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