def index_logs(self): irclogs = web_ui.IrcLogsView(self.env) framework = Framework('builtin://%s/%s.idx' % (quote(irclogs.search_db_path), quote(irclogs.prefix))) framework.add_source('file://%s' % quote(irclogs.path)) framework.update() framework.close()
def index_logs(self): irclogs = web_ui.IrcLogsView(self.env) framework = Framework( 'builtin://%s/%s.idx' % (quote(irclogs.search_db_path), quote(irclogs.prefix))) framework.add_source('file://%s' % quote(irclogs.path)) framework.update() framework.close()
def get_search_results(self, req, terms, filters): def _cut_line(text, size): """Cut the line down appending ... if the line is larger """ if len(text) > size: return text[:size] + ' ...' return text if not 'irclogs' in filters: return import time from datetime import datetime from pyndexter import Framework, READONLY from pyndexter.util import quote framework = Framework(self.indexer, stemmer='porter://', mode=READONLY) framework.add_source('file://%s?include=*.log' % quote(self.path)) try: for hit in framework.search(' '.join(terms)): path = hit.uri.path anchor = self.find_anchor(hit.current.content, terms) year, month, day = path[-12:-8], path[-8:-6], path[-6:-4] timestamp = time.mktime(datetime(int(year), int(month), int(day)).timetuple()) yield (req.href('/irclogs/%s/%s/%s' % (year, month, day)) + anchor, '%s logs for %s-%s-%s' % (self.prefix, year, month, day), timestamp, 'irclog', unicode(hit.excerpt(terms))) except Exception, e: self.log.debug('pyndexter has a big fat bug. Give alect crap about it.', exc_info=e) return
def get_search_results(self, req, terms, filters): def _cut_line(text, size): if len(text) > size: return text[:size] + '...' return text if not 'irclogs' in filters: return irclogs = web_ui.IrcLogsView(self.env) framework = Framework( 'builtin://%s/%s.idx' % (quote(irclogs.search_db_path), quote(irclogs.prefix)), mode=READWRITE) framework.add_source('file://%s' % quote(irclogs.path)) tz = req.tz utc = pytz.utc unicode_terms = [] for term in terms: unicode_terms.append(unicode(term)) for hit in framework.search(' '.join(terms)): path = hit.uri.path server_dt = self.find_anchor(irclogs, hit.current.content, terms) if server_dt is None: continue utc_dt = utc.normalize(server_dt.astimezone(utc)) user_dt = tz.normalize(server_dt.astimezone(tz)) user_time = user_dt.strftime("%H:%M:%S") anchor = utc_dt.strftime("#UTC%Y-%m-%dT%H:%M:%S") year, month, day, hour, minute, second = \ path[-14:-10], path[-9:-7], path[-6:-4], user_time[0:2], \ user_time[3:5], user_time[6:8] timestamp = user_dt.replace(tzinfo=localtz) yield req.href('/irclogs/%s/%s/%s' % (year, month, day)) + anchor, \ 'IRC: %s logs for %s-%s-%s' % \ (irclogs.prefix, year, month, day), \ timestamp, 'irclog', \ hit.excerpt(unicode_terms) framework.close()
def update_irc_search(): args = sys.argv index_path = args[1] log_path = args[2] files = os.listdir(args[2]) for file in files: try: if os.path.isdir("%s/%s.idx" % (index_path, file)): output = shutil.rmtree("%s/%s.idx" % (index_path, file)) framework = Framework('builtin://%s/%s.idx' % (quote(index_path), quote(file)), mode=READWRITE) framework.add_source('file://%s/%s' % (quote(log_path), quote(file))) framework.update() framework.close() except Exception, e: code, message = e print 'Error %s: %s' % (code, message)
def get_search_results(self, req, terms, filters): def _cut_line(text, size): if len(text) > size: return text[:size] + '...' return text if not 'irclogs' in filters: return irclogs = web_ui.IrcLogsView(self.env) framework = Framework('builtin://%s/%s.idx' % (quote(irclogs.search_db_path), quote(irclogs.prefix)), mode=READWRITE) framework.add_source('file://%s' % quote(irclogs.path)) tz = req.tz utc = pytz.utc unicode_terms = [] for term in terms: unicode_terms.append(unicode(term)) for hit in framework.search(' '.join(terms)): path = hit.uri.path server_dt = self.find_anchor(irclogs, hit.current.content, terms) if server_dt is None: continue utc_dt = utc.normalize(server_dt.astimezone(utc)) user_dt = tz.normalize(server_dt.astimezone(tz)) user_time = user_dt.strftime("%H:%M:%S") anchor = utc_dt.strftime("#UTC%Y-%m-%dT%H:%M:%S") year, month, day, hour, minute, second = \ path[-14:-10], path[-9:-7], path[-6:-4], user_time[0:2], \ user_time[3:5], user_time[6:8] timestamp = user_dt.replace(tzinfo=localtz) yield req.href('/irclogs/%s/%s/%s' % (year, month, day)) + anchor, \ 'IRC: %s logs for %s-%s-%s' % \ (irclogs.prefix, year, month, day), \ timestamp, 'irclog', \ hit.excerpt(unicode_terms) framework.close()
from pyndexter import * from pyndexter.util import TimingFilter, quote VERSION = '0.2' def index_logs(): """Run the indexing""" framework = Framework( 'builtin:///var/pacopablo/trac/casa_de_pacopablo/indexes/irclogs.idx?cache=true', stemmer='porter://') framework.add_source( 'file://%s?include=*.log' % quote('/home/pacopablo/irc/trac/logs/ChannelLogger/freenode/#trac/')) framework.update(filter=TimingFilter(progressive=True)) framework.close() def doArgs(): """ Look if you can't guess what this function does, just give up now. """ global VERSION version = "%%prog %s" % VERSION usage = "usage: %prog [options] [site]" description = "%prog is used to index the irclogs for searching." parser = OptionParser(usage=usage,
# All rights reserved. # # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. # # Author: John Hampton <*****@*****.**> from pyndexter import * from pyndexter.util import TimingFilter, quote VERSION='0.2' def index_logs(): """Run the indexing""" framework = Framework('builtin:///var/pacopablo/trac/casa_de_pacopablo/indexes/irclogs.idx?cache=true', stemmer='porter://') framework.add_source('file://%s?include=*.log' % quote('/home/pacopablo/irc/trac/logs/ChannelLogger/freenode/#trac/')) framework.update(filter=TimingFilter(progressive=True)) framework.close() def doArgs(): """ Look if you can't guess what this function does, just give up now. """ global VERSION version = "%%prog %s" % VERSION usage ="usage: %prog [options] [site]" description="%prog is used to index the irclogs for searching."