Make ShpWriter.shape return num of bytes, correctly name vars, and add shx round trip test

.gitignore

@@ -35,3 +35,4 @@ venv/
 .mypy_cache/
 .pytest_cache/
 .ruff_cache/
+.hypothesis

README.md

@@ -93,6 +93,12 @@ part of your geospatial project.
 
 # Version Changes
 
+## 3.0.14.dev
+### ShpWriter.shape API Tweak (small breaking change).
+ - Make ShpWriter.shape return shape length in bytes (the
+   same as for offset) not in 16 bit words.
+
+
 ## 3.0.13
 ### Bug fix
  - Fix bug when reading empty shp files.

changelog.txt

@@ -1,3 +1,9 @@
+VERSION 3.0.14.dev
+
+2026-06-20
+	* API Tweak (small breaking change).  Make ShpWriter.shape return shape length in bytes
+	(the same as for offset) not in 16 bit words.
+
 VERSION 3.0.13
 
 2026-06-19
@@ -21,7 +27,7 @@ VERSION 3.0.11
 
 2026-06-04
 	Edge case handling
-	* Raise ShapefileException i) when creating Non-null Shapes without (or with empty) points
+	* Raise ShapefileException: i) when creating Non-null Shapes without (or with empty) points
 	  and ii) when creating Null Shapes with non-empty points.
 	* Ensure Shape.z and Shape.partTypes are _Arrays.
 	* Make Shape stricter about its args, e.g. only points or lines, only one point for Points.

src/shapefile.py

@@ -8,7 +8,7 @@
 
 from __future__ import annotations
 
-__version__ = "3.0.13"
+__version__ = "3.0.14.dev"
 
 import abc
 import array
@@ -1607,7 +1607,6 @@ def _write_ms_to_byte_stream(
             raise ShapefileException(
                 f"Failed to write measure extremes for record {i}. Expected floats"
             )
-
         ms_to_encode = replace_None_with_NODATA(s.m)
         try:
             num_bytes_written += b_io.write(pack(f"<{len(s.m)}d", *ms_to_encode))
@@ -4135,7 +4134,11 @@ def _header(self) -> None:
     def _write_file_length(self) -> None:
         # self.file required to be at correct position, e.g.
         # if called by self._header
-        self.file.write(pack(">i", self._shp_file_length_B()))
+
+        # Calculate size as 16-bit words
+        size_B = self._shp_file_length_B()
+        size_16b_words = size_B // 2
+        self.file.write(pack(">i", size_16b_words))
 
     def _shp_file_length_B(self) -> int:
         """Calculates the file length of the shp file."""
@@ -4144,9 +4147,7 @@ def _shp_file_length_B(self) -> int:
 
         # Calculate size of all shapes
         self.file.seek(0, 2)
-        size_16b_words = self.file.tell()
-        # Calculate size as 16-bit words
-        size_B = size_16b_words // 2
+        size_B = self.file.tell()
         # Return to start
         self.file.seek(start_B)
         return size_B
@@ -4200,6 +4201,7 @@ def shape(
         self,
         s: Shape | HasGeoInterface | GeoJSONHomogeneousGeometryObject,
     ) -> tuple[int, int]:
+        """Appends s to the file.  Returns shape's offset and length in B"""
         if not isinstance(s, Shape):
             if isinstance(s, HasGeoInterface):
                 shape_dict = s.__geo_interface__
@@ -4216,6 +4218,7 @@ def shape(
         return self._shp_record(s)
 
     def _shp_record(self, s: Shape) -> tuple[int, int]:
+        """Appends s to the file.  Returns shape's offset and length in B"""
         offset = self.file.tell()
         self.shpNum += 1
 
@@ -4274,7 +4277,7 @@ def _shp_record(self, s: Shape) -> tuple[int, int]:
         # Flush to file.
         b_io.seek(0)
         self.file.write(b_io.read())
-        return offset, length_16bw
+        return offset, n
 
 
 class ShxWriter(_ShpShxHeaderWriter):
@@ -4288,7 +4291,7 @@ def __init__(
         super().__init__(file=shx)
         self.shp_writer = shp_writer
 
-    def _shx_record(self, offset_B: int, length_16bw: int) -> None:
+    def _shx_record(self, offset_B: int, length_B: int) -> None:
         """Writes the shx records."""
 
         f = self.file
@@ -4299,7 +4302,7 @@ def _shx_record(self, offset_B: int, length_16bw: int) -> None:
                 "It's over 4GB, perhaps split the .shp or the Shapefile into smaller ones? "
             )
 
-        offset_16bw = offset_B // 2
+        offset_16bw, length_16bw = offset_B // 2, length_B // 2
         f.write(pack(">2i", offset_16bw, length_16bw))
 
     def _header(self) -> None:
@@ -4454,9 +4457,9 @@ def shape(
         # Balance if already not balanced
         if self.autoBalance and self.dbf_writer.recNum < self.shp_writer.shpNum:
             self.balance()
-        offset_B, length_16bw = self.shp_writer.shape(s)
+        offset_B, length_B = self.shp_writer.shape(s)
         if self._shx:
-            self.shx_writer._shx_record(offset_B, length_16bw)
+            self.shx_writer._shx_record(offset_B, length_B)
 
     def record(
         self,

tests/hypothesis_tests.py

@@ -163,7 +163,6 @@ def multipointM_from_xyms(point_ms: tuple[float, float, float | None], oid_: int
 multipointm = builds(multipointM_from_xyms, lists(tuples(xs, ys, ms), min_size=1), oid)
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(expected=multipointm, i=integers(min_value=1))
 def test_MultiPointM_roundtrips(
     expected: shp.MultiPointM,
@@ -196,7 +195,6 @@ def multipointZ_from_xyzms(pointz_ms: tuple[float, float, float, float | None],
 
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(expected=multipointz, i=integers(min_value=1))
 def test_MultiPointZ_roundtrips(
     expected: shp.MultiPointZ,
@@ -248,7 +246,6 @@ def test_Polyline_roundtrips(
     assert actual.oid == expected.oid
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(expected=polylinem, i=integers(min_value=1))
 def test_PolylineM_roundtrips(
     expected: shp.PolylineM,
@@ -273,7 +270,6 @@ def test_PolylineM_roundtrips(
     assert actual.oid == expected.oid
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(expected=polylinez, i=integers(min_value=1))
 def test_PolylineZ_roundtrips(
     expected: shp.PolylineZ,
@@ -327,7 +323,6 @@ def test_Polygon_roundtrips(
     assert actual.oid == expected.oid
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(expected=polygonm, i=integers(min_value=1))
 def test_PolygonM_roundtrips(
     expected: shp.PolygonM,
@@ -352,7 +347,6 @@ def test_PolygonM_roundtrips(
     assert actual.oid == expected.oid
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(expected=polygonz, i=integers(min_value=1))
 def test_PolygonZ_roundtrips(
     expected: shp.PolygonZ,
@@ -392,7 +386,6 @@ def multipatch_from_xyzms_and_types(
 
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(expected=multipatch, i=integers(min_value=1))
 def test_MultiPatch_roundtrips(
     expected: shp.MultiPatch,
@@ -418,6 +411,12 @@ def test_MultiPatch_roundtrips(
     assert actual.oid == expected.oid
     assert actual.partTypes == expected.partTypes, f"{type(actual.partTypes)=}, {type(expected.partTypes)=}"
 
+MAX_FILE_SIZE_16bw = (1 << 31) - 1 # This bound comes from encoding the
+                                   # actual file size (in 16 bit words)
+                                   # as a 4 byte signed integer.
+MAX_NUM_SHAPES = (MAX_FILE_SIZE_16bw - 50) // 6 # Minus 100B header, 12 bytes
+                                                # per record (the minimum for
+                                                # a Null shape).
 
 shape_codes_names_and_strategies = [
 # (0, "Null Shape"),
@@ -438,7 +437,7 @@ def test_MultiPatch_roundtrips(
 
 def code_and_shape_strat_from_triple(t):
     x, _name, shapes  = t
-    return tuples(just(x), lists(shapes, min_size = 0))  # Empty shp files are in the esri spec.
+    return tuples(just(x), lists(shapes, min_size = 0, max_size=MAX_NUM_SHAPES))  # Empty shp files are in the esri spec.
 
 codes_and_shapes_strats = [
     code_and_shape_strat_from_triple(t)
@@ -448,7 +447,6 @@ def code_and_shape_strat_from_triple(t):
 codes_and_shapes = one_of(codes_and_shapes_strats)
 
 @pytest.mark.hypothesis
-# @settings(suppress_health_check=[HealthCheck.too_slow, HealthCheck.data_too_large])
 @given(codes_and_shapes=codes_and_shapes)
 def test_shp_reader_writer_roundtrip(codes_and_shapes)-> None:
     code_ex, expected_shapes = codes_and_shapes
@@ -483,3 +481,62 @@ def test_shp_reader_writer_roundtrip(codes_and_shapes)-> None:
                 assert actual.partTypes == expected.partTypes, f"{type(actual.partTypes)=}, {type(expected.partTypes)=}"
             else:
                 assert not hasattr(expected, "partTypes")
+
+
+
+# SHX_UB = MAX_FILE_SIZE_16bw - 50
+
+
+# ##  Surprisingly slow.  Doesn't  add enough value to merit waiting for
+# @composite
+# def positive_ints_with_bounded_sum(
+#     draw,
+#     min_x: int = 6,
+#     upper_bound: int = SHX_UB,
+#     max_len: int = MAX_NUM_SHAPES,
+#     ):
+#     assert min_x >= 1
+#     assert upper_bound >= max_len
+#     length = draw(integers(min_value=0, max_value=max_len))
+#     if length == 0:
+#         return []
+
+#     max_x = upper_bound - (length - 1)
+#     result = []
+
+#     for i in range(length):
+#         if max_x < min_x :
+#             break
+#         x = draw(integers(min_value=min_x, max_value=max_x))
+#         result.append(x)
+#         max_x -= x
+
+#     return result
+
+
+@pytest.mark.hypothesis
+@given(codes_and_shapes=codes_and_shapes)
+def test_shx_reader_writer_roundtrip(codes_and_shapes)-> None:
+    code_ex, expected_shapes = codes_and_shapes
+
+    sizes_B = []
+    offsets_B = []
+    offset_B = 100 # "Thus, the offset for the first record in the
+                   #  main file is 50 (16bw), given the 100-byte header. "
+    shp_stream = io.BytesIO()
+    shx_stream = io.BytesIO()
+    with shp.ShpWriter(shp=shp_stream, shapeType=code_ex) as shp_w:
+        with shp.ShxWriter(shx=shx_stream, shp_writer = shp_w) as shx_w:
+            for shape in expected_shapes:
+                offset_B, size_B = shp_w.shape(shape)
+                sizes_B.append(size_B)
+                offsets_B.append(offset_B)
+                shx_w._shx_record(offset_B, size_B)
+
+    shx_stream.seek(0)
+
+    with shp.ShxReader(shx=shx_stream) as r:
+        assert r.numShapes == len(expected_shapes)
+        assert r.offsets == offsets_B
+        assert r.shape_lengths_B == sizes_B
+