shopdb-flask/scripts/reconcile_locations.py

"""Generate reconciliation SQL for the locations table.

Reads a TSV export (locationid, locationname, description, locationtypeid,
parentlocationid) and emits a single transaction-wrapped SQL script that:
  - Treats bare grid coordinates ([A-V][0-9]{1,2}W? and LD[0-9]+W?) as the
    canonical identity for a cell.
  - Folds coordinate-plus-suffix rows into the canonical coordinate, moving the
    suffix text into the canonical row's description (never the name).
  - Folds named-area suffix variants ("NDE - 6409") into the parent named area
    ("NDE"); named areas are kept as-is and never forced into coordinates.
  - Repoints assets.locationid, subnets.locationid and child
    locations.parentlocationid onto the canonical row, then deletes duplicates.

Bare coordinates with no variants are left untouched. The trailing W (west
column, e.g. G2W, K3W) is part of the coordinate and is never stripped, so
G2W is kept distinct from a hypothetical G2.
"""
import re
import sys

COORD = re.compile(r'^(LD|[ABCDEFGHJKLMNPQRSTUV])(\d{1,2})(W)?(?=$|[ \-])')


def esc(s):
    return s.replace("'", "''")


def load(path):
    rows = []
    with open(path, encoding='utf-8-sig') as fh:
        for line in fh:
            line = line.rstrip('\n').rstrip('\r')
            if not line:
                continue
            parts = line.split('\t')
            if len(parts) < 5:
                parts += [''] * (5 - len(parts))
            lid, name, desc, typeid, parentid = parts[:5]
            rows.append({
                'id': int(lid),
                'name': name,
                'desc': desc,
                'typeid': typeid,
                'parentid': parentid,
            })
    return rows


def classify(name):
    """Return (canonical, suffix). canonical is the bare coordinate or named
    parent; suffix is the trailing detail (may be '')."""
    m = COORD.match(name)
    if m:
        prefix, digits, west = m.group(1), m.group(2), m.group(3) or ''
        canonical = f"{prefix}{digits}{west}"
        suffix = name[m.end():].strip()
        suffix = re.sub(r'^[\-\s]+', '', suffix).strip()
        return canonical, suffix, 'coord'
    # named area: fold on ' - ' separator only
    if ' - ' in name:
        base, _, rest = name.partition(' - ')
        return base.strip(), rest.strip(), 'named'
    return name.strip(), '', 'named'


def main(tsv, out):
    rows = load(tsv)

    # Build canonical groups. Key is casefolded canonical for grouping, but we
    # preserve a display canonical (prefer an existing exact bare/standalone).
    groups = {}
    for r in rows:
        canonical, suffix, kind = classify(r['name'])
        key = (kind, canonical.casefold())
        g = groups.setdefault(key, {
            'canonical': canonical,
            'kind': kind,
            'members': [],
            'exact_id': None,
        })
        r['_suffix'] = suffix
        r['_canonical'] = canonical
        g['members'].append(r)
        # exact row: name equals canonical (no suffix)
        if suffix == '' and r['name'].strip() == canonical:
            g['exact_id'] = r['id']
            g['canonical'] = r['name'].strip()

    lines = []
    lines.append('-- Auto-generated locations reconciliation. Review before running.')
    lines.append('START TRANSACTION;')

    touched = 0
    for key, g in sorted(groups.items(), key=lambda kv: kv[0][1]):
        members = sorted(g['members'], key=lambda r: r['id'])
        # nothing to do: single member that is already the exact canonical
        if len(members) == 1 and g['exact_id'] == members[0]['id']:
            continue
        touched += 1
        canonical = g['canonical']

        # choose target id: prefer exact bare row, else promote smallest id
        if g['exact_id'] is not None:
            target = g['exact_id']
            promote = None
        else:
            target = members[0]['id']
            promote = members[0]

        # accumulate suffix/description text from all members (dedup, ordered)
        details = []
        for m in members:
            for chunk in (m['_suffix'], m['desc']):
                chunk = (chunk or '').strip()
                if chunk and chunk not in details:
                    details.append(chunk)
        desc_val = '; '.join(details)

        lines.append('')
        lines.append(f"-- {canonical}  (target locationid {target}) <= "
                     + ', '.join(str(m['id']) for m in members))
        if promote is not None:
            lines.append(
                f"UPDATE locations SET locationname='{esc(canonical)}' "
                f"WHERE locationid={target};")
        if desc_val:
            lines.append(
                f"UPDATE locations SET description='{esc(desc_val)}' "
                f"WHERE locationid={target};")

        others = [m['id'] for m in members if m['id'] != target]
        if others:
            ids = ','.join(str(i) for i in others)
            lines.append(
                f"UPDATE assets SET locationid={target} "
                f"WHERE locationid IN ({ids});")
            lines.append(
                f"UPDATE subnets SET locationid={target} "
                f"WHERE locationid IN ({ids});")
            lines.append(
                f"UPDATE locations SET parentlocationid={target} "
                f"WHERE parentlocationid IN ({ids});")
            lines.append(
                f"DELETE FROM locations WHERE locationid IN ({ids});")

    lines.append('')
    lines.append('COMMIT;')
    lines.append(f'-- groups touched: {touched}')

    with open(out, 'w', encoding='utf-8') as fh:
        fh.write('\n'.join(lines) + '\n')
    print(f'wrote {out}: {touched} groups touched, {len(rows)} source rows')


if __name__ == '__main__':
    main(sys.argv[1], sys.argv[2])