htsn-import.cabal

   1 name:           htsn-import
   2 version:        0.0.1
   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/htsnrc-import.example
  12   doc/man1/htsn-import.1
  13   makefile
  14   test/xml/*.xml
  15   schema/*.dtd
  16   schemagen/*/*.xml
  17 synopsis:
  18   Import XML files from The Sports Network into an RDBMS.
  19 description:
  20   /Usage/:
  21   .
  22   @
  23   htsn-import [OPTIONS] [FILES]
  24   @
  25   .
  26   The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
  27   containing various sports news and statistics. Our sister program
  28   /htsn/ is capable of retrieving the feed and saving the individual
  29   XML documents contained therein. But what to do with them?
  30   .
  31   The purpose of /htsn-import/ is to take these XML documents and
  32   get them into something we can use, a relational database management
  33   system (RDBMS), loosely known as a SQL database. The structure of
  34   relational database, is, well, relational, and the feed XML is not. So
  35   there is some work to do before the data can be inserted.
  36   .
  37   First, we must parse the XML. Each supported document type (see below)
  38   has a full pickle/unpickle implementation (\"pickle\" is simply a
  39   synonym for serialize here). That means that we parse the entire
  40   document into a data structure, and if we pickle (serialize) that data
  41   structure, we get the exact same XML document tha we started with.
  42   .
  43   This is important for two reasons. First, it serves as a second level
  44   of validation. The first validation is performed by the XML parser,
  45   but if that succeeds and unpicking fails, we know that something is
  46   fishy. Second, we don't ever want to be surprised by some new element
  47   or attribute showing up in the XML. The fact that we can unpickle the
  48   whole thing now means that we won't be surprised in the future.
  49   .
  50   The aforementioned feature is especially important because we
  51   automatically migrate the database schema every time we import a
  52   document. If you attempt to import a \"newsxml.dtd\" document, all
  53   database objects relating to the news will be created if they do not
  54   exist. We don't want the schema to change out from under us without
  55   warning, so it's important that no XML be parsed that would result in
  56   a different schema than we had previously. Since we can
  57   pickle/unpickle everything already, this should be impossible.
  58   .
  59   Examples and usage documentation are available in the man page.
  60
  61 executable htsn-import
  62   build-depends:
  63     base                        == 4.*,
  64     cmdargs                     >= 0.10.6,
  65     configurator                == 0.2.*,
  66     directory                   == 1.2.*,
  67     filepath                    == 1.3.*,
  68     hslogger                    == 1.2.*,
  69     htsn-common                 == 0.0.1,
  70     hxt                         == 9.3.*,
  71     groundhog                   == 0.4.*,
  72     groundhog-postgresql        == 0.4.*,
  73     groundhog-sqlite            == 0.4.*,
  74     groundhog-th                == 0.4.*,
  75     MissingH                    == 1.2.*,
  76     old-locale                  == 1.0.*,
  77     tasty                       == 0.7.*,
  78     tasty-hunit                 == 0.4.*,
  79     time                        == 1.4.*,
  80     transformers                == 0.3.*,
  81     tuple                       == 0.2.*
  82
  83   main-is:
  84     Main.hs
  85
  86   hs-source-dirs:
  87     src/
  88
  89   other-modules:
  90     Backend
  91     CommandLine
  92     Configuration
  93     ConnectionString
  94     ExitCodes
  95     OptionalConfiguration
  96     TSN.Codegen
  97     TSN.DbImport
  98     TSN.Picklers
  99     TSN.XmlImport
 100     TSN.XML.Heartbeat
 101     TSN.XML.Injuries
 102     TSN.XML.InjuriesDetail
 103     TSN.XML.News
 104     TSN.XML.Odds
 105     Xml
 106
 107   ghc-options:
 108     -Wall
 109     -fwarn-hi-shadowing
 110     -fwarn-missing-signatures
 111     -fwarn-name-shadowing
 112     -fwarn-orphans
 113     -fwarn-type-defaults
 114     -fwarn-tabs
 115     -fwarn-incomplete-record-updates
 116     -fwarn-monomorphism-restriction
 117     -fwarn-unused-do-bind
 118     -rtsopts
 119     -threaded
 120     -optc-O3
 121     -optc-march=native
 122     -O2
 123
 124   ghc-prof-options:
 125     -prof
 126     -fprof-auto
 127     -fprof-cafs
 128     -- The following unbreak profiling with template haskell. We have
 129     -- to build the program twice; once without profile and again with
 130     -- these flags.
 131     -hisuf hi_p
 132     -osuf o_p
 133
 134
 135 test-suite testsuite
 136   type: exitcode-stdio-1.0
 137   hs-source-dirs: src test
 138   main-is: TestSuite.hs
 139   build-depends:
 140     base                        == 4.*,
 141     cmdargs                     >= 0.10.6,
 142     configurator                == 0.2.*,
 143     directory                   == 1.2.*,
 144     filepath                    == 1.3.*,
 145     hslogger                    == 1.2.*,
 146     htsn-common                 == 0.0.1,
 147     hxt                         == 9.3.*,
 148     groundhog                   == 0.4.*,
 149     groundhog-postgresql        == 0.4.*,
 150     groundhog-sqlite            == 0.4.*,
 151     groundhog-th                == 0.4.*,
 152     MissingH                    == 1.2.*,
 153     old-locale                  == 1.0.*,
 154     tasty                       == 0.7.*,
 155     tasty-hunit                 == 0.4.*,
 156     time                        == 1.4.*,
 157     transformers                == 0.3.*,
 158     tuple                       == 0.2.*
 159
 160   -- It's not entirely clear to me why I have to reproduce all of this.
 161   ghc-options:
 162     -Wall
 163     -fwarn-hi-shadowing
 164     -fwarn-missing-signatures
 165     -fwarn-name-shadowing
 166     -fwarn-orphans
 167     -fwarn-type-defaults
 168     -fwarn-tabs
 169     -fwarn-incomplete-record-updates
 170     -fwarn-monomorphism-restriction
 171     -fwarn-unused-do-bind
 172     -rtsopts
 173     -threaded
 174     -optc-O3
 175     -optc-march=native
 176     -O2
 177
 178
 179 test-suite doctests
 180   type: exitcode-stdio-1.0
 181   hs-source-dirs: test
 182   main-is: Doctests.hs
 183   build-depends:
 184     base      == 4.*,
 185     -- Additional test dependencies.
 186     doctest   == 0.9.*
 187
 188   -- It's not entirely clear to me why I have to reproduce all of this.
 189   ghc-options:
 190     -Wall
 191     -fwarn-hi-shadowing
 192     -fwarn-missing-signatures
 193     -fwarn-name-shadowing
 194     -fwarn-orphans
 195     -fwarn-type-defaults
 196     -fwarn-tabs
 197     -fwarn-incomplete-record-updates
 198     -fwarn-monomorphism-restriction
 199     -fwarn-unused-do-bind
 200     -rtsopts
 201     -threaded
 202     -optc-O3
 203     -optc-march=native
 204     -O2
 205
 206
 207 source-repository head
 208   type: git
 209   location: http://michael.orlitzky.com/git/htsn-import.git
 210   branch: master