X-Git-Url: http://gitweb.michael.orlitzky.com/?a=blobdiff_plain;f=htsn-import.cabal;h=fd9a17c65d92904fc67b2748f5b71b13d469ca88;hb=1ea954f7e3d673b427368575d4873d968faee0e3;hp=362beac36ef73d053f313ad5737f8a22bb2f8509;hpb=04f468994697d4d983a09a8e612948b23a973848;p=dead%2Fhtsn-import.git

diff --git a/htsn-import.cabal b/htsn-import.cabal
index 362beac..fd9a17c 100644
--- a/htsn-import.cabal
+++ b/htsn-import.cabal
@@ -7,10 +7,66 @@ category:       Utils
 license:        GPL-3
 license-file:   doc/LICENSE
 build-type:     Simple
+extra-source-files:
+  doc/dbschema/*.png
+  doc/htsn-importrc.example
+  doc/man1/htsn-import.1
+  doc/README.dbschema
+  doc/README.schemagen
+  doc/TODO
+  makefile
+  test/xml/*.xml
+  test/xml/*.dtd
+  schema/*.dtd
+  schemagen/Heartbeat/*.xml
+  schemagen/injuriesxml/*.xml
+  schemagen/Injuries_Detail_XML/*.xml
+  schemagen/newsxml/*.xml
+  schemagen/Odds_XML/*.xml
+  schemagen/weatherxml/*.xml
 synopsis:
   Import XML files from The Sports Network into an RDBMS.
 description:
-  Import XML files from The Sports Network into an RDBMS.
+  /Usage/:
+  .
+  @
+  htsn-import [OPTIONS] [FILES]
+  @
+  .
+  The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
+  containing various sports news and statistics. Our sister program
+  /htsn/ is capable of retrieving the feed and saving the individual
+  XML documents contained therein. But what to do with them?
+  .
+  The purpose of /htsn-import/ is to take these XML documents and
+  get them into something we can use, a relational database management
+  system (RDBMS), loosely known as a SQL database. The structure of
+  relational database, is, well, relational, and the feed XML is not. So
+  there is some work to do before the data can be inserted.
+  .
+  First, we must parse the XML. Each supported document type (see below)
+  has a full pickle/unpickle implementation (\"pickle\" is simply a
+  synonym for serialize here). That means that we parse the entire
+  document into a data structure, and if we pickle (serialize) that data
+  structure, we get the exact same XML document tha we started with.
+  .
+  This is important for two reasons. First, it serves as a second level
+  of validation. The first validation is performed by the XML parser,
+  but if that succeeds and unpicking fails, we know that something is
+  fishy. Second, we don't ever want to be surprised by some new element
+  or attribute showing up in the XML. The fact that we can unpickle the
+  whole thing now means that we won't be surprised in the future.
+  .
+  The aforementioned feature is especially important because we
+  automatically migrate the database schema every time we import a
+  document. If you attempt to import a \"newsxml.dtd\" document, all
+  database objects relating to the news will be created if they do not
+  exist. We don't want the schema to change out from under us without
+  warning, so it's important that no XML be parsed that would result in
+  a different schema than we had previously. Since we can
+  pickle/unpickle everything already, this should be impossible.
+  .
+  Examples and usage documentation are available in the man page.
 
 executable htsn-import
   build-depends:
@@ -40,6 +96,26 @@ executable htsn-import
   hs-source-dirs:
     src/
 
+  other-modules:
+    Backend
+    CommandLine
+    Configuration
+    ConnectionString
+    ExitCodes
+    OptionalConfiguration
+    TSN.Codegen
+    TSN.Database
+    TSN.DbImport
+    TSN.Picklers
+    TSN.XmlImport
+    TSN.XML.Heartbeat
+    TSN.XML.Injuries
+    TSN.XML.InjuriesDetail
+    TSN.XML.News
+    TSN.XML.Odds
+    TSN.XML.Weather
+    Xml
+
   ghc-options:
     -Wall
     -fwarn-hi-shadowing
@@ -59,8 +135,13 @@ executable htsn-import
 
   ghc-prof-options:
     -prof
-    -auto-all
-    -caf-all
+    -fprof-auto
+    -fprof-cafs
+    -- The following unbreak profiling with template haskell. We have
+    -- to build the program twice; once without profile and again with
+    -- these flags.
+    -hisuf hi_p
+    -osuf o_p
 
 
 test-suite testsuite
@@ -107,6 +188,34 @@ test-suite testsuite
     -O2
 
 
+test-suite doctests
+  type: exitcode-stdio-1.0
+  hs-source-dirs: test
+  main-is: Doctests.hs
+  build-depends:
+    base      == 4.*,
+    -- Additional test dependencies.
+    doctest   == 0.9.*
+
+  -- It's not entirely clear to me why I have to reproduce all of this.
+  ghc-options:
+    -Wall
+    -fwarn-hi-shadowing
+    -fwarn-missing-signatures
+    -fwarn-name-shadowing
+    -fwarn-orphans
+    -fwarn-type-defaults
+    -fwarn-tabs
+    -fwarn-incomplete-record-updates
+    -fwarn-monomorphism-restriction
+    -fwarn-unused-do-bind
+    -rtsopts
+    -threaded
+    -optc-O3
+    -optc-march=native
+    -O2
+
+
 source-repository head
   type: git
   location: http://michael.orlitzky.com/git/htsn-import.git