def edit(req, id, docname):
docid = atoi(id)
doc = Doc.try_get(id=docid)
if not doc:
raise Http404("Document #%d (%s) does not exist." % (docid, id))
doc.use_latest()
page = doc.get_edit_url()
dict = {}
dict['alltags'] = _alltags()
dict['alldocs'] = Doc
dict['menuitems'] = [
('/kb/', 'Knowledgebase'),
]
if len(doc.tags) > 0:
t = doc.tags[0]
dict['menuitems'].append(('/kb/%s' % t, t))
dict['menuitems'].append((doc.get_url(), 'KB%d' % doc.id))
dict['menuitems'].append((doc.get_edit_url(), '-Edit-'))
dict['page'] = page
dict['title'] = doc.title
dict['tags'] = join(', ', doc.tags)
dict['uploadurl'] = doc.get_upload_url()
dict['text'] = doc.text
return render_to_response('ekb/edit.html', dict)
def _calc_word_frequencies():
print 'Deleting all wordweights'
db.run('delete from WordWeights')
db.run('delete from Words')
totals = {}
for doc in Doc.search():
print ' %s' % doc.filename
textbits = [doc.title, doc.title, # title gets bonus points
doc.filename, doc.expanded_text(lambda x: x, headerdepth=1,
expandbooks=1)]
textbits += doc.tags
fulltext = join(' ', textbits)
words = [w.lower() for w in re.findall(r"(\w+(?:[.'#%@]\w+)?)",
fulltext)]
total = len(words)*1.0
wordcounts = {}
echo(' %d total words' % total)
for w in words:
wordcounts[w] = wordcounts.get(w, 0) + 1
echo(', %d unique' % len(wordcounts.keys()))
new = 0
for w,count in wordcounts.iteritems():
if not w in totals:
totals[w] = 0
new += 1
totals[w] += count
db.run('insert into WordWeights (docid, word, weight) '
' values (?,?,?)', doc.id, w, (count/total)**.5)
echo(', %d new\n' % new)
print ' %d total unique words' % len(totals)
print 'Saving words'
for word,count in totals.iteritems():
db.run('insert into Words (word, total) values (?,?)', word, count)
def __init__(self, want_words, highlight_tag):
self.wordsub = None
self.wordfix = None
self.replacement = None
want_esc = join("|", [re.escape(x) for x in want_words])
if want_esc and highlight_tag:
self.wordsub = re.compile('(' + want_esc + ')', re.I)
htag = re.sub(r'\W', '_', highlight_tag)
self.wordfix = re.compile('<%s>(.*?)</%s>' % (htag, htag))
self.replacement = u'<%s>\\1</%s>' % (htag, htag)
