Merge pull request #462 from knu/liquid-to_xpath
Add a Liquid filter `to_xpath`, which quotes a string for use in XPath expression.
Akinori MUSHA
3 changed files with 54 additions and 8 deletions
+ 19
- 2
app/concerns/liquid_interpolatable.rb
@@ -43,12 +43,29 @@ module LiquidInterpolatable |
||
| 43 | 43 |
end |
| 44 | 44 |
|
| 45 | 45 |
require 'uri' |
| 46 |
- # Percent encoding for URI conforming to RFC 3986. |
|
| 47 |
- # Ref: http://tools.ietf.org/html/rfc3986#page-12 |
|
| 48 | 46 |
module Filters |
| 47 |
+ # Percent encoding for URI conforming to RFC 3986. |
|
| 48 |
+ # Ref: http://tools.ietf.org/html/rfc3986#page-12 |
|
| 49 | 49 |
def uri_escape(string) |
| 50 | 50 |
CGI.escape(string) rescue string |
| 51 | 51 |
end |
| 52 |
+ |
|
| 53 |
+ # Escape a string for use in XPath expression |
|
| 54 |
+ def to_xpath(string) |
|
| 55 |
+ subs = string.scan(/\G(?:\A\z|[^"]+|[^']+)/).map { |x|
|
|
| 56 |
+ case x |
|
| 57 |
+ when /"/ |
|
| 58 |
+ %Q{'#{x}'}
|
|
| 59 |
+ else |
|
| 60 |
+ %Q{"#{x}"}
|
|
| 61 |
+ end |
|
| 62 |
+ } |
|
| 63 |
+ if subs.size == 1 |
|
| 64 |
+ subs.first |
|
| 65 |
+ else |
|
| 66 |
+ 'concat(' << subs.join(', ') << ')'
|
|
| 67 |
+ end |
|
| 68 |
+ end |
|
| 52 | 69 |
end |
| 53 | 70 |
Liquid::Template.register_filter(LiquidInterpolatable::Filters) |
| 54 | 71 |
|
+ 18
- 0
spec/concerns/liquid_interpolatable_spec.rb
@@ -1,4 +1,5 @@ |
||
| 1 | 1 |
require 'spec_helper' |
| 2 |
+require 'nokogiri' |
|
| 2 | 3 |
|
| 3 | 4 |
describe LiquidInterpolatable::Filters do |
| 4 | 5 |
before do |
@@ -36,4 +37,21 @@ describe LiquidInterpolatable::Filters do |
||
| 36 | 37 |
agent.errors[:options].first.should =~ /not properly terminated/ |
| 37 | 38 |
end |
| 38 | 39 |
end |
| 40 |
+ |
|
| 41 |
+ describe 'to_xpath' do |
|
| 42 |
+ before do |
|
| 43 |
+ def @filter.to_xpath_roundtrip(string) |
|
| 44 |
+ Nokogiri::XML('').xpath(to_xpath(string))
|
|
| 45 |
+ end |
|
| 46 |
+ end |
|
| 47 |
+ |
|
| 48 |
+ it 'should escape a string for use in XPath expression' do |
|
| 49 |
+ [ |
|
| 50 |
+ %q{abc}.freeze,
|
|
| 51 |
+ %q{'a"bc'dfa""fds''fa}.freeze,
|
|
| 52 |
+ ].each { |string|
|
|
| 53 |
+ @filter.to_xpath_roundtrip(string).should == string |
|
| 54 |
+ } |
|
| 55 |
+ end |
|
| 56 |
+ end |
|
| 39 | 57 |
end |
+ 17
- 6
spec/models/agents/website_agent_spec.rb
@@ -456,7 +456,10 @@ fire: hot |
||
| 456 | 456 |
before do |
| 457 | 457 |
@event = Event.new |
| 458 | 458 |
@event.agent = agents(:bob_rain_notifier_agent) |
| 459 |
- @event.payload = { 'url' => "http://xkcd.com" }
|
|
| 459 |
+ @event.payload = {
|
|
| 460 |
+ 'url' => 'http://xkcd.com', |
|
| 461 |
+ 'link' => 'Random', |
|
| 462 |
+ } |
|
| 460 | 463 |
end |
| 461 | 464 |
|
| 462 | 465 |
it "should scrape from the url element in incoming event payload" do |
@@ -467,17 +470,25 @@ fire: hot |
||
| 467 | 470 |
end |
| 468 | 471 |
|
| 469 | 472 |
it "should interpolate values from incoming event payload" do |
| 470 |
- @event.payload['title'] = 'XKCD' |
|
| 471 |
- |
|
| 472 | 473 |
lambda {
|
| 473 |
- @valid_options['extract']['site_title'] = {
|
|
| 474 |
- 'css' => "#comic img", 'value' => "'{{title}}'"
|
|
| 474 |
+ @valid_options['extract'] = {
|
|
| 475 |
+ 'from' => {
|
|
| 476 |
+ 'xpath' => '*[1]', |
|
| 477 |
+ 'value' => '{{url | to_xpath}}'
|
|
| 478 |
+ }, |
|
| 479 |
+ 'to' => {
|
|
| 480 |
+ 'xpath' => '(//a[@href and text()={{link | to_xpath}}])[1]',
|
|
| 481 |
+ 'value' => '@href' |
|
| 482 |
+ }, |
|
| 475 | 483 |
} |
| 476 | 484 |
@checker.options = @valid_options |
| 477 | 485 |
@checker.receive([@event]) |
| 478 | 486 |
}.should change { Event.count }.by(1)
|
| 479 | 487 |
|
| 480 |
- Event.last.payload['site_title'].should == 'XKCD' |
|
| 488 |
+ Event.last.payload.should == {
|
|
| 489 |
+ 'from' => 'http://xkcd.com', |
|
| 490 |
+ 'to' => 'http://dynamic.xkcd.com/random/comic/', |
|
| 491 |
+ } |
|
| 481 | 492 |
end |
| 482 | 493 |
end |
| 483 | 494 |
end |