htsn-import.cabal

   1 name:           htsn-import
   2 version:        0.0.3
   3 cabal-version:  >= 1.8
   4 author:         Michael Orlitzky
   5 maintainer:     Michael Orlitzky <michael@orlitzky.com>
   6 category:       Utils
   7 license:        GPL-3
   8 license-file:   doc/LICENSE
   9 build-type:     Simple
  10 extra-source-files:
  11   doc/dbschema/*.png
  12   doc/htsn-importrc.example
  13   doc/man1/htsn-import.1
  14   doc/README.dbschema
  15   doc/README.schemagen
  16   doc/TODO
  17   makefile
  18   schema/*.dtd
  19   schemagen/Auto_Racing_Schedule_XML/*.xml
  20   schemagen/Heartbeat/*.xml
  21   schemagen/injuriesxml/*.xml
  22   schemagen/Injuries_Detail_XML/*.xml
  23   schemagen/newsxml/*.xml
  24   schemagen/Odds_XML/*.xml
  25   schemagen/weatherxml/*.xml
  26   test/shell/*.test
  27   test/xml/*.xml
  28   test/xml/*.dtd
  29 synopsis:
  30   Import XML files from The Sports Network into an RDBMS.
  31 description:
  32   /Usage/:
  33   .
  34   @
  35   htsn-import [OPTIONS] [FILES]
  36   @
  37   .
  38   The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
  39   containing various sports news and statistics. Our sister program
  40   /htsn/ is capable of retrieving the feed and saving the individual
  41   XML documents contained therein. But what to do with them?
  42   .
  43   The purpose of /htsn-import/ is to take these XML documents and
  44   get them into something we can use, a relational database management
  45   system (RDBMS), loosely known as a SQL database. The structure of
  46   relational database, is, well, relational, and the feed XML is not. So
  47   there is some work to do before the data can be inserted.
  48   .
  49   First, we must parse the XML. Each supported document type (see below)
  50   has a full pickle/unpickle implementation (\"pickle\" is simply a
  51   synonym for serialize here). That means that we parse the entire
  52   document into a data structure, and if we pickle (serialize) that data
  53   structure, we get the exact same XML document tha we started with.
  54   .
  55   This is important for two reasons. First, it serves as a second level
  56   of validation. The first validation is performed by the XML parser,
  57   but if that succeeds and unpicking fails, we know that something is
  58   fishy. Second, we don't ever want to be surprised by some new element
  59   or attribute showing up in the XML. The fact that we can unpickle the
  60   whole thing now means that we won't be surprised in the future.
  61   .
  62   The aforementioned feature is especially important because we
  63   automatically migrate the database schema every time we import a
  64   document. If you attempt to import a \"newsxml.dtd\" document, all
  65   database objects relating to the news will be created if they do not
  66   exist. We don't want the schema to change out from under us without
  67   warning, so it's important that no XML be parsed that would result in
  68   a different schema than we had previously. Since we can
  69   pickle/unpickle everything already, this should be impossible.
  70   .
  71   Examples and usage documentation are available in the man page.
  72
  73 executable htsn-import
  74   build-depends:
  75     base                        == 4.*,
  76     cmdargs                     >= 0.10.6,
  77     configurator                == 0.2.*,
  78     directory                   == 1.2.*,
  79     filepath                    == 1.3.*,
  80     hslogger                    == 1.2.*,
  81     htsn-common                 == 0.0.1,
  82     hxt                         == 9.3.*,
  83     groundhog                   == 0.4.*,
  84     groundhog-postgresql        == 0.4.*,
  85     groundhog-sqlite            == 0.4.*,
  86     groundhog-th                == 0.4.*,
  87     MissingH                    == 1.2.*,
  88     old-locale                  == 1.0.*,
  89     tasty                       == 0.7.*,
  90     tasty-hunit                 == 0.4.*,
  91     time                        == 1.4.*,
  92     transformers                == 0.3.*,
  93     tuple                       == 0.2.*
  94
  95   main-is:
  96     Main.hs
  97
  98   hs-source-dirs:
  99     src/
 100
 101   other-modules:
 102     Backend
 103     CommandLine
 104     Configuration
 105     ConnectionString
 106     ExitCodes
 107     OptionalConfiguration
 108     TSN.Codegen
 109     TSN.Database
 110     TSN.DbImport
 111     TSN.Picklers
 112     TSN.XmlImport
 113     TSN.XML.AutoRacingSchedule
 114     TSN.XML.Heartbeat
 115     TSN.XML.Injuries
 116     TSN.XML.InjuriesDetail
 117     TSN.XML.News
 118     TSN.XML.Odds
 119     TSN.XML.Weather
 120     Xml
 121
 122   ghc-options:
 123     -Wall
 124     -fwarn-hi-shadowing
 125     -fwarn-missing-signatures
 126     -fwarn-name-shadowing
 127     -fwarn-orphans
 128     -fwarn-type-defaults
 129     -fwarn-tabs
 130     -fwarn-incomplete-record-updates
 131     -fwarn-monomorphism-restriction
 132     -fwarn-unused-do-bind
 133     -O2
 134
 135   ghc-prof-options:
 136     -prof
 137     -fprof-auto
 138     -fprof-cafs
 139     -- The following unbreak profiling with template haskell. We have
 140     -- to build the program twice; once without profile and again with
 141     -- these flags.
 142     -hisuf hi_p
 143     -osuf o_p
 144
 145
 146 test-suite testsuite
 147   type: exitcode-stdio-1.0
 148   hs-source-dirs: src test
 149   main-is: TestSuite.hs
 150   build-depends:
 151     base                        == 4.*,
 152     cmdargs                     >= 0.10.6,
 153     configurator                == 0.2.*,
 154     directory                   == 1.2.*,
 155     filepath                    == 1.3.*,
 156     hslogger                    == 1.2.*,
 157     htsn-common                 == 0.0.1,
 158     hxt                         == 9.3.*,
 159     groundhog                   == 0.4.*,
 160     groundhog-postgresql        == 0.4.*,
 161     groundhog-sqlite            == 0.4.*,
 162     groundhog-th                == 0.4.*,
 163     MissingH                    == 1.2.*,
 164     old-locale                  == 1.0.*,
 165     tasty                       == 0.7.*,
 166     tasty-hunit                 == 0.4.*,
 167     time                        == 1.4.*,
 168     transformers                == 0.3.*,
 169     tuple                       == 0.2.*
 170
 171   -- It's not entirely clear to me why I have to reproduce all of this.
 172   ghc-options:
 173     -Wall
 174     -fwarn-hi-shadowing
 175     -fwarn-missing-signatures
 176     -fwarn-name-shadowing
 177     -fwarn-orphans
 178     -fwarn-type-defaults
 179     -fwarn-tabs
 180     -fwarn-incomplete-record-updates
 181     -fwarn-monomorphism-restriction
 182     -fwarn-unused-do-bind
 183     -O2
 184
 185
 186 test-suite doctests
 187   type: exitcode-stdio-1.0
 188   hs-source-dirs: test
 189   main-is: Doctests.hs
 190   build-depends:
 191     base      == 4.*,
 192     -- Additional test dependencies.
 193     doctest   == 0.9.*
 194
 195   -- It's not entirely clear to me why I have to reproduce all of this.
 196   ghc-options:
 197     -Wall
 198     -fwarn-hi-shadowing
 199     -fwarn-missing-signatures
 200     -fwarn-name-shadowing
 201     -fwarn-orphans
 202     -fwarn-type-defaults
 203     -fwarn-tabs
 204     -fwarn-incomplete-record-updates
 205     -fwarn-monomorphism-restriction
 206     -fwarn-unused-do-bind
 207     -rtsopts
 208     -threaded
 209     -optc-O3
 210     -optc-march=native
 211     -O2
 212
 213
 214 -- These won't work without shelltestrunner installed in your
 215 -- $PATH. Maybe there is some way to tell Cabal that.
 216 test-suite shelltests
 217   type: exitcode-stdio-1.0
 218   hs-source-dirs: test
 219   main-is: ShellTests.hs
 220
 221   build-depends:
 222     base                        == 4.*,
 223     cmdargs                     >= 0.10.6,
 224     configurator                == 0.2.*,
 225     directory                   == 1.2.*,
 226     filepath                    == 1.3.*,
 227     hslogger                    == 1.2.*,
 228     htsn-common                 == 0.0.1,
 229     hxt                         == 9.3.*,
 230     groundhog                   == 0.4.*,
 231     groundhog-postgresql        == 0.4.*,
 232     groundhog-sqlite            == 0.4.*,
 233     groundhog-th                == 0.4.*,
 234     MissingH                    == 1.2.*,
 235     old-locale                  == 1.0.*,
 236     process                     == 1.1.*,
 237     tasty                       == 0.7.*,
 238     tasty-hunit                 == 0.4.*,
 239     time                        == 1.4.*,
 240     transformers                == 0.3.*,
 241     tuple                       == 0.2.*
 242
 243
 244
 245 source-repository head
 246   type: git
 247   location: http://michael.orlitzky.com/git/htsn-import.git
 248   branch: master