Issue #10395: Added os.path.commonpath(). Implemented in posixpath and ntpath.

Based on patch by Rafik Draoui.

1 files changed, 62 insertions, 1 deletions

diff --git a/Lib/ntpath.py b/Lib/ntpath.py
index 6732aa2..cfb4606 100644
--- a/Lib/ntpath.py
+++ b/Lib/ntpath.py
@@ -17,7 +17,7 @@ __all__ = ["normcase","isabs","join","splitdrive","split","splitext",
            "ismount", "expanduser","expandvars","normpath","abspath",
            "splitunc","curdir","pardir","sep","pathsep","defpath","altsep",
            "extsep","devnull","realpath","supports_unicode_filenames","relpath",
-           "samefile", "sameopenfile", "samestat",]
+           "samefile", "sameopenfile", "samestat", "commonpath"]
 
 # strings representing various path-related bits and pieces
 # These are primarily for export; internally, they are hardcoded.
@@ -589,6 +589,67 @@ def relpath(path, start=None):
         raise
 
 
+# Return the longest common sub-path of the sequence of paths given as input.
+# The function is case-insensitive and 'separator-insensitive', i.e. if the
+# only difference between two paths is the use of '\' versus '/' as separator,
+# they are deemed to be equal.
+#
+# However, the returned path will have the standard '\' separator (even if the
+# given paths had the alternative '/' separator) and will have the case of the
+# first path given in the sequence. Additionally, any trailing separator is
+# stripped from the returned path.
+
+def commonpath(paths):
+    """Given a sequence of path names, returns the longest common sub-path."""
+
+    if not paths:
+        raise ValueError('commonpath() arg is an empty sequence')
+
+    if isinstance(paths[0], bytes):
+        sep = b'\\'
+        altsep = b'/'
+        curdir = b'.'
+    else:
+        sep = '\\'
+        altsep = '/'
+        curdir = '.'
+
+    try:
+        drivesplits = [splitdrive(p.replace(altsep, sep).lower()) for p in paths]
+        split_paths = [p.split(sep) for d, p in drivesplits]
+
+        try:
+            isabs, = set(p[:1] == sep for d, p in drivesplits)
+        except ValueError:
+            raise ValueError("Can't mix absolute and relative paths") from None
+
+        # Check that all drive letters or UNC paths match. The check is made only
+        # now otherwise type errors for mixing strings and bytes would not be
+        # caught.
+        if len(set(d for d, p in drivesplits)) != 1:
+            raise ValueError("Paths don't have the same drive")
+
+        drive, path = splitdrive(paths[0].replace(altsep, sep))
+        common = path.split(sep)
+        common = [c for c in common if c and c != curdir]
+
+        split_paths = [[c for c in s if c and c != curdir] for s in split_paths]
+        s1 = min(split_paths)
+        s2 = max(split_paths)
+        for i, c in enumerate(s1):
+            if c != s2[i]:
+                common = common[:i]
+                break
+        else:
+            common = common[:len(s1)]
+
+        prefix = drive + sep if isabs else drive
+        return prefix + sep.join(common)
+    except (TypeError, AttributeError):
+        genericpath._check_arg_types('commonpath', *paths)
+        raise
+
+
 # determine if two files are in fact the same file
 try:
     # GetFinalPathNameByHandle is available starting with Windows 6.0.