aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorcedricbonhomme <devnull@localhost>2010-12-01 08:53:43 +0100
committercedricbonhomme <devnull@localhost>2010-12-01 08:53:43 +0100
commit6cb544b6fea2120900caf2082b122f73de1a776e (patch)
treead677472b2d9f6db74268c332a7ee24df2699e82
parentImprovement of URL (mark an article as read) (1). (diff)
downloadnewspipe-6cb544b6fea2120900caf2082b122f73de1a776e.tar.gz
newspipe-6cb544b6fea2120900caf2082b122f73de1a776e.tar.bz2
newspipe-6cb544b6fea2120900caf2082b122f73de1a776e.zip
Removed language detection functionality.
-rwxr-xr-xpyAggr3g470r.py68
-rwxr-xr-xutils.py40
2 files changed, 10 insertions, 98 deletions
diff --git a/pyAggr3g470r.py b/pyAggr3g470r.py
index c65abb9f..a27714a8 100755
--- a/pyAggr3g470r.py
+++ b/pyAggr3g470r.py
@@ -170,7 +170,7 @@ class Root:
not_read_end = ""
# display a heart for faved articles
- if article[7] == "1":
+ if article[6] == "1":
like = """ <img src="/css/img/heart.png" title="I like this article!" />"""
else:
like = ""
@@ -294,14 +294,6 @@ class Root:
if self.articles:
self.top_words = utils.top_words(self.articles, n=50, size=int(word_size))
html += "<h1>Statistics</h1>\n<br />\n"
- if "oice" not in utils.IMPORT_ERROR:
- # counter object to count the number of
- # french and english articles
- counter = Counter()
- for rss_feed_id in self.articles.keys():
- for article in self.articles[rss_feed_id]:
- counter[article[6]] += 1
-
# Tags cloud
html += 'Minimum size of a word:'
html += '<form method=get action="/management/">'
@@ -311,18 +303,6 @@ class Root:
html += '<div style="width: 35%; overflow:hidden; text-align: justify">' + \
utils.tag_cloud(self.top_words) + '</div>'
- # Languages
- html += "<br /><h3>Languages</h3>\n"
- if "oice" in utils.IMPORT_ERROR:
- html += "Install the module "
- html += """<a href="http://pypi.python.org/pypi/oice.langdet/">oice.langdet</a>"""
- else:
- html += "<ul>\n"
- for language in ['english', 'french']:
- html += """\t<li>%s articles in <a href="/language/%s">%s</a></li>\n""" % \
- (counter[language], language, language)
- html += "</ul>\n<br />"
-
html += "<hr />\n"
html += htmlfooter
return html
@@ -394,7 +374,7 @@ class Root:
not_read_end = ""
# display a heart for faved articles
- if article[7] == "1":
+ if article[6] == "1":
like = """ <img src="/css/img/heart.png" title="I like this article!" />"""
else:
like = ""
@@ -472,7 +452,7 @@ class Root:
html += """<h1><i>%s</i> from <a href="/all_articles/%s">%s</a></h1>\n<br />\n""" % \
(article[2].encode('utf-8'), feed_id, \
self.feeds[feed_id][3].encode('utf-8'))
- if article[7] == "1":
+ if article[6] == "1":
html += """<a href="/like/no:%s:%s"><img src="/css/img/heart.png" title="I like this article!" /></a>""" % \
(feed_id, article_id)
else:
@@ -487,9 +467,7 @@ class Root:
else:
html += "No description available."
html += "\n</div>\n<hr />\n"
- html += """This article seems to be written in <a href="/language/%s">%s</a>.\n""" % \
- (article[6], article[6])
- html += """<br />\n<a href="/plain_text/%s:%s">Plain text</a>\n""" % \
+ html += """\n<a href="/plain_text/%s:%s">Plain text</a>\n""" % \
(feed_id, article_id)
html += """ - <a href="/epub/%s:%s">Export to EPUB</a>\n""" % \
(feed_id, article_id)
@@ -579,7 +557,7 @@ class Root:
not_read_begin = ""
not_read_end = ""
- if article[7] == "1":
+ if article[6] == "1":
like = """ <img src="/css/img/heart.png" title="I like this article!" />"""
else:
like = ""
@@ -688,36 +666,6 @@ class Root:
unread.exposed = True
- def language(self, lang):
- """
- Display articles by language.
- """
- if lang not in ['english', 'french', 'other']:
- return self.error_page('This language is not supported.')
- html = htmlheader()
- html += htmlnav
- html += """<div class="left inner">"""
- html += """<h1>Article(s) written in %s</h1>\n<br />\n""" % (lang,)
- if "oice" not in utils.IMPORT_ERROR:
- for rss_feed_id in self.articles.keys():
- for article in self.articles[rss_feed_id]:
- if article[6] == lang:
- html += article[1].encode('utf-8') + \
- """ - <a href="/description/%s:%s" rel="noreferrer" target="_blank">%s</a>
- from <i><a href="%s">%s</a></i><br />\n""" % \
- (rss_feed_id, article[0].encode('utf-8'), article[2].encode('utf-8'), \
- self.feeds[rss_feed_id][5].encode('utf-8'), \
- self.feeds[rss_feed_id][3].encode('utf-8'))
- else:
- html += "Install the module "
- html += """<a href="http://pypi.python.org/pypi/oice.langdet/">oice.langdet</a>"""
- html += "<hr />\n"
- html += htmlfooter
- return html
-
- language.exposed = True
-
-
def history(self, querystring="all", m=""):
"""
History
@@ -765,7 +713,7 @@ class Root:
not_read_begin = ""
not_read_end = ""
- if article[7] == "1":
+ if article[6] == "1":
like = """ <img src="/css/img/heart.png" title="I like this article!" />"""
else:
like = ""
@@ -986,7 +934,7 @@ class Root:
for rss_feed_id in self.feeds.keys():
new_feed_section = True
for article in self.articles[rss_feed_id]:
- if article[7] == "1":
+ if article[6] == "1":
if new_feed_section is True:
new_feed_section = False
html += """<h2><a name="%s"><a href="%s" rel="noreferrer"
@@ -1243,7 +1191,7 @@ class Root:
self.nb_mail_notifications = len([feed for feed in self.feeds.values() \
if feed[6] == "1"])
self.nb_favorites = sum([len([article for article in self.articles[feed_id] \
- if article[7] == "1"]) \
+ if article[6] == "1"]) \
for feed_id in self.feeds.keys()])
"""
if self.articles != {}:
diff --git a/utils.py b/utils.py
index 29ca6531..ba4de97b 100755
--- a/utils.py
+++ b/utils.py
@@ -58,13 +58,6 @@ from collections import OrderedDict
from StringIO import StringIO
-try:
- from oice.langdet import langdet
- from oice.langdet import streams
- from oice.langdet import languages
-except:
- IMPORT_ERROR.append("oice")
-
import threading
LOCKER = threading.Lock()
@@ -108,24 +101,6 @@ def detect_url_errors(list_of_urls):
errors.append((url, e.reason.errno ,e.reason.strerror))
return errors
-def detect_language(text):
- """
- Detect the language of a text.
- English, French or other (not detected).
- """
- text = text.strip()
- try:
- text_stream = streams.Stream(StringIO(text))
- lang = langdet.LanguageDetector.detect(text_stream)
- except:
- return 'other'
- if lang == languages.french:
- return 'french'.encode('utf-8')
- elif lang == languages.english:
- return 'english'.encode('utf-8')
- else:
- return 'other'
-
def clear_string(data):
"""
Clear a string by removing HTML tags, HTML special caracters
@@ -375,8 +350,7 @@ def load_feed():
nb_favorites = 0
# articles[feed_id] = (article_id, article_date, article_title,
- # article_link, article_description, article_readed,
- # article_language, like)
+ # article_link, article_description, article_readed, like)
# feeds[feed_id] = (nb_article, nb_article_unreaded, feed_image,
# feed_title, feed_link, feed_site_link, mail)
articles, feeds = {}, OrderedDict()
@@ -400,20 +374,10 @@ def load_feed():
sha1_hash.update(article[2].encode('utf-8'))
article_id = sha1_hash.hexdigest()
- # check the presence of the module for language detection
- if "oice" not in IMPORT_ERROR:
- if article[3] != "":
- language = detect_language(clear_string(article[3][:80]).encode('utf-8') + \
- clear_string(article[1]).encode('utf-8'))
- else:
- language = detect_language(clear_string(article[1]).encode('utf-8'))
- else:
- language = "IMPORT_ERROR"
-
# informations about the current article
article_list = [article_id, article[0], unescape(article[1]), \
article[2], unescape(article[3]), \
- article[4], language, article[6]]
+ article[4], article[6]]
# update the number of favorites articles
nb_favorites = nb_favorites + int(article[6])
bgstack15