go/chroma
1
0
Fork 0
mirror of https://github.com/alecthomas/chroma.git synced 2025-03-25 21:39:02 +02:00
Code Issues Releases Activity

Add Restructured Text lexer.

Browse Source
This commit is contained in:
Alec Thomas 2017-09-21 22:37:03 +10:00
parent e5fd873611
commit f8658edb57
2 changed files with 90 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
lexers/markdown.go
View File

@ -21,7 +21,7 @@ var Markdown = Register(MustNewLexer(
{`^(\s*)([0-9]+\.)( .+\n)`, ByGroups(Text, Keyword, UsingSelf("inline")), nil},
{`^(\s*>\s)(.+\n)`, ByGroups(Keyword, GenericEmph), nil},
{"^(```\\n)([\\w\\W]*?)(^```$)", ByGroups(LiteralString, Text, LiteralString), nil},
{"^(```)(\\w+)(\\n)([\\w\\W]*?)(^```$)", EmitterFunc(handleCodeblock), nil},
{"^(```)(\\w+)(\\n)([\\w\\W]*?)(^```$)", EmitterFunc(markdownCodeBlock), nil},
Include("inline"),
},
"inline": {
@ -38,12 +38,12 @@ var Markdown = Register(MustNewLexer(
},
))
func handleCodeblock(groups []string, lexer Lexer) Iterator {
func markdownCodeBlock(groups []string, lexer Lexer) Iterator {
iterators := []Iterator{}
tokens := []*Token{
&Token{String, groups[1]},
&Token{String, groups[2]},
&Token{Text, groups[3]},
{String, groups[1]},
{String, groups[2]},
{Text, groups[3]},
}
code := groups[4]
lexer = Get(groups[2])

85
lexers/rst.go Normal file
View File

@ -0,0 +1,85 @@
package lexers
import (
"strings"
. "github.com/alecthomas/chroma" // nolint
)
// Restructuredtext lexer.
var Restructuredtext = Register(MustNewLexer(
&Config{
Name: "reStructuredText",
Aliases: []string{"rst", "rest", "restructuredtext"},
Filenames: []string{"*.rst", "*.rest"},
MimeTypes: []string{"text/x-rst", "text/prs.fallenstein.rst"},
},
Rules{
"root": {
{"^(=+|-+|`+|:+|\\.+|\\'+|\"+|~+|\\^+|_+|\\*+|\\++|#+)([ \\t]*\\n)(.+)(\\n)(\\1)(\\n)", ByGroups(GenericHeading, Text, GenericHeading, Text, GenericHeading, Text), nil},
{"^(\\S.*)(\\n)(={3,}|-{3,}|`{3,}|:{3,}|\\.{3,}|\\'{3,}|\"{3,}|~{3,}|\\^{3,}|_{3,}|\\*{3,}|\\+{3,}|#{3,})(\\n)", ByGroups(GenericHeading, Text, GenericHeading, Text), nil},
{`^(\s*)([-*+])( .+\n(?:\1 .+\n)*)`, ByGroups(Text, LiteralNumber, UsingSelf("inline")), nil},
{`^(\s*)([0-9#ivxlcmIVXLCM]+\.)( .+\n(?:\1 .+\n)*)`, ByGroups(Text, LiteralNumber, UsingSelf("inline")), nil},
{`^(\s*)(\(?[0-9#ivxlcmIVXLCM]+\))( .+\n(?:\1 .+\n)*)`, ByGroups(Text, LiteralNumber, UsingSelf("inline")), nil},
{`^(\s*)([A-Z]+\.)( .+\n(?:\1 .+\n)+)`, ByGroups(Text, LiteralNumber, UsingSelf("inline")), nil},
{`^(\s*)(\(?[A-Za-z]+\))( .+\n(?:\1 .+\n)+)`, ByGroups(Text, LiteralNumber, UsingSelf("inline")), nil},
{`^(\s*)(\|)( .+\n(?:\| .+\n)*)`, ByGroups(Text, Operator, UsingSelf("inline")), nil},
{`^( *\.\.)(\s*)((?:source)?code(?:-block)?)(::)([ \t]*)([^\n]+)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\8.*|)\n)+)`, EmitterFunc(rstCodeBlock), nil},
{`^( *\.\.)(\s*)([\w:-]+?)(::)(?:([ \t]*)(.*))`, ByGroups(Punctuation, Text, OperatorWord, Punctuation, Text, UsingSelf("inline")), nil},
{`^( *\.\.)(\s*)(_(?:[^:\\]|\\.)+:)(.*?)$`, ByGroups(Punctuation, Text, NameTag, UsingSelf("inline")), nil},
{`^( *\.\.)(\s*)(\[.+\])(.*?)$`, ByGroups(Punctuation, Text, NameTag, UsingSelf("inline")), nil},
{`^( *\.\.)(\s*)(\|.+\|)(\s*)([\w:-]+?)(::)(?:([ \t]*)(.*))`, ByGroups(Punctuation, Text, NameTag, Text, OperatorWord, Punctuation, Text, UsingSelf("inline")), nil},
{`^ *\.\..*(\n( +.*\n|\n)+)?`, CommentPreproc, nil},
{`^( *)(:[a-zA-Z-]+:)(\s*)$`, ByGroups(Text, NameClass, Text), nil},
{`^( *)(:.*?:)([ \t]+)(.*?)$`, ByGroups(Text, NameClass, Text, NameFunction), nil},
{`^(\S.*(?<!::)\n)((?:(?: +.*)\n)+)`, ByGroups(UsingSelf("inline"), UsingSelf("inline")), nil},
{`(::)(\n[ \t]*\n)([ \t]+)(.*)(\n)((?:(?:\3.*|)\n)+)`, ByGroups(LiteralStringEscape, Text, LiteralString, LiteralString, Text, LiteralString), nil},
Include("inline"),
},
"inline": {
{`\\.`, Text, nil},
{"``", LiteralString, Push("literal")},
{"(`.+?)(<.+?>)(`__?)", ByGroups(LiteralString, LiteralStringInterpol, LiteralString), nil},
{"`.+?`__?", LiteralString, nil},
{"(`.+?`)(:[a-zA-Z0-9:-]+?:)?", ByGroups(NameVariable, NameAttribute), nil},
{"(:[a-zA-Z0-9:-]+?:)(`.+?`)", ByGroups(NameAttribute, NameVariable), nil},
{`\*\*.+?\*\*`, GenericStrong, nil},
{`\*.+?\*`, GenericEmph, nil},
{`\[.*?\]_`, LiteralString, nil},
{`<.+?>`, NameTag, nil},
{"[^\\\\\\n\\[*`:]+", Text, nil},
{`.`, Text, nil},
},
"literal": {
{"[^`]+", LiteralString, nil},
{"``((?=$)|(?=[-/:.,; \\n\\x00\\\u2010\\\u2011\\\u2012\\\u2013\\\u2014\\\u00a0\\'\\\"\\)\\]\\}\\>\\\u2019\\\u201d\\\u00bb\\!\\?]))", LiteralString, Pop(1)},
{"`", LiteralString, nil},
},
},
))
func rstCodeBlock(groups []string, lexer Lexer) Iterator {
iterators := []Iterator{}
tokens := []*Token{
{Punctuation, groups[1]},
{Text, groups[2]},
{OperatorWord, groups[3]},
{Punctuation, groups[4]},
{Text, groups[5]},
{Keyword, groups[6]},
{Text, groups[7]},
}
code := strings.Join(groups[8:], "")
lexer = Get(groups[6])
if lexer == nil {
tokens = append(tokens, &Token{String, code})
iterators = append(iterators, Literator(tokens...))
} else {
sub, err := lexer.Tokenise(nil, code)
if err != nil {
panic(err)
}
iterators = append(iterators, Literator(tokens...), sub)
}
return Concaterator(iterators...)
}