"""Where every file of a processed session lives.

The scripts used to sit inside the data directory and address it with absolute
paths. Now that they live in a repository and the data is organised into named
subdirectories, they need one place that knows the mapping - this module.

Two rules make it work:

* The session root comes from the ASTRO_SESSION environment variable, so the
  same code runs against any session without editing. It falls back to the
  NGC 5128 session these scripts were written against.
* A file's subdirectory is derived from its NAME, using the same rules the
  directory was organised with. That means a script can go on asking for
  "master-Red.fit" or "_stars.npz" and get the right path, without every call
  site having to learn the layout.

Anything unrecognised lands at the session root, which is visible and easy to
correct rather than silently wrong.
"""
import os

SESSION = os.environ.get(
    "ASTRO_SESSION",
    r"C:\Users\lhorrocks-barlow\Downloads\NGC5128\20260721")

# Subdirectories, also created on demand by path().
RAW = "raw"
CALIBRATED = "calibrated"
MASTERS = os.path.join("stacks", "masters")
ORIGINAL = os.path.join("stacks", "original")
FINAL = "final"
RENDERINGS = "renderings"
FIGURES = os.path.join("science", "figures")
CATALOGUES = os.path.join("science", "catalogues")
SCIENCE_DATA = os.path.join("science", "data")
NOTES = os.path.join("science", "notes")
INTERMEDIATES = "intermediates"

# Names that are directories in their own right, not files.
_DIRS = {"final": FINAL, "original": ORIGINAL, "raw": RAW,
         "calibrated": CALIBRATED, "renderings": RENDERINGS,
         "_dss": os.path.join(INTERMEDIATES, "_dss")}


def subdir(name):
    """The subdirectory a given filename belongs in."""
    low = name.lower()
    if name in _DIRS:
        return _DIRS[name]
    if name.startswith("_"):
        return INTERMEDIATES
    if low.endswith(".zip") or (low.startswith("jpeg-") and
                                low.endswith(".jpg")):
        return RAW
    if low.startswith("calibrated-") and low.endswith((".fit", ".tif")):
        return CALIBRATED
    if low.startswith("raw-") and low.endswith((".fit", ".tif")):
        return RAW
    if low.startswith("master-") and low.endswith(".fit"):
        return MASTERS
    if low.startswith("original-"):
        return ORIGINAL
    if "final" in low and low.endswith((".png", ".tif", ".jpg")):
        return FINAL
    if low.startswith("notes-") and low.endswith(".md"):
        return NOTES
    if low.endswith(".csv"):
        return CATALOGUES
    if low.startswith("sb-") and low.endswith((".fits", ".npy", ".txt")):
        return SCIENCE_DATA
    if low.endswith(".png") and any(f"-{p}-" in low for p in ("gc", "sb", "mo")):
        return FIGURES
    if low.startswith(("ngc5128-lrgb", "ngc5128-img-")):
        return RENDERINGS
    if low.endswith(".md"):
        return ""
    return ""


def path(*parts, make=True):
    """Absolute path for a session file, addressed by name alone.

    Extra leading components are accepted and ignored, so calls written
    against the old flat layout - path("stacked", "_stars.npz") - still land
    correctly. The last component is the one that decides.
    """
    name = parts[-1]
    if name in _DIRS:
        # Asking for a directory by name returns the directory itself, not a
        # file of that name nested inside it.
        full = os.path.join(SESSION, _DIRS[name])
        if make:
            os.makedirs(full, exist_ok=True)
        return full
    full = os.path.join(SESSION, subdir(name), name)
    if make:
        os.makedirs(os.path.dirname(full), exist_ok=True)
    return full


def describe():
    lines = [f"session root: {SESSION}"]
    for label, d in (("raw", RAW), ("calibrated", CALIBRATED),
                     ("masters", MASTERS), ("original stacks", ORIGINAL),
                     ("final images", FINAL), ("other renderings", RENDERINGS),
                     ("science figures", FIGURES),
                     ("science catalogues", CATALOGUES),
                     ("science data", SCIENCE_DATA), ("notes", NOTES),
                     ("intermediates", INTERMEDIATES)):
        lines.append(f"  {label:20s} {d}")
    return "\n".join(lines)


if __name__ == "__main__":
    print(describe())