"""Признаки, специфичные для игровых реплик и разговорной речи."""

from __future__ import annotations

import re

import pandas as pd

from ..lexicons import (
    CONTRACTIONS,
    DISCOURSE_MARKERS,
    HEDGES,
    INTENSIFIERS,
    INTERJECTIONS,
    NEGATIONS,
    POLITENESS,
)
from .base import as_list, safe_div, word_tokens

_LAUGHTER_RE = re.compile(r"\b(?:ha){2,}\b|\bhehe\b|\bhaha\b|\blol\b", re.IGNORECASE)
_EMOTION_WORDS = {
    "love", "hate", "like", "want", "feel", "think", "know", "happy",
    "sad", "angry", "afraid", "scared", "excited", "worried", "glad",
    "sorry", "hope", "wish", "miss", "enjoy", "fun", "nice", "good",
    "bad", "terrible", "awful", "great", "wonderful",
}


def extract(row: pd.Series) -> dict[str, float]:
    text = str(row.get("text", ""))
    tokens = [str(token).lower() for token in as_list(row, "tokens")]
    words = word_tokens(tokens)
    n_words = max(len(words), 1)
    sentences = as_list(row, "sentences")
    n_sentences = max(len(sentences), 1)
    alphabetic = [token for token in tokens if re.search(r"[A-Za-z]", token)]
    n_alpha = max(len(alphabetic), 1)
    ellipsis = len(re.findall(r"\.{3,}", text))
    repeated = len(re.findall(r"[!?]{2,}", text))

    return {
        "dlg_placeholder_rate": safe_div(float(row.get("placeholder_count", 0)), n_words),
        "dlg_all_caps_rate": safe_div(
            sum(1 for token in alphabetic if len(token) > 1 and token.isupper()), n_alpha
        ),
        "dlg_ellipsis_rate": safe_div(ellipsis, n_sentences),
        "dlg_repeated_punctuation_rate": safe_div(repeated, n_sentences),
        "dlg_interjection_rate": safe_div(
            sum(1 for token in tokens if token in INTERJECTIONS), n_words
        ),
        "dlg_laughter_rate": safe_div(len(_LAUGHTER_RE.findall(text)), n_sentences),
        "dlg_discourse_marker_rate": safe_div(
            sum(1 for token in tokens if token in DISCOURSE_MARKERS), n_words
        ),
        "dlg_hedge_rate": safe_div(
            sum(1 for token in tokens if token in HEDGES), n_words
        ),
        "dlg_intensifier_rate": safe_div(
            sum(1 for token in tokens if token in INTENSIFIERS), n_words
        ),
        "dlg_politeness_rate": safe_div(
            sum(1 for token in tokens if token in POLITENESS), n_words
        ),
        "dlg_negation_rate": safe_div(
            sum(1 for token in tokens if token in NEGATIONS), n_words
        ),
        "dlg_contraction_rate": safe_div(
            sum(1 for token in tokens if token in CONTRACTIONS or "'" in token), n_words
        ),
        "dlg_question_tag_rate": safe_div(
            len(
                re.findall(
                    r"\b(?:right|isn't it|aren't you|don't you|didn't you|huh)\s*[?.!]?\s*$",
                    text,
                    flags=re.IGNORECASE,
                )
            ),
            n_sentences,
        ),
        "dlg_filler_rate": safe_div(
            sum(1 for token in tokens if token in {"um", "uh", "hmm", "mmm", "eh"}), n_words
        ),
        "dlg_emotion_word_rate": safe_div(
            sum(1 for token in tokens if token in _EMOTION_WORDS), n_words
        ),
        "dlg_first_person_rate": safe_div(
            sum(1 for token in tokens if token in {"i", "me", "my", "mine", "myself"}),
            n_words,
        ),
        "dlg_second_person_rate": safe_div(
            sum(1 for token in tokens if token in {"you", "your", "yours", "yourself"}),
            n_words,
        ),
        "dlg_one_word_sentence_rate": safe_div(
            sum(1 for sentence in sentences if len(word_tokens(sentence)) == 1),
            n_sentences,
        ),
    }