rulesParser.py
4.22 KB
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
from pyparsing import *
ParserElement.enablePackrat()
from morfeuszbuilder.tagset import segtypes
from morfeuszbuilder.utils import configFile, exceptions
from morfeuszbuilder.segrules import preprocessor, rules, rulesManager
import codecs
import re
import itertools
import logging
from morfeuszbuilder.segrules import rulesNFA
class RulesParser(object):
def __init__(self, tagset):
self.tagset = tagset
def _getKey2Defs(self, segtypesConfigFile):
res = {}
for lineNum, line in segtypesConfigFile.enumerateLinesInSection('options'):
lineToParse = Word(alphanums+'_') + Suppress('=') + Group(OneOrMore(Word(alphanums+'_'))) + LineEnd().suppress()
try:
key, defs = lineToParse.parseString(line)
res[key] = tuple(defs)
except Exception as ex:
raise exceptions.ConfigFileException(segtypesConfigFile.filename, lineNum, u'Error in [options] section: %s' % str(ex))
return res
def parse(self, filename):
segtypesConfigFile = configFile.ConfigFile(filename, ['options', 'combinations', 'tags', 'lexemes', 'segment types'])
key2Defs = self._getKey2Defs(segtypesConfigFile)
segtypesHelper = segtypes.Segtypes(self.tagset, segtypesConfigFile)
res = rulesManager.RulesManager(segtypesHelper)
def2Key = {}
for key, defs in key2Defs.iteritems():
for define in defs:
def2Key[define] = key
firstNFA = None
for defs in itertools.product(*key2Defs.values()):
key2Def = dict([(def2Key[define], define) for define in defs])
nfa = rulesNFA.RulesNFA()
if not firstNFA:
firstNFA = nfa
combinationEnumeratedLines = segtypesConfigFile.enumerateLinesInSection('combinations')
combinationEnumeratedLines = list(preprocessor.preprocess(combinationEnumeratedLines, defs))
for rule in self._doParse(combinationEnumeratedLines, segtypesHelper):
rule.addToNFA(nfa)
dfa = nfa.convertToDFA()
# print dfa.tryToRecognize(bytearray([14]))
res.addDFA(key2Def, dfa)
return res
def _doParse(self, combinationEnumeratedLines, segtypesHelper):
for lineNum, line in combinationEnumeratedLines:
if not line.startswith('#'):
yield self._doParseOneLine(lineNum, line, segtypesHelper)
def _createNewTagRule(self, segtype, lineNum, line, segtypesHelper):
if not segtypesHelper.hasSegtype(segtype):
raise exceptions.ConfigFileException(segtypesHelper.filename, lineNum, u'%s - invalid segment type: %s' % (line, segtype))
else:
# return rules.TagRule(segtype)
return rules.TagRule(segtypesHelper.getSegnum4Segtype(segtype))
def _doParseOneLine(self, lineNum, line, segtypesHelper):
rule = Forward()
tagRule = Word(alphanums+'_')
shiftOrthRule = tagRule + '>'
parenRule = Suppress('(') + rule + Suppress(')')
atomicRule = tagRule ^ shiftOrthRule ^ parenRule
zeroOrMoreRule = atomicRule + Suppress('*')
oneOrMoreRule = atomicRule + Suppress('+')
unaryRule = atomicRule ^ zeroOrMoreRule ^ oneOrMoreRule
oneOfRule = delimitedList(unaryRule, delim='|')
complexRule = unaryRule ^ oneOfRule
concatRule = OneOrMore(complexRule)
rule << concatRule
tagRule.setParseAction(lambda string, loc, toks: self._createNewTagRule(toks[0], lineNum, line, segtypesHelper))
shiftOrthRule.setParseAction(lambda string, loc, toks: rules.ShiftOrthRule(toks[0]))
# parenRule.setParseAction(lambda string, loc, toks: toks[0])
zeroOrMoreRule.setParseAction(lambda string, loc, toks: rules.ZeroOrMoreRule(toks[0]))
oneOrMoreRule.setParseAction(lambda string, loc, toks: rules.ConcatRule([toks[0], rules.ZeroOrMoreRule(toks[0])]))
oneOfRule.setParseAction(lambda string, loc, toks: rules.OrRule(toks))
concatRule.setParseAction(lambda string, loc, toks: toks[0] if len(toks) == 1 else rules.ConcatRule(toks))
parsedRule = rule.parseString(line, parseAll=True)[0]
return parsedRule