procutil: make stream detection in make_line_buffered more correct and strict
In make_line_buffered(), we don’t want to wrap the stream if we know that lines
get flushed to the underlying raw stream already.
Previously, the heuristic was too optimistic. It assumed that any stream which
is not an instance of io.BufferedIOBase doesn’t need wrapping. However, there
are buffered streams that aren’t instances of io.BufferedIOBase, like
Mercurial’s own winstdout.
The new logic is different in two ways:
First, only for the check, if unwraps any combination of WriteAllWrapper and
winstdout.
Second, it skips wrapping the stream only if it is an instance of io.RawIOBase
(or already wrapped). If it is an instance of io.BufferedIOBase, it gets
wrapped. In any other case, the function raises an exception. This ensures
that, if an unknown stream is passed or we add another wrapper in the future,
we don’t wrap the stream if it’s already line buffered or not wrap the stream
if it’s not line buffered. In fact, this was already helpful during development
of this change. Without it, I possibly would have forgot that WriteAllWrapper
needs to be ignored for the check, leading to unnecessary wrapping if stdout is
unbuffered.
The alternative would have been to always wrap unknown streams. However, I
don’t think that anyone would benefit from being less strict. We can expect
streams from the standard library to be subclassing either io.RawIOBase or
io.BufferedIOBase, so running Mercurial in the standard way should not regress
by this change. Py2exe might replace sys.stdout and sys.stderr, but that
currently breaks Mercurial anyway and also these streams don’t claim to be
interactive, so this function is not called for them.
"""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.
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))
)