"""Small, dependency-free text helpers for the brain bridge.

Kept separate from ``bridge.server`` (which imports Flask and the heavy brain)
so the pure logic here can be unit-tested in isolation.
"""

from __future__ import annotations

import re
from typing import List, Optional

# Sentence terminators across scripts: ASCII . ! ? plus the CJK fullwidth forms
# and the ellipsis. Runs of terminators ("?!", "...") collapse into one boundary.
# A run of newlines is also a boundary. This is punctuation-only and therefore
# language-agnostic (no hardcoded words), per the project's multilingual rule.
_BOUNDARY = re.compile(r"([.!?。！？…]+|\n+)")


def split_sentences(text: Optional[str], min_len: int = 5) -> List[str]:
    """Split ``text`` into sentence-sized chunks for streaming TTS.

    Each chunk ends at a sentence boundary so it can be synthesised and played
    while later chunks are still being spoken. Fragments shorter than
    ``min_len`` characters (interjections like "네.", "응") are merged into an
    adjacent chunk so we don't emit choppy micro-clips. Returns an empty list
    for blank input and never loses visible content.
    """
    text = (text or "").strip()
    if not text:
        return []

    parts = _BOUNDARY.split(text)
    chunks: List[str] = []
    buf = ""
    for i in range(0, len(parts), 2):
        seg = parts[i]
        delim = parts[i + 1] if i + 1 < len(parts) else ""
        buf += seg + delim
        # Flush at a real boundary once the buffer is a worthwhile clip.
        if delim and len(buf.strip()) >= min_len:
            chunks.append(buf.strip())
            buf = ""

    tail = buf.strip()
    if tail:
        if chunks and len(tail) < min_len:
            chunks[-1] = chunks[-1] + " " + tail
        else:
            chunks.append(tail)
    return chunks