# HG changeset patch
# User Mike Edgar <adgar@google.com>
# Date 1418406134 0
# Node ID a5dbec255f146fe0d8715e61cee933898ebbb28d
# Parent  a4951adebfb08f2e2aaf92f0b746ea0a84c583bd
synthrepo: new filenames must not also be new directories, and vice-versa

When generating many new files into a set of many possible new directories,
there is the possibility that the same path is chosen as both file and
directory. How likely this is depends on the size of the dictionary used,
the generated directory structure and the number of generated files.

diff -r a4951adebfb0 -r a5dbec255f14 contrib/synthrepo.py
--- a/contrib/synthrepo.py	Thu Jan 08 13:29:06 2015 -0800
+++ b/contrib/synthrepo.py	Fri Dec 12 17:42:14 2014 +0000
@@ -323,15 +323,32 @@
     initcount = int(opts['initfiles'])
     if initcount and initdirs:
         pctx = repo[None].parents()[0]
+        dirs = set(pctx.dirs())
         files = {}
+
+        def validpath(path):
+            # Don't pick filenames which are already directory names.
+            if path in dirs:
+                return False
+            # Don't pick directories which were used as file names.
+            while path:
+                if path in files:
+                    return False
+                path = os.path.dirname(path)
+            return True
+
         for i in xrange(0, initcount):
             ui.progress(_synthesizing, i, unit=_files, total=initcount)
 
             path = pickpath()
-            while path in pctx.dirs():
+            while not validpath(path):
                 path = pickpath()
             data = '%s contents\n' % path
             files[path] = context.memfilectx(repo, path, data)
+            dir = os.path.dirname(path)
+            while dir and dir not in dirs:
+                dirs.add(dir)
+                dir = os.path.dirname(dir)
 
         def filectxfn(repo, memctx, path):
             return files[path]