from __future__ import annotations

import logging
import re
from collections import Counter
from pathlib import Path
from typing import Iterable

from .store import Store


log = logging.getLogger(__name__)

# Minimal Spanish + English stopword list (no extra deps).
_STOPWORDS = {
    # es
    "el", "la", "los", "las", "un", "una", "unos", "unas", "de", "del", "al", "a", "y", "o", "u",
    "que", "en", "como", "por", "para", "su", "sus", "se", "si", "no", "con", "es", "son", "fue",
    "era", "este", "esta", "estos", "estas", "eso", "esa", "esos", "esas", "lo", "le", "les", "te",
    "me", "se", "nos", "os", "pero", "mas", "muy", "ya", "cuando", "donde", "quien", "como", "todo",
    "todos", "toda", "todas", "nada", "algo", "tambien", "asi", "hay", "habia", "tiene", "tener",
    "puede", "pueden", "esto", "esta", "sin", "sobre", "entre", "hasta", "desde", "mi", "tu", "yo",
    "el", "ella", "ellos", "ellas", "nosotros", "vosotros", "ustedes", "porque", "pues", "entonces",
    # en
    "the", "a", "an", "and", "or", "but", "of", "to", "in", "on", "at", "by", "for", "with", "from",
    "is", "are", "was", "were", "be", "been", "being", "this", "that", "these", "those", "it", "its",
    "as", "if", "not", "no", "so", "do", "does", "did", "have", "has", "had", "i", "you", "he", "she",
    "we", "they", "my", "your", "his", "her", "our", "their", "me", "him", "us", "them", "can", "could",
    "would", "should", "will", "shall", "may", "might", "just", "like", "what", "which", "who", "when",
    "where", "why", "how", "all", "any", "both", "each", "more", "most", "other", "some", "such",
}

_WORD = re.compile(r"[A-Za-zÁÉÍÓÚÜÑáéíóúüñ]{3,}")


def _iter_texts(store: Store, channel_id: str | None) -> Iterable[str]:
    sql = "SELECT text FROM transcript_segments"
    params: list = []
    if channel_id:
        sql += " WHERE video_id IN (SELECT video_id FROM videos WHERE channel_id = ?)"
        params.append(channel_id)
    conn = store._connect()
    try:
        cur = conn.execute(sql, params)
        for row in cur:
            yield row["text"]
    finally:
        conn.close()


def _tokenize(text: str) -> Iterable[str]:
    for m in _WORD.finditer(text.lower()):
        w = m.group(0)
        if w not in _STOPWORDS:
            yield w


def word_frequency(store: Store, channel_id: str | None = None, top: int | None = None) -> dict[str, int]:
    counter: Counter[str] = Counter()
    for text in _iter_texts(store, channel_id):
        counter.update(_tokenize(text))
    items = counter.most_common(top) if top else counter.most_common()
    return dict(items)


def top_words(store: Store, n: int = 50, channel_id: str | None = None) -> list[tuple[str, int]]:
    return list(word_frequency(store, channel_id, top=n).items())


def term_timeline(store: Store, term: str, channel_id: str | None = None) -> list[tuple[str, int]]:
    """Return [(YYYY-MM, count)] of months where `term` appears in transcripts."""
    term_l = term.lower().strip()
    if not term_l:
        return []
    sql = (
        "SELECT substr(v.upload_date,1,6) AS month, COUNT(*) AS n "
        "FROM transcript_fts f JOIN videos v ON v.video_id = f.video_id "
        "WHERE transcript_fts MATCH ?"
    )
    params: list = [f'"{term_l}"']
    if channel_id:
        sql += " AND v.channel_id = ?"
        params.append(channel_id)
    sql += " AND v.upload_date IS NOT NULL GROUP BY month ORDER BY month"
    conn = store._connect()
    try:
        rows = conn.execute(sql, params).fetchall()
    finally:
        conn.close()
    out: list[tuple[str, int]] = []
    for r in rows:
        m = r["month"]
        if m and len(m) == 6:
            out.append((f"{m[:4]}-{m[4:6]}", r["n"]))
    return out


def render_wordcloud(freq: dict[str, int], out_path: str | Path) -> Path:
    from wordcloud import WordCloud
    import matplotlib
    matplotlib.use("Agg")
    import matplotlib.pyplot as plt

    out = Path(out_path)
    out.parent.mkdir(parents=True, exist_ok=True)
    wc = WordCloud(
        width=1600, height=900, background_color="#0a0a0f",
        colormap="Reds", max_words=200,
    ).generate_from_frequencies(freq)
    fig, ax = plt.subplots(figsize=(16, 9), dpi=100)
    ax.imshow(wc, interpolation="bilinear")
    ax.set_axis_off()
    fig.tight_layout(pad=0)
    fig.savefig(str(out), facecolor="#0a0a0f")
    plt.close(fig)
    return out


def render_top_words_chart(top: list[tuple[str, int]], out_path: str | Path) -> Path:
    import matplotlib
    matplotlib.use("Agg")
    import matplotlib.pyplot as plt

    out = Path(out_path)
    out.parent.mkdir(parents=True, exist_ok=True)
    items = top[:25][::-1]
    labels = [t[0] for t in items]
    values = [t[1] for t in items]
    fig, ax = plt.subplots(figsize=(10, 8), dpi=100)
    ax.barh(labels, values, color="#f43f5e")
    ax.set_facecolor("#0a0a0f")
    fig.patch.set_facecolor("#0a0a0f")
    ax.tick_params(colors="#e5e7eb")
    for spine in ax.spines.values():
        spine.set_color("#27272a")
    ax.set_title("Top terms", color="#e5e7eb")
    fig.tight_layout()
    fig.savefig(str(out), facecolor="#0a0a0f")
    plt.close(fig)
    return out


def render_timeline_chart(timeline: list[tuple[str, int]], term: str, out_path: str | Path) -> Path:
    import matplotlib
    matplotlib.use("Agg")
    import matplotlib.pyplot as plt

    out = Path(out_path)
    out.parent.mkdir(parents=True, exist_ok=True)
    labels = [t[0] for t in timeline]
    values = [t[1] for t in timeline]
    fig, ax = plt.subplots(figsize=(12, 5), dpi=100)
    ax.plot(labels, values, marker="o", color="#f43f5e")
    ax.set_facecolor("#0a0a0f")
    fig.patch.set_facecolor("#0a0a0f")
    ax.tick_params(colors="#e5e7eb", axisxlabelrotation=45)
    for spine in ax.spines.values():
        spine.set_color("#27272a")
    ax.set_title(f"Mentions over time: {term}", color="#e5e7eb")
    fig.tight_layout()
    fig.savefig(str(out), facecolor="#0a0a0f")
    plt.close(fig)
    return out