Index: gc_core/py/text.py ================================================================== --- gc_core/py/text.py +++ gc_core/py/text.py @@ -133,18 +133,20 @@ def convertToXY (aGrammErrs, aSpellErrs, lLineSet): """Converts errors position as an y and x position in a text (y is line number, x is row number). lLineSet is a list of sets (line_number_y, start_x, end_x) describing how the paragraph is divided.""" for dErr in chain(aGrammErrs, aSpellErrs): + i = 0 for i, elem in enumerate(lLineSet, 1): if dErr['nEnd'] <= elem[2]: dErr['nEndY'] = elem[0] dErr['nEndX'] = dErr['nEnd'] - elem[1] break - for elem in reversed(lLineSet[:i]): - if dErr['nStart'] >= elem[1]: - dErr['nStartY'] = elem[0] - dErr['nStartX'] = dErr['nStart'] - elem[1] - break + if i: + for elem in reversed(lLineSet[:i]): + if dErr['nStart'] >= elem[1]: + dErr['nStartY'] = elem[0] + dErr['nStartX'] = dErr['nStart'] - elem[1] + break del dErr['nStart'] del dErr['nEnd'] return aGrammErrs, aSpellErrs Index: gc_lang/fr/modules/conj.py ================================================================== --- gc_lang/fr/modules/conj.py +++ gc_lang/fr/modules/conj.py @@ -352,11 +352,11 @@ sPartPre = _getConjWithTags(self.sVerbAux, self._tTagsAux, ":PQ", ":P") if not bPro else getConj("être", ":PQ", ":P") else: sPartPre = self.dConj[":P"][":"] if not sPartPre: return "" - bEli = True if _zStartVoy.search(sPartPre) else False + bEli = bool(_zStartVoy.search(sPartPre)) if bPro: if self.bProWithEn: sPartPre = "s’en " + sPartPre else: sPartPre = "s’" + sPartPre if bEli else "se " + sPartPre @@ -385,11 +385,11 @@ sConj = _getConjWithTags(self.sVerbAux, self._tTagsAux, sTemps, sWho) if not bPro else getConj("être", sTemps, sWho) else: sConj = self.dConj[sTemps][sWho] if not sConj: return "" - bEli = True if _zStartVoy.search(sConj) else False + bEli = bool(_zStartVoy.search(sConj)) if bPro: if not self.bProWithEn: sConj = _dProObjEl[sWho] + sConj if bEli else _dProObj[sWho] + sConj else: sConj = _dProObjEl[sWho] + "en " + sConj @@ -420,11 +420,11 @@ if sWho == ":3s": if self._sRawInfo[5] == "r": return "on" elif bFem: return "elle" - elif sWho == ":3p" and bFem: + if sWho == ":3p" and bFem: return "elles" return _dProSuj[sWho] except: traceback.print_exc() return "# erreur" @@ -438,11 +438,11 @@ sImpe = _getConjWithTags(self.sVerbAux, self._tTagsAux, ":E", sWho) if not bPro else getConj(u"être", ":E", sWho) else: sImpe = self.dConj[":E"][sWho] if not sImpe: return "" - bEli = True if _zStartVoy.search(sImpe) else False + bEli = bool(_zStartVoy.search(sImpe)) if bNeg: if bPro: if not self.bProWithEn: if bEli and sWho == ":2s": sImpe = "ne t’" + sImpe + " pas" @@ -473,10 +473,11 @@ except: traceback.print_exc() return "# erreur" def createConjTable (self, bPro=False, bNeg=False, bTpsCo=False, bInt=False, bFem=False): + "return a dictionary of all conjugations with titles, according to options (used to be displayed as is)" dConjTable = { "t_infi": "Infinitif", "infi": self.infinitif(bPro, bNeg, bTpsCo, bInt, bFem), "t_ppre": "Participe présent", "ppre": self.participePresent(bPro, bNeg, bTpsCo, bInt, bFem), Index: gc_lang/fr/modules/gce_suggestions.py ================================================================== --- gc_lang/fr/modules/gce_suggestions.py +++ gc_lang/fr/modules/gce_suggestions.py @@ -347,11 +347,11 @@ def switchGender (sFlex, bPlur=None): "return feminine or masculine form(s) of " aSugg = set() - if bPlur == None: + if bPlur is None: for sMorph in _oSpellChecker.getMorph(sFlex): if ":f" in sMorph: if ":s" in sMorph: aSugg.add(suggMasSing(sFlex)) elif ":p" in sMorph: Index: graphspell/dawg.py ================================================================== --- graphspell/dawg.py +++ graphspell/dawg.py @@ -667,11 +667,11 @@ ┗━━━━━ if 1, this node is final (only on the first arc) """ nArc = len(self.arcs) nFinalNodeMask = 1 << ((nBytesArc*8)-1) nFinalArcMask = 1 << ((nBytesArc*8)-2) - if len(self.arcs) == 0: + if not nArc: val = nFinalNodeMask | nFinalArcMask by = val.to_bytes(nBytesArc, byteorder='big') by += (0).to_bytes(nBytesNodeAddress, byteorder='big') return by by = b"" @@ -689,11 +689,11 @@ "return representation as string of node (method 1)" nArc = len(self.arcs) nFinalNodeMask = 1 << ((nBytesArc*8)-1) nFinalArcMask = 1 << ((nBytesArc*8)-2) s = "i{:_>10} -- #{:_>10}\n".format(self.i, self.addr) - if len(self.arcs) == 0: + if not nArc: s += " {:<20} {:0>16} i{:_>10} #{:_>10}\n".format("", bin(nFinalNodeMask | nFinalArcMask)[2:], "0", "0") return s for i, arc in enumerate(self.arcs, 1): val = arc if i == 1 and self.final: @@ -729,11 +729,11 @@ """ nArc = len(self.arcs) nFinalNodeMask = 1 << ((nBytesArc*8)-1) nFinalArcMask = 1 << ((nBytesArc*8)-2) nNextNodeMask = 1 << ((nBytesArc*8)-3) - if len(self.arcs) == 0: + if not nArc: val = nFinalNodeMask | nFinalArcMask by = val.to_bytes(nBytesArc, byteorder='big') by += (0).to_bytes(nBytesNodeAddress, byteorder='big') return by by = b"" @@ -756,11 +756,11 @@ nArc = len(self.arcs) nFinalNodeMask = 1 << ((nBytesArc*8)-1) nFinalArcMask = 1 << ((nBytesArc*8)-2) nNextNodeMask = 1 << ((nBytesArc*8)-3) s = "i{:_>10} -- #{:_>10}\n".format(self.i, self.addr) - if nArc == 0: + if not nArc: s += " {:<20} {:0>16} i{:_>10} #{:_>10}\n".format("", bin(nFinalNodeMask | nFinalArcMask)[2:], "0", "0") return s for i, arc in enumerate(self.arcs, 1): val = arc if i == 1 and self.final: @@ -806,11 +806,11 @@ nArc = len(self.arcs) nFinalNodeMask = 1 << ((nBytesArc*8)-1) nFinalArcMask = 1 << ((nBytesArc*8)-2) nNextNodeMask = 1 << ((nBytesArc*8)-3) nMaxOffset = (2 ** (nBytesOffset * 8)) - 1 - if nArc == 0: + if not nArc: val = nFinalNodeMask | nFinalArcMask by = val.to_bytes(nBytesArc, byteorder='big') by += (0).to_bytes(nBytesNodeAddress, byteorder='big') return by by = b"" @@ -835,11 +835,11 @@ nFinalNodeMask = 1 << ((nBytesArc*8)-1) nFinalArcMask = 1 << ((nBytesArc*8)-2) nNextNodeMask = 1 << ((nBytesArc*8)-3) nMaxOffset = (2 ** (nBytesOffset * 8)) - 1 s = "i{:_>10} -- #{:_>10} ({})\n".format(self.i, self.addr, self.size) - if nArc == 0: + if not nArc: s += " {:<20} {:0>16} i{:_>10} #{:_>10}\n".format("", bin(nFinalNodeMask | nFinalArcMask)[2:], "0", "0") return s for i, arc in enumerate(self.arcs, 1): val = arc if i == 1 and self.final: Index: graphspell/ibdawg.py ================================================================== --- graphspell/ibdawg.py +++ graphspell/ibdawg.py @@ -265,12 +265,11 @@ if sWord.isupper(): if self.bAcronymValid: return True return self.lookup(sWord.lower()) or self.lookup(sWord.capitalize()) return self.lookup(sWord[:1].lower() + sWord[1:]) - else: - return self.lookup(sWord.lower()) + return self.lookup(sWord.lower()) if sWord[0:1].isdigit(): return True return False def lookup (self, sWord): @@ -335,11 +334,11 @@ if not sRemain: oSuggResult.addSugg(sNewWord, nDeep) for sTail in self._getTails(iAddr): oSuggResult.addSugg(sNewWord+sTail, nDeep) return - elif (len(sNewWord) + len(sRemain) == len(oSuggResult.sWord)) and oSuggResult.sWord.lower().startswith(sNewWord.lower()) and self.isValid(sRemain): + if (len(sNewWord) + len(sRemain) == len(oSuggResult.sWord)) and oSuggResult.sWord.lower().startswith(sNewWord.lower()) and self.isValid(sRemain): oSuggResult.addSugg(sNewWord+" "+sRemain) if nDist > oSuggResult.nDistLimit: return cCurrent = sRemain[0:1] for cChar, jAddr in self._getCharArcs(iAddr): @@ -375,10 +374,11 @@ self._suggest(oSuggResult, "", nMaxSwitch, nMaxDel, nMaxHardRepl, nMaxJump, nDist, nDeep+1, iAddr, sNewWord, True) # remove last char and go on for sRepl in cp.dFinal1.get(sRemain, ()): self._suggest(oSuggResult, sRepl, nMaxSwitch, nMaxDel, nMaxHardRepl, nMaxJump, nDist, nDeep+1, iAddr, sNewWord, True) def isNgramsOK (self, sChars): + "returns True if sChars in known 2grams" if len(sChars) != 2: return True if not self.a2grams: return True return sChars in self.a2grams ADDED pylintrc Index: pylintrc ================================================================== --- pylintrc +++ pylintrc @@ -0,0 +1,574 @@ +[MASTER] + +# A comma-separated list of package or module names from where C extensions may +# be loaded. Extensions are loading into the active Python interpreter and may +# run arbitrary code +extension-pkg-whitelist= + +# Add files or directories to the blacklist. They should be base names, not +# paths. +ignore=CVS + +# Add files or directories matching the regex patterns to the blacklist. The +# regex matches against base names, not paths. +ignore-patterns=bottle.py + +# Python code to execute, usually for sys.path manipulation such as +# pygtk.require(). +#init-hook= + +# Use multiple processes to speed up Pylint. +jobs=4 + +# List of plugins (as comma separated values of python modules names) to load, +# usually to register additional checkers. +load-plugins= + +# Pickle collected data for later comparisons. +persistent=yes + +# Specify a configuration file. +#rcfile= + +# When enabled, pylint would attempt to guess common misconfiguration and emit +# user-friendly hints instead of false-positive error messages +suggestion-mode=yes + +# Allow loading of arbitrary C extensions. Extensions are imported into the +# active Python interpreter and may run arbitrary code. +unsafe-load-any-extension=no + + +[MESSAGES CONTROL] + +# Only show warnings with the listed confidence levels. Leave empty to show +# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED +confidence= + +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifiers separated by comma (,) or put this +# option multiple times (only on the command line, not in the configuration +# file where it should appear only once).You can also use "--disable=all" to +# disable everything first and then reenable specific checks. For example, if +# you want to run only the similarities checker, you can use "--disable=all +# --enable=similarities". If you want to run only the classes checker, but have +# no Warning level messages displayed, use"--disable=all --enable=classes +# --disable=W" +disable=print-statement, + parameter-unpacking, + unpacking-in-except, + old-raise-syntax, + backtick, + long-suffix, + old-ne-operator, + old-octal-literal, + import-star-module-level, + non-ascii-bytes-literal, + invalid-unicode-literal, + raw-checker-failed, + bad-inline-option, + locally-disabled, + locally-enabled, + file-ignored, + suppressed-message, + useless-suppression, + deprecated-pragma, + apply-builtin, + basestring-builtin, + buffer-builtin, + cmp-builtin, + coerce-builtin, + execfile-builtin, + file-builtin, + long-builtin, + raw_input-builtin, + reduce-builtin, + standarderror-builtin, + unicode-builtin, + xrange-builtin, + coerce-method, + delslice-method, + getslice-method, + setslice-method, + no-absolute-import, + old-division, + dict-iter-method, + dict-view-method, + next-method-called, + metaclass-assignment, + indexing-exception, + raising-string, + reload-builtin, + oct-method, + hex-method, + nonzero-method, + cmp-method, + input-builtin, + round-builtin, + intern-builtin, + unichr-builtin, + map-builtin-not-iterating, + zip-builtin-not-iterating, + range-builtin-not-iterating, + filter-builtin-not-iterating, + using-cmp-argument, + eq-without-hash, + div-method, + idiv-method, + rdiv-method, + exception-message-attribute, + invalid-str-codec, + sys-max-int, + bad-python3-import, + deprecated-string-function, + deprecated-str-translate-call, + deprecated-itertools-function, + deprecated-types-field, + next-method-defined, + dict-items-not-iterating, + dict-keys-not-iterating, + dict-values-not-iterating, + deprecated-operator-function, + deprecated-urllib-function, + xreadlines-attribute, + deprecated-sys-function, + exception-escape, + comprehension-escape, + bad-whitespace, + line-too-long + +# Enable the message, report, category or checker with the given id(s). You can +# either give multiple identifier separated by comma (,) or put this option +# multiple time (only on the command line, not in the configuration file where +# it should appear only once). See also the "--disable" option for examples. +enable=c-extension-no-member + + +[REPORTS] + +# Python expression which should return a note less than 10 (10 is the highest +# note). You have access to the variables errors warning, statement which +# respectively contain the number of errors / warnings messages and the total +# number of statements analyzed. This is used by the global evaluation report +# (RP0004). +evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10) + +# Template used to display messages. This is a python new-style format string +# used to format the message information. See doc for all details +#msg-template= + +# Set the output format. Available formats are text, parseable, colorized, json +# and msvs (visual studio).You can also give a reporter class, eg +# mypackage.mymodule.MyReporterClass. +output-format=text + +# Tells whether to display a full report or only the messages +reports=no + +# Activate the evaluation score. +score=yes + + +[REFACTORING] + +# Maximum number of nested blocks for function / method body +max-nested-blocks=12 + +# Complete name of functions that never returns. When checking for +# inconsistent-return-statements if a never returning function is called then +# it will be considered as an explicit return statement and no message will be +# printed. +never-returning-functions=optparse.Values,sys.exit + + +[BASIC] + +# Naming style matching correct argument names +argument-naming-style=camelCase + +# Regular expression matching correct argument names. Overrides argument- +# naming-style +#argument-rgx= + +# Naming style matching correct attribute names +attr-naming-style=camelCase + +# Regular expression matching correct attribute names. Overrides attr-naming- +# style +#attr-rgx= + +# Bad variable names which should always be refused, separated by a comma +bad-names=foo, + bar, + baz, + toto, + tutu, + tata + +# Naming style matching correct class attribute names +class-attribute-naming-style=any + +# Regular expression matching correct class attribute names. Overrides class- +# attribute-naming-style +#class-attribute-rgx= + +# Naming style matching correct class names +class-naming-style=PascalCase + +# Regular expression matching correct class names. Overrides class-naming-style +#class-rgx= + +# Naming style matching correct constant names +const-naming-style=any + +# Regular expression matching correct constant names. Overrides const-naming- +# style +#const-rgx= + +# Minimum line length for functions/classes that require docstrings, shorter +# ones are exempt. +docstring-min-length=-1 + +# Naming style matching correct function names +function-naming-style=camelCase + +# Regular expression matching correct function names. Overrides function- +# naming-style +function-rgx=^[a-z]\w+|^_* + +# Good variable names which should always be accepted, separated by a comma +good-names=i, + i1, + i2, + j, + k, + s, + s1, + s2, + sx, + sf, + sp, + spf, + c, + c1, + c2, + n, + n1, + n2, + m, + m1, + m2, + d, + l, + l1, + l2, + t, + v, + e, + by, + x, + y, + _ + +# Include a hint for the correct naming format with invalid-name +include-naming-hint=no + +# Naming style matching correct inline iteration names +inlinevar-naming-style=any + +# Regular expression matching correct inline iteration names. Overrides +# inlinevar-naming-style +#inlinevar-rgx= + +# Naming style matching correct method names +method-naming-style=camelCase + +# Regular expression matching correct method names. Overrides method-naming- +# style +#method-rgx= + +# Naming style matching correct module names +module-naming-style=snake_case + +# Regular expression matching correct module names. Overrides module-naming- +# style +#module-rgx= + +# Colon-delimited sets of names that determine each other's naming style when +# the name regexes allow several styles. +name-group= + +# Regular expression which should only match function or class names that do +# not require a docstring. +no-docstring-rgx=^_|^test_ + +# List of decorators that produce properties, such as abc.abstractproperty. Add +# to this list to register other decorators that produce valid properties. +property-classes=abc.abstractproperty + +# Naming style matching correct variable names +variable-naming-style=camelCase + +# Regular expression matching correct variable names. Overrides variable- +# naming-style +#variable-rgx= + + +[FORMAT] + +# Expected format of line ending, e.g. empty (any line ending), LF or CRLF. +expected-line-ending-format= + +# Regexp for a line that is allowed to be longer than the limit. +ignore-long-lines=^\s*(# )??$ + +# Number of spaces of indent required inside a hanging or continued line. +indent-after-paren=4 + +# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 +# tab). +indent-string=' ' + +# Maximum number of characters on a single line. +max-line-length=200 + +# Maximum number of lines in a module +max-module-lines=1000 + +# List of optional constructs for which whitespace checking is disabled. `dict- +# separator` is used to allow tabulation in dicts, etc.: {1 : 1,\n222: 2}. +# `trailing-comma` allows a space between comma and closing bracket: (a, ). +# `empty-line` allows space-only lines. +no-space-check=trailing-comma, + dict-separator + +# Allow the body of a class to be on the same line as the declaration if body +# contains single statement. +single-line-class-stmt=no + +# Allow the body of an if to be on the same line as the test if there is no +# else. +single-line-if-stmt=no + + +[LOGGING] + +# Logging modules to check that the string format arguments are in logging +# function parameter format +logging-modules=logging + + +[MISCELLANEOUS] + +# List of note tags to take in consideration, separated by a comma. +notes=FIXME, + XXX, + TODO + + +[SIMILARITIES] + +# Ignore comments when computing similarities. +ignore-comments=yes + +# Ignore docstrings when computing similarities. +ignore-docstrings=yes + +# Ignore imports when computing similarities. +ignore-imports=no + +# Minimum lines number of a similarity. +min-similarity-lines=4 + + +[SPELLING] + +# Limits count of emitted suggestions for spelling mistakes +max-spelling-suggestions=4 + +# Spelling dictionary name. Available dictionaries: none. To make it working +# install python-enchant package. +spelling-dict= + +# List of comma separated words that should not be checked. +spelling-ignore-words= + +# A path to a file that contains private dictionary; one word per line. +spelling-private-dict-file= + +# Tells whether to store unknown words to indicated private dictionary in +# --spelling-private-dict-file option instead of raising a message. +spelling-store-unknown-words=no + + +[TYPECHECK] + +# List of decorators that produce context managers, such as +# contextlib.contextmanager. Add to this list to register other decorators that +# produce valid context managers. +contextmanager-decorators=contextlib.contextmanager + +# List of members which are set dynamically and missed by pylint inference +# system, and so shouldn't trigger E1101 when accessed. Python regular +# expressions are accepted. +generated-members= + +# Tells whether missing members accessed in mixin class should be ignored. A +# mixin class is detected if its name ends with "mixin" (case insensitive). +ignore-mixin-members=yes + +# This flag controls whether pylint should warn about no-member and similar +# checks whenever an opaque object is returned when inferring. The inference +# can return multiple potential results while evaluating a Python object, but +# some branches might not be evaluated, which results in partial inference. In +# that case, it might be useful to still emit no-member and other checks for +# the rest of the inferred objects. +ignore-on-opaque-inference=yes + +# List of class names for which member attributes should not be checked (useful +# for classes with dynamically set attributes). This supports the use of +# qualified names. +ignored-classes=optparse.Values,thread._local,_thread._local + +# List of module names for which member attributes should not be checked +# (useful for modules/projects where namespaces are manipulated during runtime +# and thus existing member attributes cannot be deduced by static analysis. It +# supports qualified module names, as well as Unix pattern matching. +ignored-modules= + +# Show a hint with possible names when a member name was not found. The aspect +# of finding the hint is based on edit distance. +missing-member-hint=yes + +# The minimum edit distance a name should have in order to be considered a +# similar match for a missing member name. +missing-member-hint-distance=1 + +# The total number of similar names that should be taken in consideration when +# showing a hint for a missing member. +missing-member-max-choices=1 + + +[VARIABLES] + +# List of additional names supposed to be defined in builtins. Remember that +# you should avoid to define new builtins when possible. +additional-builtins= + +# Tells whether unused global variables should be treated as a violation. +allow-global-unused-variables=yes + +# List of strings which can identify a callback function by name. A callback +# name must start or end with one of those strings. +callbacks=cb_, + _cb + +# A regular expression matching the name of dummy variables (i.e. expectedly +# not used). +dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$) + +# Argument names that match this expression will be ignored. Default to name +# with leading underscore +ignored-argument-names=_.*|^sSentence|^dTags|^bCondMemo|^sCountry|^nLastToken|^sx?$|^m$|^dTokenPos + +# Tells whether we should check for unused import in __init__ files. +init-import=no + +# List of qualified module names which can have objects that can redefine +# builtins. +redefining-builtins-modules=six.moves,past.builtins,future.builtins,io,builtins + + +[CLASSES] + +# List of method names used to declare (i.e. assign) instance attributes. +defining-attr-methods=__init__, + __new__, + setUp + +# List of member names, which should be excluded from the protected access +# warning. +exclude-protected=_asdict, + _fields, + _replace, + _source, + _make + +# List of valid names for the first argument in a class method. +valid-classmethod-first-arg=cls + +# List of valid names for the first argument in a metaclass class method. +valid-metaclass-classmethod-first-arg=mcs + + +[DESIGN] + +# Maximum number of arguments for function / method +max-args=16 + +# Maximum number of attributes for a class (see R0902). +max-attributes=40 + +# Maximum number of boolean expressions in a if statement +max-bool-expr=5 + +# Maximum number of branch for function / method body +max-branches=30 + +# Maximum number of locals for function / method body +max-locals=40 + +# Maximum number of parents for a class (see R0901). +max-parents=7 + +# Maximum number of public methods for a class (see R0904). +max-public-methods=30 + +# Maximum number of return / yield for function / method body +max-returns=20 + +# Maximum number of statements in function / method body +max-statements=50 + +# Minimum number of public methods for a class (see R0903). +min-public-methods=2 + + +[IMPORTS] + +# Allow wildcard imports from modules that define __all__. +allow-wildcard-with-all=no + +# Analyse import fallback blocks. This can be used to support both Python 2 and +# 3 compatible code, which means that the block might have code that exists +# only in one or another interpreter, leading to false positives when analysed. +analyse-fallback-blocks=no + +# Deprecated modules which should not be used, separated by a comma +deprecated-modules=optparse,tkinter.tix + +# Create a graph of external dependencies in the given file (report RP0402 must +# not be disabled) +ext-import-graph= + +# Create a graph of every (i.e. internal and external) dependencies in the +# given file (report RP0402 must not be disabled) +import-graph= + +# Create a graph of internal dependencies in the given file (report RP0402 must +# not be disabled) +int-import-graph= + +# Force import order to recognize a module as part of the standard +# compatibility libraries. +known-standard-library= + +# Force import order to recognize a module as part of a third party library. +known-third-party=enchant + + +[EXCEPTIONS] + +# Exceptions that will emit a warning when being caught. Defaults to +# "Exception" +overgeneral-exceptions=Exception