BigBrainParking/tools/citymap/extract_map.py

#!/usr/bin/env python3
"""Extract the color-coded parking geometry from the city's parking-map PDF.

pdftocairo emits every street segment as a stroked <path> carrying its own
matrix() transform with local coordinates, and every lot as an absolute filled
<path>. So: parse the path, flatten curves, push through the path's own matrix,
and bucket by the exact colour pdftocairo wrote.

Output is GeoJSON-shaped but still in SVG *page* coordinates (y down); the
georeferencing step turns that into lat/lon.
"""
import json
import re
import sys
from xml.etree import ElementTree as ET

SVG = sys.argv[1] if len(sys.argv) > 1 else "/tmp/map.svg"
OUT = sys.argv[2] if len(sys.argv) > 2 else "map_page_coords.json"

# Colours exactly as pdftocairo writes them, mapped to the map legend.
COLORS = {
    "rgb(76.499939%, 76.899719%, 76.098633%)": "no_limit",
    "rgb(96.899414%, 54.499817%, 3.09906%)": "limit_4h",
    "rgb(79.998779%, 77.2995%, 25.898743%)": "limit_3h",
    "rgb(82.699585%, 40.39917%, 79.998779%)": "free_2h",
    "rgb(45.899963%, 69.799805%, 34.899902%)": "green_lot",
}

NUM = re.compile(r"[-+]?(?:\d*\.\d+|\d+\.?)(?:[eE][-+]?\d+)?")


def parse_matrix(s):
    """matrix(a,b,c,d,e,f) -> tuple. Identity when absent."""
    if not s:
        return (1.0, 0.0, 0.0, 1.0, 0.0, 0.0)
    m = re.search(r"matrix\s*\(([^)]*)\)", s)
    if not m:
        return (1.0, 0.0, 0.0, 1.0, 0.0, 0.0)
    v = [float(x) for x in NUM.findall(m.group(1))]
    return tuple(v[:6])


def apply(mtx, x, y):
    a, b, c, d, e, f = mtx
    return (a * x + c * y + e, b * x + d * y + f)


def bezier(p0, p1, p2, p3, steps=8):
    """Flatten a cubic to points. The map's curves are gentle; 8 is plenty."""
    out = []
    for i in range(1, steps + 1):
        t = i / steps
        u = 1 - t
        out.append(
            (
                u * u * u * p0[0] + 3 * u * u * t * p1[0] + 3 * u * t * t * p2[0] + t * t * t * p3[0],
                u * u * u * p0[1] + 3 * u * u * t * p1[1] + 3 * u * t * t * p2[1] + t * t * t * p3[1],
            )
        )
    return out


def parse_path(d):
    """Return a list of subpaths [(points, closed)] in the path's local space."""
    tokens = re.findall(r"([MmLlHhVvCcSsZz])|([-+]?(?:\d*\.\d+|\d+\.?)(?:[eE][-+]?\d+)?)", d)
    subpaths, pts = [], []
    cur = (0.0, 0.0)
    start = (0.0, 0.0)
    cmd = None
    i = 0
    flat = [(c, n) for c, n in tokens]

    def nums(k):
        nonlocal i
        vals = []
        while len(vals) < k and i < len(flat) and flat[i][1]:
            vals.append(float(flat[i][1]))
            i += 1
        return vals

    while i < len(flat):
        c, n = flat[i]
        if c:
            cmd = c
            i += 1
        elif cmd is None:
            i += 1
            continue
        if cmd in "Zz":
            if pts:
                subpaths.append((pts, True))
                pts = []
            cur = start
            cmd = None
            continue
        if cmd in "Mm":
            v = nums(2)
            if len(v) < 2:
                break
            if pts:
                subpaths.append((pts, False))
                pts = []
            cur = (v[0], v[1]) if cmd == "M" else (cur[0] + v[0], cur[1] + v[1])
            start = cur
            pts = [cur]
            cmd = "L" if cmd == "M" else "l"
        elif cmd in "Ll":
            v = nums(2)
            if len(v) < 2:
                break
            cur = (v[0], v[1]) if cmd == "L" else (cur[0] + v[0], cur[1] + v[1])
            pts.append(cur)
        elif cmd in "Hh":
            v = nums(1)
            if not v:
                break
            cur = (v[0], cur[1]) if cmd == "H" else (cur[0] + v[0], cur[1])
            pts.append(cur)
        elif cmd in "Vv":
            v = nums(1)
            if not v:
                break
            cur = (cur[0], v[0]) if cmd == "V" else (cur[0], cur[1] + v[0])
            pts.append(cur)
        elif cmd in "Cc":
            v = nums(6)
            if len(v) < 6:
                break
            if cmd == "C":
                p1, p2, p3 = (v[0], v[1]), (v[2], v[3]), (v[4], v[5])
            else:
                p1 = (cur[0] + v[0], cur[1] + v[1])
                p2 = (cur[0] + v[2], cur[1] + v[3])
                p3 = (cur[0] + v[4], cur[1] + v[5])
            pts.extend(bezier(cur, p1, p2, p3))
            cur = p3
        else:
            i += 1
    if pts:
        subpaths.append((pts, False))
    return subpaths


def main():
    tree = ET.parse(SVG)
    root = tree.getroot()
    ns = "{http://www.w3.org/2000/svg}"

    features = []
    for el in root.iter(ns + "path"):
        stroke = (el.get("stroke") or "").strip()
        fill = (el.get("fill") or "").strip()
        kind = COLORS.get(stroke) or COLORS.get(fill)
        if not kind:
            continue
        is_stroke = stroke in COLORS
        mtx = parse_matrix(el.get("transform"))
        width = float(el.get("stroke-width") or 0)
        for local, closed in parse_path(el.get("d") or ""):
            world = [apply(mtx, x, y) for x, y in local]
            if len(world) < 2:
                continue
            xs = [p[0] for p in world]
            ys = [p[1] for p in world]
            features.append(
                {
                    "kind": kind,
                    "geom": "line" if is_stroke else "polygon",
                    "closed": closed,
                    "strokeWidth": width,
                    "bbox": [min(xs), min(ys), max(xs), max(ys)],
                    "points": [[round(x, 3), round(y, 3)] for x, y in world],
                }
            )

    with open(OUT, "w") as fh:
        json.dump({"viewBox": [0, 0, 491.87, 529.043], "features": features}, fh, indent=1)

    from collections import Counter
    print(f"{len(features)} features -> {OUT}")
    for (k, g), n in sorted(Counter((f["kind"], f["geom"]) for f in features).items()):
        print(f"  {k:10s} {g:8s} {n}")
    # Where are they? Legend swatches cluster in one corner; real geometry spreads out.
    print("\nbbox spread by kind:")
    for k in COLORS.values():
        fs = [f for f in features if f["kind"] == k]
        if not fs:
            continue
        print(
            f"  {k:10s} x[{min(f['bbox'][0] for f in fs):7.1f},{max(f['bbox'][2] for f in fs):7.1f}] "
            f"y[{min(f['bbox'][1] for f in fs):7.1f},{max(f['bbox'][3] for f in fs):7.1f}]"
        )


main()