AnyBot/box/a11y

#!/usr/bin/env python3
"""The controls on the box's desktop, from its accessibility tree (AT-SPI), as JSON:
{"elements": [{"role", "name", "value", "x", "y", "w", "h", "active", "flags", "window"}]}
in screen pixels. Web pages are in it too (Chromium runs with renderer accessibility on).
AnyBot numbers them on the bot's picture; a click by number lands on the centre.

Adapted from XBot's box/box-a11y. Usage: a11y [--limit N] [--budget SECONDS]
Exit 2 when AT-SPI itself is unreachable.
"""
import json
import os
import sys
import time
import warnings

warnings.filterwarnings("ignore", category=DeprecationWarning)

# Clicked or typed into (they get a number).
ACTIVE = {
    "push button", "toggle button", "radio button", "check box", "link", "menu item", "check menu item",
    "radio menu item", "tab", "page tab", "list item", "tree item", "combo box", "spin button", "slider",
    "entry", "password text", "menu",
}
# Listed when they carry words (headings, labels, cells...).
NAMED = {"heading", "label", "static", "text", "image", "table cell", "column header", "row header", "icon",
         "tool tip", "alert", "dialog", "paragraph"}
# The desktop's own parts are visible in the picture; the list is for the windows worked in.
SKIP_APPS = {"fluxbox", "a11y", "python3", "xterm-wrapper"}


def main():
    limit, budget = 400, 3.0
    args = sys.argv[1:]
    for i, a in enumerate(args):
        if a == "--limit":
            limit = int(args[i + 1])
        if a == "--budget":
            budget = float(args[i + 1])
    if not os.environ.get("DBUS_SESSION_BUS_ADDRESS"):
        try:
            for line in open("/tmp/anybot-dbus.env", encoding="utf-8"):
                k, _, v = line.strip().partition("=")
                if k == "DBUS_SESSION_BUS_ADDRESS" and v:
                    os.environ[k] = v
        except OSError:
            pass
    os.environ.setdefault("DISPLAY", ":1")
    try:
        import gi
        gi.require_version("Atspi", "2.0")
        from gi.repository import Atspi
        Atspi.init()
        desktop = Atspi.get_desktop(0)
        apps = desktop.get_child_count()
    except Exception as exc:  # noqa: BLE001
        print(f"AT-SPI unreachable: {exc}", file=sys.stderr)
        return 2

    sw, sh = 0, 0
    try:
        geo = os.popen("xdotool getdisplaygeometry 2>/dev/null").read().split()
        sw, sh = int(geo[0]), int(geo[1])
    except Exception:  # noqa: BLE001
        pass
    deadline = time.monotonic() + budget
    out = []

    def state(node):
        try:
            return node.get_state_set()
        except Exception:  # noqa: BLE001
            return None

    def extents(node):
        try:
            r = node.get_component_iface().get_extents(Atspi.CoordType.SCREEN)
            return int(r.x), int(r.y), int(r.width), int(r.height)
        except Exception:  # noqa: BLE001
            return None

    def onscreen(b):
        x, y, w, h = b
        if w <= 0 or h <= 0 or x + w <= 0 or y + h <= 0:
            return False
        return not (sw and x >= sw) and not (sh and y >= sh)

    def walk(node, depth, window):
        if time.monotonic() > deadline or len(out) >= limit or depth > 45:
            return
        try:
            role = node.get_role_name()
        except Exception:  # noqa: BLE001
            return
        st = state(node)
        if depth > 1 and (st is None or not (st.contains(Atspi.StateType.SHOWING) and st.contains(Atspi.StateType.VISIBLE))):
            return
        box = extents(node)
        if depth > 1 and (box is None or not onscreen(box)):
            return
        try:
            name = (node.get_name() or "").strip()
        except Exception:  # noqa: BLE001
            name = ""
        if role in ("frame", "dialog", "window") and name:
            window = name
        editable = bool(st and st.contains(Atspi.StateType.EDITABLE))
        value = ""
        if (role in ("entry", "password text", "text", "spin button", "slider") or editable) and role != "password text":
            try:
                t = node.get_text_iface()
                if t is not None:
                    value = (t.get_text(0, min(t.get_character_count(), 200)) or "").strip()
            except Exception:  # noqa: BLE001
                pass
        active = role in ACTIVE or (editable and role in ("text", "paragraph", "section", "document web"))
        if depth > 1 and box is not None and (active or (role in NAMED and (name or value))):
            flags = []
            if st is not None:
                for s, word in ((Atspi.StateType.FOCUSED, "focused"), (Atspi.StateType.CHECKED, "checked"),
                                (Atspi.StateType.SELECTED, "selected")):
                    if st.contains(s):
                        flags.append(word)
                if not st.contains(Atspi.StateType.ENABLED):
                    flags.append("disabled")
            x, y, w, h = box
            out.append({"role": role, "name": name[:120], "value": value[:200], "x": x, "y": y, "w": w, "h": h,
                        "active": active, "flags": flags, "window": window})
        try:
            n = node.get_child_count()
        except Exception:  # noqa: BLE001
            return
        for i in range(min(n, 2000)):
            try:
                c = node.get_child_at_index(i)
            except Exception:  # noqa: BLE001
                continue
            if c is not None:
                walk(c, depth + 1, window)

    for i in range(apps):
        try:
            app = desktop.get_child_at_index(i)
            name = app.get_name() or ""
        except Exception:  # noqa: BLE001
            continue
        if name in SKIP_APPS:
            continue
        walk(app, 0, name)
    json.dump({"elements": out, "truncated": len(out) >= limit or time.monotonic() > deadline}, sys.stdout, ensure_ascii=False)
    return 0


if __name__ == "__main__":
    sys.exit(main())