From d5fed9641e2473048222f37402c903236fe0fc0d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Juhani=20Krekel=C3=A4?= Date: Sat, 3 Apr 2021 01:43:04 +0300 Subject: [PATCH] First commit --- CC0 | 116 ++++++++++++++++++++++++++++ README.md | 11 +++ example.pheeder | 2 + pheeder.py | 201 ++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 330 insertions(+) create mode 100644 CC0 create mode 100644 README.md create mode 100644 example.pheeder create mode 100644 pheeder.py diff --git a/CC0 b/CC0 new file mode 100644 index 0000000..670154e --- /dev/null +++ b/CC0 @@ -0,0 +1,116 @@ +CC0 1.0 Universal + +Statement of Purpose + +The laws of most jurisdictions throughout the world automatically confer +exclusive Copyright and Related Rights (defined below) upon the creator and +subsequent owner(s) (each and all, an "owner") of an original work of +authorship and/or a database (each, a "Work"). + +Certain owners wish to permanently relinquish those rights to a Work for the +purpose of contributing to a commons of creative, cultural and scientific +works ("Commons") that the public can reliably and without fear of later +claims of infringement build upon, modify, incorporate in other works, reuse +and redistribute as freely as possible in any form whatsoever and for any +purposes, including without limitation commercial purposes. These owners may +contribute to the Commons to promote the ideal of a free culture and the +further production of creative, cultural and scientific works, or to gain +reputation or greater distribution for their Work in part through the use and +efforts of others. + +For these and/or other purposes and motivations, and without any expectation +of additional consideration or compensation, the person associating CC0 with a +Work (the "Affirmer"), to the extent that he or she is an owner of Copyright +and Related Rights in the Work, voluntarily elects to apply CC0 to the Work +and publicly distribute the Work under its terms, with knowledge of his or her +Copyright and Related Rights in the Work and the meaning and intended legal +effect of CC0 on those rights. + +1. Copyright and Related Rights. A Work made available under CC0 may be +protected by copyright and related or neighboring rights ("Copyright and +Related Rights"). Copyright and Related Rights include, but are not limited +to, the following: + + i. the right to reproduce, adapt, distribute, perform, display, communicate, + and translate a Work; + + ii. moral rights retained by the original author(s) and/or performer(s); + + iii. publicity and privacy rights pertaining to a person's image or likeness + depicted in a Work; + + iv. rights protecting against unfair competition in regards to a Work, + subject to the limitations in paragraph 4(a), below; + + v. rights protecting the extraction, dissemination, use and reuse of data in + a Work; + + vi. database rights (such as those arising under Directive 96/9/EC of the + European Parliament and of the Council of 11 March 1996 on the legal + protection of databases, and under any national implementation thereof, + including any amended or successor version of such directive); and + + vii. other similar, equivalent or corresponding rights throughout the world + based on applicable law or treaty, and any national implementations thereof. + +2. Waiver. To the greatest extent permitted by, but not in contravention of, +applicable law, Affirmer hereby overtly, fully, permanently, irrevocably and +unconditionally waives, abandons, and surrenders all of Affirmer's Copyright +and Related Rights and associated claims and causes of action, whether now +known or unknown (including existing as well as future claims and causes of +action), in the Work (i) in all territories worldwide, (ii) for the maximum +duration provided by applicable law or treaty (including future time +extensions), (iii) in any current or future medium and for any number of +copies, and (iv) for any purpose whatsoever, including without limitation +commercial, advertising or promotional purposes (the "Waiver"). Affirmer makes +the Waiver for the benefit of each member of the public at large and to the +detriment of Affirmer's heirs and successors, fully intending that such Waiver +shall not be subject to revocation, rescission, cancellation, termination, or +any other legal or equitable action to disrupt the quiet enjoyment of the Work +by the public as contemplated by Affirmer's express Statement of Purpose. + +3. Public License Fallback. Should any part of the Waiver for any reason be +judged legally invalid or ineffective under applicable law, then the Waiver +shall be preserved to the maximum extent permitted taking into account +Affirmer's express Statement of Purpose. In addition, to the extent the Waiver +is so judged Affirmer hereby grants to each affected person a royalty-free, +non transferable, non sublicensable, non exclusive, irrevocable and +unconditional license to exercise Affirmer's Copyright and Related Rights in +the Work (i) in all territories worldwide, (ii) for the maximum duration +provided by applicable law or treaty (including future time extensions), (iii) +in any current or future medium and for any number of copies, and (iv) for any +purpose whatsoever, including without limitation commercial, advertising or +promotional purposes (the "License"). The License shall be deemed effective as +of the date CC0 was applied by Affirmer to the Work. Should any part of the +License for any reason be judged legally invalid or ineffective under +applicable law, such partial invalidity or ineffectiveness shall not +invalidate the remainder of the License, and in such case Affirmer hereby +affirms that he or she will not (i) exercise any of his or her remaining +Copyright and Related Rights in the Work or (ii) assert any associated claims +and causes of action with respect to the Work, in either case contrary to +Affirmer's express Statement of Purpose. + +4. Limitations and Disclaimers. + + a. No trademark or patent rights held by Affirmer are waived, abandoned, + surrendered, licensed or otherwise affected by this document. + + b. Affirmer offers the Work as-is and makes no representations or warranties + of any kind concerning the Work, express, implied, statutory or otherwise, + including without limitation warranties of title, merchantability, fitness + for a particular purpose, non infringement, or the absence of latent or + other defects, accuracy, or the present or absence of errors, whether or not + discoverable, all to the greatest extent permissible under applicable law. + + c. Affirmer disclaims responsibility for clearing rights of other persons + that may apply to the Work or any use thereof, including without limitation + any person's Copyright and Related Rights in the Work. Further, Affirmer + disclaims responsibility for obtaining any necessary consents, permissions + or other rights required for any use of the Work. + + d. Affirmer understands and acknowledges that Creative Commons is not a + party to this document and has no duty or obligation with respect to this + CC0 or use of the Work. + +For more information, please see + diff --git a/README.md b/README.md new file mode 100644 index 0000000..c577042 --- /dev/null +++ b/README.md @@ -0,0 +1,11 @@ +Pheeder +======= + +Pheeder is a proxy for translating gophermaps into RSS. The allowed gopher +URLs are defined in feedfiles (see e.g. example.pheeder), and accessible +with a short name. + +Running +======= + +`python3 pheeder.py port /path/to/feeds.pheeder` diff --git a/example.pheeder b/example.pheeder new file mode 100644 index 0000000..079dbe1 --- /dev/null +++ b/example.pheeder @@ -0,0 +1,2 @@ +shatranj gopher://ahti.space/1/~nortti/shatranj +floodfeeds gopher://gopher.floodgap.com/1/feeds/today diff --git a/pheeder.py b/pheeder.py new file mode 100644 index 0000000..ce92201 --- /dev/null +++ b/pheeder.py @@ -0,0 +1,201 @@ +#!/usr/bin/env python3 +import http.server +import socket +import sys +import urllib.parse +import xml.sax.saxutils +from collections import namedtuple + +feeds = {} + +def download_gophermap(feedurl): + split = urllib.parse.urlsplit(feedurl) + + if split.scheme != 'gopher': raise ValueError(f'Must be a gopher url, {feedurl} is not') + + host = split.hostname + port = split.port if split.port != None else 70 + + itemtype = '1' # Gophermap by default + query = None + if split.query != '': + query = urllib.parse.unquote(split.query) + if '\n' in query or '\r' in query: raise ValueError(f'Newlines not allowed in the query') + itemtype = '8' # Search has its own itemtype + + if split.path.lstrip('/') == '': + # Special handling if the url doesn't include the path part + path = '' + elif split.path.lstrip('/')[0] != itemtype: + # If the url specifies something else than a gophermap, or search if we have a search query, explode + raise ValueError(f'Must be a gophermap or search, {feedurl} is not') + else: + path = urllib.parse.unquote(split.path.lstrip('/')[1:]) + if '\n' in path or '\r' in path or '\t' in path: raise ValueError(f'Newlines or tabs not allowed in the path') + + with socket.create_connection((host, port)) as sock: + if query is None: + sock.sendall(path.encode('utf-8') + b'\r\n') + else: + sock.sendall(path.encode('utf-8') + b'\t' + query.encode('utf-8') + b'\r\n') + + lines = [] + buf = bytearray() + stream_end = False + while not stream_end: + data = sock.recv(1024) + if data == b'': break + + buf.extend(data) + + while True: + newline_index = buf.find(b'\n') + if newline_index == -1: break + + line = buf[:newline_index] + buf = buf[newline_index + 1:] + if line[-1:] == b'\r': line = line[:-1] + + if line == b'.': + # End of gophermap reached. Stop parsing here + stream_end = True + break + elif line[:1] == b'.': + # Dot unquoting + line = line[1:] + + lines.append(line) + + return lines + +def construct_url(itemtype, path, host, port): + if path.lstrip(b'/').startswith(b'URL:'): + # hURL + # Copy the URL (after sanitizing) directly + url = path.lstrip(b'/')[4:].decode('utf-8') + return url + + host = host.decode('utf-8').encode('idna').decode() + path = urllib.parse.quote(itemtype + path) + + if port == 70: + # No need to add the port explicitly + netloc = host + else: + # Do we have an IPv6 address that needs to be put in brackets? + if ':' in host: + netloc = f'[{host}]:port' + else: + netloc = f'{host}:{port}' + + return urllib.parse.urlunsplit(('gopher', netloc, path, '', '')) + +def get_links(gophermap): + links = [] + for line in gophermap: + line = line.split(b'\t') + if len(line) < 4: + continue + + itemtype_name, path, host, port, *_ = line + + itemtype = itemtype_name[:1] + name = itemtype_name[1:].decode('utf-8', errors='replace') + if itemtype == b'3': raise Exception(f'From gopher: {name}') + if itemtype == b'i': continue # Don't care about info text + + port = int(port) + + url = construct_url(itemtype, path, host, port) + links.append((name, url)) + + return links + +def construct_rss(links, feed): + rss = [f""" + + + {xml.sax.saxutils.escape(feed)} (pheeder) + {xml.sax.saxutils.escape(feeds[feed])} + +"""] + for text, url in links: + rss.append(f"""\t\t + {xml.sax.saxutils.escape(text)} + {xml.sax.saxutils.escape(url)} + """) + + rss.append('\t\n\n') + + return '\n'.join(rss) + +class Pheeder(http.server.BaseHTTPRequestHandler): + def send_404(self): + content = f'{self.path} not found'.encode('utf-8') + + self.send_response(404) + self.send_header('Content-Type', 'text/plain; charset=utf-8') + self.send_header('Content-Length', len(content)) + self.end_headers() + + self.wfile.write(content) + + def send_500(self): + content =f'Internal server error while processing {self.path}'.encode('utf-8') + + self.send_response(500) + self.send_header('Content-Type', 'text/plain; charset=utf-8') + self.send_header('Content-Length', len(content)) + self.end_headers() + + self.wfile.write(content) + + def send_rss(self, rss): + rss = rss.encode('utf-8') + + self.send_response(200) + self.send_header('Content-Type', 'application/rss+xml; charset=utf-8') + self.send_header('Content-Length', len(rss)) + self.end_headers() + + self.wfile.write(rss) + + def do_GET(self): + feed = self.path.strip('/').split('/')[-1] + + if feed in feeds: + try: + gophermap = download_gophermap(feeds[feed]) + links = get_links(gophermap) + rss = construct_rss(links, feed) + except: + self.send_500() + else: + self.send_rss(rss) + else: + self.send_404() + +def load_feedfile(feedfile): + global feeds + + with open(feedfile, 'r') as f: + for line in f: + line = line.strip() + + comment_start = line.find('#') + if comment_start != -1: + line = line[:comment_start] + + feed, url = line.split(' ', 2) + + feeds[feed] = url + +if __name__ == '__main__': + if len(sys.argv) < 3: + print(f'Usage: {sys.argv[0]} port feedfile [feedfile …]', file=sys.stderr) + sys.exit(1) + + for feedfile in sys.argv[2:]: + load_feedfile(feedfile) + + http.server.HTTPServer(('', int(sys.argv[1])), Pheeder).serve_forever()