6507626273

Committed 13 Oct 2023 11:25AM UTC coverage: 42.006% (-53.7%) from 95.72%

Build # 6507626273

Build Type

Pull #433

github

Committed by

odscjames

Commit Message

New "Geo" optional dependencies

https://github.com/OpenDataServices/flatten-tool/issues/424

Pull Request Pull Request #433: New "Geo" optional dependencies

Run Details

38 of 38 new or added lines in 6 files covered. (100.0%)

1466 of 3490 relevant lines covered (42.01%)

4.16 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

21.43

/flattentool/ODSReader.py

# Copyright 2011 Marco Conti

# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at

#     http://www.apache.org/licenses/LICENSE-2.0

# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Thanks to grt for the fixes
# https://github.com/marcoconti83/read-ods-with-odfpy

from collections import OrderedDict
from datetime import datetime

import odf.opendocument
from odf.table import Table, TableCell, TableRow

# Backport for datetime.fromisoformat, which is new in Python 3.7
try:
    _ = datetime.fromisoformat
except AttributeError:
    import backports.datetime_fromisoformat

    backports.datetime_fromisoformat.MonkeyPatch.patch_fromisoformat()


# http://stackoverflow.com/a/4544699/1846474
class GrowingList(list):
    def __setitem__(self, index, value):
        if index >= len(self):
            self.extend([None] * (index + 1 - len(self)))
        list.__setitem__(self, index, value)


class ODSReader:

    # loads the file
    def __init__(self, file, clonespannedcolumns=None):
        self.clonespannedcolumns = clonespannedcolumns
        self.doc = odf.opendocument.load(file)
        self.SHEETS = OrderedDict()
        for sheet in self.doc.spreadsheet.getElementsByType(Table):
            self.readSheet(sheet)

    # reads a sheet in the sheet dictionary, storing each sheet as an
    # array (rows) of arrays (columns)
    def readSheet(self, sheet):
        name = sheet.getAttribute("name")
        rows = sheet.getElementsByType(TableRow)
        arrRows = []

        # for each row
        for row in rows:
            row_comment = ""  # noqa
            arrCells = GrowingList()
            cells = row.getElementsByType(TableCell)

            # for each cell
            count = 0
            for cell in cells:
                # repeated value?
                repeat = cell.getAttribute("numbercolumnsrepeated")
                if not repeat:
                    repeat = 1
                    spanned = int(cell.getAttribute("numbercolumnsspanned") or 0)
                    # clone spanned cells
                    if self.clonespannedcolumns is not None and spanned > 1:
                        repeat = spanned

                for rr in range(int(repeat)):  # repeated?
                    if str(cell):
                        value_type = cell.attributes.get(
                            (
                                "urn:oasis:names:tc:opendocument:xmlns:office:1.0",
                                "value-type",
                            )
                        )
                        if value_type == "float":
                            value = cell.attributes.get(
                                (
                                    "urn:oasis:names:tc:opendocument:xmlns:office:1.0",
                                    "value",
                                )
                            )
                            if "." in str(value):
                                arrCells[count] = float(value)
                            else:
                                arrCells[count] = int(value)
                        elif value_type == "date":
                            date_value = cell.attributes.get(
                                (
                                    "urn:oasis:names:tc:opendocument:xmlns:office:1.0",
                                    "date-value",
                                )
                            )
                            # fromisoformat assumes microseconds appear as 3 or
                            # 6 digits, whereas ods drops trailing 0s, so can
                            # have 1-6 digits, so pad some extra 0s
                            if "." in date_value:
                                date_value = date_value.ljust(26, "0")
                            arrCells[count] = datetime.fromisoformat(date_value)
                        else:
                            arrCells[count] = str(cell)
                    count += 1

            arrRows.append(arrCells)

        self.SHEETS[name] = arrRows

    # returns a sheet as an array (rows) of arrays (columns)
    def getSheet(self, name):
        return self.SHEETS[name]

1	# Copyright 2011 Marco Conti
2
3	# Licensed under the Apache License, Version 2.0 (the "License");
4	# you may not use this file except in compliance with the License.
5	# You may obtain a copy of the License at
6
7	# http://www.apache.org/licenses/LICENSE-2.0
8
9	# Unless required by applicable law or agreed to in writing, software
10	# distributed under the License is distributed on an "AS IS" BASIS,
11	# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12	# See the License for the specific language governing permissions and
13	# limitations under the License.
14
15	# Thanks to grt for the fixes
16	# https://github.com/marcoconti83/read-ods-with-odfpy
17
18	from collections import OrderedDict	10✔
19	from datetime import datetime	10✔
20
21	import odf.opendocument	10✔
22	from odf.table import Table, TableCell, TableRow	10✔
23
24	# Backport for datetime.fromisoformat, which is new in Python 3.7
25	try:	10✔
26	_ = datetime.fromisoformat	10✔
27	except AttributeError:	×
28	import backports.datetime_fromisoformat	×
29
30	backports.datetime_fromisoformat.MonkeyPatch.patch_fromisoformat()	×
31
32
33	# http://stackoverflow.com/a/4544699/1846474
34	class GrowingList(list):	10✔
35	def __setitem__(self, index, value):	10✔
36	if index >= len(self):	×
37	self.extend([None] * (index + 1 - len(self)))	×
38	list.__setitem__(self, index, value)	×
39
40
41	class ODSReader:	10✔
42
43	# loads the file
44	def __init__(self, file, clonespannedcolumns=None):	10✔
45	self.clonespannedcolumns = clonespannedcolumns	×
46	self.doc = odf.opendocument.load(file)	×
47	self.SHEETS = OrderedDict()	×
48	for sheet in self.doc.spreadsheet.getElementsByType(Table):	×
49	self.readSheet(sheet)	×
50
51	# reads a sheet in the sheet dictionary, storing each sheet as an
52	# array (rows) of arrays (columns)
53	def readSheet(self, sheet):	10✔
54	name = sheet.getAttribute("name")	×
55	rows = sheet.getElementsByType(TableRow)	×
56	arrRows = []	×
57
58	# for each row
59	for row in rows:	×
60	row_comment = "" # noqa	×
61	arrCells = GrowingList()	×
62	cells = row.getElementsByType(TableCell)	×
63
64	# for each cell
65	count = 0	×
66	for cell in cells:	×
67	# repeated value?
68	repeat = cell.getAttribute("numbercolumnsrepeated")	×
69	if not repeat:	×
70	repeat = 1	×
71	spanned = int(cell.getAttribute("numbercolumnsspanned") or 0)	×
72	# clone spanned cells
73	if self.clonespannedcolumns is not None and spanned > 1:	×
74	repeat = spanned	×
75
76	for rr in range(int(repeat)): # repeated?	×
77	if str(cell):	×
78	value_type = cell.attributes.get(	×
79	(
80	"urn:oasis:names:tc:opendocument:xmlns:office:1.0",
81	"value-type",
82	)
83	)
84	if value_type == "float":	×
85	value = cell.attributes.get(	×
86	(
87	"urn:oasis:names:tc:opendocument:xmlns:office:1.0",
88	"value",
89	)
90	)
91	if "." in str(value):	×
92	arrCells[count] = float(value)	×
93	else:
94	arrCells[count] = int(value)	×
95	elif value_type == "date":	×
96	date_value = cell.attributes.get(	×
97	(
98	"urn:oasis:names:tc:opendocument:xmlns:office:1.0",
99	"date-value",
100	)
101	)
102	# fromisoformat assumes microseconds appear as 3 or
103	# 6 digits, whereas ods drops trailing 0s, so can
104	# have 1-6 digits, so pad some extra 0s
105	if "." in date_value:	×
106	date_value = date_value.ljust(26, "0")	×
107	arrCells[count] = datetime.fromisoformat(date_value)	×
108	else:
109	arrCells[count] = str(cell)	×
110	count += 1	×
111
112	arrRows.append(arrCells)	×
113
114	self.SHEETS[name] = arrRows	×
115
116	# returns a sheet as an array (rows) of arrays (columns)
117	def getSheet(self, name):	10✔
118	return self.SHEETS[name]	×

OpenDataServices / flatten-tool / 6507626273

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous