htsn-import.cabal

   1 name:           htsn-import
   2 version:        0.0.5
   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                        >= 4.6 && < 5,
  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     groundhog                   >= 0.5,
  85     groundhog-postgresql        >= 0.5,
  86     groundhog-sqlite            >= 0.5,
  87     groundhog-th                >= 0.5,
  88     MissingH                    >= 1.2,
  89     old-locale                  >= 1,
  90     split                       >= 0.2,
  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.Parse
 114     TSN.Picklers
 115     TSN.XmlImport
 116     TSN.XML.AutoRacingResults
 117     TSN.XML.AutoRacingSchedule
 118     TSN.XML.GameInfo
 119     TSN.XML.Heartbeat
 120     TSN.XML.Injuries
 121     TSN.XML.InjuriesDetail
 122     TSN.XML.News
 123     TSN.XML.Odds
 124     TSN.XML.Scores
 125     TSN.XML.SportInfo
 126     TSN.XML.Weather
 127     Xml
 128
 129   ghc-options:
 130     -Wall
 131     -fwarn-hi-shadowing
 132     -fwarn-missing-signatures
 133     -fwarn-name-shadowing
 134     -fwarn-orphans
 135     -fwarn-type-defaults
 136     -fwarn-tabs
 137     -fwarn-incomplete-record-updates
 138     -fwarn-monomorphism-restriction
 139     -fwarn-unused-do-bind
 140     -O2
 141
 142   ghc-prof-options:
 143     -prof
 144     -fprof-auto
 145     -fprof-cafs
 146     -- The following unbreak profiling with template haskell. We have
 147     -- to build the program twice; once without profile and again with
 148     -- these flags.
 149     -hisuf hi_p
 150     -osuf o_p
 151
 152
 153 test-suite testsuite
 154   type: exitcode-stdio-1.0
 155   hs-source-dirs: src test
 156   main-is: TestSuite.hs
 157   build-depends:
 158     base                        >= 4.6 && < 5,
 159     cmdargs                     >= 0.10.6,
 160     configurator                >= 0.2,
 161     directory                   >= 1.2,
 162     filepath                    >= 1.3,
 163     hslogger                    >= 1.2,
 164     htsn-common                 >= 0.0.1,
 165     hxt                         >= 9.3,
 166     groundhog                   >= 0.5,
 167     groundhog-postgresql        >= 0.5,
 168     groundhog-sqlite            >= 0.5,
 169     groundhog-th                >= 0.5,
 170     MissingH                    >= 1.2,
 171     old-locale                  >= 1,
 172     split                       >= 0.2,
 173     tasty                       >= 0.8,
 174     tasty-hunit                 >= 0.8,
 175     time                        >= 1.4,
 176     transformers                >= 0.3,
 177     tuple                       >= 0.2
 178
 179   -- It's not entirely clear to me why I have to reproduce all of this.
 180   ghc-options:
 181     -Wall
 182     -fwarn-hi-shadowing
 183     -fwarn-missing-signatures
 184     -fwarn-name-shadowing
 185     -fwarn-orphans
 186     -fwarn-type-defaults
 187     -fwarn-tabs
 188     -fwarn-incomplete-record-updates
 189     -fwarn-monomorphism-restriction
 190     -fwarn-unused-do-bind
 191     -O2
 192
 193
 194 test-suite doctests
 195   type: exitcode-stdio-1.0
 196   hs-source-dirs: test
 197   main-is: Doctests.hs
 198   build-depends:
 199     base      >= 4.6 && < 5,
 200     -- Additional test dependencies.
 201     doctest   >= 0.9
 202
 203   -- It's not entirely clear to me why I have to reproduce all of this.
 204   ghc-options:
 205     -Wall
 206     -fwarn-hi-shadowing
 207     -fwarn-missing-signatures
 208     -fwarn-name-shadowing
 209     -fwarn-orphans
 210     -fwarn-type-defaults
 211     -fwarn-tabs
 212     -fwarn-incomplete-record-updates
 213     -fwarn-monomorphism-restriction
 214     -fwarn-unused-do-bind
 215     -rtsopts
 216     -threaded
 217     -optc-O3
 218     -optc-march=native
 219     -O2
 220
 221
 222 -- These won't work without shelltestrunner installed in your
 223 -- $PATH. Maybe there is some way to tell Cabal that.
 224 test-suite shelltests
 225   type: exitcode-stdio-1.0
 226   hs-source-dirs: test
 227   main-is: ShellTests.hs
 228
 229   build-depends:
 230     base                        >= 4.6 && < 5,
 231     cmdargs                     >= 0.10.6,
 232     configurator                >= 0.2,
 233     directory                   >= 1.2,
 234     filepath                    >= 1.3,
 235     hslogger                    >= 1.2,
 236     htsn-common                 >= 0.0.1,
 237     hxt                         >= 9.3,
 238     groundhog                   >= 0.5,
 239     groundhog-postgresql        >= 0.5,
 240     groundhog-sqlite            >= 0.5,
 241     groundhog-th                >= 0.5,
 242     MissingH                    >= 1.2,
 243     old-locale                  >= 1,
 244     split                       >= 0.2,
 245     process                     >= 1.1,
 246     tasty                       >= 0.8,
 247     tasty-hunit                 >= 0.8,
 248     time                        >= 1.4,
 249     transformers                >= 0.3,
 250     tuple                       >= 0.2
 251
 252
 253
 254 source-repository head
 255   type: git
 256   location: http://michael.orlitzky.com/git/htsn-import.git
 257   branch: master