htsn-import.cabal

   1 name:           htsn-import
   2 version:        0.2.0
   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/CHANGES.database
  15   doc/README.development
  16   doc/TODO
  17   makefile
  18   schema/*.dtd
  19   schemagen/AutoRacingResultsXML/*.xml
  20   schemagen/Auto_Racing_Schedule_XML/*.xml
  21   schemagen/CBASK_3PPctXML/*.xml
  22   schemagen/Cbask_All_Tourn_Teams_XML/*.xml
  23   schemagen/CBASK_AssistsXML/*.xml
  24   schemagen/Cbask_Awards_XML/*.xml
  25   schemagen/CBASK_BlocksXML/*.xml
  26   schemagen/Cbask_Conf_Standings_XML/*.xml
  27   schemagen/Cbask_DivII_III_Indv_Stats_XML/*.xml
  28   schemagen/Cbask_DivIII_Team_Stats_XML/*.xml
  29   schemagen/Cbask_DivII_Team_Stats_XML/*.xml
  30   schemagen/CBASK_FGPctXML/*.xml
  31   schemagen/CBASK_FoulsXML/*.xml
  32   schemagen/CBASK_FTPctXML/*.xml
  33   schemagen/Cbask_Indv_No_Avg_XML/*.xml
  34   schemagen/Cbask_Indv_Scoring_XML/*.xml
  35   schemagen/Cbask_Indv_Shooting_XML/*.xml
  36   schemagen/CBASK_Lineup_XML/*.xml
  37   schemagen/CBASK_MinutesXML/*.xml
  38   schemagen/Cbask_Polls_XML/*.xml
  39   schemagen/cbaskpreviewxml/*.xml
  40   schemagen/CBASK_ReboundsXML/*.xml
  41   schemagen/CBASK_ScoringLeadersXML/*.xml
  42   schemagen/Cbask_Team_Scoring_Rebound_Margin_XML/*.xml
  43   schemagen/Cbask_Team_Scoring_XML/*.xml
  44   schemagen/Cbask_Team_Shooting_Pct_XML/*.xml
  45   schemagen/Cbask_Team_ThreePT_Made_XML/*.xml
  46   schemagen/Cbask_Team_ThreePT_PCT_XML/*.xml
  47   schemagen/Cbask_Team_Win_Pct_XML/*.xml
  48   schemagen/CBASK_TopTwentyFiveResult_XML/*.xml
  49   schemagen/Cbask_Top_Twenty_Five_XML/*.xml
  50   schemagen/Cbask_Tourn_Awards_XML/*.xml
  51   schemagen/Cbask_Tourn_Champs_XML/*.xml
  52   schemagen/Cbask_Tourn_Indiv_XML/*.xml
  53   schemagen/Cbask_Tourn_Leaders_XML/*.xml
  54   schemagen/Cbask_Tourn_MVP_XML/*.xml
  55   schemagen/Cbask_Tourn_Records_XML/*.xml
  56   schemagen/cflpreviewxml/*.xml
  57   schemagen/earlylineXML/*.xml
  58   schemagen/Heartbeat/*.xml
  59   schemagen/Injuries_Detail_XML/*.xml
  60   schemagen/injuriesxml/*.xml
  61   schemagen/jfilexml/*.xml
  62   schemagen/LeagueScheduleXML/*.xml
  63   schemagen/Matchup_NBA_NHL_XML/*.xml
  64   schemagen/Minor_Baseball_League_Leaders_XML/*.xml
  65   schemagen/Minor_Baseball_Standings_XML/*.xml
  66   schemagen/Minor_Baseball_Transactions_XML/*.xml
  67   schemagen/minorscoresxml/*.xml
  68   schemagen/mlbbattingavgxml/*.xml
  69   schemagen/mlbdoublesleadersxml/*.xml
  70   schemagen/MLB_Boxscore_XML/*.xml
  71   schemagen/MLB_ERA_Leaders/*.xml
  72   schemagen/MLB_Fielding_XML/*.xml
  73   schemagen/MLBGamesPlayedXML/*.xml
  74   schemagen/MLB_Gaming_Matchup_XML/*.xml
  75   schemagen/MLBGIDPXML/*.xml
  76   schemagen/MLBHitByPitchXML/*.xml
  77   schemagen/mlbhitsleadersxml/*.xml
  78   schemagen/mlbhomerunsxml/*.xml
  79   schemagen/MLBHRFreqXML/*.xml
  80   schemagen/MLBIntWalksXML/*.xml
  81   schemagen/MLBKORateXML/*.xml
  82   schemagen/MLB_Lineup_XML/*.xml
  83   schemagen/MLB_Matchup_XML/*.xml
  84   schemagen/mlbonbasepctxml/*.xml
  85   schemagen/MLBOPSXML/*.xml
  86   schemagen/MLB_earlylineXML/*.xml
  87   schemagen/MLB_Pitching_Appearances_Leaders/*.xml
  88   schemagen/MLB_Pitching_Balks_Leaders/*.xml
  89   schemagen/MLB_Pitching_CG_Leaders/*.xml
  90   schemagen/MLB_Pitching_ER_Allowed_Leaders/*.xml
  91   schemagen/MLB_Pitching_Hit_Batters_Leaders/*.xml
  92   schemagen/MLB_Pitching_Hits_Allowed_Leaders/*.xml
  93   schemagen/MLB_Pitching_HR_Allowed_Leaders/*.xml
  94   schemagen/MLB_Pitching_IP_Leaders/*.xml
  95   schemagen/MLB_Pitching_Runs_Allowed_Leaders/*.xml
  96   schemagen/MLB_Pitching_Saves_Leaders/*.xml
  97   schemagen/MLB_Pitching_Shut_Outs_Leaders/*.xml
  98   schemagen/MLB_Pitching_Starts_Leaders/*.xml
  99   schemagen/MLB_Pitching_Strike_Outs_Leaders/*.xml
 100   schemagen/MLB_Pitching_Walks_Leaders/*.xml
 101   schemagen/MLB_Pitching_WHIP_Leaders/*.xml
 102   schemagen/MLB_Pitching_Wild_Pitches_Leaders/*.xml
 103   schemagen/MLB_Pitching_Win_Percentage_Leaders/*.xml
 104   schemagen/MLB_Pitching_WL_Leaders/*.xml
 105   schemagen/MLBPlateAppsXML/*.xml
 106   schemagen/mlbpreviewxml/*.xml
 107   schemagen/mlbrbisxml/*.xml
 108   schemagen/mlbrunsleadersxml/*.xml
 109   schemagen/MLBSacFliesXML/*.xml
 110   schemagen/MLBSacrificesXML/*.xml
 111   schemagen/MLBSBSuccessXML/*.xml
 112   schemagen/mlbsluggingpctxml/*.xml
 113   schemagen/mlbstandxml/*.xml
 114   schemagen/mlbstandxml_preseason/*.xml
 115   schemagen/mlbstolenbasexml/*.xml
 116   schemagen/mlbtotalbasesleadersxml/*.xml
 117   schemagen/mlbtriplesleadersxml/*.xml
 118   schemagen/MLBWalkRateXML/*.xml
 119   schemagen/mlbwalksleadersxml/*.xml
 120   schemagen/MLBXtraBaseHitsXML/*.xml
 121   schemagen/MLS_Preview_XML/*.xml
 122   schemagen/NBA3PPctXML/*.xml
 123   schemagen/NBAAssistsXML/*.xml
 124   schemagen/NBABlocksXML/*.xml
 125   schemagen/nbaconfrecxml/*.xml
 126   schemagen/nbadaysxml/*.xml
 127   schemagen/nbadivisionsxml/*.xml
 128   schemagen/NBAFGPctXML/*.xml
 129   schemagen/NBAFoulsXML/*.xml
 130   schemagen/NBAFTPctXML/*.xml
 131   schemagen/NBA_Gaming_Matchup_XML/*.xml
 132   schemagen/NBALineupXML/*.xml
 133   schemagen/NBAMinutesXML/*.xml
 134   schemagen/NBA_Playoff_Matchup_XML/*.xml
 135   schemagen/nbapreviewxml/*.xml
 136   schemagen/NBAReboundsXML/*.xml
 137   schemagen/NBAScorersXML/*.xml
 138   schemagen/nbastandxml/*.xml
 139   schemagen/NBAStealsXML/*.xml
 140   schemagen/nbateamleadersxml/*.xml
 141   schemagen/NBA_Team_Stats_XML/*.xml
 142   schemagen/nbatripledoublexml/*.xml
 143   schemagen/NBATurnoversXML/*.xml
 144   schemagen/NCAA_Conference_Schedule_XML/*.xml
 145   schemagen/NCAA_FB_Preview_XML/*.xml
 146   schemagen/newsxml/*.xml
 147   schemagen/nflfirstdownxml/*.xml
 148   schemagen/NFLFumbleLeaderXML/*.xml
 149   schemagen/NFLGiveTakeXML/*.xml
 150   schemagen/NFLGrassTurfDomeOutsideXML/*.xml
 151   schemagen/NFLInside20XML/*.xml
 152   schemagen/NFLInterceptionLeadersXML/*.xml
 153   schemagen/NFL_KickingLeaders_XML/*.xml
 154   schemagen/NFLKickoffsXML/*.xml
 155   schemagen/NFLMondayNightXML/*.xml
 156   schemagen/NFL_NBA_Draft_XML/*.xml
 157   schemagen/NFL_NCAA_FB_Matchup_XML/*.xml
 158   schemagen/NFLPassingLeadersXML/*.xml
 159   schemagen/NFLPassLeadXML/*.xml
 160   schemagen/nflpreviewxml/*.xml
 161   schemagen/NFL_PuntingLeaders_XML/*.xml
 162   schemagen/NFLQBStartsXML/*.xml
 163   schemagen/NFLReceivingLeadersXML/*.xml
 164   schemagen/NFL_Roster_XML/*.xml
 165   schemagen/NFLRushingLeadersXML/*.xml
 166   schemagen/NFLSackLeadersXML/*.xml
 167   schemagen/nflstandxml/*.xml
 168   schemagen/NFLTackleFFLeadersXML/*.xml
 169   schemagen/NFLTeamRankingsXML/*.xml
 170   schemagen/NFL_Team_Stats_XML/*.xml
 171   schemagen/NFLTopKickoffReturnXML/*.xml
 172   schemagen/NFLTopPerformanceXML/*.xml
 173   schemagen/NFLTopPuntReturnXML/*.xml
 174   schemagen/NFLTotalYardageXML/*.xml
 175   schemagen/NFLYardsXML/*.xml
 176   schemagen/nhlpreviewxml/*.xml
 177   schemagen/Odds_XML/*.xml
 178   schemagen/recapxml/*.xml
 179   schemagen/Schedule_Changes_XML/*.xml
 180   schemagen/scoresxml/*.xml
 181   schemagen/Transactions_XML/*.xml
 182   schemagen/weatherxml/*.xml
 183   schemagen/Weekly_Sched_XML/*.xml
 184   schemagen/WNBA3PPctXML/*.xml
 185   schemagen/WNBAAssistsXML/*.xml
 186   schemagen/WNBABlocksXML/*.xml
 187   schemagen/WNBAFGPctXML/*.xml
 188   schemagen/WNBAFoulsXML/*.xml
 189   schemagen/WNBAFTPctXML/*.xml
 190   schemagen/WNBAMinutesXML/*.xml
 191   schemagen/WNBAReboundsXML/*.xml
 192   schemagen/WNBAScorersXML/*.xml
 193   schemagen/wnbastandxml/*.xml
 194   schemagen/WNBAStealsXML/*.xml
 195   schemagen/WNBA_Team_Leaders_XML/*.xml
 196   schemagen/WNBATurnoversXML/*.xml
 197   schemagen/WorldBaseballPreviewXML/*.xml
 198   test/shell/*.test
 199   test/xml/*.xml
 200   test/xml/*.dtd
 201   test/xml/gameinfo/*.xml
 202   test/xml/gameinfo/*.dtd
 203   test/xml/sportinfo/*.xml
 204   test/xml/sportinfo/*.dtd
 205 synopsis:
 206   Import XML files from The Sports Network into an RDBMS.
 207 description:
 208   /Usage/:
 209   .
 210   @
 211   htsn-import [OPTIONS] [FILES]
 212   @
 213   .
 214   The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
 215   containing various sports news and statistics. Our sister program
 216   /htsn/ is capable of retrieving the feed and saving the individual
 217   XML documents contained therein. But what to do with them?
 218   .
 219   The purpose of /htsn-import/ is to take these XML documents and
 220   get them into something we can use, a relational database management
 221   system (RDBMS), i.e. \"a SQL database\". The structure of
 222   relational database, is, well, relational, and the feed XML is not. So
 223   there is some work to do before the data can be inserted.
 224   .
 225   First, we must parse the XML. Each supported document type (see below)
 226   has a full pickle/unpickle implementation (\"pickle\" is simply a
 227   synonym for serialize here). That means that we parse the entire
 228   document into a data structure, and if we pickle (serialize) that data
 229   structure, we get the exact same XML document tha we started with.
 230   .
 231   This is important for two reasons. First, it serves as a second level
 232   of validation. The first validation is performed by the XML parser,
 233   but if that succeeds and unpicking fails, we know that something is
 234   fishy. Second, we don't ever want to be surprised by some new element
 235   or attribute showing up in the XML. The fact that we can unpickle the
 236   whole thing now means that we won't be surprised in the future.
 237   .
 238   The aforementioned feature is especially important because we
 239   automatically migrate the database schema every time we import a
 240   document. If you attempt to import a \"newsxml.dtd\" document, all
 241   database objects relating to the news will be created if they do not
 242   exist. We don't want the schema to change out from under us without
 243   warning, so it's important that no XML be parsed that would result in
 244   a different schema than we had previously. Since we can
 245   pickle/unpickle everything already, this should be impossible.
 246   .
 247   Examples and usage documentation are available in the man page.
 248
 249 executable htsn-import
 250   build-depends:
 251     base                        >= 4.6 && < 5,
 252     cmdargs                     >= 0.10.6,
 253     configurator                >= 0.2,
 254     directory                   >= 1.2,
 255     filepath                    >= 1.3,
 256     fixed-vector-hetero         >= 0.2,
 257     hslogger                    >= 1.2,
 258     htsn-common                 >= 0.0.1,
 259     hxt                         >= 9.3,
 260     groundhog                   >= 0.5,
 261     groundhog-postgresql        >= 0.5,
 262     groundhog-sqlite            >= 0.5,
 263     groundhog-th                >= 0.5,
 264     MissingH                    >= 1.2,
 265     old-locale                  >= 1,
 266     split                       >= 0.2,
 267     tasty                       >= 0.8,
 268     tasty-hunit                 >= 0.8,
 269     time                        >= 1.4,
 270     transformers                >= 0.3,
 271     tuple                       >= 0.2
 272
 273   main-is:
 274     Main.hs
 275
 276   hs-source-dirs:
 277     src/
 278
 279   other-modules:
 280     Backend
 281     CommandLine
 282     Configuration
 283     ConnectionString
 284     ExitCodes
 285     OptionalConfiguration
 286     TSN.Codegen
 287     TSN.Database
 288     TSN.DbImport
 289     TSN.Location
 290     TSN.Parse
 291     TSN.Picklers
 292     TSN.Team
 293     TSN.XmlImport
 294     TSN.XML.AutoRacingDriverList
 295     TSN.XML.AutoRacingResults
 296     TSN.XML.AutoRacingSchedule
 297     TSN.XML.EarlyLine
 298     TSN.XML.GameInfo
 299     TSN.XML.Heartbeat
 300     TSN.XML.Injuries
 301     TSN.XML.InjuriesDetail
 302     TSN.XML.JFile
 303     TSN.XML.MLBBoxScore
 304     TSN.XML.MLBEarlyLine
 305     TSN.XML.News
 306     TSN.XML.Odds
 307     TSN.XML.ScheduleChanges
 308     TSN.XML.Scores
 309     TSN.XML.SportInfo
 310     TSN.XML.Weather
 311     Xml
 312
 313   ghc-options:
 314     -Wall
 315     -fcontext-stack=50
 316     -fwarn-hi-shadowing
 317     -fwarn-missing-signatures
 318     -fwarn-name-shadowing
 319     -fwarn-orphans
 320     -fwarn-type-defaults
 321     -fwarn-tabs
 322     -fwarn-incomplete-record-updates
 323     -fwarn-monomorphism-restriction
 324     -fwarn-unused-do-bind
 325     -O2
 326
 327   ghc-prof-options:
 328     -prof
 329     -fprof-auto
 330     -fprof-cafs
 331     -- The following unbreak profiling with template haskell. We have
 332     -- to build the program twice; once without profile and again with
 333     -- these flags.
 334     -hisuf hi_p
 335     -osuf o_p
 336
 337
 338 test-suite testsuite
 339   type: exitcode-stdio-1.0
 340   hs-source-dirs: src test
 341   main-is: TestSuite.hs
 342   build-depends:
 343     base                        >= 4.6 && < 5,
 344     cmdargs                     >= 0.10.6,
 345     configurator                >= 0.2,
 346     directory                   >= 1.2,
 347     filepath                    >= 1.3,
 348     fixed-vector-hetero         >= 0.2,
 349     hslogger                    >= 1.2,
 350     htsn-common                 >= 0.0.1,
 351     hxt                         >= 9.3,
 352     groundhog                   >= 0.5,
 353     groundhog-postgresql        >= 0.5,
 354     groundhog-sqlite            >= 0.5,
 355     groundhog-th                >= 0.5,
 356     MissingH                    >= 1.2,
 357     old-locale                  >= 1,
 358     split                       >= 0.2,
 359     tasty                       >= 0.8,
 360     tasty-hunit                 >= 0.8,
 361     time                        >= 1.4,
 362     transformers                >= 0.3,
 363     tuple                       >= 0.2
 364
 365   -- It's not entirely clear to me why I have to reproduce all of this.
 366   ghc-options:
 367     -Wall
 368     -fcontext-stack=50
 369     -fwarn-hi-shadowing
 370     -fwarn-missing-signatures
 371     -fwarn-name-shadowing
 372     -fwarn-orphans
 373     -fwarn-type-defaults
 374     -fwarn-tabs
 375     -fwarn-incomplete-record-updates
 376     -fwarn-monomorphism-restriction
 377     -fwarn-unused-do-bind
 378     -O2
 379
 380
 381 test-suite doctests
 382   type: exitcode-stdio-1.0
 383   hs-source-dirs: test
 384   main-is: Doctests.hs
 385   build-depends:
 386     base      >= 4.6 && < 5,
 387     -- Additional test dependencies.
 388     doctest   >= 0.9
 389
 390   -- It's not entirely clear to me why I have to reproduce all of this.
 391   ghc-options:
 392     -Wall
 393     -fcontext-stack=50
 394     -fwarn-hi-shadowing
 395     -fwarn-missing-signatures
 396     -fwarn-name-shadowing
 397     -fwarn-orphans
 398     -fwarn-type-defaults
 399     -fwarn-tabs
 400     -fwarn-incomplete-record-updates
 401     -fwarn-monomorphism-restriction
 402     -fwarn-unused-do-bind
 403     -rtsopts
 404     -threaded
 405     -optc-O3
 406     -optc-march=native
 407     -O2
 408
 409
 410 -- These won't work without shelltestrunner installed in your
 411 -- $PATH. Maybe there is some way to tell Cabal that.
 412 test-suite shelltests
 413   type: exitcode-stdio-1.0
 414   hs-source-dirs: test
 415   main-is: ShellTests.hs
 416
 417   build-depends:
 418     base                        >= 4.6 && < 5,
 419     cmdargs                     >= 0.10.6,
 420     configurator                >= 0.2,
 421     directory                   >= 1.2,
 422     filepath                    >= 1.3,
 423     fixed-vector-hetero         >= 0.2,
 424     hslogger                    >= 1.2,
 425     htsn-common                 >= 0.0.1,
 426     hxt                         >= 9.3,
 427     groundhog                   >= 0.5,
 428     groundhog-postgresql        >= 0.5,
 429     groundhog-sqlite            >= 0.5,
 430     groundhog-th                >= 0.5,
 431     MissingH                    >= 1.2,
 432     old-locale                  >= 1,
 433     split                       >= 0.2,
 434     process                     >= 1.1,
 435     tasty                       >= 0.8,
 436     tasty-hunit                 >= 0.8,
 437     time                        >= 1.4,
 438     transformers                >= 0.3,
 439     tuple                       >= 0.2
 440
 441
 442
 443 source-repository head
 444   type: git
 445   location: http://michael.orlitzky.com/git/htsn-import.git
 446   branch: master