X-Git-Url: http://gitweb.michael.orlitzky.com/?a=blobdiff_plain;f=src%2FXml.hs;h=d4ea4679cef1bafc974e7d9eede7249b39957491;hb=928a90109375caaa888ae4413151b560838948b7;hp=129c6e9cebe4236b7af99a7988c168b662eefb44;hpb=988f693ce7f1abb6566e75d539ac312b627c31d5;p=dead%2Fhtsn-import.git

diff --git a/src/Xml.hs b/src/Xml.hs
index 129c6e9..d4ea467 100644
--- a/src/Xml.hs
+++ b/src/Xml.hs
@@ -1,71 +1,191 @@
+{-# LANGUAGE FlexibleContexts #-}
+{-# LANGUAGE TypeFamilies #-}
+
 -- | General XML stuff.
 --
 module Xml (
+  Child(..),
+  DtdName(..),
+  FromXml(..),
+  FromXmlFk(..),
+  ToDb(..),
   parse_opts,
-  pickle_unpickle )
+  parse_opts_novalidate,
+  pickle_unpickle,
+  unpickleable,
+  unsafe_read_document,
+  unsafe_read_invalid_document,
+  unsafe_unpickle )
 where
 
+-- System imports.
+import Control.Exception ( SomeException(..), catch )
+import Database.Groundhog.Core ( PersistEntity(..) )
 import Text.XML.HXT.Core (
   (>>>),
   (/>),
+  PU,
   SysConfigList,
-  XmlPickler(..),
-  hasName,
+  XmlTree,
+  isElem,
   no,
   readDocument,
   runX,
-  withPreserveComment,
   withRemoveWS,
   withSubstDTDEntities,
   withValidate,
   xpickleVal,
+  xunpickleDocument,
   xunpickleVal,
   yes )
 
+
+
+-- | Common associated type shared by 'FromXml' and 'FromXmlFk'. This
+--   basically just forces the client to define the \"database
+--   version\" of his type.
+--
+class ToDb a where
+  -- | Each instance @a@ must declare its associated database type @Db a@.
+  type Db a :: *
+
+-- | A typeclass for XML types that can be converted into an
+--   associated database type. The story behind this is long, but
+--   basically, we need to different types most XML thingies we're
+--   going to import: a database type and an XML type.
+--
+--   Both Groundhog and HXT are very particular about the types that
+--   they can use, and there's no way to reuse e.g. a type that HXT
+--   can pickle in Groundhog. This typeclass gives us a standard way
+--   to get the database type from the XML type that we have to define
+--   for HXT.
+--
+class (ToDb a) => FromXml a where
+  -- | A function for getting a @Db a@ out of an @a@.
+  from_xml :: a -> Db a
+
+
+-- | A class for XML representations which are children of other
+--   elements. The foal is to associate a child XML element with its
+--   parent element's database type. This is required to construct the
+--   database analogue of @a@ in 'FromXmlFk'.
+--
+class Child a where
+  -- | The type of our parent object, i.e. to the type to whom our
+  --   foreign key will point.
+  type Parent a :: *
+
+
+-- | Some database types cannot be constructed from the XML type
+--   alone; they must be supplied a foreign key to a parent object
+--   first. Members of this class can be converted from an XML
+--   representation to a database representation in this manner.
+--
+class (Child a, ToDb a) => FromXmlFk a where
+  -- | The function that produces a @Db a@ out of a foreign key and an
+  --   @a@. The parameter order makes it easier to map this function
+  --   over a bunch of things.
+  from_xml_fk :: DefaultKey (Parent a) -> a -> Db a
+
+
+
+-- | Represents the DTD filename (\"SYSTEM\") part of the DOCTYPE
+--   definition.
+newtype DtdName = DtdName String
+
 -- | A list of options passed to 'readDocument' when we parse an XML
---   document. We don't validate because the DTDs from TSN are
---   wrong. As a result, we don't want to keep useless DTDs
---   areound. Thus we disable 'withSubstDTDEntities' which, when
---   combined with "withValidate no", prevents HXT from trying to read
---   the DTD at all.
+--   document. All cosmetic whitespace should be removed, otherwise we
+--   would have to parse whitespace in each (un)pickler.
 --
 parse_opts :: SysConfigList
-parse_opts =
-  [ withPreserveComment no,
-    withRemoveWS yes,
-    withSubstDTDEntities no,
-    withValidate no ]
+parse_opts = [ withRemoveWS yes,
+               withSubstDTDEntities no ]
+
+-- | Like 'parse_opts' except we don't validate the document against
+--   its DTD. This is useful when we need to parse a document that we
+--   /know/ is invalid so that we can deliver a better error message.
+--
+parse_opts_novalidate :: SysConfigList
+parse_opts_novalidate = (withValidate no) : parse_opts
 
 
--- | Given a root element name and a file path, return both the
---   original unpickled root "object" and the one that was constructed
---   by pickled and unpickling the original. This is used in a number
---   of XML tests which pickle/unpickle and then make sure that the
---   output is the same as the input.
+-- | Given an @unpickler@ and a @filepath@, attempt to unpickle the
+--   root element of @filepath@ using @unpickler@ and return both the
+--   original unpickled object and one constructed by pickling and
+--   unpickling that original. This is used in a number of XML tests
+--   which pickle/unpickle and then make sure that the output is the
+--   same as the input.
 --
 --   We return the object instead of an XmlTree (which would save us
 --   an unpickle call) because otherwise the type of @a@ in the call
 --   to 'xpickle' would be ambiguous. By returning some @a@s, we allow
 --   the caller to annotate its type.
 --
-pickle_unpickle :: XmlPickler a
-                => String
-                -> FilePath
+--   Note that this will happily pickle nothing to nothing and then
+--   unpickle it back to more nothing. So the fact that the
+--   before/after results from this function agree does not mean that
+--   the document was successfully unpickled!
+--
+pickle_unpickle :: PU a -- ^ @unpickler@ returning an @a@
+                -> FilePath -- ^ Path to the document to unpickle.
                 -> IO ([a], [a])
-pickle_unpickle root_element filepath = do
+pickle_unpickle unpickler filepath = do
   -- We need to check only the root message element since
   -- readDocument produces a bunch of other junk.
-    expected <- runX $ arr_getobj
+    expected <- runX arr_getobj
     actual <- runX $ arr_getobj
                      >>>
-                     xpickleVal xpickle
+                     xpickleVal unpickler
                      >>>
-                     xunpickleVal xpickle
+                     xunpickleVal unpickler
 
     return (expected, actual)
   where
     arr_getobj = readDocument parse_opts filepath
                    />
-                   hasName root_element
+                   isElem -- Drop the extra junk readDocument pulls in.
                    >>>
-                   xunpickleVal xpickle
+                   xunpickleVal unpickler
+
+
+
+-- | Is the given XML file unpickleable? Unpickling will be attempted
+--   using the @unpickler@ argument. If we unilaterally used the
+--   generic 'xpickle' function for our unpickler, a type ambiguity
+--   would result. By taking the unpickler as an argument, we allow
+--   the caller to indirectly specify a concrete type.
+--
+--   Apologies the the name; unpickleable means \"we can unpickle
+--   it\", not \"not pickleable.\"
+--
+unpickleable :: FilePath -> PU a -> IO Bool
+unpickleable filepath unpickler = do
+  xmldoc <- try_unpickle `catch` (\(SomeException _) -> return [])
+  return $ (not . null) xmldoc
+  where
+    try_unpickle = runX $ readDocument parse_opts filepath
+                          >>>
+                          xunpickleVal unpickler
+
+
+-- | Unpickle from a 'FilePath' using the given pickler. Explode if it
+--   doesn't work.
+--
+unsafe_unpickle :: FilePath -> PU a -> IO a
+unsafe_unpickle filepath unpickler =
+  fmap head $ runX $ xunpickleDocument unpickler parse_opts filepath
+
+
+-- | Read an XML document from a 'FilePath' into an XmlTree. Explode if it
+--   doesn't work.
+--
+unsafe_read_document :: FilePath -> IO XmlTree
+unsafe_read_document filepath =
+  fmap head $ runX $ readDocument parse_opts filepath
+
+-- | The same as 'unsafe_read_document', except it allows you to read
+--   documents which don't validate against their DTDs.
+--
+unsafe_read_invalid_document :: FilePath -> IO XmlTree
+unsafe_read_invalid_document filepath =
+  fmap head $ runX $ readDocument parse_opts_novalidate filepath