CrawlFilterSpec.groovy

package com.ahalife.controller.system
import com.ahalife.service.WebClientService
import org.springframework.mock.web.MockHttpServletRequest
import org.springframework.mock.web.MockHttpServletResponse
import spock.lang.Specification
import spock.lang.Unroll

import javax.servlet.FilterChain

class CrawlFilterSpec extends Specification {

  CrawlFilter crawlFilter = new CrawlFilter()
  MockHttpServletRequest request
  MockHttpServletResponse response
  FilterChain chain

  def setup() {
    request = new MockHttpServletRequest('GET', '/')
    response = new MockHttpServletResponse()
    chain = Mock(FilterChain)
  }

  @Unroll("queryString #queryString should set downloadUrl #expectedUrl")
  def "CrawlFilter correctly filters bots"() {
    given:
    request.queryString = queryString

    def receivedUrl
    crawlFilter.webClientService = Mock(WebClientService) {
      getPage(_, _) >> { args -> receivedUrl = args[0] }
    }

    boolean doFilter = false
    chain.doFilter(_, _) >> { doFilter = true }

    when: "crawl filter is invoked"
    crawlFilter.doFilter(request, response, chain)

    then:
    doFilter == doFilterCalled
    (doFilterCalled ? 0 : 1) * crawlFilter.webClientService.getPage(_, _)

    where:
    queryString            | doFilterCalled |  expectedUrl
    null                   |           true |  null
    '_escaped_fragment_='  |          false |  'http://localhost:80/?seoFragment=true'
  }

}