qiRdZddlmZmZddlmZmZddlmZm Z m Z Gdde Z y)zSimple text aggregator for basic sentence-boundary text processing. This module provides a straightforward text aggregator that accumulates text until it finds an end-of-sentence marker, making it suitable for basic TTS text processing scenarios. ) AsyncIteratorOptional)SENTENCE_ENDING_PUNCTUATIONmatch_endofsentence) AggregationAggregationTypeBaseTextAggregatorceZdZdZfdZedefdZdede efdZ dede efdZ de efd Z d Zd ZxZS) SimpleTextAggregatora7Simple text aggregator that accumulates text until sentence boundaries. This aggregator provides basic functionality for accumulating text tokens and releasing them when an end-of-sentence marker is detected. It's the most straightforward implementation of text aggregation for TTS processing. c @t|di|d|_d|_y)zInitialize the simple text aggregator. Creates an empty text buffer ready to begin accumulating text tokens. Args: **kwargs: Additional arguments passed to BaseTextAggregator (e.g. aggregation_type). FN)super__init___text_needs_lookahead)selfkwargs __class__s [/opt/pipecat/venv/lib/python3.12/site-packages/pipecat/utils/text/simple_text_aggregator.pyrzSimpleTextAggregator.__init__s$ "6" &+returncjt|jjdtjS)z{Get the currently aggregated text. Returns: The text that has been accumulated in the buffer.  texttype)rrstriprSENTENCErs rrzSimpleTextAggregator.text(s& 0 0 5O>tDDF  EsA-B/A?0B7 Br%cnK|jr}|jrld|_t|j}|rM|jd|}|j|d|_t |jdt j Syy|jr|jdtvrd|_yw)aCheck for sentence boundaries using lookahead logic. This method implements the core sentence detection logic with lookahead. When sentence-ending punctuation is detected, it waits for the next non-whitespace character before calling NLTK. This disambiguates cases like "$29." (not a sentence) vs "$29. Next" (sentence ends at period). Whitespace alone is not meaningful lookahead since it appears in both cases. Instead, the first non-whitespace character after the punctuation is used to confirm the sentence boundary. Subclasses can call this via super() to reuse the lookahead behavior while adding their own logic (e.g., tag handling, pattern matching). Args: char: The most recently added character (used for lookahead check). Returns: Aggregation if sentence found, None otherwise. FNrrT)rrrrrrrr)rr% eos_markerr&s rr$z3SimpleTextAggregator._check_sentence_with_lookaheadNs*  zz|(-%0< !ZZ 4F!%JK!8DJ&FLL,=OD\D\]] ::$**R.,GG$(D !sB3B5cK|jtjk(ry|jrN|j}|j d{t |j dtjSy7/w)aiFlush any remaining text in the buffer. Returns any text remaining in the buffer. This is called at the end of a stream to ensure all text is processed. In TOKEN mode, returns None since tokens are yielded immediately. Returns: Any remaining text as a sentence, or None if buffer is empty or in TOKEN mode. Nrr)r"rr#rresetrrr)rr&s rflushzSimpleTextAggregator.flush{sb  ! !_%:%: : ::ZZF**,  FLL$5O A< 0A>c(Kd|_d|_yw)zHandle interruptions by clearing the text buffer. Called when an interruption occurs in the processing pipeline, discarding any partially accumulated text. r FNrrr s rhandle_interruptionz(SimpleTextAggregator.handle_interruption  %c(Kd|_d|_yw)zClear the internally aggregated text. Resets the aggregator to its initial empty state, discarding any accumulated text content. r FNr/r s rr,zSimpleTextAggregator.resetr1r2)__name__ __module__ __qualname____doc__rpropertyrrstrrr'rr$r-r0r, __classcell__)rs@rr r sw ,VkVVCM+,F:+++AV+ZXk2(&&rr N) r7typingrrpipecat.utils.stringrr'pipecat.utils.text.base_text_aggregatorrrr r rrrr>s'+QddK&-K&r