# An alternative specification for the Cif Parser, based on Yapps2 # by Amit Patel (http://theory.stanford.edu/~amitp/Yapps) # # helper code: we define our match tokens lastval = '' def monitor(location,value): global lastval #print 'At %s: %s' % (location,`value`) lastval = `value` return value def stripextras(value): # we get rid of semicolons and leading/trailing terminators etc. import re jj = re.compile("[\n\r\f \t\v]*") semis = re.compile("[\n\r\f \t\v]*[\n\r\f]\n*;") cut = semis.match(value) if cut: nv = value[cut.end():len(value)-2] if nv[-1]=='\r': nv = nv[:-1] else: nv = value cut = jj.match(nv) if cut: return stripstring(nv[cut.end():]) return nv # helper function to get rid of inverted commas etc. def stripstring(value): if value: if value[0]== '\'' and value[-1]=='\'': return value[1:-1] if value[0]=='"' and value[-1]=='"': return value[1:-1] return value # helper function to create a dictionary given a set of # looped datanames and data values def makeloop(namelist,itemlist,context): noitems = len(namelist) nopoints = divmod(len(itemlist),noitems) if nopoints[1]!=0: #mismatch raise "CifError:loop item mismatch" nopoints = nopoints[0] newdict = {} for i in range(0,noitems): templist = [] for j in range(0,nopoints): templist.append(itemlist[j*noitems + i]) newdict.update({namelist[i]:templist}) context.append(newdict) #print 'Contructed loop with items: '+`newdict` return {} # to keep things easy # from string import * import re from yappsrt import * class CifParserScanner(Scanner): patterns = [ ('([ \t\n\r](?!;))|[ \t]', re.compile('([ \t\n\r](?!;))|[ \t]')), ('#.*[\n\r](?!;)', re.compile('#.*[\n\r](?!;)')), ('#.*', re.compile('#.*')), ('LBLOCK', re.compile('(L|l)(O|o)(O|o)(P|p)_')), ('save_heading', re.compile('(S|s)(A|a)(V|v)(E|e)_[][!%&\\(\\)*+,./:<=>?@0-9A-Za-z\\\\^`{}\\|~"#$\';_-]+')), ('save_end', re.compile('(S|s)(A|a)(V|v)(E|e)_')), ('RESERVED', re.compile('((G|g)(L|l)(O|o)(B|b)(A|a)(L|l)_)|((S|s)(T|t)(O|o)(P|p)_)')), ('data_name', re.compile('_[][!%&\\(\\)*+,./:<=>?@0-9A-Za-z\\\\^`{}\\|~"#$\';_-]+')), ('data_heading', re.compile('(D|d)(A|a)(T|t)(A|a)_[][!%&\\(\\)*+,./:<=>?@0-9A-Za-z\\\\^`{}\\|~"#$\';_-]+')), ('start_sc_line', re.compile('(\n|\r\n);([^\n\r])*(\r\n|\r|\n)+')), ('sc_line_of_text', re.compile('[^;\r\n]([^\r\n])*(\r\n|\r|\n)+')), ('end_sc_line', re.compile(';')), ('data_value_1', re.compile('((?!(((S|s)(A|a)(V|v)(E|e)_[^\\s]*)|((G|g)(L|l)(O|o)(B|b)(A|a)(L|l)_[^\\s]*)|((S|s)(T|t)(O|o)(P|p)_[^\\s]*)|((D|d)(A|a)(T|t)(A|a)_[^\\s]*)))[^\\s"#$\'_\\[\\]][^\\s]*)|\'((\'(?=\\S))|([^\n\r\x0c\']))*\'+|"(("(?=\\S))|([^\n\r"]))*"+')), ('END', re.compile('$')), ] def __init__(self, str): Scanner.__init__(self,None,['([ \t\n\r](?!;))|[ \t]', '#.*[\n\r](?!;)', '#.*'],str) class CifParser(Parser): def input(self): _token_ = self._peek('END', 'data_heading') if _token_ == 'data_heading': dblock = self.dblock() maindict = dblock while self._peek('END', 'data_heading') == 'data_heading': dblock = self.dblock() maindict.update(monitor('input',dblock)) END = self._scan('END') else: # == 'END' END = self._scan('END') maindict = {} return maindict def dblock(self): data_heading = self._scan('data_heading') dict={data_heading[5:]:{"loops":[]} } while self._peek('save_heading', 'LBLOCK', 'data_name', 'END', 'data_heading') not in ['END', 'data_heading']: _token_ = self._peek('save_heading', 'LBLOCK', 'data_name') if _token_ != 'save_heading': dataseq = self.dataseq(dict[data_heading[5:]]["loops"]) dict[data_heading[5:]].update(dataseq) else: # == 'save_heading' save_frame = self.save_frame() return monitor('dblock',dict) def dataseq(self, loop_array): data = self.data(loop_array) datadict=data while self._peek('LBLOCK', 'data_name', 'save_heading', 'END', 'data_heading') in ['LBLOCK', 'data_name']: data = self.data(loop_array) datadict.update(data) return monitor('dataseq',datadict) def data(self, loop_array): _token_ = self._peek('LBLOCK', 'data_name') if _token_ == 'LBLOCK': data_loop = self.data_loop(loop_array) return data_loop else: # == 'data_name' datakvpair = self.datakvpair() return datakvpair def datakvpair(self): data_name = self._scan('data_name') data_value = self.data_value() return {data_name:data_value} def data_value(self): _token_ = self._peek('data_value_1', 'start_sc_line') if _token_ == 'data_value_1': data_value_1 = self._scan('data_value_1') thisval = stripstring(data_value_1) else: # == 'start_sc_line' sc_lines_of_text = self.sc_lines_of_text() thisval = stripextras(sc_lines_of_text) return monitor('data_value',thisval) def sc_lines_of_text(self): start_sc_line = self._scan('start_sc_line') lines = start_sc_line while self._peek('sc_line_of_text', 'end_sc_line') == 'sc_line_of_text': sc_line_of_text = self._scan('sc_line_of_text') lines = lines+sc_line_of_text end_sc_line = self._scan('end_sc_line') return monitor('sc_line_of_text',lines+end_sc_line) def data_loop(self, loop_array): LBLOCK = self._scan('LBLOCK') loopfield = self.loopfield() loopvalues = self.loopvalues() return makeloop(loopfield,loopvalues,loop_array) def loopfield(self): data_name = self._scan('data_name') loop=[data_name] while self._peek('data_name', 'data_value_1', 'start_sc_line') == 'data_name': data_name = self._scan('data_name') loop.append(data_name) return loop def loopvalues(self): data_value = self.data_value() loop=[data_value] while self._peek('data_value_1', 'start_sc_line', 'save_end', 'LBLOCK', 'data_name', 'save_heading', 'END', 'data_heading') in ['data_value_1', 'start_sc_line']: data_value = self.data_value() loop.append(monitor('loopval',data_value)) return loop def save_frame(self): save_heading = self._scan('save_heading') while self._peek('save_end', 'LBLOCK', 'data_name', 'save_heading', 'END', 'data_heading') in ['LBLOCK', 'data_name']: data = self.data({"dummydict":0}) save_end = self._scan('save_end') def parse(rule, text): P = CifParser(CifParserScanner(text)) return wrap_error_reporter(P, rule)