d6c029d7d5
The streaming splitter treated every "." as a sentence boundary, so the operational reply "17.5°C" was read as "17." / "5°C" and "1.8 km/h" as "1." / "8 km/h" - numbers spoken digit-by-digit plus extra TTS calls. An ASCII terminator (. ! ?) now only ends a sentence when it is followed by whitespace, a closing quote/bracket, or end of text. In-token dots (decimals "17.5", versions "v2.0", hosts "example.com") are followed by a digit/letter, so they no longer split. CJK fullwidth terminators stay unconditional since those scripts use no trailing space. Language-agnostic, punctuation only. - bridge: lookahead-gated boundary regex + finditer-based chunking - tests: regression cases for decimals (17.5/1.8), versions, URLs, and an integer that genuinely ends a sentence Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
76 lines
3.0 KiB
Python
76 lines
3.0 KiB
Python
"""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
|
|
|
|
# A sentence boundary is one of:
|
|
# - a run of newlines, OR
|
|
# - a run of CJK fullwidth terminators (。！？) / the ellipsis (…) - these are
|
|
# ALWAYS boundaries because CJK scripts put no space after a sentence, OR
|
|
# - a run of ASCII terminators (. ! ?) that actually ENDS a sentence, i.e. is
|
|
# followed by whitespace, a closing quote/bracket, or the end of the text.
|
|
#
|
|
# Requiring that trailing whitespace/end for ASCII terminators is what keeps
|
|
# in-token dots from being mistaken for sentence ends, language-agnostically:
|
|
# - decimals -> "17.5°C", "1.8 km/h": the dot is followed by a digit, no space
|
|
# - versions -> "v2.0", "3.14": same
|
|
# - URLs/hosts-> "example.com/path": the dots are followed by letters, no space
|
|
# so none of them match and the number/URL stays inside a single spoken chunk.
|
|
# This is punctuation-only (no hardcoded words), per the project's multilingual
|
|
# rule. Runs of terminators ("?!", "...") still collapse into one boundary.
|
|
_BOUNDARY = re.compile(
|
|
r"""
|
|
(?P<nl>\n+) # a run of newlines
|
|
| (?P<cjk>[。！？…]+) # CJK terminators: always end a sentence
|
|
| (?P<ascii>[.!?]+) # ASCII terminator run...
|
|
(?=[)\]"'”’》」』]*(?:\s|$)) # ...only at a real sentence end
|
|
""",
|
|
re.VERBOSE,
|
|
)
|
|
|
|
|
|
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. Sentence boundaries are detected
|
|
on terminal punctuation only (language-agnostic). Dots that live *inside* a
|
|
token - decimal points ("17.5"), version numbers ("v2.0") and URLs
|
|
("example.com") - are NOT boundaries, so numbers and links are spoken in one
|
|
piece instead of being chopped digit-by-digit.
|
|
|
|
Fragments shorter than ``min_len`` characters (interjections like "네.", and
|
|
single-letter initials like "J.") 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 []
|
|
|
|
chunks: List[str] = []
|
|
buf = ""
|
|
last = 0
|
|
for m in _BOUNDARY.finditer(text):
|
|
buf += text[last:m.end()]
|
|
last = m.end()
|
|
# Flush at a real boundary once the buffer is a worthwhile clip.
|
|
if len(buf.strip()) >= min_len:
|
|
chunks.append(buf.strip())
|
|
buf = ""
|
|
|
|
buf += text[last:]
|
|
tail = buf.strip()
|
|
if tail:
|
|
if chunks and len(tail) < min_len:
|
|
chunks[-1] = chunks[-1] + " " + tail
|
|
else:
|
|
chunks.append(tail)
|
|
return chunks
|