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