Merge pull request #146 from SethMMorton/over-zealous-extension-splitting

Over zealous extension splitting

4 files changed, 59 insertions, 18 deletions

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 2f81376..b1475fc 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,18 +1,22 @@
 Unreleased
 ---
 
+### Changed
+- When using `ns.PATH`, only split off a maximum of two suffixes from
+  a file name (issues #145, #146).
+
 [8.0.2] - 2021-12-14
 ---
 
 ### Fixed
-- Bug where sorting paths fail if one of the paths is '.'.
+- Bug where sorting paths fail if one of the paths is '.' (issues #142, #143)
 
 [8.0.1] - 2021-12-10
 ---
 
 ### Fixed
 - Compose unicode characters when using locale to ensure sorting is correct
-  across all locales.
+  across all locales (issues #140, #141)
 
 [8.0.0] - 2021-11-03
 ---
diff --git a/natsort/utils.py b/natsort/utils.py
index 8d56b06..3832318 100644
--- a/natsort/utils.py
+++ b/natsort/utils.py
@@ -893,16 +893,21 @@ def path_splitter(
         path_parts = []
         base = str(s)
 
-    # Now, split off the file extensions until we reach a decimal number at
-    # the beginning of the suffix or there are no more extensions.
-    suffixes = PurePath(base).suffixes
-    try:
-        digit_index = next(i for i, x in enumerate(reversed(suffixes)) if _d_match(x))
-    except StopIteration:
-        pass
-    else:
-        digit_index = len(suffixes) - digit_index
-        suffixes = suffixes[digit_index:]
-
+    # Now, split off the file extensions until
+    #  - we reach a decimal number at the beginning of the suffix
+    #  - more than two suffixes have been seen
+    #  - a suffix is more than five characters (including leading ".")
+    #  - there are no more extensions
+    suffixes = []
+    for i, suffix in enumerate(reversed(PurePath(base).suffixes)):
+        if _d_match(suffix) or i > 1 or len(suffix) > 5:
+            break
+        suffixes.append(suffix)
+    suffixes.reverse()
+
+    # Remove the suffixes from the base component
     base = base.replace("".join(suffixes), "")
-    return filter(None, ichain(path_parts, [base], suffixes))
+    base_component = [base] if base else []
+
+    # Join all path comonents in an iterator
+    return filter(None, ichain(path_parts, base_component, suffixes))
diff --git a/tests/test_natsorted.py b/tests/test_natsorted.py
index 4a64a27..eb3aefe 100644
--- a/tests/test_natsorted.py
+++ b/tests/test_natsorted.py
@@ -182,6 +182,21 @@ def test_natsorted_handles_numbers_and_filesystem_paths_simultaneously() -> None
     assert natsorted(given, alg=ns.PATH) == expected
 
 
+def test_natsorted_path_extensions_heuristic() -> None:
+    # https://github.com/SethMMorton/natsort/issues/145
+    given = [
+        "Try.Me.Bug - 09 - One.Two.Three.[text].mkv",
+        "Try.Me.Bug - 07 - One.Two.5.[text].mkv",
+        "Try.Me.Bug - 08 - One.Two.Three[text].mkv",
+    ]
+    expected = [
+        "Try.Me.Bug - 07 - One.Two.5.[text].mkv",
+        "Try.Me.Bug - 08 - One.Two.Three[text].mkv",
+        "Try.Me.Bug - 09 - One.Two.Three.[text].mkv",
+    ]
+    assert natsorted(given, alg=ns.PATH) == expected
+
+
 @pytest.mark.parametrize(
     "alg, expected",
     [
diff --git a/tests/test_utils.py b/tests/test_utils.py
index bb229b9..b140682 100644
--- a/tests/test_utils.py
+++ b/tests/test_utils.py
@@ -6,7 +6,7 @@ import pathlib
 import string
 from itertools import chain
 from operator import neg as op_neg
-from typing import List, Pattern, Union
+from typing import List, Pattern, Tuple, Union
 
 import pytest
 from hypothesis import given
@@ -155,9 +155,26 @@ def test_path_splitter_splits_path_string_by_sep(x: List[str]) -> None:
     assert tuple(utils.path_splitter(z)) == tuple(pathlib.Path(z).parts)
 
 
-def test_path_splitter_splits_path_string_by_sep_and_removes_extension_example() -> None:
-    given = "/this/is/a/path/file.x1.10.tar.gz"
-    expected = (os.sep, "this", "is", "a", "path", "file.x1.10", ".tar", ".gz")
+@pytest.mark.parametrize(
+    "given, expected",
+    [
+        (
+            "/this/is/a/path/file.x1.10.tar.gz",
+            (os.sep, "this", "is", "a", "path", "file.x1.10", ".tar", ".gz"),
+        ),
+        (
+            "/this/is/a/path/file.x1.10.tar",
+            (os.sep, "this", "is", "a", "path", "file.x1.10", ".tar"),
+        ),
+        (
+            "/this/is/a/path/file.x1.threethousand.tar",
+            (os.sep, "this", "is", "a", "path", "file.x1.threethousand", ".tar"),
+        ),
+    ],
+)
+def test_path_splitter_splits_path_string_by_sep_and_removes_extension_example(
+    given: str, expected: Tuple[str, ...]
+) -> None:
     assert tuple(utils.path_splitter(given)) == tuple(expected)