morss: code spacing

One of those commits that make me feel useful

morss/morss.py

@@ -18,6 +18,7 @@ from . import readabilite
 
 import wsgiref.simple_server
 import wsgiref.handlers
+import cgitb
 
 
 try:
@@ -44,7 +45,7 @@ THREADS = 10  # number of threads (1 for single-threaded)
 DEBUG = False
 PORT = 8080
 
-PROTOCOL = ['http', 'https', 'ftp']
+PROTOCOL = ['http', 'https']
 
 
 def filterOptions(options):
@@ -66,6 +67,7 @@ def log(txt, force=False):
     if DEBUG or force:
         if 'REQUEST_URI' in os.environ:
             open('morss.log', 'a').write("%s\n" % repr(txt))
+
         else:
             print(repr(txt))
 
@@ -73,6 +75,7 @@ def log(txt, force=False):
 def len_html(txt):
     if len(txt):
         return len(lxml.html.fromstring(txt).text_content())
+
     else:
         return 0
 
@@ -80,6 +83,7 @@ def len_html(txt):
 def count_words(txt):
     if len(txt):
         return len(lxml.html.fromstring(txt).text_content().split())
+
     return 0
 
 
@@ -88,12 +92,14 @@ class Options:
         if len(args):
             self.options = args
             self.options.update(options or {})
+
         else:
             self.options = options or {}
 
     def __getattr__(self, key):
         if key in self.options:
             return self.options[key]
+
         else:
             return False
 
@@ -107,17 +113,23 @@ class Options:
 def parseOptions(options):
     """ Turns ['md=True'] into {'md':True} """
     out = {}
+
     for option in options:
         split = option.split('=', 1)
+
         if len(split) > 1:
             if split[0].lower() == 'true':
                 out[split[0]] = True
+
             elif split[0].lower() == 'false':
                 out[split[0]] = False
+
             else:
                 out[split[0]] = split[1]
+
         else:
             out[split[0]] = True
+
     return out
 
 
@@ -208,6 +220,7 @@ def ItemFill(item, options, feedurl='/', fast=False):
         if len(match):
             link = match[0]
             log(link)
+
         else:
             link = None
 
@@ -217,6 +230,7 @@ def ItemFill(item, options, feedurl='/', fast=False):
         if len(match) and urlparse(match[0]).netloc != 'www.facebook.com':
             link = match[0]
             log(link)
+
         else:
             link = None
 
@@ -299,6 +313,7 @@ def UrlFix(url):
 
     return url
 
+
 def FeedFetch(url, options):
     # allow for code execution for feedify
     pre = feedify.pre_worker(url)
@@ -327,7 +342,6 @@ def FeedFetch(url, options):
     if options.items:
         # using custom rules
         rss = feeds.FeedHTML(xml)
-        feed.rule
 
         rss.rules['items'] = options.items
 
@@ -340,6 +354,8 @@ def FeedFetch(url, options):
         if options.item_time:
             rss.rules['item_time'] = options.item_time
 
+        rss = rss.convert(feeds.FeedXML)
+
     else:
         try:
             rss = feeds.parse(xml, url, contenttype)
@@ -377,6 +393,7 @@ def FeedGather(rss, url, options):
             value = queue.get()
             try:
                 worker(*value)
+
             except Exception as e:
                 log('Thread Error: %s' % e.message)
             queue.task_done()
@@ -416,6 +433,7 @@ def FeedGather(rss, url, options):
     for i, item in enumerate(list(rss.items)):
         if threads == 1:
             worker(*[i, item])
+
         else:
             queue.put([i, item])
 
@@ -435,37 +453,38 @@ def FeedGather(rss, url, options):
     return rss
 
 
-def FeedFormat(rss, options):
+def FeedFormat(rss, options, encoding='utf-8'):
     if options.callback:
         if re.match(r'^[a-zA-Z0-9\.]+$', options.callback) is not None:
-            return '%s(%s)' % (options.callback, rss.tojson())
+            out = '%s(%s)' % (options.callback, rss.tojson(encoding='unicode'))
+            return out if encoding == 'unicode' else out.encode(encoding)
 
         else:
             raise MorssException('Invalid callback var name')
 
     elif options.json:
         if options.indent:
-            return rss.tojson(encoding='UTF-8', indent=4)
+            return rss.tojson(encoding=encoding, indent=4)
 
         else:
-            return rss.tojson(encoding='UTF-8')
+            return rss.tojson(encoding=encoding)
 
     elif options.csv:
-        return rss.tocsv(encoding='UTF-8')
+        return rss.tocsv(encoding=encoding)
 
     elif options.reader:
         if options.indent:
-            return rss.tohtml(encoding='UTF-8', pretty_print=True)
+            return rss.tohtml(encoding=encoding, pretty_print=True)
 
         else:
-            return rss.tohtml(encoding='UTF-8')
+            return rss.tohtml(encoding=encoding)
 
     else:
         if options.indent:
-            return rss.torss(xml_declaration=True, encoding='UTF-8', pretty_print=True)
+            return rss.torss(xml_declaration=True, encoding=encoding, pretty_print=True)
 
         else:
-            return rss.torss(xml_declaration=True, encoding='UTF-8')
+            return rss.torss(xml_declaration=True, encoding=encoding)
 
 
 def process(url, cache=None, options=None):
@@ -499,7 +518,7 @@ def cgi_app(environ, start_response):
     if url.startswith(':'):
         split = url.split('/', 1)
 
-        options = split[0].replace('|', '/').replace('\\\'', '\'').split(':')[1:]
+        raw_options = split[0].replace('|', '/').replace('\\\'', '\'').split(':')[1:]
 
         if len(split) > 1:
             url = split[1]
@@ -507,10 +526,10 @@ def cgi_app(environ, start_response):
             url = ''
 
     else:
-        options = []
+        raw_options = []
 
     # init
-    options = Options(filterOptions(parseOptions(options)))
+    options = Options(filterOptions(parseOptions(raw_options)))
     headers = {}
 
     global DEBUG
@@ -551,18 +570,42 @@ def cgi_app(environ, start_response):
     rss = FeedGather(rss, url, options)
     out = FeedFormat(rss, options)
 
-    if not options.silent:
-        return out
+    if options.silent:
+        return ['']
+
+    else:
+        return [out]
 
 
-def cgi_wrapper(environ, start_response):
-    # simple http server for html and css
+def middleware(func):
+    " Decorator to turn a function into a wsgi middleware "
+    # This is called when parsing the code
+
+    def app_builder(app):
+        # This is called when doing app = cgi_wrapper(app)
+
+        def app_wrap(environ, start_response):
+            # This is called when a http request is being processed
+
+            return func(environ, start_response, app)
+
+        return app_wrap
+
+    return app_builder
+
+
+@middleware
+def cgi_file_handler(environ, start_response, app):
+    " Simple HTTP server to serve static files (.html, .css, etc.) "
+
     files = {
         '': 'text/html',
-        'index.html': 'text/html'}
+        'index.html': 'text/html',
+        'sheet.xsl': 'text/xsl'}
 
     if 'REQUEST_URI' in environ:
         url = environ['REQUEST_URI'][1:]
+
     else:
         url = environ['PATH_INFO'][1:]
 
@@ -591,16 +634,29 @@ def cgi_wrapper(environ, start_response):
             start_response(headers['status'], list(headers.items()))
             return ['Error %s' % headers['status']]
 
-    # actual morss use
+    else:
+        return app(environ, start_response)
+
+
+@middleware
+def cgi_error_handler(environ, start_response, app):
     try:
-        return [cgi_app(environ, start_response) or '(empty)']
+        return app(environ, start_response)
+
     except (KeyboardInterrupt, SystemExit):
         raise
+
     except Exception as e:
-        headers = {'status': '500 Oops', 'content-type': 'text/plain'}
+        headers = {'status': '500 Oops', 'content-type': 'text/html'}
         start_response(headers['status'], list(headers.items()), sys.exc_info())
-        log('ERROR <%s>: %s' % (url, e.message), force=True)
-        return ['An error happened:\n%s' % e.message]
+        log('ERROR: %s' % repr(e), force=True)
+        return [cgitb.html(sys.exc_info())]
+
+
+@middleware
+def cgi_encode(environ, start_response, app):
+    out = app(environ, start_response)
+    return [x if isinstance(x, bytes) else x.encode('utf-8') for x in out]
 
 
 def cli_app():
@@ -627,6 +683,7 @@ def isInt(string):
     try:
         int(string)
         return True
+
     except ValueError:
         return False
 
@@ -634,7 +691,12 @@ def isInt(string):
 def main():
     if 'REQUEST_URI' in os.environ:
         # mod_cgi
-        wsgiref.handlers.CGIHandler().run(cgi_wrapper)
+
+        app = cgi_app
+        app = cgi_error_handler(app)
+        app = cgi_encode(app)
+
+        wsgiref.handlers.CGIHandler().run(app)
 
     elif len(sys.argv) <= 1 or isInt(sys.argv[1]) or '--root' in sys.argv[1:]:
         # start internal (basic) http server
@@ -643,22 +705,30 @@ def main():
             argPort = int(sys.argv[1])
             if argPort > 0:
                 port = argPort
+
             else:
                 raise MorssException('Port must be positive integer')
 
         else:
             port = PORT
 
-        print('Serving http://localhost:%s/'%port)
-        httpd = wsgiref.simple_server.make_server('', port, cgi_wrapper)
+        app = cgi_app
+        app = cgi_file_handler(app)
+        app = cgi_error_handler(app)
+        app = cgi_encode(app)
+
+        print('Serving http://localhost:%s/' % port)
+        httpd = wsgiref.simple_server.make_server('', port, app)
         httpd.serve_forever()
 
     else:
         # as a CLI app
         try:
             cli_app()
+
         except (KeyboardInterrupt, SystemExit):
             raise
+
         except Exception as e:
             print('ERROR: %s' % e.message)