Fix more tests

Author: jonashaag

pandas/conftest.py

@@ -43,6 +43,11 @@
     utc,
 )
 
+try:
+    import zstandard as zstd
+except ImportError:
+    zstd = None
+
 import pandas.util._test_decorators as td
 
 from pandas.core.dtypes.dtypes import (
@@ -266,15 +271,15 @@ def other_closed(request):
     return request.param
 
 
-@pytest.fixture(params=[None, "gzip", "bz2", "zip", "xz", "zstd"])
+@pytest.fixture(params=[None, "gzip", "bz2", "zip", "xz"] + (["zstd"] if zstd else []))
 def compression(request):
     """
     Fixture for trying common compression types in compression tests.
     """
     return request.param
 
 
-@pytest.fixture(params=["gzip", "bz2", "zip", "xz", "zstd"])
+@pytest.fixture(params=["gzip", "bz2", "zip", "xz"] + (["zstd"] if zstd else []))
 def compression_only(request):
     """
     Fixture for trying common compression types in compression tests excluding

pandas/tests/io/parser/test_network.py

@@ -41,7 +41,7 @@ def check_compressed_urls(salaries_table, compression, extension, mode, engine):
         "pandas/tests/io/parser/data/salaries.csv"
     )
 
-    url = f"{base_url}.{extension}"
+    url = base_url + extension
 
     if mode != "explicit":
         compression = mode

pandas/tests/io/test_pickle.py

@@ -354,6 +354,9 @@ def test_write_explicit_bad(self, compression, get_random_path):
         "ext", ["", ".gz", ".bz2", ".zip", ".no_compress", ".xz", ".zst"]
     )
     def test_write_infer(self, ext, get_random_path):
+        if ext == ".zst":
+            pytest.importorskip("zstandard")
+
         base = get_random_path
         path1 = base + ext
         path2 = base + ".raw"

pandas/tests/io/xml/test_to_xml.py

@@ -17,6 +17,7 @@
 )
 import pandas._testing as tm
 
+import pandas.io.common as icom
 from pandas.io.common import get_handle
 from pandas.io.xml import read_xml
 
@@ -1273,15 +1274,14 @@ def test_style_to_json():
 </data>"""
 
 
-@pytest.mark.parametrize("comp", ["bz2", "gzip", "xz", "zip", "zstd"])
-def test_compression_output(parser, comp):
+def test_compression_output(parser, compression_only):
     with tm.ensure_clean() as path:
-        geom_df.to_xml(path, parser=parser, compression=comp)
+        geom_df.to_xml(path, parser=parser, compression=compression_only)
 
         with get_handle(
             path,
             "r",
-            compression=comp,
+            compression=compression_only,
         ) as handle_obj:
             output = handle_obj.handle.read()
 
@@ -1290,18 +1290,15 @@ def test_compression_output(parser, comp):
     assert geom_xml == output.strip()
 
 
-@pytest.mark.parametrize("comp", ["bz2", "gzip", "xz", "zip", "zstd"])
-@pytest.mark.parametrize(
-    "compfile", ["xml.bz2", "xml.gz", "xml.xz", "xml.zip", "xml.zst"]
-)
-def test_filename_and_suffix_comp(parser, comp, compfile):
+def test_filename_and_suffix_comp(parser, compression_only):
+    compfile = "xml." + icom._compression_to_extension[compression_only]
     with tm.ensure_clean(filename=compfile) as path:
-        geom_df.to_xml(path, parser=parser, compression=comp)
+        geom_df.to_xml(path, parser=parser, compression=compression_only)
 
         with get_handle(
             path,
             "r",
-            compression=comp,
+            compression=compression_only,
         ) as handle_obj:
             output = handle_obj.handle.read()
 

pandas/tests/io/xml/test_xml.py

@@ -4,12 +4,19 @@
     BytesIO,
     StringIO,
 )
+from lzma import LZMAError
 import os
 from urllib.error import HTTPError
+from zipfile import BadZipFile
 
 import numpy as np
 import pytest
 
+try:
+    from zstandard import ZstdError
+except ImportError:
+    ZstdError = None
+
 import pandas.util._test_decorators as td
 
 from pandas import DataFrame
@@ -1014,65 +1021,35 @@ def test_online_stylesheet():
 # COMPRESSION
 
 
-@pytest.mark.parametrize("comp", ["bz2", "gzip", "xz", "zip", "zstd"])
-def test_compression_read(parser, comp):
+def test_compression_read(parser, compression_only):
     with tm.ensure_clean() as path:
-        geom_df.to_xml(path, index=False, parser=parser, compression=comp)
+        geom_df.to_xml(path, index=False, parser=parser, compression=compression_only)
 
-        xml_df = read_xml(path, parser=parser, compression=comp)
+        xml_df = read_xml(path, parser=parser, compression=compression_only)
 
     tm.assert_frame_equal(xml_df, geom_df)
 
 
-@pytest.mark.parametrize("comp", ["gzip", "xz", "zip", "zstd"])
-def test_wrong_compression_bz2(parser, comp):
-    with tm.ensure_clean() as path:
-        geom_df.to_xml(path, parser=parser, compression=comp)
-
-        with pytest.raises(OSError, match="Invalid data stream"):
-            read_xml(path, parser=parser, compression="bz2")
-
-
-@pytest.mark.parametrize("comp", ["bz2", "xz", "zip", "zstd"])
-def test_wrong_compression_gz(parser, comp):
-    with tm.ensure_clean() as path:
-        geom_df.to_xml(path, parser=parser, compression=comp)
-
-        with pytest.raises(OSError, match="Not a gzipped file"):
-            read_xml(path, parser=parser, compression="gzip")
-
-
-@pytest.mark.parametrize("comp", ["bz2", "gzip", "zip", "zstd"])
-def test_wrong_compression_xz(parser, comp):
-    from lzma import LZMAError
-
-    with tm.ensure_clean() as path:
-        geom_df.to_xml(path, parser=parser, compression=comp)
-
-        with pytest.raises(LZMAError, match="Input format not supported by decoder"):
-            read_xml(path, parser=parser, compression="xz")
-
-
-@pytest.mark.parametrize("comp", ["bz2", "gzip", "xz", "zstd"])
-def test_wrong_compression_zip(parser, comp):
-    from zipfile import BadZipFile
-
-    with tm.ensure_clean() as path:
-        geom_df.to_xml(path, parser=parser, compression=comp)
-
-        with pytest.raises(BadZipFile, match="File is not a zip file"):
-            read_xml(path, parser=parser, compression="zip")
+def test_wrong_compression(parser, compression, compression_only):
+    actual_compression = compression
+    attempted_compression = compression_only
 
+    if actual_compression == attempted_compression:
+        return
 
-@pytest.mark.parametrize("comp", ["bz2", "gzip", "xz", "zip"])
-def test_wrong_compression_zstandard(parser, comp):
-    from zipfile import BadZipFile
+    error_cls, error_str = {
+        "bz2": (OSError, "Invalid data stream"),
+        "gzip": (OSError, "Not a gzipped file"),
+        "xz": (LZMAError, "Input format not supported by decoder"),
+        "zip": (BadZipFile, "File is not a zip file"),
+        "zstd": (ZstdError, "Unknown frame descriptor"),
+    }[attempted_compression]
 
     with tm.ensure_clean() as path:
-        geom_df.to_xml(path, parser=parser, compression=comp)
+        geom_df.to_xml(path, parser=parser, compression=actual_compression)
 
-        with pytest.raises(BadZipFile, match="File is not a zip file"):
-            read_xml(path, parser=parser, compression="zstd")
+        with pytest.raises(error_cls, match=error_str):
+            read_xml(path, parser=parser, compression=attempted_compression)
 
 
 def test_unsuported_compression(datapath, parser):