Révision 3386

TXM/trunk/org.txm.groovy.core/src/groovy/org/txm/scripts/filters/TagSentences/TagSentences.groovy (revision 3386)
115 115 
		/** The corr_tags. */
116 116 
		corr_tags = tc.corr_tags;
117 117
118 
		strongPunct = tc.punct_strong;
118 
		strongPunct = tc.punct_strong; //
119 119
120 120 
		reg_comment = /\A\s*<!--.*-->\s*\Z/
121 121 
		reg_out_of_sentence = /^(.*)<s( [^>]*)?>(.*)$/
......
159 159 
		reg_corr_tags_no_seg2 = /^(.*)<\/($corr_tags_no_seg)>(.*)$/
160 160 
		reg_block_tags = /^(.*)<\/($div_tags|$q_tags)>(.*)$/
161 161 
		reg_block_tag_alone = "<($div_tags|$q_tags)>"
162
163 
		//tc.dump()
164 
		//println "reg_punct=$reg_punct reg_strong_punct=$reg_strong_punct"
162 165 
	}
163 166
164 167 
	/* (non-Javadoc)
TXM/trunk/org.txm.tokenizer.core/src/org/txm/tokenizer/TokenizerClasses.java (revision 3386)
263 263 
	}
264 264
265 265 
	public void recombine() {
266 
		corr_tags = "" + corr_tags_no_seg + "|" + seg_tags + "";
267 
		extraword_tags = "" + div_tags + "|" + q_tags + "|" + extraword1_tags + "";
268 
		punct_strong = "[" + punct_strong1 + "]|" + punct_strong2 + "";
269 
		punct_paren_open = "" + punct_paren_open1 + "|" + punct_paren_open2 + "";
270 
		punct_paren_close = "" + punct_paren_close1 + "|" + punct_paren_close2 + "";
271 
		punct_paren = "" + punct_paren_open + "|" + punct_paren_close + "";
272 
		punct_all = "" + punct_strong + "|" + punct_paren + "|[" + punct_weak + "]";
273 
		word_chars = "[^ " + punct_quotes + "" + punct_strong1 + "" + punct_paren_open1 + "" + punct_paren_close1 + "" + punct_weak + "]+|" + entity + "";
266
267 
		if (corr_tags == null) {
268 
			corr_tags = "" + corr_tags_no_seg + "|" + seg_tags + "";
269 
		}
270 
		if (extraword_tags == null) {
271 
			extraword_tags = "" + div_tags + "|" + q_tags + "|" + extraword1_tags + "";
272 
		}
273 
		if (punct_strong == null) {
274 
			punct_strong = "[" + punct_strong1 + "]|" + punct_strong2 + "";
275 
		}
276 
		if (punct_paren_open == null) {
277 
			punct_paren_open = "" + punct_paren_open1 + "|" + punct_paren_open2 + "";
278 
		}
279 
		if (punct_paren_close == null) {
280 
			punct_paren_close = "" + punct_paren_close1 + "|" + punct_paren_close2 + "";
281 
		}
282 
		if (punct_paren == null) {
283 
			punct_paren = "" + punct_paren_open + "|" + punct_paren_close + "";
284 
		}
285 
		if (punct_all == null) {
286 
			punct_all = "" + punct_strong + "|" + punct_paren + "|[" + punct_weak + "]";
287 
		}
288 
		if (word_chars == null) {
289 
			word_chars = "[^ " + punct_quotes + "" + punct_strong1 + "" + punct_paren_open1 + "" + punct_paren_close1 + "" + punct_weak + "]+|" + entity + "";
290 
		}
274 291 
	}
275 292
276 293 
	/**
......
455 472 
		System.out.println("whitespaces = " + whitespaces + "");
456 473 
		System.out.println("regElision = " + regElision + "");
457 474 
		System.out.println("regPunct = " + regPunct + "");
458 
		System.out.println("TESTS");
475 
		System.out.println("TESTS:");
459 476
460 477 
		for (TTest test : tests) {
461 478 
			System.out.println(" " + test + "");
......
847 864 
			Field[] fields = TokenizerClasses.class.getFields();
848 865 
			for (Field field : fields) {
849 866 
				int m = field.getModifiers();
850 
				if (Modifier.isStatic(m) && Modifier.isPublic(m) && field.getType().equals(String.class)) {
867 
				if (!Modifier.isStatic(m) && Modifier.isPublic(m) && field.getType().equals(String.class)) {
851 868 
					String name = field.getName();
852 869 
					String value = params.get(name, null);
853 870 
					if (value != null) {
854 871 
						try {
855 872 
							if (debug) System.out.println(" Tokenizer parametrized with " + name + "=" + value);
856 
							field.set(field, value);
873 
							field.set(this, value);
857 874 
						}
858 875 
						catch (Exception e) {
859 876 
							Log.printStackTrace(e);

Formats disponibles : Unified diff