Move the emoji parsing to pageparser

This avoids double parsing the page content when `enableEmoji=true`.

This commit also adds some general improvements to the parser, making it in general much faster:

```bash
benchmark                     old ns/op     new ns/op     delta
BenchmarkShortcodeLexer-4     90258         101730        +12.71%
BenchmarkParse-4              148940        15037         -89.90%

benchmark                     old allocs     new allocs     delta
BenchmarkShortcodeLexer-4     456            700            +53.51%
BenchmarkParse-4              28             33             +17.86%

benchmark                     old bytes     new bytes     delta
BenchmarkShortcodeLexer-4     69875         81014         +15.94%
BenchmarkParse-4              8128          8304          +2.17%
```

Running some site benchmarks with Emoji support turned on:

```bash
benchmark                                                                                     old ns/op     new ns/op     delta
BenchmarkSiteBuilding/TOML,num_langs=3,num_pages=5000,tags_per_page=5,shortcodes,render-4     924556797     818115620     -11.51%

benchmark                                                                                     old allocs     new allocs     delta
BenchmarkSiteBuilding/TOML,num_langs=3,num_pages=5000,tags_per_page=5,shortcodes,render-4     4112613        4133787        +0.51%

benchmark                                                                                     old bytes     new bytes     delta
BenchmarkSiteBuilding/TOML,num_langs=3,num_pages=5000,tags_per_page=5,shortcodes,render-4     426982864     424363832     -0.61%
```

Fixes #5534
This commit is contained in:
Bjørn Erik Pedersen
2018-12-17 21:03:23 +01:00
parent a8853f1c5a
commit 9cd54cab20
13 changed files with 388 additions and 71 deletions

View File

@@ -152,7 +152,8 @@ var shortCodeLexerTests = []lexerTest{
{"basic inline", `{{< sc1.inline >}}Hello World{{< /sc1.inline >}}`, []Item{tstLeftNoMD, tstSC1Inline, tstRightNoMD, tstText, tstLeftNoMD, tstSCClose, tstSC1Inline, tstRightNoMD, tstEOF}},
{"basic inline with space", `{{< sc1.inline >}}Hello World{{< / sc1.inline >}}`, []Item{tstLeftNoMD, tstSC1Inline, tstRightNoMD, tstText, tstLeftNoMD, tstSCClose, tstSC1Inline, tstRightNoMD, tstEOF}},
{"inline self closing", `{{< sc1.inline >}}Hello World{{< /sc1.inline >}}Hello World{{< sc1.inline />}}`, []Item{tstLeftNoMD, tstSC1Inline, tstRightNoMD, tstText, tstLeftNoMD, tstSCClose, tstSC1Inline, tstRightNoMD, tstText, tstLeftNoMD, tstSC1Inline, tstSCClose, tstRightNoMD, tstEOF}},
{"inline with nested shortcode (not supported)", `{{< sc1.inline >}}Hello World{{< sc1 >}}{{< /sc1.inline >}}`, []Item{tstLeftNoMD, tstSC1Inline, tstRightNoMD, nti(tError, "inline shortcodes do not support nesting")}},
{"inline with template syntax", `{{< sc1.inline >}}{{ .Get 0 }}{{ .Get 1 }}{{< /sc1.inline >}}`, []Item{tstLeftNoMD, tstSC1Inline, tstRightNoMD, nti(tText, "{{ .Get 0 }}"), nti(tText, "{{ .Get 1 }}"), tstLeftNoMD, tstSCClose, tstSC1Inline, tstRightNoMD, tstEOF}},
{"inline with nested shortcode (not supported)", `{{< sc1.inline >}}Hello World{{< sc1 >}}{{< /sc1.inline >}}`, []Item{tstLeftNoMD, tstSC1Inline, tstRightNoMD, tstText, nti(tError, "inline shortcodes do not support nesting")}},
{"inline case mismatch", `{{< sc1.Inline >}}Hello World{{< /sc1.Inline >}}`, []Item{tstLeftNoMD, nti(tError, "period in shortcode name only allowed for inline identifiers")}},
}
@@ -171,10 +172,11 @@ func BenchmarkShortcodeLexer(b *testing.B) {
for i, input := range shortCodeLexerTests {
testInputs[i] = []byte(input.input)
}
var cfg Config
b.ResetTimer()
for i := 0; i < b.N; i++ {
for _, input := range testInputs {
items := collect(input, true, lexMainSection)
items := collectWithConfig(input, true, lexMainSection, cfg)
if len(items) == 0 {
}