branch for stdlib 2.7.8

lib-python/2.7/CGIHTTPServer.py

@@ -84,7 +84,7 @@ class CGIHTTPRequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):
         path begins with one of the strings in self.cgi_directories
         (and the next character is a '/' or the end of the string).
         """
-        collapsed_path = _url_collapse_path(self.path)
+        collapsed_path = _url_collapse_path(urllib.unquote(self.path))
         dir_sep = collapsed_path.find('/', 1)
         head, tail = collapsed_path[:dir_sep], collapsed_path[dir_sep+1:]
         if head in self.cgi_directories:

lib-python/2.7/Cookie.py

-#!/usr/bin/env python
-#
-
 ####
 # Copyright 2000 by Timothy O'Malley <timo@alum.mit.edu>
 #

lib-python/2.7/HTMLParser.py

@@ -22,9 +22,12 @@ charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
 starttagopen = re.compile('<[a-zA-Z]')
 piclose = re.compile('>')
 commentclose = re.compile(r'--\s*>')
-tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*')
+
 # see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
 # and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
+# note: if you change tagfind/attrfind remember to update locatestarttagend too
+tagfind = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
+# this regex is currently unused, but left for backward compatibility
 tagfind_tolerant = re.compile('[a-zA-Z][^\t\n\r\f />\x00]*')
 
 attrfind = re.compile(
@@ -32,7 +35,7 @@ attrfind = re.compile(
     r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
 
 locatestarttagend = re.compile(r"""
-  <[a-zA-Z][-.a-zA-Z0-9:_]*          # tag name
+  <[a-zA-Z][^\t\n\r\f />\x00]*       # tag name
   (?:[\s/]*                          # optional whitespace before attribute name
     (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
       (?:\s*=+\s*                    # value indicator
@@ -192,9 +195,9 @@ class HTMLParser(markupbase.ParserBase):
                     i = self.updatepos(i, k)
                     continue
                 else:
-                    if ";" in rawdata[i:]: #bail by consuming &#
-                        self.handle_data(rawdata[0:2])
-                        i = self.updatepos(i, 2)
+                    if ";" in rawdata[i:]:  # bail by consuming '&#'
+                        self.handle_data(rawdata[i:i+2])
+                        i = self.updatepos(i, i+2)
                     break
             elif startswith('&', i):
                 match = entityref.match(rawdata, i)
@@ -373,14 +376,14 @@ class HTMLParser(markupbase.ParserBase):
                 self.handle_data(rawdata[i:gtpos])
                 return gtpos
             # find the name: w3.org/TR/html5/tokenization.html#tag-name-state
-            namematch = tagfind_tolerant.match(rawdata, i+2)
+            namematch = tagfind.match(rawdata, i+2)
             if not namematch:
                 # w3.org/TR/html5/tokenization.html#end-tag-open-state
                 if rawdata[i:i+3] == '</>':
                     return i+3
                 else:
                     return self.parse_bogus_comment(i)
-            tagname = namematch.group().lower()
+            tagname = namematch.group(1).lower()
             # consume and ignore other stuff between the name and the >
             # Note: this is not 100% correct, since we might have things like
             # </tag attr=">">, but looking for > after tha name should cover

lib-python/2.7/SimpleHTTPServer.py

@@ -43,8 +43,10 @@ class SimpleHTTPRequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):
         """Serve a GET request."""
         f = self.send_head()
         if f:
-            self.copyfile(f, self.wfile)
-            f.close()
+            try:
+                self.copyfile(f, self.wfile)
+            finally:
+                f.close()
 
     def do_HEAD(self):
         """Serve a HEAD request."""
@@ -88,13 +90,17 @@ class SimpleHTTPRequestHandler(BaseHTTPServer.BaseHTTPRequestHandler):
         except IOError:
             self.send_error(404, "File not found")
             return None
-        self.send_response(200)
-        self.send_header("Content-type", ctype)
-        fs = os.fstat(f.fileno())
-        self.send_header("Content-Length", str(fs[6]))
-        self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
-        self.end_headers()
-        return f
+        try:
+            self.send_response(200)
+            self.send_header("Content-type", ctype)
+            fs = os.fstat(f.fileno())
+            self.send_header("Content-Length", str(fs[6]))
+            self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
+            self.end_headers()
+            return f
+        except:
+            f.close()
+            raise
 
     def list_directory(self, path):
         """Helper to produce a directory listing (absent index.html).

lib-python/2.7/SimpleXMLRPCServer.py

@@ -704,4 +704,5 @@ if __name__ == '__main__':
     server = SimpleXMLRPCServer(("localhost", 8000))
     server.register_function(pow)
     server.register_function(lambda x,y: x+y, 'add')
+    server.register_multicall_functions()
     server.serve_forever()

lib-python/2.7/SocketServer.py

@@ -513,35 +513,37 @@ class ForkingMixIn:
 
     def collect_children(self):
         """Internal routine to wait for children that have exited."""
-        if self.active_children is None: return
+        if self.active_children is None:
+            return
+
+        # If we're above the max number of children, wait and reap them until
+        # we go back below threshold. Note that we use waitpid(-1) below to be
+        # able to collect children in size(<defunct children>) syscalls instead
+        # of size(<children>): the downside is that this might reap children
+        # which we didn't spawn, which is why we only resort to this when we're
+        # above max_children.
         while len(self.active_children) >= self.max_children:
-            # XXX: This will wait for any child process, not just ones
-            # spawned by this library. This could confuse other
-            # libraries that expect to be able to wait for their own
-            # children.
-            try:
-                pid, status = os.waitpid(0, 0)
-            except os.error:
-                pid = None
-            if pid not in self.active_children: continue
-            self.active_children.remove(pid)
-
-        # XXX: This loop runs more system calls than it ought
-        # to. There should be a way to put the active_children into a
-        # process group and then use os.waitpid(-pgid) to wait for any
-        # of that set, but I couldn't find a way to allocate pgids
-        # that couldn't collide.
-        for child in self.active_children:
             try:
-                pid, status = os.waitpid(child, os.WNOHANG)
-            except os.error:
-                pid = None
-            if not pid: continue
+                pid, _ = os.waitpid(-1, 0)
+                self.active_children.discard(pid)
+            except OSError as e:
+                if e.errno == errno.ECHILD:
+                    # we don't have any children, we're done
+                    self.active_children.clear()
+                elif e.errno != errno.EINTR:
+                    break
+
+        # Now reap all defunct children.
+        for pid in self.active_children.copy():
             try:
-                self.active_children.remove(pid)
-            except ValueError, e:
-                raise ValueError('%s. x=%d and list=%r' % (e.message, pid,
-                                                           self.active_children))
+                pid, _ = os.waitpid(pid, os.WNOHANG)
+                # if the child hasn't exited yet, pid will be 0 and ignored by
+                # discard() below
+                self.active_children.discard(pid)
+            except OSError as e:
+                if e.errno == errno.ECHILD:
+                    # someone else reaped it
+                    self.active_children.discard(pid)
 
     def handle_timeout(self):
         """Wait for zombies after self.timeout seconds of inactivity.
@@ -557,8 +559,8 @@ class ForkingMixIn:
         if pid:
             # Parent process
             if self.active_children is None:
-                self.active_children = []
-            self.active_children.append(pid)
+                self.active_children = set()
+            self.active_children.add(pid)
             self.close_request(request) #close handle in parent process
             return
         else:

lib-python/2.7/_MozillaCookieJar.py

@@ -39,7 +39,7 @@ class MozillaCookieJar(FileCookieJar):
     magic_re = "#( Netscape)? HTTP Cookie File"
     header = """\
 # Netscape HTTP Cookie File
-# http://www.netscape.com/newsref/std/cookie_spec.html
+# http://curl.haxx.se/rfc/cookie_spec.html
 # This is a generated file!  Do not edit.
 
 """

lib-python/2.7/_abcoll.py

@@ -165,12 +165,17 @@ class Set(Sized, Iterable, Container):
     def __gt__(self, other):
         if not isinstance(other, Set):
             return NotImplemented
-        return other < self
+        return len(self) > len(other) and self.__ge__(other)
 
     def __ge__(self, other):
         if not isinstance(other, Set):
             return NotImplemented
-        return other <= self
+        if len(self) < len(other):
+            return False
+        for elem in other:
+            if elem not in self:
+                return False
+        return True
 
     def __eq__(self, other):
         if not isinstance(other, Set):
@@ -194,6 +199,8 @@ class Set(Sized, Iterable, Container):
             return NotImplemented
         return self._from_iterable(value for value in other if value in self)
 
+    __rand__ = __and__
+
     def isdisjoint(self, other):
         'Return True if two sets have a null intersection.'
         for value in other:
@@ -207,6 +214,8 @@ class Set(Sized, Iterable, Container):
         chain = (e for s in (self, other) for e in s)
         return self._from_iterable(chain)
 
+    __ror__ = __or__
+
     def __sub__(self, other):
         if not isinstance(other, Set):
             if not isinstance(other, Iterable):
@@ -215,6 +224,14 @@ class Set(Sized, Iterable, Container):
         return self._from_iterable(value for value in self
                                    if value not in other)
 
+    def __rsub__(self, other):
+        if not isinstance(other, Set):
+            if not isinstance(other, Iterable):
+                return NotImplemented
+            other = self._from_iterable(other)
+        return self._from_iterable(value for value in other
+                                   if value not in self)
+
     def __xor__(self, other):
         if not isinstance(other, Set):
             if not isinstance(other, Iterable):
@@ -222,6 +239,8 @@ class Set(Sized, Iterable, Container):
             other = self._from_iterable(other)
         return (self - other) | (other - self)
 
+    __rxor__ = __xor__
+
     # Sets are not hashable by default, but subclasses can change this
     __hash__ = None
 

lib-python/2.7/_osx_support.py

@@ -182,7 +182,7 @@ def _find_appropriate_compiler(_config_vars):
         # Compiler is GCC, check if it is LLVM-GCC
         data = _read_output("'%s' --version"
                              % (cc.replace("'", "'\"'\"'"),))
-        if 'llvm-gcc' in data:
+        if data and 'llvm-gcc' in data:
             # Found LLVM-GCC, fall back to clang
             cc = _find_build_tool('clang')
 
@@ -450,8 +450,16 @@ def get_platform_osx(_config_vars, osname, release, machine):
         # case and disallow installs.
         cflags = _config_vars.get(_INITPRE+'CFLAGS',
                                     _config_vars.get('CFLAGS', ''))
-        if ((macrelease + '.') >= '10.4.' and
-            '-arch' in cflags.strip()):
+        if macrelease:
+            try:
+                macrelease = tuple(int(i) for i in macrelease.split('.')[0:2])
+            except ValueError:
+                macrelease = (10, 0)
+        else:
+            # assume no universal support
+            macrelease = (10, 0)
+
+        if (macrelease >= (10, 4)) and '-arch' in cflags.strip():
             # The universal build will build fat binaries, but not on
             # systems before 10.4
 

lib-python/2.7/_pyio.py

@@ -192,38 +192,45 @@ def open(file, mode="r", buffering=-1,
                  (appending and "a" or "") +
                  (updating and "+" or ""),
                  closefd)
-    line_buffering = False
-    if buffering == 1 or buffering < 0 and raw.isatty():
-        buffering = -1
-        line_buffering = True
-    if buffering < 0:
-        buffering = DEFAULT_BUFFER_SIZE
-        try:
-            bs = os.fstat(raw.fileno()).st_blksize
-        except (os.error, AttributeError):
-            pass
+    result = raw
+    try:
+        line_buffering = False
+        if buffering == 1 or buffering < 0 and raw.isatty():
+            buffering = -1
+            line_buffering = True
+        if buffering < 0:
+            buffering = DEFAULT_BUFFER_SIZE
+            try:
+                bs = os.fstat(raw.fileno()).st_blksize
+            except (os.error, AttributeError):
+                pass
+            else:
+                if bs > 1:
+                    buffering = bs
+        if buffering < 0:
+            raise ValueError("invalid buffering size")
+        if buffering == 0:
+            if binary:
+                return result
+            raise ValueError("can't have unbuffered text I/O")
+        if updating:
+            buffer = BufferedRandom(raw, buffering)
+        elif writing or appending:
+            buffer = BufferedWriter(raw, buffering)
+        elif reading:
+            buffer = BufferedReader(raw, buffering)
         else:
-            if bs > 1:
-                buffering = bs
-    if buffering < 0:
-        raise ValueError("invalid buffering size")
-    if buffering == 0:
+            raise ValueError("unknown mode: %r" % mode)
+        result = buffer
         if binary:
-            return raw
-        raise ValueError("can't have unbuffered text I/O")
-    if updating:
-        buffer = BufferedRandom(raw, buffering)
-    elif writing or appending:
-        buffer = BufferedWriter(raw, buffering)
-    elif reading:
-        buffer = BufferedReader(raw, buffering)
-    else:
-        raise ValueError("unknown mode: %r" % mode)
-    if binary:
-        return buffer
-    text = TextIOWrapper(buffer, encoding, errors, newline, line_buffering)
-    text.mode = mode
-    return text
+            return result
+        text = TextIOWrapper(buffer, encoding, errors, newline, line_buffering)
+        result = text
+        text.mode = mode
+        return result
+    except:
+        result.close()
+        raise
 
 
 class DocDescriptor:
@@ -1997,7 +2004,13 @@ class StringIO(TextIOWrapper):
 
     def getvalue(self):
         self.flush()
-        return self.buffer.getvalue().decode(self._encoding, self._errors)
+        decoder = self._decoder or self._get_decoder()
+        old_state = decoder.getstate()
+        decoder.reset()
+        try:
+            return decoder.decode(self.buffer.getvalue(), final=True)
+        finally:
+            decoder.setstate(old_state)
 
     def __repr__(self):
         # TextIOWrapper tells the encoding in its repr. In StringIO,

lib-python/2.7/_weakrefset.py

@@ -60,6 +60,8 @@ class WeakSet(object):
             for itemref in self.data:
                 item = itemref()
                 if item is not None:
+                    # Caveat: the iterator will keep a strong reference to
+                    # `item` until it is resumed or closed.
                     yield item
 
     def __len__(self):

lib-python/2.7/aifc.py

@@ -778,7 +778,7 @@ class Aifc_write:
 
     def _ensure_header_written(self, datasize):
         if not self._nframeswritten:
-            if self._comptype in ('ULAW', 'ALAW'):
+            if self._comptype in ('ULAW', 'ulaw', 'ALAW', 'alaw'):
                 if not self._sampwidth:
                     self._sampwidth = 2
                 if self._sampwidth != 2:
@@ -844,7 +844,7 @@ class Aifc_write:
         if self._datalength & 1:
             self._datalength = self._datalength + 1
         if self._aifc:
-            if self._comptype in ('ULAW', 'ALAW'):
+            if self._comptype in ('ULAW', 'ulaw', 'ALAW', 'alaw'):
                 self._datalength = self._datalength // 2
                 if self._datalength & 1:
                     self._datalength = self._datalength + 1
@@ -852,7 +852,10 @@ class Aifc_write:
                 self._datalength = (self._datalength + 3) // 4
                 if self._datalength & 1:
                     self._datalength = self._datalength + 1
-        self._form_length_pos = self._file.tell()
+        try:
+            self._form_length_pos = self._file.tell()
+        except (AttributeError, IOError):
+            self._form_length_pos = None
         commlength = self._write_form_length(self._datalength)
         if self._aifc:
             self._file.write('AIFC')
@@ -864,7 +867,8 @@ class Aifc_write:
         self._file.write('COMM')
         _write_ulong(self._file, commlength)
         _write_short(self._file, self._nchannels)
-        self._nframes_pos = self._file.tell()
+        if self._form_length_pos is not None:
+            self._nframes_pos = self._file.tell()
         _write_ulong(self._file, self._nframes)
         if self._comptype in ('ULAW', 'ulaw', 'ALAW', 'alaw', 'G722'):
             _write_short(self._file, 8)
@@ -875,7 +879,8 @@ class Aifc_write:
             self._file.write(self._comptype)
             _write_string(self._file, self._compname)
         self._file.write('SSND')
-        self._ssnd_length_pos = self._file.tell()
+        if self._form_length_pos is not None:
+            self._ssnd_length_pos = self._file.tell()
         _write_ulong(self._file, self._datalength + 8)
         _write_ulong(self._file, 0)
         _write_ulong(self._file, 0)

lib-python/2.7/argparse.py

@@ -168,6 +168,8 @@ class HelpFormatter(object):
         self._prog = prog
         self._indent_increment = indent_increment
         self._max_help_position = max_help_position
+        self._max_help_position = min(max_help_position,
+                                      max(width - 20, indent_increment * 2))
         self._width = width
 
         self._current_indent = 0
@@ -339,7 +341,7 @@ class HelpFormatter(object):
                     else:
                         line_len = len(indent) - 1
                     for part in parts:
-                        if line_len + 1 + len(part) > text_width:
+                        if line_len + 1 + len(part) > text_width and line:
                             lines.append(indent + ' '.join(line))
                             line = []
                             line_len = len(indent) - 1
@@ -478,7 +480,7 @@ class HelpFormatter(object):
     def _format_text(self, text):
         if '%(prog)' in text:
             text = text % dict(prog=self._prog)
-        text_width = self._width - self._current_indent
+        text_width = max(self._width - self._current_indent, 11)
         indent = ' ' * self._current_indent
         return self._fill_text(text, text_width, indent) + '\n\n'
 
@@ -486,7 +488,7 @@ class HelpFormatter(object):
         # determine the required width and the entry label
         help_position = min(self._action_max_length + 2,
                             self._max_help_position)
-        help_width = self._width - help_position
+        help_width = max(self._width - help_position, 11)
         action_width = help_position - self._current_indent - 2
         action_header = self._format_action_invocation(action)
 
@@ -1155,9 +1157,13 @@ class Namespace(_AttributeHolder):
     __hash__ = None
 
     def __eq__(self, other):
+        if not isinstance(other, Namespace):
+            return NotImplemented
         return vars(self) == vars(other)
 
     def __ne__(self, other):
+        if not isinstance(other, Namespace):
+            return NotImplemented
         return not (self == other)
 
     def __contains__(self, key):

lib-python/2.7/bsddb/dbshelve.py

-#!/usr/bin/env python
 #------------------------------------------------------------------------
 #           Copyright (c) 1997-2001 by Total Control Software
 #                         All Rights Reserved

lib-python/2.7/bsddb/test/test_dbtables.py

-#!/usr/bin/env python
-#
 #-----------------------------------------------------------------------
 # A test suite for the table interface built on bsddb.db
 #-----------------------------------------------------------------------

lib-python/2.7/codecs.py

@@ -456,16 +456,13 @@ class StreamReader(Codec):
 
         # read until we get the required number of characters (if available)
         while True:
-            # can the request can be satisfied from the character buffer?
-            if chars < 0:
-                if size < 0:
-                    if self.charbuffer:
-                        break
-                elif len(self.charbuffer) >= size:
-                    break
-            else:
+            # can the request be satisfied from the character buffer?