codeparser: Use hashlib for hashing, not hash()

"hash() is randomised by default each time you start a new instance of
recent
versions (Python3.3+) to prevent dictionary insertion DOS attacks"

which means we need to use hashlib.md5 to get consistent values for
the codeparser cache under python 3. Prior to this, the codeparser
cache was effectively useless under python3 as shown by performance
regressions.

Signed-off-by: Richard Purdie <richard.purdie@linuxfoundation.org>

diff --git a/lib/bb/codeparser.py b/lib/bb/codeparser.py
index 6ed2adeed9d1c30190fa2162d2d98a46085682f0..25938d6586eff8900bea91e473cb658f73fadff7 100644 (file)
--- a/lib/bb/codeparser.py
+++ b/lib/bb/codeparser.py
@@ -6,12 +6,16 @@ import pickle
 import bb.pysh as pysh
 import os.path
 import bb.utils, bb.data
+import hashlib
 from itertools import chain
 from bb.pysh import pyshyacc, pyshlex, sherrors
 from bb.cache import MultiProcessCache
 
 logger = logging.getLogger('BitBake.CodeParser')
 
+def bbhash(s):
+    return hashlib.md5(s.encode("utf-8")).hexdigest()
+
 def check_indent(codestr):
     """If the code is indented, add a top level piece of code to 'remove' the indentation"""
 
@@ -270,7 +274,7 @@ class PythonParser():
         if not node or not node.strip():
             return
 
-        h = hash(str(node))
+        h = bbhash(str(node))
 
         if h in codeparsercache.pythoncache:
             self.references = set(codeparsercache.pythoncache[h].refs)
@@ -315,7 +319,7 @@ class ShellParser():
         commands it executes.
         """
 
-        h = hash(str(value))
+        h = bbhash(str(value))
 
         if h in codeparsercache.shellcache:
             self.execs = set(codeparsercache.shellcache[h].execs)