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/CBASK_3PPctXML/*.xml
  23   schemagen/Cbask_All_Tourn_Teams_XML/*.xml
  24   schemagen/CBASK_AssistsXML/*.xml
  25   schemagen/Cbask_Awards_XML/*.xml
  26   schemagen/CBASK_BlocksXML/*.xml
  27   schemagen/Cbask_Conf_Standings_XML/*.xml
  28   schemagen/Cbask_DivII_III_Indv_Stats_XML/*.xml
  29   schemagen/Cbask_DivIII_Team_Stats_XML/*.xml
  30   schemagen/Cbask_DivII_Team_Stats_XML/*.xml
  31   schemagen/CBASK_FGPctXML/*.xml
  32   schemagen/CBASK_FoulsXML/*.xml
  33   schemagen/CBASK_FTPctXML/*.xml
  34   schemagen/Cbask_Indv_Scoring_XML/*.xml
  35   schemagen/CBASK_Lineup_XML/*.xml
  36   schemagen/CBASK_MinutesXML/*.xml
  37   schemagen/Cbask_Polls_XML/*.xml
  38   schemagen/cbaskpreviewxml/*.xml
  39   schemagen/CBASK_ReboundsXML/*.xml
  40   schemagen/CBASK_ScoringLeadersXML/*.xml
  41   schemagen/Cbask_Team_ThreePT_Made_XML/*.xml
  42   schemagen/Cbask_Team_ThreePT_PCT_XML/*.xml
  43   schemagen/Cbask_Team_Win_Pct_XML/*.xml
  44   schemagen/CBASK_TopTwentyFiveResult_XML/*.xml
  45   schemagen/Cbask_Top_Twenty_Five_XML/*.xml
  46   schemagen/Cbask_Tourn_Awards_XML/*.xml
  47   schemagen/Cbask_Tourn_Champs_XML/*.xml
  48   schemagen/Cbask_Tourn_Indiv_XML/*.xml
  49   schemagen/Cbask_Tourn_Leaders_XML/*.xml
  50   schemagen/Cbask_Tourn_MVP_XML/*.xml
  51   schemagen/Cbask_Tourn_Records_XML/*.xml
  52   schemagen/cflpreviewxml/*.xml
  53   schemagen/Heartbeat/*.xml
  54   schemagen/Injuries_Detail_XML/*.xml
  55   schemagen/injuriesxml/*.xml
  56   schemagen/jfilexml/*.xml
  57   schemagen/LeagueScheduleXML/*.xml
  58   schemagen/Matchup_NBA_NHL_XML/*.xml
  59   schemagen/Minor_Baseball_League_Leaders_XML/*.xml
  60   schemagen/Minor_Baseball_Standings_XML/*.xml
  61   schemagen/Minor_Baseball_Transactions_XML/*.xml
  62   schemagen/minorscoresxml/*.xml
  63   schemagen/mlbbattingavgxml/*.xml
  64   schemagen/mlbdoublesleadersxml/*.xml
  65   schemagen/MLB_ERA_Leaders/*.xml
  66   schemagen/MLB_Fielding_XML/*.xml
  67   schemagen/MLBGamesPlayedXML/*.xml
  68   schemagen/MLB_Gaming_Matchup_XML/*.xml
  69   schemagen/MLBGIDPXML/*.xml
  70   schemagen/MLBHitByPitchXML/*.xml
  71   schemagen/mlbhitsleadersxml/*.xml
  72   schemagen/mlbhomerunsxml/*.xml
  73   schemagen/MLBHRFreqXML/*.xml
  74   schemagen/MLBIntWalksXML/*.xml
  75   schemagen/MLBKORateXML/*.xml
  76   schemagen/MLB_Lineup_XML/*.xml
  77   schemagen/MLB_Matchup_XML/*.xml
  78   schemagen/mlbonbasepctxml/*.xml
  79   schemagen/MLBOPSXML/*.xml
  80   schemagen/MLB_Pitching_Appearances_Leaders/*.xml
  81   schemagen/MLB_Pitching_Balks_Leaders/*.xml
  82   schemagen/MLB_Pitching_CG_Leaders/*.xml
  83   schemagen/MLB_Pitching_ER_Allowed_Leaders/*.xml
  84   schemagen/MLB_Pitching_Hit_Batters_Leaders/*.xml
  85   schemagen/MLB_Pitching_Hits_Allowed_Leaders/*.xml
  86   schemagen/MLB_Pitching_HR_Allowed_Leaders/*.xml
  87   schemagen/MLB_Pitching_IP_Leaders/*.xml
  88   schemagen/MLB_Pitching_Runs_Allowed_Leaders/*.xml
  89   schemagen/MLB_Pitching_Saves_Leaders/*.xml
  90   schemagen/MLB_Pitching_Shut_Outs_Leaders/*.xml
  91   schemagen/MLB_Pitching_Starts_Leaders/*.xml
  92   schemagen/MLB_Pitching_Strike_Outs_Leaders/*.xml
  93   schemagen/MLB_Pitching_Walks_Leaders/*.xml
  94   schemagen/MLB_Pitching_WHIP_Leaders/*.xml
  95   schemagen/MLB_Pitching_Wild_Pitches_Leaders/*.xml
  96   schemagen/MLB_Pitching_Win_Percentage_Leaders/*.xml
  97   schemagen/MLB_Pitching_WL_Leaders/*.xml
  98   schemagen/MLBPlateAppsXML/*.xml
  99   schemagen/mlbpreviewxml/*.xml
 100   schemagen/mlbrbisxml/*.xml
 101   schemagen/mlbrunsleadersxml/*.xml
 102   schemagen/MLBSacFliesXML/*.xml
 103   schemagen/MLBSacrificesXML/*.xml
 104   schemagen/MLBSBSuccessXML/*.xml
 105   schemagen/mlbsluggingpctxml/*.xml
 106   schemagen/mlbstandxml/*.xml
 107   schemagen/mlbstandxml_preseason/*.xml
 108   schemagen/mlbstolenbasexml/*.xml
 109   schemagen/mlbtotalbasesleadersxml/*.xml
 110   schemagen/mlbtriplesleadersxml/*.xml
 111   schemagen/MLBWalkRateXML/*.xml
 112   schemagen/mlbwalksleadersxml/*.xml
 113   schemagen/MLBXtraBaseHitsXML/*.xml
 114   schemagen/MLS_Preview_XML/*.xml
 115   schemagen/NBA3PPctXML/*.xml
 116   schemagen/NBAAssistsXML/*.xml
 117   schemagen/NBABlocksXML/*.xml
 118   schemagen/nbaconfrecxml/*.xml
 119   schemagen/nbadaysxml/*.xml
 120   schemagen/nbadivisionsxml/*.xml
 121   schemagen/NBAFGPctXML/*.xml
 122   schemagen/NBAFoulsXML/*.xml
 123   schemagen/NBAFTPctXML/*.xml
 124   schemagen/NBA_Gaming_Matchup_XML/*.xml
 125   schemagen/NBALineupXML/*.xml
 126   schemagen/NBAMinutesXML/*.xml
 127   schemagen/NBA_Playoff_Matchup_XML/*.xml
 128   schemagen/nbapreviewxml/*.xml
 129   schemagen/NBAReboundsXML/*.xml
 130   schemagen/NBAScorersXML/*.xml
 131   schemagen/nbastandxml/*.xml
 132   schemagen/NBAStealsXML/*.xml
 133   schemagen/nbateamleadersxml/*.xml
 134   schemagen/NBA_Team_Stats_XML/*.xml
 135   schemagen/nbatripledoublexml/*.xml
 136   schemagen/NBATurnoversXML/*.xml
 137   schemagen/NCAA_Conference_Schedule_XML/*.xml
 138   schemagen/NCAA_FB_Preview_XML/*.xml
 139   schemagen/newsxml/*.xml
 140   schemagen/nflfirstdownxml/*.xml
 141   schemagen/NFLFumbleLeaderXML/*.xml
 142   schemagen/NFLGiveTakeXML/*.xml
 143   schemagen/NFLInside20XML/*.xml
 144   schemagen/NFL_KickingLeaders_XML/*.xml
 145   schemagen/NFLKickoffsXML/*.xml
 146   schemagen/NFLMondayNightXML/*.xml
 147   schemagen/NFL_NBA_Draft_XML/*.xml
 148   schemagen/NFL_NCAA_FB_Matchup_XML/*.xml
 149   schemagen/NFLPassLeadXML/*.xml
 150   schemagen/nflpreviewxml/*.xml
 151   schemagen/NFLQBStartsXML/*.xml
 152   schemagen/NFL_Roster_XML/*.xml
 153   schemagen/NFLSackLeadersXML/*.xml
 154   schemagen/nflstandxml/*.xml
 155   schemagen/NFLTeamRankingsXML/*.xml
 156   schemagen/NFL_Team_Stats_XML/*.xml
 157   schemagen/NFLTopPerformanceXML/*.xml
 158   schemagen/NFLTotalYardageXML/*.xml
 159   schemagen/nhlpreviewxml/*.xml
 160   schemagen/Odds_XML/*.xml
 161   schemagen/recapxml/*.xml
 162   schemagen/scoresxml/*.xml
 163   schemagen/Transactions_XML/*.xml
 164   schemagen/weatherxml/*.xml
 165   schemagen/Weekly_Sched_XML/*.xml
 166   schemagen/WNBA3PPctXML/*.xml
 167   schemagen/WNBAAssistsXML/*.xml
 168   schemagen/WNBABlocksXML/*.xml
 169   schemagen/WNBAFGPctXML/*.xml
 170   schemagen/WNBAFoulsXML/*.xml
 171   schemagen/WNBAFTPctXML/*.xml
 172   schemagen/WNBAMinutesXML/*.xml
 173   schemagen/WNBAReboundsXML/*.xml
 174   schemagen/WNBAScorersXML/*.xml
 175   schemagen/wnbastandxml/*.xml
 176   schemagen/WNBAStealsXML/*.xml
 177   schemagen/WNBA_Team_Leaders_XML/*.xml
 178   schemagen/WNBATurnoversXML/*.xml
 179   schemagen/WorldBaseballPreviewXML/*.xml
 180   test/shell/*.test
 181   test/xml/*.xml
 182   test/xml/*.dtd
 183 synopsis:
 184   Import XML files from The Sports Network into an RDBMS.
 185 description:
 186   /Usage/:
 187   .
 188   @
 189   htsn-import [OPTIONS] [FILES]
 190   @
 191   .
 192   The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
 193   containing various sports news and statistics. Our sister program
 194   /htsn/ is capable of retrieving the feed and saving the individual
 195   XML documents contained therein. But what to do with them?
 196   .
 197   The purpose of /htsn-import/ is to take these XML documents and
 198   get them into something we can use, a relational database management
 199   system (RDBMS), loosely known as a SQL database. The structure of
 200   relational database, is, well, relational, and the feed XML is not. So
 201   there is some work to do before the data can be inserted.
 202   .
 203   First, we must parse the XML. Each supported document type (see below)
 204   has a full pickle/unpickle implementation (\"pickle\" is simply a
 205   synonym for serialize here). That means that we parse the entire
 206   document into a data structure, and if we pickle (serialize) that data
 207   structure, we get the exact same XML document tha we started with.
 208   .
 209   This is important for two reasons. First, it serves as a second level
 210   of validation. The first validation is performed by the XML parser,
 211   but if that succeeds and unpicking fails, we know that something is
 212   fishy. Second, we don't ever want to be surprised by some new element
 213   or attribute showing up in the XML. The fact that we can unpickle the
 214   whole thing now means that we won't be surprised in the future.
 215   .
 216   The aforementioned feature is especially important because we
 217   automatically migrate the database schema every time we import a
 218   document. If you attempt to import a \"newsxml.dtd\" document, all
 219   database objects relating to the news will be created if they do not
 220   exist. We don't want the schema to change out from under us without
 221   warning, so it's important that no XML be parsed that would result in
 222   a different schema than we had previously. Since we can
 223   pickle/unpickle everything already, this should be impossible.
 224   .
 225   Examples and usage documentation are available in the man page.
 226
 227 executable htsn-import
 228   build-depends:
 229     base                        >= 4.6 && < 5,
 230     cmdargs                     >= 0.10.6,
 231     configurator                >= 0.2,
 232     directory                   >= 1.2,
 233     filepath                    >= 1.3,
 234     hslogger                    >= 1.2,
 235     htsn-common                 >= 0.0.1,
 236     hxt                         >= 9.3,
 237     groundhog                   >= 0.5,
 238     groundhog-postgresql        >= 0.5,
 239     groundhog-sqlite            >= 0.5,
 240     groundhog-th                >= 0.5,
 241     MissingH                    >= 1.2,
 242     old-locale                  >= 1,
 243     split                       >= 0.2,
 244     tasty                       >= 0.8,
 245     tasty-hunit                 >= 0.8,
 246     time                        >= 1.4,
 247     transformers                >= 0.3,
 248     tuple                       >= 0.2
 249
 250   main-is:
 251     Main.hs
 252
 253   hs-source-dirs:
 254     src/
 255
 256   other-modules:
 257     Backend
 258     CommandLine
 259     Configuration
 260     ConnectionString
 261     ExitCodes
 262     OptionalConfiguration
 263     TSN.Codegen
 264     TSN.Database
 265     TSN.DbImport
 266     TSN.Parse
 267     TSN.Picklers
 268     TSN.Team
 269     TSN.XmlImport
 270     TSN.XML.AutoRacingResults
 271     TSN.XML.AutoRacingSchedule
 272     TSN.XML.GameInfo
 273     TSN.XML.Heartbeat
 274     TSN.XML.Injuries
 275     TSN.XML.InjuriesDetail
 276     TSN.XML.JFile
 277     TSN.XML.News
 278     TSN.XML.Odds
 279     TSN.XML.Scores
 280     TSN.XML.SportInfo
 281     TSN.XML.Weather
 282     Xml
 283
 284   ghc-options:
 285     -Wall
 286     -fwarn-hi-shadowing
 287     -fwarn-missing-signatures
 288     -fwarn-name-shadowing
 289     -fwarn-orphans
 290     -fwarn-type-defaults
 291     -fwarn-tabs
 292     -fwarn-incomplete-record-updates
 293     -fwarn-monomorphism-restriction
 294     -fwarn-unused-do-bind
 295     -O2
 296
 297   ghc-prof-options:
 298     -prof
 299     -fprof-auto
 300     -fprof-cafs
 301     -- The following unbreak profiling with template haskell. We have
 302     -- to build the program twice; once without profile and again with
 303     -- these flags.
 304     -hisuf hi_p
 305     -osuf o_p
 306
 307
 308 test-suite testsuite
 309   type: exitcode-stdio-1.0
 310   hs-source-dirs: src test
 311   main-is: TestSuite.hs
 312   build-depends:
 313     base                        >= 4.6 && < 5,
 314     cmdargs                     >= 0.10.6,
 315     configurator                >= 0.2,
 316     directory                   >= 1.2,
 317     filepath                    >= 1.3,
 318     hslogger                    >= 1.2,
 319     htsn-common                 >= 0.0.1,
 320     hxt                         >= 9.3,
 321     groundhog                   >= 0.5,
 322     groundhog-postgresql        >= 0.5,
 323     groundhog-sqlite            >= 0.5,
 324     groundhog-th                >= 0.5,
 325     MissingH                    >= 1.2,
 326     old-locale                  >= 1,
 327     split                       >= 0.2,
 328     tasty                       >= 0.8,
 329     tasty-hunit                 >= 0.8,
 330     time                        >= 1.4,
 331     transformers                >= 0.3,
 332     tuple                       >= 0.2
 333
 334   -- It's not entirely clear to me why I have to reproduce all of this.
 335   ghc-options:
 336     -Wall
 337     -fwarn-hi-shadowing
 338     -fwarn-missing-signatures
 339     -fwarn-name-shadowing
 340     -fwarn-orphans
 341     -fwarn-type-defaults
 342     -fwarn-tabs
 343     -fwarn-incomplete-record-updates
 344     -fwarn-monomorphism-restriction
 345     -fwarn-unused-do-bind
 346     -O2
 347
 348
 349 test-suite doctests
 350   type: exitcode-stdio-1.0
 351   hs-source-dirs: test
 352   main-is: Doctests.hs
 353   build-depends:
 354     base      >= 4.6 && < 5,
 355     -- Additional test dependencies.
 356     doctest   >= 0.9
 357
 358   -- It's not entirely clear to me why I have to reproduce all of this.
 359   ghc-options:
 360     -Wall
 361     -fwarn-hi-shadowing
 362     -fwarn-missing-signatures
 363     -fwarn-name-shadowing
 364     -fwarn-orphans
 365     -fwarn-type-defaults
 366     -fwarn-tabs
 367     -fwarn-incomplete-record-updates
 368     -fwarn-monomorphism-restriction
 369     -fwarn-unused-do-bind
 370     -rtsopts
 371     -threaded
 372     -optc-O3
 373     -optc-march=native
 374     -O2
 375
 376
 377 -- These won't work without shelltestrunner installed in your
 378 -- $PATH. Maybe there is some way to tell Cabal that.
 379 test-suite shelltests
 380   type: exitcode-stdio-1.0
 381   hs-source-dirs: test
 382   main-is: ShellTests.hs
 383
 384   build-depends:
 385     base                        >= 4.6 && < 5,
 386     cmdargs                     >= 0.10.6,
 387     configurator                >= 0.2,
 388     directory                   >= 1.2,
 389     filepath                    >= 1.3,
 390     hslogger                    >= 1.2,
 391     htsn-common                 >= 0.0.1,
 392     hxt                         >= 9.3,
 393     groundhog                   >= 0.5,
 394     groundhog-postgresql        >= 0.5,
 395     groundhog-sqlite            >= 0.5,
 396     groundhog-th                >= 0.5,
 397     MissingH                    >= 1.2,
 398     old-locale                  >= 1,
 399     split                       >= 0.2,
 400     process                     >= 1.1,
 401     tasty                       >= 0.8,
 402     tasty-hunit                 >= 0.8,
 403     time                        >= 1.4,
 404     transformers                >= 0.3,
 405     tuple                       >= 0.2
 406
 407
 408
 409 source-repository head
 410   type: git
 411   location: http://michael.orlitzky.com/git/htsn-import.git
 412   branch: master