htsn-import.cabal

   1 name:           htsn-import
   2 version:        0.0.4
   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/scoresxml/*.xml
  26   schemagen/weatherxml/*.xml
  27   test/shell/*.test
  28   test/xml/*.xml
  29   test/xml/*.dtd
  30 synopsis:
  31   Import XML files from The Sports Network into an RDBMS.
  32 description:
  33   /Usage/:
  34   .
  35   @
  36   htsn-import [OPTIONS] [FILES]
  37   @
  38   .
  39   The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
  40   containing various sports news and statistics. Our sister program
  41   /htsn/ is capable of retrieving the feed and saving the individual
  42   XML documents contained therein. But what to do with them?
  43   .
  44   The purpose of /htsn-import/ is to take these XML documents and
  45   get them into something we can use, a relational database management
  46   system (RDBMS), loosely known as a SQL database. The structure of
  47   relational database, is, well, relational, and the feed XML is not. So
  48   there is some work to do before the data can be inserted.
  49   .
  50   First, we must parse the XML. Each supported document type (see below)
  51   has a full pickle/unpickle implementation (\"pickle\" is simply a
  52   synonym for serialize here). That means that we parse the entire
  53   document into a data structure, and if we pickle (serialize) that data
  54   structure, we get the exact same XML document tha we started with.
  55   .
  56   This is important for two reasons. First, it serves as a second level
  57   of validation. The first validation is performed by the XML parser,
  58   but if that succeeds and unpicking fails, we know that something is
  59   fishy. Second, we don't ever want to be surprised by some new element
  60   or attribute showing up in the XML. The fact that we can unpickle the
  61   whole thing now means that we won't be surprised in the future.
  62   .
  63   The aforementioned feature is especially important because we
  64   automatically migrate the database schema every time we import a
  65   document. If you attempt to import a \"newsxml.dtd\" document, all
  66   database objects relating to the news will be created if they do not
  67   exist. We don't want the schema to change out from under us without
  68   warning, so it's important that no XML be parsed that would result in
  69   a different schema than we had previously. Since we can
  70   pickle/unpickle everything already, this should be impossible.
  71   .
  72   Examples and usage documentation are available in the man page.
  73
  74 executable htsn-import
  75   build-depends:
  76     base                        == 4.*,
  77     cmdargs                     >= 0.10.6,
  78     configurator                == 0.2.*,
  79     directory                   == 1.2.*,
  80     filepath                    == 1.3.*,
  81     hslogger                    == 1.2.*,
  82     htsn-common                 == 0.0.1,
  83     hxt                         == 9.3.*,
  84    -- deleteAll showed up in 0.4.1
  85     groundhog                   >= 0.4.1,
  86     groundhog-postgresql        == 0.4.*,
  87     groundhog-sqlite            == 0.4.*,
  88     groundhog-th                == 0.4.*,
  89     MissingH                    == 1.2.*,
  90     old-locale                  == 1.0.*,
  91     tasty                       == 0.8.*,
  92     tasty-hunit                 == 0.8.*,
  93     time                        == 1.4.*,
  94     transformers                == 0.3.*,
  95     tuple                       == 0.2.*
  96
  97   main-is:
  98     Main.hs
  99
 100   hs-source-dirs:
 101     src/
 102
 103   other-modules:
 104     Backend
 105     CommandLine
 106     Configuration
 107     ConnectionString
 108     ExitCodes
 109     OptionalConfiguration
 110     TSN.Codegen
 111     TSN.Database
 112     TSN.DbImport
 113     TSN.Picklers
 114     TSN.XmlImport
 115     TSN.XML.AutoRacingSchedule
 116     TSN.XML.Heartbeat
 117     TSN.XML.Injuries
 118     TSN.XML.InjuriesDetail
 119     TSN.XML.News
 120     TSN.XML.Odds
 121     TSN.XML.Scores
 122     TSN.XML.Weather
 123     Xml
 124
 125   ghc-options:
 126     -Wall
 127     -fwarn-hi-shadowing
 128     -fwarn-missing-signatures
 129     -fwarn-name-shadowing
 130     -fwarn-orphans
 131     -fwarn-type-defaults
 132     -fwarn-tabs
 133     -fwarn-incomplete-record-updates
 134     -fwarn-monomorphism-restriction
 135     -fwarn-unused-do-bind
 136     -O2
 137
 138   ghc-prof-options:
 139     -prof
 140     -fprof-auto
 141     -fprof-cafs
 142     -- The following unbreak profiling with template haskell. We have
 143     -- to build the program twice; once without profile and again with
 144     -- these flags.
 145     -hisuf hi_p
 146     -osuf o_p
 147
 148
 149 test-suite testsuite
 150   type: exitcode-stdio-1.0
 151   hs-source-dirs: src test
 152   main-is: TestSuite.hs
 153   build-depends:
 154     base                        == 4.*,
 155     cmdargs                     >= 0.10.6,
 156     configurator                == 0.2.*,
 157     directory                   == 1.2.*,
 158     filepath                    == 1.3.*,
 159     hslogger                    == 1.2.*,
 160     htsn-common                 == 0.0.1,
 161     hxt                         == 9.3.*,
 162     groundhog                   == 0.4.*,
 163     groundhog-postgresql        == 0.4.*,
 164     groundhog-sqlite            == 0.4.*,
 165     groundhog-th                == 0.4.*,
 166     MissingH                    == 1.2.*,
 167     old-locale                  == 1.0.*,
 168     tasty                       == 0.8.*,
 169     tasty-hunit                 == 0.8.*,
 170     time                        == 1.4.*,
 171     transformers                == 0.3.*,
 172     tuple                       == 0.2.*
 173
 174   -- It's not entirely clear to me why I have to reproduce all of this.
 175   ghc-options:
 176     -Wall
 177     -fwarn-hi-shadowing
 178     -fwarn-missing-signatures
 179     -fwarn-name-shadowing
 180     -fwarn-orphans
 181     -fwarn-type-defaults
 182     -fwarn-tabs
 183     -fwarn-incomplete-record-updates
 184     -fwarn-monomorphism-restriction
 185     -fwarn-unused-do-bind
 186     -O2
 187
 188
 189 test-suite doctests
 190   type: exitcode-stdio-1.0
 191   hs-source-dirs: test
 192   main-is: Doctests.hs
 193   build-depends:
 194     base      == 4.*,
 195     -- Additional test dependencies.
 196     doctest   == 0.9.*
 197
 198   -- It's not entirely clear to me why I have to reproduce all of this.
 199   ghc-options:
 200     -Wall
 201     -fwarn-hi-shadowing
 202     -fwarn-missing-signatures
 203     -fwarn-name-shadowing
 204     -fwarn-orphans
 205     -fwarn-type-defaults
 206     -fwarn-tabs
 207     -fwarn-incomplete-record-updates
 208     -fwarn-monomorphism-restriction
 209     -fwarn-unused-do-bind
 210     -rtsopts
 211     -threaded
 212     -optc-O3
 213     -optc-march=native
 214     -O2
 215
 216
 217 -- These won't work without shelltestrunner installed in your
 218 -- $PATH. Maybe there is some way to tell Cabal that.
 219 test-suite shelltests
 220   type: exitcode-stdio-1.0
 221   hs-source-dirs: test
 222   main-is: ShellTests.hs
 223
 224   build-depends:
 225     base                        == 4.*,
 226     cmdargs                     >= 0.10.6,
 227     configurator                == 0.2.*,
 228     directory                   == 1.2.*,
 229     filepath                    == 1.3.*,
 230     hslogger                    == 1.2.*,
 231     htsn-common                 == 0.0.1,
 232     hxt                         == 9.3.*,
 233     groundhog                   == 0.4.*,
 234     groundhog-postgresql        == 0.4.*,
 235     groundhog-sqlite            == 0.4.*,
 236     groundhog-th                == 0.4.*,
 237     MissingH                    == 1.2.*,
 238     old-locale                  == 1.0.*,
 239     process                     == 1.1.*,
 240     tasty                       == 0.8.*,
 241     tasty-hunit                 == 0.8.*,
 242     time                        == 1.4.*,
 243     transformers                == 0.3.*,
 244     tuple                       == 0.2.*
 245
 246
 247
 248 source-repository head
 249   type: git
 250   location: http://michael.orlitzky.com/git/htsn-import.git
 251   branch: master