src/application/formatting_governor.py

from pandas import DataFrame

from src.application.config import WORD_BREAK
from src.application.formatting import (
    color_text,
    format_entity_count,
)
from src.application.image.helper import encode_image
from src.application.image.image import ImageDetector
from src.application.text.entity import apply_highlight
from src.application.text.helper import (
    extract_equal_text,
    replace_leading_spaces,
)
from src.application.text.text import TextDetector


def create_governor_table(
    aligned_sentences_df: DataFrame,
    text: TextDetector,
    image: ImageDetector,
):
    rows = []
    if image.input is not None:
        rows.append(format_image_governor_row(image))

    if text.input is not None:
        for _, row in aligned_sentences_df.iterrows():
            if row["input"] is None:
                continue

            if row["source"] is None:
                equal_idx_1 = equal_idx_2 = []
            else:
                # Get index of equal phrases in input and source sentences
                equal_idx_1, equal_idx_2 = extract_equal_text(
                    row["input"],
                    row["source"],
                )

            text.governor_table.append(
                [
                    row,
                    equal_idx_1,
                    equal_idx_2,
                    row["entities"],
                ],
            )

        formatted_row = format_text_governor_row(text)
        rows.append(formatted_row)

    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: 170px;">
<col style="width: 170px;">
<col style="width: 30px;">
<col style="width: 75px;">
    <thead>
        <tr>
            <th>Input news</th>
            <th>Source (URL in Originality)</th>
            <th>Forensic</th>
            <th>Originality</th>
        </tr>
    </thead>
    <tbody>
        {table}
    </tbody>
</table>

<style>
        """


def format_text_governor_row(text):
    input_sentences = ""
    source_sentences = ""
    source_text_urls = ""
    urls = []
    sentence_count = 0
    entity_count = [0, 0]  # to get index of [-2]
    for row in text.governor_table:
        if row[0]["input"] is None:
            continue

        if row[0]["source"] is not None:  # source is not empty
            # highlight entities
            input_sentence, highlight_idx_input = apply_highlight(
                row[0]["input"],
                row[3],  # entities_with_colors
                "input",  # key
                entity_count[-2],  # since the last one is for current counting
            )
            source_sentence, highlight_idx_source = apply_highlight(
                row[0]["source"],
                row[3],  # entities_with_colors
                "source",  # key
                entity_count[-2],  # since the last one is for current counting
            )

            # Color overlapping words
            input_sentence = color_text(
                input_sentence,
                row[1],
                highlight_idx_input,
            )  # text, index of highlight words
            source_sentence = color_text(
                source_sentence,
                row[2],
                highlight_idx_source,
            )  # text, index of highlight words

            input_sentence = input_sentence.replace(
                "span_style",
                "span style",
            ).replace("1px_4px", "1px 4px")
            source_sentence = source_sentence.replace(
                "span_style",
                "span style",
            ).replace("1px_4px", "1px 4px")

        else:
            if row[0]["source"] is None:
                source_sentence = ""
            else:
                source_sentence = row[0]["source"]
            input_sentence = row[0]["input"]

        input_sentence = replace_leading_spaces(input_sentence)
        source_sentence = replace_leading_spaces(source_sentence)

        input_sentences += input_sentence + "<br>"
        source_sentences += source_sentence + "<br>"

        url = row[0]["url"]
        if url not in urls:
            urls.append(url)
            source_text_urls += f"""<a href="{url}">{url}</a><br><br>"""
            sentence_count += 1
            if row[3] is not None:
                entity_count.append(len(row[3]))

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


def format_image_governor_row(image: ImageDetector):
    if image.input is None:
        return ""

    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_url = f"""<a href="{image.referent_url}">{image.referent_url}</a>"""  # noqa: E501
        source_image = f"""<img src="{image.referent_url}" width="100" height="150">"""  # noqa: E501
    else:
        source_image = "Image not found"
        source_image_url = ""

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