]> gitweb.michael.orlitzky.com - dead/htsn-import.git/blob - htsn-import.cabal
afa02df98845aba5e97e94bf2ce521d185a827e5
[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/NFL_PuntingLeaders_XML/*.xml
156 schemagen/NFLQBStartsXML/*.xml
157 schemagen/NFLReceivingLeadersXML/*.xml
158 schemagen/NFL_Roster_XML/*.xml
159 schemagen/NFLRushingLeadersXML/*.xml
160 schemagen/NFLSackLeadersXML/*.xml
161 schemagen/nflstandxml/*.xml
162 schemagen/NFLTackleFFLeadersXML/*.xml
163 schemagen/NFLTeamRankingsXML/*.xml
164 schemagen/NFL_Team_Stats_XML/*.xml
165 schemagen/NFLTopKickoffReturnXML/*.xml
166 schemagen/NFLTopPerformanceXML/*.xml
167 schemagen/NFLTopPuntReturnXML/*.xml
168 schemagen/NFLTotalYardageXML/*.xml
169 schemagen/NFLYardsXML/*.xml
170 schemagen/nhlpreviewxml/*.xml
171 schemagen/Odds_XML/*.xml
172 schemagen/recapxml/*.xml
173 schemagen/Schedule_Changes_XML/*.xml
174 schemagen/scoresxml/*.xml
175 schemagen/Transactions_XML/*.xml
176 schemagen/weatherxml/*.xml
177 schemagen/Weekly_Sched_XML/*.xml
178 schemagen/WNBA3PPctXML/*.xml
179 schemagen/WNBAAssistsXML/*.xml
180 schemagen/WNBABlocksXML/*.xml
181 schemagen/WNBAFGPctXML/*.xml
182 schemagen/WNBAFoulsXML/*.xml
183 schemagen/WNBAFTPctXML/*.xml
184 schemagen/WNBAMinutesXML/*.xml
185 schemagen/WNBAReboundsXML/*.xml
186 schemagen/WNBAScorersXML/*.xml
187 schemagen/wnbastandxml/*.xml
188 schemagen/WNBAStealsXML/*.xml
189 schemagen/WNBA_Team_Leaders_XML/*.xml
190 schemagen/WNBATurnoversXML/*.xml
191 schemagen/WorldBaseballPreviewXML/*.xml
192 test/shell/*.test
193 test/xml/*.xml
194 test/xml/*.dtd
195 test/xml/gameinfo/*.xml
196 test/xml/gameinfo/*.dtd
197 test/xml/sportinfo/*.xml
198 test/xml/sportinfo/*.dtd
199 synopsis:
200 Import XML files from The Sports Network into an RDBMS.
201 description:
202 /Usage/:
203 .
204 @
205 htsn-import [OPTIONS] [FILES]
206 @
207 .
208 The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
209 containing various sports news and statistics. Our sister program
210 /htsn/ is capable of retrieving the feed and saving the individual
211 XML documents contained therein. But what to do with them?
212 .
213 The purpose of /htsn-import/ is to take these XML documents and
214 get them into something we can use, a relational database management
215 system (RDBMS), i.e. \"a SQL database\". The structure of
216 relational database, is, well, relational, and the feed XML is not. So
217 there is some work to do before the data can be inserted.
218 .
219 First, we must parse the XML. Each supported document type (see below)
220 has a full pickle/unpickle implementation (\"pickle\" is simply a
221 synonym for serialize here). That means that we parse the entire
222 document into a data structure, and if we pickle (serialize) that data
223 structure, we get the exact same XML document tha we started with.
224 .
225 This is important for two reasons. First, it serves as a second level
226 of validation. The first validation is performed by the XML parser,
227 but if that succeeds and unpicking fails, we know that something is
228 fishy. Second, we don't ever want to be surprised by some new element
229 or attribute showing up in the XML. The fact that we can unpickle the
230 whole thing now means that we won't be surprised in the future.
231 .
232 The aforementioned feature is especially important because we
233 automatically migrate the database schema every time we import a
234 document. If you attempt to import a \"newsxml.dtd\" document, all
235 database objects relating to the news will be created if they do not
236 exist. We don't want the schema to change out from under us without
237 warning, so it's important that no XML be parsed that would result in
238 a different schema than we had previously. Since we can
239 pickle/unpickle everything already, this should be impossible.
240 .
241 Examples and usage documentation are available in the man page.
242
243 executable htsn-import
244 build-depends:
245 base >= 4.6 && < 5,
246 cmdargs >= 0.10.6,
247 configurator >= 0.2,
248 directory >= 1.2,
249 filepath >= 1.3,
250 hslogger >= 1.2,
251 htsn-common >= 0.0.1,
252 hxt >= 9.3,
253 groundhog >= 0.5,
254 groundhog-postgresql >= 0.5,
255 groundhog-sqlite >= 0.5,
256 groundhog-th >= 0.5,
257 MissingH >= 1.2,
258 old-locale >= 1,
259 split >= 0.2,
260 tasty >= 0.8,
261 tasty-hunit >= 0.8,
262 time >= 1.4,
263 transformers >= 0.3,
264 tuple >= 0.2
265
266 main-is:
267 Main.hs
268
269 hs-source-dirs:
270 src/
271
272 other-modules:
273 Backend
274 CommandLine
275 Configuration
276 ConnectionString
277 ExitCodes
278 OptionalConfiguration
279 TSN.Codegen
280 TSN.Database
281 TSN.DbImport
282 TSN.Location
283 TSN.Parse
284 TSN.Picklers
285 TSN.Team
286 TSN.XmlImport
287 TSN.XML.AutoRacingResults
288 TSN.XML.AutoRacingSchedule
289 TSN.XML.EarlyLine
290 TSN.XML.GameInfo
291 TSN.XML.Heartbeat
292 TSN.XML.Injuries
293 TSN.XML.InjuriesDetail
294 TSN.XML.JFile
295 TSN.XML.MLBEarlyLine
296 TSN.XML.News
297 TSN.XML.Odds
298 TSN.XML.ScheduleChanges
299 TSN.XML.Scores
300 TSN.XML.SportInfo
301 TSN.XML.Weather
302 Xml
303
304 ghc-options:
305 -Wall
306 -fwarn-hi-shadowing
307 -fwarn-missing-signatures
308 -fwarn-name-shadowing
309 -fwarn-orphans
310 -fwarn-type-defaults
311 -fwarn-tabs
312 -fwarn-incomplete-record-updates
313 -fwarn-monomorphism-restriction
314 -fwarn-unused-do-bind
315 -O2
316
317 ghc-prof-options:
318 -prof
319 -fprof-auto
320 -fprof-cafs
321 -- The following unbreak profiling with template haskell. We have
322 -- to build the program twice; once without profile and again with
323 -- these flags.
324 -hisuf hi_p
325 -osuf o_p
326
327
328 test-suite testsuite
329 type: exitcode-stdio-1.0
330 hs-source-dirs: src test
331 main-is: TestSuite.hs
332 build-depends:
333 base >= 4.6 && < 5,
334 cmdargs >= 0.10.6,
335 configurator >= 0.2,
336 directory >= 1.2,
337 filepath >= 1.3,
338 hslogger >= 1.2,
339 htsn-common >= 0.0.1,
340 hxt >= 9.3,
341 groundhog >= 0.5,
342 groundhog-postgresql >= 0.5,
343 groundhog-sqlite >= 0.5,
344 groundhog-th >= 0.5,
345 MissingH >= 1.2,
346 old-locale >= 1,
347 split >= 0.2,
348 tasty >= 0.8,
349 tasty-hunit >= 0.8,
350 time >= 1.4,
351 transformers >= 0.3,
352 tuple >= 0.2
353
354 -- It's not entirely clear to me why I have to reproduce all of this.
355 ghc-options:
356 -Wall
357 -fwarn-hi-shadowing
358 -fwarn-missing-signatures
359 -fwarn-name-shadowing
360 -fwarn-orphans
361 -fwarn-type-defaults
362 -fwarn-tabs
363 -fwarn-incomplete-record-updates
364 -fwarn-monomorphism-restriction
365 -fwarn-unused-do-bind
366 -O2
367
368
369 test-suite doctests
370 type: exitcode-stdio-1.0
371 hs-source-dirs: test
372 main-is: Doctests.hs
373 build-depends:
374 base >= 4.6 && < 5,
375 -- Additional test dependencies.
376 doctest >= 0.9
377
378 -- It's not entirely clear to me why I have to reproduce all of this.
379 ghc-options:
380 -Wall
381 -fwarn-hi-shadowing
382 -fwarn-missing-signatures
383 -fwarn-name-shadowing
384 -fwarn-orphans
385 -fwarn-type-defaults
386 -fwarn-tabs
387 -fwarn-incomplete-record-updates
388 -fwarn-monomorphism-restriction
389 -fwarn-unused-do-bind
390 -rtsopts
391 -threaded
392 -optc-O3
393 -optc-march=native
394 -O2
395
396
397 -- These won't work without shelltestrunner installed in your
398 -- $PATH. Maybe there is some way to tell Cabal that.
399 test-suite shelltests
400 type: exitcode-stdio-1.0
401 hs-source-dirs: test
402 main-is: ShellTests.hs
403
404 build-depends:
405 base >= 4.6 && < 5,
406 cmdargs >= 0.10.6,
407 configurator >= 0.2,
408 directory >= 1.2,
409 filepath >= 1.3,
410 hslogger >= 1.2,
411 htsn-common >= 0.0.1,
412 hxt >= 9.3,
413 groundhog >= 0.5,
414 groundhog-postgresql >= 0.5,
415 groundhog-sqlite >= 0.5,
416 groundhog-th >= 0.5,
417 MissingH >= 1.2,
418 old-locale >= 1,
419 split >= 0.2,
420 process >= 1.1,
421 tasty >= 0.8,
422 tasty-hunit >= 0.8,
423 time >= 1.4,
424 transformers >= 0.3,
425 tuple >= 0.2
426
427
428
429 source-repository head
430 type: git
431 location: http://michael.orlitzky.com/git/htsn-import.git
432 branch: master