Date parser

DateParser.java

        final Parser p = new Parser();

        List<String> strings = Files.readLines(new File("c:\\users\\alexv\\Desktop\\task_titles.tsv"), Charset.defaultCharset());

        final Set<Character> chars = newHashSet(' ', '@', ':', '-');
        final Set<String> good_last_words = newHashSet("on", "@", "by", "due", "date", "untill", "til", "till", "at", "for", "before", "after", "in");
        Set<String> text_firsts = newHashSet("today", "tomorrow", "this", "next");
        final Set<String> syntaxTreeBlackList = newHashSet("(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_TIME (HOURS_OF_DAY ) (MINUTES_OF_HOUR ))))", "tomorrow", "this", "next");
        final Set<String> syntaxTreeWhiteList = newHashSet("(DATE_TIME_ALTERNATIVE (DATE_TIME (RELATIVE_DATE (SEEK > by_day  (DAY_OF_WEEK )))))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_DATE (MONTH_OF_YEAR ) (DAY_OF_MONTH ))))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (RELATIVE_DATE (SEEK > by_day  day))))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_TIME (HOURS_OF_DAY ) (MINUTES_OF_HOUR ) pm)))",
                //"(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_TIME (HOURS_OF_DAY ) (MINUTES_OF_HOUR ) am)))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (RELATIVE_DATE (SEEK > by_day  (MONTH_OF_YEAR )))))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_TIME (HOURS_OF_DAY ) (MINUTES_OF_HOUR ) (SECONDS_OF_MINUTE ) pm)))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_DATE (MONTH_OF_YEAR ) (DAY_OF_MONTH ) (YEAR_OF ))))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (RELATIVE_DATE (SEEK > by_day  (DAY_OF_WEEK ))) (EXPLICIT_TIME (HOURS_OF_DAY ) (MINUTES_OF_HOUR ))))",
                "(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_DATE (MONTH_OF_YEAR ) (DAY_OF_MONTH )) (EXPLICIT_TIME (HOURS_OF_DAY ) (MINUTES_OF_HOUR ))))");


        final BufferedWriter bw = new BufferedWriter(new FileWriter("c:\\users\\alexv\\Desktop\\task_dates_at_the_beginning.tsv"));
        final BufferedWriter bw2 = new BufferedWriter(new FileWriter("c:\\users\\alexv\\Desktop\\out.txt"));
        int cnt = 0;
        long start = System.currentTimeMillis();

        for (String string : strings) {
            String line = string.trim();

            line = line.replace("\t", " ");

            cnt++;
            if (cnt % 10000 == 0) {
                System.out.println(cnt);
            }
            bw2.write(line + "\n");
            try {
                List<DateGroup> parse = p.parse(line);
                if (!parse.isEmpty()) {
                    for (DateGroup dateGroup : parse) {
                        int pos = dateGroup.getPosition();
                        String text = dateGroup.getText();
                        String[] text_words = text.split("\\s+");
                        String text_first_word = text_words.length > 0 ? text_words[0] : "";
                        String text_last_word = text_words.length > 0 ? text_words[text_words.length - 1] : "";
                        if (pos == 0) {
                            Character next_char = dateGroup.getText().length() > line.length() ? line.charAt(dateGroup.getText().length()) : '\0';
                            //                          if (chars.contains(last_char)) { // space : - , @
                            String[] words = line.substring(text.length(), line.length()).split("\\s+");
                            String first_word = words.length > 0 ? words[0] : "";
                            String syntaxTree = dateGroup.getSyntaxTree().toStringTree();
                            String syntaxTreeClean = syntaxTree.replaceAll("\\d+", "").replace("am", "pm").trim();
                            //                              if (syntaxTreeBlackList.contains(syntaxTree))
                            //                                continue;
                            //if (last_words.contains(last_word.toLowerCase()) || last_char == '@' || text_firsts.contains(text_first_word.toLowerCase()))
                            //                            if (syntaxTreeWhiteList.contains(syntaxTree)) ||
                            //                                good_last_words.contains(last_word.toLowerCase()) ||
                            //                                last_char == '@'  ||
                            //                                (syntaxTree.equals("(DATE_TIME_ALTERNATIVE (DATE_TIME (EXPLICIT_TIME (HOURS_OF_DAY ) (MINUTES_OF_HOUR ) (SECONDS_OF_MINUTE ) pm)))") && (text_first_word.equals("this") || text_first_word.equals("tonight") || text_first_word.equals("in")))
                            //                                ) {
                            bw.write(text + "\t" + line + "\t" + first_word + "\t" + text_first_word + "\t" + text_last_word + "\t" + next_char + "\t" + syntaxTree + "\t" + syntaxTreeClean + "\n");
                            //                                }
                            //                          }
                        }
                    }
                }
            } catch (Exception e) {
//                                e.printStackTrace();
            }
        }
        bw.close();
        bw2.close();

    }