htsn-import.cabal

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