TableNode.split_by_new_lines() - Code Metrics - Inspection of "SDoc-60: \label doesn't work for tables" - SDoc/py-sdoc - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#47)

by Oleg

created 2016-09-01 14:32 UTC

TableNode.split_by_new_lines() D

↳ Parent: TableNode

Complexity

Conditions

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	1
CRAP Score	57.3016

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
dl	0
loc	24
ccs	1
cts	12
cp	0.0833
rs	4.3478
c	1
b	0
f	0
cc	8
crap	57.3016

"""
SDoc

Copyright 2016 Set Based IT Consultancy

Licence MIT
"""
# ----------------------------------------------------------------------------------------------------------------------
import csv
import io
import re

from sdoc.sdoc2 import in_scope, out_scope
from sdoc.sdoc2.helper.Enumerable import Enumerable
from sdoc.sdoc2.node.LabelNode import LabelNode
from sdoc.sdoc2.NodeStore import NodeStore
from sdoc.sdoc2.node.Node import Node


class TableNode(Node):
    """
    SDoc2 node for table.
    """

    # ------------------------------------------------------------------------------------------------------------------
    def __init__(self, in_out, options):
        """
        Object constructor.

        :param None|cleo.styles.output_style.OutputStyle in_out: The IO object.
        :param dict[str,str] options: The options of this table.
        """
        super().__init__(in_out, 'table', options)

        self.rows = []
        """
        The table rows.

        :type: list[list[str]]
        """

        self.column_headers = []
        """
        The column headers of the table (if any).

        :type: list[str]
        """

        self.alignments = []
        """
        The text alignments in the table columns.

        :type: list[str|None]
        """

    # ------------------------------------------------------------------------------------------------------------------
    def get_command(self):
        """
        Returns the command of this node, i.e. table.

        :rtype: str
        """
        return 'table'

    # ------------------------------------------------------------------------------------------------------------------
    def is_block_command(self):
        """
        Returns True.

        :rtype: bool
        """
        return True

    # ------------------------------------------------------------------------------------------------------------------
    def is_inline_command(self):
        """
        Returns False.

        :rtype: bool
        """
        return False

    # ------------------------------------------------------------------------------------------------------------------
    def number(self, numbers):
        """
        Numbers all numerable nodes such as chapters, sections, figures, and, items.

        :param dict[str,sdoc.sdoc2.helper.Enumerable.Enumerable] numbers: The current numbers.
        """
        if 'table' not in numbers:
            numbers['table'] = Enumerable()
            numbers['table'].generate_numeration(1)
            numbers['table'].increment_last_level()
        else:
            numbers['table'].increment_last_level()

        self._options['number'] = numbers['table'].get_string()

        super().number(numbers)

    # ------------------------------------------------------------------------------------------------------------------
    def prepare_content_tree(self):
        """
        Prepares this node for further processing.
        """
        table_nodes = []

        for node_id in self.child_nodes:
            node = in_scope(node_id)

            if not isinstance(node, LabelNode):
                table_nodes.append(node)
            else:
                self.setup_label(node)

            node.prepare_content_tree()

            out_scope(node)

        self.generate_table(table_nodes)

    # ------------------------------------------------------------------------------------------------------------------
    def setup_label(self, node):
        """
        Sets the data of a label to current table.

        :param sdoc.sdoc2.node.LabelNode.LabelNode node: The label node.
        """
        self._options['id'] = node.argument

    # ------------------------------------------------------------------------------------------------------------------
    def generate_table(self, nodes):
        """
        Generates the table node.

        :param list[sdoc.sdoc2.node.Node.Node] nodes: The list with nodes.
        """
        table_data = TableNode.divide_text_nodes(nodes)

        splitted_data = TableNode.split_by_new_lines(table_data)

        rows = self.generate_output_rows(splitted_data)

        if self.has_header(rows):
            self.column_headers = rows[0]
            self.rows = rows[2:]
            self.alignments = self.get_column_alignments(rows[1])
        else:
            self.rows = rows

    # ------------------------------------------------------------------------------------------------------------------
    @staticmethod
    def divide_text_nodes(nodes):
        """
        Divides text nodes from other type of nodes.

        :param: list[mixed] nodes: The list with nodes.

        :rtype: list[mixed]
        """
        table_data = []
        table_text_repr = ''

        for node in nodes:
            if node.get_command() == 'TEXT':
                table_text_repr += node.argument
            else:
                table_data.append(table_text_repr)
                table_data.append(node)
                table_text_repr = ''

        if table_text_repr:
            table_data.append(table_text_repr)

        return table_data

    # ------------------------------------------------------------------------------------------------------------------
    @staticmethod
    def split_by_new_lines(table_data):
        """
        Splits data by newline symbols.

        :param list[mixed] table_data:

        :rtype: list[mixed]
        """
        splitted_data = []

        for data in table_data:
            if isinstance(data, str):
                splitted_data.append(data.split('\n'))
            else:
                splitted_data.append(data)

        for data in splitted_data:
            if isinstance(data, list):
                for element in data:
                    if element.isspace() or element == '':
                        data.remove(element)

        return splitted_data

    # ------------------------------------------------------------------------------------------------------------------
    def generate_output_rows(self, splitted_data):
        """
        Generates the rows for final representation.

        :param list[mixed] splitted_data: The splitted data.

        :rtype: list[list[mixed]]
        """
        separated_data = TableNode.split_by_vertical_separators(splitted_data)

        rows = []

        for item in separated_data:
            row = []

            for data in item:
                if data and isinstance(data, str) and not data.isspace():
                    string = io.StringIO(data)
                    self.parse_vertical_separators(string, row)
                else:
                    row.append(data)

            if row:
                rows.append(row)

        return rows

    # ------------------------------------------------------------------------------------------------------------------
    @staticmethod
    def split_by_vertical_separators(splitted_data):
        """
        Splits data by vertical separators and creates rows with data.

        :param list[mixed] splitted_data: The splitted data.

        :rtype: list[list[mixed]]
        """
        rows = []
        row = []

        for item in splitted_data:
            # If we have a list we pass for each element.
            # In list we have only text elements.
            if isinstance(item, list):
                for element in item:

                    # If element starts with '|' we just add element to row.
                    if element.strip().startswith('|'):
                        row.append(element)

                    # If element ends with '|' we add row to rows list, reset row to empty list
                    # and append there current element. We do it because we know that if string ends with '|',
                    # after it we have non-text element.
                    elif element.strip().endswith('|'):
                        row = TableNode.reset_data(row, rows)
                        row.append(element)

                    # If we have element which not starts and not ends in '|' we do this block.
                    else:
                        # If last added element of row is not string we add row to rows list, reset row to empty.
                        if row and not isinstance(row[-1], str):
                            row = TableNode.reset_data(row, rows)
                        # And just add full element with text like a row to list of rows.
                        rows.append([element])

            # Do this block if element is not a list.
            else:
                # If last added element not ends with '|' we add row to rows list, and reset row to empty list.
                if row and not row[-1].strip().endswith('|'):
                    row = TableNode.reset_data(row, rows)
                # Add item to row.
                row.append(item)

        return rows

    # ------------------------------------------------------------------------------------------------------------------
    @staticmethod
    def reset_data(row, rows):
        """
        Appends row with data to list of rows, and clear row from any elements.

        Warning! This method changes original list 'rows'.

        :param list[mixed] row: The row with elements
        :param list[list[mixed]] rows: The list with many rows.
        """
        rows.append(row)
        return []

    # ------------------------------------------------------------------------------------------------------------------
    def parse_vertical_separators(self, string, row):
        """
        Splits row by vertical separator for future output.

        :param str string: The string which we will separate.
        :param list[mixed] row: The list with the row in which we append data.
        """
        reader = csv.reader(string, delimiter='|')
        for line in reader:
            new_row = self.prune_whitespace(line)

            for item in new_row:
                if item:
                    row.append(item)

    # ------------------------------------------------------------------------------------------------------------------
    @staticmethod
    def has_header(rows):
        """
        Returns True if the table has a table header.

        :param list[str] rows: The second row of the table.

        :rtype: bool
        """
        is_header = True

        if len(rows) == 1:
            return False

        for align in rows[1]:
            header_part = re.findall(':?---+-*:?', align)
            if not header_part:
                is_header = False
                break

        return is_header

    # ------------------------------------------------------------------------------------------------------------------
    @staticmethod
    def get_column_alignments(row):
        """
        Sets alignments on table columns.

        :param list[str] row: The row with hyphens for creating column headers.

        :rtype: list[str]
        """
        alignments = []
        for hyphens in row:
            hyphens = hyphens.strip()
            if hyphens.startswith(':') and hyphens.endswith(':'):
                alignments.append('center')
            elif hyphens.startswith(':'):
                alignments.append('left')
            elif hyphens.endswith(':'):
                alignments.append('right')
            else:
                alignments.append('')

        return alignments

    # ------------------------------------------------------------------------------------------------------------------
    @staticmethod
    def prune_whitespace(row):
        """
        Strips whitespaces from the text of an each cell.

        :param list[str] row: The row with text of an each cell.
        :rtype: list[str]
        """
        clear_row = []
        for item in row:
            clear_text = item.strip()
            clear_text = re.sub(r'\s+', ' ', clear_text)
            clear_row.append(clear_text)

        return clear_row


# ----------------------------------------------------------------------------------------------------------------------
NodeStore.register_block_command('table', TableNode)


1		"""
2		SDoc
3
4		Copyright 2016 Set Based IT Consultancy
5
6		Licence MIT
7		"""
8		# ----------------------------------------------------------------------------------------------------------------------
9	1	import csv
10	1	import io
11	1	import re
12
13	1	from sdoc.sdoc2 import in_scope, out_scope
14	1	from sdoc.sdoc2.helper.Enumerable import Enumerable
15	1	from sdoc.sdoc2.node.LabelNode import LabelNode
16	1	from sdoc.sdoc2.NodeStore import NodeStore
17	1	from sdoc.sdoc2.node.Node import Node
18
19
20	1	class TableNode(Node):
21		"""
22		SDoc2 node for table.
23		"""
24
25		# ------------------------------------------------------------------------------------------------------------------
26	1	def __init__(self, in_out, options):
27		"""
28		Object constructor.
29
30		:param None\|cleo.styles.output_style.OutputStyle in_out: The IO object.
31		:param dict[str,str] options: The options of this table.
32		"""
33		super().__init__(in_out, 'table', options)
34
35		self.rows = []
36		"""
37		The table rows.
38
39		:type: list[list[str]]
40		"""
41
42		self.column_headers = []
43		"""
44		The column headers of the table (if any).
45
46		:type: list[str]
47		"""
48
49		self.alignments = []
50		"""
51		The text alignments in the table columns.
52
53		:type: list[str\|None]
54		"""
55
56		# ------------------------------------------------------------------------------------------------------------------
57	1	def get_command(self):
58		"""
59		Returns the command of this node, i.e. table.
60
61		:rtype: str
62		"""
63		return 'table'
64
65		# ------------------------------------------------------------------------------------------------------------------
66	1	def is_block_command(self):
67		"""
68		Returns True.
69
70		:rtype: bool
71		"""
72		return True
73
74		# ------------------------------------------------------------------------------------------------------------------
75	1	def is_inline_command(self):
76		"""
77		Returns False.
78
79		:rtype: bool
80		"""
81		return False
82
83		# ------------------------------------------------------------------------------------------------------------------
84	1	def number(self, numbers):
85		"""
86		Numbers all numerable nodes such as chapters, sections, figures, and, items.
87
88		:param dict[str,sdoc.sdoc2.helper.Enumerable.Enumerable] numbers: The current numbers.
89		"""
90		if 'table' not in numbers:
91		numbers['table'] = Enumerable()
92		numbers['table'].generate_numeration(1)
93		numbers['table'].increment_last_level()
94		else:
95		numbers['table'].increment_last_level()
96
97		self._options['number'] = numbers['table'].get_string()
98
99		super().number(numbers)
100
101		# ------------------------------------------------------------------------------------------------------------------
102	1	def prepare_content_tree(self):
103		"""
104		Prepares this node for further processing.
105		"""
106		table_nodes = []
107
108		for node_id in self.child_nodes:
109		node = in_scope(node_id)
110
111		if not isinstance(node, LabelNode):
112		table_nodes.append(node)
113		else:
114		self.setup_label(node)
115
116		node.prepare_content_tree()
117
118		out_scope(node)
119
120		self.generate_table(table_nodes)
121
122		# ------------------------------------------------------------------------------------------------------------------
123	1	def setup_label(self, node):
124		"""
125		Sets the data of a label to current table.
126
127		:param sdoc.sdoc2.node.LabelNode.LabelNode node: The label node.
128		"""
129		self._options['id'] = node.argument
130
131		# ------------------------------------------------------------------------------------------------------------------
132	1	def generate_table(self, nodes):
133		"""
134		Generates the table node.
135
136		:param list[sdoc.sdoc2.node.Node.Node] nodes: The list with nodes.
137		"""
138		table_data = TableNode.divide_text_nodes(nodes)
139
140		splitted_data = TableNode.split_by_new_lines(table_data)
141
142		rows = self.generate_output_rows(splitted_data)
143
144		if self.has_header(rows):
145		self.column_headers = rows[0]
146		self.rows = rows[2:]
147		self.alignments = self.get_column_alignments(rows[1])
148		else:
149		self.rows = rows
150
151		# ------------------------------------------------------------------------------------------------------------------
152	1	@staticmethod
153		def divide_text_nodes(nodes):
154		"""
155		Divides text nodes from other type of nodes.
156
157		:param: list[mixed] nodes: The list with nodes.
158
159		:rtype: list[mixed]
160		"""
161		table_data = []
162		table_text_repr = ''
163
164		for node in nodes:
165		if node.get_command() == 'TEXT':
166		table_text_repr += node.argument
167		else:
168		table_data.append(table_text_repr)
169		table_data.append(node)
170		table_text_repr = ''
171
172		if table_text_repr:
173		table_data.append(table_text_repr)
174
175		return table_data
176
177		# ------------------------------------------------------------------------------------------------------------------
178	1	@staticmethod
179		def split_by_new_lines(table_data):
180		"""
181		Splits data by newline symbols.
182
183		:param list[mixed] table_data:
184
185		:rtype: list[mixed]
186		"""
187		splitted_data = []
188
189		for data in table_data:
190		if isinstance(data, str):
191		splitted_data.append(data.split('\n'))
192		else:
193		splitted_data.append(data)
194
195		for data in splitted_data:
196		if isinstance(data, list):
197		for element in data:
198		if element.isspace() or element == '':
199		data.remove(element)
200
201		return splitted_data
202
203		# ------------------------------------------------------------------------------------------------------------------
204	1	def generate_output_rows(self, splitted_data):
205		"""
206		Generates the rows for final representation.
207
208		:param list[mixed] splitted_data: The splitted data.
209
210		:rtype: list[list[mixed]]
211		"""
212		separated_data = TableNode.split_by_vertical_separators(splitted_data)
213
214		rows = []
215
216		for item in separated_data:
217		row = []
218
219		for data in item:
220		if data and isinstance(data, str) and not data.isspace():
221		string = io.StringIO(data)
222		self.parse_vertical_separators(string, row)
223		else:
224		row.append(data)
225
226		if row:
227		rows.append(row)
228
229		return rows
230
231		# ------------------------------------------------------------------------------------------------------------------
232	1	@staticmethod
233		def split_by_vertical_separators(splitted_data):
234		"""
235		Splits data by vertical separators and creates rows with data.
236
237		:param list[mixed] splitted_data: The splitted data.
238
239		:rtype: list[list[mixed]]
240		"""
241		rows = []
242		row = []
243
244		for item in splitted_data:
245		# If we have a list we pass for each element.
246		# In list we have only text elements.
247		if isinstance(item, list):
248		for element in item:
249
250		# If element starts with '\|' we just add element to row.
251		if element.strip().startswith('\|'):
252		row.append(element)
253
254		# If element ends with '\|' we add row to rows list, reset row to empty list
255		# and append there current element. We do it because we know that if string ends with '\|',
256		# after it we have non-text element.
257		elif element.strip().endswith('\|'):
258		row = TableNode.reset_data(row, rows)
259		row.append(element)
260
261		# If we have element which not starts and not ends in '\|' we do this block.
262		else:
263		# If last added element of row is not string we add row to rows list, reset row to empty.
264		if row and not isinstance(row[-1], str):
265		row = TableNode.reset_data(row, rows)
266		# And just add full element with text like a row to list of rows.
267		rows.append([element])
268
269		# Do this block if element is not a list.
270		else:
271		# If last added element not ends with '\|' we add row to rows list, and reset row to empty list.
272		if row and not row[-1].strip().endswith('\|'):
273		row = TableNode.reset_data(row, rows)
274		# Add item to row.
275		row.append(item)
276
277		return rows
278
279		# ------------------------------------------------------------------------------------------------------------------
280	1	@staticmethod
281		def reset_data(row, rows):
282		"""
283		Appends row with data to list of rows, and clear row from any elements.
284
285		Warning! This method changes original list 'rows'.
286
287		:param list[mixed] row: The row with elements
288		:param list[list[mixed]] rows: The list with many rows.
289		"""
290		rows.append(row)
291		return []
292
293		# ------------------------------------------------------------------------------------------------------------------
294	1	def parse_vertical_separators(self, string, row):
295		"""
296		Splits row by vertical separator for future output.
297
298		:param str string: The string which we will separate.
299		:param list[mixed] row: The list with the row in which we append data.
300		"""
301		reader = csv.reader(string, delimiter='\|')
302		for line in reader:
303		new_row = self.prune_whitespace(line)
304
305		for item in new_row:
306		if item:
307		row.append(item)
308
309		# ------------------------------------------------------------------------------------------------------------------
310	1	@staticmethod
311		def has_header(rows):
312		"""
313		Returns True if the table has a table header.
314
315		:param list[str] rows: The second row of the table.
316
317		:rtype: bool
318		"""
319		is_header = True
320
321		if len(rows) == 1:
322		return False
323
324		for align in rows[1]:
325		header_part = re.findall(':?---+-*:?', align)
326		if not header_part:
327		is_header = False
328		break
329
330		return is_header
331
332		# ------------------------------------------------------------------------------------------------------------------
333	1	@staticmethod
334		def get_column_alignments(row):
335		"""
336		Sets alignments on table columns.
337
338		:param list[str] row: The row with hyphens for creating column headers.
339
340		:rtype: list[str]
341		"""
342		alignments = []
343		for hyphens in row:
344		hyphens = hyphens.strip()
345		if hyphens.startswith(':') and hyphens.endswith(':'):
346		alignments.append('center')
347		elif hyphens.startswith(':'):
348		alignments.append('left')
349		elif hyphens.endswith(':'):
350		alignments.append('right')
351		else:
352		alignments.append('')
353
354		return alignments
355
356		# ------------------------------------------------------------------------------------------------------------------
357	1	@staticmethod
358		def prune_whitespace(row):
359		"""
360		Strips whitespaces from the text of an each cell.
361
362		:param list[str] row: The row with text of an each cell.
363		:rtype: list[str]
364		"""
365		clear_row = []
366		for item in row:
367		clear_text = item.strip()
368		clear_text = re.sub(r'\s+', ' ', clear_text)
369		clear_row.append(clear_text)
370
371		return clear_row
372
373
374		# ----------------------------------------------------------------------------------------------------------------------
375		NodeStore.register_block_command('table', TableNode)
376

SDoc / py-sdoc

Pull Request — master (#47)

TableNode.split_by_new_lines() D

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like