Hide keyboard shortcuts

Hot-keys on this page

r m x p   toggle line displays

j k   next/prev highlighted chunk

0   (zero) top of page

1   (one) first highlighted chunk

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

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

"""Shared support for scanning document type declarations in HTML and XHTML. 

 

This module is used as a foundation for the html.parser module. It has no 

documented public API and should not be used directly. 

 

""" 

 

import re 

 

_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match 

_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match 

_commentclose = re.compile(r'--\s*>') 

_markedsectionclose = re.compile(r']\s*]\s*>') 

 

# An analysis of the MS-Word extensions is available at 

# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf 

 

_msmarkedsectionclose = re.compile(r']\s*>') 

 

del re 

 

 

class ParserBase: 

"""Parser base class which provides some common support methods used 

by the SGML/HTML and XHTML parsers.""" 

 

def __init__(self): 

if self.__class__ is ParserBase: 

raise RuntimeError( 

"_markupbase.ParserBase must be subclassed") 

 

def error(self, message): 

raise NotImplementedError( 

"subclasses of ParserBase must override error()") 

 

def reset(self): 

self.lineno = 1 

self.offset = 0 

 

def getpos(self): 

"""Return current line number and offset.""" 

return self.lineno, self.offset 

 

# Internal -- update line number and offset. This should be 

# called for each piece of data exactly once, in order -- in other 

# words the concatenation of all the input strings to this 

# function should be exactly the entire input. 

def updatepos(self, i, j): 

if i >= j: 

return j 

rawdata = self.rawdata 

nlines = rawdata.count("\n", i, j) 

if nlines: 

self.lineno = self.lineno + nlines 

pos = rawdata.rindex("\n", i, j) # Should not fail 

self.offset = j-(pos+1) 

else: 

self.offset = self.offset + j-i 

return j 

 

_decl_otherchars = '' 

 

# Internal -- parse declaration (for use by subclasses). 

def parse_declaration(self, i): 

# This is some sort of declaration; in "HTML as 

# deployed," this should only be the document type 

# declaration ("<!DOCTYPE html...>"). 

# ISO 8879:1986, however, has more complex 

# declaration syntax for elements in <!...>, including: 

# --comment-- 

# [marked section] 

# name in the following list: ENTITY, DOCTYPE, ELEMENT, 

# ATTLIST, NOTATION, SHORTREF, USEMAP, 

# LINKTYPE, LINK, IDLINK, USELINK, SYSTEM 

rawdata = self.rawdata 

j = i + 2 

assert rawdata[i:j] == "<!", "unexpected call to parse_declaration" 

if rawdata[j:j+1] == ">": 

# the empty comment <!> 

return j + 1 

if rawdata[j:j+1] in ("-", ""): 

# Start of comment followed by buffer boundary, 

# or just a buffer boundary. 

return -1 

# A simple, practical version could look like: ((name|stringlit) S*) + '>' 

n = len(rawdata) 

if rawdata[j:j+2] == '--': #comment 

# Locate --.*-- as the body of the comment 

return self.parse_comment(i) 

elif rawdata[j] == '[': #marked section 

# Locate [statusWord [...arbitrary SGML...]] as the body of the marked section 

# Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA 

# Note that this is extended by Microsoft Office "Save as Web" function 

# to include [if...] and [endif]. 

return self.parse_marked_section(i) 

else: #all other declaration elements 

decltype, j = self._scan_name(j, i) 

if j < 0: 

return j 

if decltype == "doctype": 

self._decl_otherchars = '' 

while j < n: 

c = rawdata[j] 

if c == ">": 

# end of declaration syntax 

data = rawdata[i+2:j] 

if decltype == "doctype": 

self.handle_decl(data) 

else: 

# According to the HTML5 specs sections "8.2.4.44 Bogus 

# comment state" and "8.2.4.45 Markup declaration open 

# state", a comment token should be emitted. 

# Calling unknown_decl provides more flexibility though. 

self.unknown_decl(data) 

return j + 1 

if c in "\"'": 

m = _declstringlit_match(rawdata, j) 

if not m: 

return -1 # incomplete 

j = m.end() 

elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ": 

name, j = self._scan_name(j, i) 

elif c in self._decl_otherchars: 

j = j + 1 

elif c == "[": 

# this could be handled in a separate doctype parser 

if decltype == "doctype": 

j = self._parse_doctype_subset(j + 1, i) 

elif decltype in {"attlist", "linktype", "link", "element"}: 

# must tolerate []'d groups in a content model in an element declaration 

# also in data attribute specifications of attlist declaration 

# also link type declaration subsets in linktype declarations 

# also link attribute specification lists in link declarations 

self.error("unsupported '[' char in %s declaration" % decltype) 

else: 

self.error("unexpected '[' char in declaration") 

else: 

self.error( 

"unexpected %r char in declaration" % rawdata[j]) 

if j < 0: 

return j 

return -1 # incomplete 

 

# Internal -- parse a marked section 

# Override this to handle MS-word extension syntax <![if word]>content<![endif]> 

def parse_marked_section(self, i, report=1): 

rawdata= self.rawdata 

assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()" 

sectName, j = self._scan_name( i+3, i ) 

if j < 0: 

return j 

if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}: 

# look for standard ]]> ending 

match= _markedsectionclose.search(rawdata, i+3) 

elif sectName in {"if", "else", "endif"}: 

# look for MS Office ]> ending 

match= _msmarkedsectionclose.search(rawdata, i+3) 

else: 

self.error('unknown status keyword %r in marked section' % rawdata[i+3:j]) 

if not match: 

return -1 

if report: 

j = match.start(0) 

self.unknown_decl(rawdata[i+3: j]) 

return match.end(0) 

 

# Internal -- parse comment, return length or -1 if not terminated 

def parse_comment(self, i, report=1): 

rawdata = self.rawdata 

if rawdata[i:i+4] != '<!--': 

self.error('unexpected call to parse_comment()') 

match = _commentclose.search(rawdata, i+4) 

if not match: 

return -1 

if report: 

j = match.start(0) 

self.handle_comment(rawdata[i+4: j]) 

return match.end(0) 

 

# Internal -- scan past the internal subset in a <!DOCTYPE declaration, 

# returning the index just past any whitespace following the trailing ']'. 

def _parse_doctype_subset(self, i, declstartpos): 

rawdata = self.rawdata 

n = len(rawdata) 

j = i 

while j < n: 

c = rawdata[j] 

if c == "<": 

s = rawdata[j:j+2] 

if s == "<": 

# end of buffer; incomplete 

return -1 

if s != "<!": 

self.updatepos(declstartpos, j + 1) 

self.error("unexpected char in internal subset (in %r)" % s) 

if (j + 2) == n: 

# end of buffer; incomplete 

return -1 

if (j + 4) > n: 

# end of buffer; incomplete 

return -1 

if rawdata[j:j+4] == "<!--": 

j = self.parse_comment(j, report=0) 

if j < 0: 

return j 

continue 

name, j = self._scan_name(j + 2, declstartpos) 

if j == -1: 

return -1 

if name not in {"attlist", "element", "entity", "notation"}: 

self.updatepos(declstartpos, j + 2) 

self.error( 

"unknown declaration %r in internal subset" % name) 

# handle the individual names 

meth = getattr(self, "_parse_doctype_" + name) 

j = meth(j, declstartpos) 

if j < 0: 

return j 

elif c == "%": 

# parameter entity reference 

if (j + 1) == n: 

# end of buffer; incomplete 

return -1 

s, j = self._scan_name(j + 1, declstartpos) 

if j < 0: 

return j 

if rawdata[j] == ";": 

j = j + 1 

elif c == "]": 

j = j + 1 

while j < n and rawdata[j].isspace(): 

j = j + 1 

if j < n: 

if rawdata[j] == ">": 

return j 

self.updatepos(declstartpos, j) 

self.error("unexpected char after internal subset") 

else: 

return -1 

elif c.isspace(): 

j = j + 1 

else: 

self.updatepos(declstartpos, j) 

self.error("unexpected char %r in internal subset" % c) 

# end of buffer reached 

return -1 

 

# Internal -- scan past <!ELEMENT declarations 

def _parse_doctype_element(self, i, declstartpos): 

name, j = self._scan_name(i, declstartpos) 

if j == -1: 

return -1 

# style content model; just skip until '>' 

rawdata = self.rawdata 

if '>' in rawdata[j:]: 

return rawdata.find(">", j) + 1 

return -1 

 

# Internal -- scan past <!ATTLIST declarations 

def _parse_doctype_attlist(self, i, declstartpos): 

rawdata = self.rawdata 

name, j = self._scan_name(i, declstartpos) 

c = rawdata[j:j+1] 

if c == "": 

return -1 

if c == ">": 

return j + 1 

while 1: 

# scan a series of attribute descriptions; simplified: 

# name type [value] [#constraint] 

name, j = self._scan_name(j, declstartpos) 

if j < 0: 

return j 

c = rawdata[j:j+1] 

if c == "": 

return -1 

if c == "(": 

# an enumerated type; look for ')' 

if ")" in rawdata[j:]: 

j = rawdata.find(")", j) + 1 

else: 

return -1 

while rawdata[j:j+1].isspace(): 

j = j + 1 

if not rawdata[j:]: 

# end of buffer, incomplete 

return -1 

else: 

name, j = self._scan_name(j, declstartpos) 

c = rawdata[j:j+1] 

if not c: 

return -1 

if c in "'\"": 

m = _declstringlit_match(rawdata, j) 

if m: 

j = m.end() 

else: 

return -1 

c = rawdata[j:j+1] 

if not c: 

return -1 

if c == "#": 

if rawdata[j:] == "#": 

# end of buffer 

return -1 

name, j = self._scan_name(j + 1, declstartpos) 

if j < 0: 

return j 

c = rawdata[j:j+1] 

if not c: 

return -1 

if c == '>': 

# all done 

return j + 1 

 

# Internal -- scan past <!NOTATION declarations 

def _parse_doctype_notation(self, i, declstartpos): 

name, j = self._scan_name(i, declstartpos) 

if j < 0: 

return j 

rawdata = self.rawdata 

while 1: 

c = rawdata[j:j+1] 

if not c: 

# end of buffer; incomplete 

return -1 

if c == '>': 

return j + 1 

if c in "'\"": 

m = _declstringlit_match(rawdata, j) 

if not m: 

return -1 

j = m.end() 

else: 

name, j = self._scan_name(j, declstartpos) 

if j < 0: 

return j 

 

# Internal -- scan past <!ENTITY declarations 

def _parse_doctype_entity(self, i, declstartpos): 

rawdata = self.rawdata 

if rawdata[i:i+1] == "%": 

j = i + 1 

while 1: 

c = rawdata[j:j+1] 

if not c: 

return -1 

if c.isspace(): 

j = j + 1 

else: 

break 

else: 

j = i 

name, j = self._scan_name(j, declstartpos) 

if j < 0: 

return j 

while 1: 

c = self.rawdata[j:j+1] 

if not c: 

return -1 

if c in "'\"": 

m = _declstringlit_match(rawdata, j) 

if m: 

j = m.end() 

else: 

return -1 # incomplete 

elif c == ">": 

return j + 1 

else: 

name, j = self._scan_name(j, declstartpos) 

if j < 0: 

return j 

 

# Internal -- scan a name token and the new position and the token, or 

# return -1 if we've reached the end of the buffer. 

def _scan_name(self, i, declstartpos): 

rawdata = self.rawdata 

n = len(rawdata) 

if i == n: 

return None, -1 

m = _declname_match(rawdata, i) 

if m: 

s = m.group() 

name = s.strip() 

if (i + len(s)) == n: 

return None, -1 # end of buffer 

return name.lower(), m.end() 

else: 

self.updatepos(declstartpos, i) 

self.error("expected name token at %r" 

% rawdata[declstartpos:declstartpos+20]) 

 

# To be overridden -- handlers for unknown objects 

def unknown_decl(self, data): 

pass