cpython/Lib/string.py at 3.4 · python/cpython · GitHub

Repository navigation

History

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

"""A collection of string constants.

Public module variables:

whitespace -- a string containing all ASCII whitespace

ascii_lowercase -- a string containing all ASCII lowercase letters

ascii_uppercase -- a string containing all ASCII uppercase letters

ascii_letters -- a string containing all ASCII letters

digits -- a string containing all ASCII decimal digits

hexdigits -- a string containing all ASCII hexadecimal digits

octdigits -- a string containing all ASCII octal digits

punctuation -- a string containing all ASCII punctuation characters

printable -- a string containing all ASCII characters considered printable

"""

import _string

# Some strings for ctype-style character classification

whitespace = ' \t\n\r\v\f'

ascii_lowercase = 'abcdefghijklmnopqrstuvwxyz'

ascii_uppercase = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'

ascii_letters = ascii_lowercase + ascii_uppercase

digits = '0123456789'

hexdigits = digits + 'abcdef' + 'ABCDEF'

octdigits = '01234567'

punctuation = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""

printable = digits + ascii_letters + punctuation + whitespace

# Functions which aren't available as string methods.

# Capitalize the words in a string, e.g. " aBc dEf " -> "Abc Def".

def capwords(s, sep=None):

"""capwords(s [,sep]) -> string

Split the argument into words using split, capitalize each

word using capitalize, and join the capitalized words using

join. If the optional second argument sep is absent or None,

runs of whitespace characters are replaced by a single space

and leading and trailing whitespace are removed, otherwise

sep is used to split and join the words.

"""

return (sep or ' ').join(x.capitalize() for x in s.split(sep))

####################################################################

import re as _re

from collections import ChainMap

class _TemplateMetaclass(type):

pattern = r"""

%(delim)s(?:

(?P<escaped>%(delim)s) | # Escape sequence of two delimiters

(?P<named>%(id)s) | # delimiter and a Python identifier

{(?P<braced>%(id)s)} | # delimiter and a braced identifier

(?P<invalid>) # Other ill-formed delimiter exprs

)

"""

def __init__(cls, name, bases, dct):

super(_TemplateMetaclass, cls).__init__(name, bases, dct)

if 'pattern' in dct:

pattern = cls.pattern

else:

pattern = _TemplateMetaclass.pattern % {

'delim' : _re.escape(cls.delimiter),

'id' : cls.idpattern,

}

cls.pattern = _re.compile(pattern, cls.flags | _re.VERBOSE)

class Template(metaclass=_TemplateMetaclass):

"""A string class for supporting $-substitutions."""

delimiter = '$'

idpattern = r'[_a-z][_a-z0-9]*'

flags = _re.IGNORECASE

def __init__(self, template):

self.template = template

# Search for $$, $identifier, ${identifier}, and any bare $'s

def _invalid(self, mo):

i = mo.start('invalid')

lines = self.template[:i].splitlines(keepends=True)

if not lines:

colno = 1

lineno = 1

else:

colno = i - len(''.join(lines[:-1]))

lineno = len(lines)

raise ValueError('Invalid placeholder in string: line %d, col %d' %

(lineno, colno))

def substitute(*args, **kws):

if not args:

raise TypeError("descriptor 'substitute' of 'Template' object "

"needs an argument")

self, *args = args # allow the "self" keyword be passed

if len(args) > 1:

raise TypeError('Too many positional arguments')

if not args:

mapping = kws

elif kws:

mapping = ChainMap(kws, args[0])

else:

mapping = args[0]

# Helper function for .sub()

def convert(mo):

# Check the most common path first.

named = mo.group('named') or mo.group('braced')

if named is not None:

val = mapping[named]

# We use this idiom instead of str() because the latter will

# fail if val is a Unicode containing non-ASCII characters.

return '%s' % (val,)

if mo.group('escaped') is not None:

return self.delimiter

if mo.group('invalid') is not None:

self._invalid(mo)

raise ValueError('Unrecognized named group in pattern',

self.pattern)

return self.pattern.sub(convert, self.template)

def safe_substitute(*args, **kws):

if not args:

raise TypeError("descriptor 'safe_substitute' of 'Template' object "

"needs an argument")

self, *args = args # allow the "self" keyword be passed

if len(args) > 1:

raise TypeError('Too many positional arguments')

if not args:

mapping = kws

elif kws:

mapping = ChainMap(kws, args[0])

else:

mapping = args[0]

# Helper function for .sub()

def convert(mo):

named = mo.group('named') or mo.group('braced')

if named is not None:

try:

# We use this idiom instead of str() because the latter

# will fail if val is a Unicode containing non-ASCII

return '%s' % (mapping[named],)

except KeyError:

return mo.group()

if mo.group('escaped') is not None:

return self.delimiter

if mo.group('invalid') is not None:

return mo.group()

raise ValueError('Unrecognized named group in pattern',

self.pattern)

return self.pattern.sub(convert, self.template)

########################################################################

# the Formatter class

# see PEP 3101 for details and purpose of this class

# The hard parts are reused from the C implementation. They're exposed as "_"

# prefixed methods of str.

# The overall parser is implemented in _string.formatter_parser.

# The field name parser is implemented in _string.formatter_field_name_split

class Formatter:

def format(*args, **kwargs):

if not args:

raise TypeError("descriptor 'format' of 'Formatter' object "

"needs an argument")

self, *args = args # allow the "self" keyword be passed

try:

format_string, *args = args # allow the "format_string" keyword be passed

except ValueError:

if 'format_string' in kwargs:

format_string = kwargs.pop('format_string')

else:

raise TypeError("format() missing 1 required positional "

"argument: 'format_string'") from None

return self.vformat(format_string, args, kwargs)

def vformat(self, format_string, args, kwargs):

used_args = set()

result, _ = self._vformat(format_string, args, kwargs, used_args, 2)

self.check_unused_args(used_args, args, kwargs)

return result

def _vformat(self, format_string, args, kwargs, used_args, recursion_depth,

auto_arg_index=0):

if recursion_depth < 0:

raise ValueError('Max string recursion exceeded')

result = []

for literal_text, field_name, format_spec, conversion in \

self.parse(format_string):

# output the literal text

if literal_text:

result.append(literal_text)

# if there's a field, output it

if field_name is not None:

# this is some markup, find the object and do

# the formatting

# handle arg indexing when empty field_names are given.

if field_name == '':

if auto_arg_index is False:

raise ValueError('cannot switch from manual field '

'specification to automatic field '

'numbering')

field_name = str(auto_arg_index)

auto_arg_index += 1

elif field_name.isdigit():

if auto_arg_index:

raise ValueError('cannot switch from manual field '

'specification to automatic field '

'numbering')

# disable auto arg incrementing, if it gets

# used later on, then an exception will be raised

auto_arg_index = False

# given the field_name, find the object it references

# and the argument it came from

obj, arg_used = self.get_field(field_name, args, kwargs)

used_args.add(arg_used)

# do any conversion on the resulting object

obj = self.convert_field(obj, conversion)

# expand the format spec, if needed

format_spec, auto_arg_index = self._vformat(

format_spec, args, kwargs,

used_args, recursion_depth-1,

auto_arg_index=auto_arg_index)

# format the object and append to the result

result.append(self.format_field(obj, format_spec))

return ''.join(result), auto_arg_index

def get_value(self, key, args, kwargs):

if isinstance(key, int):

return args[key]

else:

return kwargs[key]

def check_unused_args(self, used_args, args, kwargs):

pass

def format_field(self, value, format_spec):

return format(value, format_spec)

def convert_field(self, value, conversion):

# do any conversion on the resulting object

if conversion is None:

return value

elif conversion == 's':

return str(value)

elif conversion == 'r':

return repr(value)

elif conversion == 'a':

return ascii(value)

raise ValueError("Unknown conversion specifier {0!s}".format(conversion))

# returns an iterable that contains tuples of the form:

# (literal_text, field_name, format_spec, conversion)

# literal_text can be zero length

# field_name can be None, in which case there's no

# object to format and output

# if field_name is not None, it is looked up, formatted

# with format_spec and conversion and then used

def parse(self, format_string):

return _string.formatter_parser(format_string)

# given a field_name, find the object it references.

# field_name: the field being looked up, e.g. "0.name"

# or "lookup[3]"

# used_args: a set of which args have been used

# args, kwargs: as passed in to vformat

def get_field(self, field_name, args, kwargs):

first, rest = _string.formatter_field_name_split(field_name)

obj = self.get_value(first, args, kwargs)

# loop through the rest of the field_name, doing

# getattr or getitem as needed

for is_attr, i in rest:

if is_attr:

obj = getattr(obj, i)

else:

obj = obj[i]

return obj, first

cpython/Lib/string.py at 3.4 · python/cpython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

string.py

Latest commit

History

Breadcrumbs

string.py

File metadata and controls