@pairling/runtime-darwin-x64 0.1.0 → 0.2.0

package/python/lib/python3.12/urllib/response.py

@@ -0,0 +1,84 @@
+"""Response classes used by urllib.
+
+The base class, addbase, defines a minimal file-like interface,
+including read() and readline().  The typical response object is an
+addinfourl instance, which defines an info() method that returns
+headers and a geturl() method that returns the url.
+"""
+
+import tempfile
+
+__all__ = ['addbase', 'addclosehook', 'addinfo', 'addinfourl']
+
+
+class addbase(tempfile._TemporaryFileWrapper):
+    """Base class for addinfo and addclosehook. Is a good idea for garbage collection."""
+
+    # XXX Add a method to expose the timeout on the underlying socket?
+
+    def __init__(self, fp):
+        super(addbase,  self).__init__(fp, '<urllib response>', delete=False)
+        # Keep reference around as this was part of the original API.
+        self.fp = fp
+
+    def __repr__(self):
+        return '<%s at %r whose fp = %r>' % (self.__class__.__name__,
+                                             id(self), self.file)
+
+    def __enter__(self):
+        if self.fp.closed:
+            raise ValueError("I/O operation on closed file")
+        return self
+
+    def __exit__(self, type, value, traceback):
+        self.close()
+
+
+class addclosehook(addbase):
+    """Class to add a close hook to an open file."""
+
+    def __init__(self, fp, closehook, *hookargs):
+        super(addclosehook, self).__init__(fp)
+        self.closehook = closehook
+        self.hookargs = hookargs
+
+    def close(self):
+        try:
+            closehook = self.closehook
+            hookargs = self.hookargs
+            if closehook:
+                self.closehook = None
+                self.hookargs = None
+                closehook(*hookargs)
+        finally:
+            super(addclosehook, self).close()
+
+
+class addinfo(addbase):
+    """class to add an info() method to an open file."""
+
+    def __init__(self, fp, headers):
+        super(addinfo, self).__init__(fp)
+        self.headers = headers
+
+    def info(self):
+        return self.headers
+
+
+class addinfourl(addinfo):
+    """class to add info() and geturl() methods to an open file."""
+
+    def __init__(self, fp, headers, url, code=None):
+        super(addinfourl, self).__init__(fp, headers)
+        self.url = url
+        self.code = code
+
+    @property
+    def status(self):
+        return self.code
+
+    def getcode(self):
+        return self.code
+
+    def geturl(self):
+        return self.url

package/python/lib/python3.12/urllib/robotparser.py

@@ -0,0 +1,275 @@
+""" robotparser.py
+
+    Copyright (C) 2000  Bastian Kleineidam
+
+    You can choose between two licenses when using this package:
+    1) GNU GPLv2
+    2) PSF license for Python 2.2
+
+    The robots.txt Exclusion Protocol is implemented as specified in
+    http://www.robotstxt.org/norobots-rfc.txt
+"""
+
+import collections
+import urllib.error
+import urllib.parse
+import urllib.request
+
+__all__ = ["RobotFileParser"]
+
+RequestRate = collections.namedtuple("RequestRate", "requests seconds")
+
+
+class RobotFileParser:
+    """ This class provides a set of methods to read, parse and answer
+    questions about a single robots.txt file.
+
+    """
+
+    def __init__(self, url=''):
+        self.entries = []
+        self.sitemaps = []
+        self.default_entry = None
+        self.disallow_all = False
+        self.allow_all = False
+        self.set_url(url)
+        self.last_checked = 0
+
+    def mtime(self):
+        """Returns the time the robots.txt file was last fetched.
+
+        This is useful for long-running web spiders that need to
+        check for new robots.txt files periodically.
+
+        """
+        return self.last_checked
+
+    def modified(self):
+        """Sets the time the robots.txt file was last fetched to the
+        current time.
+
+        """
+        import time
+        self.last_checked = time.time()
+
+    def set_url(self, url):
+        """Sets the URL referring to a robots.txt file."""
+        self.url = url
+        self.host, self.path = urllib.parse.urlparse(url)[1:3]
+
+    def read(self):
+        """Reads the robots.txt URL and feeds it to the parser."""
+        try:
+            f = urllib.request.urlopen(self.url)
+        except urllib.error.HTTPError as err:
+            if err.code in (401, 403):
+                self.disallow_all = True
+            elif err.code >= 400 and err.code < 500:
+                self.allow_all = True
+            err.close()
+        else:
+            raw = f.read()
+            self.parse(raw.decode("utf-8").splitlines())
+
+    def _add_entry(self, entry):
+        if "*" in entry.useragents:
+            # the default entry is considered last
+            if self.default_entry is None:
+                # the first default entry wins
+                self.default_entry = entry
+        else:
+            self.entries.append(entry)
+
+    def parse(self, lines):
+        """Parse the input lines from a robots.txt file.
+
+        We allow that a user-agent: line is not preceded by
+        one or more blank lines.
+        """
+        # states:
+        #   0: start state
+        #   1: saw user-agent line
+        #   2: saw an allow or disallow line
+        state = 0
+        entry = Entry()
+
+        self.modified()
+        for line in lines:
+            if not line:
+                if state == 1:
+                    entry = Entry()
+                    state = 0
+                elif state == 2:
+                    self._add_entry(entry)
+                    entry = Entry()
+                    state = 0
+            # remove optional comment and strip line
+            i = line.find('#')
+            if i >= 0:
+                line = line[:i]
+            line = line.strip()
+            if not line:
+                continue
+            line = line.split(':', 1)
+            if len(line) == 2:
+                line[0] = line[0].strip().lower()
+                line[1] = urllib.parse.unquote(line[1].strip())
+                if line[0] == "user-agent":
+                    if state == 2:
+                        self._add_entry(entry)
+                        entry = Entry()
+                    entry.useragents.append(line[1])
+                    state = 1
+                elif line[0] == "disallow":
+                    if state != 0:
+                        entry.rulelines.append(RuleLine(line[1], False))
+                        state = 2
+                elif line[0] == "allow":
+                    if state != 0:
+                        entry.rulelines.append(RuleLine(line[1], True))
+                        state = 2
+                elif line[0] == "crawl-delay":
+                    if state != 0:
+                        # before trying to convert to int we need to make
+                        # sure that robots.txt has valid syntax otherwise
+                        # it will crash
+                        if line[1].strip().isdigit():
+                            entry.delay = int(line[1])
+                        state = 2
+                elif line[0] == "request-rate":
+                    if state != 0:
+                        numbers = line[1].split('/')
+                        # check if all values are sane
+                        if (len(numbers) == 2 and numbers[0].strip().isdigit()
+                            and numbers[1].strip().isdigit()):
+                            entry.req_rate = RequestRate(int(numbers[0]), int(numbers[1]))
+                        state = 2
+                elif line[0] == "sitemap":
+                    # According to http://www.sitemaps.org/protocol.html
+                    # "This directive is independent of the user-agent line,
+                    #  so it doesn't matter where you place it in your file."
+                    # Therefore we do not change the state of the parser.
+                    self.sitemaps.append(line[1])
+        if state == 2:
+            self._add_entry(entry)
+
+    def can_fetch(self, useragent, url):
+        """using the parsed robots.txt decide if useragent can fetch url"""
+        if self.disallow_all:
+            return False
+        if self.allow_all:
+            return True
+        # Until the robots.txt file has been read or found not
+        # to exist, we must assume that no url is allowable.
+        # This prevents false positives when a user erroneously
+        # calls can_fetch() before calling read().
+        if not self.last_checked:
+            return False
+        # search for given user agent matches
+        # the first match counts
+        parsed_url = urllib.parse.urlparse(urllib.parse.unquote(url))
+        url = urllib.parse.urlunparse(('','',parsed_url.path,
+            parsed_url.params,parsed_url.query, parsed_url.fragment))
+        url = urllib.parse.quote(url)
+        if not url:
+            url = "/"
+        for entry in self.entries:
+            if entry.applies_to(useragent):
+                return entry.allowance(url)
+        # try the default entry last
+        if self.default_entry:
+            return self.default_entry.allowance(url)
+        # agent not found ==> access granted
+        return True
+
+    def crawl_delay(self, useragent):
+        if not self.mtime():
+            return None
+        for entry in self.entries:
+            if entry.applies_to(useragent):
+                return entry.delay
+        if self.default_entry:
+            return self.default_entry.delay
+        return None
+
+    def request_rate(self, useragent):
+        if not self.mtime():
+            return None
+        for entry in self.entries:
+            if entry.applies_to(useragent):
+                return entry.req_rate
+        if self.default_entry:
+            return self.default_entry.req_rate
+        return None
+
+    def site_maps(self):
+        if not self.sitemaps:
+            return None
+        return self.sitemaps
+
+    def __str__(self):
+        entries = self.entries
+        if self.default_entry is not None:
+            entries = entries + [self.default_entry]
+        return '\n\n'.join(map(str, entries))
+
+
+class RuleLine:
+    """A rule line is a single "Allow:" (allowance==True) or "Disallow:"
+       (allowance==False) followed by a path."""
+    def __init__(self, path, allowance):
+        if path == '' and not allowance:
+            # an empty value means allow all
+            allowance = True
+        path = urllib.parse.urlunparse(urllib.parse.urlparse(path))
+        self.path = urllib.parse.quote(path)
+        self.allowance = allowance
+
+    def applies_to(self, filename):
+        return self.path == "*" or filename.startswith(self.path)
+
+    def __str__(self):
+        return ("Allow" if self.allowance else "Disallow") + ": " + self.path
+
+
+class Entry:
+    """An entry has one or more user-agents and zero or more rulelines"""
+    def __init__(self):
+        self.useragents = []
+        self.rulelines = []
+        self.delay = None
+        self.req_rate = None
+
+    def __str__(self):
+        ret = []
+        for agent in self.useragents:
+            ret.append(f"User-agent: {agent}")
+        if self.delay is not None:
+            ret.append(f"Crawl-delay: {self.delay}")
+        if self.req_rate is not None:
+            rate = self.req_rate
+            ret.append(f"Request-rate: {rate.requests}/{rate.seconds}")
+        ret.extend(map(str, self.rulelines))
+        return '\n'.join(ret)
+
+    def applies_to(self, useragent):
+        """check if this entry applies to the specified agent"""
+        # split the name token and make it lower case
+        useragent = useragent.split("/")[0].lower()
+        for agent in self.useragents:
+            if agent == '*':
+                # we have the catch-all agent
+                return True
+            agent = agent.lower()
+            if agent in useragent:
+                return True
+        return False
+
+    def allowance(self, filename):
+        """Preconditions:
+        - our agent applies to this entry
+        - filename is URL decoded"""
+        for line in self.rulelines:
+            if line.applies_to(filename):
+                return line.allowance
+        return True

package/python/lib/python3.12/uu.py

@@ -0,0 +1,216 @@
+#! /usr/bin/env python3
+
+# Copyright 1994 by Lance Ellinghouse
+# Cathedral City, California Republic, United States of America.
+#                        All Rights Reserved
+# Permission to use, copy, modify, and distribute this software and its
+# documentation for any purpose and without fee is hereby granted,
+# provided that the above copyright notice appear in all copies and that
+# both that copyright notice and this permission notice appear in
+# supporting documentation, and that the name of Lance Ellinghouse
+# not be used in advertising or publicity pertaining to distribution
+# of the software without specific, written prior permission.
+# LANCE ELLINGHOUSE DISCLAIMS ALL WARRANTIES WITH REGARD TO
+# THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+# FITNESS, IN NO EVENT SHALL LANCE ELLINGHOUSE CENTRUM BE LIABLE
+# FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
+# OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+#
+# Modified by Jack Jansen, CWI, July 1995:
+# - Use binascii module to do the actual line-by-line conversion
+#   between ascii and binary. This results in a 1000-fold speedup. The C
+#   version is still 5 times faster, though.
+# - Arguments more compliant with python standard
+
+"""Implementation of the UUencode and UUdecode functions.
+
+encode(in_file, out_file [,name, mode], *, backtick=False)
+decode(in_file [, out_file, mode, quiet])
+"""
+
+import binascii
+import os
+import sys
+import warnings
+
+warnings._deprecated(__name__, remove=(3, 13))
+
+__all__ = ["Error", "encode", "decode"]
+
+class Error(Exception):
+    pass
+
+def encode(in_file, out_file, name=None, mode=None, *, backtick=False):
+    """Uuencode file"""
+    #
+    # If in_file is a pathname open it and change defaults
+    #
+    opened_files = []
+    try:
+        if in_file == '-':
+            in_file = sys.stdin.buffer
+        elif isinstance(in_file, str):
+            if name is None:
+                name = os.path.basename(in_file)
+            if mode is None:
+                try:
+                    mode = os.stat(in_file).st_mode
+                except AttributeError:
+                    pass
+            in_file = open(in_file, 'rb')
+            opened_files.append(in_file)
+        #
+        # Open out_file if it is a pathname
+        #
+        if out_file == '-':
+            out_file = sys.stdout.buffer
+        elif isinstance(out_file, str):
+            out_file = open(out_file, 'wb')
+            opened_files.append(out_file)
+        #
+        # Set defaults for name and mode
+        #
+        if name is None:
+            name = '-'
+        if mode is None:
+            mode = 0o666
+
+        #
+        # Remove newline chars from name
+        #
+        name = name.replace('\n','\\n')
+        name = name.replace('\r','\\r')
+
+        #
+        # Write the data
+        #
+        out_file.write(('begin %o %s\n' % ((mode & 0o777), name)).encode("ascii"))
+        data = in_file.read(45)
+        while len(data) > 0:
+            out_file.write(binascii.b2a_uu(data, backtick=backtick))
+            data = in_file.read(45)
+        if backtick:
+            out_file.write(b'`\nend\n')
+        else:
+            out_file.write(b' \nend\n')
+    finally:
+        for f in opened_files:
+            f.close()
+
+
+def decode(in_file, out_file=None, mode=None, quiet=False):
+    """Decode uuencoded file"""
+    #
+    # Open the input file, if needed.
+    #
+    opened_files = []
+    if in_file == '-':
+        in_file = sys.stdin.buffer
+    elif isinstance(in_file, str):
+        in_file = open(in_file, 'rb')
+        opened_files.append(in_file)
+
+    try:
+        #
+        # Read until a begin is encountered or we've exhausted the file
+        #
+        while True:
+            hdr = in_file.readline()
+            if not hdr:
+                raise Error('No valid begin line found in input file')
+            if not hdr.startswith(b'begin'):
+                continue
+            hdrfields = hdr.split(b' ', 2)
+            if len(hdrfields) == 3 and hdrfields[0] == b'begin':
+                try:
+                    int(hdrfields[1], 8)
+                    break
+                except ValueError:
+                    pass
+        if out_file is None:
+            # If the filename isn't ASCII, what's up with that?!?
+            out_file = hdrfields[2].rstrip(b' \t\r\n\f').decode("ascii")
+            if os.path.exists(out_file):
+                raise Error(f'Cannot overwrite existing file: {out_file}')
+            if (out_file.startswith(os.sep) or
+                f'..{os.sep}' in out_file or (
+                    os.altsep and
+                    (out_file.startswith(os.altsep) or
+                     f'..{os.altsep}' in out_file))
+               ):
+                raise Error(f'Refusing to write to {out_file} due to directory traversal')
+        if mode is None:
+            mode = int(hdrfields[1], 8)
+        #
+        # Open the output file
+        #
+        if out_file == '-':
+            out_file = sys.stdout.buffer
+        elif isinstance(out_file, str):
+            fp = open(out_file, 'wb')
+            os.chmod(out_file, mode)
+            out_file = fp
+            opened_files.append(out_file)
+        #
+        # Main decoding loop
+        #
+        s = in_file.readline()
+        while s and s.strip(b' \t\r\n\f') != b'end':
+            try:
+                data = binascii.a2b_uu(s)
+            except binascii.Error as v:
+                # Workaround for broken uuencoders by /Fredrik Lundh
+                nbytes = (((s[0]-32) & 63) * 4 + 5) // 3
+                data = binascii.a2b_uu(s[:nbytes])
+                if not quiet:
+                    sys.stderr.write("Warning: %s\n" % v)
+            out_file.write(data)
+            s = in_file.readline()
+        if not s:
+            raise Error('Truncated input file')
+    finally:
+        for f in opened_files:
+            f.close()
+
+def test():
+    """uuencode/uudecode main program"""
+
+    import optparse
+    parser = optparse.OptionParser(usage='usage: %prog [-d] [-t] [input [output]]')
+    parser.add_option('-d', '--decode', dest='decode', help='Decode (instead of encode)?', default=False, action='store_true')
+    parser.add_option('-t', '--text', dest='text', help='data is text, encoded format unix-compatible text?', default=False, action='store_true')
+
+    (options, args) = parser.parse_args()
+    if len(args) > 2:
+        parser.error('incorrect number of arguments')
+        sys.exit(1)
+
+    # Use the binary streams underlying stdin/stdout
+    input = sys.stdin.buffer
+    output = sys.stdout.buffer
+    if len(args) > 0:
+        input = args[0]
+    if len(args) > 1:
+        output = args[1]
+
+    if options.decode:
+        if options.text:
+            if isinstance(output, str):
+                output = open(output, 'wb')
+            else:
+                print(sys.argv[0], ': cannot do -t to stdout')
+                sys.exit(1)
+        decode(input, output)
+    else:
+        if options.text:
+            if isinstance(input, str):
+                input = open(input, 'rb')
+            else:
+                print(sys.argv[0], ': cannot do -t from stdin')
+                sys.exit(1)
+        encode(input, output)
+
+if __name__ == '__main__':
+    test()