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

1 files changed, 6 insertions, 12 deletions

diff --git a/parser/pageparser/pageparser.go b/parser/pageparser/pageparser.go
index 606a246aa..14b341ee9 100644
--- a/parser/pageparser/pageparser.go
+++ b/parser/pageparser/pageparser.go
@@ -27,7 +27,7 @@ import (
 
 // Result holds the parse result.
 type Result interface {
-	// Iterator returns a new Iterator positioned at the benning of the parse tree.
+	// Iterator returns a new Iterator positioned at the beginning of the parse tree.
 	Iterator() *Iterator
 	// Input returns the input to Parse.
 	Input() []byte
@@ -35,27 +35,21 @@ type Result interface {
 
 var _ Result = (*pageLexer)(nil)
 
-// Parse parses the page in the given reader.
-func Parse(r io.Reader) (Result, error) {
+// Parse parses the page in the given reader according to the given Config.
+func Parse(r io.Reader, cfg Config) (Result, error) {
 	b, err := ioutil.ReadAll(r)
 	if err != nil {
 		return nil, errors.Wrap(err, "failed to read page content")
 	}
-	return parseBytes(b)
+	return parseBytes(b, cfg)
 }
 
-func parseBytes(b []byte) (Result, error) {
-	lexer := newPageLexer(b, 0, lexIntroSection)
+func parseBytes(b []byte, cfg Config) (Result, error) {
+	lexer := newPageLexer(b, lexIntroSection, cfg)
 	lexer.run()
 	return lexer, nil
 }
 
-func parseMainSection(input []byte, from int) Result {
-	lexer := newPageLexer(input, from, lexMainSection)
-	lexer.run()
-	return lexer
-}
-
 // An Iterator has methods to iterate a parsed page with support going back
 // if needed.
 type Iterator struct {