wireproto: define and implement HTTP handshake to upgrade protocol
When clients connect to repositories over HTTP, they issue a request
to the well-known URL "?cmd=capabilities" to fetch the repository
capabilities. This is the handshake portion of the HTTP protocol.
This commit defines a mechanism to use that HTTP request to return
information about modern server features.
If a client sends an X-HgUpgrade-* header containing a list of
client-supported API names, the server responds with a response
containing information about available services. This includes
the normal capabilities string. So if the server doesn't support
any newer services, the client can easily fall back.
By advertising supported services from clients, server operators
can see and log what client support exists in the wild. This will
also help with debugging.
The response contains the base path to API services. We know there
are potential issues with the <repo>/api/ URL space conflicting with
hgwebdir and subrepos. By making the API URL dynamic from the
perspective of the client, the URL for APIs is not subject to backwards
compatibility concerns - at least as long as a ?cmd=capabilities request
is made.
We've also defined the ``cbor`` client capability for the X-HgProto-*
header. This MUST be sent in order to get the modern response from
"?cmd=capabilities". During implementation, I initially always sent
an application/mercurial-cbor response. However, the handshake
mechanism will be more future compatible if the client is in charge
of which formats to request. We already perform content negotiation
from X-HgProto-*, so keying off this for the capabilities response
feels appropriate.
In addition, I initially used application/cbor. However, it is
conceivable that a non-Mercurial server could serve application/cbor.
To rule out this possibility, I've invented a new media type that
is Mercurial specific and can't be confused for generic CBOR.
Differential Revision: https://phab.mercurial-scm.org/D3242
#!/usr/bin/env python
"""
Utility for inspecting files in various ways.
This tool is like the collection of tools found in a unix environment but are
cross platform and stable and suitable for our needs in the test suite.
This can be used instead of tools like:
[
dd
find
head
hexdump
ls
md5sum
readlink
sha1sum
stat
tail
test
readlink.py
md5sum.py
"""
from __future__ import absolute_import
import binascii
import glob
import hashlib
import optparse
import os
import re
import sys
# Python 3 adapters
ispy3 = (sys.version_info[0] >= 3)
if ispy3:
def iterbytes(s):
for i in range(len(s)):
yield s[i:i + 1]
else:
iterbytes = iter
def visit(opts, filenames, outfile):
"""Process filenames in the way specified in opts, writing output to
outfile."""
for f in sorted(filenames):
isstdin = f == '-'
if not isstdin and not os.path.lexists(f):
outfile.write(b'%s: file not found\n' % f.encode('utf-8'))
continue
quiet = opts.quiet and not opts.recurse or isstdin
isdir = os.path.isdir(f)
islink = os.path.islink(f)
isfile = os.path.isfile(f) and not islink
dirfiles = None
content = None
facts = []
if isfile:
if opts.type:
facts.append(b'file')
if any((opts.hexdump, opts.dump, opts.md5, opts.sha1, opts.sha256)):
with open(f, 'rb') as fobj:
content = fobj.read()
elif islink:
if opts.type:
facts.append(b'link')
content = os.readlink(f)
elif isstdin:
content = getattr(sys.stdin, 'buffer', sys.stdin).read()
if opts.size:
facts.append(b'size=%d' % len(content))
elif isdir:
if opts.recurse or opts.type:
dirfiles = glob.glob(f + '/*')
facts.append(b'directory with %d files' % len(dirfiles))
elif opts.type:
facts.append(b'type unknown')
if not isstdin:
stat = os.lstat(f)
if opts.size and not isdir:
facts.append(b'size=%d' % stat.st_size)
if opts.mode and not islink:
facts.append(b'mode=%o' % (stat.st_mode & 0o777))
if opts.links:
facts.append(b'links=%s' % stat.st_nlink)
if opts.newer:
# mtime might be in whole seconds so newer file might be same
if stat.st_mtime >= os.stat(opts.newer).st_mtime:
facts.append(b'newer than %s' % opts.newer)
else:
facts.append(b'older than %s' % opts.newer)
if opts.md5 and content is not None:
h = hashlib.md5(content)
facts.append(b'md5=%s' % binascii.hexlify(h.digest())[:opts.bytes])
if opts.sha1 and content is not None:
h = hashlib.sha1(content)
facts.append(b'sha1=%s' % binascii.hexlify(h.digest())[:opts.bytes])
if opts.sha256 and content is not None:
h = hashlib.sha256(content)
facts.append(b'sha256=%s' %
binascii.hexlify(h.digest())[:opts.bytes])
if isstdin:
outfile.write(b', '.join(facts) + b'\n')
elif facts:
outfile.write(b'%s: %s\n' % (f.encode('utf-8'), b', '.join(facts)))
elif not quiet:
outfile.write(b'%s:\n' % f.encode('utf-8'))
if content is not None:
chunk = content
if not islink:
if opts.lines:
if opts.lines >= 0:
chunk = b''.join(chunk.splitlines(True)[:opts.lines])
else:
chunk = b''.join(chunk.splitlines(True)[opts.lines:])
if opts.bytes:
if opts.bytes >= 0:
chunk = chunk[:opts.bytes]
else:
chunk = chunk[opts.bytes:]
if opts.hexdump:
for i in range(0, len(chunk), 16):
s = chunk[i:i + 16]
outfile.write(b'%04x: %-47s |%s|\n' %
(i, b' '.join(
b'%02x' % ord(c) for c in iterbytes(s)),
re.sub(b'[^ -~]', b'.', s)))
if opts.dump:
if not quiet:
outfile.write(b'>>>\n')
outfile.write(chunk)
if not quiet:
if chunk.endswith(b'\n'):
outfile.write(b'<<<\n')
else:
outfile.write(b'\n<<< no trailing newline\n')
if opts.recurse and dirfiles:
assert not isstdin
visit(opts, dirfiles, outfile)
if __name__ == "__main__":
parser = optparse.OptionParser("%prog [options] [filenames]")
parser.add_option("-t", "--type", action="store_true",
help="show file type (file or directory)")
parser.add_option("-m", "--mode", action="store_true",
help="show file mode")
parser.add_option("-l", "--links", action="store_true",
help="show number of links")
parser.add_option("-s", "--size", action="store_true",
help="show size of file")
parser.add_option("-n", "--newer", action="store",
help="check if file is newer (or same)")
parser.add_option("-r", "--recurse", action="store_true",
help="recurse into directories")
parser.add_option("-S", "--sha1", action="store_true",
help="show sha1 hash of the content")
parser.add_option("", "--sha256", action="store_true",
help="show sha256 hash of the content")
parser.add_option("-M", "--md5", action="store_true",
help="show md5 hash of the content")
parser.add_option("-D", "--dump", action="store_true",
help="dump file content")
parser.add_option("-H", "--hexdump", action="store_true",
help="hexdump file content")
parser.add_option("-B", "--bytes", type="int",
help="number of characters to dump")
parser.add_option("-L", "--lines", type="int",
help="number of lines to dump")
parser.add_option("-q", "--quiet", action="store_true",
help="no default output")
(opts, filenames) = parser.parse_args(sys.argv[1:])
if not filenames:
filenames = ['-']
visit(opts, filenames, getattr(sys.stdout, 'buffer', sys.stdout))