add perl5 support to Vx6.9 for openssl-3.1.7 (#1)

Reviewed-on: http://13.234.246.121:3000/Neominds/ossl35vx69/pulls/1
Reviewed-by: Jayesh Babu <jayesh@neominds.in>
Co-authored-by: siddhant <siddhant.singh@neominds.in>
Co-committed-by: siddhant <siddhant.singh@neominds.in>

vxworks-6.9/host/msys2-x86-win64/usr/lib/python3.9/urllib/error.py

@@ -0,0 +1,77 @@
+"""Exception classes raised by urllib.
+
+The base exception class is URLError, which inherits from OSError.  It
+doesn't define any behavior of its own, but is the base class for all
+exceptions defined in this package.
+
+HTTPError is an exception class that is also a valid HTTP response
+instance.  It behaves this way because HTTP protocol errors are valid
+responses, with a status code, headers, and a body.  In some contexts,
+an application may want to handle an exception like a regular
+response.
+"""
+
+import urllib.response
+
+__all__ = ['URLError', 'HTTPError', 'ContentTooShortError']
+
+
+class URLError(OSError):
+    # URLError is a sub-type of OSError, but it doesn't share any of
+    # the implementation.  need to override __init__ and __str__.
+    # It sets self.args for compatibility with other OSError
+    # subclasses, but args doesn't have the typical format with errno in
+    # slot 0 and strerror in slot 1.  This may be better than nothing.
+    def __init__(self, reason, filename=None):
+        self.args = reason,
+        self.reason = reason
+        if filename is not None:
+            self.filename = filename
+
+    def __str__(self):
+        return '<urlopen error %s>' % self.reason
+
+
+class HTTPError(URLError, urllib.response.addinfourl):
+    """Raised when HTTP error occurs, but also acts like non-error return"""
+    __super_init = urllib.response.addinfourl.__init__
+
+    def __init__(self, url, code, msg, hdrs, fp):
+        self.code = code
+        self.msg = msg
+        self.hdrs = hdrs
+        self.fp = fp
+        self.filename = url
+        # The addinfourl classes depend on fp being a valid file
+        # object.  In some cases, the HTTPError may not have a valid
+        # file object.  If this happens, the simplest workaround is to
+        # not initialize the base classes.
+        if fp is not None:
+            self.__super_init(fp, hdrs, url, code)
+
+    def __str__(self):
+        return 'HTTP Error %s: %s' % (self.code, self.msg)
+
+    def __repr__(self):
+        return '<HTTPError %s: %r>' % (self.code, self.msg)
+
+    # since URLError specifies a .reason attribute, HTTPError should also
+    #  provide this attribute. See issue13211 for discussion.
+    @property
+    def reason(self):
+        return self.msg
+
+    @property
+    def headers(self):
+        return self.hdrs
+
+    @headers.setter
+    def headers(self, headers):
+        self.hdrs = headers
+
+
+class ContentTooShortError(URLError):
+    """Exception raised when downloaded size does not match content-length."""
+    def __init__(self, message, content):
+        URLError.__init__(self, message)
+        self.content = content

vxworks-6.9/host/msys2-x86-win64/usr/lib/python3.9/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

vxworks-6.9/host/msys2-x86-win64/usr/lib/python3.9/urllib/robotparser.py

@@ -0,0 +1,273 @@
+""" 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.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
+        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