List of usage examples for org.apache.poi.xwpf.usermodel XWPFParagraph getParagraphText
public String getParagraphText()
From source file:com.pdf.GetPdf.java
public static void docConvert(Document document, String url, String type) throws IOException, DocumentException { WordExtractor we;/* w w w . j a va2 s .c om*/ if (type.equals("doc")) { HWPFDocument wordDoc = new HWPFDocument(new URL(url).openStream()); we = new WordExtractor(wordDoc); String[] paragraphs = we.getParagraphText(); for (int i = 0; i < paragraphs.length; i++) { paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", ""); document.add(new Paragraph(paragraphs[i])); } } else { XWPFDocument wordDoc = new XWPFDocument(new URL(url).openStream()); List<IBodyElement> contents = wordDoc.getBodyElements(); for (IBodyElement content : contents) { if (content.getElementType() == BodyElementType.PARAGRAPH) { List<XWPFParagraph> paras = content.getBody().getParagraphs(); for (XWPFParagraph para : paras) { document.add(new Paragraph(para.getParagraphText())); } } else if (content.getElementType() == BodyElementType.TABLE) { List<XWPFTable> tables = content.getBody().getTables(); for (XWPFTable table : tables) { List<XWPFTableRow> rows = table.getRows(); for (XWPFTableRow row : rows) { List<XWPFTableCell> tablecells = row.getTableCells(); } } } } } }
From source file:com.project3.utils.poi.DocumentPropertyChecker.java
public static Map<String, HashMap> checkRunPropertiesOfParagraphs(List<XWPFParagraph> pl, List<String> sl, Map<String, String> properties) { Map<String, HashMap> results = new HashMap<>(), tempMap = new HashMap<>(); ArrayList tempList;// w w w .j av a 2 s.c o m String removeString = ""; // Initialize results, strings which were not found in the document are left as EXISTS : false for (String s : sl) { results.put(s, new HashMap<>()); results.get(s).put("EXISTS", false); } for (XWPFParagraph p : pl) { for (String s : sl) { tempMap = null; //Will fail on typos, but pass on extra elements before or after string of interest //Need to change for typo toleration and exactness? if (p.getParagraphText().contains(s)) { tempList = new ArrayList(); tempList.add(s); tempMap = checkPropertiesofParagraphRuns(p, tempList, properties); results.put(s, tempMap.get(s)); removeString = s; break; } } //Remove string if it has been evaluated if (tempMap != null) { sl.remove(removeString); } } return results; }
From source file:com.project3.utils.poi.DocumentPropertyChecker.java
public static Map<String, HashMap> checkPropertiesOfParagraphs(List<XWPFParagraph> pl, List<String> sl, Map<String, String> properties) { Map<String, HashMap> results = new HashMap<>(), tempMap = new HashMap<>(); ArrayList tempList;// www . ja v a2 s .c o m String removeString = ""; // Initialize results, strings which were not found in the document are left as EXISTS : false for (String s : sl) { results.put(s, new HashMap<>()); results.get(s).put("EXISTS", false); } for (XWPFParagraph p : pl) { for (String s : sl) { tempMap = null; //Will fail on typos, but pass on extra elements before or after string of interest //Need to change for typo toleration and exactness? if (p.getParagraphText().contains(s)) { tempMap = checkPropertiesofParagraph(p, s, properties); results.put(s, tempMap.get(s)); removeString = s; break; } } //Remove string if it has been evaluated if (tempMap != null) { sl.remove(removeString); } } return results; }
From source file:com.project3.utils.poiold.DocumentPropertyCheckerOld.java
public static Map<String, HashMap> checkRunPropertiesOfParagraphs(List<XWPFParagraph> pl, ArrayList<String> sl, Map<String, String> properties) { Map<String, HashMap> results = new HashMap<>(), tempMap = new HashMap<>(); ArrayList<String> tempList; String removeString = ""; // Initialize results, strings which were not found in the document are left as EXISTS : false for (String s : sl) { results.put(s, new HashMap<>()); results.get(s).put("EXISTS", false); }/*from ww w . j a va 2 s . co m*/ for (XWPFParagraph p : pl) { for (String s : sl) { tempMap = null; //Will fail on typos, but pass on extra elements before or after string of interest //Need to change for typo toleration and exactness? if (p.getParagraphText().contains(s)) { tempList = new ArrayList(); tempList.add(s); tempMap = checkPropertiesofParagraphRuns(p, tempList, properties); results.put(s, tempMap.get(s)); removeString = s; break; } } //Remove string if it has been evaluated if (tempMap != null) { sl.remove(removeString); } } return results; }
From source file:com.project3.utils.poiold.DocumentPropertyEnumerator.java
public static void showAllParagraphProperties(List<XWPFParagraph> lp) { int i1 = 1;/*w w w . j a v a 2s . c o m*/ for (XWPFParagraph p : lp) { //System.out.println(p.getStyleID() + " " + sl1.getStyle(p.getStyleID()).getCTStyle().xmlText()); System.out.println("____________________________________"); if (p.getParagraphText().trim().length() > 0) { System.out.println("\n#" + i1++ + " LINE: " + p.getParagraphText()); System.out.println("ALIGNMENT: " + p.getAlignment().toString()); System.out.println("BORDER BETWEEN: " + p.getBorderBetween().toString()); System.out.println("BORDER BOTTOM: " + p.getBorderBottom().toString()); System.out.println("BORDER LEFT: " + p.getBorderLeft().toString()); System.out.println("BORDER RIGHT: " + p.getBorderRight().toString()); System.out.println("BORDER TOP: " + p.getBorderTop().toString()); System.out.println("BODY ELEMENT TYPE: " + p.getElementType().toString()); System.out.println("FOOTNOTE: " + p.getFootnoteText()); System.out.println("INDENTATION 1ST LINE: " + p.getIndentationFirstLine()); System.out.println("INDENTATION HANGING: " + p.getIndentationHanging()); System.out.println("INDENTATION LEFT: " + p.getIndentationLeft()); System.out.println("INDENTATION RIGHT: " + p.getIndentationRight()); System.out.println("NUMBERING FORMAT: " + p.getNumFmt()); System.out.println("NUMERIC STYLE ILVL: " + p.getNumIlvl()); System.out.println("STYLE: " + p.getBody().getXWPFDocument().getStyles().getStyle(p.getStyleID())); XWPFParagraphClone pc; pc = new XWPFParagraphClone(p.getCTP(), p.getBody()); System.out.println("SPACING VALUE: " + pc.getCTSpacing(false).getLine().floatValue() / 240); System.out.println("SPACING AFTER: " + p.getSpacingAfter()); System.out.println("SPACING AFTER LINES: " + p.getSpacingAfterLines()); System.out.println("SPACING BEFORE: " + p.getSpacingBefore()); System.out.println("SPACING BEFORE LINES: " + p.getSpacingBeforeLines()); System.out.println("SPACING LINE RULE: " + p.getSpacingLineRule()); System.out.println("VERTICAL ALIGNMENT: " + p.getVerticalAlignment()); } // can also use .searchText to look for a string else { // Uncomment to display lines //System.out.println("\n#" + i1++ + " LINE: <SPACE>"); } } }
From source file:persistentie.PixelMapper.java
public List<String> leesDocFile(String bestandsNaam) { List<String> zin = new ArrayList<>(); letterLijst = new ArrayList<>(); File file = null;/*from www . j a v a2 s .c o m*/ XWPFWordExtractor extractor = null; try { XWPFDocument document = new XWPFDocument(Files.newInputStream(Paths.get(bestandsNaam))); List<XWPFParagraph> paragraphs = document.getParagraphs(); for (XWPFParagraph par : paragraphs) { /** * Elke paragraph op spaties splitten en elk woord in de letterlijst plaatsen. */ zin = Arrays.asList(par.getParagraphText().split(" ")); for (String woord : zin) { letterLijst.add(woord); letterLijst.add(" "); } letterLijst.add("\n"); } } catch (Exception exep) { exep.printStackTrace(); } return letterLijst; }