Blame for taxonomy.py

"""Read-only taxonomy navigation, independent of the annotation lookup index."""
from collections import Counter
from contextlib import closing
import math
from html import escape
import json
from pathlib import Path
import sqlite3

import gradio as gr

ROOT = Path(__file__).resolve().parent
DATABASE = ROOT / "data/taxonomy.sqlite"
COMMON_NAMES = ROOT / "data/common_names.json"
ICONS = ROOT / "data/icons.json"
ICON_DIR = ROOT / "data/icons"
# Gradio serves whitelisted files from this route; see build_taxonomy_tab.
ICON_ROUTE = "/gradio_api/file="
LICENSE_NAMES = {"https://creativecommons.org/publicdomain/zero/1.0/": "CC0 1.0",
                 "https://creativecommons.org/licenses/by/4.0/": "CC BY 4.0",
                 "https://creativecommons.org/licenses/by/3.0/": "CC BY 3.0",
                 "https://creativecommons.org/publicdomain/mark/1.0/": "Public Domain Mark 1.0"}
EUKARYOTA = 2759
EUK_TREE = """WITH RECURSIVE euk(taxid) AS (
    SELECT 2759 UNION ALL
    SELECT t.taxid FROM taxa t JOIN euk e ON t.parent_id=e.taxid
    WHERE t.taxid != t.parent_id
) """
# Scientific names stay the primary label; English glosses are a secondary line.
# See refresh_common_names.py for how the lookup is built.
MAX_ENGLISH = 30
MAX_LABEL = 24


COLUMN_LIMIT = 6
MAX_DEPTH = 80
DEFAULT_PATH = "2759/33154"


def encode_path(steps):
    """Serialize selected (taxid, offset) pairs; an offset marks an expanded "Other lineages" aggregate."""
    return "/".join(f"{t}~{o}" if o else str(t) for t, o in steps)


class Taxonomy:
    def __init__(self, path=DATABASE, common_names=COMMON_NAMES, icons=ICONS):
        self.path = Path(path)
        self.english, self.english_sources = {}, {}
        if Path(common_names).exists():
            payload = json.loads(Path(common_names).read_text())
            self.english = {int(t): name for t, name in payload["names"].items()}
            self.english_sources = payload.get("sources", {})
        self.icons, self.icon_credits, self.icon_meta = {}, {}, {}
        if Path(icons).exists():
            payload = json.loads(Path(icons).read_text())
            self.icon_meta = {k: v for k, v in payload.items() if k not in ("images", "taxa")}
            self.icon_credits = payload.get("images", {})
            self.icons = {int(t): image for t, image in payload.get("taxa", {}).items()
                          if (ICON_DIR / f"{image}.svg").exists()}
        self._inherited_icons = {}
        with closing(self.connect()) as conn:
            self.metadata = json.loads(conn.execute("SELECT value FROM metadata").fetchone()[0])
            self.eukaryote_ids = frozenset(r[0] for r in conn.execute(EUK_TREE + "SELECT taxid FROM euk"))
            self.eukaryotes = dict(conn.execute("SELECT * FROM taxa WHERE taxid=?", (EUKARYOTA,)).fetchone())
        self.coverage = self.metadata.get("coverage")

    def connect(self):
        conn = sqlite3.connect(f"{self.path.resolve().as_uri()}?mode=ro", uri=True)
        conn.row_factory = sqlite3.Row
        return conn

    def search(self, query):
        query = str(query or "").strip()
        aliases = {"animals": "33208", "plants": "33090", "green plants": "33090", "eukaryotes": "2759"}
        query = aliases.get(query.casefold(), query)
        with closing(self.connect()) as conn:
            if query.lstrip("-").isdigit():
                rows = conn.execute(EUK_TREE + "SELECT taxa.* FROM taxa JOIN euk USING(taxid) WHERE taxid=?", (int(query),)).fetchall()
            else:
                pattern = "%" + query.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_") + "%"
                rows = conn.execute(EUK_TREE + "SELECT taxa.* FROM taxa JOIN euk USING(taxid) WHERE name LIKE ? ESCAPE '\\' ORDER BY total_count DESC LIMIT 100", (pattern,)).fetchall()
        return [(f"{r['name']} · {r['total_count']:,} assemblies · taxid {r['taxid']}", str(r['taxid'])) for r in rows]

    def icon_for(self, conn, taxid):
        """Nearest icon at or above this taxon, following the lineage to Eukaryota.

        Returns the image and whether it belongs to this taxon or was borrowed.
        """
        if taxid in self.icons:
            return self.icons[taxid], False
        if taxid in self._inherited_icons:
            return self._inherited_icons[taxid], True
        walked, current = [], taxid
        for _ in range(MAX_DEPTH):
            row = conn.execute("SELECT parent_id FROM taxa WHERE taxid=?", (current,)).fetchone()
            if row is None or row['parent_id'] == current:
                break
            walked.append(current)
            current = row['parent_id']
            if current in self.icons or current in self._inherited_icons:
                break
        found = self.icons.get(current) or self._inherited_icons.get(current, "")
        for step in walked:
            self._inherited_icons[step] = found
        return found, True

    def lineage(self, conn, taxid):
        rows = [dict(conn.execute("SELECT * FROM taxa WHERE taxid=?", (taxid,)).fetchone())]
        while rows[-1]['taxid'] != EUKARYOTA:
            rows.append(dict(conn.execute("SELECT * FROM taxa WHERE taxid=?", (rows[-1]['parent_id'],)).fetchone()))
        return rows[::-1]

    def taxon_path(self, taxid):
        """Path that expands every ancestor of a taxon, for search results and shortcuts."""
        taxid = int(taxid)
        if taxid not in self.eukaryote_ids:
            raise ValueError("Choose a eukaryotic taxon from this snapshot.")
        with closing(self.connect()) as conn:
            return encode_path((r['taxid'], 0) for r in self.lineage(conn, taxid))

    def view_taxon(self, taxid):
        return self.view(self.taxon_path(taxid))

    def view(self, path=DEFAULT_PATH):
        """Render one column per expanded group. A path lists the selected node of each column."""
        try:
            steps = [(int(t), int(o or 0)) for t, _, o in (part.partition("~") for part in str(path).split("/"))]
        except ValueError as exc:
            raise ValueError("Choose a eukaryotic taxon from this snapshot.") from exc
        if steps[0] != (EUKARYOTA, 0) or len(steps) > MAX_DEPTH or any(
                t not in self.eukaryote_ids or o < 0 for t, o in steps):
            raise ValueError("Choose a eukaryotic taxon from this snapshot.")
        with closing(self.connect()) as conn:
            def taxon(t):
                return dict(conn.execute("SELECT * FROM taxa WHERE taxid=?", (t,)).fetchone())

            def node(row, offset=0, **extra):
                return dict(taxid=row['taxid'], offset=offset, name=row['name'], label=row['name'],
                            english=self.english.get(row['taxid'], ""),
                            **dict(zip(("icon", "borrowed_icon"), self.icon_for(conn, row['taxid']))),
                            total=row['total_count'], covered=row.get('covered_total', 0), **extra)

            def remainder(rows, parent, start):
                return dict(taxid=parent, offset=start, name=f"Other lineages · {len(rows):,} groups (display aggregate)",
                            label=f"Other lineages ({len(rows):,})", english="", icon="", borrowed_icon=False, total=sum(r['total_count'] for r in rows),
                            covered=sum(r.get('covered_total', 0) for r in rows), aggregate=True)

            def column(step, selected):
                """Direct lineages of a selected node, keeping the next selection visible."""
                parent, offset = step
                rows = [dict(r) for r in conn.execute("SELECT * FROM taxa WHERE parent_id=? AND taxid!=? ORDER BY total_count DESC, taxid", (parent, parent))]
                if offset and offset >= len(rows):
                    raise ValueError("This group has no further lineages.")
                shown, rest = rows[offset:offset + COLUMN_LIMIT], rows[offset + COLUMN_LIMIT:]
                pinned = [r for r in rest if selected and not selected[1] and r['taxid'] == selected[0]]
                shown, rest = shown + pinned, [r for r in rest if r not in pinned]
                nodes = [node(r) for r in shown]
                if rest:
                    nodes.append(remainder(rest, parent, offset + COLUMN_LIMIT))
                row = taxon(parent)
                if not offset and row['direct_count'] and rows:
                    nodes.append(dict(taxid=parent, offset=0, name="Assemblies assigned directly to this taxon",
                                      label="Direct assignments", english="", icon="", borrowed_icon=False, total=row['direct_count'],
                                      covered=row.get('covered_direct', 0), direct=True))
                return nodes

            columns = [[node(taxon(EUKARYOTA))]]
            for depth, step in enumerate(steps[1:], 1):
                if step[1] and (step[0] != steps[depth - 1][0] or step[1] <= steps[depth - 1][1]) or \
                        not step[1] and taxon(step[0])['parent_id'] != steps[depth - 1][0]:
                    raise ValueError("Choose a eukaryotic taxon from this snapshot.")
                columns.append(column(steps[depth - 1], step))
            tail = column(steps[-1], None)
            if tail:
                columns.append(tail)
            for depth, nodes in enumerate(columns):
                for item in nodes:
                    item['path'] = encode_path(steps[:depth] + [(item['taxid'], item['offset'])])
                    item['selected'] = depth < len(steps) and not item.get('direct') and \
                        (item['taxid'], item['offset']) == steps[depth]
                if depth < len(steps) and not any(item['selected'] for item in nodes):
                    raise ValueError("Choose a eukaryotic taxon from this snapshot.")
            lineage = [taxon(t) for t, _ in steps]
            shortcuts = {t: encode_path((r['taxid'], 0) for r in self.lineage(conn, t)) for t in (33208, 33090, 4751)}
        return self.render(columns, steps, lineage, shortcuts, has_children=bool(tail))

    def render(self, columns, steps, lineage, shortcuts, has_children):
        top, chart, spacing, bar = 24, 460, 274, 14
        # Silhouettes are not square: they run from tall and thin to long and
        # flat. Fitting them all into one box turns most into slivers, so each
        # gets its own box with the same area and its own proportions.
        icon_area, icon_max, gutter = 23 * 23, 40, 46
        width = max(830, 40 + (len(columns) - 1) * spacing + bar + 250)
        height = top * 2 + chart

        def stack(nodes):
            """Sankey layout: bar heights follow assembly counts, with room for every label."""
            gap, slot = (12 if len(nodes) > 1 else 0), 46
            fixed, scale = set(), 0
            for _ in range(len(nodes) + 1):
                free = chart - gap * (len(nodes) - 1) - slot * len(fixed)
                flexible = sum(n['total'] for k, n in enumerate(nodes) if k not in fixed)
                scale = free / flexible if flexible else 0
                small = fixed | {k for k, n in enumerate(nodes) if n['total'] * scale < slot}
                if small == fixed:
                    break
                fixed = small
            y = top
            for k, n in enumerate(nodes):
                room = slot if k in fixed else n['total'] * scale
                n['h'] = max(3, n['total'] * scale)
                n['y'] = y + (room - n['h']) / 2
                y += room + gap

        def clip(text, limit):
            return text if len(text) <= limit else text[:limit - 2] + "…"

        def share(n):
            return n['covered'] / n['total'] if self.coverage and n['total'] else 0

        def ribbon(x0, a0, a1, x1, b0, b1, kind):
            bend = (x0 + x1) / 2
            return (f'<path d="M{x0},{a0:.1f} C{bend},{a0:.1f} {bend},{b0:.1f} {x1},{b0:.1f} '
                    f'L{x1},{b1:.1f} C{bend},{b1:.1f} {bend},{a1:.1f} {x0},{a1:.1f} Z" class="flow flow-{kind}"/>')

        flows, nodes = [], []
        for depth, column in enumerate(columns):
            stack(column)
            x = 40 + depth * spacing
            for n in column:
                n['x'] = x
        for depth, column in enumerate(columns[:-1]):
            parent = next((n for n in column if n['selected']), None)
            children = columns[depth + 1]
            if not parent:
                continue
            total = sum(c['total'] for c in children) or 1
            cursor = parent['y']
            for child in children:
                a0 = cursor
                a1 = cursor + parent['h'] * child['total'] / total
                cursor = a1
                f = share(child)
                am, bm = a0 + f * (a1 - a0), child['y'] + f * child['h']
                x0, x1 = parent['x'] + bar, child['x']
                if f > 0:
                    flows.append(ribbon(x0, a0, am, x1, child['y'], bm, "annotated"))
                if f < 1:
                    flows.append(ribbon(x0, am, a1, x1, bm, child['y'] + child['h'], "missing"))

        for depth, column in enumerate(columns):
            on_path = depth < len(steps)
            shown = Counter(n['icon'] for n in column if n['icon'])
            for n in column:
                if n['borrowed_icon'] and shown[n['icon']] > 1:
                    n['icon'] = ""  # identical borrowed outlines read as "same group"
                x, y, h = n['x'], n['y'], n['h']
                f = share(n)
                percent = 100 * f
                title = f"{n['name']} ({n['english']})" if n['english'] else n['name']
                detail = (f"{title} · {n['covered']:,} of {n['total']:,} assemblies have published annotations ({percent:.2f}%). Includes partial assemblies."
                          if self.coverage else f"{title} · {n['total']:,} assemblies. Coverage inventory unavailable.")
                if n.get('aggregate'):
                    detail += " Display aggregate, not a taxonomic clade. Activate to see its lineages."
                elif not n.get('direct') and not n['selected']:
                    detail += " Activate to expand this group to the right."
                action = "" if n.get('direct') else f'data-path="{n["path"]}" role="button" tabindex="0"'
                classes = "tree-node" + (" is-selected" if n['selected'] else " is-sibling" if on_path else "") + \
                    (" is-direct" if n.get('direct') else "")
                nodes.append(f'<g class="{classes}" {action} aria-label="{escape(detail, quote=True)}" data-detail="{escape(detail, quote=True)}">')
                cy = y + h / 2
                nodes.append(f'<rect x="{x - 6}" y="{min(y, cy - 23):.1f}" width="{spacing - 40}" height="{max(h, 46):.1f}" rx="10" class="tree-hit"/>')
                green = h * f
                if green > 0:
                    nodes.append(f'<rect x="{x}" y="{y:.1f}" width="{bar}" height="{green:.1f}" class="bar bar-annotated"/>')
                if green < h:
                    nodes.append(f'<rect x="{x}" y="{y + green:.1f}" width="{bar}" height="{h - green:.1f}" class="bar bar-missing"/>')
                nodes.append(f'<rect x="{x}" y="{y:.1f}" width="{bar}" height="{h:.1f}" class="bar-outline"/>')
                label, english = clip(n['label'], MAX_LABEL), clip(n['english'], MAX_ENGLISH)
                stats = f"{percent:.1f}% · {n['covered']:,} / {n['total']:,}" if self.coverage else f"{n['total']:,} assemblies"
                # The gutter is reserved whether or not this node has a silhouette, so
                # labels stay aligned down the column.
                if n['icon']:
                    ratio = self.icon_credits.get(n['icon'], {}).get('ratio') or 1.0
                    icon_h = min(icon_max, max(6, math.sqrt(icon_area / ratio)))
                    icon_w = min(icon_max, max(6, icon_h * ratio))
                    icon_h = min(icon_max, max(6, icon_w / ratio))
                    nodes.append(f'<image class="tree-icon" x="{x + bar + 8 + (gutter - 12 - icon_w) / 2:.1f}" y="{cy - icon_h / 2:.1f}" '
                                 f'width="{icon_w:.1f}" height="{icon_h:.1f}" '
                                 f'href="{ICON_ROUTE}{ICON_DIR / (n["icon"] + ".svg")}"/>')
                text_x = x + bar + 8 + gutter
                # Three lines when there is an English gloss, two without, both centred on the bar.
                head, stat_line = (cy - 10, cy + 16) if english else (cy - 3, cy + 13)
                nodes.append(f'<text x="{text_x}" y="{head:.1f}" class="tree-label">{escape(label)}</text>')
                if english:
                    nodes.append(f'<text x="{text_x}" y="{cy + 3:.1f}" class="tree-english">{escape(english)}</text>')
                nodes.append(f'<text x="{text_x}" y="{stat_line:.1f}" class="tree-count">{stats}</text></g>')
        svg = (f'<svg viewBox="0 0 {width} {height}" class="life-tree" data-route="{encode_path(steps)}" style="min-width:{width if width > 1040 else 760}px" '
               f'aria-label="Eukaryotic taxonomy and annotation coverage">' + ''.join(flows) + ''.join(nodes) + '</svg>')

        focus = next(n for n in columns[len(steps) - 1] if n['selected'])
        total, covered = focus['total'], focus['covered']
        percent = 100 * covered / total if self.coverage and total else 0
        selected_name = f"Other lineages of {lineage[-1]['name']}" if focus.get('aggregate') else focus['label']
        if focus.get('english'):
            selected_name += f" · {focus['english']}"
        crumbs = []
        for depth, (row, (_, offset)) in enumerate(zip(lineage, steps)):
            name = "Other lineages" if offset else row['name']
            crumbs.append(f'<button data-path="{encode_path(steps[:depth + 1])}">{escape(name)}</button>')
        breadcrumbs = ' <span class="crumb-divider">/</span> '.join(crumbs)
        parent = encode_path(steps[:-1] or steps)
        stamp = (self.coverage or self.metadata)['created_at'][:10]
        if self.coverage:
            summary = (f'<div class="atlas-kicker">{escape(selected_name)} · ASSEMBLY COVERAGE</div>'
                       f'<div class="atlas-summary"><strong>{covered:,}</strong><span>of {total:,}<br>assemblies annotated</span>'
                       f'<b class="atlas-badge">{percent:.1f}%</b></div>')
            legend = ('<div class="atlas-legend"><i class="atlas-swatch atlas-annotated"></i><span>Annotated</span>'
                      '<i class="atlas-swatch atlas-missing"></i><span>Not annotated</span></div>')
        else:
            summary = f'<div class="atlas-kicker">{escape(selected_name)}</div><div class="atlas-summary"><strong>{total:,}</strong><span>GenBank assemblies<br>Coverage unavailable</span></div>'
            legend = '<div class="atlas-legend"><i class="atlas-swatch atlas-missing"></i><span>Assemblies · coverage unavailable</span></div>'
        leaf_note = '<p class="atlas-leaf-note">This is a terminal taxon in the assembly snapshot. Use the breadcrumb to explore its relatives.</p>' if not has_children else ''
        return f'''<section class="atlas" aria-label="Tree of eukaryotic life">
          <header class="atlas-header">
            <div><div class="atlas-kicker">HUGGING FACE BIO <span> / </span> GENOME ATLAS</div>
              <h1>The tree of eukaryotic life<span>.</span></h1>
              <p>Follow the branches. Discover where we’ve annotated.</p></div>
            <div class="atlas-summary-block">{summary}</div>
          </header>
          <nav class="atlas-nav" aria-label="Explore major lineages">
            <div class="atlas-shortcuts"><button data-path="{DEFAULT_PATH}">All eukaryotes</button>
            <button data-path="{shortcuts[33208]}">Animals</button><button data-path="{shortcuts[33090]}">Green plants</button>
            <button data-path="{shortcuts[4751]}">Fungi</button></div>
            <button class="atlas-back" data-path="{parent}">← Collapse last group</button>
          </nav>
          <div class="atlas-breadcrumb">{breadcrumbs}</div>
          <div class="tree-scroll" tabindex="0" aria-label="Interactive tree. Scroll horizontally to see deeper lineages.">{svg}</div>
          {leaf_note}<div class="atlas-tooltip" role="tooltip" hidden></div>
          <footer class="atlas-footer">{legend}
            <span>Click a group to expand it to the right <span class="atlas-mobile-hint">· Swipe to explore</span></span>
            <span class="atlas-date">Updated {stamp}</span></footer>
          <div class="atlas-footnote">Bar and flow heights are proportional to assembly counts within each column; each column is rescaled to fill the height, so compare sizes within a column. Coverage counts assemblies with published annotations, including partial assemblies.</div>
        </section>'''


def credit_lines(taxonomy):
    """One line per artist, as CC BY asks, with the licences their images carry."""
    artists = {}
    for image in set(taxonomy.icons.values()):
        meta = taxonomy.icon_credits.get(image, {})
        name = meta.get("attribution") or meta.get("contributor") or "Unknown artist"
        entry = artists.setdefault(name, {"licenses": set(), "pages": []})
        entry["licenses"].add(LICENSE_NAMES.get(meta.get("license"), meta.get("license") or "unknown licence"))
        entry["pages"].append(meta.get("page"))
    lines = []
    for name in sorted(artists, key=str.casefold):
        entry = artists[name]
        count = len(entry["pages"])
        lines.append(f"- [{name}]({entry['pages'][0]}) — {', '.join(sorted(entry['licenses']))}"
                     f"{f' — {count} silhouettes' if count > 1 else ''}")
    return lines


def build_taxonomy_tab():
    """Render the tree and its controls inside the Genome atlas tab."""
    if not DATABASE.exists():
        gr.Markdown("The eukaryotic tree will appear when the taxonomy snapshot is available.")
        return
    taxonomy = Taxonomy()
    if taxonomy.icons:
        # The chart references each silhouette by URL, so the browser caches it
        # once instead of the file riding along in every re-render.
        gr.set_static_paths(paths=[ICON_DIR])
    tree = gr.HTML(taxonomy.view(), css_template=(ROOT / "atlas.css").read_text(),
                   js_on_load=(ROOT / "atlas.js").read_text(), apply_default_css=False,
                   elem_id="eukaryotic-atlas")

    def explore_tree(evt: gr.EventData):
        try:
            return taxonomy.view(evt.route)
        except (ValueError, TypeError, AttributeError) as exc:
            raise gr.Error("Choose a eukaryotic group in this snapshot.") from exc

    tree.click(explore_tree, outputs=tree, show_progress="minimal", concurrency_limit=1)
    with gr.Accordion("Find a lineage", open=False, elem_classes="atlas-disclosure"):
        with gr.Row():
            query = gr.Textbox(label="Eukaryotic taxon", placeholder="Scientific name, taxon ID, or a group such as animals")
            find = gr.Button("Search lineages", elem_classes="action-button")
        matches = gr.Dropdown(choices=[], label="Matching lineages", interactive=True)
        status = gr.Markdown()

        def taxonomy_search(text):
            choices = taxonomy.search(text) if str(text or '').strip() else []
            return gr.Dropdown(choices=choices, value=None), f"{len(choices)} results (up to 100, largest first)." if choices else "No matching eukaryotic taxa in this snapshot."

        def taxonomy_view(taxid):
            return taxonomy.view_taxon(taxid) if taxid else taxonomy.view()

        matches.input(taxonomy_view, matches, tree)
        find.click(taxonomy_search, query, [matches, status])
        query.submit(taxonomy_search, query, [matches, status])
    if taxonomy.icons:
        with gr.Accordion("Silhouette credits", open=False, elem_classes="atlas-disclosure"):
            gr.Markdown("\n".join(["Silhouettes from [PhyloPic](https://www.phylopic.org), used unmodified. "
                                   "Public-domain images need no credit; the CC BY ones do, and every artist is listed here. "
                                   "`data/icons.json` maps each taxon to its image.", ""] + credit_lines(taxonomy)))
    with gr.Accordion("About the tree and coverage", open=False, elem_classes="atlas-disclosure"):
        gr.Markdown("This tree follows **NCBI Taxonomy within Eukaryota**. Animals and fungi share the Opisthokonta branch; "
                    "green plants include green algae. ‘Other lineages’ combines the remaining siblings for display and can be expanded. "
                    "Each expanded group adds a column on the right with up to six direct lineages plus any remainder, so every ancestor stays visible. "
                    "The opening view also expands the animal/fungal branch. Bars and flows are drawn like a Sankey diagram: "
                    "heights follow **actual assembly counts** within each column, split into annotated and not-annotated assemblies.\n\n"
                    "Each group shows its scientific name with a plain-English name underneath where one is available. These come from "
                    "NCBI Taxonomy's common names plus a curated set of short glosses for the large unranked clades NCBI leaves unnamed, "
                    "such as Opisthokonta (animals and fungi) or Ecdysozoa (moulting animals). The glosses describe the living members of a "
                    "clade in everyday words; they are not formal taxonomic synonyms, so the scientific name stays the primary label.\n\n"
                    "Coverage means the fraction of current GenBank assembly versions with published annotations, including partial assemblies. "
                    "It does not measure the fraction of bases annotated. Parent counts include descendants once each. "
                    "Exact accession versions are matched. The Database tab searches a dated snapshot of all published annotation files.\n\n"
                    "Sources: [NCBI assembly summary](https://ftp.ncbi.nlm.nih.gov/genomes/ASSEMBLY_REPORTS/assembly_summary_genbank.txt), "
                    "[NCBI Taxonomy](https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdump.tar.gz) for both the tree and its common names, "
                    "and [published annotations](https://huggingface.co/buckets/HuggingFaceBio/genbank-annotations).")
        if taxonomy.icons:
            gr.Markdown("Silhouettes come from [PhyloPic](https://www.phylopic.org), resolved from each taxon's NCBI ID and "
                        "stored unmodified. Only public-domain (CC0) and CC BY 4.0 images are used; NonCommercial and "
                        "ShareAlike images are filtered out at build time. A group without a silhouette of its own borrows "
                        "its nearest illustrated ancestor, so a fungal genus shows the fungal outline.")
        coverage = taxonomy.coverage or {}
        gr.JSON({"taxonomy_updated": taxonomy.metadata['created_at'], "coverage_updated": coverage.get('created_at'),
                 "silhouettes": taxonomy.icon_meta or None,
                 "display_scope": "Eukaryota (NCBI taxid 2759) and its descendants only",
                 "inventory_method": coverage.get('method'),
                 "published_versions_outside_current_GenBank_snapshot": coverage.get('unmatched_assembly_versions'),
                 "sources": taxonomy.metadata['sources']}, label="Snapshot provenance")