Grammalecte  Check-in [a59fbc32a0]

Overview
Comment:[build][core] merge actions in key <rules> + code clarification
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | core | build | rg
Files: files | file ages | folders
SHA3-256: a59fbc32a0cec714cec8e4a4e786ad15f9599497453ea88ca0bbd86413b8affb
User & Date: olr on 2018-05-19 14:06:03
Other Links: branch diff | manifest | tags
Context
2018-05-19
14:28
[build][core] graph rule: condition is moved in action check-in: 5d1e6b3f8b user: olr tags: build, core, rg
14:06
[build][core] merge actions in key <rules> + code clarification check-in: a59fbc32a0 user: olr tags: build, core, rg
2018-05-18
13:11
[graphspell] tokenizer: add token index and avoid punctuations aggregation check-in: be6d99bbdc user: olr tags: graphspell, rg
Changes

Modified compile_rules_graph.py from [61c35162ee] to [9991956fdc].

64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
    for nAction, sAction in enumerate(sActions.split(" <<- ")):
        if sAction.strip():
            sActionId = sRuleName + "_a" + str(nAction)
            sCondition, tAction = createAction(sActionId, sAction, nGroup, nPriority, dPos)
            if tAction:
                dACTIONS[sActionId] = tAction
                lResult = list(lToken)
                lResult.extend([iLine, sRuleName, sCondition, sActionId])
                yield lResult


def createAction (sIdAction, sAction, nGroup, nPriority, dPos):
    m = re.search("([-~=])(\\d+|)(:\\d+|)>> ", sAction)
    if not m:
        print(" # Error. No action found at: ", sIdAction)







|







64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
    for nAction, sAction in enumerate(sActions.split(" <<- ")):
        if sAction.strip():
            sActionId = sRuleName + "_a" + str(nAction)
            sCondition, tAction = createAction(sActionId, sAction, nGroup, nPriority, dPos)
            if tAction:
                dACTIONS[sActionId] = tAction
                lResult = list(lToken)
                lResult.extend(["##"+str(iLine), sRuleName, sCondition, sActionId])
                yield lResult


def createAction (sIdAction, sAction, nGroup, nPriority, dPos):
    m = re.search("([-~=])(\\d+|)(:\\d+|)>> ", sAction)
    if not m:
        print(" # Error. No action found at: ", sIdAction)

Modified datg.py from [7505f580c7] to [c340246af4].

70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
...
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
...
165
166
167
168
169
170
171

172
173
174


175
176
177
178


179
180
181
182
183
        iToken = nCommonPrefix
        for token in aRule[nCommonPrefix:]:
            oNextNode = Node()
            oNode.dArcs[token] = oNextNode
            self.lUncheckedNodes.append((oNode, token, oNextNode))
            if iToken == (len(aRule) - 4): 
                oNode.bFinal = True
                oNextNode.bInfo = True
            iToken += 1
            oNode = oNextNode
        oNode.bFinal = True
        self.aPreviousRule = aRule

    def finish (self):
        "minimize unchecked nodes"
................................................................................
class Node:
    NextId = 0
    
    def __init__ (self):
        self.i = Node.NextId
        Node.NextId += 1
        self.bFinal = False
        self.bInfo = False
        self.dArcs = {}          # key: arc value; value: a node

    @classmethod
    def resetNextId (cls):
        cls.NextId = 0

    def __str__ (self):
        # Caution! this function is used for hashing and comparison!
        cFinal = "1"  if self.bFinal  else "0"
        cInfo = "1"  if self.bInfo  else "0"
        l = [cFinal, cInfo]
        for (key, oNode) in self.dArcs.items():
            l.append(str(key))
            l.append(str(oNode.i))
        return "_".join(l)

    def __hash__ (self):
        # Used as a key in a python dictionary.
................................................................................
        # Nodes are equivalent if they have identical arcs, and each identical arc leads to identical states.
        return self.__str__() == other.__str__()        

    def getNodeAsDict (self):
        "returns the node as a dictionary structure"
        dNode = {}
        dRegex = {}

        for arc, oNode in self.dArcs.items():
            if type(arc) == str and arc.startswith("~"):
                dRegex[arc[1:]] = oNode.__hash__()


            else:
                dNode[arc] = oNode.__hash__()
        if dRegex:
            dNode["<regex>"] = dRegex


        if self.bFinal:
            dNode["<final>"] = 1
        if self.bInfo:
            dNode["<info>"] = 1
        return dNode







<







 







<









<
|







 







>



>
>




>
>
|
|
<
<

70
71
72
73
74
75
76

77
78
79
80
81
82
83
...
134
135
136
137
138
139
140

141
142
143
144
145
146
147
148
149

150
151
152
153
154
155
156
157
...
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182


183
        iToken = nCommonPrefix
        for token in aRule[nCommonPrefix:]:
            oNextNode = Node()
            oNode.dArcs[token] = oNextNode
            self.lUncheckedNodes.append((oNode, token, oNextNode))
            if iToken == (len(aRule) - 4): 
                oNode.bFinal = True

            iToken += 1
            oNode = oNextNode
        oNode.bFinal = True
        self.aPreviousRule = aRule

    def finish (self):
        "minimize unchecked nodes"
................................................................................
class Node:
    NextId = 0
    
    def __init__ (self):
        self.i = Node.NextId
        Node.NextId += 1
        self.bFinal = False

        self.dArcs = {}          # key: arc value; value: a node

    @classmethod
    def resetNextId (cls):
        cls.NextId = 0

    def __str__ (self):
        # Caution! this function is used for hashing and comparison!
        cFinal = "1"  if self.bFinal  else "0"

        l = [cFinal]
        for (key, oNode) in self.dArcs.items():
            l.append(str(key))
            l.append(str(oNode.i))
        return "_".join(l)

    def __hash__ (self):
        # Used as a key in a python dictionary.
................................................................................
        # Nodes are equivalent if they have identical arcs, and each identical arc leads to identical states.
        return self.__str__() == other.__str__()        

    def getNodeAsDict (self):
        "returns the node as a dictionary structure"
        dNode = {}
        dRegex = {}
        dRules = {}
        for arc, oNode in self.dArcs.items():
            if type(arc) == str and arc.startswith("~"):
                dRegex[arc[1:]] = oNode.__hash__()
            elif arc.startswith("##"):
                dRules[arc[1:]] = oNode.__hash__()
            else:
                dNode[arc] = oNode.__hash__()
        if dRegex:
            dNode["<regex>"] = dRegex
        if dRules:
            dNode["<rules>"] = dRules
        #if self.bFinal:
        #    dNode["<final>"] = 1


        return dNode