#!/usr/bin/env python3
import sys
import csv
from collections import defaultdict

"""
Usage:
  python transform_coverage.py old.txt new.txt

Where:
  old.txt, new.txt each line looks like:
    C4,M1,M2
    C1,SA1,SA2
  etc.

We parse the first token as coverage name (e.g. 'C4'),
the rest as element names (e.g. 'M1','M2').
We store them in a dictionary keyed by the sorted tuple of elements.

Then we produce a transform table:
  old_coverage -> new_coverage
for each matching element-tuple.
If multiple old coverages map to the same new coverage or vice versa,
we show those collisions or many-to-many relationships explicitly.
"""

def parse_cutset_file(filename):
    """
    Parse lines like "C4,M1,M2" into:
      coverage='C4'
      elements=('M1','M2')  # sorted
    We'll store coverage -> set of element_tuples
    We'll also store element_tuple -> coverage
    Returns (coverage2sets, element2cov)
    """
    coverage2sets = defaultdict(set)   # coverage -> { (el1,el2,...) , ... }
    element2cov = {}
    with open(filename, "r", encoding="utf-8") as f:
        for line in f:
            line=line.strip()
            if not line or line.startswith("#"):
                continue
            # split by comma
            parts = [x.strip() for x in line.split(",")]
            coverage = parts[0]
            elements = parts[1:]
            # sort elements so (M1,M2) == (M2,M1)
            sorted_e = tuple(sorted(elements))
            coverage2sets[coverage].add(sorted_e)
            element2cov[sorted_e] = coverage
    return coverage2sets, element2cov

def main(oldfile, newfile):
    old_cov2sets, old_elem2cov = parse_cutset_file(oldfile)
    new_cov2sets, new_elem2cov = parse_cutset_file(newfile)

    # We'll create a transform table: oldCov -> newCov
    # by checking each element tuple in old
    # and see what coverage is assigned in new.
    transform_map = defaultdict(set)  
    # key=oldCoverageName, value=set of newCoverageNames
    # Because it's possible multiple new coverages appear.

    # Also track if some old coverage references multiple distinct new coverage
    # or vice versa.

    # all element tuples from old
    for etuple, oldcov in old_elem2cov.items():
        if etuple in new_elem2cov:
            newcov = new_elem2cov[etuple]
            transform_map[oldcov].add(newcov)
        else:
            # no match in new => discrepancy
            transform_map[oldcov].add("NO_MATCH_IN_NEW")

    # Now produce a nice table
    print("=== Coverage transform table ===")
    for oldcov in sorted(transform_map.keys()):
        newcovs = transform_map[oldcov]
        if len(newcovs)==1:
            single = list(newcovs)[0]
            if single=="NO_MATCH_IN_NEW":
                print(f"{oldcov} => [NO MATCH in NEW file!]")
            else:
                print(f"{oldcov} => {single}")
        else:
            # multiple new coverages
            nclist = ",".join(sorted(newcovs))
            print(f"{oldcov} => {{{nclist}}}  # multiple new coverage found for same old coverage")

    print()
    print("=== Reverse check: new coverage => old coverage ===")
    # We'll do similarly in reverse
    # create new_elem2cov from parse => done
    # but we want coverage -> set of element tuples
    rev_map = defaultdict(set)  # new-> old coverage
    for etuple, newcov in new_elem2cov.items():
        if etuple in old_elem2cov:
            oldcov = old_elem2cov[etuple]
            rev_map[newcov].add(oldcov)
        else:
            rev_map[newcov].add("NO_MATCH_IN_OLD")

    for newcov in sorted(rev_map.keys()):
        oldcovs = rev_map[newcov]
        if len(oldcovs)==1:
            single = list(oldcovs)[0]
            if single=="NO_MATCH_IN_OLD":
                print(f"{newcov} => [NO MATCH in OLD file!]")
            else:
                print(f"{newcov} => {single}")
        else:
            # multiple old coverage
            oclist = ",".join(sorted(oldcovs))
            print(f"{newcov} => {{{oclist}}}  # multiple old coverage found for same new coverage")

    print()
    print("=== Detailed mismatch check (cutset by cutset) ===")
    # We'll unify the union of all element tuples
    all_etups = set(list(old_elem2cov.keys())+ list(new_elem2cov.keys()))
    for et in sorted(all_etups):
        ocov = old_elem2cov.get(et,"-")
        ncov = new_elem2cov.get(et,"-")
        elements_str = ",".join(et)
        print(f"Cutset({elements_str}): old={ocov} , new={ncov}")

if __name__=="__main__":
    if len(sys.argv)<3:
        print("Usage: python transform_coverage.py old.txt new.txt")
        sys.exit(0)
    oldfile=sys.argv[1]
    newfile=sys.argv[2]
    main(oldfile,newfile)