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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
|
package parser
import (
"bytes"
"io"
"strconv"
"github.com/yuin/goldmark/text"
"github.com/yuin/goldmark/util"
)
var attrNameID = []byte("id")
var attrNameClass = []byte("class")
// An Attribute is an attribute of the markdown elements.
type Attribute struct {
Name []byte
Value interface{}
}
// An Attributes is a collection of attributes.
type Attributes []Attribute
// Find returns a (value, true) if an attribute correspond with given name is found, otherwise (nil, false).
func (as Attributes) Find(name []byte) (interface{}, bool) {
for _, a := range as {
if bytes.Equal(a.Name, name) {
return a.Value, true
}
}
return nil, false
}
func (as Attributes) findUpdate(name []byte, cb func(v interface{}) interface{}) bool {
for i, a := range as {
if bytes.Equal(a.Name, name) {
as[i].Value = cb(a.Value)
return true
}
}
return false
}
// ParseAttributes parses attributes into a map.
// ParseAttributes returns a parsed attributes and true if could parse
// attributes, otherwise nil and false.
func ParseAttributes(reader text.Reader) (Attributes, bool) {
savedLine, savedPosition := reader.Position()
reader.SkipSpaces()
if reader.Peek() != '{' {
reader.SetPosition(savedLine, savedPosition)
return nil, false
}
reader.Advance(1)
attrs := Attributes{}
for {
if reader.Peek() == '}' {
reader.Advance(1)
return attrs, true
}
attr, ok := parseAttribute(reader)
if !ok {
reader.SetPosition(savedLine, savedPosition)
return nil, false
}
if bytes.Equal(attr.Name, attrNameClass) {
if !attrs.findUpdate(attrNameClass, func(v interface{}) interface{} {
ret := make([]byte, 0, len(v.([]byte))+1+len(attr.Value.([]byte)))
ret = append(ret, v.([]byte)...)
return append(append(ret, ' '), attr.Value.([]byte)...)
}) {
attrs = append(attrs, attr)
}
} else {
attrs = append(attrs, attr)
}
reader.SkipSpaces()
if reader.Peek() == ',' {
reader.Advance(1)
reader.SkipSpaces()
}
}
}
func parseAttribute(reader text.Reader) (Attribute, bool) {
reader.SkipSpaces()
c := reader.Peek()
if c == '#' || c == '.' {
reader.Advance(1)
line, _ := reader.PeekLine()
i := 0
// HTML5 allows any kind of characters as id, but XHTML restricts characters for id.
// CommonMark is basically defined for XHTML(even though it is legacy).
// So we restrict id characters.
for ; i < len(line) && !util.IsSpace(line[i]) &&
(!util.IsPunct(line[i]) || line[i] == '_' ||
line[i] == '-' || line[i] == ':' || line[i] == '.'); i++ {
}
name := attrNameClass
if c == '#' {
name = attrNameID
}
reader.Advance(i)
return Attribute{Name: name, Value: line[0:i]}, true
}
line, _ := reader.PeekLine()
if len(line) == 0 {
return Attribute{}, false
}
c = line[0]
if !((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
c == '_' || c == ':') {
return Attribute{}, false
}
i := 0
for ; i < len(line); i++ {
c = line[i]
if !((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
(c >= '0' && c <= '9') ||
c == '_' || c == ':' || c == '.' || c == '-') {
break
}
}
name := line[:i]
reader.Advance(i)
reader.SkipSpaces()
c = reader.Peek()
if c != '=' {
return Attribute{}, false
}
reader.Advance(1)
reader.SkipSpaces()
value, ok := parseAttributeValue(reader)
if !ok {
return Attribute{}, false
}
if bytes.Equal(name, attrNameClass) {
if _, ok = value.([]byte); !ok {
return Attribute{}, false
}
}
return Attribute{Name: name, Value: value}, true
}
func parseAttributeValue(reader text.Reader) (interface{}, bool) {
reader.SkipSpaces()
c := reader.Peek()
var value interface{}
var ok bool
switch c {
case text.EOF:
return Attribute{}, false
case '{':
value, ok = ParseAttributes(reader)
case '[':
value, ok = parseAttributeArray(reader)
case '"':
value, ok = parseAttributeString(reader)
default:
if c == '-' || c == '+' || util.IsNumeric(c) {
value, ok = parseAttributeNumber(reader)
} else {
value, ok = parseAttributeOthers(reader)
}
}
if !ok {
return nil, false
}
return value, true
}
func parseAttributeArray(reader text.Reader) ([]interface{}, bool) {
reader.Advance(1) // skip [
ret := []interface{}{}
for i := 0; ; i++ {
c := reader.Peek()
comma := false
if i != 0 && c == ',' {
reader.Advance(1)
comma = true
}
if c == ']' {
if !comma {
reader.Advance(1)
return ret, true
}
return nil, false
}
reader.SkipSpaces()
value, ok := parseAttributeValue(reader)
if !ok {
return nil, false
}
ret = append(ret, value)
reader.SkipSpaces()
}
}
func parseAttributeString(reader text.Reader) ([]byte, bool) {
reader.Advance(1) // skip "
line, _ := reader.PeekLine()
i := 0
l := len(line)
var buf bytes.Buffer
for i < l {
c := line[i]
if c == '\\' && i != l-1 {
n := line[i+1]
switch n {
case '"', '/', '\\':
buf.WriteByte(n)
i += 2
case 'b':
buf.WriteString("\b")
i += 2
case 'f':
buf.WriteString("\f")
i += 2
case 'n':
buf.WriteString("\n")
i += 2
case 'r':
buf.WriteString("\r")
i += 2
case 't':
buf.WriteString("\t")
i += 2
default:
buf.WriteByte('\\')
i++
}
continue
}
if c == '"' {
reader.Advance(i + 1)
return buf.Bytes(), true
}
buf.WriteByte(c)
i++
}
return nil, false
}
func scanAttributeDecimal(reader text.Reader, w io.ByteWriter) {
for {
c := reader.Peek()
if util.IsNumeric(c) {
_ = w.WriteByte(c)
} else {
return
}
reader.Advance(1)
}
}
func parseAttributeNumber(reader text.Reader) (float64, bool) {
sign := 1
c := reader.Peek()
if c == '-' {
sign = -1
reader.Advance(1)
} else if c == '+' {
reader.Advance(1)
}
var buf bytes.Buffer
if !util.IsNumeric(reader.Peek()) {
return 0, false
}
scanAttributeDecimal(reader, &buf)
if buf.Len() == 0 {
return 0, false
}
c = reader.Peek()
if c == '.' {
buf.WriteByte(c)
reader.Advance(1)
scanAttributeDecimal(reader, &buf)
}
c = reader.Peek()
if c == 'e' || c == 'E' {
buf.WriteByte(c)
reader.Advance(1)
c = reader.Peek()
if c == '-' || c == '+' {
buf.WriteByte(c)
reader.Advance(1)
}
scanAttributeDecimal(reader, &buf)
}
f, err := strconv.ParseFloat(buf.String(), 64)
if err != nil {
return 0, false
}
return float64(sign) * f, true
}
var bytesTrue = []byte("true")
var bytesFalse = []byte("false")
var bytesNull = []byte("null")
func parseAttributeOthers(reader text.Reader) (interface{}, bool) {
line, _ := reader.PeekLine()
c := line[0]
if !((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
c == '_' || c == ':') {
return nil, false
}
i := 0
for ; i < len(line); i++ {
c := line[i]
if !((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') ||
(c >= '0' && c <= '9') ||
c == '_' || c == ':' || c == '.' || c == '-') {
break
}
}
value := line[:i]
reader.Advance(i)
if bytes.Equal(value, bytesTrue) {
return true, true
}
if bytes.Equal(value, bytesFalse) {
return false, true
}
if bytes.Equal(value, bytesNull) {
return nil, true
}
return value, true
}
|