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

@@ -88,8 +88,8 @@ func TestFrontMatter(t *testing.T) {
}
}
func collect(input []byte, skipFrontMatter bool, stateStart stateFunc) (items []Item) {
l := newPageLexer(input, 0, stateStart)
func collectWithConfig(input []byte, skipFrontMatter bool, stateStart stateFunc, cfg Config) (items []Item) {
l := newPageLexer(input, stateStart, cfg)
l.run()
t := l.newIterator()
@@ -103,6 +103,13 @@ func collect(input []byte, skipFrontMatter bool, stateStart stateFunc) (items []
return
}
func collect(input []byte, skipFrontMatter bool, stateStart stateFunc) (items []Item) {
var cfg Config
return collectWithConfig(input, skipFrontMatter, stateStart, cfg)
}
// no positional checking, for now ...
func equal(i1, i2 []Item) bool {
if len(i1) != len(i2) {