Grammalecte  Changes On Branch 5d1e6b3f8b0180ed

Changes In Branch rg Through [5d1e6b3f8b] Excluding Merge-Ins

This is equivalent to a diff from f2d8271145 to 5d1e6b3f8b

2018-05-20
10:07
[build][core] graph generation update check-in: 0f6ac8c5a7 user: olr tags: core, build, rg
2018-05-19
14:28
[build][core] graph rule: condition is moved in action check-in: 5d1e6b3f8b user: olr tags: core, build, rg
14:06
[build][core] merge actions in key <rules> + code clarification check-in: a59fbc32a0 user: olr tags: core, build, rg
2018-05-16
16:22
[fr] pt: descente aux enfers/flambeaux check-in: b5310203be user: olr tags: trunk, fr
16:14
[build][core] rules graph: first draft check-in: 061252f41e user: olr tags: core, build, rg
11:58
[graphspell][bug] fix affixes occurrences calculation check-in: f2d8271145 user: olr tags: trunk, graphspell
2018-05-15
12:51
[fr] test contre faux positif check-in: f8bf9c3922 user: olr tags: trunk, fr

Added compile_rules_graph.py version [ecde868c3b].



















































































































































































































































































































































































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
# Create a Direct Acyclic Rule Graph (DARG)

import re
import traceback
import json
import datg


dDEF = {}
dACTIONS = {}
lFUNCTIONS = []


def prepareFunction (s):
    s = s.replace("__also__", "bCondMemo")
    s = s.replace("__else__", "not bCondMemo")
    s = re.sub(r"isStart *\(\)", 'before(["<START>", ","])', s)
    s = re.sub(r"isRealStart *\(\)", 'before(["<START>"])', s)
    s = re.sub(r"isStart0 *\(\)", 'before0(["<START>", ","])', s)
    s = re.sub(r"isRealStart0 *\(\)", 'before0(["<START>"])', s)
    s = re.sub(r"isEnd *\(\)", 'after(["<END>", ","])', s)
    s = re.sub(r"isRealEnd *\(\)", 'after(["<END>"])', s)
    s = re.sub(r"isEnd0 *\(\)", 'after0(["<END>", ","])', s)
    s = re.sub(r"isRealEnd0 *\(\)", 'after0(["<END>"])', s)
    s = re.sub(r"(select|exclude)[(][\\](\d+)", '\\1(lToken[\\2]', s)
    s = re.sub(r"define[(][\\](\d+)", 'define(lToken[\\1]', s)
    s = re.sub(r"(morph|morphex|displayInfo)[(][\\](\d+)", '\\1(lToken[\\2])', s)
    s = re.sub(r"token\(\s*(\d)", 'nextToken(\\1', s)                                       # token(n)
    s = re.sub(r"token\(\s*-(\d)", 'prevToken(\\1', s)                                      # token(-n)
    s = re.sub(r"before\(\s*", 'look(s[:m.start()], ', s)                                   # before(s)
    s = re.sub(r"after\(\s*", 'look(s[m.end():], ', s)                                      # after(s)
    s = re.sub(r"textarea\(\s*", 'look(s, ', s)                                             # textarea(s)
    s = re.sub(r"before_chk1\(\s*", 'look_chk1(dDA, s[:m.start()], 0, ', s)                 # before_chk1(s)
    s = re.sub(r"after_chk1\(\s*", 'look_chk1(dDA, s[m.end():], m.end(), ', s)              # after_chk1(s)
    s = re.sub(r"textarea_chk1\(\s*", 'look_chk1(dDA, s, 0, ', s)                           # textarea_chk1(s)
    s = re.sub(r"isEndOfNG\(\s*\)", 'isEndOfNG(dDA, s[m.end():], m.end())', s)              # isEndOfNG(s)
    s = re.sub(r"isNextNotCOD\(\s*\)", 'isNextNotCOD(dDA, s[m.end():], m.end())', s)        # isNextNotCOD(s)
    s = re.sub(r"isNextVerb\(\s*\)", 'isNextVerb(dDA, s[m.end():], m.end())', s)            # isNextVerb(s)
    s = re.sub(r"\bspell *[(]", '_oSpellChecker.isValid(', s)
    s = re.sub(r"[\\](\d+)", 'lToken[\\1]', s)
    return s


def changeReferenceToken (s, dPos):
    for i in range(len(dPos), 0, -1):
        s = s.replace("\\"+str(i), "\\"+dPos[i])
    return s


def createRule (iLine, sRuleName, sTokenLine, sActions, nPriority):
    # print(iLine, "//", sRuleName, "//", sTokenLine, "//", sActions, "//", nPriority)
    lToken = sTokenLine.split()

    # Calculate positions
    dPos = {}
    nGroup = 0
    for i, sToken in enumerate(lToken):
        if sToken.startswith("(") and sToken.endswith(")"):
            lToken[i] = sToken[1:-1]
            nGroup += 1
            dPos[nGroup] = i

    # Parse actions
    for nAction, sAction in enumerate(sActions.split(" <<- ")):
        if sAction.strip():
            sActionId = sRuleName + "_a" + str(nAction)
            aAction = createAction(sActionId, sAction, nGroup, nPriority, dPos)
            if aAction:
                dACTIONS[sActionId] = aAction
                lResult = list(lToken)
                lResult.extend(["##"+str(iLine), 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)
        print("   ==", sAction, "==")
        return None
    # Condition
    sCondition = sAction[:m.start()].strip()
    if sCondition:
        sCondition = prepareFunction(sCondition)
        sCondition = changeReferenceToken(sCondition, dPos)    
        lFUNCTIONS.append(("gc_"+sIdAction, sCondition))
        sCondition = "gc_"+sIdAction
    else:
        sCondition = ""
    # Action
    cAction = m.group(1)
    sAction = sAction[m.end():].strip()
    sAction = changeReferenceToken(sAction, dPos)
    iStartAction = int(m.group(2))  if m.group(2)  else 0
    iEndAction = int(m.group(3)[1:])  if m.group(3)  else iStartAction
    if nGroup:
        iStartAction = dPos[iStartAction]
        iEndAction = dPos[iEndAction]

    if cAction == "-":
        ## error
        iMsg = sAction.find(" # ")
        if iMsg == -1:
            sMsg = "# Error. Error message not found."
            sURL = ""
            print(sMsg + " Action id: " + sIdAction)
        else:
            sMsg = sAction[iMsg+3:].strip()
            sAction = sAction[:iMsg].strip()
            sURL = ""
            mURL = re.search("[|] *(https?://.*)", sMsg)
            if mURL:
                sURL = mURL.group(1).strip()
                sMsg = sMsg[:mURL.start(0)].strip()
            if sMsg[0:1] == "=":
                sMsg = prepareFunction(sMsg[1:])
                lFUNCTIONS.append(("gm_"+sIdAction, sMsg))
                for x in re.finditer("group[(](\d+)[)]", sMsg):
                    if int(x.group(1)) > nGroup:
                        print("# Error in groups in message at line " + sIdAction + " ("+str(nGroup)+" groups only)")
                sMsg = "=m_"+sIdAction
            else:
                for x in re.finditer(r"\\(\d+)", sMsg):
                    if int(x.group(1)) > nGroup:
                        print("# Error in groups in message at line " + sIdAction + " ("+str(nGroup)+" groups only)")
                if re.search("[.]\\w+[(]", sMsg):
                    print("# Error in message at line " + sIdAction + ":  This message looks like code. Line should begin with =")
            
    if sAction[0:1] == "=" or cAction == "=":
        if "define" in sAction and not re.search(r"define\(\\\d+ *, *\[.*\] *\)", sAction):
            print("# Error in action at line " + sIdAction + ": second argument for define must be a list of strings")
        sAction = prepareFunction(sAction)
        for x in re.finditer("group[(](\d+)[)]", sAction):
            if int(x.group(1)) > nGroup:
                print("# Error in groups in replacement at line " + sIdAction + " ("+str(nGroup)+" groups only)")
    else:
        for x in re.finditer(r"\\(\d+)", sAction):
            if int(x.group(1)) > nGroup:
                print("# Error in groups in replacement at line " + sIdAction + " ("+str(nGroup)+" groups only)")
        if re.search("[.]\\w+[(]|sugg\\w+[(]", sAction):
            print("# Error in action at line " + sIdAction + ":  This action looks like code. Line should begin with =")

    if cAction == "-":
        ## error detected --> suggestion
        if not sAction:
            print("# Error in action at line " + sIdAction + ":  This action is empty.")
        if sAction[0:1] == "=":
            lFUNCTIONS.append(("gs_"+sIdAction, sAction[1:]))
            sAction = "=gs_"+sIdAction
        elif sAction.startswith('"') and sAction.endswith('"'):
            sAction = sAction[1:-1]
        if not sMsg:
            print("# Error in action at line " + sIdAction + ":  The message is empty.")
        return [sCondition, cAction, sAction, iStartAction, iEndAction, nPriority, sMsg, sURL]
    elif cAction == "~":
        ## text processor
        if not sAction:
            print("# Error in action at line " + sIdAction + ":  This action is empty.")
        if sAction[0:1] == "=":
            lFUNCTIONS.append(("gp_"+sIdAction, sAction[1:]))
            sAction = "=gp_"+sIdAction
        elif sAction.startswith('"') and sAction.endswith('"'):
            sAction = sAction[1:-1]
        return [sCondition, cAction, sAction, iStartAction, iEndAction]
    elif cAction == "=":
        ## disambiguator
        if sAction[0:1] == "=":
            sAction = sAction[1:]
        if not sAction:
            print("# Error in action at line " + sIdAction + ":  This action is empty.")
        lFUNCTIONS.append(("gd_"+sIdAction, sAction))
        sAction = "gd_"+sIdAction
        return [sCondition, cAction, sAction]
    elif cAction == ">":
        ## no action, break loop if condition is False
        return [sCondition, cAction, ""]
    else:
        print("# Unknown action at line " + sIdAction)
        return None


def make (spLang, sLang, bJavaScript):
    "compile rules, returns a dictionary of values"
    # for clarity purpose, don’t create any file here

    print("> read graph rules file...")
    try:
        lRules = open(spLang + "/rules_graph.grx", 'r', encoding="utf-8").readlines()
    except:
        print("Error. Rules file in project [" + sLang + "] not found.")
        exit()

    # removing comments, zeroing empty lines, creating definitions, storing tests, merging rule lines
    print("  parsing rules...")
    global dDEF
    lLine = []
    lRuleLine = []
    lTest = []
    lOpt = []
    lTokenLine = []
    sActions = ""
    nPriority = 4

    for i, sLine in enumerate(lRules, 1):
        sLine = sLine.rstrip()
        if "\t" in sLine:
            print("Error. Tabulation at line: ", i)
            break
        if sLine.startswith('#END'):
            printBookmark(0, "BREAK BY #END", i)
            break
        elif sLine.startswith("#"):
            pass
        elif sLine.startswith("DEF:"):
            m = re.match("DEF: +([a-zA-Z_][a-zA-Z_0-9]*) +(.+)$", sLine.strip())
            if m:
                dDEF["{"+m.group(1)+"}"] = m.group(2)
            else:
                print("Error in definition: ", end="")
                print(sLine.strip())
        elif sLine.startswith("TEST:"):
            lTest.append("{:<8}".format(i) + "  " + sLine[5:].strip())
        elif sLine.startswith("TODO:"):
            pass
        elif sLine.startswith("!!"):
            m = re.search("^!!+", sLine)
            nExMk = len(m.group(0))
            if sLine[nExMk:].strip():
                printBookmark(nExMk-2, sLine[nExMk:].strip(), i)
        elif sLine.startswith("__") and sLine.endswith("__"):
            # new rule group
            m = re.match("__(\\w+)(!\\d|)__", sLine)
            if m:
                sRuleName = m.group(1)
                nPriority = int(m.group(2)[1:]) if m.group(2)  else 4
            else:
                print("Error at rule group: ", sLine, " -- line:", i)
                break
        elif re.match("[  ]*$", sLine):
            # empty line to end merging
            for i, sTokenLine in lTokenLine:
                lRuleLine.append((i, sRuleName, sTokenLine, sActions, nPriority))
            lTokenLine = []
            sActions = ""
            sRuleName = ""
            nPriority = 4
        elif sLine.startswith(("        ")):
            # actions
            sActions += " " + sLine.strip()
        else:
            lTokenLine.append([i, sLine.strip()])

    # tests
    print("  list tests...")
    sGCTests = "\n".join(lTest)
    sGCTestsJS = '{ "aData2": ' + json.dumps(lTest, ensure_ascii=False) + " }\n"

    # processing rules
    print("  preparing rules...")
    lPreparedRule = []
    for i, sRuleGroup, sTokenLine, sActions, nPriority in lRuleLine:
        for lRule in createRule(i, sRuleGroup, sTokenLine, sActions, nPriority):
            lPreparedRule.append(lRule)

    # Graph creation
    for e in lPreparedRule:
        print(e)

    oDATG = datg.DATG(lPreparedRule, sLang)
    oRuleGraph = oDATG.createGraph()

    # Result
    d = {
        "g_callables": None,
        "g_gctests": None,
        "graph_rules": None,
    }

    return d


Added datg.py version [c288dbf7f8].















































































































































































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
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
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
#!python3

# RULE GRAPH BUILDER
#
# by Olivier R.
# License: MPL 2


import json
import time
import traceback

from graphspell.progressbar import ProgressBar



class DATG:
    """DIRECT ACYCLIC TOKEN GRAPH"""
    # This code is inspired from Steve Hanov’s DAWG, 2011. (http://stevehanov.ca/blog/index.php?id=115)

    def __init__ (self, lRule, sLangCode):
        print("===== Direct Acyclic Token Graph - Minimal Acyclic Finite State Automaton =====")

        # Preparing DATG
        print(" > Preparing list of tokens")
        self.sLangCode = sLangCode
        self.nRule = len(lRule)
        self.aPreviousRule = []
        Node.resetNextId()
        self.oRoot = Node()
        self.lUncheckedNodes = []  # list of nodes that have not been checked for duplication.
        self.lMinimizedNodes = {}  # list of unique nodes that have been checked for duplication.
        self.nNode = 0
        self.nArc = 0
        
        # build
        lRule.sort()
        oProgBar = ProgressBar(0, len(lRule))
        for aRule in lRule:
            self.insert(aRule)
            oProgBar.increment(1)
        oProgBar.done()
        self.finish()
        self.countNodes()
        self.countArcs()
        self.displayInfo()

    # BUILD DATG
    def insert (self, aRule):
        if aRule < self.aPreviousRule:
            sys.exit("# Error: tokens must be inserted in order.")
    
        # find common prefix between word and previous word
        nCommonPrefix = 0
        for i in range(min(len(aRule), len(self.aPreviousRule))):
            if aRule[i] != self.aPreviousRule[i]:
                break
            nCommonPrefix += 1

        # Check the lUncheckedNodes for redundant nodes, proceeding from last
        # one down to the common prefix size. Then truncate the list at that point.
        self._minimize(nCommonPrefix)

        # add the suffix, starting from the correct node mid-way through the graph
        if len(self.lUncheckedNodes) == 0:
            oNode = self.oRoot
        else:
            oNode = self.lUncheckedNodes[-1][2]

        iToken = nCommonPrefix
        for token in aRule[nCommonPrefix:]:
            oNextNode = Node()
            oNode.dArcs[token] = oNextNode
            self.lUncheckedNodes.append((oNode, token, oNextNode))
            if iToken == (len(aRule) - 2): 
                oNode.bFinal = True
            iToken += 1
            oNode = oNextNode
        oNode.bFinal = True
        self.aPreviousRule = aRule

    def finish (self):
        "minimize unchecked nodes"
        self._minimize(0)

    def _minimize (self, downTo):
        # proceed from the leaf up to a certain point
        for i in range( len(self.lUncheckedNodes)-1, downTo-1, -1 ):
            oNode, token, oChildNode = self.lUncheckedNodes[i]
            if oChildNode in self.lMinimizedNodes:
                # replace the child with the previously encountered one
                oNode.dArcs[token] = self.lMinimizedNodes[oChildNode]
            else:
                # add the state to the minimized nodes.
                self.lMinimizedNodes[oChildNode] = oChildNode
            self.lUncheckedNodes.pop()

    def countNodes (self):
        self.nNode = len(self.lMinimizedNodes)

    def countArcs (self):
        self.nArc = 0
        for oNode in self.lMinimizedNodes:
            self.nArc += len(oNode.dArcs)
        
    def lookup (self, sWord):
        oNode = self.oRoot
        for c in sWord:
            if c not in oNode.dArcs:
                return False
            oNode = oNode.dArcs[c]
        return oNode.bFinal

    def displayInfo (self):
        print(" * {:<12} {:>16,}".format("Rules:", self.nRule))
        print(" * {:<12} {:>16,}".format("Nodes:", self.nNode))
        print(" * {:<12} {:>16,}".format("Arcs:", self.nArc))

    def createGraph (self):
        dGraph = { 0: self.oRoot.getNodeAsDict() }
        print(0, "\t", self.oRoot.getNodeAsDict())
        for oNode in self.lMinimizedNodes:
            sHashId = oNode.__hash__() 
            if sHashId not in dGraph:
                dGraph[sHashId] = oNode.getNodeAsDict()
                print(sHashId, "\t", dGraph[sHashId])
            else:
                print("Error. Double node… same id: ", sHashId)
                print(str(oNode.getNodeAsDict()))
        return dGraph



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.
        return self.__str__().__hash__()

    def __eq__ (self, other):
        # 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

Added gc_lang/fr/rules_graph.grx version [0c5fd71826].

























































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
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
#
#   RÈGLES DE GRAMMAIRE FRANÇAISE POUR GRAMMALECTE
#   par Olivier R.
#
#   Copyright © 2011-2017.
#
#   This file is part of Grammalecte.
#
#   Grammalecte is free software: you can redistribute it and/or modify
#   it under the terms of the GNU General Public License as published by
#   the Free Software Foundation, either version 3 of the License, or
#   (at your option) any later version.
#
#   Grammalecte is distributed in the hope that it will be useful,
#   but WITHOUT ANY WARRANTY; without even the implied warranty of
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#   GNU General Public License for more details.
#
#   You should have received a copy of the GNU General Public License
#   along with Grammalecte.  If not, see <http://www.gnu.org/licenses/>
#

# RÈGLES POUR LE  GRAPHE DE TOKENS

# DOCUMENTATION
# Expressions régulières en Python : http://docs.python.org/library/re.html

# [++] : séparateur des règles pour le paragraphe et des règles pour la phrase.

# Types d’action:
#   ->> erreur
#   ~>> préprocesseur de texte
#   =>> désambiguïsateur


# Fin d’interprétation du fichier avec une ligne commençant par #END

# ERREURS COURANTES
# http://fr.wikipedia.org/wiki/Wikip%C3%A9dia:Fautes_d%27orthographe/Courantes


__rule1__
    les  ~:N:.:s
    des  ~:N:.:s
    ces  ~:N:.:s
        <<-  -1>> acquit                        # Message0|http://test.grammalecte.net

__rule2__
    ci important que soi
    ci vraiment il y a
    ci pour ça
        <<- morph(\2, ":[WAR]", False) -1>> si   # Message1|http://test.grammalecte.net

__rule3__
    contre nature
    contre pétrie
    contre action
        <<- morph(\1, "xxxx") -1:2>> =$area.replace(" ", "")     # Message2|http://test.grammalecte.org
        <<-  ~>> =$area.replace(" ", "")

Modified graphspell-js/tokenizer.js from [bdd895b918] to [9bd60cca8a].

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
const aTkzPatterns = {
    // All regexps must start with ^.
    "default":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERUNIX'],
            [/^[a-zA-Z]:\\(?:Program Files(?: \(x86\)|)|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st.()]+)(?:\\[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERWIN'],
            [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'],
            [/^[A-Z][.][A-Z][.](?:[A-Z][.])*/, 'ACRONYM'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]{2,}[@.])[a-zA-Z0-9][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^\d\d?h\d\d\b/, 'HOUR'],
            [/^-?\d+(?:[.,]\d+|)/, 'NUM'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+)*/, 'WORD']
        ],
    "fr":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERUNIX'],
            [/^[a-zA-Z]:\\(?:Program Files(?: \(x86\)|)|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st.()]+)(?:\\[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERWIN'],
            [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]+/, 'SEPARATOR'],
            [/^[A-Z][.][A-Z][.](?:[A-Z][.])*/, 'ACRONYM'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]{2,}[@.])[a-zA-Z0-9][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`]/i, 'ELPFX'],







|















|







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
const aTkzPatterns = {
    // All regexps must start with ^.
    "default":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERUNIX'],
            [/^[a-zA-Z]:\\(?:Program Files(?: \(x86\)|)|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st.()]+)(?:\\[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERWIN'],
            [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]/, 'SEPARATOR'],
            [/^[A-Z][.][A-Z][.](?:[A-Z][.])*/, 'ACRONYM'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]{2,}[@.])[a-zA-Z0-9][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^\d\d?h\d\d\b/, 'HOUR'],
            [/^-?\d+(?:[.,]\d+|)/, 'NUM'],
            [/^[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+(?:[’'`-][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+)*/, 'WORD']
        ],
    "fr":
        [
            [/^[   \t]+/, 'SPACE'],
            [/^\/(?:~|bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERUNIX'],
            [/^[a-zA-Z]:\\(?:Program Files(?: \(x86\)|)|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st.()]+)(?:\\[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.()-]+)*/, 'FOLDERWIN'],
            [/^[,.;:!?…«»“”‘’"(){}\[\]/·–—]/, 'SEPARATOR'],
            [/^[A-Z][.][A-Z][.](?:[A-Z][.])*/, 'ACRONYM'],
            [/^(?:https?:\/\/|www[.]|[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+[@.][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]{2,}[@.])[a-zA-Z0-9][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_.\/?&!%=+*"'@$#-]+/, 'LINK'],
            [/^[#@][a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st_-]+/, 'TAG'],
            [/^<[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+.*?>|<\/[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+ *>/, 'HTML'],
            [/^\[\/?[a-zA-Zà-öÀ-Ö0-9ø-ÿØ-ßĀ-ʯfi-st]+\]/, 'PSEUDOHTML'],
            [/^&\w+;(?:\w+;|)/, 'HTMLENTITY'],
            [/^(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`]/i, 'ELPFX'],
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
93
94
95
            this.sLang = "default";
        }
        this.aRules = aTkzPatterns[this.sLang];
    }

    * genTokens (sText) {
        let m;
        let i = 0;
        while (sText) {
            let nCut = 1;

            for (let [zRegex, sType] of this.aRules) {
                try {
                    if ((m = zRegex.exec(sText)) !== null) {
                        if (sType == 'SEPARATOR') {
                            for (let c of m[0]) {
                                yield { "sType": sType, "sValue": c, "nStart": i, "nEnd": i + m[0].length }
                            }
                        } else {
                            yield { "sType": sType, "sValue": m[0], "nStart": i, "nEnd": i + m[0].length }
                        }
                        nCut = m[0].length;
                        break;
                    }
                }
                catch (e) {
                    helpers.logerror(e);
                }
            }
            i += nCut;
            sText = sText.slice(nCut);
        }
    }
}


if (typeof(exports) !== 'undefined') {
    exports.Tokenizer = Tokenizer;
}







|

|
>



|
<
<
<
<
|
<
|







|
|








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
            this.sLang = "default";
        }
        this.aRules = aTkzPatterns[this.sLang];
    }

    * genTokens (sText) {
        let m;
        let iNext = 0;
        while (sText) {
            let iCut = 1;
            let iToken = 0;
            for (let [zRegex, sType] of this.aRules) {
                try {
                    if ((m = zRegex.exec(sText)) !== null) {
                        iToken += 1;




                        yield { "i": iToken, "sType": sType, "sValue": m[0], "nStart": iNext, "nEnd": iNext + m[0].length }

                        iCut = m[0].length;
                        break;
                    }
                }
                catch (e) {
                    helpers.logerror(e);
                }
            }
            iNext += iCut;
            sText = sText.slice(iCut);
        }
    }
}


if (typeof(exports) !== 'undefined') {
    exports.Tokenizer = Tokenizer;
}

Modified graphspell/tokenizer.py from [17f452887e] to [b3cbfe75ea].

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
# Very simple tokenizer

import re

_PATTERNS = {
    "default":
        (
            r'(?P<FOLDERUNIX>/(?:bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:/[\w.()-]+)*)',
            r'(?P<FOLDERWIN>[a-zA-Z]:\\(?:Program Files(?: [(]x86[)]|)|[\w.()]+)(?:\\[\w.()-]+)*)',
            r'(?P<PUNC>[.,?!:;…«»“”"()/·]+)',
            r'(?P<ACRONYM>[A-Z][.][A-Z][.](?:[A-Z][.])*)',
            r'(?P<LINK>(?:https?://|www[.]|\w+[@.]\w\w+[@.])\w[\w./?&!%=+*"\'@$#-]+)',
            r'(?P<HASHTAG>[#@][\w-]+)',
            r'(?P<HTML><\w+.*?>|</\w+ *>)',
            r'(?P<PSEUDOHTML>\[/?\w+\])',
            r'(?P<HOUR>\d\d?h\d\d\b)',
            r'(?P<NUM>-?\d+(?:[.,]\d+))',
            r"(?P<WORD>\w+(?:[’'`-]\w+)*)"
        ),
    "fr":
        (
            r'(?P<FOLDERUNIX>/(?:bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:/[\w.()-]+)*)',
            r'(?P<FOLDERWIN>[a-zA-Z]:\\(?:Program Files(?: [(]x86[)]|)|[\w.()]+)(?:\\[\w.()-]+)*)',
            r'(?P<PUNC>[.,?!:;…«»“”"()/·]+)',
            r'(?P<ACRONYM>[A-Z][.][A-Z][.](?:[A-Z][.])*)',
            r'(?P<LINK>(?:https?://|www[.]|\w+[@.]\w\w+[@.])\w[\w./?&!%=+*"\'@$#-]+)',
            r'(?P<HASHTAG>[#@][\w-]+)',
            r'(?P<HTML><\w+.*?>|</\w+ *>)',
            r'(?P<PSEUDOHTML>\[/?\w+\])',
            r"(?P<ELPFX>(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`])",
            r'(?P<ORDINAL>\d+(?:er|nd|e|de|ième|ème|eme)\b)',









|













|







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
# Very simple tokenizer

import re

_PATTERNS = {
    "default":
        (
            r'(?P<FOLDERUNIX>/(?:bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:/[\w.()-]+)*)',
            r'(?P<FOLDERWIN>[a-zA-Z]:\\(?:Program Files(?: [(]x86[)]|)|[\w.()]+)(?:\\[\w.()-]+)*)',
            r'(?P<PUNC>[][,.;:!?…«»“”‘’"(){}/·–—])',
            r'(?P<ACRONYM>[A-Z][.][A-Z][.](?:[A-Z][.])*)',
            r'(?P<LINK>(?:https?://|www[.]|\w+[@.]\w\w+[@.])\w[\w./?&!%=+*"\'@$#-]+)',
            r'(?P<HASHTAG>[#@][\w-]+)',
            r'(?P<HTML><\w+.*?>|</\w+ *>)',
            r'(?P<PSEUDOHTML>\[/?\w+\])',
            r'(?P<HOUR>\d\d?h\d\d\b)',
            r'(?P<NUM>-?\d+(?:[.,]\d+))',
            r"(?P<WORD>\w+(?:[’'`-]\w+)*)"
        ),
    "fr":
        (
            r'(?P<FOLDERUNIX>/(?:bin|boot|dev|etc|home|lib|mnt|opt|root|sbin|tmp|usr|var|Bureau|Documents|Images|Musique|Public|Téléchargements|Vidéos)(?:/[\w.()-]+)*)',
            r'(?P<FOLDERWIN>[a-zA-Z]:\\(?:Program Files(?: [(]x86[)]|)|[\w.()]+)(?:\\[\w.()-]+)*)',
            r'(?P<PUNC>[][,.;:!?…«»“”‘’"(){}/·–—])',
            r'(?P<ACRONYM>[A-Z][.][A-Z][.](?:[A-Z][.])*)',
            r'(?P<LINK>(?:https?://|www[.]|\w+[@.]\w\w+[@.])\w[\w./?&!%=+*"\'@$#-]+)',
            r'(?P<HASHTAG>[#@][\w-]+)',
            r'(?P<HTML><\w+.*?>|</\w+ *>)',
            r'(?P<PSEUDOHTML>\[/?\w+\])',
            r"(?P<ELPFX>(?:l|d|n|m|t|s|j|c|ç|lorsqu|puisqu|jusqu|quoiqu|qu)['’`])",
            r'(?P<ORDINAL>\d+(?:er|nd|e|de|ième|ème|eme)\b)',
41
42
43
44
45
46
47
48
49
    def __init__ (self, sLang):
        self.sLang = sLang
        if sLang not in _PATTERNS:
            self.sLang = "default"
        self.zToken = re.compile( "(?i)" + '|'.join(sRegex for sRegex in _PATTERNS[sLang]) )

    def genTokens (self, sText):
        for m in self.zToken.finditer(sText):
            yield { "sType": m.lastgroup, "sValue": m.group(), "nStart": m.start(), "nEnd": m.end() }







|
|
41
42
43
44
45
46
47
48
49
    def __init__ (self, sLang):
        self.sLang = sLang
        if sLang not in _PATTERNS:
            self.sLang = "default"
        self.zToken = re.compile( "(?i)" + '|'.join(sRegex for sRegex in _PATTERNS[sLang]) )

    def genTokens (self, sText):
        for i, m in enumerate(self.zToken.finditer(sText), 1):
            yield { "i": i, "sType": m.lastgroup, "sValue": m.group(), "nStart": m.start(), "nEnd": m.end() }

Modified make.py from [14e0172bf2] to [08ab9e62c7].

15
16
17
18
19
20
21

22
23
24
25
26
27
28
import json
import platform

from distutils import dir_util, file_util

import dialog_bundled
import compile_rules

import helpers
import lex_build


sWarningMessage = "The content of this folder is generated by code and replaced at each build.\n"









>







15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
import json
import platform

from distutils import dir_util, file_util

import dialog_bundled
import compile_rules
import compile_rules_graph
import helpers
import lex_build


sWarningMessage = "The content of this folder is generated by code and replaced at each build.\n"


189
190
191
192
193
194
195
196
197


198
199
200
201
202
203
204
    spLang = "gc_lang/" + sLang

    dVars = xConfig._sections['args']
    dVars['locales'] = dVars["locales"].replace("_", "-")
    dVars['loc'] = str(dict([ [s, [s[0:2], s[3:5], ""]] for s in dVars["locales"].split(" ") ]))

    ## COMPILE RULES
    dResult = compile_rules.make(spLang, dVars['lang'], bJavaScript)
    dVars.update(dResult)



    ## READ GRAMMAR CHECKER PLUGINS
    print("PYTHON:")
    print("+ Plugins: ", end="")
    sCodePlugins = ""
    for sf in os.listdir(spLang+"/modules"):
        if re.match(r"gce_\w+[.]py$", sf):







|
|
>
>







190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
    spLang = "gc_lang/" + sLang

    dVars = xConfig._sections['args']
    dVars['locales'] = dVars["locales"].replace("_", "-")
    dVars['loc'] = str(dict([ [s, [s[0:2], s[3:5], ""]] for s in dVars["locales"].split(" ") ]))

    ## COMPILE RULES
    dResultRegex = compile_rules.make(spLang, dVars['lang'], bJavaScript)
    dVars.update(dResultRegex)

    dResultGraph = compile_rules_graph.make(spLang, dVars['lang'], bJavaScript)

    ## READ GRAMMAR CHECKER PLUGINS
    print("PYTHON:")
    print("+ Plugins: ", end="")
    sCodePlugins = ""
    for sf in os.listdir(spLang+"/modules"):
        if re.match(r"gce_\w+[.]py$", sf):