app.py

import gradio as gr
import matplotlib.pyplot as plt
import networkx as nx

from collections.abc import Iterable

from gradio.themes.base import Base
from gradio.themes.utils import colors, fonts, sizes

from model import Parser


parser = Parser()


def parse(text):
    output = parser.parse(text)

    dependency_tree = render_dependency_tree(output["forms"], output["heads"], output["deprel"])
    table = render_table(output["forms"], output["lemmas"], output["upos"], output["xpos"], output["feats"], output["ne"])

    return dependency_tree, table


def render_dependency_tree(words, parents, labels):
    fig, ax = plt.subplots(figsize=(40, 16))

    main_font_size = 40 if len(words) < 10 else 30 if len(words) < 20 else 24 if len(words) < 40 else 16
    minor_font_size = 30 if len(words) < 10 else 22 if len(words) < 20 else 16 if len(words) < 40 else 12
    pad = main_font_size // 2

    # Create a directed graph
    G = nx.DiGraph()

    # Adding nodes to the graph
    for i, word in enumerate(words):
        G.add_node(i, label=word)

    # Adding edges with labels
    for i, (parent, label) in enumerate(zip(parents, labels)):
        if parent != 0:
            G.add_edge(parent - 1, i, label=label)

    # Position nodes using Graphviz
    pos = nx.nx_agraph.graphviz_layout(G, prog='dot')

    # Draw the graph
    nx.draw(G, pos, ax=ax, with_labels=True, labels=nx.get_node_attributes(G, 'label'), 
            arrows=True, node_color='#ffffff', node_size=0, node_shape='s', font_size=main_font_size, bbox = dict(facecolor="white", pad=pad)
    )

    # Draw edge labels
    edge_labels = nx.get_edge_attributes(G, 'label')
    nx.draw_networkx_edge_labels(G, pos, ax=ax, edge_labels=edge_labels, rotate=False, alpha=1.0, font_size=minor_font_size)

    return fig


description = """
<div style="text-align: center;">
    <h1>Norsk UD (Bokmål og Nynorsk)</h1>
    <p align="center">
        <img src="https://huggingface.co/ltg/norbert3-base/resolve/main/norbert.png" width=6.75%>
    </p><p></p>
</div>
"""


def render_table(forms, lemmas, upos, xpos, feats, named_entities):
    feats = [[f"*{f.split('=')[0]}:* {f.split('=')[1]}" for f in (feat.split("|")) if '=' in f] for feat in feats]
    max_len = max(1, max([len(feat) for feat in feats]))
    feats = [feat + [""] * (max_len - len(feat)) for feat in feats]
    feats = list(zip(*feats))

    named_entities_converted = []
    for i, ne in enumerate(named_entities):
        if ne == "O":
            named_entities_converted.append("")
        elif ne.startswith("B") and (i + 1 == len(named_entities) or named_entities[i + 1].startswith("I")):
            named_entities_converted.append(f"<<— {ne.split('-')[1]} —")
        elif ne.startswith("B"):
            named_entities_converted.append(f"<<— {ne.split('-')[1]} —>>")
        elif ne.startswith("I") and i + 1 < len(named_entities) and named_entities[i + 1].startswith("I"):
            named_entities_converted.append("————")
        else:
            named_entities_converted.append(f"——>>")

    array = [
        [""] + forms,
        ["*LEMMAS:*"] + lemmas,
        ["*UPOS:*"] + upos,
        ["*XPOS:*"] + xpos,
        ["*UFEATS:*"] + list(feats[0]),
        *([""] + list(row) for row in feats[1:]),
        ["*NE:*"] + named_entities_converted,
        ['' for _ in range(len(forms) + 1)]
    ]

    return {"data": array[1:], "headers": array[0]}


class Soft(Base):
    def __init__(
        self,
        *,
        primary_hue: colors.Color | str = colors.indigo,
        secondary_hue: colors.Color | str = colors.indigo,
        neutral_hue: colors.Color | str = colors.gray,
        spacing_size: sizes.Size | str = sizes.spacing_md,
        radius_size: sizes.Size | str = sizes.radius_md,
        text_size: sizes.Size | str = sizes.text_md,
        font: fonts.Font | str | Iterable[fonts.Font | str] = (
            # fonts.LocalFont("Montserrat"),
            "ui-sans-serif",
            "system-ui",
            "sans-serif",
        ),
        font_mono: fonts.Font | str | Iterable[fonts.Font | str] = (
            # fonts.LocalFont("IBM Plex Mono"),
            "ui-monospace",
            "Consolas",
            "monospace",
        ),
    ):
        super().__init__(
            primary_hue=primary_hue,
            secondary_hue=secondary_hue,
            neutral_hue=neutral_hue,
            spacing_size=spacing_size,
            radius_size=radius_size,
            text_size=text_size,
            font=font,
            font_mono=font_mono,
        )
        self.name = "soft"
        super().set(
            # Colors
            background_fill_primary="*neutral_50",
            slider_color="*primary_500",
            slider_color_dark="*primary_600",
            # Shadows
            shadow_drop="0 1px 4px 0 rgb(0 0 0 / 0.1)",
            shadow_drop_lg="0 2px 5px 0 rgb(0 0 0 / 0.2)",
            # Block Labels
            block_background_fill="white",
            block_label_padding="*spacing_sm *spacing_md",
            block_label_background_fill="*primary_100",
            block_label_background_fill_dark="*primary_600",
            block_label_radius="*radius_md",
            block_label_text_size="*text_md",
            block_label_text_weight="600",
            block_label_text_color="*primary_500",
            block_label_text_color_dark="white",
            block_title_radius="*block_label_radius",
            block_title_padding="*block_label_padding",
            block_title_background_fill="*block_label_background_fill",
            block_title_text_weight="600",
            block_title_text_color="*primary_500",
            block_title_text_color_dark="white",
            block_label_margin="*spacing_md",

            # Inputs
            input_background_fill="white",
            input_border_color="*neutral_100",
            input_shadow="*shadow_drop",
            input_shadow_focus="*shadow_drop_lg",
            checkbox_shadow="none",
            # Buttons
            shadow_spread="6px",
            button_primary_shadow="*shadow_drop_lg",
            button_primary_shadow_hover="*shadow_drop_lg",
            button_primary_shadow_active="*shadow_inset",
            button_secondary_shadow="*shadow_drop_lg",
            button_secondary_shadow_hover="*shadow_drop_lg",
            button_secondary_shadow_active="*shadow_inset",
            checkbox_label_shadow="*shadow_drop_lg",
            button_primary_background_fill="*primary_500",
            button_primary_background_fill_hover="*primary_400",
            button_primary_background_fill_hover_dark="*primary_500",
            button_primary_text_color="white",
            button_secondary_background_fill="white",
            button_secondary_background_fill_hover="*neutral_100",
            button_secondary_background_fill_hover_dark="*primary_500",
            button_secondary_text_color="*neutral_800",
            button_cancel_background_fill="*button_secondary_background_fill",
            button_cancel_background_fill_hover="*button_secondary_background_fill_hover",
            button_cancel_background_fill_hover_dark="*button_secondary_background_fill_hover",
            button_cancel_text_color="*button_secondary_text_color",
            checkbox_label_background_fill_selected="*primary_500",
            checkbox_label_background_fill_selected_dark="*primary_600",
            checkbox_border_width="1px",
            checkbox_border_color="*neutral_100",
            checkbox_border_color_dark="*neutral_600",
            checkbox_background_color_selected="*primary_600",
            checkbox_background_color_selected_dark="*primary_700",
            checkbox_border_color_focus="*primary_500",
            checkbox_border_color_focus_dark="*primary_600",
            checkbox_border_color_selected="*primary_600",
            checkbox_border_color_selected_dark="*primary_700",
            checkbox_label_text_color_selected="white",
            # Borders
            block_border_width="0px",
            panel_border_width="0px",
        )


custom_css = \
"""
    /* Hide sort buttons at gr.DataFrame */
    .sort-button {
        display: none !important;
    }
"""
with gr.Blocks(theme=Soft(), css=custom_css) as demo:
    gr.HTML(description)

    with gr.Row():
        with gr.Column(scale=1, variant="panel"):
            source = gr.Textbox(
                label="Input sentence", placeholder="Write a sentence to parse", show_label=False, lines=1, max_lines=5, autofocus=True
            )
            submit = gr.Button("Submit", variant="primary")

        with gr.Column(scale=1, variant="panel"):
            dataset = gr.Dataset(components=[gr.Textbox(visible=False)],
                label="Input examples",
                samples=[
                    ["Thomassen er på vei til sin neste gjerning."],
                    ["På toppen av dette kom de metodiske utfordringer."],
                    ["Berntsen har påtatt seg en både viktig og vanskelig oppgave."],
                    ["Ikke bare har det vært et problem, som han selv skriver i forordet, å bli klok på Borten."],
                    ["Statsministeren i Norges første brede og varige borgerlige koalisjonsregjering etterlot seg timelange radiointervjuer med tidligere Dagsnytt-redaktør Per Bøhn og 70-80 stappfulle esker med usorterte papirer på loft og i kjeller hjemme på gården i Flå."]
                ]
            )

    with gr.Column(scale=1, variant="panel"):
        #gr.Label("", show_label=False, container=False)
        table = gr.DataFrame([[""] * 42 for _ in range(8)], headers=[""] * 42, interactive=False, datatype="markdown")
        dependency_plot = gr.Plot(None, container=False)

    source.submit(
        fn=parse, inputs=[source], outputs=[dependency_plot, table], queue=True
    )
    submit.click(
        fn=parse, inputs=[source], outputs=[dependency_plot, table], queue=True
    )
    dataset.click(
        fn=lambda text: text[0], inputs=[dataset], outputs=[source]
    ).then(
        fn=parse, inputs=[source], outputs=[dependency_plot, table], queue=True
    )


demo.queue(max_size=32)
demo.launch()