}

    /**
     * Gets the replacement string for colons in URLs.
     *
     * @return the colon replacement string
     */
    public String getColonStr() {
        return colonStr;
    }

    /**
     * Sets the replacement string for colons in URLs.
     *
     * @param colonStr the colon replacement string to set
     */
    public void setColonStr(final String colonStr) {

     *  The implementation of this is a little slow, since it creates
     *  a number of objects each time it is called.  This could be optimized
     *  to keep the same objects around, but then thread-safety issues would arise.
     *
     *  @param contextNode The node to start searching from.
     *  @param expression A valid XPath string.

            return parse(new GZIPInputStream(bis), false);
        } catch (final CrawlingAccessException e) {
            throw e;
        } catch (final Exception e) {
            throw new CrawlingAccessException("Could not parse Sitemaps: " + preloadDate, e);
        }
    }

    /**
     * Parses a text-based sitemap from the given input stream.
     * @param in the input stream to parse
     * @return the parsed sitemap set

        }

        final ExtractorFactory extractorFactory = crawlerContainer.getComponent("extractorFactory");
        if (extractorFactory == null) {
            throw new CrawlerSystemException("Could not find extractorFactory.");
        }
        final Extractor extractor = extractorFactory.getExtractor(responseData.getMimeType());
        final Map<String, String> params = new HashMap<>();

        } catch (final Exception e) {
            CloseableUtil.closeQuietly(fos); // for deleting file
            FileUtil.deleteInBackground(tempFile); // clean up
            throw new CrawlingAccessException("Could not read a response body: " + responseData.getUrl(), e);
        } finally {
            CloseableUtil.closeQuietly(fos);
        }
        return tempFile;
    }

                is.setEncoding(responseData.getCharSet());
            }
            parser.parse(is);
        } catch (final Exception e) {
            throw new CrawlingAccessException("Could not parse " + responseData.getUrl(), e);
        }
        final Document document = parser.getDocument();

        final StringBuilder buf = new StringBuilder(1000);
        buf.append(getResultDataHeader());

            if (!ignoreException) {
                throw e;
            }
        } catch (final Exception e) {
            if (!ignoreException) {
                throw new CrawlerSystemException("Could not stop a process.", e);
            }
        }
    }

    /**
     * Delays the crawling process before processing a URL.
     */
    protected abstract void delayBeforeProcessing();

    /**

     */
    public MimeTypeHelperImpl() {
        try {
            mimeTypes = MimeTypesFactory.create(MIME_TYPES_RESOURCE_NAME);
        } catch (final Exception e) {
            throw new CrawlerSystemException("Could not initialize MimeTypeHelper.", e);
        }
    }

    @Override
    public String getContentType(final InputStream is, final String filename) {
        final Map<String, String> params = new HashMap<>();

                suffixWords = WordlistLoader.getWordSet(reader);
            } catch (final IOException e) {
                throw new IllegalArgumentException("Could not load " + suffixWordsFile.getAbsolutePath(), e);
            }
        } else {
            suffixWords = new CharArraySet(0, false);
        }
    }

    @Override

                extractData.putValues("resourceName", new String[] { resourceName });
            }

            return extractData;
        } catch (final OfficeException e) {
            throw new ExtractException("Could not extract a content.", e);
        } finally {
            FileUtil.deleteInBackground(inputFile);
            FileUtil.deleteInBackground(outputFile);
        }
    }

    /**