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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
|
# Licensed under a 3-clause BSD style license - see LICENSE.rst
# Note that files generated by lex/yacc not always fully py 2/3 compatible.
# Hence, the ``clean_parse_tables.py`` tool in the astropy-tools
# (https://github.com/astropy/astropy-tools) repository should be used to fix
# this when/if lextab/parsetab files are re-generated.
"""
Handles a "generic" string format for units
"""
from __future__ import (absolute_import, division, print_function,
unicode_literals)
from ...extern import six
import os
import re
import warnings
from . import core, utils
from .base import Base
from ...utils import classproperty
from ...utils.misc import did_you_mean
def _to_string(cls, unit):
if isinstance(unit, core.CompositeUnit):
parts = []
if cls._show_scale and unit.scale != 1:
parts.append('{0:g}'.format(unit.scale))
if len(unit.bases):
positives, negatives = utils.get_grouped_by_powers(
unit.bases, unit.powers)
if len(positives):
parts.append(cls._format_unit_list(positives))
elif len(parts) == 0:
parts.append('1')
if len(negatives):
parts.append('/')
unit_list = cls._format_unit_list(negatives)
if len(negatives) == 1:
parts.append('{0}'.format(unit_list))
else:
parts.append('({0})'.format(unit_list))
return ' '.join(parts)
elif isinstance(unit, core.NamedUnit):
return cls._get_unit_name(unit)
class Generic(Base):
"""
A "generic" format.
The syntax of the format is based directly on the FITS standard,
but instead of only supporting the units that FITS knows about, it
supports any unit available in the `astropy.units` namespace.
"""
_show_scale = True
_tokens = (
'DOUBLE_STAR',
'STAR',
'PERIOD',
'SOLIDUS',
'CARET',
'OPEN_PAREN',
'CLOSE_PAREN',
'FUNCNAME',
'UNIT',
'SIGN',
'UINT',
'UFLOAT'
)
@classproperty(lazy=True)
def _all_units(cls):
return cls._generate_unit_names()
@classproperty(lazy=True)
def _units(cls):
return cls._all_units[0]
@classproperty(lazy=True)
def _deprecated_units(cls):
return cls._all_units[1]
@classproperty(lazy=True)
def _functions(cls):
return cls._all_units[2]
@classproperty(lazy=True)
def _parser(cls):
return cls._make_parser()
@classproperty(lazy=True)
def _lexer(cls):
return cls._make_lexer()
@classmethod
def _make_lexer(cls):
from ply import lex
tokens = cls._tokens
t_STAR = r'\*'
t_PERIOD = r'\.'
t_SOLIDUS = r'/'
t_DOUBLE_STAR = r'\*\*'
t_CARET = r'\^'
t_OPEN_PAREN = r'\('
t_CLOSE_PAREN = r'\)'
# NOTE THE ORDERING OF THESE RULES IS IMPORTANT!!
# Regular expression rules for simple tokens
def t_UFLOAT(t):
r'((\d+\.?\d*)|(\.\d+))([eE][+-]?\d+)?'
if not re.search(r'[eE\.]', t.value):
t.type = 'UINT'
t.value = int(t.value)
elif t.value.endswith('.'):
t.type = 'UINT'
t.value = int(t.value[:-1])
else:
t.value = float(t.value)
return t
def t_UINT(t):
r'\d+'
t.value = int(t.value)
return t
def t_SIGN(t):
r'[+-](?=\d)'
t.value = float(t.value + '1')
return t
# This needs to be a function so we can force it to happen
# before t_UNIT
def t_FUNCNAME(t):
r'((sqrt)|(ln)|(exp)|(log)|(mag)|(dB)|(dex))(?=\ *\()'
return t
def t_UNIT(t):
r"%|([YZEPTGMkhdcmunpfazy]?'((?!\d)\w)+')|((?!\d)\w)+"
t.value = cls._get_unit(t)
return t
t_ignore = ' '
# Error handling rule
def t_error(t):
raise ValueError(
"Invalid character at col {0}".format(t.lexpos))
try:
from . import generic_lextab
lexer = lex.lex(optimize=True, lextab=generic_lextab,
reflags=re.UNICODE)
except ImportError:
lexer = lex.lex(optimize=True, lextab='generic_lextab',
outputdir=os.path.dirname(__file__),
reflags=re.UNICODE)
return lexer
@classmethod
def _make_parser(cls):
"""
The grammar here is based on the description in the `FITS
standard
<http://fits.gsfc.nasa.gov/standard30/fits_standard30aa.pdf>`_,
Section 4.3, which is not terribly precise. The exact grammar
is here is based on the YACC grammar in the `unity library
<https://bitbucket.org/nxg/unity/>`_.
This same grammar is used by the `"fits"` and `"vounit"`
formats, the only difference being the set of available unit
strings.
"""
from ply import yacc
tokens = cls._tokens
def p_main(p):
'''
main : product_of_units
| factor product_of_units
| factor product product_of_units
| division_product_of_units
| factor division_product_of_units
| factor product division_product_of_units
| inverse_unit
| factor inverse_unit
| factor product inverse_unit
| factor
'''
from ..core import Unit
if len(p) == 2:
p[0] = Unit(p[1])
elif len(p) == 3:
p[0] = Unit(p[1] * p[2])
elif len(p) == 4:
p[0] = Unit(p[1] * p[3])
def p_division_product_of_units(p):
'''
division_product_of_units : division_product_of_units division product_of_units
| product_of_units
'''
from ..core import Unit
if len(p) == 4:
p[0] = Unit(p[1] / p[3])
else:
p[0] = p[1]
def p_inverse_unit(p):
'''
inverse_unit : division unit_expression
'''
p[0] = p[2] ** -1
def p_factor(p):
'''
factor : factor_fits
| factor_float
| factor_int
'''
p[0] = p[1]
def p_factor_float(p):
'''
factor_float : signed_float
| signed_float UINT signed_int
| signed_float UINT power numeric_power
'''
if cls.name == 'fits':
raise ValueError("Numeric factor not supported by FITS")
if len(p) == 4:
p[0] = p[1] * p[2] ** float(p[3])
elif len(p) == 5:
p[0] = p[1] * p[2] ** float(p[4])
elif len(p) == 2:
p[0] = p[1]
def p_factor_int(p):
'''
factor_int : UINT
| UINT signed_int
| UINT power numeric_power
| UINT UINT signed_int
| UINT UINT power numeric_power
'''
if cls.name == 'fits':
raise ValueError("Numeric factor not supported by FITS")
if len(p) == 2:
p[0] = p[1]
elif len(p) == 3:
p[0] = p[1] ** float(p[2])
elif len(p) == 4:
if isinstance(p[2], int):
p[0] = p[1] * p[2] ** float(p[3])
else:
p[0] = p[1] ** float(p[3])
elif len(p) == 5:
p[0] = p[1] * p[2] ** p[4]
def p_factor_fits(p):
'''
factor_fits : UINT power OPEN_PAREN signed_int CLOSE_PAREN
| UINT power signed_int
| UINT SIGN UINT
| UINT OPEN_PAREN signed_int CLOSE_PAREN
'''
if p[1] != 10:
if cls.name == 'fits':
raise ValueError("Base must be 10")
else:
return
if len(p) == 4:
if p[2] in ('**', '^'):
p[0] = 10 ** p[3]
else:
p[0] = 10 ** (p[2] * p[3])
elif len(p) == 5:
p[0] = 10 ** p[3]
elif len(p) == 6:
p[0] = 10 ** p[4]
def p_product_of_units(p):
'''
product_of_units : unit_expression product product_of_units
| unit_expression product_of_units
| unit_expression
'''
if len(p) == 2:
p[0] = p[1]
elif len(p) == 3:
p[0] = p[1] * p[2]
else:
p[0] = p[1] * p[3]
def p_unit_expression(p):
'''
unit_expression : function
| unit_with_power
| OPEN_PAREN product_of_units CLOSE_PAREN
'''
if len(p) == 2:
p[0] = p[1]
else:
p[0] = p[2]
def p_unit_with_power(p):
'''
unit_with_power : UNIT power numeric_power
| UNIT numeric_power
| UNIT
'''
if len(p) == 2:
p[0] = p[1]
elif len(p) == 3:
p[0] = p[1] ** p[2]
else:
p[0] = p[1] ** p[3]
def p_numeric_power(p):
'''
numeric_power : sign UINT
| OPEN_PAREN paren_expr CLOSE_PAREN
'''
if len(p) == 3:
p[0] = p[1] * p[2]
elif len(p) == 4:
p[0] = p[2]
def p_paren_expr(p):
'''
paren_expr : sign UINT
| signed_float
| frac
'''
if len(p) == 3:
p[0] = p[1] * p[2]
else:
p[0] = p[1]
def p_frac(p):
'''
frac : sign UINT division sign UINT
'''
p[0] = (p[1] * p[2]) / (p[4] * p[5])
def p_sign(p):
'''
sign : SIGN
|
'''
if len(p) == 2:
p[0] = p[1]
else:
p[0] = 1.0
def p_product(p):
'''
product : STAR
| PERIOD
'''
pass
def p_division(p):
'''
division : SOLIDUS
'''
pass
def p_power(p):
'''
power : DOUBLE_STAR
| CARET
'''
p[0] = p[1]
def p_signed_int(p):
'''
signed_int : SIGN UINT
'''
p[0] = p[1] * p[2]
def p_signed_float(p):
'''
signed_float : sign UINT
| sign UFLOAT
'''
p[0] = p[1] * p[2]
def p_function_name(p):
'''
function_name : FUNCNAME
'''
p[0] = p[1]
def p_function(p):
'''
function : function_name OPEN_PAREN main CLOSE_PAREN
'''
if p[1] == 'sqrt':
p[0] = p[3] ** 0.5
return
elif p[1] in ('mag', 'dB', 'dex'):
function_unit = cls._parse_unit(p[1])
# In Generic, this is callable, but that does not have to
# be the case in subclasses (e.g., in VOUnit it is not).
if callable(function_unit):
p[0] = function_unit(p[3])
return
raise ValueError("'{0}' is not a recognized function".format(p[1]))
def p_error(p):
raise ValueError()
try:
from . import generic_parsetab
parser = yacc.yacc(debug=False, tabmodule=generic_parsetab,
write_tables=False)
except ImportError:
parser = yacc.yacc(debug=False, tabmodule='generic_parsetab',
outputdir=os.path.dirname(__file__))
return parser
@classmethod
def _get_unit(cls, t):
try:
return cls._parse_unit(t.value)
except ValueError as e:
raise ValueError(
"At col {0}, {1}".format(
t.lexpos, six.text_type(e)))
@classmethod
def _parse_unit(cls, s, detailed_exception=True):
registry = core.get_current_unit_registry().registry
if s == '%':
return registry['percent']
elif s in registry:
return registry[s]
if detailed_exception:
raise ValueError(
'{0} is not a valid unit. {1}'.format(
s, did_you_mean(s, registry)))
else:
raise ValueError()
@classmethod
def parse(cls, s, debug=False):
if not isinstance(s, six.text_type):
s = s.decode('ascii')
result = cls._do_parse(s, debug=debug)
if s.count('/') > 1:
warnings.warn(
"'{0}' contains multiple slashes, which is "
"discouraged by the FITS standard".format(s),
core.UnitsWarning)
return result
@classmethod
def _do_parse(cls, s, debug=False):
try:
# This is a short circuit for the case where the string
# is just a single unit name
return cls._parse_unit(s, detailed_exception=False)
except ValueError as e:
try:
return cls._parser.parse(s, lexer=cls._lexer, debug=debug)
except ValueError as e:
if six.text_type(e):
raise
else:
raise ValueError(
"Syntax error parsing unit '{0}'".format(s))
@classmethod
def _get_unit_name(cls, unit):
return unit.get_format_name('generic')
@classmethod
def _format_unit_list(cls, units):
out = []
units.sort(key=lambda x: cls._get_unit_name(x[0]).lower())
for base, power in units:
if power == 1:
out.append(cls._get_unit_name(base))
else:
power = utils.format_power(power)
if '/' in power:
out.append('{0}({1})'.format(
cls._get_unit_name(base), power))
else:
out.append('{0}{1}'.format(
cls._get_unit_name(base), power))
return ' '.join(out)
@classmethod
def to_string(cls, unit):
return _to_string(cls, unit)
class Unscaled(Generic):
"""
A format that doesn't display the scale part of the unit, other
than that, it is identical to the `Generic` format.
This is used in some error messages where the scale is irrelevant.
"""
_show_scale = False
|