채팅 답은 문단마다

import re

TAG = re.compile(r"\[(?:emotion:)?[a-z][a-z ]*\]")             # audio tags and the emotion tag
CARD = re.compile(r"^(`{3,})card[ \t]*\n(?:.*?\n)??\1`*[ \t]*$\n?", re.MULTILINE | re.DOTALL)   # closes on as many or more


def paragraph_ends(content: str) -> list[int]:
    """Just past each blank line that follows text or a closing fence, outside every fence."""
    ends, fence, line = [], 0, 0
    while (newline := content.find("\n", line)) != -1:
        text = content[line:newline]
        ticks = len(m.group(1)) if (m := re.match(r"(`{3,})", text)) else 0
        opens = not fence and ticks > 0
        if opens:
            fence = ticks                       # a four-backtick card keeps its inner ```
        elif fence and ticks >= fence and re.fullmatch(r"`+[ \t]*", text):
            fence = 0
        if not fence and not opens and newline > line and content[newline + 1:newline + 2] == "\n":
            ends.append(newline + 2)
        line = newline + 1
    return ends


def says_something(unit: str) -> bool:
    return bool(TAG.sub("", CARD.sub("", unit)).strip())


def spoken_units(content: str, final: bool) -> list[str]:
    """Every unit ready now; a paragraph with nothing to say joins the next."""
    units, start = [], 0
    for end in paragraph_ends(content):
        if says_something(content[start:end]):
            units.append(content[start:end].strip())
            start = end
    if final and start < len(content) and says_something(content[start:]):
        units.append(content[start:].strip())
    return units


reply = (
    "응, 오늘 저녁은 해변 쪽으로 걷자. 해 지는 게 8시 10분쯤이래.\n\n"
    "[softly]\n\n"                                   # nothing to say: joins the next
    "가는 길에 들를 만한 데를 카드에 적어 뒀어.\n\n"
    "````card\n| 어디 | 몇 분 |\n|---|---|\n| 말라게타 해변 | 15 |\n\n```text\n(코드 블록 속 빈 줄)\n```\n````\n\n"
    "춥진 않을 거야. 얇은 겉옷 하나면 돼.\n\n"
    "[emotion:warm]\n"                             # the face's tag: never a take of its own
)
half = reply[: reply.index("가는 길에") + 5]       # the stream so far
print("while streaming:", spoken_units(half, final=False))
for n, unit in enumerate(spoken_units(reply, final=True), 1):
    print(n, repr(CARD.sub("", unit).strip()))      # what the voice gets: the card stays on screen

# Output:
# while streaming: ['응, 오늘 저녁은 해변 쪽으로 걷자. 해 지는 게 8시 10분쯤이래.']
# 1 '응, 오늘 저녁은 해변 쪽으로 걷자. 해 지는 게 8시 10분쯤이래.'
# 2 '[softly]\n\n가는 길에 들를 만한 데를 카드에 적어 뒀어.'
# 3 '춥진 않을 거야. 얇은 겉옷 하나면 돼.'
#   (the card's blank lines never cut it, the card alone joined the paragraph after it,
#    and the closing [emotion:warm] says nothing, so the voice gets no take of it)