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