-
Notifications
You must be signed in to change notification settings - Fork 1
/
main.go
185 lines (171 loc) · 4.5 KB
/
main.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
// The genlex command generates lexers from JSON input containing regular
// expressions for terminals of a given input grammar.
package main
import (
"flag"
"fmt"
"log"
"os"
"path/filepath"
"regexp"
"strings"
"text/template"
"github.com/mewkiz/pkg/goutil"
"github.com/mewmew/speak/terminals"
"github.com/pkg/errors"
)
func usage() {
const use = `
genlex [OPTION]... FILE.json
Flags:`
fmt.Fprintln(os.Stderr, use[1:])
flag.PrintDefaults()
}
func main() {
// Parse command line arguments.
flag.Usage = usage
flag.Parse()
if flag.NArg() != 1 {
flag.Usage()
os.Exit(1)
}
jsonPath := flag.Arg(0)
// Parse regular expressions for terminators from JSON input.
tokenData, regs, err := parseJSON(jsonPath)
if err != nil {
log.Fatal(err)
}
// Create a regular expression for identifying the different token
// alternatives.
reg, err := createRegexp(regs)
if err != nil {
log.Fatal(err)
}
// Generate lexer based on the regular expression identifying for
// terminators.
if err := genLexer(tokenData, reg); err != nil {
log.Fatal(err)
}
}
// genLexer generates a lexer based on the regular expression for identifying
// terminators of the input grammar.
func genLexer(tokenData map[string]interface{}, reg string) error {
// Parse templates.
dir, err := goutil.SrcDir("github.com/mewmew/speak/cmd/genlex")
if err != nil {
return errors.WithStack(err)
}
tokenTmplPath := filepath.Join(dir, "token.go.tmpl")
lexerTmplPath := filepath.Join(dir, "lexer.go.tmpl")
t, err := template.ParseFiles(tokenTmplPath, lexerTmplPath)
if err != nil {
return errors.WithStack(err)
}
// Generate token/token.go.
log.Println(`Creating "token/token.go"`)
t1 := t.Lookup("token.go.tmpl")
if err := os.MkdirAll("token", 0755); err != nil {
return errors.WithStack(err)
}
f1, err := os.Create("token/token.go")
if err != nil {
return errors.WithStack(err)
}
defer f1.Close()
if err := t1.Execute(f1, tokenData); err != nil {
return errors.WithStack(err)
}
// Locate import path of the token package.
tokenImportPath, err := goutil.RelImpPath("token")
if err != nil {
return errors.WithStack(err)
}
// Generate lexer/lexer.go.
log.Println(`Creating "lexer/lexer.go"`)
t2 := t.Lookup("lexer.go.tmpl")
if err := os.MkdirAll("lexer", 0755); err != nil {
return errors.WithStack(err)
}
f2, err := os.Create("lexer/lexer.go")
if err != nil {
return errors.WithStack(err)
}
defer f2.Close()
lexerData := map[string]string{
"ImportPath": tokenImportPath,
"Regexp": reg,
}
if err := t2.Execute(f2, lexerData); err != nil {
return errors.WithStack(err)
}
return nil
}
// createRegexp creates a regular expression for identifying the different
// token alternatives.
func createRegexp(regs []string) (string, error) {
tokenAlts := "(" + strings.Join(regs, ")|(") + ")"
regstr := "^(" + tokenAlts + ")"
// Verify that the regular expression compiles successfully.
if _, err := regexp.Compile(regstr); err != nil {
return "", errors.WithStack(err)
}
return regstr, nil
}
// parseJSON parses and returns the regular expressions for terminators and
// their associated IDs, based on the given JSON input.
func parseJSON(jsonPath string) (tokenData map[string]interface{}, regs []string, err error) {
terms, err := terminals.DecodeFile(jsonPath)
if err != nil {
return nil, nil, errors.WithStack(err)
}
var ids []string
tokenData = make(map[string]interface{})
minName := 0
maxName := 0
minToken := 0
maxToken := 0
minSkip := 0
maxSkip := 0
if len(terms.Names) > 0 {
minName = len(ids) + 1
}
for _, term := range terms.Names {
id := fmt.Sprintf("name(%d, `%s`)", len(ids)+1, term.ID)
ids = append(ids, id)
regs = append(regs, term.Reg)
}
if len(terms.Names) > 0 {
maxName = len(ids)
}
if len(terms.Tokens) > 0 {
minToken = len(ids) + 1
}
for _, term := range terms.Tokens {
id := fmt.Sprintf("token(%d, `%s`)", len(ids)+1, term.ID)
ids = append(ids, id)
regs = append(regs, term.Reg)
}
if len(terms.Tokens) > 0 {
maxToken = len(ids)
}
if len(terms.Skip) > 0 {
minSkip = len(ids) + 1
}
for _, term := range terms.Skip {
id := fmt.Sprintf("skip(%d, `%s`)", len(ids)+1, term.ID)
ids = append(ids, id)
regs = append(regs, term.Reg)
}
if len(terms.Skip) > 0 {
maxSkip = len(ids)
}
tokenData["MinName"] = minName
tokenData["MaxName"] = maxName
tokenData["MinToken"] = minToken
tokenData["MaxToken"] = maxToken
tokenData["MinSkip"] = minSkip
tokenData["MaxSkip"] = maxSkip
tokenData["NumTokens"] = len(ids)
tokenData["IDs"] = ids
return tokenData, regs, nil
}