mirror of https://github.com/pulumi/pulumi.git
76 lines
2.6 KiB
Go
76 lines
2.6 KiB
Go
package python
|
|
|
|
import (
|
|
"io"
|
|
"strings"
|
|
"unicode"
|
|
|
|
"github.com/pulumi/pulumi/pkg/codegen"
|
|
)
|
|
|
|
// pythonKeywords is a map of reserved keywords used by python 2 and 3. We use this to avoid generating unspeakable
|
|
// names in the resulting code. This map was sourced by merging the following reference material:
|
|
//
|
|
// * Python 2: https://docs.python.org/2.5/ref/keywords.html
|
|
// * Python 3: https://docs.python.org/3/reference/lexical_analysis.html#keywords
|
|
//
|
|
var pythonKeywords = codegen.NewStringSet("false", "none", "true", "and", "as", "assert", "async", "await", "break",
|
|
"class", "continue", "def", "del", "elif", "else", "except", "exec", "finally", "for", "from", "global", "if",
|
|
"import", "in", "is", "lambda", "nonlocal", "not", "or", "pass", "print", "raise", "return", "try", "while",
|
|
"with", "yield")
|
|
|
|
func isReservedWord(word string) bool {
|
|
return pythonKeywords.Has(word)
|
|
}
|
|
|
|
// isLegalIdentifierStart returns true if it is legal for c to be the first character of a Python identifier as per
|
|
// https://docs.python.org/3.7/reference/lexical_analysis.html#identifiers.
|
|
func isLegalIdentifierStart(c rune) bool {
|
|
return c >= 'a' && c <= 'z' || c >= 'A' && c <= 'Z' || c == '_' ||
|
|
unicode.In(c, unicode.Lu, unicode.Ll, unicode.Lt, unicode.Lm, unicode.Lo, unicode.Nl)
|
|
}
|
|
|
|
// isLegalIdentifierPart returns true if it is legal for c to be part of a Python identifier (besides the first
|
|
// character) as per https://docs.python.org/3.7/reference/lexical_analysis.html#identifiers.
|
|
func isLegalIdentifierPart(c rune) bool {
|
|
return isLegalIdentifierStart(c) || c >= '0' && c <= '9' ||
|
|
unicode.In(c, unicode.Lu, unicode.Ll, unicode.Lt, unicode.Lm, unicode.Lo, unicode.Nl, unicode.Mn, unicode.Mc,
|
|
unicode.Nd, unicode.Pc)
|
|
}
|
|
|
|
// isLegalIdentifier returns true if s is a legal Python identifier as per
|
|
// https://docs.python.org/3.7/reference/lexical_analysis.html#identifiers.
|
|
func isLegalIdentifier(s string) bool {
|
|
reader := strings.NewReader(s)
|
|
c, _, _ := reader.ReadRune()
|
|
if !isLegalIdentifierStart(c) {
|
|
return false
|
|
}
|
|
for {
|
|
c, _, err := reader.ReadRune()
|
|
if err != nil {
|
|
return err == io.EOF
|
|
}
|
|
if !isLegalIdentifierPart(c) {
|
|
return false
|
|
}
|
|
}
|
|
}
|
|
|
|
// cleanName replaces characters that are not allowed in Python identifiers with underscores. No attempt is made to
|
|
// ensure that the result is unique.
|
|
func cleanName(name string) string {
|
|
var builder strings.Builder
|
|
for i, c := range name {
|
|
if !isLegalIdentifierPart(c) {
|
|
builder.WriteRune('_')
|
|
} else {
|
|
if i == 0 && !isLegalIdentifierStart(c) {
|
|
builder.WriteRune('_')
|
|
}
|
|
builder.WriteRune(c)
|
|
}
|
|
}
|
|
return builder.String()
|
|
}
|