hyphenationtree.java

一个java操作pdf文件的开发包,很好用的.

            } else
                p = d < 0 ? lo[p] : hi[p];
        }
    }

    /**
     * Hyphenate word and return a Hyphenation object.
     * @param word the word to be hyphenated
     * @param remainCharCount Minimum number of characters allowed
     * before the hyphenation point.
     * @param pushCharCount Minimum number of characters allowed after
     * the hyphenation point.
     * @return a {@link Hyphenation Hyphenation} object representing
     * the hyphenated word or null if word is not hyphenated.
     */
    public Hyphenation hyphenate(String word, int remainCharCount,
                                 int pushCharCount) {
        char[] w = word.toCharArray();
        return hyphenate(w, 0, w.length, remainCharCount, pushCharCount);
    }

    /**
     * Hyphenate word and return an array of hyphenation points.
     * @param w char array that contains the word
     * @param offset Offset to first character in word
     * @param len Length of word
     * @param remainCharCount Minimum number of characters allowed
     * before the hyphenation point.
     * @param pushCharCount Minimum number of characters allowed after
     * the hyphenation point.
     * @return a {@link Hyphenation Hyphenation} object representing
     * the hyphenated word or null if word is not hyphenated.
     */
    public Hyphenation hyphenate(char[] w, int offset, int len,
                                 int remainCharCount, int pushCharCount) {
        int i;
        char[] word = new char[len + 3];

        // normalize word
        char[] c = new char[2];
        for (i = 1; i <= len; i++) {
            c[0] = w[offset + i - 1];
            int nc = classmap.find(c, 0);
            if (nc < 0) {    // found a non-letter character, abort
                return null;
            }
            word[i] = (char)nc;
        }
        int[] result = new int[len + 1];
        int k = 0;

        // check exception list first
        String sw = new String(word, 1, len);
        if (stoplist.containsKey(sw)) {
            // assume only simple hyphens (Hyphen.pre="-", Hyphen.post = Hyphen.no = null)
            Vector hw = (Vector)stoplist.get(sw);
            int j = 0;
            for (i = 0; i < hw.size(); i++) {
                Object o = hw.elementAt(i);
                if (o instanceof String) {
                    j += ((String)o).length();
                    if (j >= remainCharCount && j < (len - pushCharCount))
                        result[k++] = j;
                }
            }
        } else {
            // use algorithm to get hyphenation points
            word[0] = '.';                    // word start marker
            word[len + 1] = '.';              // word end marker
            word[len + 2] = 0;                // null terminated
            byte[] il = new byte[len + 3];    // initialized to zero
            for (i = 0; i < len + 1; i++) {
                searchPatterns(word, i, il);
            }

            // hyphenation points are located where interletter value is odd
            for (i = 0; i < len; i++) {
                if (((il[i + 1] & 1) == 1) && i >= remainCharCount
                        && i < (len - pushCharCount)) {
                    result[k++] = i;
                }
            }
        }


        if (k > 0) {
            // trim result array
            int[] res = new int[k];
            System.arraycopy(result, 0, res, 0, k);
            return new Hyphenation(new String(w, offset, len), res);
        } else {
            return null;
        }
    }

    /**
     * Add a character class to the tree. It is used by
     * PatternParser as callback to
     * add character classes. Character classes define the
     * valid word characters for hyphenation. If a word contains
     * a character not defined in any of the classes, it is not hyphenated.
     * It also defines a way to normalize the characters in order
     * to compare them with the stored patterns. Usually pattern
     * files use only lower case characters, in this case a class
     * for letter 'a', for example, should be defined as "aA", the first
     * character being the normalization char.
     */
    public void addClass(String chargroup) {
        if (chargroup.length() > 0) {
            char equivChar = chargroup.charAt(0);
            char[] key = new char[2];
            key[1] = 0;
            for (int i = 0; i < chargroup.length(); i++) {
                key[0] = chargroup.charAt(i);
                classmap.insert(key, 0, equivChar);
            }
        }
    }

    /**
     * Add an exception to the tree. It is used by
     * PatternParser class as callback to
     * store the hyphenation exceptions.
     * @param word normalized word
     * @param hyphenatedword a vector of alternating strings and
     * {@link Hyphen hyphen} objects.
     */
    public void addException(String word, Vector hyphenatedword) {
        stoplist.put(word, hyphenatedword);
    }

    /**
     * Add a pattern to the tree. Mainly, to be used by
     * PatternParser class as callback to
     * add a pattern to the tree.
     * @param pattern the hyphenation pattern
     * @param ivalue interletter weight values indicating the
     * desirability and priority of hyphenating at a given point
     * within the pattern. It should contain only digit characters.
     * (i.e. '0' to '9').
     */
    public void addPattern(String pattern, String ivalue) {
        int k = ivalues.find(ivalue);
        if (k <= 0) {
            k = packValues(ivalue);
            ivalues.insert(ivalue, (char)k);
        }
        insert(pattern, (char)k);
    }

    public void printStats() {
        System.out.println("Value space size = "
                           + Integer.toString(vspace.length()));
        super.printStats();

    }
/*
    public static void main(String[] argv) throws Exception {
        HyphenationTree ht = null;
        int minCharCount = 2;
        BufferedReader in =
            new BufferedReader(new InputStreamReader(System.in));
        for (; ; ) {
            System.out.print("l:\tload patterns from XML\nL:\tload patterns from serialized object\ns:\tset minimun character count\nw:\twrite hyphenation tree to object file\nh:\thyphenate\nf:\tfind pattern\nb:\tbenchmark\nq:\tquit\n\nCommand:");
            String token = in.readLine().trim();
            if (token.equals("f")) {
                System.out.print("Pattern: ");
                token = in.readLine().trim();
                System.out.println("Values: " + ht.findPattern(token));
            } else if (token.equals("s")) {
                System.out.print("Minimun value: ");
                token = in.readLine().trim();
                minCharCount = Integer.parseInt(token);
            } else if (token.equals("l")) {
                ht = new HyphenationTree();
                System.out.print("XML file name: ");
                token = in.readLine().trim();
                ht.loadPatterns(token);
            } else if (token.equals("L")) {
                ObjectInputStream ois = null;
                System.out.print("Object file name: ");
                token = in.readLine().trim();
                try {
                    ois = new ObjectInputStream(new FileInputStream(token));
                    ht = (HyphenationTree)ois.readObject();
                } catch (Exception e) {
                    e.printStackTrace();
                }
                finally {
                    if (ois != null) {
                        try {
                            ois.close();
                        } catch (IOException e) {}
                    }
                }
            } else if (token.equals("w")) {
                System.out.print("Object file name: ");
                token = in.readLine().trim();
                ObjectOutputStream oos = null;
                try {
                    oos = new ObjectOutputStream(new FileOutputStream(token));
                    oos.writeObject(ht);
                } catch (Exception e) {
                    e.printStackTrace();
                }
                finally {
                    if (oos != null) {
                        try {
                            oos.flush();
                        } catch (IOException e) {}
                        try {
                            oos.close();
                        } catch (IOException e) {}
                    }
                }
            } else if (token.equals("h")) {
                System.out.print("Word: ");
                token = in.readLine().trim();
                System.out.print("Hyphenation points: ");
                System.out.println(ht.hyphenate(token, minCharCount,
                                                minCharCount));
            } else if (token.equals("b")) {
                if (ht == null) {
                    System.out.println("No patterns has been loaded.");
                    break;
                }
                System.out.print("Word list filename: ");
                token = in.readLine().trim();
                long starttime = 0;
                int counter = 0;
                ;
                try {
                    BufferedReader reader =
                        new BufferedReader(new FileReader(token));
                    String line;

                    starttime = System.currentTimeMillis();
                    while ((line = reader.readLine()) != null) {
                        // System.out.print("\nline: ");
                        Hyphenation hyp = ht.hyphenate(line, minCharCount,
                                                       minCharCount);
                        if (hyp != null) {
                            String hword = hyp.toString();
                            // System.out.println(line);
                            // System.out.println(hword);
                        } else {
                            // System.out.println("No hyphenation");
                        }
                        counter++;
                    }
                } catch (Exception ioe) {
                    System.out.println("Exception " + ioe);
                    ioe.printStackTrace();
                }
                long endtime = System.currentTimeMillis();
                long result = endtime - starttime;
                System.out.println(counter + " words in " + result
                                   + " Millisekunden hyphenated");

            } else if (token.equals("q"))
                break;
        }

    }*/

}