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

@@ -34,10 +34,37 @@ This is some summary. This is some summary. This is some summary. This is some s
`
input := []byte(start + strings.Repeat(strings.Repeat("this is text", 30)+"{{< myshortcode >}}This is some inner content.{{< /myshortcode >}}", 10))
cfg := Config{EnableEmoji: false}
b.ResetTimer()
for i := 0; i < b.N; i++ {
if _, err := parseBytes(input); err != nil {
if _, err := parseBytes(input, cfg); err != nil {
b.Fatal(err)
}
}
}
func BenchmarkParseWithEmoji(b *testing.B) {
start := `
---
title: "Front Matters"
description: "It really does"
---
This is some summary. This is some summary. This is some summary. This is some summary.
<!--more-->
`
input := []byte(start + strings.Repeat("this is not emoji: ", 50) + strings.Repeat("some text ", 70) + strings.Repeat("this is not: ", 50) + strings.Repeat("but this is a :smile: ", 3) + strings.Repeat("some text ", 70))
cfg := Config{EnableEmoji: true}
b.ResetTimer()
for i := 0; i < b.N; i++ {
if _, err := parseBytes(input, cfg); err != nil {
b.Fatal(err)
}
}