "${WORK}/msgs"
COUNT=0
while IFS='|' read -r fid fpath; do
  [[ -z "${fid}" ]] && continue
  COUNT=$((COUNT+1))
  out="${WORK}/msgs/$(printf '%03d' "${COUNT}").json"
  "${ZOHO_CURL}" "/accounts/${AID}/messages/view?folderId=${fid}&limit=${LIMIT}&sortorder=false&start=1" > "${out}" 2>/dev/null || echo '{"data":[]}' > "${out}"
  echo "${fpath}" > "${out}.path"
done <<< "${FOLDER_IDS}"

# 4. Render
python3 - "${WORK}/msgs" "${CANDIDATES_ONLY}" <<'PY'
import json, sys, os, re, datetime, glob
msgs_dir, candidates_only_str = sys.argv[1:3]
candidates_only = candidates_only_str == "1"

CANDIDATE_PATTERN = re.compile(
    r'facture|invoice|receipt|re[cç]u|payment|paiement|abonnement|subscription|order|commande|invoice|bill',
    re.IGNORECASE,
)

# Subjects that look like calendar invites / event updates / generic notifications
# get filtered out of --candidates-only — they always have a .ics attachment so
# the "has-attachment" heuristic alone catches them as false positives.
EXCLUDE_PATTERN = re.compile(
    r'^(?:re:\s*|fwd:\s*|tr:\s*)*'                       # strip Re:/Fwd:/Tr: prefixes
    r'(?:invitation|updated\s+invitation|canceled\s+event|accepted|declined|tentative|maybe)\s*:',
    re.IGNORECASE,
)

# Senders that are pure noise — newsletter/marketing patterns.
EXCLUDE_SENDER = re.compile(
    r'(updates\.|noreply@.*calendar|@calendar\.|news@|newsletter@|@updates\.)',
    re.IGNORECASE,
)

def is_candidate(m):
    subj   = m.get("subject","") or ""
    sender = m.get("fromAddress","") or m.get("sender","") or ""
    # Hard exclusions take precedence over inclusions
    if EXCLUDE_PATTERN.match(subj.strip()): return False
    if EXCLUDE_SENDER.search(sender): return False
    if str(m.get("hasAttachment","")) == "1": return True
    if CANDIDATE_PATTERN.search(subj): return True
    return False

rows = []
for f in sorted(glob.glob(os.path.join(msgs_dir, "*.json"))):
    fpath = open(f + ".path").read().strip()
    try: data = json.load(open(f)).get("data") or []
    except: continue
    for m in data:
        if candidates_only and not is_candidate(m): continue
        ts = int(m.get("sentDateInGMT") or m.get("receivedTime") or 0) // 1000
        dt = datetime.datetime.fromtimestamp(ts).strftime("%Y-%m-%d") if ts else "-"
        frm = (m.get("fromAddress") or m.get("sender") or "-").replace("&lt;","<").replace("&gt;",">").replace("<","").replace(">","")[:36]
        subj = (m.get("subject") or "-")[:55]
        has = "Y" if str(m.get("hasAttachment","")) == "1" else " "
        cand = "*" if is_candidate(m) else " "
        rows.append((dt, fpath, cand, has, m.get("messageId","-"), frm, subj))

rows.sort(key=lambda r: r[0], reverse=True)
print(f"{'date':<10}  {'cand':<4} {'att':<3} {'messageId':<22}  {'folder':<22}  {'from':<36}  subject")
print("-" * 130)
for dt, fpath, cand, has, mid, frm, subj in rows:
    print(f"{dt:<10}  [{cand}]  [{has}]  {mid:<22}  {fpath[:22]:<22}  {frm:<36}  {subj}")
print("-" * 130)
print(f"# {len(rows)} message(s)" + (" (candidates only)" if candidates_only else ""))
PY