1
0
mirror of https://github.com/alecthomas/chroma.git synced 2025-02-05 13:05:18 +02:00
chroma/lexers/go.go
Mikhail Sorochan 3044bf5f32
Go lexer: single line comment without consuming endline, disable EnsureNL (#984)
This PR changes `CommentSingle` to not consume the newline at the end as
a part of comment.
That solves the problems of single line comment being not parsed at the
end of the line or at the end of the file. Which was reported earlier as
the reason to not highlight single line comment properly.

Disabling `EnsureNL: true` does not add unnecessary newline element for
`Text`, `CommentSymbol` symbols. Using chroma in console with syntax
highlighting was unusable becasue of this, since typing e.g. `b := `
adds newline each time space is at the end when host app asks for
highlighted text from `quick`.

Tokens behavior:
<table>
<tr>
<td> Before </td> <td> After </td>
</tr>
<tr>
<td>

``` go
t.Run("Single space", func(t *testing.T) {
        tokens, _ := chroma.Tokenise(Go, nil, " ")
        expected := []chroma.Token{
                {chroma.Text, " \n"},
        }
        assert.Equal(t, expected, tokens)
})
t.Run("Assignment unfinished", func(t *testing.T) {
        tokens, _ := chroma.Tokenise(Go, nil, "i = ")
        expected := []chroma.Token{
                { chroma.NameOther, "i" },
                { chroma.Text, " " },
                { chroma.Punctuation, "=" },
                { chroma.Text, " \n" },
        }
        assert.Equal(t, expected, tokens)
})
t.Run("Single comment", func(t *testing.T) {
        tokens, _ := chroma.Tokenise(Go, nil, "// W")
        expected := []chroma.Token{
                { chroma.CommentSingle, "// W\n" },
        }
        assert.Equal(t, expected, tokens)
})
```

</td>
<td>
    
``` go
t.Run("Single space", func(t *testing.T) {
        tokens, _ := chroma.Tokenise(Go, nil, " ")
        expected := []chroma.Token{
                {chroma.Text, " "},
        }
        assert.Equal(t, expected, tokens)
})
t.Run("Assignment unfinished", func(t *testing.T) {
        tokens, _ := chroma.Tokenise(Go, nil, "i = ")
        expected := []chroma.Token{
                { chroma.NameOther, "i" },
                { chroma.Text, " " },
                { chroma.Punctuation, "=" },
                { chroma.Text, " " },
        }
        assert.Equal(t, expected, tokens)
})
t.Run("Single comment", func(t *testing.T) {
        tokens, _ := chroma.Tokenise(Go, nil, "// W")
        expected := []chroma.Token{
                { chroma.CommentSingle, "// W" },
        }
        assert.Equal(t, expected, tokens)
})
```
</td>
</tr>
</table>
2024-07-23 02:19:08 +10:00

82 lines
3.2 KiB
Go

package lexers
import (
"strings"
. "github.com/alecthomas/chroma/v2" // nolint
)
// Go lexer.
var Go = Register(MustNewLexer(
&Config{
Name: "Go",
Aliases: []string{"go", "golang"},
Filenames: []string{"*.go"},
MimeTypes: []string{"text/x-gosrc"},
},
goRules,
).SetAnalyser(func(text string) float32 {
if strings.Contains(text, "fmt.") && strings.Contains(text, "package ") {
return 0.5
}
if strings.Contains(text, "package ") {
return 0.1
}
return 0.0
}))
func goRules() Rules {
return Rules{
"root": {
{`\n`, Text, nil},
{`\s+`, Text, nil},
{`\\\n`, Text, nil},
{`//[^\n\r]*`, CommentSingle, nil},
{`/(\\\n)?[*](.|\n)*?[*](\\\n)?/`, CommentMultiline, nil},
{`(import|package)\b`, KeywordNamespace, nil},
{`(var|func|struct|map|chan|type|interface|const)\b`, KeywordDeclaration, nil},
{Words(``, `\b`, `break`, `default`, `select`, `case`, `defer`, `go`, `else`, `goto`, `switch`, `fallthrough`, `if`, `range`, `continue`, `for`, `return`), Keyword, nil},
{`(true|false|iota|nil)\b`, KeywordConstant, nil},
{Words(``, `\b(\()`, `uint`, `uint8`, `uint16`, `uint32`, `uint64`, `int`, `int8`, `int16`, `int32`, `int64`, `float`, `float32`, `float64`, `complex64`, `complex128`, `byte`, `rune`, `string`, `bool`, `error`, `uintptr`, `print`, `println`, `panic`, `recover`, `close`, `complex`, `real`, `imag`, `len`, `cap`, `append`, `copy`, `delete`, `new`, `make`, `clear`, `min`, `max`), ByGroups(NameBuiltin, Punctuation), nil},
{Words(``, `\b`, `uint`, `uint8`, `uint16`, `uint32`, `uint64`, `int`, `int8`, `int16`, `int32`, `int64`, `float`, `float32`, `float64`, `complex64`, `complex128`, `byte`, `rune`, `string`, `bool`, `error`, `uintptr`), KeywordType, nil},
{`\d+i`, LiteralNumber, nil},
{`\d+\.\d*([Ee][-+]\d+)?i`, LiteralNumber, nil},
{`\.\d+([Ee][-+]\d+)?i`, LiteralNumber, nil},
{`\d+[Ee][-+]\d+i`, LiteralNumber, nil},
{`\d+(\.\d+[eE][+\-]?\d+|\.\d*|[eE][+\-]?\d+)`, LiteralNumberFloat, nil},
{`\.\d+([eE][+\-]?\d+)?`, LiteralNumberFloat, nil},
{`0[0-7]+`, LiteralNumberOct, nil},
{`0[xX][0-9a-fA-F_]+`, LiteralNumberHex, nil},
{`0b[01_]+`, LiteralNumberBin, nil},
{`(0|[1-9][0-9_]*)`, LiteralNumberInteger, nil},
{`'(\\['"\\abfnrtv]|\\x[0-9a-fA-F]{2}|\\[0-7]{1,3}|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|[^\\])'`, LiteralStringChar, nil},
{"(`)([^`]*)(`)", ByGroups(LiteralString, UsingLexer(TypeRemappingLexer(GoTextTemplate, TypeMapping{{Other, LiteralString, nil}})), LiteralString), nil},
{`"(\\\\|\\"|[^"])*"`, LiteralString, nil},
{`(<<=|>>=|<<|>>|<=|>=|&\^=|&\^|\+=|-=|\*=|/=|%=|&=|\|=|&&|\|\||<-|\+\+|--|==|!=|:=|\.\.\.|[+\-*/%&])`, Operator, nil},
{`([a-zA-Z_]\w*)(\s*)(\()`, ByGroups(NameFunction, UsingSelf("root"), Punctuation), nil},
{`[|^<>=!()\[\]{}.,;:~]`, Punctuation, nil},
{`[^\W\d]\w*`, NameOther, nil},
},
}
}
var GoHTMLTemplate = Register(DelegatingLexer(HTML, MustNewXMLLexer(
embedded,
"embedded/go_template.xml",
).SetConfig(
&Config{
Name: "Go HTML Template",
Aliases: []string{"go-html-template"},
},
)))
var GoTextTemplate = Register(MustNewXMLLexer(
embedded,
"embedded/go_template.xml",
).SetConfig(
&Config{
Name: "Go Text Template",
Aliases: []string{"go-text-template"},
},
))