##// END OF EJS Templates
branchmap-v3: filter topo heads using node for performance reason...
branchmap-v3: filter topo heads using node for performance reason The branchmap currently contains heads as nodeid. If we build a set of revnum with the topological heads, we need to turn the nodeid in the branchmap to revnum to be able to check if they are topo-heads. That nodeid → revnum lookup is "expensive" and adds up to something noticeable if you do it hundreds of thousand of time. Instead we turn all the topo-heads revnums into nodes and build a set. So we can directly test membership of the nodeids stored in the branchmap. That is much faster. Ideally we would have revnum in the branchmap and could directly test revnum against a revnum set and that would be even faster. However that's an adventure for another time. Without this change, the branchmap format "v3" was significantly slower than the "v2" format. With this changes, some of that gap is recovered With rust + persistent nodemap, this overhead was smaller because the extra lookup did not had to to build the nodemap from scratch. In addition the mozilla-unified repository is able to use the "pure_top" mode of branchmap v3, so it was not really affected by this. Future changeset will work of the remaining of the performance gap. ### benchmark.name = hg.command.unbundle # bin-env-vars.hg.py-re2-module = default # benchmark.variants.issue6528 = disabled # benchmark.variants.resource-usage = default # benchmark.variants.reuse-external-delta-parent = yes # benchmark.variants.revs = any-1-extra-rev # benchmark.variants.source = unbundle # benchmark.variants.validate = default # benchmark.variants.verbosity = quiet ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.233711 ~~~~~ branch-v3 before: 0.380994 (+63.02%, +0.15) branch-v3 after: 0.368769 (+57.79%, +0.14) # bin-env-vars.hg.flavor = rust branch-v2: 0.235230 ~~~~~ branch-v3 before: 0.385060 (+63.70%, +0.15) branch-v3 after: 0.372460 (+58.34%, +0.14) ## data-env-vars.name = netbeans-2018-08-01-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.255586 ~~~~~ branch-v3 before: 0.317524 (+24.23%, +0.06) branch-v3 after: 0.318907 (+24.78%, +0.06) ## data-env-vars.name = mozilla-central-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.339010 ~~~~~ branch-v3 before: 0.410007 (+20.94%, +0.07) branch-v3 after: 0.349752 (+3.17%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.346525 ~~~~~ branch-v3 before: 0.410428 (+18.44%, +0.06) branch-v3 after: 0.354300 (+2.24%, +0.01) ## data-env-vars.name = mozilla-central-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.380202 ~~~~~ branch-v3 before: 0.393871 (+3.60%, +0.01) branch-v3 after: 0.396293 (+4.23%, +0.02) ## data-env-vars.name = mozilla-unified-2024-03-22-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 0.412165 ~~~~~ branch-v3 before: 0.438105 (+6.29%, +0.03) branch-v3 after: 0.424769 (+3.06%, +0.01) # bin-env-vars.hg.flavor = rust branch-v2: 0.412397 ~~~~~ branch-v3 before: 0.438405 (+6.31%, +0.03) branch-v3 after: 0.421796 (+2.28%, +0.01) ## data-env-vars.name = mozilla-unified-2024-03-22-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 0.429501 ~~~~~ branch-v3 before: 0.452692 (+5.40%, +0.02) branch-v3 after: 0.443849 (+3.34%, +0.01) ## data-env-vars.name = mozilla-try-2024-03-26-zstd-sparse-revlog # bin-env-vars.hg.flavor = default branch-v2: 3.403171 ~~~~~ branch-v3 before: 6.562345 (+92.83%, +3.16) branch-v3 after: 6.234055 (+83.18%, +2.83) # bin-env-vars.hg.flavor = rust branch-v2: 3.454876 ~~~~~ branch-v3 before: 6.160248 (+78.31%, +2.71) branch-v3 after: 6.307813 (+82.58%, +2.85) ## data-env-vars.name = mozilla-try-2024-03-26-ds2-pnm # bin-env-vars.hg.flavor = rust branch-v2: 3.465435 ~~~~~ branch-v3 before: 5.381648 (+55.30%, +1.92) branch-v3 after: 5.176076 (+49.36%, +1.71)

File last commit:

r52756:f4733654 default
r52869:41b8892a default
Show More
wsgiheaders.py
185 lines | 6.9 KiB | text/x-python | PythonLexer
"""This was forked from cpython's wsgiref.headers module to work on bytes.
Header from old file showing copyright is below.
Much of this module is red-handedly pilfered from email.message in the stdlib,
so portions are Copyright (C) 2001,2002 Python Software Foundation, and were
written by Barry Warsaw.
"""
# Regular expression that matches `special' characters in parameters, the
# existence of which force quoting of the parameter value.
from __future__ import annotations
import re
tspecials = re.compile(br'[ ()<>@,;:\\"/\[\]?=]')
def _formatparam(param, value=None, quote=1):
"""Convenience function to format and return a key=value pair.
This will quote the value if needed or if quote is true.
"""
if value is not None and len(value) > 0:
if quote or tspecials.search(value):
value = value.replace(b'\\', b'\\\\').replace(b'"', r'\"')
return b'%s="%s"' % (param, value)
else:
return b'%s=%s' % (param, value)
else:
return param
class Headers:
"""Manage a collection of HTTP response headers"""
def __init__(self, headers=None):
headers = headers if headers is not None else []
if type(headers) is not list:
raise TypeError(b"Headers must be a list of name/value tuples")
self._headers = headers
if __debug__:
for k, v in headers:
self._convert_string_type(k)
self._convert_string_type(v)
def _convert_string_type(self, value):
"""Convert/check value type."""
if type(value) is bytes:
return value
raise AssertionError(
u"Header names/values must be"
u" of type bytes (got %s)" % repr(value)
)
def __len__(self):
"""Return the total number of headers, including duplicates."""
return len(self._headers)
def __setitem__(self, name, val):
"""Set the value of a header."""
del self[name]
self._headers.append(
(self._convert_string_type(name), self._convert_string_type(val))
)
def __delitem__(self, name):
"""Delete all occurrences of a header, if present.
Does *not* raise an exception if the header is missing.
"""
name = self._convert_string_type(name.lower())
self._headers[:] = [kv for kv in self._headers if kv[0].lower() != name]
def __getitem__(self, name):
"""Get the first header value for 'name'
Return None if the header is missing instead of raising an exception.
Note that if the header appeared multiple times, the first exactly which
occurrence gets returned is undefined. Use getall() to get all
the values matching a header field name.
"""
return self.get(name)
def __contains__(self, name):
"""Return true if the message contains the header."""
return self.get(name) is not None
def get_all(self, name):
"""Return a list of all the values for the named field.
These will be sorted in the order they appeared in the original header
list or were added to this instance, and may contain duplicates. Any
fields deleted and re-inserted are always appended to the header list.
If no fields exist with the given name, returns an empty list.
"""
name = self._convert_string_type(name.lower())
return [kv[1] for kv in self._headers if kv[0].lower() == name]
def get(self, name, default=None):
"""Get the first header value for 'name', or return 'default'"""
name = self._convert_string_type(name.lower())
for k, v in self._headers:
if k.lower() == name:
return v
return default
def keys(self):
"""Return a list of all the header field names.
These will be sorted in the order they appeared in the original header
list, or were added to this instance, and may contain duplicates.
Any fields deleted and re-inserted are always appended to the header
list.
"""
return [k for k, v in self._headers]
def values(self):
"""Return a list of all header values.
These will be sorted in the order they appeared in the original header
list, or were added to this instance, and may contain duplicates.
Any fields deleted and re-inserted are always appended to the header
list.
"""
return [v for k, v in self._headers]
def items(self):
"""Get all the header fields and values.
These will be sorted in the order they were in the original header
list, or were added to this instance, and may contain duplicates.
Any fields deleted and re-inserted are always appended to the header
list.
"""
return self._headers[:]
def __repr__(self):
return "%s(%r)" % (self.__class__.__name__, self._headers)
def __str__(self):
"""str() returns the formatted headers, complete with end line,
suitable for direct HTTP transmission."""
return b'\r\n'.join(
[b"%s: %s" % kv for kv in self._headers] + [b'', b'']
)
def __bytes__(self):
return str(self).encode('iso-8859-1')
def setdefault(self, name, value):
"""Return first matching header value for 'name', or 'value'
If there is no header named 'name', add a new header with name 'name'
and value 'value'."""
result = self.get(name)
if result is None:
self._headers.append(
(
self._convert_string_type(name),
self._convert_string_type(value),
)
)
return value
else:
return result
def add_header(self, _name, _value, **_params):
"""Extended header setting.
_name is the header field to add. keyword arguments can be used to set
additional parameters for the header field, with underscores converted
to dashes. Normally the parameter will be added as key="value" unless
value is None, in which case only the key will be added.
Example:
h.add_header('content-disposition', 'attachment', filename='bud.gif')
Note that unlike the corresponding 'email.message' method, this does
*not* handle '(charset, language, value)' tuples: all values must be
strings or None.
"""
parts = []
if _value is not None:
_value = self._convert_string_type(_value)
parts.append(_value)
for k, v in _params.items():
k = self._convert_string_type(k)
if v is None:
parts.append(k.replace(b'_', b'-'))
else:
v = self._convert_string_type(v)
parts.append(_formatparam(k.replace(b'_', b'-'), v))
self._headers.append(
(self._convert_string_type(_name), b"; ".join(parts))
)