wireproto: syntax for encoding CBOR into frames

We just vendored a library for encoding and decoding the CBOR
data format. While the intent of that vendor was to support state
files, CBOR is really a nice data format. It is extensible and
compact.

I've been feeling dirty inventing my own data formats for
frame payloads. While custom formats can always beat out a generic
format, there is a cost to be paid in terms of implementation,
comprehension, etc. CBOR is compact enough that I'm not too
worried about efficiency loss. I think the benefits of using
a standardized format outweigh rolling our own formats. So
I plan to make heavy use of CBOR in the wire protocol going
forward.

This commit introduces support for encoding CBOR data in frame
payloads to our function to make a frame from a human string.
We do need to employ some low-level Python code in order to
evaluate a string as a Python expression. But other than that,
this should hopefully be pretty straightforward.

Unit tests for this function have been added.

Differential Revision: https://phab.mercurial-scm.org/D2948

mercurial/debugcommands.py

@@ -2793,7 +2793,10 b' def debugwireproto(ui, repo, path=None, '
     or a flag name for stream flags or frame flags, respectively. Values are
     resolved to integers and then bitwise OR'd together.
 
-    ``payload`` is is evaluated as a Python byte string literal.
+    ``payload`` represents the raw frame payload. If it begins with
+    ``cbor:``, the following string is evaluated as Python code and the
+    resulting object is fed into a CBOR encoder. Otherwise it is interpreted
+    as a Python byte string literal.
     """
     opts = pycompat.byteskwargs(opts)
 

mercurial/utils/stringutil.py

@@ -9,6 +9,7 b''
 
 from __future__ import absolute_import
 
+import __future__
 import codecs
 import re as remod
 import textwrap
@@ -497,3 +498,29 b' def parsebool(s):'
     If s is not a valid boolean, returns None.
     """
     return _booleans.get(s.lower(), None)
+
+def evalpython(s):
+    """Evaluate a string containing a Python expression.
+
+    THIS FUNCTION IS NOT SAFE TO USE ON UNTRUSTED INPUT. IT'S USE SHOULD BE
+    LIMITED TO DEVELOPER-FACING FUNCTIONALITY.
+    """
+    globs = {
+        r'__builtins__': {
+            r'None': None,
+            r'False': False,
+            r'True': True,
+            r'int': int,
+            r'set': set,
+            r'tuple': tuple,
+            # Don't need to expose dict and list because we can use
+            # literals.
+        },
+    }
+
+    # We can't use eval() directly because it inherits compiler
+    # flags from this module and we need unicode literals for Python 3
+    # compatibility.
+    code = compile(s, r'<string>', r'eval',
+                   __future__.unicode_literals.compiler_flag, True)
+    return eval(code, globs, {})

mercurial/wireprotoframing.py

@@ -16,6 +16,7 b' import struct'
 from .i18n import _
 from .thirdparty import (
     attr,
+    cbor,
 )
 from . import (
     error,
@@ -156,6 +157,9 b' def makeframe(requestid, streamid, strea'
 def makeframefromhumanstring(s):
     """Create a frame from a human readable string
 
+    DANGER: NOT SAFE TO USE WITH UNTRUSTED INPUT BECAUSE OF POTENTIAL
+    eval() USAGE. DO NOT USE IN CORE.
+
     Strings have the form:
 
         <request-id> <stream-id> <stream-flags> <type> <flags> <payload>
@@ -169,6 +173,11 b' def makeframefromhumanstring(s):'
     named constant.
 
     Flags can be delimited by `|` to bitwise OR them together.
+
+    If the payload begins with ``cbor:``, the following string will be
+    evaluated as Python code and the resulting object will be fed into
+    a CBOR encoder. Otherwise, the payload is interpreted as a Python
+    byte string literal.
     """
     fields = s.split(b' ', 5)
     requestid, streamid, streamflags, frametype, frameflags, payload = fields
@@ -196,7 +205,11 b' def makeframefromhumanstring(s):'
         else:
             finalflags |= int(flag)
 
-    payload = stringutil.unescapestr(payload)
+    if payload.startswith(b'cbor:'):
+        payload = cbor.dumps(stringutil.evalpython(payload[5:]), canonical=True)
+
+    else:
+        payload = stringutil.unescapestr(payload)
 
     return makeframe(requestid=requestid, streamid=streamid,
                      streamflags=finalstreamflags, typeid=frametype,

tests/test-wireproto-serverreactor.py

@@ -35,6 +35,59 b' def sendcommandframes(reactor, stream, r'
                       framing.createcommandframes(stream, rid, cmd, args,
                                                   datafh))
 
+class FrameHumanStringTests(unittest.TestCase):
+    def testbasic(self):
+        self.assertEqual(ffs(b'1 1 0 1 0 '),
+                         b'\x00\x00\x00\x01\x00\x01\x00\x10')
+
+        self.assertEqual(ffs(b'2 4 0 1 0 '),
+                         b'\x00\x00\x00\x02\x00\x04\x00\x10')
+
+        self.assertEqual(ffs(b'2 4 0 1 0 foo'),
+                         b'\x03\x00\x00\x02\x00\x04\x00\x10foo')
+
+    def testcborint(self):
+        self.assertEqual(ffs(b'1 1 0 1 0 cbor:15'),
+                         b'\x01\x00\x00\x01\x00\x01\x00\x10\x0f')
+
+        self.assertEqual(ffs(b'1 1 0 1 0 cbor:42'),
+                         b'\x02\x00\x00\x01\x00\x01\x00\x10\x18*')
+
+        self.assertEqual(ffs(b'1 1 0 1 0 cbor:1048576'),
+                         b'\x05\x00\x00\x01\x00\x01\x00\x10\x1a'
+                         b'\x00\x10\x00\x00')
+
+        self.assertEqual(ffs(b'1 1 0 1 0 cbor:0'),
+                         b'\x01\x00\x00\x01\x00\x01\x00\x10\x00')
+
+        self.assertEqual(ffs(b'1 1 0 1 0 cbor:-1'),
+                         b'\x01\x00\x00\x01\x00\x01\x00\x10 ')
+
+        self.assertEqual(ffs(b'1 1 0 1 0 cbor:-342542'),
+                         b'\x05\x00\x00\x01\x00\x01\x00\x10:\x00\x05:\r')
+
+    def testcborstrings(self):
+        # String literals should be unicode.
+        self.assertEqual(ffs(b"1 1 0 1 0 cbor:'foo'"),
+                         b'\x04\x00\x00\x01\x00\x01\x00\x10cfoo')
+
+        self.assertEqual(ffs(b"1 1 0 1 0 cbor:b'foo'"),
+                         b'\x04\x00\x00\x01\x00\x01\x00\x10Cfoo')
+
+        self.assertEqual(ffs(b"1 1 0 1 0 cbor:u'foo'"),
+                         b'\x04\x00\x00\x01\x00\x01\x00\x10cfoo')
+
+    def testcborlists(self):
+        self.assertEqual(ffs(b"1 1 0 1 0 cbor:[None, True, False, 42, b'foo']"),
+                         b'\n\x00\x00\x01\x00\x01\x00\x10\x85\xf6\xf5\xf4'
+                         b'\x18*Cfoo')
+
+    def testcbordicts(self):
+        self.assertEqual(ffs(b"1 1 0 1 0 "
+                             b"cbor:{b'foo': b'val1', b'bar': b'val2'}"),
+                         b'\x13\x00\x00\x01\x00\x01\x00\x10\xa2'
+                         b'CbarDval2CfooDval1')
+
 class FrameTests(unittest.TestCase):
     def testdataexactframesize(self):
         data = util.bytesio(b'x' * framing.DEFAULT_MAX_FRAME_SIZE)