Overview
| Comment: | [core][py] gc engine: better debugging information |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | core | rg |
| Files: | files | file ages | folders |
| SHA3-256: |
ba6939effa5af5b121661602d37b5966 |
| User & Date: | olr on 2018-09-12 09:44:15 |
| Other Links: | branch diff | manifest | tags |
Context
|
2018-09-12
| ||
| 09:46 | [core][build][js] fix several issues, better debugging information, create RegExp at runtime instead of preprocessing them at build check-in: 50bef581ca user: olr tags: core, build, rg | |
| 09:44 | [core][py] gc engine: better debugging information check-in: ba6939effa user: olr tags: core, rg | |
| 08:05 | [build] update code conversion to JS check-in: 0c1e2728dd user: olr tags: build, rg | |
Changes
Modified gc_core/py/lang_core/gc_engine.py from [ce1482f7e7] to [a6af5aa7ed].
| ︙ | ︙ | |||
506 507 508 509 510 511 512 |
"execute actions found in the DARG"
bChange = False
for sLineId, nextNodeKey in dNode.items():
bCondMemo = None
for sRuleId in dGraph[nextNodeKey]:
try:
if bDebug:
| | | 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 |
"execute actions found in the DARG"
bChange = False
for sLineId, nextNodeKey in dNode.items():
bCondMemo = None
for sRuleId in dGraph[nextNodeKey]:
try:
if bDebug:
echo(" >TRY: " + sRuleId + " " + sLineId)
sOption, sFuncCond, cActionType, sWhat, *eAct = _rules_graph.dRule[sRuleId]
# Suggestion [ option, condition, "-", replacement/suggestion/action, iTokenStart, iTokenEnd, cStartLimit, cEndLimit, bCaseSvty, nPriority, sMessage, sURL ]
# TextProcessor [ option, condition, "~", replacement/suggestion/action, iTokenStart, iTokenEnd, bCaseSvty ]
# Disambiguator [ option, condition, "=", replacement/suggestion/action ]
# Tag [ option, condition, "/", replacement/suggestion/action, iTokenStart, iTokenEnd ]
# Immunity [ option, condition, "%", "", iTokenStart, iTokenEnd ]
# Test [ option, condition, ">", "" ]
|
| ︙ | ︙ | |||
529 530 531 532 533 534 535 |
nTokenErrorEnd = nTokenOffset + iTokenEnd if iTokenEnd > 0 else nLastToken + iTokenEnd
nErrorStart = self.nOffsetWithinParagraph + (self.lToken[nTokenErrorStart]["nStart"] if cStartLimit == "<" else self.lToken[nTokenErrorStart]["nEnd"])
nErrorEnd = self.nOffsetWithinParagraph + (self.lToken[nTokenErrorEnd]["nEnd"] if cEndLimit == ">" else self.lToken[nTokenErrorEnd]["nStart"])
if nErrorStart not in self.dError or nPriority > self.dErrorPriority.get(nErrorStart, -1):
self.dError[nErrorStart] = self._createErrorFromTokens(sWhat, nTokenOffset, nLastToken, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, bCaseSvty, sMessage, sURL, bShowRuleId, sOption, bContext)
self.dErrorPriority[nErrorStart] = nPriority
if bDebug:
| | | < | | < | | | | 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 |
nTokenErrorEnd = nTokenOffset + iTokenEnd if iTokenEnd > 0 else nLastToken + iTokenEnd
nErrorStart = self.nOffsetWithinParagraph + (self.lToken[nTokenErrorStart]["nStart"] if cStartLimit == "<" else self.lToken[nTokenErrorStart]["nEnd"])
nErrorEnd = self.nOffsetWithinParagraph + (self.lToken[nTokenErrorEnd]["nEnd"] if cEndLimit == ">" else self.lToken[nTokenErrorEnd]["nStart"])
if nErrorStart not in self.dError or nPriority > self.dErrorPriority.get(nErrorStart, -1):
self.dError[nErrorStart] = self._createErrorFromTokens(sWhat, nTokenOffset, nLastToken, nTokenErrorStart, nErrorStart, nErrorEnd, sLineId, sRuleId, bCaseSvty, sMessage, sURL, bShowRuleId, sOption, bContext)
self.dErrorPriority[nErrorStart] = nPriority
if bDebug:
echo(" NEW_ERROR: {}".format(self.dError[nErrorStart]))
elif cActionType == "~":
# text processor
nTokenStart = nTokenOffset + eAct[0] if eAct[0] > 0 else nLastToken + eAct[0]
nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1]
self._tagAndPrepareTokenForRewriting(sWhat, nTokenStart, nTokenEnd, nTokenOffset, nLastToken, eAct[2], bDebug)
bChange = True
if bDebug:
echo(" TEXT_PROCESSOR: [{}:{}] > {}".format(self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"], sWhat))
elif cActionType == "=":
# disambiguation
globals()[sWhat](self.lToken, nTokenOffset, nLastToken)
if bDebug:
echo(" DISAMBIGUATOR: ({}) [{}:{}]".format(sWhat, self.lToken[nTokenOffset+1]["sValue"], self.lToken[nLastToken]["sValue"]))
elif cActionType == ">":
# we do nothing, this test is just a condition to apply all following actions
if bDebug:
echo(" COND_OK")
pass
elif cActionType == "/":
# Tag
nTokenStart = nTokenOffset + eAct[0] if eAct[0] > 0 else nLastToken + eAct[0]
nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1]
for i in range(nTokenStart, nTokenEnd+1):
if "tags" in self.lToken[i]:
self.lToken[i]["tags"].update(sWhat.split("|"))
else:
self.lToken[i]["tags"] = set(sWhat.split("|"))
if bDebug:
echo(" TAG: {} > [{}:{}]".format(sWhat, self.lToken[nTokenStart]["sValue"], self.lToken[nTokenEnd]["sValue"]))
if sWhat not in self.dTags:
self.dTags[sWhat] = [nTokenStart, nTokenStart]
else:
self.dTags[sWhat][0] = min(nTokenStart, self.dTags[sWhat][0])
self.dTags[sWhat][1] = max(nTokenEnd, self.dTags[sWhat][1])
elif cActionType == "%":
# immunity
if bDebug:
echo(" IMMUNITY: " + _rules_graph.dRule[sRuleId])
nTokenStart = nTokenOffset + eAct[0] if eAct[0] > 0 else nLastToken + eAct[0]
nTokenEnd = nTokenOffset + eAct[1] if eAct[1] > 0 else nLastToken + eAct[1]
if nTokenEnd - nTokenStart == 0:
self.lToken[nTokenStart]["bImmune"] = True
nErrorStart = self.nOffsetWithinParagraph + self.lToken[nTokenStart]["nStart"]
if nErrorStart in self.dError:
del self.dError[nErrorStart]
else:
for i in range(nTokenStart, nTokenEnd+1):
self.lToken[i]["bImmune"] = True
nErrorStart = self.nOffsetWithinParagraph + self.lToken[i]["nStart"]
if nErrorStart in self.dError:
del self.dError[nErrorStart]
else:
echo("# error: unknown action at " + sLineId)
elif cActionType == ">":
if bDebug:
echo(" COND_BREAK")
break
except Exception as e:
raise Exception(str(e), sLineId, sRuleId, self.sSentence)
return bChange
def _createErrorFromRegex (self, sText, sText0, sRepl, nOffset, m, iGroup, sLineId, sRuleId, bUppercase, sMsg, sURL, bShowRuleId, sOption, bContext):
nStart = nOffset + m.start(iGroup)
|
| ︙ | ︙ | |||
699 700 701 702 703 704 705 |
else:
sNew = m.expand(sRepl)
sNew = sNew + " " * (nLen-len(sNew))
return sText[0:m.start(iGroup)] + sNew + sText[m.end(iGroup):]
def _tagAndPrepareTokenForRewriting (self, sWhat, nTokenRewriteStart, nTokenRewriteEnd, nTokenOffset, nLastToken, bCaseSvty, bDebug):
"text processor: rewrite tokens between <nTokenRewriteStart> and <nTokenRewriteEnd> position"
| < < | 697 698 699 700 701 702 703 704 705 706 707 708 709 710 |
else:
sNew = m.expand(sRepl)
sNew = sNew + " " * (nLen-len(sNew))
return sText[0:m.start(iGroup)] + sNew + sText[m.end(iGroup):]
def _tagAndPrepareTokenForRewriting (self, sWhat, nTokenRewriteStart, nTokenRewriteEnd, nTokenOffset, nLastToken, bCaseSvty, bDebug):
"text processor: rewrite tokens between <nTokenRewriteStart> and <nTokenRewriteEnd> position"
if sWhat == "*":
# purge text
if nTokenRewriteEnd - nTokenRewriteStart == 0:
self.lToken[nTokenRewriteStart]["bToRemove"] = True
else:
for i in range(nTokenRewriteStart, nTokenRewriteEnd+1):
self.lToken[i]["bToRemove"] = True
|
| ︙ | ︙ | |||
851 852 853 854 855 856 857 |
if sNegPattern and re.search(sNegPattern, s):
return False
if re.search(sPattern, s):
return True
return False
| | < | | | 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 |
if sNegPattern and re.search(sNegPattern, s):
return False
if re.search(sPattern, s):
return True
return False
def look_chk1 (dTokenPos, s, nOffset, sPattern, sPatternGroup1, sNegPatternGroup1=""):
"returns True if s has pattern sPattern and m.group(1) has pattern sPatternGroup1"
m = re.search(sPattern, s)
if not m:
return False
try:
sWord = m.group(1)
nPos = m.start(1) + nOffset
except:
return False
return morph(dTokenPos, (nPos, sWord), sPatternGroup1, sNegPatternGroup1)
#### Analyse groups for regex rules
def displayInfo (dTokenPos, tWord):
"for debugging: retrieve info of word"
if not tWord:
|
| ︙ | ︙ |