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.Database
 105     TSN.DbImport
 106     TSN.Picklers
 107     TSN.XmlImport
 108     TSN.XML.Heartbeat
 109     TSN.XML.Injuries
 110     TSN.XML.InjuriesDetail
 111     TSN.XML.News
 112     TSN.XML.Odds
 113     TSN.XML.Weather
 114     Xml
 115
 116   ghc-options:
 117     -Wall
 118     -fwarn-hi-shadowing
 119     -fwarn-missing-signatures
 120     -fwarn-name-shadowing
 121     -fwarn-orphans
 122     -fwarn-type-defaults
 123     -fwarn-tabs
 124     -fwarn-incomplete-record-updates
 125     -fwarn-monomorphism-restriction
 126     -fwarn-unused-do-bind
 127     -rtsopts
 128     -threaded
 129     -optc-O3
 130     -optc-march=native
 131     -O2
 132
 133   ghc-prof-options:
 134     -prof
 135     -fprof-auto
 136     -fprof-cafs
 137     -- The following unbreak profiling with template haskell. We have
 138     -- to build the program twice; once without profile and again with
 139     -- these flags.
 140     -hisuf hi_p
 141     -osuf o_p
 142
 143
 144 test-suite testsuite
 145   type: exitcode-stdio-1.0
 146   hs-source-dirs: src test
 147   main-is: TestSuite.hs
 148   build-depends:
 149     base                        == 4.*,
 150     cmdargs                     >= 0.10.6,
 151     configurator                == 0.2.*,
 152     directory                   == 1.2.*,
 153     filepath                    == 1.3.*,
 154     hslogger                    == 1.2.*,
 155     htsn-common                 == 0.0.1,
 156     hxt                         == 9.3.*,
 157     groundhog                   == 0.4.*,
 158     groundhog-postgresql        == 0.4.*,
 159     groundhog-sqlite            == 0.4.*,
 160     groundhog-th                == 0.4.*,
 161     MissingH                    == 1.2.*,
 162     old-locale                  == 1.0.*,
 163     tasty                       == 0.7.*,
 164     tasty-hunit                 == 0.4.*,
 165     time                        == 1.4.*,
 166     transformers                == 0.3.*,
 167     tuple                       == 0.2.*
 168
 169   -- It's not entirely clear to me why I have to reproduce all of this.
 170   ghc-options:
 171     -Wall
 172     -fwarn-hi-shadowing
 173     -fwarn-missing-signatures
 174     -fwarn-name-shadowing
 175     -fwarn-orphans
 176     -fwarn-type-defaults
 177     -fwarn-tabs
 178     -fwarn-incomplete-record-updates
 179     -fwarn-monomorphism-restriction
 180     -fwarn-unused-do-bind
 181     -rtsopts
 182     -threaded
 183     -optc-O3
 184     -optc-march=native
 185     -O2
 186
 187
 188 test-suite doctests
 189   type: exitcode-stdio-1.0
 190   hs-source-dirs: test
 191   main-is: Doctests.hs
 192   build-depends:
 193     base      == 4.*,
 194     -- Additional test dependencies.
 195     doctest   == 0.9.*
 196
 197   -- It's not entirely clear to me why I have to reproduce all of this.
 198   ghc-options:
 199     -Wall
 200     -fwarn-hi-shadowing
 201     -fwarn-missing-signatures
 202     -fwarn-name-shadowing
 203     -fwarn-orphans
 204     -fwarn-type-defaults
 205     -fwarn-tabs
 206     -fwarn-incomplete-record-updates
 207     -fwarn-monomorphism-restriction
 208     -fwarn-unused-do-bind
 209     -rtsopts
 210     -threaded
 211     -optc-O3
 212     -optc-march=native
 213     -O2
 214
 215
 216 source-repository head
 217   type: git
 218   location: http://michael.orlitzky.com/git/htsn-import.git
 219   branch: master