ltk-data 1.2.4__tar.gz → 1.2.5__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {ltk_data-1.2.4 → ltk_data-1.2.5}/PKG-INFO +1 -1
- ltk_data-1.2.5/ltk_data/__env__.py +44 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/__init__.py +4 -0
- ltk_data-1.2.5/ltk_data/path.py +18 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data.egg-info/PKG-INFO +1 -1
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data.egg-info/SOURCES.txt +1 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/pyproject.toml +1 -1
- ltk_data-1.2.4/ltk_data/path.py +0 -50
- {ltk_data-1.2.4 → ltk_data-1.2.5}/LICENSE +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/MANIFEST.in +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/compile.py +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/__init__.py +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/crubadan/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/crubadan/de-3grams.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/crubadan/en-3grams.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/crubadan/es-3grams.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/crubadan/fr-3grams.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/crubadan/table.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/names/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/names/family +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/names/female +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/names/male +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/stopwords/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/stopwords/english +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/stopwords/french +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/stopwords/german +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/words/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/words/en +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/corpora/words/en-basic +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Close_Punctuation.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Currency_Symbol.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/IsAlnum.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/IsAlpha.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/IsLower.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/IsN.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/IsSc.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/IsSo.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/IsUpper.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Line_Separator.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Number.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Open_Punctuation.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Punctuation.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Separator.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/misc/perluniprops/Symbol.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt/PY3/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/README +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/abbrev_types.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/collocations.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/ortho_context.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/sent_starters.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/abbrev_types.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/collocations.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/ortho_context.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/sent_starters.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/abbrev_types.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/collocations.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/ortho_context.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/sent_starters.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/greek/abbrev_types.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/greek/collocations.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/greek/ortho_context.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/greek/sent_starters.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/abbrev_types.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/collocations.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/ortho_context.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/sent_starters.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/abbrev_types.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/collocations.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/ortho_context.tab +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/sent_starters.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/utils.py +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data.egg-info/dependency_links.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data.egg-info/requires.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data.egg-info/top_level.txt +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/setup.cfg +0 -0
- {ltk_data-1.2.4 → ltk_data-1.2.5}/tests/test_setup.py +0 -0
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
import os
|
|
2
|
+
import pathlib
|
|
3
|
+
|
|
4
|
+
import utilo
|
|
5
|
+
|
|
6
|
+
ROOT = os.path.abspath(utilo.join(os.path.dirname(__file__), '..'))
|
|
7
|
+
# nltk requires env setup before first import
|
|
8
|
+
LTK_DATA = utilo.join(ROOT, 'ltk_data/data')
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
def make_private(path):
|
|
12
|
+
"""Do not allow other user to change content which is pickeld later.
|
|
13
|
+
|
|
14
|
+
NLTK
|
|
15
|
+
UserWarning: NLTK will not authorize the non-private download directory
|
|
16
|
+
|
|
17
|
+
In short, ~0o022 means preserve all existing permissions except
|
|
18
|
+
group-write and others-write.
|
|
19
|
+
|
|
20
|
+
Original: 0o777
|
|
21
|
+
Mask: ~0o022
|
|
22
|
+
Result: 0o755
|
|
23
|
+
"""
|
|
24
|
+
root = pathlib.Path(path)
|
|
25
|
+
for item in root.rglob("*"):
|
|
26
|
+
utilo.debug(item)
|
|
27
|
+
os.chmod(item, os.stat(item).st_mode & ~0o022)
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
def update_env(path):
|
|
31
|
+
utilo.exists_assert(path)
|
|
32
|
+
seperator = os.pathsep
|
|
33
|
+
before = os.environ.get('NLTK_DATA', '')
|
|
34
|
+
if path in before:
|
|
35
|
+
utilo.error(f'path {path} already in os.env[NLTK_DATA]')
|
|
36
|
+
return
|
|
37
|
+
if before:
|
|
38
|
+
before += seperator
|
|
39
|
+
current = f'{before}{path}'
|
|
40
|
+
os.environ['NLTK_DATA'] = current
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
make_private(LTK_DATA)
|
|
44
|
+
update_env(LTK_DATA)
|
|
@@ -12,6 +12,8 @@ import os
|
|
|
12
12
|
|
|
13
13
|
import utilo
|
|
14
14
|
|
|
15
|
+
import ltk_data.__env__
|
|
16
|
+
|
|
15
17
|
__version__ = importlib.metadata.version('ltk_data')
|
|
16
18
|
|
|
17
19
|
ROOT = os.path.abspath(utilo.join(os.path.dirname(__file__), '..'))
|
|
@@ -22,6 +24,8 @@ from ltk_data.utils import pickler # isort:skip
|
|
|
22
24
|
from ltk_data.utils import load_pickle # isort:skip
|
|
23
25
|
from ltk_data.utils import picklepath # isort:skip
|
|
24
26
|
from ltk_data.path import add_nltk_path # isort:skip
|
|
27
|
+
from ltk_data.__env__ import make_private
|
|
28
|
+
from ltk_data.__env__ import update_env
|
|
25
29
|
from ltk_data.compile import compile_names
|
|
26
30
|
|
|
27
31
|
# nltk requires env setup before first import
|
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
# =============================================================================
|
|
2
|
+
# C O P Y R I G H T
|
|
3
|
+
# -----------------------------------------------------------------------------
|
|
4
|
+
# Copyright (c) 2021-2022 by Helmut Konrad Fahrendholz. All rights reserved.
|
|
5
|
+
# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
|
|
6
|
+
# use or distribution is an offensive act against international law and may
|
|
7
|
+
# be prosecuted under federal law. Its content is company confidential.
|
|
8
|
+
# =============================================================================
|
|
9
|
+
|
|
10
|
+
import utilo
|
|
11
|
+
|
|
12
|
+
import ltk_data
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
def add_nltk_path(path: str):
|
|
16
|
+
utilo.exists_assert(path)
|
|
17
|
+
ltk_data.update_env(path)
|
|
18
|
+
ltk_data.make_private(path)
|
ltk_data-1.2.4/ltk_data/path.py
DELETED
|
@@ -1,50 +0,0 @@
|
|
|
1
|
-
# =============================================================================
|
|
2
|
-
# C O P Y R I G H T
|
|
3
|
-
# -----------------------------------------------------------------------------
|
|
4
|
-
# Copyright (c) 2021-2022 by Helmut Konrad Fahrendholz. All rights reserved.
|
|
5
|
-
# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
|
|
6
|
-
# use or distribution is an offensive act against international law and may
|
|
7
|
-
# be prosecuted under federal law. Its content is company confidential.
|
|
8
|
-
# =============================================================================
|
|
9
|
-
|
|
10
|
-
import os
|
|
11
|
-
import pathlib
|
|
12
|
-
|
|
13
|
-
import utilo
|
|
14
|
-
|
|
15
|
-
|
|
16
|
-
def add_nltk_path(path: str):
|
|
17
|
-
utilo.exists_assert(path)
|
|
18
|
-
make_private(path)
|
|
19
|
-
seperator = os.pathsep
|
|
20
|
-
before = os.environ.get('NLTK_DATA', '')
|
|
21
|
-
if before:
|
|
22
|
-
before += seperator
|
|
23
|
-
current = f'{before}{path}'
|
|
24
|
-
os.environ['NLTK_DATA'] = current
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
READ_WRITE_EXECUTE = 0o700
|
|
28
|
-
READ_WRITE = 0o600
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
def make_private(path):
|
|
32
|
-
"""Do not allow other user to change content which is pickeld later.
|
|
33
|
-
|
|
34
|
-
NLTK
|
|
35
|
-
UserWarning: NLTK will not authorize the non-private download directory
|
|
36
|
-
|
|
37
|
-
In short, ~0o022 means preserve all existing permissions except
|
|
38
|
-
group-write and others-write.
|
|
39
|
-
|
|
40
|
-
Original: 0o777
|
|
41
|
-
Mask: ~0o022
|
|
42
|
-
Result: 0o755
|
|
43
|
-
"""
|
|
44
|
-
root = pathlib.Path(path)
|
|
45
|
-
for item in root.rglob("*"):
|
|
46
|
-
if item.is_file():
|
|
47
|
-
item.chmod(READ_WRITE)
|
|
48
|
-
continue
|
|
49
|
-
os.chmod(path, os.stat(path).st_mode & ~0o022)
|
|
50
|
-
os.chmod(path, os.stat(path).st_mode & ~0o022)
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/abbrev_types.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/collocations.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/ortho_context.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/english/sent_starters.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/abbrev_types.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/collocations.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/ortho_context.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/french/sent_starters.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/abbrev_types.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/collocations.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/ortho_context.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/german/sent_starters.txt
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/greek/ortho_context.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/greek/sent_starters.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/abbrev_types.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/collocations.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/ortho_context.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/italian/sent_starters.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/abbrev_types.txt
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/collocations.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/ortho_context.tab
RENAMED
|
File without changes
|
{ltk_data-1.2.4 → ltk_data-1.2.5}/ltk_data/data/tokenizers/punkt_tab/spanish/sent_starters.txt
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|