Code Duplication - OCR-D/core - Measure and Improve Code Quality continuously with Scrutinizer

Code Duplication Length = 25-25 lines in 2 locations

src/ocrd_page_user_methods/get_AllTextLines.py 1 location


def get_AllTextLines(self, region_order='document', respect_textline_order=True):
    """
    Return all the TextLine in the document

    Arguments:
        region_order ("document"|"reading-order"|"reading-order-only"): Whether to \
            return regions sorted by document order (``document``, default) or by \
            reading order with regions not in the reading order at the end of the \
            returned list (``reading-order``) or regions not in the reading order \
            omitted (``reading-order-only``)
        respect_textline_order (boolean): Whether to respect `@textLineOrder` attribute

    Returns:
        a list of :py:class:`TextLineType`
    """
    # TODO handle textLineOrder according to https://github.com/PRImA-Research-Lab/PAGE-XML/issues/26
    ret = []
    for reg in self.get_AllRegions(['Text'], order=region_order):
        lines = reg.get_TextLine()
        if not respect_textline_order:
            ret += lines
        else:
            lo = reg.get_textLineOrder() or self.get_textLineOrder() or 'top-to-bottom'
            ret += lines if lo in ['top-to-bottom', 'left-to-right'] else list(reversed(lines))
    return ret



src/ocrd_models/ocrd_page_generateds.py 1 location


        """
        self.invalidate_AlternativeImage(feature_selector='cropped')
        self.Border = Border
    def get_AllTextLines(self, region_order='document', respect_textline_order=True):
        """
        Return all the TextLine in the document
    
        Arguments:
            region_order ("document"|"reading-order"|"reading-order-only"): Whether to \
                return regions sorted by document order (``document``, default) or by \
                reading order with regions not in the reading order at the end of the \
                returned list (``reading-order``) or regions not in the reading order \
                omitted (``reading-order-only``)
            respect_textline_order (boolean): Whether to respect `@textLineOrder` attribute
    
        Returns:
            a list of :py:class:`TextLineType`
        """
        # TODO handle textLineOrder according to https://github.com/PRImA-Research-Lab/PAGE-XML/issues/26
        ret = []
        for reg in self.get_AllRegions(['Text'], order=region_order):
            lines = reg.get_TextLine()
            if not respect_textline_order:
                ret += lines
            else:
                lo = reg.get_textLineOrder() or self.get_textLineOrder() or 'top-to-bottom'
                ret += lines if lo in ['top-to-bottom', 'left-to-right'] else list(reversed(lines))
        return ret
    
    def get_ReadingOrderGroups(self) -> dict:
        """

		@@ 3895-3919 (lines=25) @@
3892		"""
3893		self.invalidate_AlternativeImage(feature_selector='cropped')
3894		self.Border = Border
3895		def get_AllTextLines(self, region_order='document', respect_textline_order=True):
3896		"""
3897		Return all the TextLine in the document
3898
3899		Arguments:
3900		region_order ("document"\|"reading-order"\|"reading-order-only"): Whether to \
3901		return regions sorted by document order (``document``, default) or by \
3902		reading order with regions not in the reading order at the end of the \
3903		returned list (``reading-order``) or regions not in the reading order \
3904		omitted (``reading-order-only``)
3905		respect_textline_order (boolean): Whether to respect `@textLineOrder` attribute
3906
3907		Returns:
3908		a list of :py:class:`TextLineType`
3909		"""
3910		# TODO handle textLineOrder according to https://github.com/PRImA-Research-Lab/PAGE-XML/issues/26
3911		ret = []
3912		for reg in self.get_AllRegions(['Text'], order=region_order):
3913		lines = reg.get_TextLine()
3914		if not respect_textline_order:
3915		ret += lines
3916		else:
3917		lo = reg.get_textLineOrder() or self.get_textLineOrder() or 'top-to-bottom'
3918		ret += lines if lo in ['top-to-bottom', 'left-to-right'] else list(reversed(lines))
3919		return ret
3920
3921		def get_ReadingOrderGroups(self) -> dict:
3922		"""

		@@ 1-25 (lines=25) @@
1		def get_AllTextLines(self, region_order='document', respect_textline_order=True):
2		"""
3		Return all the TextLine in the document
4
5		Arguments:
6		region_order ("document"\|"reading-order"\|"reading-order-only"): Whether to \
7		return regions sorted by document order (``document``, default) or by \
8		reading order with regions not in the reading order at the end of the \
9		returned list (``reading-order``) or regions not in the reading order \
10		omitted (``reading-order-only``)
11		respect_textline_order (boolean): Whether to respect `@textLineOrder` attribute
12
13		Returns:
14		a list of :py:class:`TextLineType`
15		"""
16		# TODO handle textLineOrder according to https://github.com/PRImA-Research-Lab/PAGE-XML/issues/26
17		ret = []
18		for reg in self.get_AllRegions(['Text'], order=region_order):
19		lines = reg.get_TextLine()
20		if not respect_textline_order:
21		ret += lines
22		else:
23		lo = reg.get_textLineOrder() or self.get_textLineOrder() or 'top-to-bottom'
24		ret += lines if lo in ['top-to-bottom', 'left-to-right'] else list(reversed(lines))
25		return ret
26
27

OCR-D / core

Code Duplication Length = 25-25 lines in 2 locations

src/ocrd_page_user_methods/get_AllTextLines.py 1 location

src/ocrd_models/ocrd_page_generateds.py 1 location