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