src/application/formatting_ordinary_user.py

from pandas import DataFrame

from src.application.config import WORD_BREAK
from src.application.image.helper import encode_image
from src.application.image.image import ImageDetector
from src.application.text.helper import replace_leading_spaces
from src.application.text.text import TextDetector


def create_ordinary_user_table(
    aligned_sentences_df: DataFrame,
    text: TextDetector,
    image: ImageDetector,
) -> str:
    """
    Creates an HTML table comparing input news with source news
        for ordinary users.

    Args:
        aligned_sentences_df (DataFrame): Aligned sentence data.
        text (TextDetector): Text comparison data.
        image (ImageDetector): Image comparison data.

    Returns:
        A string representing the HTML table.
    """
    rows = []

    if image.input is not None:
        rows.append(format_image_ordinary_user_row(image))

    if text.input is not None:
        rows.append(format_text_ordinary_user_row(aligned_sentences_df, text))

    table = "\n".join(rows)

    return f"""
<h5>Comparison between input news and source news:</h5>
<table border="1" style="width:100%; text-align:left;">
<col style="width: 340px;">
<col style="width: 30px;">
<col style="width: 75px;">
    <thead>
        <tr>
            <th>Input news</th>
            <th>Forensic</th>
            <th>Originality</th>
        </tr>
    </thead>
    <tbody>
        {table}
    </tbody>
</table>
    """


def format_text_ordinary_user_row(
    aligned_sentences_df,
    text,
) -> str:
    """
    Formats a row for the text in the ordinary user table.

    Args:
        aligned_sentences_df (DataFrame): Aligned sentence data.
        text (TextDetector): Text comparison data.

    Returns:
        A string representing the HTML table row for the text.
    """
    input_sentences = ""
    source_text_html = ""
    urls = []
    for _, row in aligned_sentences_df.iterrows():
        if row["input"] is None:
            continue

        input_sentences += replace_leading_spaces(row["input"]) + "<br>"
        url = row["url"]
        if url not in urls:
            urls.append(url)
            source_text_html += f"""<a href="{url}">{url}</a><br>"""

    return f"""
            <tr>
                <td>{input_sentences}</td>
                <td>{text.prediction_label[0]}<br>
                ({text.prediction_score[0] * 100:.2f}%)</td>
                <td style="{WORD_BREAK}";>{source_text_html}</td>
            </tr>
            """


def format_image_ordinary_user_row(image: ImageDetector) -> str:
    """
    Formats a row for the image in the ordinary user table.

    Args:
        image: Image comparison data.

    Returns:
        A string representing the HTML table row for the image.
    """
    if image.input is None:
        return ""

    # Put image, label, and score into html tag
    if image.referent_url is not None or image.referent_url != "":
        if "http" in image.input:
            input_image = (
                f"""<a href="{image.input}">{image.input}</a>"""  # noqa: E501
            )
        else:
            base64_image = encode_image(image.input)
            input_image = f"""<img src="data:image/jpeg;base64,{base64_image}" width="100" height="150">"""  # noqa: E501
        source_image_html = f"""<a href="{image.referent_url}">{image.referent_url}</a>"""  # noqa: E501
    else:
        source_image_html = ""

    return f"""
<tr>
    <td>{input_image}</td>
    <td>{image.prediction_label}<br>({image.prediction_score:.2f}%)</td>
    <td style="{WORD_BREAK}";>{source_image_html}</td>
</tr>
"""