Examples with Pattern java.util.regex.Pattern used on opensource projects

Example 36 with Pattern

use of java.util.regex.Pattern in project CoreNLP by stanfordnlp.

the class Units method loadUnits.

public static List<Unit> loadUnits(String filename) throws IOException {
    Pattern commaPattern = Pattern.compile("\\s*,\\s*");
    BufferedReader br = IOUtils.getBufferedFileReader(filename);
    String headerString = br.readLine();
    String[] header = commaPattern.split(headerString);
    Map<String, Integer> headerIndex = new HashMap<>();
    for (int i = 0; i < header.length; i++) {
        headerIndex.put(header[i], i);
    }
    int iName = headerIndex.get("unit");
    int iPrefix = headerIndex.get("prefix");
    int iSymbol = headerIndex.get("symbol");
    int iType = headerIndex.get("type");
    int iSystem = headerIndex.get("system");
    int iDefaultUnit = headerIndex.get("defaultUnit");
    int iDefaultUnitScale = headerIndex.get("defaultUnitScale");
    String line;
    List<Unit> list = new ArrayList<>();
    Map<String, Unit> unitsByName = new HashMap<>();
    Map<String, Pair<String, Double>> unitToDefaultUnits = new HashMap<>();
    while ((line = br.readLine()) != null) {
        String[] fields = commaPattern.split(line);
        Unit unit = new Unit(fields[iName], fields[iSymbol], fields[iType].toUpperCase());
        unit.system = fields[iSystem];
        if (fields.length > iPrefix) {
            unit.prefixSystem = fields[iPrefix];
        }
        if (fields.length > iDefaultUnit) {
            double scale = 1.0;
            if (fields.length > iDefaultUnitScale) {
                scale = Double.parseDouble(fields[iDefaultUnitScale]);
            }
            unitToDefaultUnits.put(unit.getName(), Pair.makePair(fields[iDefaultUnit], scale));
        }
        unitsByName.put(unit.getName(), unit);
        list.add(unit);
    }
    for (Map.Entry<String, Pair<String, Double>> entry : unitToDefaultUnits.entrySet()) {
        Unit unit = unitsByName.get(entry.getKey());
        Unit defaultUnit = unitsByName.get(entry.getValue().first);
        if (defaultUnit != null) {
            unit.defaultUnit = defaultUnit;
            unit.defaultUnitScale = entry.getValue().second;
        } else {
            Redwood.Util.warn("Unknown default unit " + entry.getValue().first + " for " + entry.getKey());
        }
    }
    br.close();
    return list;
}

Example 37 with Pattern

use of java.util.regex.Pattern in project CoreNLP by stanfordnlp.

the class CMMClassifier method getThresholds.

private static List<Pair<Pattern, Integer>> getThresholds(String filename) {
    BufferedReader in = null;
    try {
        in = IOUtils.readerFromString(filename);
        List<Pair<Pattern, Integer>> thresholds = new ArrayList<>();
        for (String line; (line = in.readLine()) != null; ) {
            int i = line.lastIndexOf(' ');
            Pattern p = Pattern.compile(line.substring(0, i));
            //log.info(":"+line.substring(0,i)+":");
            Integer t = Integer.valueOf(line.substring(i + 1));
            Pair<Pattern, Integer> pair = new Pair<>(p, t);
            thresholds.add(pair);
        }
        in.close();
        return thresholds;
    } catch (IOException e) {
        throw new RuntimeIOException("Error reading threshold file", e);
    } finally {
        IOUtils.closeIgnoringExceptions(in);
    }
}

Example 38 with Pattern

use of java.util.regex.Pattern in project CoreNLP by stanfordnlp.

the class MultiWordStringMatcher method getPattern.

public Pattern getPattern(String targetString) {
    Pattern pattern = targetStringPatternCache.get(targetString);
    if (pattern == null) {
        pattern = createPattern(targetString);
        targetStringPatternCache.put(targetString, pattern);
    }
    return pattern;
}

Example 39 with Pattern

use of java.util.regex.Pattern in project CoreNLP by stanfordnlp.

the class TreeToTSV method main.

public static void main(String[] args) {
    if (args.length < 1) {
        System.err.printf("Usage: java %s tree_file%n", TreeToTSV.class.getName());
        System.exit(-1);
    }
    String treeFile = args[0];
    try {
        BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
        TreeReaderFactory trf = new SpanishTreeReaderFactory();
        TreeReader tr = trf.newTreeReader(br);
        StringBuilder sb = new StringBuilder();
        String nl = System.getProperty("line.separator");
        Pattern nePattern = Pattern.compile("^grup\\.nom\\.");
        Pattern npPattern = Pattern.compile("^np0000.$");
        for (Tree tree; (tree = tr.readTree()) != null; ) {
            for (Tree t : tree) {
                if (!t.isPreTerminal())
                    continue;
                char type = 'O';
                Tree grandma = t.ancestor(1, tree);
                String grandmaValue = ((CoreLabel) grandma.label()).value();
                // grup.nom.x
                if (nePattern.matcher(grandmaValue).find())
                    type = grandmaValue.charAt(9);
                else // else check the pos for np0000x or not
                {
                    String pos = ((CoreLabel) t.label()).value();
                    if (npPattern.matcher(pos).find())
                        type = pos.charAt(6);
                }
                Tree wordNode = t.firstChild();
                String word = ((CoreLabel) wordNode.label()).value();
                sb.append(word).append("\t");
                switch(type) {
                    case 'p':
                        sb.append("PERS");
                        break;
                    case 'l':
                        sb.append("LUG");
                        break;
                    case 'o':
                        sb.append("ORG");
                        break;
                    case '0':
                        sb.append("OTROS");
                        break;
                    default:
                        sb.append("O");
                }
                sb.append(nl);
            }
            sb.append(nl);
        }
        System.out.print(sb.toString());
        tr.close();
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

Example 40 with Pattern

use of java.util.regex.Pattern in project CoreNLP by stanfordnlp.

the class ChineseSimWordAvgDepGrammar method getMap.

public Map<Pair<Integer, String>, List<Triple<Integer, String, Double>>> getMap(String filename) {
    Map<Pair<Integer, String>, List<Triple<Integer, String, Double>>> hashMap = Generics.newHashMap();
    try {
        BufferedReader wordMapBReader = new BufferedReader(new InputStreamReader(new FileInputStream(filename), "UTF-8"));
        String wordMapLine;
        Pattern linePattern = Pattern.compile("sim\\((.+)/(.+):(.+)/(.+)\\)=(.+)");
        while ((wordMapLine = wordMapBReader.readLine()) != null) {
            Matcher m = linePattern.matcher(wordMapLine);
            if (!m.matches()) {
                log.info("Ill-formed line in similar word map file: " + wordMapLine);
                continue;
            }
            Pair<Integer, String> iTW = new Pair<>(wordIndex.addToIndex(m.group(1)), m.group(2));
            double score = Double.parseDouble(m.group(5));
            List<Triple<Integer, String, Double>> tripleList = hashMap.get(iTW);
            if (tripleList == null) {
                tripleList = new ArrayList<>();
                hashMap.put(iTW, tripleList);
            }
            tripleList.add(new Triple<>(wordIndex.addToIndex(m.group(3)), m.group(4), score));
        }
    } catch (IOException e) {
        throw new RuntimeException("Problem reading similar words file!");
    }
    return hashMap;
}