r53927 MediaWiki - Code Review archive

Repository:	MediaWiki
Revision:	< r53926‎ \| r53927 \| r53928 >
Date:	09:27, 29 July 2009
Author:	daniel
Status:	deferred
Tags:
Comment:	{{0}}
Modified paths:	/trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_dewiki.java (modified) (history) /trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_enwiki.java (modified) (history) /trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_frwiki.java (modified) (history) /trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_ndswiki.java (modified) (history) /trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_nlwiki.java (modified) (history) /trunk/WikiWord/pom.xml (modified) (history)

Diff [purge]

Index: trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_ndswiki.java
—	—	@@ -14,30 +14,30 @@
15	15
16	16	public WikiConfiguration_ndswiki() {
17	17	super();
18		~~- conceptTypeSensors.add( new HasTemplateLikeSensor(ConceptType.PLACE, "^[Ll]\u00e4nner_in_.*", 0));~~
19		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.PLACE, "Oort"));~~
20		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.PLACE, "Land"));~~
	18	+ conceptTypeSensors.add( new HasTemplateLikeSensor<ConceptType>(ConceptType.PLACE, "^[Ll]\u00e4nner_in_.*", 0));
	19	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.PLACE, "Oort"));
	20	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.PLACE, "Land"));
21	21
22		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.PERSON, "Mann"));~~
23		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.PERSON, "Fru"));~~
	22	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.PERSON, "Mann"));
	23	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.PERSON, "Fru"));
24	24
25		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "V\u00f6rnaam_f\u00f6r_Deerns"));~~
26		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "V\u00f6rnaam_f\u00f6r_Jungs"));~~
27		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "Familiennaam"));~~
	25	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "V\u00f6rnaam_f\u00f6r_Deerns"));
	26	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "V\u00f6rnaam_f\u00f6r_Jungs"));
	27	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "Familiennaam"));
28	28
29		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.TIME, "Johr"));~~
30		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.TIME, "Dag"));~~
31		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.TIME, "Johrhunnert"));~~
	29	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.TIME, "Johr"));
	30	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.TIME, "Dag"));
	31	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.TIME, "Johrhunnert"));
32	32
33		~~- conceptTypeSensors.add( new HasTemplateSensor(ConceptType.LIFEFORM, "Taxobox"));~~
	33	+ conceptTypeSensors.add( new HasTemplateSensor<ConceptType>(ConceptType.LIFEFORM, "Taxobox"));
34	34	//TODO: cooperations & organizations
35	35
36		~~- resourceTypeSensors.add( new HasTemplateSensor(ResourceType.BAD, "Delete"));~~
37		~~- resourceTypeSensors.add( new HasTemplateSensor(ResourceType.BAD, "Gauweg"));~~
38		~~- resourceTypeSensors.add( new HasTemplateSensor(ResourceType.BAD, "Wegsmieten"));~~
	36	+ resourceTypeSensors.add( new HasTemplateSensor<ResourceType>(ResourceType.BAD, "Delete"));
	37	+ resourceTypeSensors.add( new HasTemplateSensor<ResourceType>(ResourceType.BAD, "Gauweg"));
	38	+ resourceTypeSensors.add( new HasTemplateSensor<ResourceType>(ResourceType.BAD, "Wegsmieten"));
39	39
40	40	//resourceTypeSensors.add( new HasTemplateSensor(ResourceType.DISAMBIG, "Mehrd\u00fcdig_Begreep") );
41		~~- resourceTypeSensors.add( new TitleSensor(ResourceType.LIST, "Lieste?_(van\|mit).*", 0));~~
	41	+ resourceTypeSensors.add( new TitleSensor<ResourceType>(ResourceType.LIST, "Lieste?_(van\|mit).*", 0));
42	42
43	43	disambigStripSectionPattern = sectionPattern("Kiek ok( bi)?:?", 0); //FIXME: often not as a section, but plain text!
44	44
Index: trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_enwiki.java
—	—	@@ -79,6 +79,7 @@
80	80	stripClutterManglers.add( new RegularExpressionMangler("\\[\\[:commons:", "[[commons:", Pattern.CASE_INSENSITIVE));
81	81
82	82	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("Okina", 0, false), "\u02BB"));
	83	+ stripClutterManglers.add( new RegularExpressionMangler(templatePattern("0", 0, true), " "));
83	84	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("\u00b7\|moddot\|dot", 0, false), "\u00b7"));
84	85	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("spaces", 1, true), " "));
85	86
Index: trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_nlwiki.java
—	—	@@ -19,35 +19,36 @@
20	20	super();
21	21	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("wrapper", 0, true), "{\|"));
22	22
	23	+ stripClutterManglers.add( new RegularExpressionMangler(templatePattern("0", 0, true), " "));
23	24	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("e", 0, false), "$1"));
24	25	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("unicode", 1, true), "$2"));
25	26
26		~~- conceptTypeSensors.add( new HasTemplateLikeSensor(ConceptType.PLACE, "^(Landtabel\|Gemeente\|Plaats)($\|_)\|(^\|_)plaats$", 0));~~
27		~~- conceptTypeSensors.add( new HasCategoryLikeSensor(ConceptType.PLACE, "^(Gemeente\|Stad\|Land\|Plaats)(_\|$)", 0));~~
	27	+ conceptTypeSensors.add( new HasTemplateLikeSensor<ConceptType>(ConceptType.PLACE, "^(Landtabel\|Gemeente\|Plaats)($\|_)\|(^\|_)plaats$", 0));
	28	+ conceptTypeSensors.add( new HasCategoryLikeSensor<ConceptType>(ConceptType.PLACE, "^(Gemeente\|Stad\|Land\|Plaats)(_\|$)", 0));
28	29
29		~~- conceptTypeSensors.add( new HasTemplateSensor(ConceptType.TIME, "Jaarbox"));~~
30		~~- conceptTypeSensors.add( new HasTemplateSensor(ConceptType.TIME, "Kalenders"));~~
31		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.TIME, "Datum"));~~
32		~~- conceptTypeSensors.add( new TitleSensor(ConceptType.TIME, "(\\d{1,4}\|\\d{1,2}e_eeuw)(_v\\._Chr\\.)?", 0));~~
	30	+ conceptTypeSensors.add( new HasTemplateSensor<ConceptType>(ConceptType.TIME, "Jaarbox"));
	31	+ conceptTypeSensors.add( new HasTemplateSensor<ConceptType>(ConceptType.TIME, "Kalenders"));
	32	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.TIME, "Datum"));
	33	+ conceptTypeSensors.add( new TitleSensor<ConceptType>(ConceptType.TIME, "(\\d{1,4}\|\\d{1,2}e_eeuw)(_v\\._Chr\\.)?", 0));
33	34
34		~~- conceptTypeSensors.add( new HasCategoryLikeSensor(ConceptType.PERSON, "(^\|_)persoon(_\|$)\|(.schapper\|.oloog\|.*icus)$", 0));~~
35		~~- conceptTypeSensors.add( new HasTemplateLikeSensor(ConceptType.PERSON, "^(Infobox_(artiest\|Auteur\|acteur\|Comedian\|.speler\|Presentator\|regisseur)\|Winnaars_.)$", Pattern.CASE_INSENSITIVE));~~
36		~~- conceptTypeSensors.add( new HasTemplateLikeSensor(ConceptType.PERSON, "^(Infobox_.\|.cus\|.eur\|.ler\|.*schapper)$", Pattern.CASE_INSENSITIVE, new String[] {"geboren"}));~~
37		- conceptTypeSensors.add( new HasSectionLikeSensor(ConceptType.PERSON, "^((.* )?leven\|Carri\u00e8re\|Stamvader\|Levensloop\|Filmografie\|Bibliografie\|publicaties\|(Eigen )?Biografie\|Priv\u00e9\|.Loopbaan.\|Jeugd\|Kinderen\|Familie\|Familieachtergrond)$", Pattern.CASE_INSENSITIVE) );
	35	+ conceptTypeSensors.add( new HasCategoryLikeSensor<ConceptType>(ConceptType.PERSON, "(^\|_)persoon(_\|$)\|(.schapper\|.oloog\|.*icus)$", 0));
	36	+ conceptTypeSensors.add( new HasTemplateLikeSensor<ConceptType>(ConceptType.PERSON, "^(Infobox_(artiest\|Auteur\|acteur\|Comedian\|.speler\|Presentator\|regisseur)\|Winnaars_.)$", Pattern.CASE_INSENSITIVE));
	37	+ conceptTypeSensors.add( new HasTemplateLikeSensor<ConceptType>(ConceptType.PERSON, "^(Infobox_.\|.cus\|.eur\|.ler\|.*schapper)$", Pattern.CASE_INSENSITIVE, new String[] {"geboren"}));
	38	+ conceptTypeSensors.add( new HasSectionLikeSensor<ConceptType>(ConceptType.PERSON, "^((.* )?leven\|Carri\u00e8re\|Stamvader\|Levensloop\|Filmografie\|Bibliografie\|publicaties\|(Eigen )?Biografie\|Priv\u00e9\|.Loopbaan.\|Jeugd\|Kinderen\|Familie\|Familieachtergrond)$", Pattern.CASE_INSENSITIVE) );
38	39
39	40	//conceptTypeSensors.add( new WikiTextAnalyzer.TitleSensor(".*_\$voornaam\$", 0));
40		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "Jongensnaam"));~~
41		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "Meisjesnaam"));~~
42		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "Achternaam"));~~
	41	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "Jongensnaam"));
	42	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "Meisjesnaam"));
	43	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "Achternaam"));
43	44
44		~~- conceptTypeSensors.add( new HasTemplateSensor(ConceptType.LIFEFORM, "Taxobox_end"));~~
	45	+ conceptTypeSensors.add( new HasTemplateSensor<ConceptType>(ConceptType.LIFEFORM, "Taxobox_end"));
45	46	//TODO: cooperations & organizations
46	47
47		~~- resourceTypeSensors.add( new HasTemplateLikeSensor(ResourceType.BAD, "^(Weg\|Ne)$\|weg$", 0));~~
48		~~- resourceTypeSensors.add( new HasTemplateSensor(ResourceType.DISAMBIG, "Dp") );~~
	48	+ resourceTypeSensors.add( new HasTemplateLikeSensor<ResourceType>(ResourceType.BAD, "^(Weg\|Ne)$\|weg$", 0));
	49	+ resourceTypeSensors.add( new HasTemplateSensor<ResourceType>(ResourceType.DISAMBIG, "Dp") );
49	50	//resourceTypeSensors.add( new TitleSensor(ResourceType.DISAMBIG, ".*\$doorverwijspagina\$", 0) );
50		~~- resourceTypeSensors.add( new HasCategoryLikeSensor(ResourceType.LIST, "^Lijsten_\|lijsten$", 0) );~~
51		~~- resourceTypeSensors.add( new TitleSensor(ResourceType.LIST, "Lijst_.\|.lijst", 0) );~~
	51	+ resourceTypeSensors.add( new HasCategoryLikeSensor<ResourceType>(ResourceType.LIST, "^Lijsten_\|lijsten$", 0) );
	52	+ resourceTypeSensors.add( new TitleSensor<ResourceType>(ResourceType.LIST, "Lijst_.\|.lijst", 0) );
52	53	//resourceTypeSensors.add( new WikiTextAnalyzer.RegularExpressionTitleSensor("^Lijst_", 0) ); //NOTE: too broad. some concrete concepts have a name matching this.
53	54
54	55	disambigStripSectionPattern = sectionPattern("Zie ook", 0);
Index: trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_dewiki.java
—	—	@@ -39,6 +39,7 @@
40	40	stripClutterManglers.add( new RegularExpressionMangler("\\[\\[:commons:", "[[commons:", Pattern.CASE_INSENSITIVE));
41	41
42	42	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("Okina", 0, false), "\u02BB"));
	43	+ stripClutterManglers.add( new RegularExpressionMangler(templatePattern("0", 0, true), " "));
43	44	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("IPA(?:-Text)\|IAST\|Unicode\|Musik", 1, true), "$2"));
44	45	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("SWD\|Wiktionary", 0, true), ""));
45	46
Index: trunk/WikiWord/WikiWordBuilder/src/main/java/de/brightbyte/wikiword/wikis/WikiConfiguration_frwiki.java
—	—	@@ -23,6 +23,7 @@
24	24
25	25	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("er?\|\u00e8?re\|(?:mini[ _])?[IVXCM]+(?:e\|re\|er)?\|\\d+r?er?\|Mlle\|Mme\|elle", 0, true), "$1"));
26	26	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("romain\|rom\|rom-min\|rom-maj\|APIb\|IPA", 1, true), "$2"));
	27	+ stripClutterManglers.add( new RegularExpressionMangler(templatePattern("0", 0, true), " "));
27	28	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("avjc", 0, false), "av. J.-C."));
28	29	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("[XVI]+es", 0, false), "$1"));
29	30	stripClutterManglers.add( new RegularExpressionMangler(templatePattern("formatnum", 1, true), "$2"));
—	—	@@ -43,24 +44,24 @@
44	45	stripClutterManglers.add( new RegularExpressionMangler(
45	46	templatePattern("lang(?:\\s\\\|\\s(?:rtl\|ltr)\\s*)?", 2, true), "$3"));
46	47
47		~~- conceptTypeSensors.add( new HasCategoryLikeSensor(ConceptType.PLACE, "^(Pays\|Territoire\|R\u00e9publique\|Subdivision\|Ville\|Municipalit\u00e9s\|Ocean)(_\|$)", 0));~~
	48	+ conceptTypeSensors.add( new HasCategoryLikeSensor<ConceptType>(ConceptType.PLACE, "^(Pays\|Territoire\|R\u00e9publique\|Subdivision\|Ville\|Municipalit\u00e9s\|Ocean)(_\|$)", 0));
48	49	conceptTypeSensors.add( new HasTemplateSensor<ConceptType>(ConceptType.PLACE, "ODP", new HashMap<String, NameMatcher>() { { put("1", new PatternNameMatcher("Regional/.*", 0, true)); } }));
49		~~- conceptTypeSensors.add( new HasTemplateLikeSensor(ConceptType.PLACE, "^(Infobox_)?(Pays\|Continent\|Commune_)(_\|$)", 0));~~
	50	+ conceptTypeSensors.add( new HasTemplateLikeSensor<ConceptType>(ConceptType.PLACE, "^(Infobox_)?(Pays\|Continent\|Commune_)(_\|$)", 0));
50	51
51		~~- conceptTypeSensors.add( new HasCategoryLikeSensor(ConceptType.PERSON, "(^Homme$\|^Femme$\|^Naissance_en\|D\u00e9c\u00e8s_en)", 0));~~
	52	+ conceptTypeSensors.add( new HasCategoryLikeSensor<ConceptType>(ConceptType.PERSON, "(^Homme$\|^Femme$\|^Naissance_en\|D\u00e9c\u00e8s_en)", 0));
52	53
53		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "Pr\u00e9nom"));~~
54		~~- conceptTypeSensors.add( new HasCategorySensor(ConceptType.NAME, "Patronyme"));~~
	54	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "Pr\u00e9nom"));
	55	+ conceptTypeSensors.add( new HasCategorySensor<ConceptType>(ConceptType.NAME, "Patronyme"));
55	56
56		~~- conceptTypeSensors.add( new HasTemplateLikeSensor(ConceptType.TIME, "^(Ann\u00e9es\|Portail_ann\u00e9es_\\d+\|Portails_?I+er?_mill\u00e9naire(_av\\._J\\.-C\\.)?\|Portails_d\u00e9cennies)$", 0));~~
	57	+ conceptTypeSensors.add( new HasTemplateLikeSensor<ConceptType>(ConceptType.TIME, "^(Ann\u00e9es\|Portail_ann\u00e9es_\\d+\|Portails_?I+er?_mill\u00e9naire(_av\\._J\\.-C\\.)?\|Portails_d\u00e9cennies)$", 0));
57	58
58		~~- conceptTypeSensors.add( new HasTemplateLikeSensor(ConceptType.LIFEFORM, "^Taxobox_", 0));~~
	59	+ conceptTypeSensors.add( new HasTemplateLikeSensor<ConceptType>(ConceptType.LIFEFORM, "^Taxobox_", 0));
59	60	//TODO: cooperations & organizations
60	61
61		~~- resourceTypeSensors.add( new HasTemplateLikeSensor(ResourceType.BAD, "^Suppression[ _/]", 0));~~
	62	+ resourceTypeSensors.add( new HasTemplateLikeSensor<ResourceType>(ResourceType.BAD, "^Suppression[ _/]", 0));
62	63
63	64	//resourceTypeSensors.add( new HasTemplateLikeSensor(ResourceType.DISAMBIG, "^Homonymie(_\|$)\|_homonymes$\|^Paronymie$\|^Patronyme$\|^Internationalisation$", 0) );
64		~~- resourceTypeSensors.add( new HasCategoryLikeSensor(ResourceType.LIST, "^Liste(_\|$)", 0));~~
	65	+ resourceTypeSensors.add( new HasCategoryLikeSensor<ResourceType>(ResourceType.LIST, "^Liste(_\|$)", 0));
65	66
66	67	disambigStripSectionPattern = sectionPattern("^(Voir aussi\|Liens internes)$", 0);
67	68
Index: trunk/WikiWord/pom.xml
—	—	@@ -12,8 +12,7 @@
13	13	<module>WikiWord</module>
14	14	<module>WikiWordBuilder</module>
15	15	<module>WikiWordIntegrator</module>
16		~~- <module>WikiWordBuilder4LifeScience</module>~~
17		~~- <module>WikiWordBuilder4Biography</module>~~
	16	+ <module>WikiWordProperties</module>
18	17	</modules>
19	18
20	19	<!--

Status & tagging log

18:27, 1 August 2009 😂 (talk | contribs) changed the status of r53927 [removed: new added: deferred]