List of usage examples for org.apache.commons.configuration BaseConfiguration BaseConfiguration
BaseConfiguration
From source file:revaligner.service.FileAligner.java
private Configuration createConfigForSegmenter(boolean segmentParagraph, String srcLangcode) throws Exception { Configuration config = new BaseConfiguration(); config.setProperty("segmenter.default.paragraphsegmenter", Boolean.valueOf(segmentParagraph)); config.setProperty("segmenter.strategy.trados.rule1enabled", "true"); config.setProperty("segmenter.default.strategy", "trados"); config.setProperty("segmenter.default.simplifier", "fontformat"); config.setProperty("breakiterator.strategy.sentence.trados.esps", createESMString(Locale.makeLocale(srcLangcode))); String abbv = getAbbreviations(srcLangcode); if (!abbv.equals("")) { config.setProperty("abbreviations." + srcLangcode.split("-")[0], abbv); }//from w w w . j a va 2 s . co m return config; }
From source file:revaligner.service.FileAligner.java
public ArrayList<String[]> populateSourceTxlf() throws Exception { System.out.println("populating source txlf with aligned segments...."); ArrayList<String[]> reportStates = new ArrayList(); ExtractionSupportImpl extractionSupportImpl = new ExtractionSupportImpl( Locale.makeLocale(this.sourcelanguage), Locale.makeLocale(this.targetlanguage)); Configuration config = new BaseConfiguration(); config.setProperty("extraction.tokens.extract", "all"); extractionSupportImpl.setConfiguration(config); Locale locale = Locale.makeLocale(this.sourcelanguage); TradosWordCounter wcounter = new TradosWordCounter(locale, config); org.dom4j.Document document_src = XmlParser.parseXmlFile(this.sourcetxlf_nonSeg); org.dom4j.Element root_src = document_src.getRootElement(); org.dom4j.Document document_src_ingt = XmlParser.parseXmlFile(this.sourcetxlf_nonSeg); org.dom4j.Element root_src_ingt = document_src_ingt.getRootElement(); org.dom4j.Document document_src_seg = XmlParser.parseXmlFile(this.sourcetxlf_seg); org.dom4j.Element root_src_seg = document_src_seg.getRootElement(); List<com.aspose.words.Node> list_source = root_src .selectNodes("//*[name() = 'group'][@restype = 'x-paragraph']"); List<com.aspose.words.Node> list_source_ingt = root_src_ingt .selectNodes("//*[name() = 'group'][@restype = 'x-paragraph']"); List<com.aspose.words.Node> list_source_seg = root_src_seg .selectNodes("//*[name() = 'group'][@restype = 'x-paragraph']"); int count = 0; int totalWC = 0; org.dom4j.Document document = XmlParser.parseXmlFile(this.alignedfile); List<org.dom4j.Element> groups = document.getRootElement().element("aligned").elements("group"); for (int i = 0; i < groups.size(); i++) { org.dom4j.Element group = (org.dom4j.Element) groups.get(i); List<org.dom4j.Element> units = group.elements("unit"); if (((org.dom4j.Element) units.get(0)).element("src_para") != null) { boolean isParaAllSegmented = true; for (int j = 0; j < units.size(); j++) { if (((org.dom4j.Element) units.get(j)).attributeValue("alignsegs").equals("false")) { isParaAllSegmented = false; break; }/*from w w w . jav a 2 s . c o m*/ } String srcTextAccepted = group.elementText("text").replaceAll("(?s)<del>.*?</del>", "") .replaceAll("<(/)*ins>", ""); if (!extractionSupportImpl.isExtractable(srcTextAccepted)) { if (isParaAllSegmented) { for (int j = 0; j < units.size(); j++) { org.dom4j.Element unit = (org.dom4j.Element) units.get(j); List<org.dom4j.Element> srcsegs = unit.element("src_para").element("segments") .elements("src_seg"); List<org.dom4j.Element> trgsegs = unit.element("trg_para").element("segments") .elements("trg_seg"); for (int x = 0; x < srcsegs.size(); x++) { String[] s = new String[7]; s[0] = ((org.dom4j.Element) srcsegs.get(x)).getText(); if (x >= trgsegs.size()) { s[1] = ""; } else { org.dom4j.Element trgseg = (org.dom4j.Element) trgsegs.get(x); String id = trgseg.attributeValue("id"); if (id.startsWith("n - ")) { s[1] = trgseg.getText(); } else { List tmp_contents = new ArrayList(); if (id.contains(" - ")) { int start = Integer.parseInt(id.split(" - ")[0]); int end = Integer.parseInt(id.split(" - ")[1]); tmp_contents.addAll( (Collection) this.txlftrgsegmap.get(Integer.valueOf(start))); for (int su = start + 1; su <= end; su++) { boolean isprevendofpara = ((boolean[]) this.txlftrgsewsmap .get(Integer.valueOf(su - 1)))[1]; boolean iscurrentstartofpara = ((boolean[]) this.txlftrgsewsmap .get(Integer.valueOf(su)))[0]; if ((isprevendofpara) && (iscurrentstartofpara)) { List prevseg = (List) this.txlftrgsegmap .get(Integer.valueOf(su - 1)); int previdx = -1; for (int prev = 0; prev < prevseg.size(); prev++) { org.dom4j.Node prevnode = (org.dom4j.Node) prevseg .get(prev); if (prevnode.getNodeType() == 1) { org.dom4j.Element prevnode_e = (org.dom4j.Element) prevnode; if ((prevnode_e.getName().equals("ws")) && (prevnode_e .attributeValue("pos").equals("after"))) { previdx = prevseg.size() - prev; } } } if (previdx != -1) { tmp_contents.remove(tmp_contents.size() - previdx); } List currseg = (List) this.txlftrgsegmap .get(Integer.valueOf(su)); int curridx = -1; for (int curr = 0; curr < currseg.size(); curr++) { org.dom4j.Node currnode = (org.dom4j.Node) currseg .get(curr); if (currnode.getNodeType() == 1) { org.dom4j.Element currnode_e = (org.dom4j.Element) currnode; if ((currnode_e.getName().equals("ws")) && (currnode_e .attributeValue("pos").equals("before"))) { curridx = curr; } } } if (curridx != -1) { currseg.remove(curridx); } if (Locale.makeLocale(this.targetlanguage).isFarEast()) { tmp_contents.addAll(currseg); } else { tmp_contents.add(DocumentHelper.createText(" ")); tmp_contents.addAll(currseg); } } else { tmp_contents.addAll((Collection) this.txlftrgsegmap .get(Integer.valueOf(su))); } } } else { tmp_contents.addAll((Collection) this.txlftrgsegmap .get(Integer.valueOf(Integer.parseInt(id)))); } s[1] = trimText(assembleText(tmp_contents).replace("<br> ", "↵<br>"), false)[0]; } } s[2] = "N/A"; s[3] = "N/A"; s[4] = ((org.dom4j.Element) srcsegs.get(x)).attributeValue("tctype"); s[5] = "0"; s[6] = ""; reportStates.add(s); } } } else { String[] s = new String[7]; for (int j = 0; j < units.size(); j++) { s[0] = ((org.dom4j.Element) units.get(j)).element("src_para").elementText("text"); if (((org.dom4j.Element) units.get(j)).element("trg_para") != null) { s[1] = ((org.dom4j.Element) units.get(j)).element("trg_para").elementText("text"); } else { s[1] = ""; } s[2] = "N/A"; s[3] = "N/A"; s[4] = ((org.dom4j.Element) units.get(j)).element("src_para").attributeValue("tctype"); s[5] = "0"; s[6] = ""; reportStates.add(s); } } } else { if (isParaAllSegmented) { org.dom4j.Element txlf_group = (org.dom4j.Element) list_source.get(count); org.dom4j.Element txlf_group_ingt = (org.dom4j.Element) list_source_ingt.get(count); org.dom4j.Element txlf_group_seg = (org.dom4j.Element) list_source_seg.get(count); txlf_group.setContent(txlf_group_seg.content()); List transunits = txlf_group.elements("trans-unit"); txlf_group_ingt.setContent(txlf_group_seg.content()); List transunits_ingt = txlf_group_ingt.elements("trans-unit"); ArrayList<String> mergedsegtext = new ArrayList(); ArrayList<List> merged_trg_contents = new ArrayList(); ArrayList<String> mergedsegtctypes = new ArrayList(); ArrayList<String> keys = new ArrayList(); ArrayList<String> key_left = new ArrayList(); ArrayList<String> key_right = new ArrayList(); ArrayList<String> org_keys = new ArrayList(); ArrayList<String> trg_keys = new ArrayList(); ArrayList<List> trg_contents = new ArrayList(); ArrayList<String> src_tctypes = new ArrayList(); ArrayList<String> src_review_stats = new ArrayList(); ArrayList<String> src_ignore_stats = new ArrayList(); ArrayList<Integer> edited_idx = new ArrayList(); for (int j = 0; j < units.size(); j++) { org.dom4j.Element unit = (org.dom4j.Element) units.get(j); org.dom4j.Element src_para = unit.element("src_para"); org.dom4j.Element trg_para = unit.element("trg_para"); List src_segs = src_para.element("segments").elements("src_seg"); for (int z = 0; z < src_segs.size(); z++) { org.dom4j.Element src_seg = (org.dom4j.Element) src_segs.get(z); src_tctypes.add(src_seg.attributeValue("tctype")); src_review_stats.add(src_seg.attributeValue("needreview")); src_ignore_stats.add(src_seg.attributeValue("ignored")); keys.add(src_seg.getText().replaceAll("(?s)<del>.*?</del>", "") .replaceAll("<(/)*ins>", "").replace("<br>", "").trim()); org_keys.add(src_seg.getText()); if (trg_para != null) { List trg_segs = trg_para.element("segments").elements("trg_seg"); if (((org.dom4j.Element) trg_segs.get(z)).attributeValue("edited") .equals("true")) { edited_idx.add(Integer.valueOf(trg_contents.size())); } if (trg_segs.size() > z) { trg_keys.add(((org.dom4j.Element) trg_segs.get(z)).getText()); String id = ((org.dom4j.Element) trg_segs.get(z)).attributeValue("id"); if (id.startsWith("n - ")) { trg_contents.add(new ArrayList()); } else { List tmp_contents = new ArrayList(); if (id.contains(" - ")) { int start = Integer.parseInt(id.split(" - ")[0]); int end = Integer.parseInt(id.split(" - ")[1]); tmp_contents.addAll((Collection) this.txlftrgsegmap .get(Integer.valueOf(start))); for (int su = start + 1; su <= end; su++) { boolean isprevendofpara = ((boolean[]) this.txlftrgsewsmap .get(Integer.valueOf(su - 1)))[1]; boolean iscurrentstartofpara = ((boolean[]) this.txlftrgsewsmap .get(Integer.valueOf(su)))[0]; if ((isprevendofpara) && (iscurrentstartofpara)) { List prevseg = (List) this.txlftrgsegmap .get(Integer.valueOf(su - 1)); int previdx = -1; for (int prev = 0; prev < prevseg.size(); prev++) { org.dom4j.Node prevnode = (org.dom4j.Node) prevseg .get(prev); if (prevnode.getNodeType() == 1) { org.dom4j.Element prevnode_e = (org.dom4j.Element) prevnode; if ((prevnode_e.getName().equals("ws")) && (prevnode_e.attributeValue("pos") .equals("after"))) { previdx = prevseg.size() - prev; } } } if (previdx != -1) { tmp_contents.remove(tmp_contents.size() - previdx); } List currseg = (List) this.txlftrgsegmap .get(Integer.valueOf(su)); int curridx = -1; for (int curr = 0; curr < currseg.size(); curr++) { org.dom4j.Node currnode = (org.dom4j.Node) currseg .get(curr); if (currnode.getNodeType() == 1) { org.dom4j.Element currnode_e = (org.dom4j.Element) currnode; if ((currnode_e.getName().equals("ws")) && (currnode_e.attributeValue("pos") .equals("before"))) { curridx = curr; } } } if (curridx != -1) { currseg.remove(curridx); } if (Locale.makeLocale(this.targetlanguage).isFarEast()) { tmp_contents.addAll(currseg); } else { tmp_contents.add(DocumentHelper.createText(" ")); tmp_contents.addAll(currseg); } } else { tmp_contents.addAll((Collection) this.txlftrgsegmap .get(Integer.valueOf(su))); } } } else { tmp_contents.addAll((Collection) this.txlftrgsegmap .get(Integer.valueOf(Integer.parseInt(id)))); } trg_contents.add(tmp_contents); } } else { trg_keys.add(""); trg_contents.add(new ArrayList()); } } else { trg_keys.add(""); trg_contents.add(new ArrayList()); } if ((z == 0) && (z == src_segs.size() - 1)) { key_left.add(src_para.attributeValue("lefttrim")); key_right.add(src_para.attributeValue("righttrim")); } else if (z == 0) { key_left.add(src_para.attributeValue("lefttrim")); key_right.add("true"); } else if (z == src_segs.size() - 1) { key_left.add("true"); key_right.add(src_para.attributeValue("righttrim")); } else { key_left.add("true"); key_right.add("true"); } } } SegmenterFactory factory = new SegmenterFactory(); Configuration segconfig = createConfigForSegmenter(false, this.sourcelanguage); Segmenter segmenter = factory.getSegmenter("trados", Locale.makeLocale(this.sourcelanguage), segconfig); List<String> finsegs = segmenter .segment(group.elementText("text").replaceAll("(?s)<del>.*?</del>", "") .replaceAll("<(/)*ins>", "").replace("<br>", "").replace("<", "<") .replace(">", ">").replace("&", "&")); ArrayList<ArrayList<Integer>> indices = new ArrayList(); int key_start_index = 0; for (int k = 0; k < finsegs.size(); k++) { String finsegtext = ((String) finsegs.get(k)).replace("&", "&").replace("<", "<") .replace(">", ">"); String combined_key = ""; ArrayList<Integer> indice = new ArrayList(); for (int x = key_start_index; x < keys.size(); x++) { combined_key = combined_key + (String) keys.get(x); indice.add(Integer.valueOf(x)); if (combined_key.replace("", " ").trim().replaceAll("(\\s)+", "") .equals(finsegtext.replace("", " ").trim().replaceAll("(\\s)+", ""))) { indices.add(indice); key_start_index = x + 1; break; } } } ArrayList<Integer> merged_edited_idx = new ArrayList(); ArrayList<String[]> statss = new ArrayList(); for (int m = 0; m < indices.size(); m++) { boolean iscontentsuseable = true; ArrayList<Integer> temp_indice = (ArrayList) indices.get(m); String temp_src = ""; String temp_org_src = ""; String temp_trg = ""; List temp_trg_content = new ArrayList(); int id = 1; int rid = 1; int bxrid = 1; int bptrid = 1; int bxid = 1; int bptid = 1; HashMap<String, String> map_rid = new HashMap(); String temp_tctype = (String) src_tctypes .get(((Integer) temp_indice.get(0)).intValue()); String temp_review_stats = (String) src_review_stats .get(((Integer) temp_indice.get(0)).intValue()); for (Iterator localIterator = temp_indice.iterator(); localIterator.hasNext();) { int it = ((Integer) localIterator.next()).intValue(); temp_tctype = temp_tctype.equals(src_tctypes.get(it)) ? temp_tctype : "MIX"; temp_review_stats = ((String) src_review_stats.get(it)).equals("true") ? "true" : temp_review_stats.equals("true") ? "true" : "false"; String temp_ignore_stats = (String) src_ignore_stats.get(it); if (edited_idx.contains(Integer.valueOf(it))) { iscontentsuseable = false; } temp_src = temp_src + (String) keys.get(it); temp_org_src = temp_org_src + (String) org_keys.get(it); if (temp_ignore_stats.equals("true")) { temp_trg = temp_trg + "[skipseg]"; temp_trg_content.add(DocumentHelper.createText("[skipseg]")); } else { temp_trg = temp_trg + (String) trg_keys.get(it); List trg_content = (List) trg_contents.get(it); for (int nc = 0; nc < trg_content.size(); nc++) { org.dom4j.Node raw = (org.dom4j.Node) trg_content.get(nc); if (raw.getNodeType() == 3) { temp_trg_content.add(raw); } else if (raw.getNodeType() == 1) { org.dom4j.Element rawe = (org.dom4j.Element) raw; if (rawe.getName().equals("source")) { for (int ncc = 0; ncc < rawe.content().size(); ncc++) { org.dom4j.Node node = (org.dom4j.Node) rawe.content().get(ncc); if (node.getNodeType() == 3) { temp_trg_content.add(node); } else if (node.getNodeType() == 1) { org.dom4j.Element e = (org.dom4j.Element) node; if (!e.getName().equals("x")) { if (!e.getName().equals("ph")) { if (e.getName().equals("bx")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf( Integer.valueOf(it)) != 0)) { continue; } if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } else if (e.getName().equals("ex")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf(Integer.valueOf( it)) != temp_indice.size() - 1)) { continue; } if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } else if (e.getName().equals("bpt")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf( Integer.valueOf(it)) != 0)) { continue; } if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } else if (e.getName().equals("ept")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf(Integer.valueOf( it)) != temp_indice.size() - 1)) { continue; } if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } } } if (e.attribute("fake") != null) { e.remove(e.attribute("fake")); } temp_trg_content.add(e); } } } else if (rawe.getName().equals("ws")) { String pos = rawe.attributeValue("pos"); if (pos.equals("before")) { for (int ncc = 0; ncc < rawe.content().size(); ncc++) { org.dom4j.Node node = (org.dom4j.Node) rawe.content() .get(ncc); if (node.getNodeType() == 3) { temp_trg_content.add(0, node); } else if (node.getNodeType() == 1) { org.dom4j.Element e = (org.dom4j.Element) node; if ((!e.getName().equals("x")) && (e.getName().equals("it"))) { if (e.attributeValue("pos").equals("open")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf( Integer.valueOf(it)) != 0)) { continue; } if (e.getText().equals("")) { e.setName("bx"); } else { e.setName("bpt"); } if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } else if (e.attributeValue("pos") .equals("close")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf(Integer.valueOf( it)) != temp_indice.size() - 1)) { continue; } if (e.getText().equals("")) { e.setName("ex"); } else { e.setName("ept"); } e.remove(e.attribute("ctype")); if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } e.remove(e.attribute("pos")); } else { if (e.attribute("fake") != null) { e.remove(e.attribute("fake")); } temp_trg_content.add(0, e); } } } } else if (pos.equals("after")) { for (int ncc = 0; ncc < rawe.content().size(); ncc++) { org.dom4j.Node node = (org.dom4j.Node) rawe.content() .get(ncc); if (node.getNodeType() == 3) { temp_trg_content.add(node); } else if (node.getNodeType() == 1) { org.dom4j.Element e = (org.dom4j.Element) node; if ((!e.getName().equals("x")) && (e.getName().equals("it"))) { if (e.attributeValue("pos").equals("open")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf( Integer.valueOf(it)) != 0)) { continue; } if (e.getText().equals("")) { e.setName("bx"); } else { e.setName("bpt"); } if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } else if (e.attributeValue("pos") .equals("close")) { if ((e.attribute("fake") != null) && (e.attributeValue("fake") .equals("true")) && (temp_indice.indexOf(Integer.valueOf( it)) != temp_indice.size() - 1)) { continue; } if (e.getText().equals("")) { e.setName("ex"); } else { e.setName("ept"); } e.remove(e.attribute("ctype")); if ((e.attribute("fake") == null) || (!e.attributeValue("fake") .equals("true"))) { } } e.remove(e.attribute("pos")); } else { if (e.attribute("fake") != null) { e.remove(e.attribute("fake")); } temp_trg_content.add(e); } } } } } } } } } String[] stats = TrackChangeHelper.getTxlfTrgStatsFromTCType(temp_tctype, temp_trg); if ((stats[0].equals("1")) && (temp_review_stats.equals("true"))) { stats[2] = "fuzzy-match"; } String[] s = new String[7]; s[0] = temp_org_src.replace("<br> ", "↵<br>"); if (iscontentsuseable) { s[1] = trimText(assembleText(temp_trg_content).replace("<br> ", "↵<br>"), false)[0]; } else { s[1] = temp_trg.replace("<br> ", "↵<br>"); } if (s[1].contains("[skipseg]")) { if (s[1].replace("[skipseg]", "").trim().equals("")) { s[1] = ""; temp_trg_content = new ArrayList(); temp_trg_content.add(DocumentHelper.createText("")); temp_trg = ""; stats[0] = "1"; stats[1] = "translated"; stats[2] = "exact-match"; } else { s[1] = s[1].replace("[skipseg]", ""); temp_trg_content = replacetextinDomObj(temp_trg_content); temp_trg = temp_trg.replace("[skipseg]", ""); } } s[2] = stats[0]; s[3] = stats[2]; s[4] = temp_tctype; wcounter = new TradosWordCounter(locale, config); wcounter.countText(((org.dom4j.Element) transunits.get(m)).element("source").getText()); s[5] = Integer.toString(wcounter.getWordCount()); s[6] = ""; totalWC += wcounter.getWordCount(); reportStates.add(s); if (extractionSupportImpl.isExtractable(temp_src)) { mergedsegtext.add(temp_trg); if (!iscontentsuseable) { merged_edited_idx.add(Integer.valueOf(merged_trg_contents.size())); } merged_trg_contents.add(temp_trg_content); mergedsegtctypes.add(temp_tctype); statss.add(stats); } } for (int t = 0; t < transunits.size(); t++) { org.dom4j.Element trans_unit = (org.dom4j.Element) transunits.get(t); org.dom4j.Element trans_unit_ignt = (org.dom4j.Element) transunits_ingt.get(t); trans_unit.addAttribute("gs4tr:editStatus", "leveraged"); org.dom4j.Element source = trans_unit.element("source"); org.dom4j.Element target = trans_unit.addElement("target"); trans_unit.elements().add(source.indexOf(source.getParent()) + 2, target.clone()); trans_unit.remove(target); target = trans_unit.element("target"); org.dom4j.Element target_ignt = trans_unit_ignt.addElement("target"); trans_unit_ignt.elements().add(source.indexOf(source.getParent()) + 2, target_ignt.clone()); trans_unit_ignt.remove(target_ignt); target_ignt = trans_unit_ignt.element("target"); if (merged_edited_idx.contains(Integer.valueOf(t))) { target.setText(((String) mergedsegtext.get(t)).replace("<", "<") .replace(">", ">").replace("&", "&").trim()); target_ignt.setText(((String) mergedsegtext.get(t)).replace("<", "<") .replace(">", ">").replace("&", "&").trim()); } else { target.setContent(trimContents((List) merged_trg_contents.get(t))); target_ignt.setContent(trimContents((List) merged_trg_contents.get(t))); if (!((String[]) statss.get(t))[0].equals("75")) { org.dom4j.Element source_ingt = trans_unit_ignt.element("source"); source_ingt.setContent(trimContents((List) merged_trg_contents.get(t))); } } String[] stats = (String[]) statss.get(t); if (stats[0].equals("1")) { trans_unit.addAttribute("gs4tr:locked", "true"); } target.addAttribute("gs4tr:score", stats[0]); target.addAttribute("state", stats[1]); target.addAttribute("state-qualifier", stats[2]); if (stats[0].equals("0")) { trans_unit.remove(target); } } } else { String trgtext = ""; if (((org.dom4j.Element) units.get(0)).element("trg_para") != null) { trgtext = ((org.dom4j.Element) units.get(0)).element("trg_para").elementText("text"); } String temp_tctype = ((org.dom4j.Element) units.get(0)).element("src_para") .attributeValue("tctype"); for (int j = 1; j < units.size(); j++) { org.dom4j.Element prev_unit = (org.dom4j.Element) units.get(j - 1); org.dom4j.Element unit = (org.dom4j.Element) units.get(j); String src_tctype = unit.element("src_para").attributeValue("tctype"); temp_tctype = temp_tctype.equals(src_tctype) ? temp_tctype : "MIX"; if (unit.element("trg_para") != null) { String Rtrim = prev_unit.element("src_para").attributeValue("righttrim"); String Ltrim = unit.element("src_para").attributeValue("lefttrim"); if ((Rtrim.equals("true")) || (Ltrim.equals("true"))) { trgtext = trgtext + " " + unit.element("trg_para").elementText("text"); } else { trgtext = trgtext + unit.element("trg_para").elementText("text"); } } } org.dom4j.Element txlf_group = (org.dom4j.Element) list_source.get(count); org.dom4j.Element trans_unit = txlf_group.element("trans-unit"); trans_unit.addAttribute("gs4tr:editStatus", "leveraged"); org.dom4j.Element source = trans_unit.element("source"); org.dom4j.Element target = trans_unit.addElement("target"); trans_unit.elements().add(source.indexOf(source.getParent()) + 2, target.clone()); trans_unit.remove(target); target = trans_unit.element("target"); int lb_cnt = 0; String surfix = trgtext; while (surfix.indexOf("<br> ") != -1) { lb_cnt++; int pos = surfix.indexOf("<br> "); String prefix = surfix.substring(0, pos); target.addText(prefix.replace("<", "<").replace(">", ">").replace("&", "&")); org.dom4j.Element x = target.addElement("x"); x.addAttribute("ctype", "lb"); x.addAttribute("id", Integer.toString(lb_cnt)); x.addAttribute("equiv-text", " "); surfix = surfix.substring(pos + 5, surfix.length()); } target.addText(surfix.replace("<", "<").replace(">", ">").replace("&", "&")); String[] stats = TrackChangeHelper.getTxlfTrgStatsFromTCType(temp_tctype, trgtext); target.addAttribute("gs4tr:score", stats[0]); target.addAttribute("state", stats[1]); target.addAttribute("state-qualifier", stats[2]); String[] s = new String[7]; s[0] = group.elementText("text").replace("<br> ", "↵<br>"); s[1] = trgtext.replace("<br> ", "↵<br>"); s[2] = stats[0]; s[3] = stats[2]; s[4] = temp_tctype; wcounter = new TradosWordCounter(locale, config); wcounter.countText(source.getText()); s[5] = Integer.toString(wcounter.getWordCount()); s[6] = ""; totalWC += wcounter.getWordCount(); reportStates.add(s); } count++; } } } root_src.element("file").addAttribute("gs4tr:wordcount", Integer.toString(totalWC)); fixTxlfTrgTags(document_src); this.populatedsourcetxlf = (this.sourcefile + ".txlf"); if (new File(this.populatedsourcetxlf).exists()) { new File(this.populatedsourcetxlf).delete(); } OutputStreamWriter writer = new OutputStreamWriter( new BufferedOutputStream(new FileOutputStream(this.populatedsourcetxlf)), "UTF8"); document_src.write(writer); writer.close(); removeBlankLinesAndNameSpace(this.populatedsourcetxlf); root_src_ingt.element("file").addAttribute("gs4tr:wordcount", Integer.toString(totalWC)); fixTxlfTrgTags(document_src_ingt); String ingtfile = this.sourcefile + ".ingt.txlf"; if (new File(ingtfile).exists()) { new File(ingtfile).delete(); } OutputStreamWriter writer_ingt = new OutputStreamWriter( new BufferedOutputStream(new FileOutputStream(ingtfile)), "UTF8"); document_src_ingt.write(writer_ingt); writer_ingt.close(); removeBlankLinesAndNameSpace(ingtfile); return reportStates; }
From source file:revaligner.service.FileAligner.java
public void createTargetFile() throws Exception { System.out.println("creating target file...."); if (!isReplaceStyleAvailable(new com.aspose.words.Document(this.backupsourcefile))) { throw new Exception("cannot create target file, replace styles not available"); }/*from w ww . j a v a 2s . c o m*/ Configuration config = new BaseConfiguration(); MergeDOC merger = new MergeDOC(); merger.setConfiguration(config); merger.setOverwriteOriginalFile(false); XliffDocument xliffDocument = null; String tmp_translatedtxlf = this.translatedtxlf + ".tmp"; FileUtils.copyFile(new File(this.translatedtxlf), new File(tmp_translatedtxlf), true); List<String[]> notesinfo = integrateNotesIntoSegments(tmp_translatedtxlf); xliffDocument = new XliffDocument(new File(tmp_translatedtxlf)); String skeletonFile = this.sourcefile; com.aspose.words.Document document = new AsposeFactory() .createDocumentInstance(new FileInputStream(skeletonFile)); Configuration docConfig = xliffDocument.getConfiguration(new OfficeConfigurationConverterImpl()); WordDocumentAligner aligner = new WordDocumentAligner(document, xliffDocument); aligner.addWordConfiguration(docConfig); aligner.align(); String ext = this.sourcefile.substring(this.sourcefile.lastIndexOf('.'), this.sourcefile.length()); String name = new File(this.sourcefile).getName(); this.aligneddoc = (new File(this.translatedtxlf).getParent() + File.separator + name.substring(0, name.lastIndexOf(".")) + "_" + this.targetlanguage + ext); aligner.writeAlignedDocument(new File(this.aligneddoc)); com.aspose.words.Document trg_doc = new com.aspose.words.Document(this.aligneddoc); if (this.replacestyles[1] == doublestrikethrough) { for (int i = 0; i < trg_doc.getChildNodes(21, true).getCount(); i++) { Run run = (Run) trg_doc.getChildNodes(21, true).get(i); if ((run.getFont().getUnderline() == this.replacestyles[0]) && (run.getFont().getDoubleStrikeThrough() == true)) { run.getFont().setUnderline(1); run.getFont().setDoubleStrikeThrough(false); run.getFont().setStrikeThrough(true); } else if (run.getFont().getUnderline() == this.replacestyles[0]) { run.getFont().setUnderline(1); } else if (run.getFont().getDoubleStrikeThrough() == true) { run.getFont().setDoubleStrikeThrough(false); run.getFont().setStrikeThrough(true); } } } else { for (int i = 0; i < trg_doc.getChildNodes(21, true).getCount(); i++) { Run run = (Run) trg_doc.getChildNodes(21, true).get(i); if (run.getFont().getUnderline() == this.replacestyles[2]) { run.getFont().setUnderline(1); run.getFont().setStrikeThrough(true); } else if (run.getFont().getUnderline() == this.replacestyles[0]) { run.getFont().setUnderline(1); } else if (run.getFont().getUnderline() == this.replacestyles[1]) { run.getFont().setUnderline(0); run.getFont().setStrikeThrough(true); } } } removeIgnoredSegments(trg_doc, Locale.makeLocale(this.targetlanguage)); removeIgnoredParagraphs(trg_doc); insertComments(trg_doc, notesinfo); trg_doc.save(this.aligneddoc); if (xliffDocument != null) { xliffDocument.dispose(); } new File(tmp_translatedtxlf).delete(); }