def _parse(self, value):
"""
Parse media type string into components
:attr value: Media type value
e.g. text/html;level=2;q=0.4
:type value: str, bytes
:returns: MediaType instance
"""
full_type, parameters = padded_split(value.strip(), ';', 1)
full_type = '*/*' if full_type == '*' else full_type
type, subtype = padded_split(full_type, '/', 1)
if type is None or subtype is None:
raise ParseError()
# type can only be a wildcard with subtype
if type == '*' and subtype != '*':
raise ParseError()
def fix_param(x):
key, value = padded_split(x, '=', 1)
if not key or not value:
raise ParseError()
if str.isdigit(value):
value = int(value)
return (key, value)
parameters = OrderedDict([ fix_param(param)
for param in parameters.split(";") ]) if parameters else {}
kwargs = dict(type=type, subtype=subtype, parameters=parameters)
return kwargs
def ionic_strength(molalities,
charges=None,
units=None,
substances=None,
substance_factory=Substance.from_formula,
warn=True):
""" Calculates the ionic strength
Parameters
----------
molalities: array_like or dict
Optionally with unit (amount / mass).
when dict: mapping substance key to molality.
charges: array_like
Charge of respective ion, taken for substances when None.
units: object (optional, default: None)
Attributes accessed: molal.
substances: dict, optional
Mapping of substance keys to Substance instances (used when molalities
is a dict).
substance_factory: callback
Used if `substances` is a string.
warn: bool
Issue a warning if molalities violates net charge neutrality.
Examples
--------
>>> ionic_strength([1e-3, 3e-3], [3, -1]) == .5 * (9 + 3) * 1e-3
True
>>> ionic_strength({'Mg+2': 6, 'PO4-3': 4})
30.0
"""
tot = None
if charges is None:
if substances is None:
substances = ' '.join(molalities.keys())
if isinstance(substances, str):
substances = OrderedDict([(k, substance_factory(k))
for k in substances.split()])
charges, molalities = zip(*[(substances[k].charge, v)
for k, v in molalities.items()])
if len(molalities) != len(charges):
raise ValueError("molalities and charges of different lengths")
for b, z in zip(molalities, charges):
if tot is None:
tot = b * z**2
else:
tot += b * z**2
if warn:
net = None
for b, z in zip(molalities, charges):
if net is None:
net = b * z
else:
net += b * z
if not allclose(net, tot * 0, atol=tot * 1e-14):
warnings.warn("Molalities not charge neutral: %s" % str(net))
return tot / 2
def __init__(self, word, columns):
word = OrderedDict(zip(columns, word.split()))
self.idx = int(word.pop('idx'))
self.token = word.pop('token')
self.lemma = word.pop('lemma')
self.tag = word.pop('tag')
self._extras = word.copy()
def ionic_strength(molalities, charges=None, units=None, substances=None,
substance_factory=Substance.from_formula, warn=True):
""" Calculates the ionic strength
Parameters
----------
molalities: array_like or dict
Optionally with unit (amount / mass).
when dict: mapping substance key to molality.
charges: array_like
Charge of respective ion, taken for substances when None.
units: object (optional, default: None)
Attributes accessed: molal.
substances: dict, optional
Mapping of substance keys to Substance instances (used when molalities
is a dict).
substance_factory: callback
Used if `substances` is a string.
warn: bool
Issue a warning if molalities violates net charge neutrality.
Examples
--------
>>> ionic_strength([1e-3, 3e-3], [3, -1]) == .5 * (9 + 3) * 1e-3
True
>>> ionic_strength({'Mg+2': 6, 'PO4-3': 4})
30.0
"""
tot = None
if charges is None:
if substances is None:
substances = ' '.join(molalities.keys())
if isinstance(substances, str):
substances = OrderedDict([(k, substance_factory(k)) for k
in substances.split()])
charges, molalities = zip(*[(substances[k].charge, v) for k, v in molalities.items()])
if len(molalities) != len(charges):
raise ValueError("molalities and charges of different lengths")
for b, z in zip(molalities, charges):
if tot is None:
tot = b * z**2
else:
tot += b * z**2
if warn:
net = None
for b, z in zip(molalities, charges):
if net is None:
net = b * z
else:
net += b * z
if not allclose(net, tot*0, atol=tot*1e-14):
warnings.warn("Molalities not charge neutral: %s" % str(net))
return tot/2
def _simplify_feature_value(self, name, value):
"""Return simplified and more pythonic feature values."""
if name == 'prefix':
channel_modes, channel_chars = value.split(')')
channel_modes = channel_modes[1:]
# [::-1] to reverse order and go from lowest to highest privs
value = OrderedDict(list(zip(channel_modes, channel_chars))[::-1])
return value
elif name == 'chanmodes':
value = value.split(',')
return value
elif name == 'targmax':
max_available = {}
for sort in value.split(','):
command, limit = sort.split(':')
command = command.casefold()
max_available[command] = limit_to_number(limit)
return max_available
elif name == 'chanlimit':
limit_available = {}
for sort in value.split(','):
chan_types, limit = sort.split(':')
for prefix in chan_types:
limit_available[prefix] = limit_to_number(limit)
return limit_available
elif name in _limits:
value = limit_to_number(value)
return value
else:
return value
def compact_etable_plot(df,
title=None,
size=2.2,
col_wrap=8,
xticks=np.arange(0, 7),
yticks=np.arange(-2, 3),
xlim=(0.0, 6.0),
ylim=(-2.5, 2.5),
marker='',
ms=0,
lw=1,
aspect=0.7,
scores=None):
if not scores:
scores = OrderedDict(
fa_atr='green',
fa_rep='red',
fa_sol='blue',
fa_elec='orange',
lk_ball_wtd='purple',
score='black',
)
elif isinstance(scores, str):
colors = 'black red green blue orange purple'.split()
tmp = OrderedDict()
for i, k in enumerate(scores.split()):
tmp[k] = colors[i]
scores = tmp
sns.set(style="ticks")
grid = sns.FacetGrid(df,
col='t',
size=size,
col_wrap=col_wrap,
aspect=aspect)
grid.map(plt.axhline, y=0, ls=":", c='.5')
for score, col in list(scores.items()):
grid.map(plt.plot,
'dist',
score,
marker=marker,
lw=lw,
ms=ms,
color=col)
grid.set(xticks=xticks, yticks=yticks, xlim=xlim, ylim=ylim)
grid.fig.tight_layout(h_pad=1, w_pad=0)
if title:
grid.fig.suptitle(title)
return grid
def get_dropout(self, conv_drop='', blocks=0):
if conv_drop.startswith('all-'):
dropout = float(conv_drop.split('-')[1])
conv_drop = OrderedDict()
for i in range(1, blocks + 1):
conv_drop.setdefault(i, dropout)
return conv_drop
elif conv_drop.startswith('bet-'):
import numpy as np
dropout = conv_drop.split('-')
dropout = [float(dropout[1]), float(dropout[2])]
dropout = np.arange(dropout[0], dropout[1],
(dropout[1] - dropout[0]) / blocks)
conv_drop = OrderedDict()
for i in range(1, blocks + 1):
conv_drop.setdefault(i, round(dropout[i - 1], 3))
return conv_drop
def ionic_strength(molalities,
charges=None,
b0=1,
units=None,
substances=None,
substance_factory=Substance.from_formula):
""" Calculates the ionic strength
Parameters
----------
molalities: array_like or dict
Optionally with unit (amount / mass).
when dict: mapping substance key to molality.
charges: array_like
Charge of respective ion, taken for substances when None.
units: object (optional, default: None)
Attributes accessed: molal.
substances: dict, optional
Mapping of substance keys to Substance instances (used when molalities
is a dict).
substance_factory: callback
Used if `substances` is a string.
Examples
--------
>>> ionic_strength([1e-3, 3e-3], [3, -1]) == .5 * (9 + 3) * 1e-3
True
>>> ionic_strength({'Mg+2': 6, 'PO4-3': 4})
30.0
"""
tot = 0
if charges is None:
if substances is None:
substances = ' '.join(molalities.keys())
if isinstance(substances, str):
substances = OrderedDict([(k, substance_factory(k))
for k in substances.split()])
charges, molalities = zip(*[(substances[k].charge, v)
for k, v in molalities.items()])
if len(molalities) != len(charges):
raise ValueError("molalities and charges of different lengths")
for b, z in zip(molalities, charges):
tot += b * z**2
return tot / 2
def ionic_strength(molalities, charges=None, b0=1, units=None, substances=None,
substance_factory=Substance.from_formula):
""" Calculates the ionic strength
Parameters
----------
molalities: array_like or dict
Optionally with unit (amount / mass).
when dict: mapping substance key to molality.
charges: array_like
Charge of respective ion, taken for substances when None.
units: object (optional, default: None)
Attributes accessed: molal.
substances: dict, optional
Mapping of substance keys to Substance instances (used when molalities
is a dict).
substance_factory: callback
Used if `substances` is a string.
Examples
--------
>>> ionic_strength([1e-3, 3e-3], [3, -1]) == .5 * (9 + 3) * 1e-3
True
>>> ionic_strength({'Mg+2': 6, 'PO4-3': 4})
30.0
"""
tot = 0
if charges is None:
if substances is None:
substances = ' '.join(molalities.keys())
if isinstance(substances, str):
substances = OrderedDict([(k, substance_factory(k)) for k
in substances.split()])
charges, molalities = zip(*[(substances[k].charge, v) for k, v in molalities.items()])
if len(molalities) != len(charges):
raise ValueError("molalities and charges of different lengths")
for b, z in zip(molalities, charges):
tot += b * z**2
return tot/2
def parse_ascconv(ascconv_str, str_delim='"'):
'''Parse the 'ASCCONV' format from `input_str`.
Parameters
----------
ascconv_str : str
The string we are parsing
str_delim : str, optional
String delimiter. Typically '"' or '""'
Returns
-------
prot_dict : OrderedDict
Meta data pulled from the ASCCONV section.
attrs : OrderedDict
Any attributes stored in the 'ASCCONV BEGIN' line
Raises
------
AsconvParseError
A line of the ASCCONV section could not be parsed.
'''
attrs, content = ASCCONV_RE.match(ascconv_str).groups()
attrs = OrderedDict((tuple(x.split('=')) for x in attrs.split()))
# Normalize string start / end markers to something Python understands
content = content.replace(str_delim, '"""').replace("\\", "\\\\")
# Use Python's own parser to parse modified ASCCONV assignments
tree = ast.parse(content)
prot_dict = OrderedDict()
for assign in tree.body:
atoms = assign2atoms(assign)
obj_to_index, key = obj_from_atoms(atoms, prot_dict)
obj_to_index[key] = _get_value(assign)
return prot_dict, attrs
class SMParser(object):
TOKENS = (
'TITLE', 'SUBTITLE', 'ARTIST',
'TITLETRANSLIT', 'SUBTITLETRANSLIT',
'ARTISTTRANSLIT', 'CREDIT', 'BANNER',
'BACKGROUND', 'LYRICSPATH', 'CDTITLE',
'MUSIC', 'OFFSET', 'SAMPLESTART',
'SAMPLELENGTH', 'SELECTABLE', 'DISPLAYBPM',
'BPMS', 'STOPS', 'BGCHANGES',
)
BOM_CHAR = '\xef\xbb\xbf'
SECTION_HEADER = '//--'
STYLES = ('dance-single', 'dance-double')
DIFFICULTIES = ('Easy', 'Medium', 'Hard')
FOOT_RATINGS = range(1, 11)
STEP_TYPES = '0123'
def __init__(self, simfile):
self.charts = {}
self._simfile = simfile
self._parse_header_tokens()
self._parse_sections()
def _parse_header_tokens(self):
for line in StringIO(self._simfile):
try:
token, value = (line.strip()
.replace(self.BOM_CHAR, '')
.split(':')[:2])
except ValueError:
continue
if token[1:] in self.TOKENS:
setattr(self, token[1:], value.strip(';'))
if token[1:] == 'BPMS':
self.BPMS = OrderedDict([measure.split('=') for measure
in self.BPMS.split(',')])
elif line.startswith(self.SECTION_HEADER):
break
def _parse_sections(self):
def _dos_to_unix(s):
return s.replace('\r', '')
parsing = False
parsing_measure = False
measure_counter = 1
for line in StringIO(self._simfile):
line = _dos_to_unix(line.strip())
if not parsing and not line.startswith(self.SECTION_HEADER):
continue
elif line.startswith(self.SECTION_HEADER):
# parse section header
parsing = True
style = 'Double' if 'double' in line else 'Single'
self.charts[style] = self.charts.setdefault(style, {})
elif parsing and ':' in line:
# Parse #INFO section
value = line.split(':')[0]
if value in self.DIFFICULTIES:
difficulty = value
self.charts[style][difficulty] = {}
elif value in self.FOOT_RATINGS:
self.charts[style][difficulty]['foot rating'] = value
elif ',' in value:
self.charts[style][difficulty]['?'] = value
elif all((c in self.STEP_TYPES for c in line)) and line != '':
# parse individual measures
if parsing_measure:
measure['steps'].append(line)
else:
measure = {'measure': measure_counter, 'steps': [line]}
parsing_measure = True
self.charts[style][difficulty]['chart'] = self.charts[style][
difficulty].setdefault('chart', [])
elif line.startswith(',') and parsing_measure:
# stop parsing measure
self.charts[style][difficulty]['chart'].append(measure)
parsing_measure = False
measure_counter += 1
elif line.startswith(';') and parsing:
# stop parsing section
parsing, parsing_measure = False, False
measure_counter = 1
def balance_stoichiometry(reactants, products, substances=None,
substance_factory=Substance.from_formula,
parametric_symbols=None, underdetermined=True, allow_duplicates=False):
""" Balances stoichiometric coefficients of a reaction
Parameters
----------
reactants : iterable of reactant keys
products : iterable of product keys
substances : OrderedDict or string or None
Mapping reactant/product keys to instances of :class:`Substance`.
substance_factory : callback
parametric_symbols : generator of symbols
Used to generate symbols for parametric solution for
under-determined system of equations. Default is numbered "x-symbols" starting
from 1.
underdetermined : bool
Allows to find a non-unique solution (in addition to a constant factor
across all terms). Set to ``False`` to disallow (raise ValueError) on
e.g. "C + O2 -> CO + CO2". Set to ``None`` if you want the symbols replaced
so that the coefficients are the smallest possible positive (non-zero) integers.
allow_duplicates : bool
If False: raises an excpetion if keys appear in both ``reactants`` and ``products``.
Examples
--------
>>> ref = {'C2H2': 2, 'O2': 3}, {'CO': 4, 'H2O': 2}
>>> balance_stoichiometry({'C2H2', 'O2'}, {'CO', 'H2O'}) == ref
True
>>> ref2 = {'H2': 1, 'O2': 1}, {'H2O2': 1}
>>> balance_stoichiometry('H2 O2'.split(), ['H2O2'], 'H2 O2 H2O2') == ref2
True
>>> reac, prod = 'CuSCN KIO3 HCl'.split(), 'CuSO4 KCl HCN ICl H2O'.split()
>>> Reaction(*balance_stoichiometry(reac, prod)).string()
'4 CuSCN + 7 KIO3 + 14 HCl -> 4 CuSO4 + 7 KCl + 4 HCN + 7 ICl + 5 H2O'
>>> balance_stoichiometry({'Fe', 'O2'}, {'FeO', 'Fe2O3'}, underdetermined=False)
Traceback (most recent call last):
...
ValueError: The system was under-determined
>>> r, p = balance_stoichiometry({'Fe', 'O2'}, {'FeO', 'Fe2O3'})
>>> list(set.union(*[v.free_symbols for v in r.values()]))
[x1]
>>> b = balance_stoichiometry({'Fe', 'O2'}, {'FeO', 'Fe2O3'}, underdetermined=None)
>>> b == ({'Fe': 3, 'O2': 2}, {'FeO': 1, 'Fe2O3': 1})
True
>>> d = balance_stoichiometry({'C', 'CO'}, {'C', 'CO', 'CO2'}, underdetermined=None, allow_duplicates=True)
>>> d == ({'CO': 2}, {'C': 1, 'CO2': 1})
True
Returns
-------
balanced reactants : dict
balanced products : dict
"""
import sympy
from sympy import (
MutableDenseMatrix, gcd, zeros, linsolve, numbered_symbols, Wild, Symbol,
Integer, Tuple, preorder_traversal as pre
)
_intersect = sorted(set.intersection(*map(set, (reactants, products))))
if _intersect:
if allow_duplicates:
if underdetermined is not None:
raise NotImplementedError("allow_duplicates currently requires underdetermined=None")
if set(reactants) == set(products):
raise ValueError("cannot balance: reactants and products identical")
# For each duplicate, try to drop it completely:
for dupl in _intersect:
try:
result = balance_stoichiometry(
[sp for sp in reactants if sp != dupl],
[sp for sp in products if sp != dupl],
substances=substances, substance_factory=substance_factory,
underdetermined=underdetermined, allow_duplicates=True)
except Exception:
continue
else:
return result
for perm in product(*[(False, True)]*len(_intersect)): # brute force (naive)
r = set(reactants)
p = set(products)
for remove_reac, dupl in zip(perm, _intersect):
if remove_reac:
r.remove(dupl)
else:
p.remove(dupl)
try:
result = balance_stoichiometry(
r, p, substances=substances, substance_factory=substance_factory,
parametric_symbols=parametric_symbols, underdetermined=underdetermined,
allow_duplicates=False)
except ValueError:
continue
else:
return result
else:
raise ValueError("Failed to remove duplicate keys: %s" % _intersect)
else:
raise ValueError("Substances on both sides: %s" % str(_intersect))
if substances is None:
substances = OrderedDict([(k, substance_factory(k)) for k in chain(reactants, products)])
if isinstance(substances, str):
substances = OrderedDict([(k, substance_factory(k)) for k in substances.split()])
if type(reactants) == set: # we don't want isinstance since it might be "OrderedSet"
reactants = sorted(reactants)
if type(products) == set:
products = sorted(products)
subst_keys = list(reactants) + list(products)
cks = Substance.composition_keys(substances.values())
if parametric_symbols is None:
parametric_symbols = numbered_symbols('x', start=1, integer=True, positive=True)
# ?C2H2 + ?O2 -> ?CO + ?H2O
# Ax = 0
# A: x:
#
# C2H2 O2 CO H2O
# C -2 0 1 0 x0 = 0
# H -2 0 0 2 x1 0
# O 0 -2 1 1 x2 0
# x3
def _get(ck, sk):
return substances[sk].composition.get(ck, 0) * (-1 if sk in reactants else 1)
for ck in cks: # check that all components are present on reactant & product sides
for rk in reactants:
if substances[rk].composition.get(ck, 0) != 0:
break
else:
any_pos = any(substances[pk].composition.get(ck, 0) > 0 for pk in products)
any_neg = any(substances[pk].composition.get(ck, 0) < 0 for pk in products)
if any_pos and any_neg:
pass # negative and positive parts among products, no worries
else:
raise ValueError("Component '%s' not among reactants" % ck)
for pk in products:
if substances[pk].composition.get(ck, 0) != 0:
break
else:
any_pos = any(substances[pk].composition.get(ck, 0) > 0 for pk in reactants)
any_neg = any(substances[pk].composition.get(ck, 0) < 0 for pk in reactants)
if any_pos and any_neg:
pass # negative and positive parts among reactants, no worries
else:
raise ValueError("Component '%s' not among products" % ck)
A = MutableDenseMatrix([[_get(ck, sk) for sk in subst_keys] for ck in cks])
symbs = list(reversed([next(parametric_symbols) for _ in range(len(subst_keys))]))
sol, = linsolve((A, zeros(len(cks), 1)), symbs)
wi = Wild('wi', properties=[lambda k: not k.has(Symbol)])
cd = reduce(gcd, [1] + [1/m[wi] for m in map(
lambda n: n.match(symbs[-1]/wi), pre(sol)) if m is not None])
sol = sol.func(*[arg/cd for arg in sol.args])
def remove(cont, symb, remaining):
subsd = dict(zip(remaining/symb, remaining))
cont = cont.func(*[(arg/symb).expand().subs(subsd) for arg in cont.args])
if cont.has(symb):
raise ValueError("Bug, please report an issue at https://github.com/bjodah/chempy")
return cont
done = False
for idx, symb in enumerate(symbs):
for expr in sol:
iterable = expr.args if expr.is_Add else [expr]
for term in iterable:
if term.is_number:
done = True
break
if done:
break
if done:
break
for expr in sol:
if (expr/symb).is_number:
sol = remove(sol, symb, MutableDenseMatrix(symbs[idx+1:]))
break
for symb in symbs:
cd = 1
for expr in sol:
iterable = expr.args if expr.is_Add else [expr]
for term in iterable:
if term.is_Mul and term.args[0].is_number and term.args[1] == symb:
cd = gcd(cd, term.args[0])
if cd != 1:
sol = sol.func(*[arg.subs(symb, symb/cd) for arg in sol.args])
integer_one = 1 # need 'is' check, SyntaxWarning when checking against literal
if underdetermined is integer_one:
from ._release import __version__
if int(__version__.split('.')[1]) > 6:
warnings.warn( # deprecated because comparison with ``1`` problematic (True==1)
("Pass underdetermined == None instead of ``1`` (depreacted since 0.7.0,"
" will_be_missing_in='0.9.0')"), ChemPyDeprecationWarning)
underdetermined = None
if underdetermined is None:
sol = Tuple(*[Integer(x) for x in _solve_balancing_ilp_pulp(A)])
fact = gcd(sol)
sol = MutableDenseMatrix([e/fact for e in sol]).reshape(len(sol), 1)
sol /= reduce(gcd, sol)
if 0 in sol:
raise ValueError("Superfluous species given.")
if underdetermined:
if any(x == sympy.nan for x in sol):
raise ValueError("Failed to balance reaction")
else:
for x in sol:
if len(x.free_symbols) != 0:
raise ValueError("The system was under-determined")
if not all(residual == 0 for residual in A * sol):
raise ValueError("Failed to balance reaction")
def _x(k):
coeff = sol[subst_keys.index(k)]
return int(coeff) if underdetermined is None else coeff
return (
OrderedDict([(k, _x(k)) for k in reactants]),
OrderedDict([(k, _x(k)) for k in products])
)
def gdx_to_df(gdx_file, symbol, type='L', domain_info=None):
def __get_set(gdx_file, set_name):
if sys.platform in ['linux2', 'darwin']:
proc = subprocess.Popen(['gdxdump %s Symb=%s Format=csv NoHeader' % (gdx_file, set_name), ""],
stdout=subprocess.PIPE, shell=True,
stderr=subprocess.STDOUT)
elif sys.platform in ['win32']:
proc = subprocess.Popen(['gdxdump', '%s' % gdx_file, 'Symb=%s' % set_name, 'Format=csv', 'NoHeader', ''],
stdout=subprocess.PIPE, shell=True,
stderr=subprocess.STDOUT)
else:
raise GamsAddOnException('ERROR {platform} not handled'.format(platform=sys.platform))
(out, err) = proc.communicate()
try:
csv_in = csv.reader(out.split('\n'), delimiter=',')
return [int(row[0]) for row in csv_in if row]
except ValueError:
csv_in = csv.reader(out.split('\n'), delimiter=',')
return [row[0] for row in csv_in if row]
def __int(v):
try:
return int(v)
except ValueError:
return v
def __float(v):
try:
return float(v)
except ValueError:
return v
if domain_info is None:
domain_info = DomainInfo(gdx_file)
if symbol not in domain_info.symbols:
raise GamsAddOnException('"%s" not in Domain of "%s"' % (symbol, gdx_file))
sets = domain_info.get_sets(symbol)
index = OrderedDict()
if sets is None:
index['Idx'] = [1]
sets = ['Idx']
else:
for s in sets:
if s in domain_info.symbols:
set_values = __get_set(gdx_file, s)
set_name = s
while set_name in index.keys():
set_name = set_name + s
index[set_name] = set_values
elif s == '*':
index[s] = ['---PLACEHOLDER---']
else:
raise GamsAddOnException('Set "%s" of "%s" not in Domain of "%s"' % (s, symbol, gdx_file))
# print index.values()+[['l', 'm']]
if domain_info.symbols[symbol][0] in ['Var', 'Equ']:
multi_index = MultiIndex.from_product([index[s] for s in sets] + [['L', 'M', 'LO', 'UP', 'SCALE']])
df = DataFrame(0.0, index=multi_index, columns=[symbol])
df.index.names = index.keys() + ['Type']
else:
multi_index = MultiIndex.from_product([index[s] for s in index.keys()])
df = DataFrame(0.0, index=multi_index, columns=[symbol])
df.index.names = index.keys()
if sys.platform in ['linux2', 'darwin']:
proc = subprocess.Popen(['gdxdump %s Symb=%s FilterDef=N' % (gdx_file, symbol), ""],
stdout=subprocess.PIPE, shell=True,
stderr=subprocess.STDOUT)
elif sys.platform in ['win32']:
proc = subprocess.Popen(['gdxdump', '%s' % gdx_file, 'Symb=%s' % symbol, 'FilterDef=N', ''],
stdout=subprocess.PIPE, shell=True,
stderr=subprocess.STDOUT)
else:
raise GamsAddOnException('ERROR {platform} not handled'.format(platform=sys.platform))
(out, err) = proc.communicate()
out = out.replace('\n', '')
content = re.search(r'/.*/', out).group(0)[1:-1].replace('\'', '').strip().split(',')
if err:
raise GamsAddOnException('ERROR: {err}'.format(err=err))
elif content is []:
raise GamsAddOnException('ERROR: No content found for {symbol}'.format(symbol=symbol))
else:
indices = []
values = []
if domain_info.symbols[symbol][0] in ['Set']:
df[symbol] = False
for data in content:
if '.' in data:
indices.append(tuple([__int(d) for d in data.strip().split('.')]))
else:
indices.append(__int(data.strip()))
values.append(True)
else:
for data in content:
data = data.strip().split(' ')
if len(data) == 1:
indices.append(1)
values.append(__float(data[0]))
else:
index = data[0]
if '.' in index:
index = tuple([__int(i) for i in index.split('.')])
indices.append(index)
elif index in ['L', 'M', 'UP', 'LO', 'SCALE']:
index = (1, index)
indices.append(index)
else:
indices.append(__int(index))
values.append(__float(data[1]))
try:
# print 'NAME:', symbol, indices, values, len(values), df
if len(values) == 1 and values[0] == '':
return df
else:
# df.loc[indices, symbol] = values
# print df.index
df.loc[indices, symbol] = values
# for i,idx in enumerate(indices):
# df.loc[idx, symbol] = values[i]
except KeyError as ke:
print 'Warning', ke
if '*' in df.index.names:
for i, idx in enumerate(indices):
df.loc[idx, symbol] = True
df.drop('---PLACEHOLDER---', inplace=True)
if type is not None and 'Type' in df.index.names:
# print type
# print df.head()
return df.query('Type == "%s"' % type)
else:
return df
class SMParser(object):
TOKENS = (
'TITLE',
'SUBTITLE',
'ARTIST',
'TITLETRANSLIT',
'SUBTITLETRANSLIT',
'ARTISTTRANSLIT',
'CREDIT',
'BANNER',
'BACKGROUND',
'LYRICSPATH',
'CDTITLE',
'MUSIC',
'OFFSET',
'SAMPLESTART',
'SAMPLELENGTH',
'SELECTABLE',
'DISPLAYBPM',
'BPMS',
'STOPS',
'BGCHANGES',
)
BOM_CHAR = '\xef\xbb\xbf'
SECTION_HEADER = '//--'
STYLES = ('dance-single', 'dance-double')
DIFFICULTIES = ('Easy', 'Medium', 'Hard')
FOOT_RATINGS = range(1, 11)
STEP_TYPES = '0123'
def __init__(self, simfile):
self.charts = {}
self._simfile = simfile
self._parse_header_tokens()
self._parse_sections()
def _parse_header_tokens(self):
for line in StringIO(self._simfile):
try:
token, value = (line.strip().replace(self.BOM_CHAR,
'').split(':')[:2])
except ValueError:
continue
if token[1:] in self.TOKENS:
setattr(self, token[1:], value.strip(';'))
if token[1:] == 'BPMS':
self.BPMS = OrderedDict(
[measure.split('=') for measure in self.BPMS.split(',')])
elif line.startswith(self.SECTION_HEADER):
break
def _parse_sections(self):
def _dos_to_unix(s):
return s.replace('\r', '')
parsing = False
parsing_measure = False
measure_counter = 1
for line in StringIO(self._simfile):
line = _dos_to_unix(line.strip())
if not parsing and not line.startswith(self.SECTION_HEADER):
continue
elif line.startswith(self.SECTION_HEADER):
# parse section header
parsing = True
style = 'Double' if 'double' in line else 'Single'
self.charts[style] = self.charts.setdefault(style, {})
elif parsing and ':' in line:
# Parse #INFO section
value = line.split(':')[0]
if value in self.DIFFICULTIES:
difficulty = value
self.charts[style][difficulty] = {}
elif value in self.FOOT_RATINGS:
self.charts[style][difficulty]['foot rating'] = value
elif ',' in value:
self.charts[style][difficulty]['?'] = value
elif all((c in self.STEP_TYPES for c in line)) and line != '':
# parse individual measures
if parsing_measure:
measure['steps'].append(line)
else:
measure = {'measure': measure_counter, 'steps': [line]}
parsing_measure = True
self.charts[style][difficulty]['chart'] = self.charts[style][
difficulty].setdefault('chart', [])
elif line.startswith(',') and parsing_measure:
# stop parsing measure
self.charts[style][difficulty]['chart'].append(measure)
parsing_measure = False
measure_counter += 1
elif line.startswith(';') and parsing:
# stop parsing section
parsing, parsing_measure = False, False
measure_counter = 1
def varsplit(ref, alts, info, frmt, gts):
"""
Split a variant with multiple alternate alleles into separate records to aid
in annotation.
>>> n = varsplit('TA', ['TAA', 'TAAA', 'T'], 'AF=0.2,0.3,0.1;KKKK',
... 'GT:DP:PL', ['1/2:81:281,5,9,58,0,115,338,46,116,809',
... '0/0:86:0,30,323,31,365,483,38,291,325,567'])
>>> next(n)
('TA', 'TAA', 'KKKK;ORIG_ALLELES=TA/TAA,TAAA,T;ORIG_ALLELE_i=1', 'GT:PL', ['1/.:281,5,9', '0/0:0,30,323'])
>>> next(n)
('TA', 'TAAA', 'KKKK;ORIG_ALLELES=TA/TAA,TAAA,T;ORIG_ALLELE_i=2', 'GT:PL', ['./1:281,58,115', '0/0:0,31,483'])
>>> next(n)
('TA', 'T', 'KKKK;ORIG_ALLELES=TA/TAA,TAAA,T;ORIG_ALLELE_i=3', 'GT:PL', ['./.:281,338,809', '0/0:0,38,567'])
# test new snp eff ANN= field
>>> n = varsplit('G', ['A', 'C', 'T'],
... 'ANN=A|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.|||||||',
... 'GT:DP:PL', ['1/2:81:281,5,9,58,0,115,338,46,116,809'])
>>> next(n)
('G', 'A', 'ANN=A|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||,A|.|.|.|.|.|.|.|.|.||||||;ORIG_ALLELES=G/A,C,T;ORIG_ALLELE_i=1', 'GT:PL', ['1/.:281,5,9'])
>>> next(n)
('G', 'C', 'ANN=C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||,C|.|.|.|.|.|.|.|.|.||||||;ORIG_ALLELES=G/A,C,T;ORIG_ALLELE_i=2', 'GT:PL', ['./1:281,58,115'])
>>> next(n)
('G', 'T', 'ANN=T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.||||||,T|.|.|.|.|.|.|.|.|.|||||||;ORIG_ALLELES=G/A,C,T;ORIG_ALLELE_i=3', 'GT:PL', ['./.:281,338,809'])
>>> next(n)
Traceback (most recent call last):
...
StopIteration
# test older snpeff EFF= field
>>> n = varsplit('TTCC', ['T', 'TTCCTCC'], 'EFF=CODON_CHANGE_PLUS_CODON_DELETION(MODERATE||gaggaa/gaa|EE28E|196|MICAL3|protein_coding|CODING|ENST00000498573|1|1|WARNING_TRANSCRIPT_NO_START_CODON),CODON_CHANGE_PLUS_CODON_DELETION(MODERATE||gaggaa/gaa|EE4E|188|MICAL3|protein_coding|CODING|ENST00000578984|1|1|WARNING_TRANSCRIPT_INCOMPLETE),CODON_CHANGE_PLUS_CODON_DELETION(MODERATE||gaggaa/gaa|EE998E|2002|MICAL3|protein_coding|CODING|ENST00000441493|21|1),CODON_INSERTION(MODERATE||gag/gaGGAg|E28EE|196|MICAL3|protein_coding|CODING|ENST00000498573|1|2|WARNING_TRANSCRIPT_NO_START_CODON),CODON_INSERTION(MODERATE||gag/gaGGAg|E4EE|188|MICAL3|protein_coding|CODING|ENST00000578984|1|2|WARNING_TRANSCRIPT_INCOMPLETE),CODON_INSERTION(MODERATE||gag/gaGGAg|E998EE|2002|MICAL3|protein_coding|CODING|ENST00000441493|21|2),DOWNSTREAM(MODIFIER||2412||966|MICAL3|protein_coding|CODING|ENST00000400561||2),DOWNSTREAM(MODIFIER||2415||966|MICAL3|protein_coding|CODING|ENST00000400561||1),DOWNSTREAM(MODIFIER||2422||966|MICAL3|protein_coding|CODING|ENST00000444520||2),DOWNSTREAM(MODIFIER||2425||966|MICAL3|protein_coding|CODING|ENST00000444520||1)', 'GT:DP:PL', ['1/2:81:281,5,9,58,0,115,338'])
>>> next(n)
('TTCC', 'T', 'EFF=CODON_CHANGE_PLUS_CODON_DELETION(MODERATE||gaggaa/gaa|EE28E|196|MICAL3|protein_coding|CODING|ENST00000498573|1|1|WARNING_TRANSCRIPT_NO_START_CODON),CODON_CHANGE_PLUS_CODON_DELETION(MODERATE||gaggaa/gaa|EE4E|188|MICAL3|protein_coding|CODING|ENST00000578984|1|1|WARNING_TRANSCRIPT_INCOMPLETE),CODON_CHANGE_PLUS_CODON_DELETION(MODERATE||gaggaa/gaa|EE998E|2002|MICAL3|protein_coding|CODING|ENST00000441493|21|1),DOWNSTREAM(MODIFIER||2415||966|MICAL3|protein_coding|CODING|ENST00000400561||1),DOWNSTREAM(MODIFIER||2425||966|MICAL3|protein_coding|CODING|ENST00000444520||1);ORIG_ALLELES=TTCC/T,TTCCTCC;ORIG_ALLELE_i=1', 'GT:PL', ['1/.:281,5,9'])
>>> next(n)
('TTCC', 'TTCCTCC', 'EFF=CODON_INSERTION(MODERATE||gag/gaGGAg|E28EE|196|MICAL3|protein_coding|CODING|ENST00000498573|1|2|WARNING_TRANSCRIPT_NO_START_CODON),CODON_INSERTION(MODERATE||gag/gaGGAg|E4EE|188|MICAL3|protein_coding|CODING|ENST00000578984|1|2|WARNING_TRANSCRIPT_INCOMPLETE),CODON_INSERTION(MODERATE||gag/gaGGAg|E998EE|2002|MICAL3|protein_coding|CODING|ENST00000441493|21|2),DOWNSTREAM(MODIFIER||2412||966|MICAL3|protein_coding|CODING|ENST00000400561||2),DOWNSTREAM(MODIFIER||2422||966|MICAL3|protein_coding|CODING|ENST00000444520||2);ORIG_ALLELES=TTCC/T,TTCCTCC;ORIG_ALLELE_i=2', 'GT:PL', ['./1:281,58,115'])
>>> next(n)
Traceback (most recent call last):
...
StopIteration
"""
if len(alts) == 1:
yield ref, alts[0], infostr(info, ()), frmt, gts
raise StopIteration
if not isinstance(info, dict):
info = OrderedDict((kv[0], (kv[1] if len(kv) > 1 else None))
for kv in (x.split('=') for x in info.split(';')))
fmts = frmt.split(':')
gts = [OrderedDict(zip(fmts, x.split(':'))) for x in gts]
for i, g in enumerate(gts):
if 'GT' in g:
gts[i]['__sep'] = "|" if "|" in g['GT'] else "/"
gts[i]['GT'] = g['GT'].split(gts[i]['__sep'])
for i, alt in enumerate(alts, start=1):
if any('GT' in g for g in gts):
fixed_genos = fix_genos(gts, i)
else:
fixed_genos = gts
if fixed_genos:
fields = [f for f in fixed_genos[0].keys()
if f != "__sep"] # ordered
else:
fields = []
info_sub = fix_info(info, alt, alts)
# now we temporarily replace info[field] with ann
info_sub['ORIG_ALLELES'] = '%s/%s' % (ref, ",".join(alts))
info_sub['ORIG_ALLELE_i'] = str(i)
ret = ref, alt, infostr(info_sub), ":".join(fields), fmt_genos(
fixed_genos)
yield ret
def balance_stoichiometry(reactants, products, substances=None,
substance_factory=Substance.from_formula,
parametric_symbols=None, underdetermined=True, allow_duplicates=False):
""" Balances stoichiometric coefficients of a reaction
Parameters
----------
reactants : iterable of reactant keys
products : iterable of product keys
substances : OrderedDict or string or None
Mapping reactant/product keys to instances of :class:`Substance`.
substance_factory : callback
parametric_symbols : generator of symbols
Used to generate symbols for parametric solution for
under-determined system of equations. Default is numbered "x-symbols" starting
from 1.
underdetermined : bool
Allows to find a non-unique solution (in addition to a constant factor
across all terms). Set to ``False`` to disallow (raise ValueError) on
e.g. "C + O2 -> CO + CO2". Set to ``None`` if you want the symbols replaced
so that the coefficients are the smallest possible positive (non-zero) integers.
allow_duplicates : bool
If False: raises an excpetion if keys appear in both ``reactants`` and ``products``.
Examples
--------
>>> ref = {'C2H2': 2, 'O2': 3}, {'CO': 4, 'H2O': 2}
>>> balance_stoichiometry({'C2H2', 'O2'}, {'CO', 'H2O'}) == ref
True
>>> ref2 = {'H2': 1, 'O2': 1}, {'H2O2': 1}
>>> balance_stoichiometry('H2 O2'.split(), ['H2O2'], 'H2 O2 H2O2') == ref2
True
>>> reac, prod = 'CuSCN KIO3 HCl'.split(), 'CuSO4 KCl HCN ICl H2O'.split()
>>> Reaction(*balance_stoichiometry(reac, prod)).string()
'4 CuSCN + 7 KIO3 + 14 HCl -> 4 CuSO4 + 7 KCl + 4 HCN + 7 ICl + 5 H2O'
>>> balance_stoichiometry({'Fe', 'O2'}, {'FeO', 'Fe2O3'}, underdetermined=False)
Traceback (most recent call last):
...
ValueError: The system was under-determined
>>> r, p = balance_stoichiometry({'Fe', 'O2'}, {'FeO', 'Fe2O3'})
>>> list(set.union(*[v.free_symbols for v in r.values()]))
[x1]
>>> b = balance_stoichiometry({'Fe', 'O2'}, {'FeO', 'Fe2O3'}, underdetermined=None)
>>> b == ({'Fe': 3, 'O2': 2}, {'FeO': 1, 'Fe2O3': 1})
True
>>> d = balance_stoichiometry({'C', 'CO'}, {'C', 'CO', 'CO2'}, underdetermined=None, allow_duplicates=True)
>>> d == ({'CO': 2}, {'C': 1, 'CO2': 1})
True
Returns
-------
balanced reactants : dict
balanced products : dict
"""
import sympy
from sympy import (
MutableDenseMatrix, gcd, zeros, linsolve, numbered_symbols, Wild, Symbol,
Integer, Tuple, preorder_traversal as pre
)
_intersect = sorted(set.intersection(*map(set, (reactants, products))))
if _intersect:
if allow_duplicates:
if underdetermined is not None:
raise NotImplementedError("allow_duplicates currently requires underdetermined=None")
if set(reactants) == set(products):
raise ValueError("cannot balance: reactants and products identical")
# For each duplicate, try to drop it completely:
for dupl in _intersect:
try:
result = balance_stoichiometry(
[sp for sp in reactants if sp != dupl],
[sp for sp in products if sp != dupl],
substances=substances, substance_factory=substance_factory,
underdetermined=underdetermined, allow_duplicates=True)
except Exception:
continue
else:
return result
for perm in product(*[(False, True)]*len(_intersect)): # brute force (naive)
r = set(reactants)
p = set(products)
for remove_reac, dupl in zip(perm, _intersect):
if remove_reac:
r.remove(dupl)
else:
p.remove(dupl)
try:
result = balance_stoichiometry(
r, p, substances=substances, substance_factory=substance_factory,
parametric_symbols=parametric_symbols, underdetermined=underdetermined,
allow_duplicates=False)
except Exception:
continue
else:
return result
else:
raise ValueError("Failed to remove duplicate keys: %s" % _intersect)
else:
raise ValueError("Substances on both sides: %s" % str(_intersect))
if substances is None:
substances = OrderedDict([(k, substance_factory(k)) for k in chain(reactants, products)])
if isinstance(substances, str):
substances = OrderedDict([(k, substance_factory(k)) for k in substances.split()])
if type(reactants) == set: # we don't want isinstance since it might be "OrderedSet"
reactants = sorted(reactants)
if type(products) == set:
products = sorted(products)
subst_keys = list(reactants) + list(products)
cks = Substance.composition_keys(substances.values())
if parametric_symbols is None:
parametric_symbols = numbered_symbols('x', start=1, integer=True, positive=True)
# ?C2H2 + ?O2 -> ?CO + ?H2O
# Ax = 0
# A: x:
#
# C2H2 O2 CO H2O
# C -2 0 1 0 x0 = 0
# H -2 0 0 2 x1 0
# O 0 -2 1 1 x2 0
# x3
def _get(ck, sk):
return substances[sk].composition.get(ck, 0) * (-1 if sk in reactants else 1)
for ck in cks: # check that all components are present on reactant & product sides
for rk in reactants:
if substances[rk].composition.get(ck, 0) != 0:
break
else:
raise ValueError("Component '%s' not among reactants" % ck)
for pk in products:
if substances[pk].composition.get(ck, 0) != 0:
break
else:
raise ValueError("Component '%s' not among products" % ck)
A = MutableDenseMatrix([[_get(ck, sk) for sk in subst_keys] for ck in cks])
symbs = list(reversed([next(parametric_symbols) for _ in range(len(subst_keys))]))
sol, = linsolve((A, zeros(len(cks), 1)), symbs)
wi = Wild('wi', properties=[lambda k: not k.has(Symbol)])
cd = reduce(gcd, [1] + [1/m[wi] for m in map(
lambda n: n.match(symbs[-1]/wi), pre(sol)) if m is not None])
sol = sol.func(*[arg/cd for arg in sol.args])
def remove(cont, symb, remaining):
subsd = dict(zip(remaining/symb, remaining))
cont = cont.func(*[(arg/symb).expand().subs(subsd) for arg in cont.args])
if cont.has(symb):
raise ValueError("Bug, please report an issue at https://github.com/bjodah/chempy")
return cont
done = False
for idx, symb in enumerate(symbs):
for expr in sol:
iterable = expr.args if expr.is_Add else [expr]
for term in iterable:
if term.is_number:
done = True
break
if done:
break
if done:
break
for expr in sol:
if (expr/symb).is_number:
sol = remove(sol, symb, MutableDenseMatrix(symbs[idx+1:]))
break
for symb in symbs:
cd = 1
for expr in sol:
iterable = expr.args if expr.is_Add else [expr]
for term in iterable:
if term.is_Mul and term.args[0].is_number and term.args[1] == symb:
cd = gcd(cd, term.args[0])
if cd != 1:
sol = sol.func(*[arg.subs(symb, symb/cd) for arg in sol.args])
if underdetermined is 1:
from ._release import __version__
if int(__version__.split('.')[1]) > 6:
warnings.warn( # deprecated because comparison with ``1`` problematic (True==1)
("Pass underdetermined == None instead of ``1`` (depreacted since 0.7.0,"
" will_be_missing_in='0.9.0')"), ChemPyDeprecationWarning)
underdetermined = None
if underdetermined is None:
sol = Tuple(*[Integer(x) for x in _solve_balancing_ilp_pulp(A)])
fact = gcd(sol)
sol = MutableDenseMatrix([e/fact for e in sol]).reshape(len(sol), 1)
sol /= reduce(gcd, sol)
if 0 in sol:
raise ValueError("Superfluous species given.")
if underdetermined:
if any(x == sympy.nan for x in sol):
raise ValueError("Failed to balance reaction")
else:
for x in sol:
if len(x.free_symbols) != 0:
raise ValueError("The system was under-determined")
if not all(residual == 0 for residual in A * sol):
raise ValueError("Failed to balance reaction")
def _x(k):
coeff = sol[subst_keys.index(k)]
return int(coeff) if underdetermined is None else coeff
return (
OrderedDict([(k, _x(k)) for k in reactants]),
OrderedDict([(k, _x(k)) for k in products])
)
def read(filename):
"""Create a |Geoset| instance from a DS9 region file.
.. note:: This will break if the region file was not written using
`write`!
Parameters
----------
filename : str
Path to the DS9 region file to be loaded.
Returns
-------
out : |Geoset|
A |Geoset| instance build using the polygons stored in the DS9 region
file.
"""
def parse_ds9_attrs(attrstr, global_attrs=False):
attrstr = attrstr + ' junk'
if not global_attrs:
attrstr = 'junk ' + attrstr
j = [0] + [i for i in range(len(attrstr)) if attrstr[i] == '='] + [-1]
keys, vals = [], []
for j1, j2 in zip(j[:-1], j[1:]):
val, key = attrstr[j1+1:j2].rsplit(' ', 1)
if ((val[0], val[-1]) == ('"', '"') or
(val[0], val[-1]) == ('{', '}')):
val = val[1:-1]
keys.append(key)
vals.append(val)
return zip(keys[:-1], vals[1:])
with open(filename, 'r') as file:
lines = file.readlines()
geoset = _geoset.Geoset(None)
i0, j0, k0 = None, None, None
for line in lines:
line = line.split('\n')[0]
# Skip comments and blank lines:
if line.startswith('#') or not line:
continue
# Parse global attributes:
elif line.startswith('global'):
attrs = parse_ds9_attrs(line, global_attrs=True)
attrs = OrderedDict(attrs)
geoset.attrs = attrs
# Parse coordinate system:
elif line in ['physical', 'fk5']:
if geoset.attrs is None:
geoset.attrs = OrderedDict()
geoset.attrs['coordsys'] = line
# Build geoset:
elif line.startswith('polygon'):
coords, delim, attrs = line.partition('(')[-1].partition(')')
coords, attrs = coords.replace(',', ' '), attrs.split('#')[-1]
# Make polygon
xy = [float(i) for i in coords.split()]
x, y = xy[0::2], xy[1::2]
poly = geometry.Polygon(zip(x, y))
# Test if polygon is a hole:
is_hole = False
if 'background' in attrs:
is_hole = True
attrs = attrs.split('background')[-1]
# Get item/geo/poly structure indices:
idx_list = parse_ds9_attrs(attrs)
for idx in idx_list:
tag, n = idx[1].split()
n = int(n)
if tag == 'item':
i = n
elif tag == 'geo':
j = n
elif tag == 'poly':
k = n
if i != i0:
geo = _geoset.Geo(poly)
item = _geoset.Item(geo)
geoset.items.append(item)
elif j != j0:
geo = _geoset.Geo(poly)
item.geos.append(geo)
elif k != k0:
geo.geo = geo.geo.union(poly)
elif is_hole:
geo.geo = geo.geo.difference(poly)
i0, j0, k0 = i, j, k
return geoset
