4 author: Michael Orlitzky
5 maintainer: Michael Orlitzky <michael@orlitzky.com>
8 license-file: doc/LICENSE
12 doc/htsn-importrc.example
13 doc/man1/htsn-import.1
15 doc/README.development
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/NFLSackLeadersXML/*.xml
159 schemagen/nflstandxml/*.xml
160 schemagen/NFLTeamRankingsXML/*.xml
161 schemagen/NFL_Team_Stats_XML/*.xml
162 schemagen/NFLTopPerformanceXML/*.xml
163 schemagen/NFLTotalYardageXML/*.xml
164 schemagen/nhlpreviewxml/*.xml
165 schemagen/Odds_XML/*.xml
166 schemagen/recapxml/*.xml
167 schemagen/Schedule_Changes_XML/*.xml
168 schemagen/scoresxml/*.xml
169 schemagen/Transactions_XML/*.xml
170 schemagen/weatherxml/*.xml
171 schemagen/Weekly_Sched_XML/*.xml
172 schemagen/WNBA3PPctXML/*.xml
173 schemagen/WNBAAssistsXML/*.xml
174 schemagen/WNBABlocksXML/*.xml
175 schemagen/WNBAFGPctXML/*.xml
176 schemagen/WNBAFoulsXML/*.xml
177 schemagen/WNBAFTPctXML/*.xml
178 schemagen/WNBAMinutesXML/*.xml
179 schemagen/WNBAReboundsXML/*.xml
180 schemagen/WNBAScorersXML/*.xml
181 schemagen/wnbastandxml/*.xml
182 schemagen/WNBAStealsXML/*.xml
183 schemagen/WNBA_Team_Leaders_XML/*.xml
184 schemagen/WNBATurnoversXML/*.xml
185 schemagen/WorldBaseballPreviewXML/*.xml
189 test/xml/gameinfo/*.xml
190 test/xml/gameinfo/*.dtd
191 test/xml/sportinfo/*.xml
192 test/xml/sportinfo/*.dtd
194 Import XML files from The Sports Network into an RDBMS.
199 htsn-import [OPTIONS] [FILES]
202 The Sports Network <http://www.sportsnetwork.com/> offers an XML feed
203 containing various sports news and statistics. Our sister program
204 /htsn/ is capable of retrieving the feed and saving the individual
205 XML documents contained therein. But what to do with them?
207 The purpose of /htsn-import/ is to take these XML documents and
208 get them into something we can use, a relational database management
209 system (RDBMS), i.e. \"a SQL database\". The structure of
210 relational database, is, well, relational, and the feed XML is not. So
211 there is some work to do before the data can be inserted.
213 First, we must parse the XML. Each supported document type (see below)
214 has a full pickle/unpickle implementation (\"pickle\" is simply a
215 synonym for serialize here). That means that we parse the entire
216 document into a data structure, and if we pickle (serialize) that data
217 structure, we get the exact same XML document tha we started with.
219 This is important for two reasons. First, it serves as a second level
220 of validation. The first validation is performed by the XML parser,
221 but if that succeeds and unpicking fails, we know that something is
222 fishy. Second, we don't ever want to be surprised by some new element
223 or attribute showing up in the XML. The fact that we can unpickle the
224 whole thing now means that we won't be surprised in the future.
226 The aforementioned feature is especially important because we
227 automatically migrate the database schema every time we import a
228 document. If you attempt to import a \"newsxml.dtd\" document, all
229 database objects relating to the news will be created if they do not
230 exist. We don't want the schema to change out from under us without
231 warning, so it's important that no XML be parsed that would result in
232 a different schema than we had previously. Since we can
233 pickle/unpickle everything already, this should be impossible.
235 Examples and usage documentation are available in the man page.
237 executable htsn-import
245 htsn-common >= 0.0.1,
248 groundhog-postgresql >= 0.5,
249 groundhog-sqlite >= 0.5,
272 OptionalConfiguration
281 TSN.XML.AutoRacingResults
282 TSN.XML.AutoRacingSchedule
287 TSN.XML.InjuriesDetail
292 TSN.XML.ScheduleChanges
301 -fwarn-missing-signatures
302 -fwarn-name-shadowing
306 -fwarn-incomplete-record-updates
307 -fwarn-monomorphism-restriction
308 -fwarn-unused-do-bind
315 -- The following unbreak profiling with template haskell. We have
316 -- to build the program twice; once without profile and again with
323 type: exitcode-stdio-1.0
324 hs-source-dirs: src test
325 main-is: TestSuite.hs
333 htsn-common >= 0.0.1,
336 groundhog-postgresql >= 0.5,
337 groundhog-sqlite >= 0.5,
348 -- It's not entirely clear to me why I have to reproduce all of this.
352 -fwarn-missing-signatures
353 -fwarn-name-shadowing
357 -fwarn-incomplete-record-updates
358 -fwarn-monomorphism-restriction
359 -fwarn-unused-do-bind
364 type: exitcode-stdio-1.0
369 -- Additional test dependencies.
372 -- It's not entirely clear to me why I have to reproduce all of this.
376 -fwarn-missing-signatures
377 -fwarn-name-shadowing
381 -fwarn-incomplete-record-updates
382 -fwarn-monomorphism-restriction
383 -fwarn-unused-do-bind
391 -- These won't work without shelltestrunner installed in your
392 -- $PATH. Maybe there is some way to tell Cabal that.
393 test-suite shelltests
394 type: exitcode-stdio-1.0
396 main-is: ShellTests.hs
405 htsn-common >= 0.0.1,
408 groundhog-postgresql >= 0.5,
409 groundhog-sqlite >= 0.5,
423 source-repository head
425 location: http://michael.orlitzky.com/git/htsn-import.git