bitbake: siggen: Change file format of siginfo files to use zstd comp…

…ressed json

Since OE is about to change to zstd compression of sstate, it would make it
timely to convert the siginfo files from pickle which isn't reproducible
to json which is both reproducible and also human readable. At the same time
add zstd compression. This makes the siginfo files smaller, reprodubicle
and easier to debug.

Backwards compatibility mixing the two formats hasn't been supported since
in reality if sstate changes at the same time, files will be in one format
or the new one but comparing mixed formats won't make much sense.

Since json doesn't support sets, we translate them into lists in the files
themselves. We only use sets in bitbake since it makes things easier in
the internal code, sorted lists are fine for the file format.

[YOCTO #13973]

(Bitbake rev: b530e42ef01b9531c67fb260884fb89d096687a8)

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

bitbake/lib/bb/siggen.py

@@ -11,6 +11,8 @@
 import bb.data
 import difflib
 import simplediff
+import json
+import bb.compress.zstd
 from bb.checksum import FileChecksumCache
 from bb import runqueue
 import hashserv
@@ -19,6 +21,12 @@
 logger = logging.getLogger('BitBake.SigGen')
 hashequiv_logger = logging.getLogger('BitBake.SigGen.HashEquiv')
 
+class SetEncoder(json.JSONEncoder):
+    def default(self, obj):
+        if isinstance(obj, set):
+            return list(sorted(obj))
+        return json.JSONEncoder.default(self, obj)
+
 def init(d):
     siggens = [obj for obj in globals().values()
                       if type(obj) is type and issubclass(obj, SignatureGenerator)]
@@ -398,9 +406,9 @@ def dump_sigtask(self, fn, task, stampbase, runtime):
 
         fd, tmpfile = tempfile.mkstemp(dir=os.path.dirname(sigfile), prefix="sigtask.")
         try:
-            with os.fdopen(fd, "wb") as stream:
-                p = pickle.dump(data, stream, -1)
-                stream.flush()
+            with bb.compress.zstd.open(fd, "wt", encoding="utf-8", num_threads=1) as f:
+                json.dump(data, f, sort_keys=True, separators=(",", ":"), cls=SetEncoder)
+                f.flush()
             os.chmod(tmpfile, 0o664)
             bb.utils.rename(tmpfile, sigfile)
         except (OSError, IOError) as err:
@@ -794,12 +802,10 @@ def color_format(formatstr, **values):
         formatparams.update(values)
         return formatstr.format(**formatparams)
 
-    with open(a, 'rb') as f:
-        p1 = pickle.Unpickler(f)
-        a_data = p1.load()
-    with open(b, 'rb') as f:
-        p2 = pickle.Unpickler(f)
-        b_data = p2.load()
+    with bb.compress.zstd.open(a, "rt", encoding="utf-8", num_threads=1) as f:
+        a_data = json.load(f)
+    with bb.compress.zstd.open(b, "rt", encoding="utf-8", num_threads=1) as f:
+        b_data = json.load(f)
 
     def dict_diff(a, b, whitelist=set()):
         sa = set(a.keys())
@@ -1031,9 +1037,8 @@ def calc_taskhash(sigdata):
 def dump_sigfile(a):
     output = []
 
-    with open(a, 'rb') as f:
-        p1 = pickle.Unpickler(f)
-        a_data = p1.load()
+    with bb.compress.zstd.open(a, "rt", encoding="utf-8", num_threads=1) as f:
+        a_data = json.load(f)
 
     output.append("basewhitelist: %s" % (a_data['basewhitelist']))