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     tasty                       >= 0.8,
  91     tasty-hunit                 >= 0.8,
  92     time                        >= 1.4,
  93     transformers                >= 0.3,
  94     tuple                       >= 0.2
  95
  96   main-is:
  97     Main.hs
  98
  99   hs-source-dirs:
 100     src/
 101
 102   other-modules:
 103     Backend
 104     CommandLine
 105     Configuration
 106     ConnectionString
 107     ExitCodes
 108     OptionalConfiguration
 109     TSN.Codegen
 110     TSN.Database
 111     TSN.DbImport
 112     TSN.Parse
 113     TSN.Picklers
 114     TSN.XmlImport
 115     TSN.XML.AutoRacingSchedule
 116     TSN.XML.GameInfo
 117     TSN.XML.Heartbeat
 118     TSN.XML.Injuries
 119     TSN.XML.InjuriesDetail
 120     TSN.XML.News
 121     TSN.XML.Odds
 122     TSN.XML.Scores
 123     TSN.XML.SportInfo
 124     TSN.XML.Weather
 125     Xml
 126
 127   ghc-options:
 128     -Wall
 129     -fwarn-hi-shadowing
 130     -fwarn-missing-signatures
 131     -fwarn-name-shadowing
 132     -fwarn-orphans
 133     -fwarn-type-defaults
 134     -fwarn-tabs
 135     -fwarn-incomplete-record-updates
 136     -fwarn-monomorphism-restriction
 137     -fwarn-unused-do-bind
 138     -O2
 139
 140   ghc-prof-options:
 141     -prof
 142     -fprof-auto
 143     -fprof-cafs
 144     -- The following unbreak profiling with template haskell. We have
 145     -- to build the program twice; once without profile and again with
 146     -- these flags.
 147     -hisuf hi_p
 148     -osuf o_p
 149
 150
 151 test-suite testsuite
 152   type: exitcode-stdio-1.0
 153   hs-source-dirs: src test
 154   main-is: TestSuite.hs
 155   build-depends:
 156     base                        >= 4.6 && < 5,
 157     cmdargs                     >= 0.10.6,
 158     configurator                >= 0.2,
 159     directory                   >= 1.2,
 160     filepath                    >= 1.3,
 161     hslogger                    >= 1.2,
 162     htsn-common                 >= 0.0.1,
 163     hxt                         >= 9.3,
 164     groundhog                   >= 0.5,
 165     groundhog-postgresql        >= 0.5,
 166     groundhog-sqlite            >= 0.5,
 167     groundhog-th                >= 0.5,
 168     MissingH                    >= 1.2,
 169     old-locale                  >= 1,
 170     tasty                       >= 0.8,
 171     tasty-hunit                 >= 0.8,
 172     time                        >= 1.4,
 173     transformers                >= 0.3,
 174     tuple                       >= 0.2
 175
 176   -- It's not entirely clear to me why I have to reproduce all of this.
 177   ghc-options:
 178     -Wall
 179     -fwarn-hi-shadowing
 180     -fwarn-missing-signatures
 181     -fwarn-name-shadowing
 182     -fwarn-orphans
 183     -fwarn-type-defaults
 184     -fwarn-tabs
 185     -fwarn-incomplete-record-updates
 186     -fwarn-monomorphism-restriction
 187     -fwarn-unused-do-bind
 188     -O2
 189
 190
 191 test-suite doctests
 192   type: exitcode-stdio-1.0
 193   hs-source-dirs: test
 194   main-is: Doctests.hs
 195   build-depends:
 196     base      >= 4.6 && < 5,
 197     -- Additional test dependencies.
 198     doctest   >= 0.9
 199
 200   -- It's not entirely clear to me why I have to reproduce all of this.
 201   ghc-options:
 202     -Wall
 203     -fwarn-hi-shadowing
 204     -fwarn-missing-signatures
 205     -fwarn-name-shadowing
 206     -fwarn-orphans
 207     -fwarn-type-defaults
 208     -fwarn-tabs
 209     -fwarn-incomplete-record-updates
 210     -fwarn-monomorphism-restriction
 211     -fwarn-unused-do-bind
 212     -rtsopts
 213     -threaded
 214     -optc-O3
 215     -optc-march=native
 216     -O2
 217
 218
 219 -- These won't work without shelltestrunner installed in your
 220 -- $PATH. Maybe there is some way to tell Cabal that.
 221 test-suite shelltests
 222   type: exitcode-stdio-1.0
 223   hs-source-dirs: test
 224   main-is: ShellTests.hs
 225
 226   build-depends:
 227     base                        >= 4.6 && < 5,
 228     cmdargs                     >= 0.10.6,
 229     configurator                >= 0.2,
 230     directory                   >= 1.2,
 231     filepath                    >= 1.3,
 232     hslogger                    >= 1.2,
 233     htsn-common                 >= 0.0.1,
 234     hxt                         >= 9.3,
 235     groundhog                   >= 0.5,
 236     groundhog-postgresql        >= 0.5,
 237     groundhog-sqlite            >= 0.5,
 238     groundhog-th                >= 0.5,
 239     MissingH                    >= 1.2,
 240     old-locale                  >= 1,
 241     process                     >= 1.1,
 242     tasty                       >= 0.8,
 243     tasty-hunit                 >= 0.8,
 244     time                        >= 1.4,
 245     transformers                >= 0.3,
 246     tuple                       >= 0.2
 247
 248
 249
 250 source-repository head
 251   type: git
 252   location: http://michael.orlitzky.com/git/htsn-import.git
 253   branch: master