feat(raster): IO abstraction with godal implementation; cgo Dockerfile

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

build/package/Dockerfile

@@ -1,5 +1,8 @@
 # Build context is the repo root: docker build -f build/package/Dockerfile .
-FROM golang:1.26.1-alpine AS builder
+FROM golang:1.26-alpine AS builder
+
+# godal (GDAL bindings) needs cgo, a C toolchain and the GDAL headers.
+RUN apk add --no-cache gdal-dev gcc musl-dev pkgconfig
 
 WORKDIR /src
 
@@ -7,13 +10,13 @@ COPY go.mod go.sum ./
 RUN go mod download
 
 COPY . .
-RUN CGO_ENABLED=0 GOOS=linux go build -trimpath -o /out/gis ./cmd/gis
+RUN CGO_ENABLED=1 GOOS=linux go build -trimpath -o /out/gis ./cmd/gis
 
-FROM alpine:3.20
+FROM alpine:3.22
 
-# gdal-tools provides gdal_translate / gdalinfo for raster COG conversion and
+# gdal: shared library for godal (raster math in the worker).
-# ogr2ogr for extracting vector feature geometry (worker).
+# gdal-tools: gdal_translate / gdalinfo (COG conversion) and ogr2ogr.
-RUN apk add --no-cache ca-certificates tzdata gdal-tools \
+RUN apk add --no-cache ca-certificates tzdata gdal gdal-tools \
     && adduser -D -u 10001 app
 
 WORKDIR /app

go.mod

@@ -5,6 +5,7 @@ go 1.26.1
 toolchain go1.26.2
 
 require (
+	github.com/airbusgeo/godal v0.0.18
 	github.com/caarlos0/env/v11 v11.4.1
 	github.com/go-chi/chi/v5 v5.3.0
 	github.com/go-playground/validator/v10 v10.30.3

go.sum

@@ -1,3 +1,5 @@
+github.com/airbusgeo/godal v0.0.18 h1:NQJ9P7OgSs5zVtlWH/tOta7QHYbbtha7Nttf63YM01Q=
+github.com/airbusgeo/godal v0.0.18/go.mod h1:Mpn/6exBzEbIx4DaG2rIjCmAiF9Ww4SJN2ZtwVsSwCo=
 github.com/caarlos0/env/v11 v11.4.1 h1:fYwH0sWEsBSMPG7t4e/PEfTFzrWrpjyygXyUnWiSwEw=
 github.com/caarlos0/env/v11 v11.4.1/go.mod h1:qupehSf/Y0TUTsxKywqRt/vJjN5nz6vauiYEUUr8P4U=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=

internal/raster/godal.go

@@ -0,0 +1,133 @@
+package raster
+
+import (
+	"context"
+	"fmt"
+	"math"
+	"sync"
+
+	"github.com/airbusgeo/godal"
+)
+
+var registerOnce sync.Once
+
+// GodalIO implements IO with the GDAL bindings (github.com/airbusgeo/godal).
+// GDAL datasets are not goroutine-safe: callers must not share a Reader or
+// Writer between goroutines without external synchronisation.
+type GodalIO struct{}
+
+// NewGodalIO registers GDAL drivers (once) and returns a GodalIO.
+func NewGodalIO() *GodalIO {
+	registerOnce.Do(godal.RegisterAll)
+	return &GodalIO{}
+}
+
+// DefaultWriterOptions returns the Landscape Program output profile.
+func DefaultWriterOptions() WriterOptions {
+	return WriterOptions{NoData: -9999, TileSize: 512, Compression: "DEFLATE"}
+}
+
+type godalReader struct {
+	ds   *godal.Dataset
+	grid Grid
+}
+
+func (g *GodalIO) Open(_ context.Context, path string) (Reader, error) {
+	ds, err := godal.Open(path)
+	if err != nil {
+		return nil, fmt.Errorf("open raster %s: %w", path, err)
+	}
+	st := ds.Structure()
+	if st.NBands < 1 {
+		ds.Close()
+		return nil, fmt.Errorf("open raster %s: no bands", path)
+	}
+	gt, err := ds.GeoTransform()
+	if err != nil {
+		ds.Close()
+		return nil, fmt.Errorf("open raster %s: geotransform: %w", path, err)
+	}
+	return &godalReader{ds: ds, grid: Grid{Width: st.SizeX, Height: st.SizeY, GeoTransform: gt, ProjectionWKT: ds.Projection()}}, nil
+}
+
+func (r *godalReader) Grid() Grid { return r.grid }
+
+func (r *godalReader) NoData() (float64, bool) { return r.ds.Bands()[0].NoData() }
+
+func (r *godalReader) ReadFloat64(w Window, dst []float64) error {
+	if len(dst) < w.Width*w.Height {
+		return fmt.Errorf("read window: dst has %d elements, need %d", len(dst), w.Width*w.Height)
+	}
+	return r.ds.Bands()[0].Read(w.X, w.Y, dst[:w.Width*w.Height], w.Width, w.Height)
+}
+
+func (r *godalReader) Close() error { return r.ds.Close() }
+
+type godalWriter struct{ ds *godal.Dataset }
+
+func (g *GodalIO) Create(_ context.Context, path string, grid Grid, o WriterOptions) (Writer, error) {
+	tile := fmt.Sprint(o.TileSize)
+	ds, err := godal.Create(godal.GTiff, path, 1, godal.Int16, grid.Width, grid.Height,
+		godal.CreationOption("TILED=YES", "BLOCKXSIZE="+tile, "BLOCKYSIZE="+tile,
+			"COMPRESS="+o.Compression, "PREDICTOR=2", "BIGTIFF=IF_SAFER"))
+	if err != nil {
+		return nil, fmt.Errorf("create raster %s: %w", path, err)
+	}
+	if err := ds.SetGeoTransform(grid.GeoTransform); err != nil {
+		ds.Close()
+		return nil, fmt.Errorf("create raster %s: geotransform: %w", path, err)
+	}
+	if grid.ProjectionWKT != "" {
+		if err := ds.SetProjection(grid.ProjectionWKT); err != nil {
+			ds.Close()
+			return nil, fmt.Errorf("create raster %s: projection: %w", path, err)
+		}
+	}
+	if err := ds.Bands()[0].SetNoData(float64(o.NoData)); err != nil {
+		ds.Close()
+		return nil, fmt.Errorf("create raster %s: nodata: %w", path, err)
+	}
+	return &godalWriter{ds: ds}, nil
+}
+
+func (w *godalWriter) WriteInt16(win Window, src []int16) error {
+	if len(src) < win.Width*win.Height {
+		return fmt.Errorf("write window: src has %d elements, need %d", len(src), win.Width*win.Height)
+	}
+	return w.ds.Bands()[0].Write(win.X, win.Y, src[:win.Width*win.Height], win.Width, win.Height)
+}
+
+func (w *godalWriter) Close() error { return w.ds.Close() }
+
+// SameGrid reports whether two grids describe the same pixels: equal size,
+// geotransform within 1e-9 (absolute), and the same CRS (GDAL IsSame; an
+// empty projection only matches an empty projection).
+//
+// ProjectionWKT is parsed with godal.NewSpatialRef rather than
+// NewSpatialRefFromWKT: despite the field name, callers may pass any user
+// projection string GDAL's SetProjection accepts (e.g. "EPSG:32642"), not
+// only WKT, and NewSpatialRefFromWKT rejects non-WKT input.
+func (g *GodalIO) SameGrid(a, b Grid) bool {
+	if a.Width != b.Width || a.Height != b.Height {
+		return false
+	}
+	for i := range a.GeoTransform {
+		if math.Abs(a.GeoTransform[i]-b.GeoTransform[i]) > 1e-9 {
+			return false
+		}
+	}
+	if a.ProjectionWKT == "" || b.ProjectionWKT == "" {
+		return a.ProjectionWKT == b.ProjectionWKT
+	}
+	sa, err := godal.NewSpatialRef(a.ProjectionWKT)
+	if err != nil {
+		return false
+	}
+	defer sa.Close()
+	sb, err := godal.NewSpatialRef(b.ProjectionWKT)
+	if err != nil {
+		return false
+	}
+	defer sb.Close()
+	return sa.IsSame(sb)
+}

internal/raster/godal_test.go

@@ -0,0 +1,62 @@
+package raster
+
+import (
+	"context"
+	"path/filepath"
+	"testing"
+)
+
+func TestGodalIO_RoundTrip(t *testing.T) {
+	rio := NewGodalIO()
+	ctx := context.Background()
+	path := filepath.Join(t.TempDir(), "out.tif")
+	grid := Grid{Width: 10, Height: 7, GeoTransform: [6]float64{100, 30, 0, 200, 0, -30}, ProjectionWKT: "EPSG:32642"}
+
+	w, err := rio.Create(ctx, path, grid, DefaultWriterOptions())
+	if err != nil {
+		t.Fatal(err)
+	}
+	full := make([]int16, 10*7)
+	for i := range full {
+		full[i] = int16(i%6) - 1 // -1..4 (-1 stands in for garbage, not nodata)
+	}
+	full[0] = -9999
+	if err := w.WriteInt16(Window{0, 0, 10, 7}, full); err != nil {
+		t.Fatal(err)
+	}
+	if err := w.Close(); err != nil {
+		t.Fatal(err)
+	}
+
+	r, err := rio.Open(ctx, path)
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer r.Close()
+	g := r.Grid()
+	if g.Width != 10 || g.Height != 7 || g.GeoTransform != grid.GeoTransform || g.ProjectionWKT == "" {
+		t.Fatalf("grid mismatch: %+v", g)
+	}
+	if nd, ok := r.NoData(); !ok || nd != -9999 {
+		t.Fatalf("nodata = %v %v", nd, ok)
+	}
+	dst := make([]float64, 3*2)
+	if err := r.ReadFloat64(Window{X: 8, Y: 5, Width: 2, Height: 2}, dst[:4]); err != nil {
+		t.Fatal(err)
+	}
+	// pixel (8,5) has index 58 -> 58%6-1 = 3 ; (9,5)=59 -> 4 ; (8,6)=68 -> 1 ; (9,6)=69 -> 2
+	want := []float64{3, 4, 1, 2}
+	for i, v := range want {
+		if dst[i] != v {
+			t.Fatalf("pixel %d = %v want %v", i, dst[i], v)
+		}
+	}
+	if !rio.SameGrid(g, grid) {
+		t.Fatal("SameGrid should be true for identical grids")
+	}
+	other := grid
+	other.GeoTransform[0] += 1
+	if rio.SameGrid(g, other) {
+		t.Fatal("SameGrid should be false for shifted origin")
+	}
+}

internal/raster/io.go

@@ -0,0 +1,77 @@
+package raster
+
+import "context"
+
+// Grid describes a raster's pixel grid: its size, geotransform, and
+// projection. Two grids describe the same pixels when IO.SameGrid reports
+// true for them.
+type Grid struct {
+	Width, Height int
+	GeoTransform  [6]float64
+	ProjectionWKT string
+}
+
+// Window is a rectangular block of pixels within a raster, in pixel/line
+// coordinates with (0,0) at the top-left corner.
+type Window struct {
+	X, Y, Width, Height int
+}
+
+// Reader reads pixel data and metadata from an existing raster.
+type Reader interface {
+	// Grid returns the raster's pixel grid.
+	Grid() Grid
+	// NoData returns the raster's nodata value and whether one is set.
+	NoData() (float64, bool)
+	// ReadFloat64 reads the pixels in w into dst, row-major, converting the
+	// underlying pixel type to float64. len(dst) must be at least
+	// w.Width*w.Height.
+	ReadFloat64(w Window, dst []float64) error
+	// Close releases the underlying dataset handle.
+	Close() error
+}
+
+// WriterOptions configures a raster created by IO.Create.
+type WriterOptions struct {
+	// NoData is the nodata value written to the output band.
+	NoData int16
+	// TileSize is the internal tile size (both block dimensions) in pixels.
+	TileSize int
+	// Compression is the GDAL COMPRESS creation option value.
+	Compression string
+}
+
+// Writer writes pixel data to a raster created by IO.Create.
+type Writer interface {
+	// WriteInt16 writes src, row-major, into the pixels described by w.
+	// len(src) must be at least w.Width*w.Height.
+	WriteInt16(w Window, src []int16) error
+	// Close flushes and releases the underlying dataset handle.
+	Close() error
+}
+
+// IO is an engine-agnostic block I/O abstraction over raster storage. It lets
+// callers open and create rasters without depending on a particular GDAL
+// binding.
+type IO interface {
+	// Open opens the raster at path for reading.
+	Open(ctx context.Context, path string) (Reader, error)
+	// Create creates a new single-band int16 raster at path with the given
+	// grid and writer options, ready for WriteInt16 calls.
+	Create(ctx context.Context, path string, g Grid, o WriterOptions) (Writer, error)
+	// SameGrid reports whether a and b describe the same pixel grid: equal
+	// size, geotransform, and coordinate reference system.
+	SameGrid(a, b Grid) bool
+}
+
+// Windows tiles a w×h raster into row-major windows of at most size×size.
+func Windows(w, h, size int) []Window {
+	var out []Window
+	for y := 0; y < h; y += size {
+		wh := min(size, h-y)
+		for x := 0; x < w; x += size {
+			out = append(out, Window{X: x, Y: y, Width: min(size, w-x), Height: wh})
+		}
+	}
+	return out
+}

internal/raster/io_test.go

@@ -0,0 +1,61 @@
+package raster
+
+import (
+	"reflect"
+	"testing"
+)
+
+func TestWindows(t *testing.T) {
+	tests := []struct {
+		name       string
+		w, h, size int
+		want       []Window
+	}{
+		{
+			name: "10x10 size4 tiles into 9 windows",
+			w:    10, h: 10, size: 4,
+			want: []Window{
+				{X: 0, Y: 0, Width: 4, Height: 4},
+				{X: 4, Y: 0, Width: 4, Height: 4},
+				{X: 8, Y: 0, Width: 2, Height: 4},
+				{X: 0, Y: 4, Width: 4, Height: 4},
+				{X: 4, Y: 4, Width: 4, Height: 4},
+				{X: 8, Y: 4, Width: 2, Height: 4},
+				{X: 0, Y: 8, Width: 4, Height: 2},
+				{X: 4, Y: 8, Width: 4, Height: 2},
+				{X: 8, Y: 8, Width: 2, Height: 2},
+			},
+		},
+		{
+			name: "5x3 size8 fits in one window",
+			w:    5, h: 3, size: 8,
+			want: []Window{
+				{X: 0, Y: 0, Width: 5, Height: 3},
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got := Windows(tt.w, tt.h, tt.size)
+			if !reflect.DeepEqual(got, tt.want) {
+				t.Fatalf("Windows(%d, %d, %d) = %+v, want %+v", tt.w, tt.h, tt.size, got, tt.want)
+			}
+			if len(got) > 0 {
+				last := got[len(got)-1]
+				wantLast := tt.want[len(tt.want)-1]
+				if last != wantLast {
+					t.Fatalf("last window = %+v, want %+v", last, wantLast)
+				}
+			}
+		})
+	}
+}
+
+func TestDefaultWriterOptions(t *testing.T) {
+	got := DefaultWriterOptions()
+	want := WriterOptions{NoData: -9999, TileSize: 512, Compression: "DEFLATE"}
+	if got != want {
+		t.Fatalf("DefaultWriterOptions() = %+v, want %+v", got, want)
+	}
+}