square brackets support
DonHalkon opened this issue · 2 comments
DonHalkon commented
I tried to parse "[Fe(CN)6]-4" and got ParseException:
In [2]: import chempy.util.parsing as chem
In [3]: comp = chem.formula_to_composition("[Fe(CN)6]-4")
---------------------------------------------------------------------------
ParseException Traceback (most recent call last)
<ipython-input-3-da99372ece8d> in <module>()
----> 1 comp = chem.formula_to_composition("[Fe(CN)6]-4")
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/chempy/util/parsing.py in formula_to_composition(formula, prefixes, suffixes)
247 else:
248 m, stoich = _get_leading_integer(stoich)
--> 249 comp = _parse_stoich(stoich)
250 for k, v in comp.items():
251 if k not in tot_comp:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/chempy/util/parsing.py in _parse_stoich(stoich)
175 return {}
176 return {symbols.index(k)+1: n for k, n
--> 177 in _get_formula_parser().parseString(stoich)}
178
179 _greek_letters = (
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseString(self, instring, parseAll)
1630 else:
1631 # catch and re-raise exception from here, clears out pyparsing internal stack trace
-> 1632 raise exc
1633 else:
1634 return tokens
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseString(self, instring, parseAll)
1620 instring = instring.expandtabs()
1621 try:
-> 1622 loc, tokens = self._parse( instring, 0 )
1623 if parseAll:
1624 loc = self.preParse( instring, loc )
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in _parseNoCache(self, instring, loc, doActions, callPreParse)
1377 if self.mayIndexError or loc >= len(instring):
1378 try:
-> 1379 loc,tokens = self.parseImpl( instring, preloc, doActions )
1380 except IndexError:
1381 raise ParseException( instring, len(instring), self.errmsg, self )
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseImpl(self, instring, loc, doActions)
3715 def parseImpl( self, instring, loc, doActions=True ):
3716 if self.expr is not None:
-> 3717 return self.expr._parse( instring, loc, doActions, callPreParse=False )
3718 else:
3719 raise ParseException("",loc,self.errmsg,self)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in _parseNoCache(self, instring, loc, doActions, callPreParse)
1377 if self.mayIndexError or loc >= len(instring):
1378 try:
-> 1379 loc,tokens = self.parseImpl( instring, preloc, doActions )
1380 except IndexError:
1381 raise ParseException( instring, len(instring), self.errmsg, self )
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseImpl(self, instring, loc, doActions)
3846 if check_ender:
3847 try_not_ender(instring, loc)
-> 3848 loc, tokens = self_expr_parse( instring, loc, doActions, callPreParse=False )
3849 try:
3850 hasIgnoreExprs = (not not self.ignoreExprs)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in _parseNoCache(self, instring, loc, doActions, callPreParse)
1377 if self.mayIndexError or loc >= len(instring):
1378 try:
-> 1379 loc,tokens = self.parseImpl( instring, preloc, doActions )
1380 except IndexError:
1381 raise ParseException( instring, len(instring), self.errmsg, self )
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseImpl(self, instring, loc, doActions)
3715 def parseImpl( self, instring, loc, doActions=True ):
3716 if self.expr is not None:
-> 3717 return self.expr._parse( instring, loc, doActions, callPreParse=False )
3718 else:
3719 raise ParseException("",loc,self.errmsg,self)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in _parseNoCache(self, instring, loc, doActions, callPreParse)
1377 if self.mayIndexError or loc >= len(instring):
1378 try:
-> 1379 loc,tokens = self.parseImpl( instring, preloc, doActions )
1380 except IndexError:
1381 raise ParseException( instring, len(instring), self.errmsg, self )
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseImpl(self, instring, loc, doActions)
3376 # pass False as last arg to _parse for first element, since we already
3377 # pre-parsed the string as part of our And pre-parsing
-> 3378 loc, resultlist = self.exprs[0]._parse( instring, loc, doActions, callPreParse=False )
3379 errorStop = False
3380 for e in self.exprs[1:]:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in _parseNoCache(self, instring, loc, doActions, callPreParse)
1377 if self.mayIndexError or loc >= len(instring):
1378 try:
-> 1379 loc,tokens = self.parseImpl( instring, preloc, doActions )
1380 except IndexError:
1381 raise ParseException( instring, len(instring), self.errmsg, self )
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseImpl(self, instring, loc, doActions)
3543 if maxException is not None:
3544 maxException.msg = self.errmsg
-> 3545 raise maxException
3546 else:
3547 raise ParseException(instring, loc, "no defined alternatives to match", self)
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseImpl(self, instring, loc, doActions)
3528 for e in self.exprs:
3529 try:
-> 3530 ret = e._parse( instring, loc, doActions )
3531 return ret
3532 except ParseException as err:
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in _parseNoCache(self, instring, loc, doActions, callPreParse)
1381 raise ParseException( instring, len(instring), self.errmsg, self )
1382 else:
-> 1383 loc,tokens = self.parseImpl( instring, preloc, doActions )
1384
1385 tokens = self.postParse( instring, loc, tokens )
/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/pyparsing.py in parseImpl(self, instring, loc, doActions)
2792 result = self.re.match(instring,loc)
2793 if not result:
-> 2794 raise ParseException(instring, loc, self.errmsg, self)
2795
2796 loc = result.end()
ParseException: Expected {Re:('A[cglmrstu]|B[aehikr]?|C[adeflmorsu]?|D[bsy]|E[rsu]|F[emr]?|G[ade]|H[efgos]?|I[nr]?|Kr?|L[airu]|M[dgnot]|N[abdeiop]?|Os?|P[abdmortu]?|R[abefghnu]|S[bcegimnr]?|T[abcehilm]|Uu[bhopqst]|U|V|W|Xe|Yb?|Z[nr]') | Group:({Suppress:("(") Forward: ... Suppress:(")")})} (at char 0), (line:1, col:1)The problem is in square brackets I guess, without them parsing works well:
In [5]: chem.formula_to_composition("Fe(CN)6-4")
Out[5]: {26: 1, 6: 6, 7: 6, 0: -4}bjodah commented
Yes, the parser has not been written to account for square brackets.
If they don't add any information you could write your own "pre-processor" which just removes them:
lambda s: s.replace('[', '').replace(']', '')
(or replaces them with ordinary parenthesis).
DonHalkon commented
Thank you!