Grammalecte  Diff

#import unicodedata
from itertools import chain

from ..graphspell.spellchecker import SpellChecker
from ..graphspell.echo import echo
from . import gc_options





__all__ = [ "lang", "locales", "pkg", "name", "version", "author", \
            "load", "parse", "getSpellChecker", \
            "setOption", "setOptions", "getOptions", "getDefaultOptions", "getOptionsLabels", "resetOptions", "displayOptions", \
            "ignoreRule", "resetIgnoreRules", "reactivateRule", "listRules", "displayRules" ]

__version__ = "${version}"

_rules = None                               # module gc_rules

# data
_sAppContext = ""                           # what software is running
_dOptions = None
_aIgnoredRules = set()
_oSpellChecker = None
_dAnalyses = {}                             # cache for data from dictionary



#### Parsing

def parse (sText, sCountry="${country_default}", bDebug=False, dOptions=None, bContext=False):
    "analyses the paragraph sText and returns list of errors"
    #sText = unicodedata.normalize("NFC", sText)
    aErrors = None
    sAlt = sText
    dDA = {}        # Disambiguisator. Key = position; value = list of morphologies
    dPriority = {}  # Key = position; value = priority
    dOpt = _dOptions  if not dOptions  else dOptions

    # parse paragraph
    try:
        sNew, aErrors = _proofread(sText, sAlt, 0, True, dDA, dPriority, sCountry, dOpt, bDebug, bContext)
        if sNew:
            sText = sNew
    except:
        raise

    # cleanup
    if " " in sText:
        sText = sText.replace(" ", ' ') # nbsp
    if " " in sText:
        sText = sText.replace(" ", ' ') # nnbsp
    if "'" in sText:
        sText = sText.replace("'", "’")
    if "‑" in sText:
        sText = sText.replace("‑", "-") # nobreakdash

    # parse sentences
    for iStart, iEnd in _getSentenceBoundaries(sText):
        if 4 < (iEnd - iStart) < 2000:
            dDA.clear()
            try:

                _, errs = _proofread(sText[iStart:iEnd], sAlt[iStart:iEnd], iStart, False, dDA, dPriority, sCountry, dOpt, bDebug, bContext)
                aErrors.update(errs)
            except:
                raise
    return aErrors.values() # this is a view (iterable)


def _getSentenceBoundaries (sText):

    _createError = _createDictError


def load (sContext="Python"):
    global _oSpellChecker
    global _sAppContext
    global _dOptions

    try:
        _oSpellChecker = SpellChecker("${lang}", "${dic_main_filename_py}", "${dic_extended_filename_py}", "${dic_community_filename_py}", "${dic_personal_filename_py}")
        _sAppContext = sContext
        _dOptions = dict(gc_options.getOptions(sContext))   # duplication necessary, to be able to reset to default


    except:
        traceback.print_exc()


def setOption (sOpt, bVal):
    if sOpt in _dOptions:
        _dOptions[sOpt] = bVal

    return os.path.join(os.path.dirname(sys.modules[__name__].__file__), __name__ + ".py")



#### common functions

# common regexes
_zEndOfSentence = re.compile('([.?!:;…][ .?!… »”")]*|.$)')
_zBeginOfParagraph = re.compile("^\W*")
_zEndOfParagraph = re.compile("\W*$")
_zNextWord = re.compile(" +(\w[\w-]*)")
_zPrevWord = re.compile("(\w[\w-]*) +$")


def option (sOpt):
    "return True if option sOpt is active"
    return _dOptions.get(sOpt, False)


def displayInfo (dDA, tWord):
    "for debugging: retrieve info of word"
    if not tWord:
        echo("> nothing to find")
        return True
    if tWord[1] not in _dAnalyses and not _storeMorphFromFSA(tWord[1]):

        echo("> not in FSA")
        return True
    if tWord[0] in dDA:
        echo("DA: " + str(dDA[tWord[0]]))
    echo("FSA: " + str(_dAnalyses[tWord[1]]))
    return True


def _storeMorphFromFSA (sWord):
    "retrieves morphologies list from _oSpellChecker -> _dAnalyses"
    global _dAnalyses
    _dAnalyses[sWord] = _oSpellChecker.getMorph(sWord)
    return True  if _dAnalyses[sWord]  else False


def morph (dDA, tWord, sPattern, bStrict=True, bNoWord=False):
    "analyse a tuple (position, word), return True if sPattern in morphologies (disambiguation on)"
    if not tWord:
        return bNoWord
    if tWord[1] not in _dAnalyses and not _storeMorphFromFSA(tWord[1]):
        return False
    lMorph = dDA[tWord[0]]  if tWord[0] in dDA  else _dAnalyses[tWord[1]]
    if not lMorph:
        return False
    p = re.compile(sPattern)
    if bStrict:
        return all(p.search(s)  for s in lMorph)
    return any(p.search(s)  for s in lMorph)


def morphex (dDA, tWord, sPattern, sNegPattern, bNoWord=False):
    "analyse a tuple (position, word), returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation on)"
    if not tWord:
        return bNoWord
    if tWord[1] not in _dAnalyses and not _storeMorphFromFSA(tWord[1]):

        return False
    lMorph = dDA[tWord[0]]  if tWord[0] in dDA  else _dAnalyses[tWord[1]]
    # check negative condition
    np = re.compile(sNegPattern)
    if any(np.search(s)  for s in lMorph):
        return False
    # search sPattern
    p = re.compile(sPattern)
    return any(p.search(s)  for s in lMorph)


def analyse (sWord, sPattern, bStrict=True):
    "analyse a word, return True if sPattern in morphologies (disambiguation off)"
    if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
        return False
    if not _dAnalyses[sWord]:
        return False
    p = re.compile(sPattern)
    if bStrict:
        return all(p.search(s)  for s in _dAnalyses[sWord])
    return any(p.search(s)  for s in _dAnalyses[sWord])


def analysex (sWord, sPattern, sNegPattern):
    "analyse a word, returns True if not sNegPattern in word morphologies and sPattern in word morphologies (disambiguation off)"
    if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):

        return False
    # check negative condition
    np = re.compile(sNegPattern)
    if any(np.search(s)  for s in _dAnalyses[sWord]):
        return False
    # search sPattern
    p = re.compile(sPattern)
    return any(p.search(s)  for s in _dAnalyses[sWord])


def stem (sWord):
    "returns a list of sWord's stems"
    if not sWord:
        return []
    if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
        return []
    return [ s[1:s.find(" ")]  for s in _dAnalyses[sWord] ]


## functions to get text outside pattern scope

# warning: check compile_rules.py to understand how it works

def nextword (s, iStart, n):

#### Disambiguator

def select (dDA, nPos, sWord, sPattern, lDefault=None):
    if not sWord:
        return True
    if nPos in dDA:
        return True
    if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
        return True
    if len(_dAnalyses[sWord]) == 1:
        return True
    lSelect = [ sMorph  for sMorph in _dAnalyses[sWord]  if re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(_dAnalyses[sWord]):
            dDA[nPos] = lSelect
            #echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
    elif lDefault:
        dDA[nPos] = lDefault
        #echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
    return True


def exclude (dDA, nPos, sWord, sPattern, lDefault=None):
    if not sWord:
        return True
    if nPos in dDA:
        return True
    if sWord not in _dAnalyses and not _storeMorphFromFSA(sWord):
        return True
    if len(_dAnalyses[sWord]) == 1:
        return True
    lSelect = [ sMorph  for sMorph in _dAnalyses[sWord]  if not re.search(sPattern, sMorph) ]
    if lSelect:
        if len(lSelect) != len(_dAnalyses[sWord]):
            dDA[nPos] = lSelect
            #echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
    elif lDefault:
        dDA[nPos] = lDefault
        #echo("= "+sWord+" "+str(dDA.get(nPos, "null")))
    return True


def define (dDA, nPos, lMorph):
    dDA[nPos] = lMorph
    #echo("= "+str(nPos)+" "+str(dDA[nPos]))
    return True


#### GRAMMAR CHECKER PLUGINS

${plugins}




${callables}