cborutil: implement sans I/O decoder
The vendored CBOR package decodes by calling read(n) on an object.
There are a number of disadvantages to this:
* Uses blocking I/O. If sufficient data is not available, the decoder
will hang until it is.
* No support for partial reads. If the read(n) returns less data than
requested, the decoder raises an error.
* Requires the use of a file like object. If the original data is in
say a buffer, we need to "cast" it to e.g. a BytesIO to appease the
decoder.
In addition, the vendored CBOR decoder doesn't provide flexibility
that we desire. Specifically:
* It buffers indefinite length bytestrings instead of streaming them.
* It doesn't allow limiting the set of types that can be decoded. This
property is useful when implementing a "hardened" decoder that is
less susceptible to abusive input.
* It doesn't provide sufficient "hook points" and introspection to
institute checks around behavior. These are useful for implementing
a "hardened" decoder.
This all adds up to a reasonable set of justifications for writing our
own decoder.
So, this commit implements our own CBOR decoder.
At the heart of the decoder is a function that decodes a single "item"
from a buffer. This item can be a complete simple value or a special
value, such as "start of array." Using this function, we can build a
decoder that effectively iterates over the stream of decoded items and
builds up higher-level values, such as arrays, maps, sets, and indefinite
length bytestrings. And we can do this without performing I/O in the
decoder itself.
The core of the sans I/O decoder will probably not be used directly.
Instead, it is expected that we'll build utility functions for invoking
the decoder given specific input types. This will allow extreme
flexibility in how data is delivered to the decoder.
I'm pretty happy with the state of the decoder modulo the TODO items
to track wanted features to help with a "hardened" decoder. The one
thing I could be convinced to change is the handling of semantic tags.
Since we only support a single semantic tag (sets), I thought it would
be easier to handle them inline in decodeitem(). This is simpler now.
But if we add support for other semantic tags, it will likely be easier
to move semantic tag handling outside of decodeitem(). But, properly
supporting semantic tags opens up a whole can of worms, as many
semantic tags imply new types. I'm optimistic we won't need these in
Mercurial. But who knows.
I'm also pretty happy with the test coverage. Writing comprehensive
tests for partial decoding did flush out a handful of bugs. One
general improvement to testing would be fuzz testing for partial
decoding. I may implement that later. I also anticipate switching the
wire protocol code to this new decoder will flush out any lingering
bugs.
Differential Revision: https://phab.mercurial-scm.org/D4414
from __future__ import absolute_import
import unittest
from mercurial import error, mdiff
# for readability, line numbers are 0-origin
text1 = b'''
00 at OLD
01 at OLD
02 at OLD
02 at NEW, 03 at OLD
03 at NEW, 04 at OLD
04 at NEW, 05 at OLD
05 at NEW, 06 at OLD
07 at OLD
08 at OLD
09 at OLD
10 at OLD
11 at OLD
'''[1:] # strip initial LF
text2 = b'''
00 at NEW
01 at NEW
02 at NEW, 03 at OLD
03 at NEW, 04 at OLD
04 at NEW, 05 at OLD
05 at NEW, 06 at OLD
06 at NEW
07 at NEW
08 at NEW
09 at NEW
10 at NEW
11 at NEW
'''[1:] # strip initial LF
def filteredblocks(blocks, rangeb):
"""return `rangea` extracted from `blocks` coming from
`mdiff.blocksinrange` along with the mask of blocks within rangeb.
"""
filtered, rangea = mdiff.blocksinrange(blocks, rangeb)
skipped = [b not in filtered for b in blocks]
return rangea, skipped
class blocksinrangetests(unittest.TestCase):
def setUp(self):
self.blocks = list(mdiff.allblocks(text1, text2))
assert self.blocks == [
([0, 3, 0, 2], b'!'),
((3, 7, 2, 6), b'='),
([7, 12, 6, 12], b'!'),
((12, 12, 12, 12), b'='),
], self.blocks
def testWithinEqual(self):
"""linerange within an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^
linerange2 = (3, 5)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (4, 6))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualStrictly(self):
"""linerange matching exactly an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^
linerange2 = (2, 6)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (3, 7))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualLowerbound(self):
"""linerange at beginning of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^
linerange2 = (2, 4)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (3, 5))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualLowerboundOneline(self):
"""oneline-linerange at beginning of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
linerange2 = (2, 3)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (3, 4))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualUpperbound(self):
"""linerange at end of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^
linerange2 = (3, 6)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (4, 7))
self.assertEqual(skipped, [True, False, True, True])
def testWithinEqualUpperboundOneLine(self):
"""oneline-linerange at end of an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
linerange2 = (5, 6)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (6, 7))
self.assertEqual(skipped, [True, False, True, True])
def testWithinFirstBlockNeq(self):
"""linerange within the first "!" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
# | (empty)
# ^
# ^^
for linerange2 in [
(0, 1),
(1, 1),
(1, 2),
(0, 2),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (0, 3))
self.assertEqual(skipped, [False, True, True, True])
def testWithinLastBlockNeq(self):
"""linerange within the last "!" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^
# ^
# | (empty)
# ^^^^^^
# ^
for linerange2 in [
(6, 7),
(7, 8),
(7, 7),
(6, 12),
(11, 12),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (7, 12))
self.assertEqual(skipped, [True, True, False, True])
def testAccrossTwoBlocks(self):
"""linerange accross two blocks"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^
linerange2 = (1, 5)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (0, 6))
self.assertEqual(skipped, [False, False, True, True])
def testCrossingSeveralBlocks(self):
"""linerange accross three blocks"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^^^^
linerange2 = (1, 8)
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, (0, 12))
self.assertEqual(skipped, [False, False, False, True])
def testStartInEqBlock(self):
"""linerange starting in an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^^^
# ^^^^^^^
for linerange2, expectedlinerange1 in [
((5, 9), (6, 12)),
((4, 11), (5, 12)),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, expectedlinerange1)
self.assertEqual(skipped, [True, False, False, True])
def testEndInEqBlock(self):
"""linerange ending in an "=" block"""
# IDX 0 1
# 012345678901
# SRC NNOOOONNNNNN (New/Old)
# ^^
# ^^^^^
for linerange2, expectedlinerange1 in [
((1, 3), (0, 4)),
((0, 4), (0, 5)),
]:
linerange1, skipped = filteredblocks(self.blocks, linerange2)
self.assertEqual(linerange1, expectedlinerange1)
self.assertEqual(skipped, [False, False, True, True])
def testOutOfRange(self):
"""linerange exceeding file size"""
exctype = error.Abort
for linerange2 in [
(0, 34),
(15, 12),
]:
# Could be `with self.assertRaises(error.Abort)` but python2.6
# does not have assertRaises context manager.
try:
mdiff.blocksinrange(self.blocks, linerange2)
except exctype as exc:
self.assertTrue('line range exceeds file size' in str(exc))
else:
self.fail('%s not raised' % exctype.__name__)
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)