def get_interesting_topics():
"""
Get a list of interesting topics for the given language.
Interesting topics are for now defined as:
- The topic is not followed yet
- The topic is not in the filters list
- There are articles with that topic in the language
:return:
"""
topic_data = []
already_filtered = [each.topic for each in TopicFilter.all_for_user(flask.g.user)]
already_subscribed = [
each.topic for each in TopicSubscription.all_for_user(flask.g.user)
]
reading_languages = Language.all_reading_for_user(flask.g.user)
loc_topics = []
for each in reading_languages:
loc_topics.extend(LocalizedTopic.all_for_language(each))
topics = [each.topic for each in loc_topics]
for topic in topics:
if (topic not in already_filtered) and (topic not in already_subscribed):
topic_data.append(topic.as_dictionary())
return json_result(topic_data)
def _reading_preferences_hash(user):
"""
Method to retrieve the hash, as this is done several times.
:param user:
:return: articles_hash: ArticlesHash
"""
user_filter_subscriptions = TopicFilter.all_for_user(user)
filters = [topic_id.topic for topic_id in user_filter_subscriptions]
user_topic_subscriptions = TopicSubscription.all_for_user(user)
topics = [topic_id.topic for topic_id in user_topic_subscriptions]
user_languages = Language.all_reading_for_user(user)
user_search_filters = SearchFilter.all_for_user(user)
search_filters = [search_id.search for search_id in user_search_filters]
user_searches = SearchSubscription.all_for_user(user)
searches = [search_id.search for search_id in user_searches]
articles_hash = ArticlesCache.calculate_hash(
user, topics, filters, searches, search_filters, user_languages
)
return articles_hash
def article_recommendations_for_user(user, count):
"""
Retrieve :param count articles which are equally distributed
over all the feeds to which the :param user is registered to.
Fails if no language is selected.
:return:
"""
# Temporary fix for the experiment of Gabriel
AIKI_USERS_COHORT_ID = 109
if user.cohort_id == AIKI_USERS_COHORT_ID:
return CohortArticleMap.get_articles_info_for_cohort(user.cohort)
import zeeguu_core
user_languages = Language.all_reading_for_user(user)
if not user_languages:
return [user.learned_language]
reading_pref_hash = _reading_preferences_hash(user)
_recompute_recommender_cache_if_needed(user, zeeguu_core.db.session)
# two fast calls ot /articles/recommended might result in a race condition
# in _recompute_recommender_cache;
# race condition in _recompute_recommender_cache might result in
# duplicates in the db; since this is being sunset for the elastic search
# it's not worth fixing the race condition; instead we're simply
# ensuring that duplicate articles are removed at this point
all_articles = set(
ArticlesCache.get_articles_for_hash(reading_pref_hash, count))
all_articles = [
each for each in all_articles
if (not each.broken and each.published_time)
]
all_articles = SortedList(all_articles, lambda x: x.published_time)
return [
UserArticle.user_article_info(user, article)
for article in reversed(all_articles)
]
def _find_articles_for_user(user):
"""
This method gets all the topic and search subscriptions for a user.
It then returns all the articles that are associated with these.
:param user:
:return:
"""
user_languages = Language.all_reading_for_user(user)
topic_subscriptions = TopicSubscription.all_for_user(user)
search_subscriptions = SearchSubscription.all_for_user(user)
subscribed_articles = _filter_subscribed_articles(
search_subscriptions, topic_subscriptions, user_languages, user
)
return subscribed_articles
def _get_user_articles_sources_languages(user, limit=1000):
"""
This method is used to get all the user articles for the sources if there are any
selected sources for the user, and it otherwise gets all the articles for the
current learning languages for the user.
:param user: the user for which the articles should be fetched
:param limit: the amount of articles for each source or language
:return: a list of articles based on the parameters
"""
user_languages = Language.all_reading_for_user(user)
all_articles = []
for language in user_languages:
info(f"Getting articles for {language}")
new_articles = language.get_articles(most_recent_first=True)
all_articles.extend(new_articles)
info(f"Added {len(new_articles)} articles for {language}")
return all_articles
def article_recommendations_for_user(user, count):
"""
Retrieve :param count articles which are equally distributed
over all the feeds to which the :param user is registered to.
Fails if no language is selected.
:return:
"""
# Temporary fix for the experiment of Gabriel
AIKI_USERS_COHORT_ID = 109
if user.cohort_id == AIKI_USERS_COHORT_ID:
return CohortArticleMap.get_articles_info_for_cohort(user.cohort)
import zeeguu_core
user_languages = Language.all_reading_for_user(user)
if not user_languages:
return [user.learned_language]
reading_pref_hash = _reading_preferences_hash(user)
_recompute_recommender_cache_if_needed(user, zeeguu_core.db.session)
all_articles = ArticlesCache.get_articles_for_hash(reading_pref_hash,
count)
all_articles = [
each for each in all_articles
if (not each.broken and each.published_time)
]
all_articles = SortedList(all_articles, lambda x: x.published_time)
return [
UserArticle.user_article_info(user, article)
for article in reversed(all_articles)
]
def article_search_for_user(user, count, search_terms):
"""
Handles searching.
Find the relational values from the database and use them to search in elasticsearch for relative articles.
:param user:
:param count: max amount of articles to return
:param search_terms: the inputed search string by the user
:return: articles
"""
user_languages = Language.all_reading_for_user(user)
per_language_article_count = count / len(user_languages)
final_article_mix = []
for language in user_languages:
print(f"language: {language}")
# 0. Ensure appropriate difficulty
declared_level_min, declared_level_max = user.levels_for(language)
lower_bounds = declared_level_min * 10
upper_bounds = declared_level_max * 10
# 1. Unwanted user topics
# ==============================
user_search_filters = SearchFilter.all_for_user(user)
unwanted_user_topics = []
for user_search_filter in user_search_filters:
unwanted_user_topics.append(user_search_filter.search.keywords)
print(f"keywords to exclude: {unwanted_user_topics}")
# 2. Topics to exclude / filter out
# =================================
excluded_topics = TopicFilter.all_for_user(user)
topics_to_exclude = [each.topic.title for each in excluded_topics]
print(f"topics to exclude: {topics_to_exclude}")
# 3. Topics subscribed, and thus to include
# =========================================
topic_subscriptions = TopicSubscription.all_for_user(user)
topics_to_include = [
subscription.topic.title
for subscription in TopicSubscription.all_for_user(user)
]
print(f"topics to include: {topic_subscriptions}")
# 4. Wanted user topics
# =========================================
user_subscriptions = SearchSubscription.all_for_user(user)
wanted_user_topics = []
for sub in user_subscriptions:
wanted_user_topics.append(sub.search.keywords)
print(f"keywords to include: {wanted_user_topics}")
# build the query using elastic_query_builder
query_body = build_elastic_query(
per_language_article_count,
search_terms,
_list_to_string(topics_to_include),
_list_to_string(topics_to_exclude),
_list_to_string(wanted_user_topics),
_list_to_string(unwanted_user_topics),
language,
upper_bounds,
lower_bounds,
)
es = Elasticsearch(ES_CONN_STRING)
res = es.search(index=ES_ZINDEX, body=query_body)
hit_list = res["hits"].get("hits")
final_article_mix.extend(_to_articles_from_ES_hits(hit_list))
# convert to article_info and return
return [
UserArticle.user_article_info(user, article)
for article in final_article_mix if article is not None
]
