Python Character.set_utf8方法代码示例

# 需要导入模块: from tegaki.character import Character [as 别名]
# 或者: from tegaki.character.Character import set_utf8 [as 别名]
    def to_stroke_collection(self, dictionary, silent=True):
        """
        @type dictionary: L{CharacterStrokeDictionary
        """
        strokecol = CharacterCollection()
        for char in self.get_all_characters_gen():
            stroke_labels = dictionary.get_strokes(char.get_unicode())[0]
            strokes = char.get_writing().get_strokes(full=True)

            if len(strokes) != len(stroke_labels):
                if silent:
                    continue
                else:
                    raise ValueError, "The number of strokes doesn't " \
                                      "match with reference character"

            for stroke, label in zip(strokes, stroke_labels):
                utf8 = label.encode("utf-8")
                strokecol.add_set(utf8)
                writing = Writing()
                writing.append_stroke(stroke)
                writing.normalize_position()
                schar = Character()
                schar.set_utf8(utf8)
                schar.set_writing(writing)
                strokecol.append_character(utf8, schar)

        return strokecol

# 需要导入模块: from tegaki.character import Character [as 别名]
# 或者: from tegaki.character.Character import set_utf8 [as 别名]
    def _getCharacter(self):
        writing = self._getWriting()

        char = Character()
        char.set_writing(writing)
        char.set_utf8("A")

        return char

# 需要导入模块: from tegaki.character import Character [as 别名]
# 或者: from tegaki.character.Character import set_utf8 [as 别名]
 def set_writings(self, writings):
     """
     writings: a list of tegaki.Writing objects.
     """
     self._model.clear()
     characters = []
     for writing in writings:
         char = Character()
         char.set_writing(writing)
         char.set_utf8("?")
         characters.append(char)
     self.set_characters(characters)

# 需要导入模块: from tegaki.character import Character [as 别名]
# 或者: from tegaki.character.Character import set_utf8 [as 别名]
    def _end_element(self, name):
        if name == "kanji":
            char = Character()
            char.set_utf8(self._utf8)
            char.set_writing(self._writing)
            self._charcol.add_set(self._utf8)
            self._charcol.append_character(self._utf8, char)
            for s in ["_tag", "_stroke"]:
                if s in self.__dict__:
                    del self.__dict__[s]

        if name == "stroke":
            self._writing.append_stroke(self._stroke)
            self._stroke = None

        self._tag = None

# 需要导入模块: from tegaki.character import Character [as 别名]
# 或者: from tegaki.character.Character import set_utf8 [as 别名]
	def get_character_collection(self):
		charcol = CharacterCollection()

		# group characters with the same label into sets
		sets = {}
		for i in range(len(self._labels)):
			# Create Character
			writing = Writing()
			if self.height and self.width:
				writing.set_height(self.height)
				writing.set_width(self.width)

			for delin_range in self._delineations[i]:
				if delin_range.start_comp == (delin_range.end_comp - 1):
					stroke_points = self._strokes[delin_range.start_comp][delin_range.start_point:delin_range.end_point]
					writing.append_stroke(Stroke.from_list(stroke_points))
				else:
					# add first stroke to writing
					start_stroke_points = self._strokes[delin_range.start_comp][delin_range.start_point:-1]
					if len(start_stroke_points) > 0:
						writing.append_stroke(Stroke.from_list(start_stroke_points))

					# add last stroke to writing
					end_stroke_points = self._strokes[delin_range.end_comp - 1][0:delin_range.end_point]
					if len(end_stroke_points) > 0:
						writing.append_stroke(Stroke.from_list(end_stroke_points))

					# add the remaining strokes to writing
					for stroke in self._strokes[delin_range.start_comp + 1:delin_range.end_comp - 1]:
						writing.append_stroke(stroke)

			character = Character()
			character.set_writing(writing)

			utf8 = self._labels[i]
			character.set_utf8(utf8)

			sets[utf8] = sets.get(utf8, []) + [character]

		charcol.add_sets(sets.keys())

		for set_name, characters in sets.items():
			charcol.append_characters(set_name, characters)

		return charcol

# 需要导入模块: from tegaki.character import Character [as 别名]
# 或者: from tegaki.character.Character import set_utf8 [as 别名]

#.........这里部分代码省略.........
                    newcc.merge([self])
                    newcc.commit()
                    del newcc
                    self.bind(path)
            else:
                gzip, bz2 = _gzipbz2(path)
                self.write(path, gzip=gzip, bz2=bz2)

        self.commit()

    def to_stroke_collection(self, dictionary, silent=True):
        """
        @type dictionary: L{CharacterStrokeDictionary
        """
        strokecol = CharacterCollection()
        for char in self.get_all_characters_gen():
            stroke_labels = dictionary.get_strokes(char.get_unicode())[0]
            strokes = char.get_writing().get_strokes(full=True)

            if len(strokes) != len(stroke_labels):
                if silent:
                    continue
                else:
                    raise ValueError, "The number of strokes doesn't " \
                                      "match with reference character"

            for stroke, label in zip(strokes, stroke_labels):
                utf8 = label.encode("utf-8")
                strokecol.add_set(utf8)
                writing = Writing()
                writing.append_stroke(stroke)
                writing.normalize_position()
                schar = Character()
                schar.set_utf8(utf8)
                schar.set_writing(writing)
                strokecol.append_character(utf8, schar)

        return strokecol


    @staticmethod
    def from_character_directory(directory,
                                 extensions=["xml", "bz2", "gz"],
                                 recursive=True,
                                 check_duplicate=False):
        """
        Creates a character collection from a directory containing
        individual character files.
        """
        regexp = re.compile("\.(%s)$" % "|".join(extensions))
        charcol = CharacterCollection()

        for name in os.listdir(directory):
            full_path = os.path.join(directory, name)
            if os.path.isdir(full_path) and recursive:
                charcol += CharacterCollection.from_character_directory(
                               full_path, extensions)
            elif regexp.search(full_path):
                char = Character()
                gzip = False; bz2 = False
                if full_path.endswith(".gz"): gzip = True
                if full_path.endswith(".bz2"): bz2 = True

                try:
                    char.read(full_path, gzip=gzip, bz2=bz2)
                except ValueError: