ralsina/tartrazine
1
0
Fork 0
mirror of https://github.com/ralsina/tartrazine.git synced 2025-06-19 06:33:06 -03:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Refactor Oniguruma integration

Browse Source 
Instead of use a command to change imports before build, using a build tag to generate the correct binary.

This will allow applications to compile enry using oniguruma with less troubles.

Signed-off-by: Antonio Jesus Navarro Perez <antnavper@gmail.com>
This commit is contained in:
Antonio Jesus Navarro Perez
2018-08-28 17:27:18 +02:00
committed by Denys Smirnov
parent 8da8516ac1
commit 15bb13117f
8 changed files with 70 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
internal/code-generator/generator/heuristics.go
View File

@ -6,10 +6,11 @@ import (
"fmt"
"io"
"io/ioutil"
"regexp"
"strconv"
"strings"
"text/template"
"gopkg.in/src-d/enry.v1/regex"
)
// Heuristics reads from fileToParse and builds source file from tmplPath. It complies with type File signature.
@ -38,7 +39,7 @@ const (
)
var (
disambLine = regexp.MustCompile(`^(\s*)disambiguate`)
disambLine = regex.MustCompile(`^(\s*)disambiguate`)
definedRegs = make(map[string]string)
illegalCharacter = map[string]string{
"#": "Sharp",
@ -378,7 +379,7 @@ func convertToValidRegexp(reg string) string {
func includeToRegExp(include string) string {
content := include[strings.Index(include, `(`)+1 : strings.Index(include, `)`)]
content = strings.Trim(content, `"'`)
return regexp.QuoteMeta(content)
return regex.QuoteMeta(content)
}
func getLanguages(line string) []string {

37
internal/tokenizer/tokenize.go
View File

@ -2,7 +2,8 @@ package tokenizer
import (
"bytes"
"regexp"
"gopkg.in/src-d/enry.v1/regex"
)
const byteLimit = 100000
@ -72,20 +73,20 @@ var (
//
// These regexps were converted to work in the same way for both engines:
//
reLiteralStringQuotes = regexp.MustCompile(`("(.|\n)*?"|'(.|\n)*?')`)
reSingleLineComment = regexp.MustCompile(`(?m)(//|--|#|%|")\s([^\n]*$)`)
reMultilineComment = regexp.MustCompile(`(/\*(.|\n)*?\*/|<!--(.|\n)*?-->|\{-(.|\n)*?-\}|\(\*(.|\n)*?\*\)|"""(.|\n)*?"""|'''(.|\n)*?''')`)
reLiteralNumber = regexp.MustCompile(`(0x[0-9A-Fa-f]([0-9A-Fa-f]|\.)*|\d(\d|\.)*)([uU][lL]{0,2}|([eE][-+]\d*)?[fFlL]*)`)
reShebang = regexp.MustCompile(`(?m)^#!(?:/[0-9A-Za-z_]+)*/(?:([0-9A-Za-z_]+)|[0-9A-Za-z_]+(?:\s*[0-9A-Za-z_]+=[0-9A-Za-z_]+\s*)*\s*([0-9A-Za-z_]+))(?:\s*-[0-9A-Za-z_]+\s*)*$`)
rePunctuation = regexp.MustCompile(`;|\{|\}|\(|\)|\[|\]`)
reSGML = regexp.MustCompile(`(<\/?[^\s<>=\d"']+)(?:\s(.|\n)*?\/?>|>)`)
reSGMLComment = regexp.MustCompile(`(<!--(.|\n)*?-->)`)
reSGMLAttributes = regexp.MustCompile(`\s+([0-9A-Za-z_]+=)|\s+([^\s>]+)`)
reSGMLLoneAttribute = regexp.MustCompile(`([0-9A-Za-z_]+)`)
reRegularToken = regexp.MustCompile(`[0-9A-Za-z_\.@#\/\*]+`)
reOperators = regexp.MustCompile(`<<?|\+|\-|\*|\/|%|&&?|\|\|?`)
reLiteralStringQuotes = regex.MustCompile(`("(.|\n)*?"|'(.|\n)*?')`)
reSingleLineComment = regex.MustCompile(`(?m)(//|--|#|%|")\s([^\n]*$)`)
reMultilineComment = regex.MustCompile(`(/\*(.|\n)*?\*/|<!--(.|\n)*?-->|\{-(.|\n)*?-\}|\(\*(.|\n)*?\*\)|"""(.|\n)*?"""|'''(.|\n)*?''')`)
reLiteralNumber = regex.MustCompile(`(0x[0-9A-Fa-f]([0-9A-Fa-f]|\.)*|\d(\d|\.)*)([uU][lL]{0,2}|([eE][-+]\d*)?[fFlL]*)`)
reShebang = regex.MustCompile(`(?m)^#!(?:/[0-9A-Za-z_]+)*/(?:([0-9A-Za-z_]+)|[0-9A-Za-z_]+(?:\s*[0-9A-Za-z_]+=[0-9A-Za-z_]+\s*)*\s*([0-9A-Za-z_]+))(?:\s*-[0-9A-Za-z_]+\s*)*$`)
rePunctuation = regex.MustCompile(`;|\{|\}|\(|\)|\[|\]`)
reSGML = regex.MustCompile(`(<\/?[^\s<>=\d"']+)(?:\s(.|\n)*?\/?>|>)`)
reSGMLComment = regex.MustCompile(`(<!--(.|\n)*?-->)`)
reSGMLAttributes = regex.MustCompile(`\s+([0-9A-Za-z_]+=)|\s+([^\s>]+)`)
reSGMLLoneAttribute = regex.MustCompile(`([0-9A-Za-z_]+)`)
reRegularToken = regex.MustCompile(`[0-9A-Za-z_\.@#\/\*]+`)
reOperators = regex.MustCompile(`<<?|\+|\-|\*|\/|%|&&?|\|\|?`)
regexToSkip = []*regexp.Regexp{
regexToSkip = []regex.EnryRegexp{
// The order must be this
reLiteralStringQuotes,
reMultilineComment,
@ -124,22 +125,22 @@ func getShebangToken(matchedShebang [][]byte) []byte {
return tokenShebang
}
func commonExtracAndReplace(content []byte, re *regexp.Regexp) ([]byte, [][]byte) {
func commonExtractAndReplace(content []byte, re regex.EnryRegexp) ([]byte, [][]byte) {
tokens := re.FindAll(content, -1)
content = re.ReplaceAll(content, []byte(` `))
return content, tokens
}
func extractAndReplacePunctuation(content []byte) ([]byte, [][]byte) {
return commonExtracAndReplace(content, rePunctuation)
return commonExtractAndReplace(content, rePunctuation)
}
func extractAndReplaceRegular(content []byte) ([]byte, [][]byte) {
return commonExtracAndReplace(content, reRegularToken)
return commonExtractAndReplace(content, reRegularToken)
}
func extractAndReplaceOperator(content []byte) ([]byte, [][]byte) {
return commonExtracAndReplace(content, reOperators)
return commonExtractAndReplace(content, reOperators)
}
func extractAndReplaceSGML(content []byte) ([]byte, [][]byte) {