Context Navigation

Changeset 92:c307d90395db

Timestamp:

05/28/07 15:49:13 (17 months ago)

Author:

Tarek Ziad?? <tarek@…>

Message:

overall fix

Files:

r81	r92
515	515	====================
516	516
517		XXX
	517	- punctuation signs to underline sections
	518	- text enhancements
	519
	520	- ``emphasis``
	521	- ``strong emphasis``
	522	- ```interpreted text```
	523	- ````inline literal text````
	524
	525	reST syntax overview
	526	====================
	527
	528	- bullet list: use +, * or -
	529	- enumerated list: use n. (1., 2., etc.) or #. (automatic)
518	530
519	531	Part 2

r87	r92
39	39
40	40	>>> from filters import levenshtein
41		>>> all = entries~~.select_entries()~~
	41	>>> all = entries
42	42
43	43	Text 2 should be blocked because a similar entry is in::

r91	r92
16	16
17	17	>>> from outputs import write_output
18		>>> write_output('rss', entries)
	18	>>> print write_output('rss', entries)
	19	<?xml version="1.0" encoding="utf-8"?>
	20	...
19	21
20	22
21

r85	r92
24	24	"""
25	25	from datetime import datetime
	26	from time import strftime
26	27	from sqlalchemy import *
	28	from sqlalchemy.exceptions import *
27	29
28	30	_connector = None
	31	TIME_FMT = '%Y-%m-%d %H:%M:%S'
29	32
30	33	class Entries(object):
…	…
32	35	def __init__(self, sqluri):
33	36	self._mapper = self._getEntriesMapper(sqluri)
34		self._mapper.create()
	37	try:
	38	self._mapper.create()
	39	except SQLError:
	40	pass # already there
35	41
36	42	def getConnector(self):
…	…
50	56	Column('creation_date', DateTime))
51	57
52		def insert_entry(self, url, title, content, date=~~datetime.now(~~),
53		creation_date=~~datetime.now(~~)):
	58	def insert_entry(self, url, title, content, date=strftime(TIME_FMT),
	59	creation_date=strftime(TIME_FMT)):
54	60	"""inserts entry"""
55	61	inserter = self._mapper.insert()
56	62	inserter.execute(url=url, title=title, content=content, date=date,
57	63	creation_date=creation_date)
	64
	65	def insert_entries(self, entries):
	66	"""insert entries"""
	67	for entry in entries:
	68	if 'url' in entry:
	69	url = entry['url']
	70	else:
	71	url = entry['link']
	72
	73	if 'creation_date' not in entry:
	74	entry['creation_date'] = strftime(TIME_FMT)
	75
	76	content = entry['content']
	77
	78	entry_date = entry['date']
	79	if isinstance(entry_date, basestring):
	80	try:
	81	entry_date = datetime.strptime(entry_date,
	82	'%Y-%m-%dT%H:%M:%S+00:00')
	83	strftime(TIME_FMT, entry_date.timetuple())
	84	except ValueError:
	85	pass
	86
	87	self.insert_entry(url, entry['title'], content,
	88	entry_date, entry['creation_date'])
	89
58	90
59	91	def select_entries(self, *args):

r88	r92
	1	from filtering import run_filters
	2
1	3	from levenshtein import levenshtein
2	4

r88	r92
32	32	"""
33	33	content = entry['content']
34		for stored_entry in entries:
	34	for stored_entry in entries.select_entries():
35	35	if ratio(content, stored_entry.content) > 0.7:
36	36	return False

r91	r92
31	31	def write_output(type_, entries):
32	32	"""Returns entries from all sources"""
33		_outputs[type_](entries)
	33	return _outputs[type_](entries)
34	34

r91	r92
67	67
68	68	for item in entries:
69		if 'link' in item:
	69	if 'link' in item.keys():
70	70	url = escape(item['link'])
	71	elif 'url' in item.keys():
	72	url = escape(item['url'])
71	73	else:
72	74	url = 'no link'
73	75
74	76	header_text += RSS_ITEM_LI % {'item_id': url}
75		if 'modified_parsed' in item:
	77	if 'modified_parsed' in item.keys():
76	78	item_time = item['modified_parsed']
77	79	else:
…	…
94	96	summary = summary[:i]
95	97	summary += '...'
	98	elif 'description' in item.keys():
	99	summary = item['description']
	100	elif 'content' in item.keys():
	101	summary = item['content']
96	102	else:
97	103	summary = '?'
98	104
99		if 'title' in item:
	105	if 'title' in item.keys():
100	106	title = item['title']
101	107	else:

r89	r92
	1	from sourcing import get_entries
1	2
2	3	import rss

r89	r92
31	31	for entry in entries:
32	32	if 'content' not in entry:
33		entry['content'] = entry['summary']
	33	if 'summary' in entry:
	34	entry['content'] = entry['summary']
	35	elif 'title_detail' in entry:
	36	entry['content'] = entry['title_detail']['value']
	37	else:
	38	entry['content'] = u''
	39
	40	content = entry['content']
	41
	42	# better parsiong to be done here
	43	if isinstance(content, list):
	44	content = content[0]
	45
	46	if not isinstance(content, basestring):
	47	if isinstance(content, dict) and 'value' in content:
	48	entry['content'] = content['value']
	49	else:
	50	entry['content'] = u''
	51
34	52	return entries
35	53