mirror/hugo
1
0
Fork 0
mirror of https://github.com/gohugoio/hugo.git synced 2025-08-12 20:13:59 +02:00
Code Issues Packages Projects Releases Wiki Activity

Improve abs url replacement speed

Browse Source 
This commit replaces the multuple `bytes.Containts` and `bytes.Replace` with a custom replacer that does one pass through the document and exploits the fact that there are two common prefixes we search for, `src=` and `href=`.

This is both faster and consumes less memory. There may be even better algos to use here, but we must leave some room for improvements for future versions.

This should also make it possible to solve #816.

```
benchmark              old ns/op     new ns/op     delta
BenchmarkAbsUrl        25795         22597         -12.40%
BenchmarkXmlAbsUrl     17187         11166         -35.03%

benchmark              old allocs     new allocs     delta
BenchmarkAbsUrl        60             33             -45.00%
BenchmarkXmlAbsUrl     30             16             -46.67%

benchmark              old bytes     new bytes     delta
BenchmarkAbsUrl        5844          4167          -28.70%
BenchmarkXmlAbsUrl     3754          2069          -44.89%
```

Fixes #894
This commit is contained in:
bep
2015-02-16 10:48:15 +01:00
committed by spf13
parent 27c03a6dd0
commit f1fec88c30
4 changed files with 357 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
transform/chain_test.go
View File

@@ -14,21 +14,29 @@ const CORRECT_OUTPUT_SRC_HREF_DQ = "<!DOCTYPE html><html><head><script src=\"foo
const CORRECT_OUTPUT_SRC_HREF_SQ = "<!DOCTYPE html><html><head><script src='foobar.js'></script><script src='http://base/barfoo.js'></script></head><body><nav><h1>title</h1></nav><article>content <a href='foobar'>foobar</a>. <a href='http://base/foobar'>Follow up</a></article></body></html>"
const H5_XML_CONTENT_ABS_URL = "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"yes\" ?><feed xmlns=\"http://www.w3.org/2005/Atom\"><entry><content type=\"html\">&lt;p&gt;&lt;a href=&#34;/foobar&#34;&gt;foobar&lt;/a&gt;&lt;/p&gt; &lt;p&gt;A video: &lt;iframe src=&#39;/foo&#39;&gt;&lt;/iframe&gt;&lt;/p&gt;</content></entry></feed>"
const CORRECT_OUTPUT_SRC_HREF_IN_XML = "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"yes\" ?><feed xmlns=\"http://www.w3.org/2005/Atom\"><entry><content type=\"html\">&lt;p&gt;&lt;a href=&#34;http://xml/foobar&#34;&gt;foobar&lt;/a&gt;&lt;/p&gt; &lt;p&gt;A video: &lt;iframe src=&#39;http://xml/foo&#39;&gt;&lt;/iframe&gt;&lt;/p&gt;</content></entry></feed>"
const CORRECT_OUTPUT_SRC_HREF_IN_XML = "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"yes\" ?><feed xmlns=\"http://www.w3.org/2005/Atom\"><entry><content type=\"html\">&lt;p&gt;&lt;a href=&#34;http://base/foobar&#34;&gt;foobar&lt;/a&gt;&lt;/p&gt; &lt;p&gt;A video: &lt;iframe src=&#39;http://base/foo&#39;&gt;&lt;/iframe&gt;&lt;/p&gt;</content></entry></feed>"
const H5_XML_CONTENT_GUARDED = "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"yes\" ?><feed xmlns=\"http://www.w3.org/2005/Atom\"><entry><content type=\"html\">&lt;p&gt;&lt;a href=&#34;//foobar&#34;&gt;foobar&lt;/a&gt;&lt;/p&gt; &lt;p&gt;A video: &lt;iframe src=&#39;//foo&#39;&gt;&lt;/iframe&gt;&lt;/p&gt;</content></entry></feed>"
var abs_url_tests = []test{
// additional sanity tests for replacements testing
const REPLACE_1 = "No replacements."
const REPLACE_2 = "ᚠᛇᚻ ᛒᛦᚦ ᚠᚱᚩᚠᚢᚱ\nᚠᛁᚱᚪ ᚷᛖᚻᚹᛦᛚᚳᚢᛗ"
var abs_url_bench_tests = []test{
{H5_JS_CONTENT_DOUBLE_QUOTE, CORRECT_OUTPUT_SRC_HREF_DQ},
{H5_JS_CONTENT_SINGLE_QUOTE, CORRECT_OUTPUT_SRC_HREF_SQ},
{H5_JS_CONTENT_ABS_URL, H5_JS_CONTENT_ABS_URL},
{H5_JS_CONTENT_ABS_URL_SCHEMALESS, H5_JS_CONTENT_ABS_URL_SCHEMALESS},
}
var xml_abs_url_tests = []test{
var xml_abs_url_bench_tests = []test{
{H5_XML_CONTENT_ABS_URL, CORRECT_OUTPUT_SRC_HREF_IN_XML},
{H5_XML_CONTENT_GUARDED, H5_XML_CONTENT_GUARDED},
}
var sanity_tests = []test{{REPLACE_1, REPLACE_1}, {REPLACE_2, REPLACE_2}}
var abs_url_tests = append(abs_url_bench_tests, sanity_tests...)
var xml_abs_url_tests = append(xml_abs_url_bench_tests, sanity_tests...)
func TestChainZeroTransformers(t *testing.T) {
tr := NewChain()
in := new(bytes.Buffer)
@@ -44,7 +52,7 @@ func BenchmarkAbsUrl(b *testing.B) {
b.ResetTimer()
for i := 0; i < b.N; i++ {
apply(b.Errorf, tr, abs_url_tests)
apply(b.Errorf, tr, abs_url_bench_tests)
}
}
@@ -57,17 +65,17 @@ func TestAbsUrl(t *testing.T) {
}
func BenchmarkXmlAbsUrl(b *testing.B) {
absURLInXML, _ := AbsURLInXML("http://xml")
absURLInXML, _ := AbsURLInXML("http://base")
tr := NewChain(absURLInXML...)
b.ResetTimer()
for i := 0; i < b.N; i++ {
apply(b.Errorf, tr, xml_abs_url_tests)
apply(b.Errorf, tr, xml_abs_url_bench_tests)
}
}
func TestXMLAbsUrl(t *testing.T) {
absURLInXML, _ := AbsURLInXML("http://xml")
absURLInXML, _ := AbsURLInXML("http://base")
tr := NewChain(absURLInXML...)
apply(t.Errorf, tr, xml_abs_url_tests)
}