Grammalecte  Check-in [4ff036a562]

Overview
Comment:[build] compile rules: code clarification
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | build | rg
Files: files | file ages | folders
SHA3-256: 4ff036a562cbf367beaafb2402a819d13a567151904fa716fe87872aa0be03fb
User & Date: olr on 2018-06-24 18:45:40
Other Links: branch diff | manifest | tags
Context
2018-06-24
19:02
[build] compile rules: code clarification check-in: 19d7545cd6 user: olr tags: build, rg
18:45
[build] compile rules: code clarification check-in: 4ff036a562 user: olr tags: build, rg
17:51
[build] compile rules: code cleaning (pylint) check-in: 18191569f4 user: olr tags: build, rg
Changes

Modified compile_rules.py from [30d53476f8] to [79df313117].

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
...
282
283
284
285
286
287
288

289
290
291
292
293
294
295
296
297
298
299
300
301
302

303
304
305
306
307
308
309
310
311
312
313
314
315
316








317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
...
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
        if t:
            lActions.append(t)
    if not lActions:
        return None

    return [sOption, sRegex, bCaseInsensitive, sLineId, sRuleId, nPriority, lActions, tGroups]










def createAction (sIdAction, sAction, nGroup):
    "returns an action to perform as a tuple (condition, action type, action[, iGroup [, message, URL ]])"
    m = re.search(r"([-~=>])(\d*|)>>", sAction)
    if not m:
        print("# No action at line " + sIdAction)
        return None

    #### CONDITION
    sCondition = sAction[:m.start()].strip()
    if sCondition:
        sCondition = prepareFunction(sCondition)
        lFUNCTIONS.append(("_c_"+sIdAction, sCondition))
        for x in re.finditer(r"[.](?:group|start|end)[(](\d+)[)]", sCondition):
            if int(x.group(1)) > nGroup:
                print("# Error in groups in condition at line " + sIdAction + " ("+str(nGroup)+" groups only)")
        if ".match" in sCondition:
            print("# Error. JS compatibility. Don't use .match() in condition, use .search()")
        sCondition = "_c_"+sIdAction
    else:
        sCondition = None

    #### iGroup / positioning
................................................................................
            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(("_m_"+sIdAction, sMsg))
                for x in re.finditer(r"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)
        sAction = sAction.replace("m.group(i[4])", "m.group("+str(iGroup)+")")
        for x in re.finditer(r"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(("_s_"+sIdAction, sAction[1:]))
            sAction = "=_s_"+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, iGroup, 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(("_p_"+sIdAction, sAction[1:]))
            sAction = "=_p_"+sIdAction
        elif sAction.startswith('"') and sAction.endswith('"'):
            sAction = sAction[1:-1]
        return [sCondition, cAction, sAction, iGroup]
    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(("_d_"+sIdAction, sAction))
        sAction = "_d_"+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 _calcRulesStats (lRules):
    "count rules and actions"
................................................................................
        lRules = open(spLang + "/rules.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
    lRuleLine = []
    lTest = []
    lOpt = []
    bGraph = False
    lGraphRule = []

    for i, sLine in enumerate(lRules, 1):







>
>
>
>
>
>
>
>













|
<
<







 







>



<
<
<


<
<
<



>





<
<
<

<
<
<


>
>
>
>
>
>
>
>



<
<










<
<










<
<



<
<
<







 







<







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
...
288
289
290
291
292
293
294
295
296
297
298



299
300



301
302
303
304
305
306
307
308
309



310



311
312
313
314
315
316
317
318
319
320
321
322
323


324
325
326
327
328
329
330
331
332
333


334
335
336
337
338
339
340
341
342
343


344
345
346



347
348
349
350
351
352
353
...
440
441
442
443
444
445
446

447
448
449
450
451
452
453
        if t:
            lActions.append(t)
    if not lActions:
        return None

    return [sOption, sRegex, bCaseInsensitive, sLineId, sRuleId, nPriority, lActions, tGroups]


def checkReferenceNumbers (sText, sActionId, nToken):
    "check if token references in <sText> greater than <nToken> (debugging)"
    for x in re.finditer(r"\\(\d+)", sText):
        if int(x.group(1)) > nToken:
            print("# Error in token index at line " + sActionId + " ("+str(nToken)+" tokens only)")
            print(sText)


def createAction (sIdAction, sAction, nGroup):
    "returns an action to perform as a tuple (condition, action type, action[, iGroup [, message, URL ]])"
    m = re.search(r"([-~=>])(\d*|)>>", sAction)
    if not m:
        print("# No action at line " + sIdAction)
        return None

    #### CONDITION
    sCondition = sAction[:m.start()].strip()
    if sCondition:
        sCondition = prepareFunction(sCondition)
        lFUNCTIONS.append(("_c_"+sIdAction, sCondition))
        checkReferenceNumbers(sCondition, sIdAction, nGroup)


        if ".match" in sCondition:
            print("# Error. JS compatibility. Don't use .match() in condition, use .search()")
        sCondition = "_c_"+sIdAction
    else:
        sCondition = None

    #### iGroup / positioning
................................................................................
            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()
            checkReferenceNumbers(sMsg, sIdAction, nGroup)
            if sMsg[0:1] == "=":
                sMsg = prepareFunction(sMsg[1:])
                lFUNCTIONS.append(("_m_"+sIdAction, sMsg))



                sMsg = "=_m_"+sIdAction
            else:



                if re.search("[.]\\w+[(]", sMsg):
                    print("# Error in message at line " + sIdAction + ":  This message looks like code. Line should begin with =")

    checkReferenceNumbers(sAction, sIdAction, nGroup)
    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)
        sAction = sAction.replace("m.group(i[4])", "m.group("+str(iGroup)+")")



    else:



        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 == ">":
        ## no action, break loop if condition is False
        return [sCondition, cAction, ""]

    if not sAction:
        print("# Error in action at line " + sIdAction + ":  This action is empty.")
        return None

    if cAction == "-":
        ## error detected --> suggestion


        if sAction[0:1] == "=":
            lFUNCTIONS.append(("_s_"+sIdAction, sAction[1:]))
            sAction = "=_s_"+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, iGroup, sMsg, sURL]
    elif cAction == "~":
        ## text processor


        if sAction[0:1] == "=":
            lFUNCTIONS.append(("_p_"+sIdAction, sAction[1:]))
            sAction = "=_p_"+sIdAction
        elif sAction.startswith('"') and sAction.endswith('"'):
            sAction = sAction[1:-1]
        return [sCondition, cAction, sAction, iGroup]
    elif cAction == "=":
        ## disambiguator
        if sAction[0:1] == "=":
            sAction = sAction[1:]


        lFUNCTIONS.append(("_d_"+sIdAction, sAction))
        sAction = "_d_"+sIdAction
        return [sCondition, cAction, sAction]



    else:
        print("# Unknown action at line " + sIdAction)
        return None


def _calcRulesStats (lRules):
    "count rules and actions"
................................................................................
        lRules = open(spLang + "/rules.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...")

    lRuleLine = []
    lTest = []
    lOpt = []
    bGraph = False
    lGraphRule = []

    for i, sLine in enumerate(lRules, 1):