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