Get text around passage

flair_text_around_passage.py

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "flair",
#     "IPython",
# ]
# ///


from flair.splitter import SegtokSentenceSplitter

# Initialize the splitter once
splitter = SegtokSentenceSplitter()


def get_sentence_context_flair(
    text: str,
    passage: str,
    window: int = 4,
) -> tuple[list[str], list[str], list[str]]:
    """
    Extract up to `window` sentences before/after `passage` using Flair's SegtokSentenceSplitter.
    Returns a tuple (before, target, after) of sentence lists.
    """
    # Split text into Sentence objects, then extract raw text
    sentences = [sent.text for sent in splitter.split(text)]

    # Locate the character offset of the passage
    start_char = text.find(passage)
    if start_char < 0:
        raise ValueError("Passage not found in text.")
    end_char = start_char + len(passage)

    # Build cumulative character offsets for each sentence
    offsets: list[tuple[int, int]] = []
    cum = 0
    for s in sentences:
        offsets.append((cum, cum + len(s)))
        # Account for the separator that was in the original text (usually a space or newline)
        cum += len(s) + 1

    # Find which sentence contains the start of the passage
    target_idx = next(
        (i for i, (a, b) in enumerate(offsets) if a <= start_char < b), None
    )
    if target_idx is None:
        raise ValueError("Could not map passage to a sentence.")

    # Compute context window bounds
    start = max(0, target_idx - window)
    end = min(len(sentences), target_idx + window + 1)

    before = sentences[start:target_idx]
    target = sentences[target_idx : end - window]
    after = sentences[target_idx + 1 : end]

    return before, target, after


# Example usage
if __name__ == "__main__":
    full_text = (
        "Alice was beginning to get very tired of sitting by her sister on the bank, and of having nothing to do. "
        "Once or twice she had peeped into the book her sister was reading, but it had no pictures or conversations in it, "
        "'and what is the use of a book,' thought Alice 'without pictures or conversation?' "
        "So she was considering in her own mind (as well as she could, for the hot day made her feel very sleepy and stupid), "
        "whether the pleasure of making a daisy-chain would be worth the trouble. "
        "Suddenly a White Rabbit with pink eyes ran close by her. "
        "There was nothing so very remarkable in that; nor did Alice think it so very much out of the way to hear the Rabbit say "
        "to itself 'Oh dear! Oh dear! I shall be late!' (when she thought it over afterwards, it occurred to her that she ought to "
        "have wondered at this, but at the time it all seemed quite natural); but when the Rabbit actually took a watch out of its "
        "waistcoat-pocket, and looked at it, and hurried on, Alice started to her feet, for it flashed across her mind that she had "
        "never before seen a rabbit with either a waistcoat-pocket, or a watch to take out of it. "
        "With nothing more than a curious glance back at her sister, who was still sitting on the bank, and was getting very "
        "tired of waiting by now, Alice ran across the field after the Rabbit, and fortunately was just in time to see it pop down "
        "a large rabbit-hole under the hedge. "
        "In another moment down went Alice after it, never once considering how in the world she was to get out again. "
        "The rabbit-hole went straight on like a tunnel for some way, and then dipped suddenly down, so suddenly that Alice had not "
        "a moment to think about stopping herself before she found herself falling down a very deep well. "
        "Either the well was very deep, or she fell very slowly, for she had plenty of time as she went down to look about her and to "
        "wonder what was going to happen next. First, she tried to look down and make out what she was coming to, but it was too dark to "
        "see anything; she felt that she was dozing off, and had just begun to dream that she was walking hand in hand with Dinah, and "
        "saying to her 'Now, Dinah, tell me the truth: did you ever eat a bat?' when suddenly, thump! Down she came upon a heap of sticks "
        "and dry leaves, and the fall was over."
    )
    passage = "Oh dear! Oh dear! I shall be late!"
    window = 4

    before, target, after = get_sentence_context_flair(
        full_text, passage, window=window
    )

    # Nicely print the context window
    print(f"=== {window} sentences BEFORE ===")
    for s in before:
        print(f" • {s}")
    print(f"\n=== TARGET sentence ===")
    for s in target:
        print(f" • {s}")
    print(f"\n=== {window} sentences AFTER ===")
    for s in after:
        print(f" • {s}")

sentence_splitter_text_around_passage.py

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "sentence-splitter",
#     "IPython",
# ]
# ///

from sentence_splitter import SentenceSplitter

# Initialize the splitter for English
splitter = SentenceSplitter(language="en")


def get_sentence_context_splitter(
    text: str,
    passage: str,
    window: int = 4,
) -> tuple[list[str], list[str], list[str]]:
    """
    Extract up to `window` sentences before/after `passage` using sentence-splitter.
    Returns a tuple (before, target, after) of sentence lists.
    """
    # Split the full text into sentences
    sentences = splitter.split(text)

    # Locate the character offset of the passage
    start_char = text.find(passage)
    if start_char < 0:
        raise ValueError("Passage not found in text.")
    end_char = start_char + len(passage)

    # Build cumulative character offsets for each sentence
    offsets: list[tuple[int, int]] = []
    cum = 0
    for s in sentences:
        offsets.append((cum, cum + len(s)))
        # Account for the separator (a single space) in the original text
        cum += len(s) + 1

    # Find which sentence contains the start of the passage
    target_idx = next(
        (i for i, (a, b) in enumerate(offsets) if a <= start_char < b), None
    )
    if target_idx is None:
        raise ValueError("Could not map passage to a sentence.")

    # Compute context window bounds
    start = max(0, target_idx - window)
    end = min(len(sentences), target_idx + window + 1)

    before = sentences[start:target_idx]
    target = sentences[target_idx : end - window]
    after = sentences[target_idx + 1 : end]

    return before, target, after


if __name__ == "__main__":
    # Define the text and the passage of interest
    full_text = (
        "Alice was beginning to get very tired of sitting by her sister on the bank, and of having nothing to do. "
        "Once or twice she had peeped into the book her sister was reading, but it had no pictures or conversations in it, "
        "'and what is the use of a book,' thought Alice 'without pictures or conversation?' "
        "So she was considering in her own mind (as well as she could, for the hot day made her feel very sleepy and stupid), "
        "whether the pleasure of making a daisy-chain would be worth the trouble. "
        "Suddenly a White Rabbit with pink eyes ran close by her. "
        "There was nothing so very remarkable in that; nor did Alice think it so very much out of the way to hear the Rabbit say "
        "to itself 'Oh dear! Oh dear! I shall be late!' (when she thought it over afterwards, it occurred to her that she ought to "
        "have wondered at this, but at the time it all seemed quite natural); but when the Rabbit actually took a watch out of its "
        "waistcoat-pocket, and looked at it, and hurried on, Alice started to her feet, for it flashed across her mind that she had "
        "never before seen a rabbit with either a waistcoat-pocket, or a watch to take out of it. "
        "With nothing more than a curious glance back at her sister, who was still sitting on the bank, and was getting very "
        "tired of waiting by now, Alice ran across the field after the Rabbit, and fortunately was just in time to see it pop down "
        "a large rabbit-hole under the hedge. "
        "In another moment down went Alice after it, never once considering how in the world she was to get out again. "
        "The rabbit-hole went straight on like a tunnel for some way, and then dipped suddenly down, so suddenly that Alice had not "
        "a moment to think about stopping herself before she found herself falling down a very deep well. "
        "Either the well was very deep, or she fell very slowly, for she had plenty of time as she went down to look about her and to "
        "wonder what was going to happen next. First, she tried to look down and make out what she was coming to, but it was too dark to "
        "see anything; she felt that she was dozing off, and had just begun to dream that she was walking hand in hand with Dinah, and "
        "saying to her 'Now, Dinah, tell me the truth: did you ever eat a bat?' when suddenly, thump! Down she came upon a heap of sticks "
        "and dry leaves, and the fall was over."
    )
    passage = "Oh dear! Oh dear! I shall be late!"
    window = 4

    before, target, after = get_sentence_context_splitter(
        full_text, passage, window=window
    )

    # Nicely print the context window
    print(f"=== {window} sentences BEFORE ===")
    for s in before:
        print(f" • {s}")
    print(f"\n=== TARGET sentence ===")
    for s in target:
        print(f" • {s}")
    print(f"\n=== {window} sentences AFTER ===")
    for s in after:
        print(f" • {s}")

stanza_text_around_passage.py

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "stanza",
#     "IPython",
# ]
# ///

import stanza

# Download once: stanza.download('en')
nlp = stanza.Pipeline(lang="en", processors="tokenize")


def get_sentence_context_stanza(
    text: str,
    passage: str,
    window: int = 4,
) -> tuple[list[str], list[str], list[str]]:
    """
    Extract up to `window` sentences before/after `passage` using Stanza.
    Returns a tuple (before, target, after) of sentence lists.
    """
    # Process the full text
    doc = nlp(text)
    # Extract raw sentence texts
    sentences = [sent.text for sent in doc.sentences]

    # Locate passage in the original text
    start_char = text.find(passage)
    if start_char < 0:
        raise ValueError("Passage not found in text.")
    end_char = start_char + len(passage)

    # Build cumulative character offsets to map passage → sentence index
    offsets: list[tuple[int, int]] = []
    cum = 0
    for s in sentences:
        offsets.append((cum, cum + len(s)))
        cum += len(s) + 1  # Account for the space/newline separator

    # Find the index of the sentence containing the passage
    target_idx = next(
        (i for i, (a, b) in enumerate(offsets) if a <= start_char < b), None
    )
    if target_idx is None:
        raise ValueError("Could not map passage to a sentence.")

    # Compute window bounds
    start = max(0, target_idx - window)
    end = min(len(sentences), target_idx + window + 1)

    before = sentences[start:target_idx]
    target = sentences[target_idx : end - window]
    after = sentences[target_idx + 1 : end]

    return before, target, after


if __name__ == "__main__":
    # Define the text and the passage of interest
    full_text = (
        "Alice was beginning to get very tired of sitting by her sister on the bank, and of having nothing to do. "
        "Once or twice she had peeped into the book her sister was reading, but it had no pictures or conversations in it, "
        "'and what is the use of a book,' thought Alice 'without pictures or conversation?' "
        "So she was considering in her own mind (as well as she could, for the hot day made her feel very sleepy and stupid), "
        "whether the pleasure of making a daisy-chain would be worth the trouble. "
        "Suddenly a White Rabbit with pink eyes ran close by her. "
        "There was nothing so very remarkable in that; nor did Alice think it so very much out of the way to hear the Rabbit say "
        "to itself 'Oh dear! Oh dear! I shall be late!' (when she thought it over afterwards, it occurred to her that she ought to "
        "have wondered at this, but at the time it all seemed quite natural); but when the Rabbit actually took a watch out of its "
        "waistcoat-pocket, and looked at it, and hurried on, Alice started to her feet, for it flashed across her mind that she had "
        "never before seen a rabbit with either a waistcoat-pocket, or a watch to take out of it. "
        "With nothing more than a curious glance back at her sister, who was still sitting on the bank, and was getting very "
        "tired of waiting by now, Alice ran across the field after the Rabbit, and fortunately was just in time to see it pop down "
        "a large rabbit-hole under the hedge. "
        "In another moment down went Alice after it, never once considering how in the world she was to get out again. "
        "The rabbit-hole went straight on like a tunnel for some way, and then dipped suddenly down, so suddenly that Alice had not "
        "a moment to think about stopping herself before she found herself falling down a very deep well. "
        "Either the well was very deep, or she fell very slowly, for she had plenty of time as she went down to look about her and to "
        "wonder what was going to happen next. First, she tried to look down and make out what she was coming to, but it was too dark to "
        "see anything; she felt that she was dozing off, and had just begun to dream that she was walking hand in hand with Dinah, and "
        "saying to her 'Now, Dinah, tell me the truth: did you ever eat a bat?' when suddenly, thump! Down she came upon a heap of sticks "
        "and dry leaves, and the fall was over."
    )
    passage = "Oh dear! Oh dear! I shall be late!"
    window = 4

    before, target, after = get_sentence_context_stanza(
        full_text, passage, window=window
    )

    # Nicely print the context window
    print(f"=== {window} sentences BEFORE ===")
    for s in before:
        print(f" • {s}")
    print(f"\n=== TARGET sentence ===")
    for s in target:
        print(f" • {s}")
    print(f"\n=== {window} sentences AFTER ===")
    for s in after:
        print(f" • {s}")