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