]> gitweb.michael.orlitzky.com - dead/htsn-import.git/blob - htsn-import.cabal
Add SportInfo support for NFLTackleFFLeadersXML.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/NFLTackleFFLeadersXML/*.xml
162 schemagen/NFLTeamRankingsXML/*.xml
163 schemagen/NFL_Team_Stats_XML/*.xml
164 schemagen/NFLTopPerformanceXML/*.xml
165 schemagen/NFLTotalYardageXML/*.xml
166 schemagen/nhlpreviewxml/*.xml
167 schemagen/Odds_XML/*.xml
168 schemagen/recapxml/*.xml
169 schemagen/Schedule_Changes_XML/*.xml
170 schemagen/scoresxml/*.xml
171 schemagen/Transactions_XML/*.xml
172 schemagen/weatherxml/*.xml
173 schemagen/Weekly_Sched_XML/*.xml
174 schemagen/WNBA3PPctXML/*.xml
175 schemagen/WNBAAssistsXML/*.xml
176 schemagen/WNBABlocksXML/*.xml
177 schemagen/WNBAFGPctXML/*.xml
178 schemagen/WNBAFoulsXML/*.xml
179 schemagen/WNBAFTPctXML/*.xml
180 schemagen/WNBAMinutesXML/*.xml
181 schemagen/WNBAReboundsXML/*.xml
182 schemagen/WNBAScorersXML/*.xml
183 schemagen/wnbastandxml/*.xml
184 schemagen/WNBAStealsXML/*.xml
185 schemagen/WNBA_Team_Leaders_XML/*.xml
186 schemagen/WNBATurnoversXML/*.xml
187 schemagen/WorldBaseballPreviewXML/*.xml
188 test/shell/*.test
189 test/xml/*.xml
190 test/xml/*.dtd
191 test/xml/gameinfo/*.xml
192 test/xml/gameinfo/*.dtd
193 test/xml/sportinfo/*.xml
194 test/xml/sportinfo/*.dtd
195 synopsis:
196 Import XML files from The Sports Network into an RDBMS.
197 description:
198 /Usage/:
199 .
200 @
201 htsn-import [OPTIONS] [FILES]
202 @
203 .
204 The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
205 containing various sports news and statistics. Our sister program
206 /htsn/ is capable of retrieving the feed and saving the individual
207 XML documents contained therein. But what to do with them?
208 .
209 The purpose of /htsn-import/ is to take these XML documents and
210 get them into something we can use, a relational database management
211 system (RDBMS), i.e. \"a SQL database\". The structure of
212 relational database, is, well, relational, and the feed XML is not. So
213 there is some work to do before the data can be inserted.
214 .
215 First, we must parse the XML. Each supported document type (see below)
216 has a full pickle/unpickle implementation (\"pickle\" is simply a
217 synonym for serialize here). That means that we parse the entire
218 document into a data structure, and if we pickle (serialize) that data
219 structure, we get the exact same XML document tha we started with.
220 .
221 This is important for two reasons. First, it serves as a second level
222 of validation. The first validation is performed by the XML parser,
223 but if that succeeds and unpicking fails, we know that something is
224 fishy. Second, we don't ever want to be surprised by some new element
225 or attribute showing up in the XML. The fact that we can unpickle the
226 whole thing now means that we won't be surprised in the future.
227 .
228 The aforementioned feature is especially important because we
229 automatically migrate the database schema every time we import a
230 document. If you attempt to import a \"newsxml.dtd\" document, all
231 database objects relating to the news will be created if they do not
232 exist. We don't want the schema to change out from under us without
233 warning, so it's important that no XML be parsed that would result in
234 a different schema than we had previously. Since we can
235 pickle/unpickle everything already, this should be impossible.
236 .
237 Examples and usage documentation are available in the man page.
238
239 executable htsn-import
240 build-depends:
241 base >= 4.6 && < 5,
242 cmdargs >= 0.10.6,
243 configurator >= 0.2,
244 directory >= 1.2,
245 filepath >= 1.3,
246 hslogger >= 1.2,
247 htsn-common >= 0.0.1,
248 hxt >= 9.3,
249 groundhog >= 0.5,
250 groundhog-postgresql >= 0.5,
251 groundhog-sqlite >= 0.5,
252 groundhog-th >= 0.5,
253 MissingH >= 1.2,
254 old-locale >= 1,
255 split >= 0.2,
256 tasty >= 0.8,
257 tasty-hunit >= 0.8,
258 time >= 1.4,
259 transformers >= 0.3,
260 tuple >= 0.2
261
262 main-is:
263 Main.hs
264
265 hs-source-dirs:
266 src/
267
268 other-modules:
269 Backend
270 CommandLine
271 Configuration
272 ConnectionString
273 ExitCodes
274 OptionalConfiguration
275 TSN.Codegen
276 TSN.Database
277 TSN.DbImport
278 TSN.Location
279 TSN.Parse
280 TSN.Picklers
281 TSN.Team
282 TSN.XmlImport
283 TSN.XML.AutoRacingResults
284 TSN.XML.AutoRacingSchedule
285 TSN.XML.EarlyLine
286 TSN.XML.GameInfo
287 TSN.XML.Heartbeat
288 TSN.XML.Injuries
289 TSN.XML.InjuriesDetail
290 TSN.XML.JFile
291 TSN.XML.MLBEarlyLine
292 TSN.XML.News
293 TSN.XML.Odds
294 TSN.XML.ScheduleChanges
295 TSN.XML.Scores
296 TSN.XML.SportInfo
297 TSN.XML.Weather
298 Xml
299
300 ghc-options:
301 -Wall
302 -fwarn-hi-shadowing
303 -fwarn-missing-signatures
304 -fwarn-name-shadowing
305 -fwarn-orphans
306 -fwarn-type-defaults
307 -fwarn-tabs
308 -fwarn-incomplete-record-updates
309 -fwarn-monomorphism-restriction
310 -fwarn-unused-do-bind
311 -O2
312
313 ghc-prof-options:
314 -prof
315 -fprof-auto
316 -fprof-cafs
317 -- The following unbreak profiling with template haskell. We have
318 -- to build the program twice; once without profile and again with
319 -- these flags.
320 -hisuf hi_p
321 -osuf o_p
322
323
324 test-suite testsuite
325 type: exitcode-stdio-1.0
326 hs-source-dirs: src test
327 main-is: TestSuite.hs
328 build-depends:
329 base >= 4.6 && < 5,
330 cmdargs >= 0.10.6,
331 configurator >= 0.2,
332 directory >= 1.2,
333 filepath >= 1.3,
334 hslogger >= 1.2,
335 htsn-common >= 0.0.1,
336 hxt >= 9.3,
337 groundhog >= 0.5,
338 groundhog-postgresql >= 0.5,
339 groundhog-sqlite >= 0.5,
340 groundhog-th >= 0.5,
341 MissingH >= 1.2,
342 old-locale >= 1,
343 split >= 0.2,
344 tasty >= 0.8,
345 tasty-hunit >= 0.8,
346 time >= 1.4,
347 transformers >= 0.3,
348 tuple >= 0.2
349
350 -- It's not entirely clear to me why I have to reproduce all of this.
351 ghc-options:
352 -Wall
353 -fwarn-hi-shadowing
354 -fwarn-missing-signatures
355 -fwarn-name-shadowing
356 -fwarn-orphans
357 -fwarn-type-defaults
358 -fwarn-tabs
359 -fwarn-incomplete-record-updates
360 -fwarn-monomorphism-restriction
361 -fwarn-unused-do-bind
362 -O2
363
364
365 test-suite doctests
366 type: exitcode-stdio-1.0
367 hs-source-dirs: test
368 main-is: Doctests.hs
369 build-depends:
370 base >= 4.6 && < 5,
371 -- Additional test dependencies.
372 doctest >= 0.9
373
374 -- It's not entirely clear to me why I have to reproduce all of this.
375 ghc-options:
376 -Wall
377 -fwarn-hi-shadowing
378 -fwarn-missing-signatures
379 -fwarn-name-shadowing
380 -fwarn-orphans
381 -fwarn-type-defaults
382 -fwarn-tabs
383 -fwarn-incomplete-record-updates
384 -fwarn-monomorphism-restriction
385 -fwarn-unused-do-bind
386 -rtsopts
387 -threaded
388 -optc-O3
389 -optc-march=native
390 -O2
391
392
393 -- These won't work without shelltestrunner installed in your
394 -- $PATH. Maybe there is some way to tell Cabal that.
395 test-suite shelltests
396 type: exitcode-stdio-1.0
397 hs-source-dirs: test
398 main-is: ShellTests.hs
399
400 build-depends:
401 base >= 4.6 && < 5,
402 cmdargs >= 0.10.6,
403 configurator >= 0.2,
404 directory >= 1.2,
405 filepath >= 1.3,
406 hslogger >= 1.2,
407 htsn-common >= 0.0.1,
408 hxt >= 9.3,
409 groundhog >= 0.5,
410 groundhog-postgresql >= 0.5,
411 groundhog-sqlite >= 0.5,
412 groundhog-th >= 0.5,
413 MissingH >= 1.2,
414 old-locale >= 1,
415 split >= 0.2,
416 process >= 1.1,
417 tasty >= 0.8,
418 tasty-hunit >= 0.8,
419 time >= 1.4,
420 transformers >= 0.3,
421 tuple >= 0.2
422
423
424
425 source-repository head
426 type: git
427 location: http://michael.orlitzky.com/git/htsn-import.git
428 branch: master