Overview
| Comment: | [graphspell] code cleaning (pylint) |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | trunk | graphspell |
| Files: | files | file ages | folders |
| SHA3-256: |
23fcc016eebebd4bb10d93f2b2130908 |
| User & Date: | olr on 2019-05-11 14:34:36 |
| Other Links: | manifest | tags |
Context
|
2019-05-11
| ||
| 14:34 | [core][fr] code cleaning check-in: b41f8c080b user: olr tags: trunk, fr, core | |
| 14:34 | [graphspell] code cleaning (pylint) check-in: 23fcc016ee user: olr tags: trunk, graphspell | |
| 12:56 | [build] code cleaning (pylint) check-in: 0f67f597ce user: olr tags: trunk, build | |
Changes
Modified graphspell/dawg.py from [bef1848caf] to [c0bbecd002].
| ︙ | ︙ | |||
67 68 69 70 71 72 73 |
else:
raise ValueError("# Error. Unknown stemming code: {}".format(cStemming))
aEntry = set()
lChar = ['']; dChar = {}; nChar = 1; dCharOccur = {}
lAff = []; dAff = {}; nAff = 0; dAffOccur = {}
lTag = []; dTag = {}; nTag = 0; dTagOccur = {}
| < | | | | 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 |
else:
raise ValueError("# Error. Unknown stemming code: {}".format(cStemming))
aEntry = set()
lChar = ['']; dChar = {}; nChar = 1; dCharOccur = {}
lAff = []; dAff = {}; nAff = 0; dAffOccur = {}
lTag = []; dTag = {}; nTag = 0; dTagOccur = {}
self.a2grams = set()
try:
zFilter = re.compile(sSelectFilterRegex) if sSelectFilterRegex else None
except re.error:
print("# Error. Wrong filter regex. Filter ignored: ", zFilter)
traceback.print_exc()
zFilter = None
# read lexicon
if isinstance(src, str):
iterable = readFile(src)
else:
iterable = src
for sFlex, sStem, sTag in iterable:
if not zFilter or zFilter.search(sTag):
self.a2grams.update(st.getNgrams(sFlex))
addWordToCharDict(sFlex)
|
| ︙ | ︙ | |||
123 124 125 126 127 128 129 |
aEntry = None
# Dictionary of arc values occurrency, to sort arcs of each node
dValOccur = dict( [ (dChar[c], dCharOccur[c]) for c in dChar ] \
+ [ (dAff[aff]+nChar, dAffOccur[aff]) for aff in dAff ] \
+ [ (dTag[tag]+nChar+nAff, dTagOccur[tag]) for tag in dTag ] )
| | | 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
aEntry = None
# Dictionary of arc values occurrency, to sort arcs of each node
dValOccur = dict( [ (dChar[c], dCharOccur[c]) for c in dChar ] \
+ [ (dAff[aff]+nChar, dAffOccur[aff]) for aff in dAff ] \
+ [ (dTag[tag]+nChar+nAff, dTagOccur[tag]) for tag in dTag ] )
self.sFileName = src if isinstance(src, str) else "[None]"
self.sLangCode = sLangCode
self.sLangName = sLangName
self.sDicName = sDicName
self.sDescription = sDescription
if dLexiconData:
self.sLangCode = dLexiconData.get("LangCode", self.sLangCode)
self.sLangName = dLexiconData.get("LangName", self.sLangName)
|
| ︙ | ︙ | |||
330 331 332 333 334 335 336 |
def select (self, sPattern=""):
"generator: returns all entries which morphology fits <sPattern>"
zPattern = None
if sPattern:
try:
zPattern = re.compile(sPattern)
| | | 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 |
def select (self, sPattern=""):
"generator: returns all entries which morphology fits <sPattern>"
zPattern = None
if sPattern:
try:
zPattern = re.compile(sPattern)
except re.error:
print("# Error in regex pattern")
traceback.print_exc()
yield from self._select(zPattern, self.oRoot, "")
def _select (self, zPattern, oNode, sWord):
# recursive generator
for nVal, oNextNode in oNode.arcs.items():
|
| ︙ | ︙ |
Modified graphspell/ibdawg.py from [b4fbad68fc] to [35ba56f9ba].
| ︙ | ︙ | |||
88 89 90 91 92 93 94 |
self.dSugg.clear()
class IBDAWG:
"""INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH"""
def __init__ (self, source):
| | | | 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 |
self.dSugg.clear()
class IBDAWG:
"""INDEXABLE BINARY DIRECT ACYCLIC WORD GRAPH"""
def __init__ (self, source):
if isinstance(source, str):
self.by = pkgutil.get_data(__package__, "_dictionaries/" + source)
if not self.by:
raise OSError("# Error. File not found or not loadable: "+source)
if source.endswith(".bdic"):
self._initBinary()
elif source.endswith(".json"):
self._initJSON(json.loads(self.by.decode("utf-8"))) #json.loads(self.by) # In Python 3.6, can read directly binary strings
else:
raise OSError("# Error. Unknown file type: "+source)
else:
self._initJSON(source)
self.sFileName = source if isinstance(source, str) else "[None]"
self._arcMask = (2 ** ((self.nBytesArc * 8) - 3)) - 1
self._finalNodeMask = 1 << ((self.nBytesArc * 8) - 1)
self._lastArcMask = 1 << ((self.nBytesArc * 8) - 2)
self._addrBitMask = 1 << ((self.nBytesArc * 8) - 3) # version 2
# function to decode the affix/suffix code
|
| ︙ | ︙ | |||
476 477 478 479 480 481 482 |
zFlexPattern = None
zTagsPattern = None
try:
if sFlexPattern:
zFlexPattern = re.compile(sFlexPattern)
if sTagsPattern:
zTagsPattern = re.compile(sTagsPattern)
| | | 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 |
zFlexPattern = None
zTagsPattern = None
try:
if sFlexPattern:
zFlexPattern = re.compile(sFlexPattern)
if sTagsPattern:
zTagsPattern = re.compile(sTagsPattern)
except re.error:
print("# Error in regex pattern")
traceback.print_exc()
yield from self._select1(zFlexPattern, zTagsPattern, 0, "")
# def morph (self, sWord):
# is defined in __init__
|
| ︙ | ︙ | |||
510 511 512 513 514 515 516 |
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
| | | | < | | | | | 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 |
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
# Now , we go to the next node and retrieve all following arcs values, all of them are tags
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
nRawArc2 = 0
while not nRawArc2 & self._lastArcMask:
iEndArcAddr2 = iAddr2 + self.nBytesArc
nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
l.append(sStem + "/" + self.lArcVal[nRawArc2 & self._arcMask])
iAddr2 = iEndArcAddr2+self.nBytesNodeAddress
iAddr = iEndArcAddr+self.nBytesNodeAddress
return l
return []
def _stem1 (self, sWord):
"returns stems list of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
iAddr = iEndArcAddr+self.nBytesNodeAddress
return l
return []
def _lookupArcNode1 (self, nVal, iAddr):
"looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
if nVal == (nRawArc & self._arcMask):
# the value we are looking for
# we return the address of the next node
return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
# value not found
if nRawArc & self._lastArcMask:
return None
iAddr = iEndArcAddr+self.nBytesNodeAddress
def _getArcs1 (self, iAddr):
"generator: return all arcs at <iAddr> as tuples of (nVal, iAddr)"
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
yield nRawArc & self._arcMask, int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
|
| ︙ | ︙ | |||
608 609 610 611 612 613 614 |
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
| | | | | | | | | | | | < | | | | | | < | | | | | | 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 |
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
# Now , we go to the next node and retrieve all following arcs values, all of them are tags
if not nRawArc & self._addrBitMask:
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
else:
# we go to the end of the node
iAddr2 = iEndArcAddr
while not nRawArc & self._lastArcMask:
nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
iAddr2 += self.nBytesArc + self.nBytesNodeAddress
nRawArc2 = 0
while not nRawArc2 & self._lastArcMask:
iEndArcAddr2 = iAddr2 + self.nBytesArc
nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
l.append(sStem + "/" + self.lArcVal[nRawArc2 & self._arcMask])
iAddr2 = iEndArcAddr2+self.nBytesNodeAddress if not nRawArc2 & self._addrBitMask else iEndArcAddr2
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr
return l
return []
def _stem2 (self, sWord):
"returns stems list of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
# Now , we go to the next node
if not nRawArc & self._addrBitMask:
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
else:
# we go to the end of the node
iAddr2 = iEndArcAddr
while not nRawArc & self._lastArcMask:
nRawArc = int.from_bytes(self.byDic[iAddr2:iAddr2+self.nBytesArc], byteorder='big')
iAddr2 += self.nBytesArc + self.nBytesNodeAddress
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr
return l
return []
def _lookupArcNode2 (self, nVal, iAddr):
"looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
if nVal == (nRawArc & self._arcMask):
# the value we are looking for
if not nRawArc & self._addrBitMask:
# we return the address of the next node
return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
# we go to the end of the node
iAddr = iEndArcAddr
while not nRawArc & self._lastArcMask:
nRawArc = int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big')
iAddr += self.nBytesArc + self.nBytesNodeAddress if not nRawArc & self._addrBitMask else self.nBytesArc
return iAddr
# value not found
if nRawArc & self._lastArcMask:
return None
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr
def _writeNodes2 (self, spfDest):
"for debugging only"
print(" > Write binary nodes")
with open(spfDest, 'w', 'utf-8', newline="\n") as hDst:
iAddr = 0
hDst.write("i{:_>10} -- #{:_>10}\n".format("0", iAddr))
while iAddr < len(self.byDic):
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if not nRawArc & self._addrBitMask:
iNextNodeAddr = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
hDst.write(" {:<20} {:0>16} i{:>10} #{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", iNextNodeAddr))
iAddr = iEndArcAddr+self.nBytesNodeAddress
else:
hDst.write(" {:<20} {:0>16}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:]))
iAddr = iEndArcAddr
if nRawArc & self._lastArcMask:
|
| ︙ | ︙ | |||
724 725 726 727 728 729 730 |
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
iAddrNode = iAddr
| | | | | | | | | < | < | | | | | | 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 |
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
iAddrNode = iAddr
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
sStem = ">" + self.funcStemming(sWord, self.lArcVal[nArc])
# Now , we go to the next node and retrieve all following arcs values, all of them are tags
if not nRawArc & self._addrBitMask:
iAddr2 = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
else:
iAddr2 = iAddrNode + int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
nRawArc2 = 0
while not nRawArc2 & self._lastArcMask:
iEndArcAddr2 = iAddr2 + self.nBytesArc
nRawArc2 = int.from_bytes(self.byDic[iAddr2:iEndArcAddr2], byteorder='big')
l.append(sStem + "/" + self.lArcVal[nRawArc2 & self._arcMask])
iAddr2 = iEndArcAddr2+self.nBytesNodeAddress if not nRawArc2 & self._addrBitMask else iEndArcAddr2+self.nBytesOffset
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr+self.nBytesOffset
return l
return []
def _stem3 (self, sWord):
"returns stems list of <sWord>"
iAddr = 0
for c in sWord:
if c not in self.dChar:
return []
iAddr = self._lookupArcNode(self.dChar[c], iAddr)
if iAddr is None:
return []
if int.from_bytes(self.byDic[iAddr:iAddr+self.nBytesArc], byteorder='big') & self._finalNodeMask:
l = []
nRawArc = 0
#iAddrNode = iAddr
while not nRawArc & self._lastArcMask:
iEndArcAddr = iAddr + self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if nArc > self.nChar:
# This value is not a char, this is a stemming code
l.append(self.funcStemming(sWord, self.lArcVal[nArc]))
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr+self.nBytesOffset
return l
return []
def _lookupArcNode3 (self, nVal, iAddr):
"looks if <nVal> is an arc at the node at <iAddr>, if yes, returns address of next node else None"
iAddrNode = iAddr
while True:
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
if nVal == (nRawArc & self._arcMask):
# the value we are looking for
if not nRawArc & self._addrBitMask:
return int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
return iAddrNode + int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
# value not found
if nRawArc & self._lastArcMask:
return None
iAddr = iEndArcAddr+self.nBytesNodeAddress if not nRawArc & self._addrBitMask else iEndArcAddr+self.nBytesOffset
def _writeNodes3 (self, spfDest):
"for debugging only"
print(" > Write binary nodes")
with open(spfDest, 'w', 'utf-8', newline="\n") as hDst:
iAddr = 0
hDst.write("i{:_>10} -- #{:_>10}\n".format("0", iAddr))
while iAddr < len(self.byDic):
iEndArcAddr = iAddr+self.nBytesArc
nRawArc = int.from_bytes(self.byDic[iAddr:iEndArcAddr], byteorder='big')
nArc = nRawArc & self._arcMask
if not nRawArc & self._addrBitMask:
iNextNodeAddr = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesNodeAddress], byteorder='big')
hDst.write(" {:<20} {:0>16} i{:>10} #{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", iNextNodeAddr))
iAddr = iEndArcAddr+self.nBytesNodeAddress
else:
iNextNodeAddr = int.from_bytes(self.byDic[iEndArcAddr:iEndArcAddr+self.nBytesOffset], byteorder='big')
hDst.write(" {:<20} {:0>16} i{:>10} +{:_>10}\n".format(self.lArcVal[nArc], bin(nRawArc)[2:], "?", iNextNodeAddr))
iAddr = iEndArcAddr+self.nBytesOffset
if nRawArc & self._lastArcMask:
hDst.write("\ni{:_>10} -- #{:_>10}\n".format("?", iAddr))
hDst.close()
|