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