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