Make the game_info schedule_id optional and add a test case for it.

diff --git a/src/TSN/Parse.hs b/src/TSN/Parse.hs
index 9fe51259ddb518b46a83338fe55792226af7bbae..d707f5fd9575a4d2945f0285204145e0b44b5117 100644 (file)
--- a/src/TSN/Parse.hs
+++ b/src/TSN/Parse.hs
@@ -113,6 +113,30 @@ parse_message_int child xmltree =
 
 
 
+-- | Parse an optional 'Int' from a direct descendent of the
+--   (top-level) \<message\> element in an XmlTree. This is just like
+--   'parse_message_int', except we expect the element/value to be
+--   missing sometimes.
+--
+--   To handle the fact that the element/value is optional, we pattern
+--   match on the 'ParseError' that comes back in case of failure. If
+--   we didn't find anything, we turn that into a \"successful
+--   nothing\". But if we find a value and it can't be parsed, we let
+--   the error propagate, because that shouldn't happen. Of course, if
+--   the parse worked, that's nice too: we wrap the parsed value in a
+--   'Just' and return that wrapped in a 'Right'
+--
+parse_message_int_optional :: String
+                           -> XmlTree
+                           -> Either ParseError (Maybe Int)
+parse_message_int_optional child xmltree =
+  case (parse_message_int child xmltree) of
+    Left (ParseNotFound _)     -> Right Nothing
+    Left pm@(ParseMismatch {}) -> Left pm
+    Right whatever             -> Right (Just whatever)
+
+
+
 -- | Extract the \"XML_File_ID\" element from a document. If we fail
 --   to parse an XML_File_ID, we return an appropriate 'ParseError'
 --   wrapped in a 'Left' constructor. The reason should be one of two
@@ -135,53 +159,21 @@ parse_xmlfid = parse_message_int "XML_File_ID"
 
 -- | Extract the \<game_id\> element from within the top-level
 --   \<message\> of a document. These appear in the "TSN.XML.GameInfo"
---   documents. Unlike the \<schedule_id\> and \<XML_File_ID\>
---   elements, the \<game_id\> can be missing from GameInfo
---   documents. So even the 'Right' value of the 'Either' can be
---   \"missing\". There are two reasons that the parse might fail.
---
---     1. No such elements were found. This is expected sometimes, and
---        should be returned as a 'Right' 'Nothing'.
---
---     2. An element was found, but it could not be read into an
---        'Int'. This is NOT expected, and will be returned as a
---        'ParseError', wrapped in a 'Left'.
---
---   Most of implementation for this ('parse_message_int') is shared,
---   but to handle the fact that game_id is optional, we pattern match
---   on the 'ParseError' that comes back in case of failure. If we
---   didn't find any game_id elements, we turn that into a
---   \"successful nothing\". But if we find a game_id and it can't be
---   parsed, we let the error propagate, because that shouldn't
---   happen. Of course, if the parse worked, that's nice too: we wrap
---   the parsed value in a 'Just' and return that wrapped in a 'Right'
+--   documents. Unlike the \<XML_File_ID\> elements, the \<game_id\>
+--   can be missing from GameInfo documents, so for our implementation
+--   we use 'parse_message_int_optional' instead.
 --
 parse_game_id :: XmlTree -> Either ParseError (Maybe Int)
-parse_game_id xml =
-  case (parse_message_int "game_id" xml) of
-    Left (ParseNotFound _)     -> Right Nothing
-    Left pm@(ParseMismatch {}) -> Left pm
-    Right whatever             -> Right (Just whatever)
+parse_game_id = parse_message_int_optional "game_id"
 
 
 
 -- | Extract the \<schedule_id\> element from within the top-level
---   \<message\> of a document.  These appear in the
---   "TSN.XML.GameInfo" documents. If we fail to parse a schedule_id,
---   we return the reason wrapped in an appropriate 'ParseError'. The reason
---   should be one of two things:
---
---     1. No such elements were found.
---
---     2. An element was found, but it could not be read
---        into an Int.
---
---   Both of these are truly errors in the case of schedule_id. The
---   implementation for this ('parse_message_int') is shared among a
---   few functions.
+--   \<message\> of a document. Identical to 'parse_game_id' except
+--   for the element name.
 --
-parse_schedule_id :: XmlTree -> Either ParseError Int
-parse_schedule_id = parse_message_int "schedule_id"
+parse_schedule_id :: XmlTree -> Either ParseError (Maybe Int)
+parse_schedule_id = parse_message_int_optional "schedule_id"
 
 
 
@@ -262,6 +254,7 @@ parse_tests =
     "TSN.Parse tests"
     [ test_parse_game_id,
       test_parse_missing_game_id,
+      test_parse_missing_schedule_id,
       test_parse_schedule_id,
       test_parse_xmlfid ]
   where
@@ -312,3 +305,15 @@ test_parse_missing_game_id =
     let actual = parse_game_id xmltree
     let expected = Right Nothing
     actual @?= expected
+
+
+-- | The schedule_id element can be missing, so we test that too.
+--
+test_parse_missing_schedule_id :: TestTree
+test_parse_missing_schedule_id =
+  testCase "missing schedule_id is not an error" $ do
+    let path = "test/xml/gameinfo/recapxml-no-game-schedule-ids.xml"
+    xmltree <- unsafe_read_document path
+    let actual = parse_schedule_id xmltree
+    let expected = Right Nothing
+    actual @?= expected

diff --git a/src/TSN/XML/GameInfo.hs b/src/TSN/XML/GameInfo.hs
index 2830295a78d16d898989d0d45df94858c760e3f1..d165c194957c57cac0fe8f11c113a194d5628290 100644 (file)
--- a/src/TSN/XML/GameInfo.hs
+++ b/src/TSN/XML/GameInfo.hs
@@ -102,8 +102,9 @@ data GameInfo =
                           --   They provide foreign keys into any tables storing
                           --   games with their IDs.
 
-    schedule_id :: Int,   -- ^ Required foreign key into any table storing a
-                          --   schedule along with its ID.
+    schedule_id :: Maybe Int, -- ^ Optional key into any table storing a
+                              --   schedule along with its ID. We've noticed
+                              --   them missing in e.g. recapxml.dtd documents.
     time_stamp :: UTCTime,
     xml :: String }
   deriving (Eq, Show)
@@ -190,7 +191,7 @@ test_accessors = testCase "we can access a parsed game_info" $ do
   let a4  = game_id t
   let ex4  = Just 39978
   let a5  = schedule_id t
-  let ex5  = 39978
+  let ex5  = Just 39978
   let a6  = take 9 (xml t)
   let ex6 = "<message>"
   let actual = (a1,a2,a3,a4,a5,a6)

diff --git a/test/xml/gameinfo/recapxml-no-game-schedule-ids.xml b/test/xml/gameinfo/recapxml-no-game-schedule-ids.xml
new file mode 100644 (file)
index 0000000..07037e0
--- /dev/null
+++ b/test/xml/gameinfo/recapxml-no-game-schedule-ids.xml
@@ -0,0 +1 @@
+<?xml version="1.0" standalone="no" ?>\r<!DOCTYPE message PUBLIC "-//TSN//DTD Recap 1.0/EN" "recapxml.dtd">\r<message>\r<XML_File_ID>21246048</XML_File_ID>\r<heading>AAD;RECAP-SEA-TAM-P1</heading>\r<game_id></game_id>\r<schedule_id></schedule_id>\r<category>Recaps</category>\r<sport>MLB</sport>\r<title>American League Game Summary - Seattle at Tampa Bay</title>\r<final>\r<vteam>Seattle</vteam><vscore></vscore>\r<hteam></hteam><hscore></hscore>\r</final>\r<body>\r<P>\r St.  Petersburg, FL (SportsNetwork.com) - Endy Chavez's two-out single broke a\r scoreless  tie  and started  a five-run  ninth inning  that helped the Seattle\r Mariners  beat  the Tampa Bay  Rays, 5-0, in the  rubber match of a three-game\r series at Tropicana Field on Sunday.\r \r</P>\r<P>\r Brad  Miller  smacked a two-out  triple into the  right-field corner on an 0-2\r slider  from Grant  Balfour (0-2).  After a  Willie Bloomquist  walk, Chavez's\r sharp  grounder on  another 0-2 pitch went under the glove of diving shortstop\r Yunel  Escobar. James  Jones  then  tripled over  the  head  of right  fielder\r Kevin Kiermaier, who was playing shallow, to make it a 3-0 advantage.\r \r</P>\r<P>\r Robinson  Cano was  walked on four pitches before Kyle Seager's two-run double\r to  right increased the  cushion to five for the Mariners, winners in seven of\r their last eight contests.\r \r</P>\r<P>\r Yoervis  Medina  (3-1) walked one  in the eighth inning  to earn the win after\r taking  over for  Seattle starter  Felix Hernandez.  King Felix  struck out  a\r career-high  15 batters  and allowed just four  hits in seven innings in a no-\r decision.\r \r</P>\r \r \r \r \r \r \r \r \r</body>\r<gamenotes>\r</gamenotes>\r<time_stamp> June 8, 2014, at 05:00 PM ET </time_stamp>\r</message>\r
\ No newline at end of file