Merge pull request #1799 from et-repositories/main

Byron · web-flow · commit d28c20b1dbf1 · 2024-01-16T21:14:43.000+01:00
fix: treeNotSorted issue
diff --git a/AUTHORS b/AUTHORS
@@ -53,5 +53,6 @@ Contributors are:
 -Santos Gallegos <stsewd _at_ proton.me>
 -Wenhan Zhu <wzhu.cosmos _at_ gmail.com>
 -Eliah Kagan <eliah.kagan _at_ gmail.com>
+-Ethan Lin <et.repositories _at_ gmail.com>
 
 Portions derived from other open source works and are clearly marked.
diff --git a/git/objects/tree.py b/git/objects/tree.py
@@ -53,54 +53,6 @@
 __all__ = ("TreeModifier", "Tree")
 
 
-def git_cmp(t1: TreeCacheTup, t2: TreeCacheTup) -> int:
-    a, b = t1[2], t2[2]
-    # assert isinstance(a, str) and isinstance(b, str)
-    len_a, len_b = len(a), len(b)
-    min_len = min(len_a, len_b)
-    min_cmp = cmp(a[:min_len], b[:min_len])
-
-    if min_cmp:
-        return min_cmp
-
-    return len_a - len_b
-
-
-def merge_sort(a: List[TreeCacheTup], cmp: Callable[[TreeCacheTup, TreeCacheTup], int]) -> None:
-    if len(a) < 2:
-        return
-
-    mid = len(a) // 2
-    lefthalf = a[:mid]
-    righthalf = a[mid:]
-
-    merge_sort(lefthalf, cmp)
-    merge_sort(righthalf, cmp)
-
-    i = 0
-    j = 0
-    k = 0
-
-    while i < len(lefthalf) and j < len(righthalf):
-        if cmp(lefthalf[i], righthalf[j]) <= 0:
-            a[k] = lefthalf[i]
-            i = i + 1
-        else:
-            a[k] = righthalf[j]
-            j = j + 1
-        k = k + 1
-
-    while i < len(lefthalf):
-        a[k] = lefthalf[i]
-        i = i + 1
-        k = k + 1
-
-    while j < len(righthalf):
-        a[k] = righthalf[j]
-        j = j + 1
-        k = k + 1
-
-
 class TreeModifier:
     """A utility class providing methods to alter the underlying cache in a list-like fashion.
 
@@ -131,7 +83,7 @@ def set_done(self) -> "TreeModifier":
 
         :return self:
         """
-        merge_sort(self._cache, git_cmp)
+        self._cache.sort(key=lambda x: (x[2] + "/") if x[1] == Tree.tree_id << 12 else x[2])
         return self
 
     # } END interface
diff --git a/test/test_tree.py b/test/test_tree.py
@@ -8,7 +8,9 @@
 from git.objects import Tree, Blob
 from test.lib import TestBase
 
+import os
 import os.path as osp
+import subprocess
 
 
 class TestTree(TestBase):
@@ -40,6 +42,62 @@ def test_serializable(self):
             testtree._deserialize(stream)
         # END for each item in tree
 
+    def test_tree_modifier_ordering(self):
+        def setup_git_repository_and_get_ordered_files():
+            os.mkdir("tmp")
+            os.chdir("tmp")
+            subprocess.run(["git", "init", "-q"], check=True)
+            os.mkdir("file")
+            for filename in [
+                "bin",
+                "bin.d",
+                "file.to",
+                "file.toml",
+                "file.toml.bin",
+                "file0",
+                "file/a",
+            ]:
+                open(filename, "a").close()
+
+            subprocess.run(["git", "add", "."], check=True)
+            subprocess.run(["git", "commit", "-m", "c1"], check=True)
+            tree_hash = subprocess.check_output(["git", "rev-parse", "HEAD^{tree}"]).decode().strip()
+            cat_file_output = subprocess.check_output(["git", "cat-file", "-p", tree_hash]).decode()
+            return [line.split()[-1] for line in cat_file_output.split("\n") if line]
+
+        hexsha = "6c1faef799095f3990e9970bc2cb10aa0221cf9c"
+        roottree = self.rorepo.tree(hexsha)
+        blob_mode = Tree.blob_id << 12
+        tree_mode = Tree.tree_id << 12
+
+        files_in_desired_order = [
+            (blob_mode, "bin"),
+            (blob_mode, "bin.d"),
+            (blob_mode, "file.to"),
+            (blob_mode, "file.toml"),
+            (blob_mode, "file.toml.bin"),
+            (blob_mode, "file0"),
+            (tree_mode, "file"),
+        ]
+        mod = roottree.cache
+        for file_mode, file_name in files_in_desired_order:
+            mod.add(hexsha, file_mode, file_name)
+        # end for each file
+
+        def file_names_in_order():
+            return [t[1] for t in files_in_desired_order]
+
+        def names_in_mod_cache():
+            a = [t[2] for t in mod._cache]
+            here = file_names_in_order()
+            return [e for e in a if e in here]
+
+        git_file_names_in_order = setup_git_repository_and_get_ordered_files()
+        os.chdir("..")
+
+        mod.set_done()
+        assert names_in_mod_cache() == git_file_names_in_order, "set_done() performs git-sorting"
+
     def test_traverse(self):
         root = self.rorepo.tree("0.1.6")
         num_recursive = 0
