BLD, TST: Build and test Pyodide wheels for pandas in CI

.github/workflows/emscripten.yml

@@ -0,0 +1,76 @@
+name: Test Emscripten/Pyodide build
+
+on:
+# TODO: refine when this workflow should run when this
+# is ready for use or before merging
+  pull_request:
+  push:
+  workflow_dispatch:
+
+env:
+  FORCE_COLOR: 3
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build-wasm-emscripten:
+    name: Build pandas distribution for Pyodide
+    runs-on: ubuntu-22.04
+    # To enable this workflow on a fork, comment out:
+    # if: github.repository == 'pandas-dev/pandas'
+    env:
+      PYODIDE_VERSION: 0.25.0
+      # PYTHON_VERSION and EMSCRIPTEN_VERSION are determined by PYODIDE_VERSION.
+      # The appropriate versions can be found in the Pyodide repodata.json
+      # "info" field, or in Makefile.envs:
+      # https://github.com/pyodide/pyodide/blob/main/Makefile.envs#L2
+      PYTHON_VERSION: 3.11.3
+      EMSCRIPTEN_VERSION: 3.1.46
+      NODE_VERSION: 18
+    steps:
+      - name: Checkout pandas
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Set up Emscripten toolchain
+        uses: mymindstorm/setup-emsdk@v14
+        with:
+          version: ${{ env.EMSCRIPTEN_VERSION }}
+          actions-cache-folder: emsdk-cache
+
+      - name: Install pyodide-build
+        run: pip install "pydantic<2" pyodide-build==${{ env.PYODIDE_VERSION }}
+
+      - name: Build pandas for Pyodide
+        run: |
+          # pyodide build -Ceditable-verbose=true
+          pyodide build
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ env.NODE_VERSION }}
+
+      - name: Set up Pyodide virtual environment
+        run: |
+          pyodide venv .venv-pyodide
+          source .venv-pyodide/bin/activate
+          pip install dist/*.whl
+
+      - name: Test pandas for Pyodide
+        run: |
+          source .venv-pyodide/bin/activate
+          export PANDAS_CI=1
+          pip install "pytest<8.1.0" hypothesis
+          # do not import pandas from the checked out repo
+          cd ..
+          python -c 'import pandas as pd; pd.test(extra_args=["-m not clipboard and not single_cpu and not slow and not network and not db"])'

pandas/compat/__init__.py

@@ -22,6 +22,7 @@
     PY311,
     PY312,
     PYPY,
+    WASM,
 )
 import pandas.compat.compressors
 from pandas.compat.numpy import is_numpy_dev
@@ -193,4 +194,5 @@ def get_bz2_file() -> type[pandas.compat.compressors.BZ2File]:
     "PY311",
     "PY312",
     "PYPY",
+    "WASM",
 ]

pandas/compat/_constants.py

@@ -17,6 +17,7 @@
 PY311 = sys.version_info >= (3, 11)
 PY312 = sys.version_info >= (3, 12)
 PYPY = platform.python_implementation() == "PyPy"
+WASM = (sys.platform == "emscripten") or (platform.machine() in ["wasm32", "wasm64"])
 ISMUSL = "musl" in (sysconfig.get_config_var("HOST_GNU_TYPE") or "")
 REF_COUNT = 2 if PY311 else 3
 
@@ -27,4 +28,5 @@
     "PY311",
     "PY312",
     "PYPY",
+    "WASM",
 ]

pandas/tests/indexes/datetimes/methods/test_normalize.py

@@ -70,6 +70,7 @@ def test_normalize_tz(self):
         assert not rng.is_normalized
 
     @td.skip_if_windows
+    @td.skip_if_wasm  # tzset is available only on Unix-like systems
     @pytest.mark.parametrize(
         "timezone",
         [

pandas/tests/indexes/datetimes/methods/test_resolution.py

@@ -1,7 +1,7 @@
 from dateutil.tz import tzlocal
 import pytest
 
-from pandas.compat import IS64
+from pandas.compat import IS64, WASM
 
 from pandas import date_range
 
@@ -22,7 +22,7 @@
 )
 def test_dti_resolution(request, tz_naive_fixture, freq, expected):
     tz = tz_naive_fixture
-    if freq == "YE" and not IS64 and isinstance(tz, tzlocal):
+    if freq == "YE" and ((not IS64) or WASM) and isinstance(tz, tzlocal):
         request.applymarker(
             pytest.mark.xfail(reason="OverflowError inside tzlocal past 2038")
         )

pandas/tests/io/parser/common/test_file_buffer_url.py

@@ -80,6 +80,7 @@ def test_path_path_lib(all_parsers):
     tm.assert_frame_equal(df, result)
 
 
+@td.skip_if_wasm  # limited file system access on WASM
 def test_nonexistent_path(all_parsers):
     # gh-2428: pls no segfault
     # gh-14086: raise more helpful FileNotFoundError
@@ -93,6 +94,8 @@ def test_nonexistent_path(all_parsers):
     assert path == e.value.filename
 
 
+@td.skip_if_wasm  # limited file system access on WASM, it leads to different
+# error messages than on other platforms
 @td.skip_if_windows  # os.chmod does not work in windows
 def test_no_permission(all_parsers):
     # GH 23784

pandas/tests/io/parser/test_c_parser_only.py

@@ -550,6 +550,7 @@ def test_chunk_whitespace_on_boundary(c_parser_only):
     tm.assert_frame_equal(result, expected)
 
 
+@td.skip_if_wasm  # limited file system access on WASM
 def test_file_handles_mmap(c_parser_only, csv1):
     # gh-14418
     #

pandas/tests/io/sas/test_sas7bdat.py

@@ -7,7 +7,7 @@
 import numpy as np
 import pytest
 
-from pandas.compat import IS64
+from pandas.compat import IS64, WASM
 from pandas.errors import EmptyDataError
 
 import pandas as pd
@@ -190,7 +190,7 @@ def test_date_time(datapath):
     res = df0["DateTimeHi"].astype("M8[us]").dt.round("ms")
     df0["DateTimeHi"] = res.astype("M8[ms]")
 
-    if not IS64:
+    if (not IS64) or (WASM):
         # No good reason for this, just what we get on the CI
         df0.loc[0, "DateTimeHi"] += np.timedelta64(1, "ms")
         df0.loc[[2, 3], "DateTimeHi"] -= np.timedelta64(1, "ms")
@@ -285,7 +285,7 @@ def test_max_sas_date(datapath):
         columns=["text", "dt_as_float", "dt_as_dt", "date_as_float", "date_as_date"],
     )
 
-    if not IS64:
+    if (not IS64) or (WASM):
         # No good reason for this, just what we get on the CI
         expected.loc[:, "dt_as_dt"] -= np.timedelta64(1, "ms")
 
@@ -328,7 +328,7 @@ def test_max_sas_date_iterator(datapath):
             columns=col_order,
         ),
     ]
-    if not IS64:
+    if (not IS64) or (WASM):
         # No good reason for this, just what we get on the CI
         expected[0].loc[0, "dt_as_dt"] -= np.timedelta64(1, "ms")
         expected[1].loc[0, "dt_as_dt"] -= np.timedelta64(1, "ms")
@@ -359,7 +359,7 @@ def test_null_date(datapath):
             ),
         },
     )
-    if not IS64:
+    if (not IS64) or (WASM):
         # No good reason for this, just what we get on the CI
         expected.loc[0, "datetimecol"] -= np.timedelta64(1, "ms")
     tm.assert_frame_equal(df, expected)

pandas/tests/io/test_common.py

@@ -23,6 +23,7 @@
 
 import pandas as pd
 import pandas._testing as tm
+import pandas.util._test_decorators as td
 
 import pandas.io.common as icom
 
@@ -163,6 +164,7 @@ def test_iterator(self):
             tm.assert_frame_equal(first, expected.iloc[[0]])
             tm.assert_frame_equal(pd.concat(it), expected.iloc[1:])
 
+    @td.skip_if_wasm  # limited file system access on WASM
     @pytest.mark.parametrize(
         "reader, module, error_class, fn_ext",
         [
@@ -228,6 +230,8 @@ def test_write_missing_parent_directory(self, method, module, error_class, fn_ex
         ):
             method(dummy_frame, path)
 
+
+    @td.skip_if_wasm  # limited file system access on WASM
     @pytest.mark.parametrize(
         "reader, module, error_class, fn_ext",
         [
@@ -382,6 +386,7 @@ def mmap_file(datapath):
 
 
 class TestMMapWrapper:
+    @td.skip_if_wasm  # limited file system access on WASM
     def test_constructor_bad_file(self, mmap_file):
         non_file = StringIO("I am not a file")
         non_file.fileno = lambda: -1
@@ -404,6 +409,7 @@ def test_constructor_bad_file(self, mmap_file):
         with pytest.raises(ValueError, match=msg):
             icom._maybe_memory_map(target, True)
 
+    @td.skip_if_wasm  # limited file system access on WASM
     def test_next(self, mmap_file):
         with open(mmap_file, encoding="utf-8") as target:
             lines = target.readlines()
@@ -586,7 +592,7 @@ def test_bad_encdoing_errors():
         with pytest.raises(LookupError, match="unknown error handler name"):
             icom.get_handle(path, "w", errors="bad")
 
-
+@td.skip_if_wasm  # limited file system access on WASM
 def test_errno_attribute():
     # GH 13872
     with pytest.raises(FileNotFoundError, match="\\[Errno 2\\]") as err:

pandas/tests/io/xml/test_xml.py

@@ -484,7 +484,7 @@ def test_empty_string_etree(val):
     with pytest.raises(ParseError, match="no element found"):
         read_xml(data, parser="etree")
 
-
+@td.skip_if_wasm  # limited file system access on WASM
 def test_wrong_file_path(parser):
     filename = os.path.join("does", "not", "exist", "books.xml")
 

pandas/tests/scalar/timestamp/methods/test_replace.py

@@ -99,13 +99,15 @@ def test_replace_integer_args(self, tz_aware_fixture):
         with pytest.raises(ValueError, match=msg):
             ts.replace(hour=0.1)
 
+    @td.skip_if_wasm  # tzset is available only on Unix-like systems
     def test_replace_tzinfo_equiv_tz_localize_none(self):
         # GH#14621, GH#7825
         # assert conversion to naive is the same as replacing tzinfo with None
         ts = Timestamp("2013-11-03 01:59:59.999999-0400", tz="US/Eastern")
         assert ts.tz_localize(None) == ts.replace(tzinfo=None)
 
     @td.skip_if_windows
+    @td.skip_if_wasm  # tzset is available only on Unix-like systems
     def test_replace_tzinfo(self):
         # GH#15683
         dt = datetime(2016, 3, 27, 1)

pandas/tests/scalar/timestamp/methods/test_timestamp_method.py

@@ -11,6 +11,7 @@
 
 class TestTimestampMethod:
     @td.skip_if_windows
+    @td.skip_if_wasm  # tzset is available only on Unix-like systems
     def test_timestamp(self, fixed_now_ts):
         # GH#17329
         # tz-naive --> treat it as if it were UTC for purposes of timestamp()

pandas/tests/scalar/timestamp/test_formats.py

@@ -6,6 +6,7 @@
 import pytz  # a test below uses pytz but only inside a `eval` call
 
 from pandas import Timestamp
+import pandas.util._test_decorators as td
 
 ts_no_ns = Timestamp(
     year=2019,
@@ -95,6 +96,7 @@ class TestTimestampRendering:
     @pytest.mark.parametrize(
         "date", ["2014-03-07", "2014-01-01 09:00", "2014-01-01 00:00:00.000000001"]
     )
+    @td.skip_if_wasm  # tzset is not available in WASM
     def test_repr(self, date, freq, tz):
         # avoid to match with timezone name
         freq_repr = f"'{freq}'"

pandas/tests/tools/test_to_datetime.py

@@ -959,6 +959,7 @@ def test_to_datetime_YYYYMMDD(self):
         assert actual == datetime(2008, 1, 15)
 
     @td.skip_if_windows  # `tm.set_timezone` does not work in windows
+    @td.skip_if_wasm  # tzset is available only on Unix-like systems
     def test_to_datetime_now(self):
         # See GH#18666
         with tm.set_timezone("US/Eastern"):
@@ -975,7 +976,8 @@ def test_to_datetime_now(self):
             assert pdnow.tzinfo is None
             assert pdnow2.tzinfo is None
 
-    @td.skip_if_windows  # `tm.set_timezone` does not work in windows
+    @td.skip_if_windows  # `tm.set_timezone` does not work on Windows
+    @td.skip_if_wasm  # tzset is available only on Unix-like systems
     @pytest.mark.parametrize("tz", ["Pacific/Auckland", "US/Samoa"])
     def test_to_datetime_today(self, tz):
         # See GH#18666
@@ -1007,6 +1009,7 @@ def test_to_datetime_today_now_unicode_bytes(self, arg):
         to_datetime([arg])
 
     @pytest.mark.filterwarnings("ignore:Timestamp.utcnow is deprecated:FutureWarning")
+    @td.skip_if_wasm  # tzset is available only on Unix-like systems
     @pytest.mark.parametrize(
         "format, expected_ds",
         [

pandas/tests/tseries/offsets/test_common.py

@@ -9,6 +9,7 @@
 )
 from pandas.compat import (
     IS64,
+    WASM,
     is_platform_windows,
 )
 
@@ -130,7 +131,7 @@ def test_apply_out_of_range(request, tz_naive_fixture, _offset):
         if tz is not None:
             assert t.tzinfo is not None
 
-        if isinstance(tz, tzlocal) and not IS64 and _offset is not DateOffset:
+        if isinstance(tz, tzlocal) and ((not IS64) or WASM) and _offset is not DateOffset:
             # If we hit OutOfBoundsDatetime on non-64 bit machines
             # we'll drop out of the try clause before the next test
             request.applymarker(

pandas/tests/tslibs/test_parsing.py

@@ -25,7 +25,7 @@
 import pandas._testing as tm
 from pandas._testing._hypothesis import DATETIME_NO_TZ
 
-
+@td.skip_if_wasm  # tzset is available only on Unix-like systems
 @pytest.mark.skipif(
     is_platform_windows() or ISMUSL,
     reason="TZ setting incorrect on Windows and MUSL Linux",

pandas/util/_test_decorators.py

@@ -26,6 +26,8 @@ def test_foo():
 
 from __future__ import annotations
 
+import sys
+import platform
 import locale
 from typing import (
     TYPE_CHECKING,
@@ -115,6 +117,10 @@ def skip_if_no(package: str, min_version: str | None = None) -> pytest.MarkDecor
     locale.getlocale()[0] != "en_US",
     reason=f"Set local {locale.getlocale()[0]} is not en_US",
 )
+skip_if_wasm = pytest.mark.skipif(
+    (sys.platform == "emscripten") or (platform.machine() in ["wasm32", "wasm64"]),
+    reason="does not support wasm"
+)
 
 
 def parametrize_fixture_doc(*args) -> Callable[[F], F]: