python/python-LTTL
SHA256
15
0
Fork 0
forked from pool/python-LTTL
Code Pull Requests Activity

- Add patch remove-future-requirement.patch, drop requirement on future

Browse Source 
- Switch to pyproject and autosetup macros
- Remove skips, unneeded
- Stop using greedy globs in %files

OBS-URL: https://build.opensuse.org/package/show/devel:languages:python/python-LTTL?expand=0&rev=11
This commit is contained in:
Steve Kowalik
2023-09-11 07:08:18 +00:00
committed by Git OBS Bridge
parent 530380b589
commit bd7a2ca053
3 changed files with 529 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
python-LTTL.changes
View File

@@ -1,3 +1,11 @@
-------------------------------------------------------------------
Mon Sep 11 07:07:11 UTC 2023 - Steve Kowalik <steven.kowalik@suse.com>
- Add patch remove-future-requirement.patch, drop requirement on future
- Switch to pyproject and autosetup macros
- Remove skips, unneeded
- Stop using greedy globs in %files
-------------------------------------------------------------------
Sat Feb 13 09:50:39 UTC 2021 - Dirk Müller <dmueller@suse.com>

19
python-LTTL.spec
View File

@@ -1,7 +1,7 @@
#
# spec file for package python-LTTL
#
# Copyright (c) 2021 SUSE LLC
# Copyright (c) 2023 SUSE LLC
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
@@ -16,9 +16,6 @@
#
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
%define skip_python2 1
%define skip_python36 1
Name: python-LTTL
Version: 2.0.12
Release: 0
@@ -26,16 +23,17 @@ Summary: Library for text processing and analysis
License: GPL-3.0-only
URL: https://github.com/axanthos/LTTL
Source: https://files.pythonhosted.org/packages/source/L/LTTL/LTTL-%{version}.zip
Patch0: remove-future-requirement.patch
BuildRequires: %{python_module pip}
BuildRequires: %{python_module setuptools}
BuildRequires: %{python_module wheel}
BuildRequires: fdupes
BuildRequires: python-rpm-macros
BuildRequires: unzip
Requires: python-future
Requires: python-numpy
Requires: python-scipy
BuildArch: noarch
# SECTION test requirements
BuildRequires: %{python_module future}
BuildRequires: %{python_module numpy}
BuildRequires: %{python_module pytest}
BuildRequires: %{python_module scipy}
@@ -46,14 +44,14 @@ BuildRequires: %{python_module scipy}
LangTech Text Library (LTTL) for text processing and analysis
%prep
%setup -q -n LTTL-%{version}
%autosetup -p1 -n LTTL-%{version}
sed -i 's/\r$//' README.rst
%build
%python_build
%pyproject_wheel
%install
%python_install
%pyproject_install
%python_expand %fdupes %{buildroot}%{$python_sitelib}
%check
@@ -62,6 +60,7 @@ sed -i 's/\r$//' README.rst
%files %{python_files}
%doc README.rst
%license LICENSE
%{python_sitelib}/*
%{python_sitelib}/LTTL
%{python_sitelib}/LTTL-%{version}.dist-info
%changelog

512
remove-future-requirement.patch Normal file
View File

@@ -0,0 +1,512 @@
Index: LTTL-2.0.12/LTTL/Segmentation.py
===================================================================
--- LTTL-2.0.12.orig/LTTL/Segmentation.py
+++ LTTL-2.0.12/LTTL/Segmentation.py
@@ -22,8 +22,6 @@ from __future__ import unicode_literals
import numpy as np
-from future.utils import iteritems
-
import re
import os
@@ -131,7 +129,7 @@ def cleanup_segmentation(segmentation):
def clone_chunks(source, dst):
"""Copy all chunks related to a given "source" segmentation
and associate them with a given "dst" segmentation."""
- for k, v in iteritems(segments_cache):
+ for k, v in segments_cache.items():
if k[0] == source:
s = get_chunk(k[0], k[1])
add_chunk(dst, k[1], s.copy())
@@ -339,7 +337,7 @@ class Segmentation(object):
def get_annotation_tab(self, segment):
annotations_id = list()
- for key, value in iteritems(segment.annotations):
+ for key, value in segment.annotations.items():
self.add_annotation_tuple((key, value))
annotations_id.append(
[
Index: LTTL-2.0.12/LTTL/Table.py
===================================================================
--- LTTL-2.0.12.orig/LTTL/Table.py
+++ LTTL-2.0.12/LTTL/Table.py
@@ -38,10 +38,6 @@ import os
import math
import sys
-from builtins import str as text
-from future.utils import iteritems
-from past.builtins import xrange
-
__version__ = "1.0.5"
@@ -140,7 +136,7 @@ class Table(object):
output_string = self.header_col_id + col_delimiter
# Convert col headers to unicode strings and output...
- output_string += col_delimiter.join(text(i) for i in self.col_ids)
+ output_string += col_delimiter.join(str(i) for i in self.col_ids)
# Add Orange 2 table headers if needed...
if output_orange_headers:
@@ -162,7 +158,7 @@ class Table(object):
if self.missing is None:
missing = ''
else:
- missing = text(self.missing)
+ missing = str(self.missing)
# Format row strings...
row_strings = (
@@ -172,7 +168,7 @@ class Table(object):
col_delimiter,
col_delimiter.join(
[
- text(self.values.get((row_id, col_id), missing))
+ str(self.values.get((row_id, col_id), missing))
for col_id in self.col_ids
]
)
@@ -225,7 +221,7 @@ class Table(object):
# For each col header...
for col_id in ordered_cols:
# Convert it to string
- str_col_id = text(col_id)
+ str_col_id = str(col_id)
col_type = col_type_for_id(col_id)
if col_type == 'string':
var = Orange.data.StringVariable(str_col_id)
@@ -247,13 +243,13 @@ class Table(object):
values = list()
if col_id == self.header_col_id:
for row_id in self.row_ids:
- value = text(row_id)
+ value = str(row_id)
if value not in values:
values.append(value)
else:
for row_id in self.row_ids:
if (row_id, col_id) in self.values:
- value = text(self.values[(row_id, col_id)])
+ value = str(self.values[(row_id, col_id)])
if value not in values:
values.append(value)
var = Orange.data.DiscreteVariable(
@@ -267,7 +263,7 @@ class Table(object):
# Create Orange 3 domain and table
domain = Orange.data.Domain(attr_vars, class_vars, meta_vars)
if self.missing is not None:
- missing = text(self.missing)
+ missing = str(self.missing)
else:
missing = None
rows = []
@@ -285,7 +281,7 @@ class Table(object):
if isinstance(value, int):
# Assume all column values are of the same type
col_var.number_of_decimals = 0
- value = text(value)
+ value = str(value)
else:
value = missing
row_data.append(value)
@@ -326,7 +322,7 @@ class Table(object):
for col_id in ordered_cols:
# Convert it to string and encode as specified...
- str_col_id = text(col_id)
+ str_col_id = str(col_id)
encoded_col_id = str_col_id.encode(
encoding,
errors='xmlcharrefreplace',
@@ -354,7 +350,7 @@ class Table(object):
else:
for row_id in self.row_ids:
if (row_id, col_id) in self.values:
- value = text(self.values[(row_id, col_id)])
+ value = str(self.values[(row_id, col_id)])
value = value.encode(
encoding,
errors='xmlcharrefreplace',
@@ -375,7 +371,7 @@ class Table(object):
if self.missing is None:
missing = '?'
if self.missing is not None:
- missing = text(self.missing)
+ missing = str(self.missing)
# Store values in each row...
for row_id in self.row_ids:
@@ -386,7 +382,7 @@ class Table(object):
else:
value = self.values.get((row_id, col_id), missing)
if value:
- value = text(value).encode(
+ value = str(value).encode(
encoding,
errors='xmlcharrefreplace',
)
@@ -579,7 +575,7 @@ class PivotCrosstab(Crosstab):
new_col_ids,
dict(
(tuple(reversed(key)), count)
- for key, count in iteritems(self.values)
+ for key, count in self.values.items()
),
self.header_col_id,
self.header_col_type,
@@ -665,8 +661,8 @@ class PivotCrosstab(Crosstab):
np_table.fill(self.missing or 0)
# Fill and return numpy table...
- for row_idx in xrange(len(self.row_ids)):
- for col_idx in xrange(len(self.col_ids)):
+ for row_idx in range(len(self.row_ids)):
+ for col_idx in range(len(self.col_ids)):
try:
np_table[row_idx][col_idx] = self.values[
(self.row_ids[row_idx], self.col_ids[col_idx])
@@ -896,7 +892,7 @@ class IntPivotCrosstab(PivotCrosstab):
for col_id in col_ids
]
row_total = sum(row_values)
- for col_idx in xrange(len(col_ids)):
+ for col_idx in range(len(col_ids)):
freq_under_indep = row_total * col_total[col_idx]
if freq_under_indep > 0:
new_values[(row_id, col_ids[col_idx])] = (
@@ -998,7 +994,7 @@ class IntPivotCrosstab(PivotCrosstab):
output_matrix = np.dot(pi_inv, np.dot(exchange, pi_inv))
col_ids = self.col_ids
values = dict()
- for col_id_idx1 in xrange(len(col_ids)):
+ for col_id_idx1 in range(len(col_ids)):
col_id1 = col_ids[col_id_idx1]
values.update(
dict(
@@ -1006,7 +1002,7 @@ class IntPivotCrosstab(PivotCrosstab):
(col_id1, col_ids[i]),
output_matrix[col_id_idx1, i]
)
- for i in xrange(len(col_ids))
+ for i in range(len(col_ids))
)
)
if progress_callback:
@@ -1050,8 +1046,8 @@ class IntPivotCrosstab(PivotCrosstab):
for row_id in self.row_ids:
for col_id in self.col_ids:
count = get_count((row_id, col_id), 0)
- for i in xrange(count):
- new_row_id = text(row_counter)
+ for i in range(count):
+ new_row_id = str(row_counter)
new_row_ids.append(new_row_id)
new_values[(new_row_id, first_col_id)] = col_id
if num_row_ids > 1:
@@ -1194,7 +1190,7 @@ class FlatCrosstab(Crosstab):
known_pair_row_id = row_id_for_pair[pair]
new_values[(known_pair_row_id, '__weight__')] += 1
else:
- new_row_id = text(row_counter)
+ new_row_id = str(row_counter)
new_row_ids.append(new_row_id)
row_id_for_pair[pair] = new_row_id
new_values[(new_row_id, first_col_id)] = first_col_value
@@ -1212,7 +1208,7 @@ class FlatCrosstab(Crosstab):
known_value_row_id = row_id_for_value[col_value]
new_values[(known_value_row_id, '__weight__')] += 1
else:
- new_row_id = text(row_counter)
+ new_row_id = str(row_counter)
new_row_ids.append(new_row_id)
row_id_for_value[col_value] = new_row_id
new_values[(new_row_id, col_id)] = col_value
@@ -1344,8 +1340,8 @@ class IntWeightedFlatCrosstab(WeightedFl
count = self.values[(row_id, '__weight__')]
first_col_value = self.values[row_id, first_col_id]
second_col_value = self.values[row_id, second_col_id]
- for i in xrange(count):
- new_row_id = text(row_counter)
+ for i in range(count):
+ new_row_id = str(row_counter)
new_row_ids.append(new_row_id)
new_values[(new_row_id, first_col_id)] = first_col_value
new_values[(new_row_id, second_col_id)] = second_col_value
@@ -1357,8 +1353,8 @@ class IntWeightedFlatCrosstab(WeightedFl
for row_id in self.row_ids:
count = self.values[(row_id, '__weight__')]
col_value = self.values[row_id, col_id]
- for i in xrange(count):
- new_row_id = text(row_counter)
+ for i in range(count):
+ new_row_id = str(row_counter)
new_row_ids.append(new_row_id)
new_values[(new_row_id, col_id)] = col_value
row_counter += 1
Index: LTTL-2.0.12/LTTL/Utils.py
===================================================================
--- LTTL-2.0.12.orig/LTTL/Utils.py
+++ LTTL-2.0.12/LTTL/Utils.py
@@ -34,15 +34,9 @@ from __future__ import division
from __future__ import absolute_import
from __future__ import unicode_literals
-from future.utils import iteritems, itervalues
-from builtins import range, chr
-
import random, math
-try:
- from functools import lru_cache
-except ImportError:
- from backports.functools_lru_cache import lru_cache
+from functools import lru_cache
try:
from scipy.special import comb as binom
@@ -69,8 +63,8 @@ def sample_dict(dictionary, sample_size)
"""Return a randomly sampled frequency dict"""
new_dict = dict()
num_to_sample = sample_size
- num_to_process = sum(itervalues(dictionary))
- for (k, v) in iteritems(dictionary):
+ num_to_process = sum(dictionary.values())
+ for (k, v) in dictionary.items():
for i in range(v):
if random.random() < num_to_sample / num_to_process:
new_dict[k] = new_dict.get(k, 0) + 1
@@ -101,14 +95,14 @@ def get_variety(
else:
category_dict = dict()
if not unit_weighting and not category_weighting:
- for (k, v) in iteritems(dictionary):
+ for (k, v) in dictionary.items():
(category, unit) = k.split(category_delimiter, 1)
category_dict[category] = category_dict.get(category, 0) + v
return (len(dictionary) / len(category_dict))
else:
units_in_category_dict = dict()
unit_dict = dict()
- for (k, v) in iteritems(dictionary):
+ for (k, v) in dictionary.items():
(category, unit) = k.split(category_delimiter, 1)
category_dict[category] = category_dict.get(category, 0) + v
units_in_category_dict[(category, unit,)] = (
@@ -179,7 +173,7 @@ def tuple_to_simple_dict(dictionary, key
"""
return dict(
(k[1], v)
- for (k, v) in iteritems(dictionary)
+ for (k, v) in dictionary.items()
if k[0] == key and v > 0
)
@@ -192,7 +186,7 @@ def tuple_to_simple_dict_transpose(dicti
"""
return dict(
(k[0], v)
- for (k, v) in iteritems(dictionary)
+ for (k, v) in dictionary.items()
if k[1] == key and v > 0
)
@@ -226,7 +220,7 @@ def get_perplexity(dictionary):
"""Compute the perplexity (=exp entropy) of a dictionary"""
my_sum = 0
weighted_sum_of_logs = 0
- for freq in itervalues(dictionary):
+ for freq in dictionary.values():
if freq:
my_sum += freq
weighted_sum_of_logs += freq * math.log(freq)
Index: LTTL-2.0.12/LTTL/Processor.py
===================================================================
--- LTTL-2.0.12.orig/LTTL/Processor.py
+++ LTTL-2.0.12/LTTL/Processor.py
@@ -24,8 +24,6 @@ from __future__ import absolute_import
from __future__ import unicode_literals
from math import sqrt
-from builtins import range
-from builtins import str as text
import numpy as np
@@ -385,7 +383,7 @@ def count_in_window(
# Update main counts...
freq = dict(
- [(('1', k), v) for (k, v) in iteritems(window_freq)]
+ [(('1', k), v) for (k, v) in window_freq.items()]
)
if progress_callback:
@@ -418,14 +416,14 @@ def count_in_window(
# Get window type...
window_type = window_index + 1
- window_str = text(window_type)
+ window_str = str(window_type)
# Update main counts...
freq.update(
dict(
[
((window_str, k), v)
- for (k, v) in iteritems(window_freq)
+ for (k, v) in window_freq.items()
]
)
)
@@ -447,7 +445,7 @@ def count_in_window(
# Update main counts...
freq = dict(
- [(('1', k), v) for (k, v) in iteritems(window_freq)]
+ [(('1', k), v) for (k, v) in window_freq.items()]
)
if progress_callback:
@@ -468,13 +466,13 @@ def count_in_window(
# Get window type...
window_type = window_index + 1
- window_str = text(window_type)
+ window_str = str(window_type)
# Update main counts...
freq.update(
dict(
[
((window_str, k), v)
- for (k, v) in iteritems(window_freq)
+ for (k, v) in window_freq.items()
]
)
)
@@ -485,7 +483,7 @@ def count_in_window(
# Create pivot crosstab...
return (
IntPivotCrosstab(
- [text(i) for i in range(1, window_type + 1)],
+ [str(i) for i in range(1, window_type + 1)],
unit_types,
freq,
'__unit__',
@@ -566,7 +564,7 @@ def count_in_chain(
# Get the list of units in final format (content or annotation)...
if unit_annotation_key is not None:
unit_list = [
- text(
+ str(
unit_token.annotations.get(
unit_annotation_key,
'__none__', # Default annotation
@@ -943,7 +941,7 @@ def length_in_context(
]
values = dict(
(key, value)
- for key, value in iteritems(values)
+ for key, value in values.items()
if key[0] in context_types
)
@@ -1063,7 +1061,7 @@ def length_in_window(
sum_squares / window_size -
average * average
)
- window_str = text(window_type)
+ window_str = str(window_type)
values[(window_str, '__length_average__')] = average
values[(window_str, '__length_std_deviation__')] = stdev
values[(window_str, '__length_count__')] = window_size
@@ -1115,7 +1113,7 @@ def length_in_window(
# Compute and store average and standard deviation...
average = sum_values / window_size
- window_str = text(window_type)
+ window_str = str(window_type)
values[(window_str, '__length_average__')] = average
values[(window_str, '__length_count__')] = window_size
@@ -1132,7 +1130,7 @@ def length_in_window(
# Create Table...
return (
Table(
- [text(i) for i in range(1, window_type + 1)],
+ [str(i) for i in range(1, window_type + 1)],
col_ids,
values,
'__col__',
@@ -1779,7 +1777,7 @@ def annotate_contexts(
else:
new_values[(row_id, '__annotation__')] = (
multiple_values['value_delimiter'].join(
- text(a) for a in annotations
+ str(a) for a in annotations
)
)
@@ -2073,7 +2071,7 @@ def neighbors(
)
else:
string_value = left_token.get_content()
- new_values[(row_id, text(pos) + 'L')] = \
+ new_values[(row_id, str(pos) + 'L')] = \
string_value
right_index = context_index + pos
if right_index < len(context_segmentation):
@@ -2089,7 +2087,7 @@ def neighbors(
)
else:
string_value = right_token.get_content()
- new_values[(row_id, text(pos) + 'R')] = \
+ new_values[(row_id, str(pos) + 'R')] = \
string_value
if progress_callback:
@@ -2097,9 +2095,9 @@ def neighbors(
# Create table...
col_ids = ['__pos__']
- col_ids.extend([text(p) + 'L' for p in reversed(adjacent_positions)])
+ col_ids.extend([str(p) + 'L' for p in reversed(adjacent_positions)])
col_ids.append('__key_segment__')
- col_ids.extend([text(p) + 'R' for p in adjacent_positions])
+ col_ids.extend([str(p) + 'R' for p in adjacent_positions])
if unit_annotation_key is not None and units['separate_annotation']:
col_ids.append(unit_annotation_key)
col_types = dict([(p, 'string') for p in col_ids])
@@ -2333,10 +2331,10 @@ def cooc_in_context(
row_labels = contingency.row_ids
row_labels2 = contingency2.row_ids
keep_from_contingency = [
- i for i in xrange(len(row_labels)) if row_labels[i] in row_labels2
+ i for i in range(len(row_labels)) if row_labels[i] in row_labels2
]
keep_from_contingency2 =[
- i for i in xrange(len(row_labels2)) if row_labels2[i] in row_labels
+ i for i in range(len(row_labels2)) if row_labels2[i] in row_labels
]
try:
np_contingency = np_contingency[keep_from_contingency].astype(int)
Index: LTTL-2.0.12/setup.py
===================================================================
--- LTTL-2.0.12.orig/setup.py
+++ LTTL-2.0.12/setup.py
@@ -73,11 +73,8 @@ setup(
packages=find_packages(exclude=['docs', 'tests', 'bugs']),
install_requires=[
- 'setuptools',
'numpy',
'scipy',
- 'future',
- 'backports.functools_lru_cache',
],
test_suite='nose.collector',