Use 0 for size of infinite datasets.

compiler_gym/bin/service.py

@@ -75,7 +75,6 @@
 import sys
 from typing import Iterable
 
-import humanize
 from absl import app, flags
 
 from compiler_gym.datasets import Dataset
@@ -132,7 +131,8 @@ def summarize_datasets(datasets: Iterable[Dataset]) -> str:
             [
                 (
                     n,
-                    humanize.intcomma(f) if f >= 0 else "∞",
+                    # A size of zero means infinite.
+                    f"{f:,d}" if f > 0 else "∞",
                     l,
                     v,
                 )

compiler_gym/datasets/dataset.py

@@ -233,21 +233,19 @@ def site_data_size_in_bytes(self) -> int:
             )
         return total_size
 
-    # We use Union[int, float] to represent the size because infinite size is
-    # represented by math.inf, which is a float. For all other sizes this should
-    # be an int.
     @property
-    def size(self) -> Union[int, float]:
-        """The number of benchmarks in the dataset. If the number of benchmarks
-        is unbounded, for example because the dataset represents a program
-        generator that can produce an infinite number of programs, the value is
-        :code:`math.inf`.
+    def size(self) -> int:
+        """The number of benchmarks in the dataset.
+
+        If the number of benchmarks is unknown or unbounded, for example because
+        the dataset represents a program generator that can produce an infinite
+        number of programs, the value is 0.
 
-        :type: Union[int, float]
+        :type: int
         """
         return 0
 
-    def __len__(self) -> Union[int, float]:
+    def __len__(self) -> int:
         """The number of benchmarks in the dataset.
 
         This is the same as :meth:`Dataset.size
@@ -256,7 +254,11 @@ def __len__(self) -> Union[int, float]:
             >>> len(dataset) == dataset.size
             True
 
-        :return: An integer, or :code:`math.float`.
+        If the number of benchmarks is unknown or unbounded, for example because
+        the dataset represents a program generator that can produce an infinite
+        number of programs, the value is 0.
+
+        :return: An integer.
         """
         return self.size
 

compiler_gym/envs/llvm/datasets/csmith.py

@@ -230,10 +230,10 @@ def _build_csmith(install_root: Path, logger: logging.Logger):
                 raise CsmithBuildError("make install", stdout, stderr)
 
     @property
-    def size(self) -> float:
+    def size(self) -> int:
         # Actually 2^32 - 1, but practically infinite for all intents and
         # purposes.
-        return float("inf")
+        return 0
 
     def benchmark_uris(self) -> Iterable[str]:
         return (f"{self.name}/{i}" for i in range(UINT_MAX))

compiler_gym/envs/llvm/datasets/llvm_stress.py

@@ -50,7 +50,7 @@ def __init__(self, site_data_base: Path, sort_order: int = 0):
     def size(self) -> int:
         # Actually 2^32 - 1, but practically infinite for all intents and
         # purposes.
-        return float("inf")
+        return 0
 
     def benchmark_uris(self) -> Iterable[str]:
         return (f"{self.name}/{i}" for i in range(UINT_MAX))

tests/llvm/datasets/csmith_test.py

@@ -30,7 +30,8 @@ def csmith_dataset() -> CsmithDataset:
 
 
 def test_csmith_size(csmith_dataset: CsmithDataset):
-    assert csmith_dataset.size == float("inf")
+    assert csmith_dataset.size == 0
+    assert len(csmith_dataset) == 0
 
 
 @pytest.mark.parametrize("index", range(3) if is_ci() else range(250))

tests/llvm/datasets/llvm_stress_test.py

@@ -31,7 +31,8 @@ def llvm_stress_dataset() -> LlvmStressDataset:
 
 
 def test_llvm_stress_size(llvm_stress_dataset: LlvmStressDataset):
-    assert llvm_stress_dataset.size == float("inf")
+    assert llvm_stress_dataset.size == 0
+    assert len(llvm_stress_dataset) == 0
 
 
 @pytest.mark.parametrize("index", range(3) if is_ci() else range(250))