#!/usr/bin/env python3
"""Which .xpr package holds each effect the datasheets bind.

Effect names are matched EXACTLY, not as substrings: Base.xpr contains
eff_f0002_barnhaze, so a substring test for "eff_f0002" reports a false hit for
a resource that is not there. Names are pulled as maximal [A-Za-z0-9_] runs
containing "eff_", which yields whole resource names -- 268 of ptc_pack's 727
carry an EF_IDX_ prefix, so a pattern anchored at "eff_" would truncate them and
silently merge distinct names. A bound name is looked up bare AND under that
prefix.

Regenerates docs/re/data/effect-homes.txt.
"""
import glob, os, re, subprocess, sys, collections
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from unit_substructures import pak_entries
import unitgroup as U

XPR = '/work/sylph_extract/hidden/resource3d'
FX = re.compile(r'(FxModel|EffectName|Effect_|ShellModel|CoverModel)')

def width(n):
    m = re.match(r'eff_[a-z](\d+)', n)
    return len(m.group(1)) if m else 0

def main():
    if not os.path.isdir(XPR):
        print('disc not mounted; nothing to do'); return
    home = collections.defaultdict(set)
    for path in sorted(glob.glob(os.path.join(XPR, '*.xpr'))):
        out = subprocess.run(['grep', '-o', '-a', '[A-Za-z0-9_]*eff_[A-Za-z0-9_]*', path],
                             capture_output=True, text=True, errors='replace').stdout
        for name in set(out.split()):
            home[name].add(os.path.basename(path))

    bound = set()
    for pk in sorted(glob.glob('/work/sylph_extract/**/*.pak', recursive=True)):
        for _h, b in pak_entries(pk):
            if b[:4] != b'IDXD':
                continue
            try:
                recs = U.parse(b)
            except Exception:
                continue
            for r in recs:
                for _t, f, v in r['fields']:
                    if f and FX.search(f) and isinstance(v, str) and v.startswith('eff_'):
                        bound.add(v)

    # a name may be stored bare or under the EF_IDX_ index prefix
    def where(n):
        return home.get(n, set()) | home.get('EF_IDX_' + n, set())

    res = sorted(n for n in bound if where(n))
    un = sorted(n for n in bound if not where(n))
    print('effect names bound by a datasheet field : %d' % len(bound))
    print('resolved to an .xpr package (exact name): %d' % len(res))
    print('unlocated                               : %d' % len(un))
    print()
    per = collections.Counter()
    for n in res:
        for f in where(n):
            per[f] += 1
    print('resolved, by package:')
    for f, k in sorted(per.items(), key=lambda kv: (-kv[1], kv[0])):
        print('   %-26s %d' % (f, k))
    print()
    print('by digit-width:')
    for k in (3, 4, 0):
        s = [n for n in bound if width(n) == k]
        if s:
            print('   %d-digit: %d resolved of %d' % (k, len([n for n in s if where(n)]), len(s)))
    print()
    print('the %d unlocated, in full:' % len(un))
    for n in un:
        print('   %s' % n)

if __name__ == '__main__':
    main()