Grammalecte  Diff

Differences From Artifact [86b9b97d23]:

To Artifact [3a1bfb17f3]:


97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
97
98
99
100
101
102
103

104
105
106
107
108
109
110







-







        self.dDef = dDef
        self.dDecl = dDecl
        self.dOptPriority = dOptPriority
        self.dAntiPatterns = {}
        self.dActions = {}
        self.dFuncName = {}
        self.dFunctions = {}
        self.dURL = {}

    def _genTokenLines (self, sTokenLine):
        "tokenize a string and return a list of lines of tokens"
        lTokenLines = []
        for sTokBlock in sTokenLine.split():
            # replace merger characters by spaces
            if "␣" in sTokBlock:
320
321
322
323
324
325
326
327

328
329
330
331
332
333
334
319
320
321
322
323
324
325

326
327
328
329
330
331
332
333







-
+








        if cAction == "-":
            ## error
            iMsg = sAction.find(" # ")
            if iMsg == -1:
                sMsg = "# Error. Error message not found."
                sURL = ""
                print("\n" + sMsg + " at: ", sLineId, sActionId)
                print("\n# Error. No message at: ", sLineId, sActionId)
            else:
                sMsg = sAction[iMsg+3:].strip()
                sAction = sAction[:iMsg].strip()
                sURL = ""
                mURL = re.search("[|] *(https?://.*)", sMsg)
                if mURL:
                    sURL = mURL.group(1).strip()
474
475
476
477
478
479
480
481

482
483
484
485
486
487
488
489
490

491
492
493
494
495

496
497
498
499
500
501
502
503

504
505
506
507
508
509

510
511
512
513
514
515
516
473
474
475
476
477
478
479

480
481
482
483
484
485
486
487
488

489
490
491
492
493

494
495
496
497
498
499
500
501

502
503
504
505
506
507

508
509
510
511
512
513
514
515







-
+








-
+




-
+







-
+





-
+







    iActionBlock = 0
    aRuleName = set()

    for iLine, sLine in lRule:
        sLine = sLine.rstrip()
        if "\t" in sLine:
            # tabulation not allowed
            print("Error. Tabulation at line: ", iLine)
            print("# Error. Tabulation at line: ", iLine)
            exit()
        elif sLine.startswith("@@@@GRAPH: "):
            # rules graph call
            m = re.match(r"@@@@GRAPH: *(\w+) *[|] *(\w+)", sLine.strip())
            if m:
                sGraphName = m.group(1)
                sGraphCode = m.group(2)
                if sGraphName in dAllGraph or sGraphCode in dGraphCode:
                    print(f"Error at line {iLine}. Graph name <{sGraphName}> or graph code <{sGraphCode}> already exists.")
                    print(f"# Error at line {iLine}. Graph name <{sGraphName}> or graph code <{sGraphCode}> already exists.")
                    exit()
                dAllGraph[sGraphName] = []
                dGraphCode[sGraphName] = sGraphCode
            else:
                print("Error. Graph name not found at line", iLine)
                print("# Error. Graph name not found at line", iLine)
                exit()
        elif sLine.startswith("__") and sLine.endswith("__"):
            # new rule group
            m = re.match("__(\\w+)(!\\d|)__", sLine)
            if m:
                sRuleName = m.group(1)
                if sRuleName in aRuleName:
                    print(f"Error at line {iLine}. Rule name <{sRuleName}> already exists.")
                    print(f"# Error at line {iLine}. Rule name <{sRuleName}> already exists.")
                    exit()
                aRuleName.add(sRuleName)
                iActionBlock = 1
                nPriority = int(m.group(2)[1:]) if m.group(2)  else -1
            else:
                print("Syntax error in rule group: ", sLine, " -- line:", iLine)
                print("# Syntax error in rule group: ", sLine, " -- line:", iLine)
                exit()
        elif re.match("    \\S", sLine):
            # tokens line
            lTokenLine.append([iLine, sLine.strip()])
        elif sLine.startswith("        ||"):
            # tokens line continuation
            iPrevLine, sPrevLine = lTokenLine[-1]
531
532
533
534
535
536
537
538

539
540
541
542

543
544
545
546
547
548
549
550

551
552
553
554
555
556
557
530
531
532
533
534
535
536

537
538
539
540

541
542
543
544
545
546
547
548

549
550
551
552
553
554
555
556







-
+



-
+







-
+







            if re.search(r"[-=~/!>](?:-?\d\.?(?::\.?-?\d+|)|):?>>", sLine):
                bActionBlock = False
        elif re.match("[  ]*$", sLine):
            # empty line to end merging
            if not lTokenLine:
                continue
            if bActionBlock or not lActions:
                print("Error. No action found at line:", iLine)
                print("# Error. No action found at line:", iLine)
                print(bActionBlock, lActions)
                exit()
            if not sGraphName:
                print("Error. All rules must belong to a named graph. Line: ", iLine)
                print("# Error. All rules must belong to a named graph. Line: ", iLine)
                exit()
            for j, sTokenLine in lTokenLine:
                dAllGraph[sGraphName].append((j, sRuleName, sTokenLine, iActionBlock, list(lActions), nPriority))
            lTokenLine.clear()
            lActions.clear()
            iActionBlock += 1
        else:
            print("Unknown line at:", iLine)
            print("# Unknown line at:", iLine)
            print(sLine)

    # processing rules
    print("  processing graph rules...")
    initProcessPoolExecutor(len(dAllGraph))
    fStartTimer = time.time()
    # build graph