#!/usr/bin/env python3
"""list_files.py <corpus_dir>: print the files the sweep probes, one per line,
as <corpus>/<path> in byte order.

  * every file named *.h5 *.hdf5 *.he5 *.nc *.nc4 *.hdf *.h5f in each corpus,
    except netCDF classic / 64-bit-offset / CDF5 files (magic "CDF"): they are
    not HDF5, so neither side can read them and they say nothing;
  * plus, for cve_hdf5, every file in cvefiles/ and fuzzerfiles/ except
    .md/.c sources — the reproducers are mostly extension-less, and they are
    kept whatever their bytes look like (that is their point).
"""
import os
import sys

EXTS = (".h5", ".hdf5", ".he5", ".nc", ".nc4", ".hdf", ".h5f")


def walk(top):
    for dirpath, dirnames, filenames in os.walk(top):
        dirnames[:] = [d for d in dirnames if d != ".git"]
        for fn in filenames:
            p = os.path.join(dirpath, fn)
            if os.path.isfile(p) and not os.path.islink(p):
                yield os.path.relpath(p, top)


def main(root):
    out = set()
    for corpus in sorted(os.listdir(root)):
        top = os.path.join(root, corpus)
        if not os.path.isdir(top):
            continue
        for rel in walk(top):
            path = os.path.join(top, rel)
            if rel.lower().endswith(EXTS):
                with open(path, "rb") as fh:
                    if fh.read(3) == b"CDF":
                        continue
                out.add(f"{corpus}/{rel}")
            elif corpus == "cve_hdf5" and rel.split(os.sep)[0] in ("cvefiles", "fuzzerfiles") \
                    and not rel.endswith((".md", ".c")):
                out.add(f"{corpus}/{rel}")
    for f in sorted(out, key=lambda s: s.encode()):
        print(f)


if __name__ == "__main__":
    main(sys.argv[1])