"""Persisted leaderboard rows: the results-CSV schema and its Hugging Face IO.

Kept out of ``app.py`` so the schema has one owner and so the baseline publisher
(``benchmark/public_benchmark/baselines.py``) can append rows without importing
Gradio. ``huggingface_hub`` is imported lazily, so the unit tests touch no
network.

``is_baseline`` marks a reference submission we produced ourselves (a random
embedding, a PCA of log-CPM) rather than a model somebody sent us. Baselines are
ranked in place, never pinned: the point of showing them is that a foundation
model can lose to a PCA, and a row pushed to the bottom of the table would hide
exactly that.

``hf_username`` records who submitted a name, because the board keeps each
name's LATEST rows: without an owner, anyone could supersede another team's
ranked entry by sending a one-task file under their model name. The Submit form
refuses a name somebody else already claimed. It is stored in the PRIVATE
results dataset and never rendered -- it is a lock on the name, not a credit.

Rows written before either column existed carry no column at all, so every
reader goes through ``with_baseline_flag`` and ``with_owner``: a missing or
unparsable flag means "a submitted model", and a missing owner means "unclaimed",
so the first submitter of a legacy name takes it.
"""

import io

import pandas as pd
from evaluator import RESULTS_REPO

RESULTS_FILE = "task_results.csv"
SUBMISSIONS_FILE = "submissions.csv"

MODEL_NAME = "model_name"
IS_BASELINE = "is_baseline"
OWNER = "hf_username"

RESULT_COLUMNS = [MODEL_NAME, "task_id", "score", "submitted_at", IS_BASELINE, OWNER]
SUBMISSION_COLUMNS = [
    MODEL_NAME,
    "submitted_at",
    OWNER,
    "email",
    "paper_link",
    "hf_model_link",
    "notes",
]

TRUTHY = ("true", "1")
BASELINE_TAG = "(baseline)"


def with_baseline_flag(df: pd.DataFrame) -> pd.DataFrame:
    """Guarantee a boolean ``is_baseline`` column, whatever the CSV held.

    Read back from CSV the column can be bool, the strings ``True``/``False``, or
    absent on rows written before baselines existed; all of those must collapse
    to a real boolean before anything ranks on it.
    """
    if IS_BASELINE not in df.columns:
        return df.assign(**{IS_BASELINE: False})
    flags = df[IS_BASELINE].astype(str).str.strip().str.lower().isin(TRUTHY)
    return df.assign(**{IS_BASELINE: flags})


def with_owner(df: pd.DataFrame) -> pd.DataFrame:
    """Guarantee a string ``hf_username`` column; an absent one means unclaimed."""
    if OWNER not in df.columns:
        return df.assign(**{OWNER: ""})
    return df.assign(**{OWNER: df[OWNER].fillna("").astype(str).str.strip()})


def owner_of(df: pd.DataFrame, model: str) -> str:
    """Who claimed this submitted model name, or ``""`` if it is free.

    Baselines are ignored: they live in their own namespace (``is_baseline``), so
    publishing ``pca-50`` never stops somebody submitting a model of that name.
    """
    if df.empty:
        return ""
    claimed = with_owner(with_baseline_flag(df))
    rows = claimed[
        (claimed[MODEL_NAME] == model) & ~claimed[IS_BASELINE] & (claimed[OWNER] != "")
    ]
    return "" if rows.empty else str(rows.iloc[-1][OWNER])


def display_name(model: str, is_baseline: bool) -> str:
    """Leaderboard label: a baseline says so, in the one column everybody reads."""
    return f"{model} {BASELINE_TAG}" if is_baseline else model


def read_csv(filename: str, columns: list[str], token: str | None) -> pd.DataFrame:
    """One CSV from the private results dataset; an absent file is an empty table."""
    from huggingface_hub import hf_hub_download
    from huggingface_hub.utils import EntryNotFoundError, RepositoryNotFoundError

    try:
        path = hf_hub_download(RESULTS_REPO, filename, repo_type="dataset", token=token)
    except (RepositoryNotFoundError, EntryNotFoundError):
        return pd.DataFrame(columns=columns)
    return pd.read_csv(path)


def upload_csv(filename: str, df: pd.DataFrame, token: str | None) -> None:
    """Overwrite one CSV in the private results dataset."""
    from huggingface_hub import HfApi

    api = HfApi(token=token)
    api.create_repo(RESULTS_REPO, repo_type="dataset", private=True, exist_ok=True)
    buffer = io.BytesIO()
    df.to_csv(buffer, index=False)
    buffer.seek(0)
    api.upload_file(
        path_or_fileobj=buffer,
        path_in_repo=filename,
        repo_id=RESULTS_REPO,
        repo_type="dataset",
    )


def read_results(token: str | None) -> pd.DataFrame:
    """Every persisted task score, with the baseline flag and owner normalised."""
    return with_owner(with_baseline_flag(read_csv(RESULTS_FILE, RESULT_COLUMNS, token)))


def append_results(rows: list[dict], token: str | None) -> None:
    """Append scored rows to the leaderboard, keeping the history intact."""
    if not rows:
        return
    df = pd.concat([read_results(token), pd.DataFrame(rows)], ignore_index=True)
    upload_csv(RESULTS_FILE, with_owner(with_baseline_flag(df)), token)


def append_submission(meta: dict, token: str | None) -> None:
    """Persist a submitter's contact metadata, never shown on a public page."""
    df = pd.concat(
        [read_csv(SUBMISSIONS_FILE, SUBMISSION_COLUMNS, token), pd.DataFrame([meta])],
        ignore_index=True,
    )
    upload_csv(SUBMISSIONS_FILE, df, token)