[Python-checkins] python/dist/src/Lib glob.py,1.11,1.12

[jlgijsbers at users.sourceforge.net]

Update of /cvsroot/python/python/dist/src/Lib
In directory sc8-pr-cvs1.sourceforge.net:/tmp/cvs-serv8739/Lib

Modified Files:
	glob.py 
Log Message:
Patch #943206:

`glob.glob()` currently calls itself recursively to build a list of matches of
the dirname part of the pattern and then filters by the basename part. This is
effectively BFS. ``glob.glob('*/*/*/*/*/foo')`` will build a huge list of all
directories 5 levels deep even if only a handful of them contain a ``foo``
entry. A generator-based recusion would never have to store these list at once
by implementing DFS. This patch converts the `glob` function to an `iglob`
recursive generator . `glob()` now just returns ``list(iglob(pattern))``.

I also cleaned up the code a bit (reduced duplicate `has_magic()` checks and
created a second `glob0` helper func so that the main loop need not be
duplicated).

Thanks to Cherniavsky Beni for the patch!



Index: glob.py
===================================================================
RCS file: /cvsroot/python/python/dist/src/Lib/glob.py,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -d -r1.11 -r1.12
--- glob.py	30 Aug 2004 10:19:54 -0000	1.11
+++ glob.py	8 Jan 2005 13:13:14 -0000	1.12
@@ -4,7 +4,7 @@
 import fnmatch
 import re
 
-__all__ = ["glob"]
+__all__ = ["glob", "iglob"]
 
 def glob(pathname):
     """Return a list of paths matching a pathname pattern.
@@ -12,35 +12,42 @@
     The pattern may contain simple shell-style wildcards a la fnmatch.
 
     """
+    return list(iglob(pathname))
+
+def iglob(pathname):
+    """Return a list of paths matching a pathname pattern.
+
+    The pattern may contain simple shell-style wildcards a la fnmatch.
+
+    """
     if not has_magic(pathname):
         if os.path.lexists(pathname):
-            return [pathname]
-        else:
-            return []
+            yield pathname
+        return
     dirname, basename = os.path.split(pathname)
     if not dirname:
-        return glob1(os.curdir, basename)
-    elif has_magic(dirname):
-        list = glob(dirname)
+        for name in glob1(os.curdir, basename):
+            yield name
+        return
+    if has_magic(dirname):
+        dirs = iglob(dirname)
     else:
-        list = [dirname]
-    if not has_magic(basename):
-        result = []
-        for dirname in list:
-            if basename or os.path.isdir(dirname):
-                name = os.path.join(dirname, basename)
-                if os.path.lexists(name):
-                    result.append(name)
+        dirs = [dirname]
+    if has_magic(basename):
+        glob_in_dir = glob1
     else:
-        result = []
-        for dirname in list:
-            sublist = glob1(dirname, basename)
-            for name in sublist:
-                result.append(os.path.join(dirname, name))
-    return result
+        glob_in_dir = glob0
+    for dirname in dirs:
+        for name in glob_in_dir(dirname, basename):
+            yield os.path.join(dirname, name)
+
+# These 2 helper functions non-recursively glob inside a literal directory.
+# They return a list of basenames. `glob1` accepts a pattern while `glob0`
+# takes a literal basename (so it only has to check for its existence).
 
 def glob1(dirname, pattern):
-    if not dirname: dirname = os.curdir
+    if not dirname:
+        dirname = os.curdir
     try:
         names = os.listdir(dirname)
     except os.error:
@@ -49,6 +56,17 @@
         names=filter(lambda x: x[0]!='.',names)
     return fnmatch.filter(names,pattern)
 
+def glob0(dirname, basename):
+    if basename == '':
+        # `os.path.split()` returns an empty basename for paths ending with a
+        # directory separator.  'q*x/' should match only directories.
+        if os.isdir(dirname):
+            return [basename]
+    else:
+        if os.path.lexists(os.path.join(dirname, basename)):
+            return [basename]
+    return []
+
 
 magic_check = re.compile('[*?[]')