Remove redundant file size guards from rio-warp, add --dry-run (#2889)

* Remove redundant file size guards from rio-warp, add --dry-run

Resolves #2887

* Update change log

CHANGES.txt

@@ -1,6 +1,14 @@
 Changes
 =======
 
+Next
+----
+
+- The output file size limits of rio-warp were made redundant by changes to the
+  GTiff driver in GDAL 2.1 and have been removed (#2889). A --dry-run option
+  has been added to the command. If used, the profile of the output dataset
+  will be printed and no warping will occur.
+
 1.3.8 (2023-06-26)
 ------------------
 

rasterio/rio/warp.py

@@ -1,5 +1,6 @@
-"""$ rio warp"""
+"""rio warp: CLI for reprojecting rasters."""
 
+import json
 import logging
 from math import ceil, floor
 import sys
@@ -20,12 +21,6 @@ from rasterio.warp import (
 
 logger = logging.getLogger(__name__)
 
-# Improper usage of rio-warp can lead to accidental creation of
-# extremely large datasets. We'll put a hard limit on the size of
-# datasets and raise a usage error if the limits are exceeded.
-MAX_OUTPUT_WIDTH = 100000
-MAX_OUTPUT_HEIGHT = 100000
-
 
 @click.command(short_help='Warp a raster dataset.')
 @options.files_inout_arg
@@ -93,6 +88,11 @@ MAX_OUTPUT_HEIGHT = 100000
     callback=_cb_key_val,
     help="GDAL warper and coordinate transformer options.",
 )
+@click.option(
+    "--dry-run",
+    is_flag=True,
+    help="Do not create an output file, but report on its expected size and other characteristics.",
+)
 @click.pass_context
 def warp(
     ctx,
@@ -114,6 +114,7 @@ def warp(
     creation_options,
     target_aligned_pixels,
     warper_options,
+    dry_run,
 ):
     """
     Warp a raster dataset.
@@ -127,23 +128,19 @@ def warp(
     \b
         $ rio warp input.tif output.tif --like template.tif
 
-    The output coordinate reference system may be either a PROJ.4 or
-    EPSG:nnnn string,
+    The destination's coordinate reference system may be an authority
+    name, PROJ4 string, JSON-encoded PROJ4, or WKT.
 
     \b
         --dst-crs EPSG:4326
         --dst-crs '+proj=longlat +ellps=WGS84 +datum=WGS84'
-
-    or a JSON text-encoded PROJ.4 object.
-
-    \b
         --dst-crs '{"proj": "utm", "zone": 18, ...}'
 
-    If --dimensions are provided, --res and --bounds are not applicable and an
-    exception will be raised.
-    Resolution is calculated based on the relationship between the
-    raster bounds in the target coordinate system and the dimensions,
-    and may produce rectangular rather than square pixels.
+    If --dimensions are provided, --res and --bounds are not applicable
+    and an exception will be raised.  Resolution is calculated based on
+    the relationship between the raster bounds in the target coordinate
+    system and the dimensions, and may produce rectangular rather than
+    square pixels.
 
     \b
         $ rio warp input.tif output.tif --dimensions 100 200 \\
@@ -354,15 +351,6 @@ def warp(
                     # Update the dst nodata value
                     out_kwargs.update(nodata=dst_nodata)
 
-            # When the bounds option is misused, extreme values of
-            # destination width and height may result.
-            if (dst_width < 0 or dst_height < 0 or
-                    dst_width > MAX_OUTPUT_WIDTH or
-                    dst_height > MAX_OUTPUT_HEIGHT):
-                raise click.BadParameter(
-                    "Invalid output dimensions: {0}.".format(
-                        (dst_width, dst_height)))
-
             out_kwargs.update(
                 crs=dst_crs,
                 transform=dst_transform,
@@ -386,18 +374,29 @@ def warp(
 
             out_kwargs.update(**creation_options)
 
-            with rasterio.open(output, 'w', **out_kwargs) as dst:
-                reproject(
-                    source=rasterio.band(src, list(range(1, src.count + 1))),
-                    destination=rasterio.band(
-                        dst, list(range(1, src.count + 1))),
-                    src_transform=src.transform,
-                    src_crs=src.crs,
-                    src_nodata=src_nodata,
-                    dst_transform=out_kwargs['transform'],
-                    dst_crs=out_kwargs['crs'],
-                    dst_nodata=dst_nodata,
-                    resampling=resampling,
-                    num_threads=threads,
-                    **warper_options
-                )
+            if dry_run:
+                crs = out_kwargs.get("crs", None)
+                if crs:
+                    epsg = src.crs.to_epsg()
+                    if epsg:
+                        out_kwargs['crs'] = 'EPSG:{}'.format(epsg)
+                    else:
+                        out_kwargs['crs'] = src.crs.to_string()
+
+                click.echo("Output dataset profile:")
+                click.echo(json.dumps(dict(**out_kwargs), indent=2))
+            else:
+                with rasterio.open(output, "w", **out_kwargs) as dst:
+                    reproject(
+                        source=rasterio.band(src, list(range(1, src.count + 1))),
+                        destination=rasterio.band(dst, list(range(1, src.count + 1))),
+                        src_transform=src.transform,
+                        src_crs=src.crs,
+                        src_nodata=src_nodata,
+                        dst_transform=out_kwargs["transform"],
+                        dst_crs=out_kwargs["crs"],
+                        dst_nodata=dst_nodata,
+                        resampling=resampling,
+                        num_threads=threads,
+                        **warper_options
+                    )

tests/test_rio_warp.py

@@ -332,14 +332,25 @@ def test_warp_reproject_multi_bounds_fail(runner, tmpdir):
 
 
 def test_warp_reproject_bounds_crossup_fail(runner, tmpdir):
-    """Crossed-up bounds raises click.BadParameter."""
+    """Crossed-up bounds raises RasterioIOError."""
     srcname = 'tests/data/shade.tif'
     outputname = str(tmpdir.join('test.tif'))
     out_bounds = [-11850000, 4810000, -11849000, 4812000]
-    result = runner.invoke(main_group, [
-        'warp', srcname, outputname, '--dst-crs', 'EPSG:4326', '--res', 0.001,
-        '--bounds'] + out_bounds)
-    assert result.exit_code == 2
+    result = runner.invoke(
+        main_group,
+        [
+            "warp",
+            srcname,
+            outputname,
+            "--dst-crs",
+            "EPSG:4326",
+            "--res",
+            0.001,
+            "--bounds",
+        ]
+        + out_bounds,
+    )
+    assert result.exit_code == 1
 
 
 def test_warp_reproject_src_bounds_res(runner, tmpdir):
@@ -604,3 +615,29 @@ def test_coordinate_operation(runner, tmp_path, wotopt):
 
     with rasterio.open(outputname) as src:
         assert src.checksum(1) == 4705
+
+
+def test_dry_run(runner, tmpdir):
+    # See also warp_reproject_bounds_crossup_fail.
+    srcname = 'tests/data/shade.tif'
+    outputname = str(tmpdir.join('test.tif'))
+    out_bounds = [-11850000, 4810000, -11849000, 4812000]
+    result = runner.invoke(
+        main_group,
+        [
+            "warp",
+            "--dry-run",
+            srcname,
+            outputname,
+            "--dst-crs",
+            "EPSG:4326",
+            "--res",
+            0.001,
+            "--bounds",
+        ]
+        + out_bounds,
+    )
+
+    assert result.exit_code == 0
+    assert '"width": 1000000' in result.output
+    assert '"height": 2000000' in result.output