""" This module contains an extension to Blosxom file entries to support comments. Contributors: Ted Leung Will Guaraldi Wari Wahab Robert Wall Bill Mill Roberto De Almeida David Geller If you make any changes to this plugin, please a send a patch with your changes to twl+pyblosxom@sauria.com so that we can incorporate your changes. Thanks! This plugin requires the PyXML module. This module supports the following config parameters (they are not required): comment_dir - the directory we're going to store all our comments in. this defaults to datadir + "comments". comment_ext - the file extension used to denote a comment file. this defaults to "cmt". comment_draft_ext - the file extension used for new comments that have not been manually approved by you. this defaults to comment_ext (i.e. there is no draft stage) comment_smtp_server - the smtp server to send comments notifications through. comment_smtp_from - the person comment notifications will be from. If you omit this, the from address will be the e-mail address as input in the comment form comment_smtp_to - the person to send comment notifications to. comment_nofollow - set this to 1 to add rel="nofollow" attributes to links in the description -- these attributes are embedded in the stored representation. Comments are stored 1 per file in a parallel hierarchy to the datadir hierarchy. The filename of the comment is the filename of the blog entry, plus the creation time of the comment as a float, plus the comment extension. The contents of the comment file is an RSS 2.0 formatted item. Comments now follow the blog_encoding variable specified in config.py Each entry has to have the following properties in order to work with comments: 1. absolute_path - the category of the entry. ex. "dev/pyblosxom" 2. fn - the filename of the entry without the file extension and without the directory. ex. "staticrendering" 3. file_path - the absolute_path plus the fn. ex. "dev/pyblosxom/staticrendering" Also, for any entry that you don't want to have comments, just add "nocomments" to the properties of the entry. If you would like comment previews, you need to do 2 things. 1) Add a preview button to comment-form.html like this: You may change the contents of the value attribute, but the name of the input must be "preview". 2) Still in your comment-form.html template, you need to use the comment values to fill in the values of your input fields like so: If there is no preview available, these variables will be stripped from the text and cause no problem. 3) Copy comment.html to a template called comment-preview.html. All of the available variables from the comment template are available for this template. This plugin implements Google's nofollow support for links in the body of the comment. If you display the link of the comment poster in your HTML template then you must add the rel="nofollow" attribute to your template as well Copyright (c) 2003-2005 Ted Leung Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. """ __author__ = "Ted Leung" __version__ = "$Id: comments.py,v 1.41.4.7 2005/06/10 13:58:29 willhelm Exp $" import cgi, glob, os.path, re, time, cPickle, os, codecs from xml.sax.saxutils import escape from Pyblosxom import tools from Pyblosxom.entries.base import EntryBase def cb_start(args): request = args["request"] config = request.getConfiguration() logdir = config.get("logdir", "/tmp/") # logfile = os.path.normpath(logdir + os.sep + "comments.log") # tools.make_logger(logfile) if not config.has_key('comment_dir'): config['comment_dir'] = os.path.join(config['datadir'],'comments') if not config.has_key('comment_ext'): config['comment_ext'] = 'cmt' if not config.has_key('comment_draft_ext'): config['comment_draft_ext'] = config['comment_ext'] if not config.has_key('comment_nofollow'): config['comment_nofollow'] = 0 def verify_installation(request): config = request.getConfiguration() retval = 1 if config.has_key('comment_dir') and not os.path.isdir(config['comment_dir']): print 'The "comment_dir" property in the config file must refer to a directory' retval = 0 smtp_keys_defined = [] smtp_keys=['comment_smtp_server', 'comment_smtp_from', 'comment_smtp_to'] for k in smtp_keys: if config.has_key(k): smtp_keys_defined.append(k) if smtp_keys_defined: for i in smtp_keys: if i not in smtp_keys_defined: print("Missing comment SMTP property: '%s'" % i) retval = 0 optional_keys = ['comment_dir', 'comment_ext', 'comment_draft_ext'] for i in optional_keys: if not config.has_key(i): print("missing optional property: '%s'" % i) return retval def createhtmlmail (html, headers): """Create a mime-message that will render HTML in popular MUAs, text in better ones Based on: http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/67083""" import MimeWriter import mimetools import cStringIO out = cStringIO.StringIO() # output buffer for our message htmlin = cStringIO.StringIO(html) text = re.sub('<.*?>', '', html) txtin = cStringIO.StringIO(text) writer = MimeWriter.MimeWriter(out) for header,value in headers: writer.addheader(header, value) writer.addheader("MIME-Version", "1.0") writer.startmultipartbody("alternative") writer.flushheaders() subpart = writer.nextpart() subpart.addheader("Content-Transfer-Encoding", "quoted-printable") pout = subpart.startbody("text/plain", [("charset", 'us-ascii')]) mimetools.encode(txtin, pout, 'quoted-printable') txtin.close() subpart = writer.nextpart() subpart.addheader("Content-Transfer-Encoding", "quoted-printable") pout = subpart.startbody("text/html", [("charset", 'us-ascii')]) mimetools.encode(htmlin, pout, 'quoted-printable') htmlin.close() writer.lastpart() msg = out.getvalue() out.close() return msg def readComments(entry, config): """ @param: a file entry @type: dict @returns: a list of comment dicts """ encoding = config['blog_encoding'] filelist = glob.glob(cmtExpr(entry, config)) if not entry.has_key('num_comments'): entry['num_comments'] = len(filelist) comments = [readComment(f, encoding) for f in filelist] comments = [(cmt['cmt_time'], cmt) for cmt in comments] comments.sort() return [c[1] for c in comments] def getCommentCount(entry, config): """ @param: a file entry @type: dict @returns: the number of comments for the entry """ if entry['absolute_path'] == None: return 0 filelist = glob.glob(cmtExpr(entry,config)) if filelist is not None: return len(filelist) return 0 def cmtExpr(entry, config): """ Return a string containing the regular expression for comment entries @param: a file entry @type: dict @returns: a string with the directory path for the comment @param: configuratioin dictionary @type: dict @returns: a string containing the regular expression for comment entries """ cmtDir = os.path.join(config['comment_dir'], entry['absolute_path']) cmtExpr = os.path.join(cmtDir,entry['fn']+'-*.'+config['comment_ext']) return cmtExpr def readComment(filename, encoding): """ Read a comment from filename @param filename: filename containing a comment @type filename: string @param encoding: encoding of comment files @type encoding: string @returns: a comment dict """ from xml.sax import make_parser, SAXException from xml.sax.handler import feature_namespaces, ContentHandler class cmtHandler(ContentHandler): def __init__(self, cmt): self._data = "" self.cmt = cmt def startElement(self, name, atts): self._data = "" def endElement(self, name): self.cmt['cmt_'+name] = self._data def characters(self, content): self._data += content cmt = {} try: parser = make_parser() parser.setFeature(feature_namespaces, 0) handler = cmtHandler(cmt) parser.setContentHandler(handler) parser.parse(filename) cmt['cmt_time'] = float(cmt['cmt_pubDate']) #time.time() cmt['cmt_pubDate'] = time.ctime(float(cmt['cmt_pubDate'])) #pretty time return cmt except: #don't error out on a bad comment # tools.log('bad comment file: %s' % filename) pass def writeComment(request, config, data, comment, encoding): """ Write a comment @param config: dict containing pyblosxom config info @type config: dict @param data: dict containing entry info @type data: dict @param comment: dict containing comment info @type comment: dict @return: The success or failure of creating the comment. @rtype: string """ entry = data['entry_list'][0] cdir = os.path.join(config['comment_dir'],entry['absolute_path']) cdir = os.path.normpath(cdir) if not os.path.isdir(cdir): os.makedirs(cdir, mode = 0775) cfn = os.path.join(cdir,entry['fn']+"-"+comment['pubDate']+"."+config['comment_draft_ext']) argdict = { "request": request, "comment": comment } reject = tools.run_callback("comment_reject", argdict, donefunc=lambda x:x) if reject == 1: return "Comment rejected." def makeXMLField(name, field): return "<"+name+">" + cgi.escape(field.get(name, "")) + "\n"; filedata = '\n' % encoding filedata += "\n" filedata += makeXMLField('title', comment) filedata += makeXMLField('author', comment) filedata += makeXMLField('link', comment) filedata += makeXMLField('email', comment) filedata += makeXMLField('source', comment) filedata += makeXMLField('pubDate', comment) filedata += makeXMLField('description', comment) filedata += "\n" try : cfile = codecs.open(cfn, "w", encoding) except IOError: # tools.log("Couldn't open comment file %s for writing" % cfn) return "Internal error: Your comment could not be saved." cfile.write(filedata) cfile.close() os.chmod(cfn, 0664) #write latest pickle latest = None latestFilename = os.path.join(config['comment_dir'],'LATEST.cmt') try: latest = open(latestFilename,"w") except IOError: # tools.log("Couldn't open latest comment pickle for writing") return "Couldn't open latest comment pickle for writing." else: modTime = float(comment['pubDate']) try: cPickle.dump(modTime,latest) latest.close() except IOError: # should log or e-mail if latest: latest.close() return "Internal error: Your comment may not have been saved." if config.has_key('comment_smtp_server') and \ config.has_key('comment_smtp_to'): # FIXME - removed grabbing send_email's return error message # so there's no way to know if email is getting sent or not. send_email(config, entry, comment, cdir, cfn) # figure out if the comment was submitted as a draft if config["comment_ext"] != config["comment_draft_ext"]: return "Comment was submitted for approval. Thanks!" return "Comment submitted. Thanks!" def send_email(config, entry, comment, comment_dir, comment_filename): """Send an email to the blog owner on a new comment @param config: configuration as parsed by Pyblosxom @type config: dictionary @param entry: a file entry @type config: dictionary @param comment: comment as generated by readComment @type comment: dictionary @param comment_dir: the comment directory @type comment_dir: string @param comment_filename: file name of current comment @type comment_filename: string """ import smtplib # import the formatdate function which is in a different # place in Python 2.3 and up. try: from email.Utils import formatdate except ImportError: from rfc822 import formatdate author = escape_SMTP_commands(clean_author(comment['author'])) description = escape_SMTP_commands(comment['description']) if comment.has_key('email'): email = comment['email'] else: email = config['comment_smtp_from'] try: server = smtplib.SMTP(config['comment_smtp_server']) curl = config['base_url']+'/'+entry['file_path'] comment_dir = os.path.join(config['comment_dir'], entry['absolute_path']) message = [] message.append("From: %s" % email) message.append("To: %s" % config["comment_smtp_to"]) message.append("Date: %s" % formatdate(float(comment['pubDate']))) message.append("Subject: write back by %s" % author) message.append("") message.append("%s\n%s\n%s\n" % (description, comment_filename, curl)) server.sendmail(from_addr=email, to_addrs=config['comment_smtp_to'], msg="\n".join(message)) server.quit() except Exception, e: # tools.log("Error sending mail: %s" % e) # FIXME - if we error out, no one will know. pass def clean_author(s): """ Guard against blasterattacko style attacks that embedd SMTP commands in author field. If author field is more than one line, reduce to one line @param the string to be checked @type string @returns the sanitized string """ return s.splitlines()[0] def escape_SMTP_commands(s): """ Guard against blasterattacko style attacks that embed SMTP commands by using an HTML span to make the command syntactically invalid to SMTP but renderable by HTML @param the string to be checked @type string @returns the sanitized string """ def repl_fn(mo): return ''+mo.group(0)+'' s = re.sub('([Tt]o:.*)',repl_fn,s) s = re.sub('([Ff]rom:.*)',repl_fn,s) s = re.sub('([Ss]ubject:.*)',repl_fn,s) return s def sanitize(body): """ This code shamelessly lifted from Sam Ruby's mombo/post.py """ body=re.sub(r'\s+$','',body) body=re.sub('\r\n?','\n', body) # naked urls become hypertext links body=re.sub('(^|[\\s.:;?\\-\\]<])' + '(http://[-\\w;/?:@&=+$.!~*\'()%,#]+[\\w/])' + '(?=$|[\\s.:;?\\-\\[\\]>])', '\\1\\2',body) # html characters used in text become escaped body=escape(body) # passthru , , , ,
,
,

, # , , , , , , , 

, 
    # , , , , 
    body=re.sub('<a href="([^"]*)">([^&]*)</a>',
                '\\2', body)
    body=re.sub('<a href=\'([^\']*)\'>([^&]*)</a>',
                '\\2', body)
    body=re.sub('<em>([^&]*)</em>', '\\1', body)
    body=re.sub('<i>([^&]*)</i>', '\\1', body)
    body=re.sub('<b>([^&]*)</b>', '\\1', body)
    body=re.sub('<blockquote>([^&]*)</blockquote>', 
                '
\\1
', body)
    body=re.sub('<br\s*/?>\n?','\n',body)

    body=re.sub('<abbr>([^&]*)</abbr>', '\\1', body)
    body=re.sub('<acronym>([^&]*)</acronym>', '\\1', body)
    body=re.sub('<big>([^&]*)</big>', '\\1', body)
    body=re.sub('<cite>([^&]*)</cite>', '\\1', body)
    body=re.sub('<code>([^&]*)</code>', '\\1', body)
    body=re.sub('<dfn>([^&]*)</dfn>', '\\1', body)
    body=re.sub('<kbd>([^&]*)</kbd>', '\\1', body)
    body=re.sub('<pre>([^&]*)</pre>', '
\\1
', body)
    body=re.sub('<small>([^&]*)</small>', '\\1', body)
    body=re.sub('<strong>([^&]*)</strong>', '\\1', body)
    body=re.sub('<sub>([^&]*)</sub>', '\\1', body)
    body=re.sub('<sup>([^&]*)</sup>', '\\1', body)
    body=re.sub('<tt>([^&]*)</tt>', '\\1', body)
    body=re.sub('<var>([^&]*)</var>', '\\1', body)

    body=re.sub('</?p>','\n\n',body).strip()

    # wiki like support: _em_, *b*, [url title]
    body=re.sub(r'\b_(\w.*?)_\b', r'\1', body)
    body=re.sub(r'\*(\w.*?)\*', r'\1', body)
    body=re.sub(r'\[(\w+:\S+\.gif) (.*?)\]', r'\2', body)
    body=re.sub(r'\[(\w+:\S+\.jpg) (.*?)\]', r'\2', body)
    body=re.sub(r'\[(\w+:\S+\.png) (.*?)\]', r'\2', body)
    body=re.sub(r'\[(\w+:\S+) (.*?)\]', r'\2', body).strip()

    # unordered lists: consecutive lines starting with spaces and an asterisk
    chunk=re.compile(r'^( *\*.*(?:\n *\*.*)+)',re.M).split(body)
    for i in range(1, len(chunk), 2):
        (html,stack)=('', [''])
        for indent,line in re.findall(r'( +)\* +(.*)', chunk[i]) + [('','')]:
            if indent>stack[-1]: (stack,html)=(stack+[indent],html+'