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