bpo-32775: Fix regular expression warnings in fnmatch. (#5583)

fnmatch.translate() no longer produces patterns which contain set
operations.

Sets starting with '[' or containing '--', '&&', '~~' or '||' will
be interpreted differently in regular expressions in future versions.
Currently they emit warnings. fnmatch.translate() now avoids producing
patterns containing such sets by accident.

1 files changed, 21 insertions, 2 deletions

diff --git a/Lib/fnmatch.py b/Lib/fnmatch.py
index fd3b514..b98e641 100644
--- a/Lib/fnmatch.py
+++ b/Lib/fnmatch.py
@@ -97,11 +97,30 @@ def translate(pat):
             if j >= n:
                 res = res + '\\['
             else:
-                stuff = pat[i:j].replace('\\','\\\\')
+                stuff = pat[i:j]
+                if '--' not in stuff:
+                    stuff = stuff.replace('\\', r'\\')
+                else:
+                    chunks = []
+                    k = i+2 if pat[i] == '!' else i+1
+                    while True:
+                        k = pat.find('-', k, j)
+                        if k < 0:
+                            break
+                        chunks.append(pat[i:k])
+                        i = k+1
+                        k = k+3
+                    chunks.append(pat[i:j])
+                    # Escape backslashes and hyphens for set difference (--).
+                    # Hyphens that create ranges shouldn't be escaped.
+                    stuff = '-'.join(s.replace('\\', r'\\').replace('-', r'\-')
+                                     for s in chunks)
+                # Escape set operations (&&, ~~ and ||).
+                stuff = re.sub(r'([&~|])', r'\\\1', stuff)
                 i = j+1
                 if stuff[0] == '!':
                     stuff = '^' + stuff[1:]
-                elif stuff[0] == '^':
+                elif stuff[0] in ('^', '['):
                     stuff = '\\' + stuff
                 res = '%s[%s]' % (res, stuff)
         else: