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.development
  16   doc/README.schemagen
  17   doc/TODO
  18   makefile
  19   schema/*.dtd
  20   schemagen/Auto_Racing_Schedule_XML/*.xml
  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/scoresxml/*.xml
  27   schemagen/weatherxml/*.xml
  28   test/shell/*.test
  29   test/xml/*.xml
  30   test/xml/*.dtd
  31 synopsis:
  32   Import XML files from The Sports Network into an RDBMS.
  33 description:
  34   /Usage/:
  35   .
  36   @
  37   htsn-import [OPTIONS] [FILES]
  38   @
  39   .
  40   The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
  41   containing various sports news and statistics. Our sister program
  42   /htsn/ is capable of retrieving the feed and saving the individual
  43   XML documents contained therein. But what to do with them?
  44   .
  45   The purpose of /htsn-import/ is to take these XML documents and
  46   get them into something we can use, a relational database management
  47   system (RDBMS), loosely known as a SQL database. The structure of
  48   relational database, is, well, relational, and the feed XML is not. So
  49   there is some work to do before the data can be inserted.
  50   .
  51   First, we must parse the XML. Each supported document type (see below)
  52   has a full pickle/unpickle implementation (\"pickle\" is simply a
  53   synonym for serialize here). That means that we parse the entire
  54   document into a data structure, and if we pickle (serialize) that data
  55   structure, we get the exact same XML document tha we started with.
  56   .
  57   This is important for two reasons. First, it serves as a second level
  58   of validation. The first validation is performed by the XML parser,
  59   but if that succeeds and unpicking fails, we know that something is
  60   fishy. Second, we don't ever want to be surprised by some new element
  61   or attribute showing up in the XML. The fact that we can unpickle the
  62   whole thing now means that we won't be surprised in the future.
  63   .
  64   The aforementioned feature is especially important because we
  65   automatically migrate the database schema every time we import a
  66   document. If you attempt to import a \"newsxml.dtd\" document, all
  67   database objects relating to the news will be created if they do not
  68   exist. We don't want the schema to change out from under us without
  69   warning, so it's important that no XML be parsed that would result in
  70   a different schema than we had previously. Since we can
  71   pickle/unpickle everything already, this should be impossible.
  72   .
  73   Examples and usage documentation are available in the man page.
  74
  75 executable htsn-import
  76   build-depends:
  77     base                        >= 4.6 && < 5,
  78     cmdargs                     >= 0.10.6,
  79     configurator                >= 0.2,
  80     directory                   >= 1.2,
  81     filepath                    >= 1.3,
  82     hslogger                    >= 1.2,
  83     htsn-common                 >= 0.0.1,
  84     hxt                         >= 9.3,
  85     groundhog                   >= 0.5,
  86     groundhog-postgresql        >= 0.5,
  87     groundhog-sqlite            >= 0.5,
  88     groundhog-th                >= 0.5,
  89     MissingH                    >= 1.2,
  90     old-locale                  >= 1,
  91     split                       >= 0.2,
  92     tasty                       >= 0.8,
  93     tasty-hunit                 >= 0.8,
  94     time                        >= 1.4,
  95     transformers                >= 0.3,
  96     tuple                       >= 0.2
  97
  98   main-is:
  99     Main.hs
 100
 101   hs-source-dirs:
 102     src/
 103
 104   other-modules:
 105     Backend
 106     CommandLine
 107     Configuration
 108     ConnectionString
 109     ExitCodes
 110     OptionalConfiguration
 111     TSN.Codegen
 112     TSN.Database
 113     TSN.DbImport
 114     TSN.Parse
 115     TSN.Picklers
 116     TSN.XmlImport
 117     TSN.XML.AutoRacingResults
 118     TSN.XML.AutoRacingSchedule
 119     TSN.XML.GameInfo
 120     TSN.XML.Heartbeat
 121     TSN.XML.Injuries
 122     TSN.XML.InjuriesDetail
 123     TSN.XML.News
 124     TSN.XML.Odds
 125     TSN.XML.Scores
 126     TSN.XML.SportInfo
 127     TSN.XML.Weather
 128     Xml
 129
 130   ghc-options:
 131     -Wall
 132     -fwarn-hi-shadowing
 133     -fwarn-missing-signatures
 134     -fwarn-name-shadowing
 135     -fwarn-orphans
 136     -fwarn-type-defaults
 137     -fwarn-tabs
 138     -fwarn-incomplete-record-updates
 139     -fwarn-monomorphism-restriction
 140     -fwarn-unused-do-bind
 141     -O2
 142
 143   ghc-prof-options:
 144     -prof
 145     -fprof-auto
 146     -fprof-cafs
 147     -- The following unbreak profiling with template haskell. We have
 148     -- to build the program twice; once without profile and again with
 149     -- these flags.
 150     -hisuf hi_p
 151     -osuf o_p
 152
 153
 154 test-suite testsuite
 155   type: exitcode-stdio-1.0
 156   hs-source-dirs: src test
 157   main-is: TestSuite.hs
 158   build-depends:
 159     base                        >= 4.6 && < 5,
 160     cmdargs                     >= 0.10.6,
 161     configurator                >= 0.2,
 162     directory                   >= 1.2,
 163     filepath                    >= 1.3,
 164     hslogger                    >= 1.2,
 165     htsn-common                 >= 0.0.1,
 166     hxt                         >= 9.3,
 167     groundhog                   >= 0.5,
 168     groundhog-postgresql        >= 0.5,
 169     groundhog-sqlite            >= 0.5,
 170     groundhog-th                >= 0.5,
 171     MissingH                    >= 1.2,
 172     old-locale                  >= 1,
 173     split                       >= 0.2,
 174     tasty                       >= 0.8,
 175     tasty-hunit                 >= 0.8,
 176     time                        >= 1.4,
 177     transformers                >= 0.3,
 178     tuple                       >= 0.2
 179
 180   -- It's not entirely clear to me why I have to reproduce all of this.
 181   ghc-options:
 182     -Wall
 183     -fwarn-hi-shadowing
 184     -fwarn-missing-signatures
 185     -fwarn-name-shadowing
 186     -fwarn-orphans
 187     -fwarn-type-defaults
 188     -fwarn-tabs
 189     -fwarn-incomplete-record-updates
 190     -fwarn-monomorphism-restriction
 191     -fwarn-unused-do-bind
 192     -O2
 193
 194
 195 test-suite doctests
 196   type: exitcode-stdio-1.0
 197   hs-source-dirs: test
 198   main-is: Doctests.hs
 199   build-depends:
 200     base      >= 4.6 && < 5,
 201     -- Additional test dependencies.
 202     doctest   >= 0.9
 203
 204   -- It's not entirely clear to me why I have to reproduce all of this.
 205   ghc-options:
 206     -Wall
 207     -fwarn-hi-shadowing
 208     -fwarn-missing-signatures
 209     -fwarn-name-shadowing
 210     -fwarn-orphans
 211     -fwarn-type-defaults
 212     -fwarn-tabs
 213     -fwarn-incomplete-record-updates
 214     -fwarn-monomorphism-restriction
 215     -fwarn-unused-do-bind
 216     -rtsopts
 217     -threaded
 218     -optc-O3
 219     -optc-march=native
 220     -O2
 221
 222
 223 -- These won't work without shelltestrunner installed in your
 224 -- $PATH. Maybe there is some way to tell Cabal that.
 225 test-suite shelltests
 226   type: exitcode-stdio-1.0
 227   hs-source-dirs: test
 228   main-is: ShellTests.hs
 229
 230   build-depends:
 231     base                        >= 4.6 && < 5,
 232     cmdargs                     >= 0.10.6,
 233     configurator                >= 0.2,
 234     directory                   >= 1.2,
 235     filepath                    >= 1.3,
 236     hslogger                    >= 1.2,
 237     htsn-common                 >= 0.0.1,
 238     hxt                         >= 9.3,
 239     groundhog                   >= 0.5,
 240     groundhog-postgresql        >= 0.5,
 241     groundhog-sqlite            >= 0.5,
 242     groundhog-th                >= 0.5,
 243     MissingH                    >= 1.2,
 244     old-locale                  >= 1,
 245     split                       >= 0.2,
 246     process                     >= 1.1,
 247     tasty                       >= 0.8,
 248     tasty-hunit                 >= 0.8,
 249     time                        >= 1.4,
 250     transformers                >= 0.3,
 251     tuple                       >= 0.2
 252
 253
 254
 255 source-repository head
 256   type: git
 257   location: http://michael.orlitzky.com/git/htsn-import.git
 258   branch: master