where
import Data.Maybe
+import Data.String.Utils (join, splitWs)
+import Test.HUnit
+import Text.Regex (matchRegex, mkRegex)
import Text.XML.HaXml
+import StringUtils (listify)
import Twitter.User
import Twitter.Xml
first_user = user_from_content (users !! 0)
+-- |Takes an XML String as an argument, and returns the
+-- status that was parsed from it. Should only be used
+-- on XML string where a <status> is a top-level element.
+parse_status :: String -> [Status]
+parse_status xml_data =
+ catMaybes maybe_status
+ where
+ (Document _ _ root _) = xmlParse xml_file_name xml_data
+ root_elem = CElem root
+ status_element = (single_status root_elem)
+ maybe_status = map status_from_content status_element
+
+
-- |Takes an XML String as an argument, and returns the list of
-- statuses that can be parsed from it.
parse_statuses :: String -> [Status]
replicate ((length name) + 3 + (length (created_at status))) '-',
"\n",
replace_entities (text status),
+ "\n\n",
+ join "\n" user_timeline_urls,
"\n" ]
where
name = screen_name (user status)
-
+ user_timeline_urls = listify (make_user_timeline_urls status)
-- |Given a list of statuses, returns the greatest status_id belonging
maximum status_ids
where
status_ids = map status_id statuses
+
+
+-- |Parse one username from a word.
+parse_username :: String -> Maybe String
+parse_username word =
+ case matches of
+ Nothing -> Nothing
+ Just [] -> Nothing
+ Just (first_match:_) -> Just first_match
+ where
+ username_regex = mkRegex "@([a-zA-Z0-9_]+)"
+ matches = matchRegex username_regex word
+
+
+-- |Parse all usernames of the form @username from a status.
+parse_usernames_from_status :: Status -> [String]
+parse_usernames_from_status status =
+ catMaybes (map parse_username status_words)
+ where
+ status_words = splitWs (text status)
+
+-- |Get all referenced users' timeline URLs.
+make_user_timeline_urls :: Status -> [String]
+make_user_timeline_urls status =
+ map screen_name_to_timeline_url usernames
+ where
+ usernames = parse_usernames_from_status status
+
+
+status_tests :: [Test]
+status_tests = [ test_parse_usernames ]
+
+
+test_parse_usernames :: Test
+test_parse_usernames =
+ TestCase $ assertEqual "All usernames are parsed." expected_usernames actual_usernames
+ where
+ dummy_user = User { screen_name = "nobody" }
+ dummy_status = Status { status_id = 1,
+ created_at = "never",
+ text = "Hypothesis: @donsbot and @bonus500 are two personalities belonging to the same person.",
+ user = dummy_user }
+
+ actual_usernames = parse_usernames_from_status dummy_status
+ expected_usernames = ["donsbot", "bonus500"]