smith-utils 0.2.1__tar.gz → 0.3.1__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.
- smith_utils-0.3.1/.gitignore +59 -0
- {smith_utils-0.2.1/src/smith_utils.egg-info → smith_utils-0.3.1}/PKG-INFO +37 -19
- {smith_utils-0.2.1 → smith_utils-0.3.1}/README.md +22 -4
- {smith_utils-0.2.1 → smith_utils-0.3.1}/pyproject.toml +17 -5
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/__init__.py +13 -0
- smith_utils-0.3.1/src/smith_utils/crypto/__init__.py +6 -0
- smith_utils-0.3.1/src/smith_utils/crypto/hashes.py +26 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/text/__init__.py +4 -0
- smith_utils-0.3.1/tests/test_hashes.py +34 -0
- smith_utils-0.3.1/tests/test_package_exports.py +22 -0
- smith_utils-0.2.1/PKG-INFO +0 -114
- smith_utils-0.2.1/setup.cfg +0 -4
- smith_utils-0.2.1/src/smith_utils.egg-info/SOURCES.txt +0 -24
- smith_utils-0.2.1/src/smith_utils.egg-info/dependency_links.txt +0 -1
- smith_utils-0.2.1/src/smith_utils.egg-info/requires.txt +0 -7
- smith_utils-0.2.1/src/smith_utils.egg-info/top_level.txt +0 -1
- {smith_utils-0.2.1 → smith_utils-0.3.1}/LICENSE +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/datetime/__init__.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/datetime/date_utils.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/numeric/__init__.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/numeric/refinement.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/text/metrics.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/text/newlines.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/text/normalization.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/src/smith_utils/text/unicode_char_names.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/tests/test_date_utils.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/tests/test_metrics.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/tests/test_newlines.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/tests/test_normalization.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/tests/test_refinement.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.1}/tests/test_unicode_char_names.py +0 -0
|
@@ -0,0 +1,59 @@
|
|
|
1
|
+
# Python artifacts
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[cod]
|
|
4
|
+
*$py.class
|
|
5
|
+
|
|
6
|
+
# Distribution / packaging
|
|
7
|
+
build/
|
|
8
|
+
develop-eggs/
|
|
9
|
+
dist/
|
|
10
|
+
downloads/
|
|
11
|
+
eggs/
|
|
12
|
+
.eggs/
|
|
13
|
+
parts/
|
|
14
|
+
sdist/
|
|
15
|
+
var/
|
|
16
|
+
wheels/
|
|
17
|
+
*.egg-info/
|
|
18
|
+
.installed.cfg
|
|
19
|
+
*.egg
|
|
20
|
+
|
|
21
|
+
# Unit test / coverage reports
|
|
22
|
+
htmlcov/
|
|
23
|
+
.tox/
|
|
24
|
+
.nox/
|
|
25
|
+
.coverage
|
|
26
|
+
.coverage.*
|
|
27
|
+
.cache
|
|
28
|
+
nosetests.xml
|
|
29
|
+
coverage.xml
|
|
30
|
+
*.cover
|
|
31
|
+
*.sved
|
|
32
|
+
.pytest_cache/
|
|
33
|
+
.ruff_cache/
|
|
34
|
+
|
|
35
|
+
# Environments
|
|
36
|
+
.env
|
|
37
|
+
.venv
|
|
38
|
+
env/
|
|
39
|
+
venv/
|
|
40
|
+
ENV/
|
|
41
|
+
env.bak/
|
|
42
|
+
venv.bak/
|
|
43
|
+
|
|
44
|
+
# IDEs and Editors
|
|
45
|
+
.idea/
|
|
46
|
+
.vscode/
|
|
47
|
+
*.swp
|
|
48
|
+
*.swo
|
|
49
|
+
|
|
50
|
+
# Project specific
|
|
51
|
+
legacy/
|
|
52
|
+
*.log
|
|
53
|
+
|
|
54
|
+
# Documentation
|
|
55
|
+
docs/_build/
|
|
56
|
+
docs/source/generated/
|
|
57
|
+
|
|
58
|
+
# Misc
|
|
59
|
+
scripts/
|
|
@@ -1,7 +1,11 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: smith-utils
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.3.1
|
|
4
4
|
Summary: A utility library for data cleaning and parsing.
|
|
5
|
+
Project-URL: Homepage, https://github.com/yeiichi/smith-utils
|
|
6
|
+
Project-URL: Repository, https://github.com/yeiichi/smith-utils
|
|
7
|
+
Project-URL: Documentation, https://smith-utils.readthedocs.io/
|
|
8
|
+
Project-URL: Changelog, https://smith-utils.readthedocs.io/en/latest/changelog.html
|
|
5
9
|
Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
|
|
6
10
|
License: MIT License
|
|
7
11
|
|
|
@@ -24,27 +28,23 @@ License: MIT License
|
|
|
24
28
|
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
|
25
29
|
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
|
|
26
30
|
IN THE SOFTWARE.
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
Project-URL: Changelog, https://smith-utils.readthedocs.io/en/latest/changelog.html
|
|
32
|
-
Keywords: csv,deduplication,data-filtering,file-organization,filtering
|
|
31
|
+
License-File: LICENSE
|
|
32
|
+
Keywords: csv,data-filtering,deduplication,file-organization,filtering
|
|
33
|
+
Classifier: Intended Audience :: Developers
|
|
34
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
33
35
|
Classifier: Programming Language :: Python :: 3
|
|
34
36
|
Classifier: Programming Language :: Python :: 3 :: Only
|
|
35
|
-
Classifier: License :: OSI Approved :: MIT License
|
|
36
|
-
Classifier: Intended Audience :: Developers
|
|
37
37
|
Classifier: Topic :: Software Development :: Libraries
|
|
38
38
|
Classifier: Topic :: Utilities
|
|
39
39
|
Requires-Python: >=3.10
|
|
40
|
-
|
|
41
|
-
|
|
40
|
+
Provides-Extra: dev
|
|
41
|
+
Requires-Dist: pytest<9,>=8; extra == 'dev'
|
|
42
42
|
Provides-Extra: docs
|
|
43
|
-
Requires-Dist:
|
|
44
|
-
Requires-Dist:
|
|
43
|
+
Requires-Dist: furo>=2024.8.6; extra == 'docs'
|
|
44
|
+
Requires-Dist: sphinx<9,>=8; extra == 'docs'
|
|
45
45
|
Provides-Extra: release
|
|
46
|
-
Requires-Dist: python-semantic-release<10,>=9; extra ==
|
|
47
|
-
|
|
46
|
+
Requires-Dist: python-semantic-release<10,>=9; extra == 'release'
|
|
47
|
+
Description-Content-Type: text/markdown
|
|
48
48
|
|
|
49
49
|
# smith-utils
|
|
50
50
|
[](https://pypi.org/project/smith-utils/)
|
|
@@ -60,22 +60,31 @@ This package consolidates distributed utility functions to improve code reuse an
|
|
|
60
60
|
|
|
61
61
|
## Key Features
|
|
62
62
|
|
|
63
|
-
###
|
|
63
|
+
### Datetime Utilities (`smith_utils.datetime`)
|
|
64
64
|
Robust date parsing and formatting.
|
|
65
65
|
- `ensure_date`: Flexible conversion of strings, `datetime.date` objects, or `None` (returns today) into a `date` object.
|
|
66
66
|
- `parse_strict_date`: Strict parsing for `YYYYMMDD` or `YYYY-MM-DD` formats, rejecting ambiguous inputs.
|
|
67
67
|
- `format_ordinal`: Converts integers to ordinal strings (e.g., `1` → `"1st"`, `22` → `"22nd"`).
|
|
68
68
|
|
|
69
|
-
###
|
|
69
|
+
### Numeric Refinement (`smith_utils.numeric`)
|
|
70
70
|
Clean and parse messy numeric data.
|
|
71
71
|
- `parse_numeric_value`: Handles custom separators, decimals, and negative formats like `(1,234.56)`.
|
|
72
72
|
- `parse_currency_value`: Alias for numeric parsing, specifically for currency strings.
|
|
73
73
|
|
|
74
|
-
###
|
|
74
|
+
### Text Normalization & Metrics (`smith_utils.text`)
|
|
75
75
|
Standardize text and compare string similarity.
|
|
76
76
|
- `normalize_text`: Unicode NFKC normalization, case folding, and whitespace handling.
|
|
77
77
|
- `StringDistance`: Implementation of Damerau-Levenshtein and Jaro-Winkler algorithms for fuzzy matching.
|
|
78
|
+
- `analyze_pair`: Convenience function for string comparison returning a `Result`.
|
|
79
|
+
- `Relation` / `Result`: Relation enum and typed result for text comparisons.
|
|
78
80
|
- `make_unicode_char_name_records`: Extract Unicode codepoint/name metadata from text.
|
|
81
|
+
- `normalize_newlines_stream`: Stream-based newline normalization to LF with newline type detection.
|
|
82
|
+
- `normalize_file_to_lf`: File-based newline normalization helper.
|
|
83
|
+
|
|
84
|
+
### Crypto Hash Utilities (`smith_utils.crypto`)
|
|
85
|
+
Calculate SHA-256 digests for text and files.
|
|
86
|
+
- `get_text_digest`: Returns the SHA-256 hexadecimal digest for a text string.
|
|
87
|
+
- `get_file_digest`: Returns the SHA-256 hexadecimal digest for a file using streaming reads.
|
|
79
88
|
|
|
80
89
|
## Installation
|
|
81
90
|
|
|
@@ -88,8 +97,9 @@ pip install smith-utils
|
|
|
88
97
|
## Quick Start
|
|
89
98
|
|
|
90
99
|
```python
|
|
91
|
-
from smith_utils import ensure_date, parse_numeric_value, normalize_text
|
|
100
|
+
from smith_utils import ensure_date, get_text_digest, parse_numeric_value, normalize_text
|
|
92
101
|
from smith_utils import make_unicode_char_name_records
|
|
102
|
+
from smith_utils import get_file_digest, normalize_file_to_lf
|
|
93
103
|
|
|
94
104
|
# Datetime
|
|
95
105
|
date = ensure_date("20231225") # datetime.date(2023, 12, 25)
|
|
@@ -103,6 +113,14 @@ clean_text = normalize_text(" Smith Utils ") # "smith uti
|
|
|
103
113
|
# Unicode metadata
|
|
104
114
|
records = make_unicode_char_name_records("Aあ")
|
|
105
115
|
# [UnicodeCharNameRecord(index=0, codepoint='U+0041', ...), ...]
|
|
116
|
+
|
|
117
|
+
# Normalize a file's newlines to LF
|
|
118
|
+
summary = normalize_file_to_lf("input.txt", "output.txt")
|
|
119
|
+
# {'newline_type': 'CRLF', 'bytes_in': ..., 'bytes_out': ...}
|
|
120
|
+
|
|
121
|
+
# SHA-256 digests
|
|
122
|
+
text_digest = get_text_digest("smith-utils")
|
|
123
|
+
file_digest = get_file_digest("input.txt")
|
|
106
124
|
```
|
|
107
125
|
|
|
108
126
|
## Directory Structure
|
|
@@ -12,22 +12,31 @@ This package consolidates distributed utility functions to improve code reuse an
|
|
|
12
12
|
|
|
13
13
|
## Key Features
|
|
14
14
|
|
|
15
|
-
###
|
|
15
|
+
### Datetime Utilities (`smith_utils.datetime`)
|
|
16
16
|
Robust date parsing and formatting.
|
|
17
17
|
- `ensure_date`: Flexible conversion of strings, `datetime.date` objects, or `None` (returns today) into a `date` object.
|
|
18
18
|
- `parse_strict_date`: Strict parsing for `YYYYMMDD` or `YYYY-MM-DD` formats, rejecting ambiguous inputs.
|
|
19
19
|
- `format_ordinal`: Converts integers to ordinal strings (e.g., `1` → `"1st"`, `22` → `"22nd"`).
|
|
20
20
|
|
|
21
|
-
###
|
|
21
|
+
### Numeric Refinement (`smith_utils.numeric`)
|
|
22
22
|
Clean and parse messy numeric data.
|
|
23
23
|
- `parse_numeric_value`: Handles custom separators, decimals, and negative formats like `(1,234.56)`.
|
|
24
24
|
- `parse_currency_value`: Alias for numeric parsing, specifically for currency strings.
|
|
25
25
|
|
|
26
|
-
###
|
|
26
|
+
### Text Normalization & Metrics (`smith_utils.text`)
|
|
27
27
|
Standardize text and compare string similarity.
|
|
28
28
|
- `normalize_text`: Unicode NFKC normalization, case folding, and whitespace handling.
|
|
29
29
|
- `StringDistance`: Implementation of Damerau-Levenshtein and Jaro-Winkler algorithms for fuzzy matching.
|
|
30
|
+
- `analyze_pair`: Convenience function for string comparison returning a `Result`.
|
|
31
|
+
- `Relation` / `Result`: Relation enum and typed result for text comparisons.
|
|
30
32
|
- `make_unicode_char_name_records`: Extract Unicode codepoint/name metadata from text.
|
|
33
|
+
- `normalize_newlines_stream`: Stream-based newline normalization to LF with newline type detection.
|
|
34
|
+
- `normalize_file_to_lf`: File-based newline normalization helper.
|
|
35
|
+
|
|
36
|
+
### Crypto Hash Utilities (`smith_utils.crypto`)
|
|
37
|
+
Calculate SHA-256 digests for text and files.
|
|
38
|
+
- `get_text_digest`: Returns the SHA-256 hexadecimal digest for a text string.
|
|
39
|
+
- `get_file_digest`: Returns the SHA-256 hexadecimal digest for a file using streaming reads.
|
|
31
40
|
|
|
32
41
|
## Installation
|
|
33
42
|
|
|
@@ -40,8 +49,9 @@ pip install smith-utils
|
|
|
40
49
|
## Quick Start
|
|
41
50
|
|
|
42
51
|
```python
|
|
43
|
-
from smith_utils import ensure_date, parse_numeric_value, normalize_text
|
|
52
|
+
from smith_utils import ensure_date, get_text_digest, parse_numeric_value, normalize_text
|
|
44
53
|
from smith_utils import make_unicode_char_name_records
|
|
54
|
+
from smith_utils import get_file_digest, normalize_file_to_lf
|
|
45
55
|
|
|
46
56
|
# Datetime
|
|
47
57
|
date = ensure_date("20231225") # datetime.date(2023, 12, 25)
|
|
@@ -55,6 +65,14 @@ clean_text = normalize_text(" Smith Utils ") # "smith uti
|
|
|
55
65
|
# Unicode metadata
|
|
56
66
|
records = make_unicode_char_name_records("Aあ")
|
|
57
67
|
# [UnicodeCharNameRecord(index=0, codepoint='U+0041', ...), ...]
|
|
68
|
+
|
|
69
|
+
# Normalize a file's newlines to LF
|
|
70
|
+
summary = normalize_file_to_lf("input.txt", "output.txt")
|
|
71
|
+
# {'newline_type': 'CRLF', 'bytes_in': ..., 'bytes_out': ...}
|
|
72
|
+
|
|
73
|
+
# SHA-256 digests
|
|
74
|
+
text_digest = get_text_digest("smith-utils")
|
|
75
|
+
file_digest = get_file_digest("input.txt")
|
|
58
76
|
```
|
|
59
77
|
|
|
60
78
|
## Directory Structure
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
[build-system]
|
|
2
|
-
requires = ["
|
|
3
|
-
build-backend = "
|
|
2
|
+
requires = ["hatchling>=1.27"]
|
|
3
|
+
build-backend = "hatchling.build"
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "smith-utils"
|
|
7
|
-
version = "0.
|
|
7
|
+
version = "0.3.1"
|
|
8
8
|
description = "A utility library for data cleaning and parsing."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
requires-python = ">=3.10"
|
|
@@ -34,6 +34,9 @@ classifiers = [
|
|
|
34
34
|
dependencies = []
|
|
35
35
|
|
|
36
36
|
[project.optional-dependencies]
|
|
37
|
+
dev = [
|
|
38
|
+
"pytest>=8,<9",
|
|
39
|
+
]
|
|
37
40
|
docs = [
|
|
38
41
|
"sphinx>=8,<9",
|
|
39
42
|
"furo>=2024.8.6",
|
|
@@ -48,8 +51,17 @@ Repository = "https://github.com/yeiichi/smith-utils"
|
|
|
48
51
|
Documentation = "https://smith-utils.readthedocs.io/"
|
|
49
52
|
Changelog = "https://smith-utils.readthedocs.io/en/latest/changelog.html"
|
|
50
53
|
|
|
51
|
-
[tool.
|
|
52
|
-
|
|
54
|
+
[tool.hatch.build.targets.wheel]
|
|
55
|
+
packages = ["src/smith_utils"]
|
|
56
|
+
|
|
57
|
+
[tool.hatch.build.targets.sdist]
|
|
58
|
+
include = [
|
|
59
|
+
"src/smith_utils",
|
|
60
|
+
"tests",
|
|
61
|
+
"README.md",
|
|
62
|
+
"LICENSE",
|
|
63
|
+
"pyproject.toml",
|
|
64
|
+
]
|
|
53
65
|
|
|
54
66
|
[tool.semantic_release]
|
|
55
67
|
allow_zero_version = true
|
|
@@ -1,20 +1,33 @@
|
|
|
1
|
+
from .crypto import get_file_digest, get_text_digest
|
|
1
2
|
from .datetime import ensure_date, format_ordinal, parse_strict_date
|
|
2
3
|
from .numeric import parse_currency_value, parse_numeric_value
|
|
3
4
|
from .text import (
|
|
5
|
+
NewlineType,
|
|
6
|
+
Relation,
|
|
7
|
+
Result,
|
|
4
8
|
StringDistance,
|
|
5
9
|
UnicodeCharNameRecord,
|
|
6
10
|
analyze_pair,
|
|
7
11
|
make_unicode_char_name_records,
|
|
12
|
+
normalize_file_to_lf,
|
|
13
|
+
normalize_newlines_stream,
|
|
8
14
|
normalize_text,
|
|
9
15
|
)
|
|
10
16
|
|
|
11
17
|
__all__ = [
|
|
18
|
+
"NewlineType",
|
|
19
|
+
"Relation",
|
|
20
|
+
"Result",
|
|
12
21
|
"StringDistance",
|
|
13
22
|
"UnicodeCharNameRecord",
|
|
14
23
|
"analyze_pair",
|
|
15
24
|
"ensure_date",
|
|
16
25
|
"format_ordinal",
|
|
26
|
+
"get_file_digest",
|
|
27
|
+
"get_text_digest",
|
|
17
28
|
"make_unicode_char_name_records",
|
|
29
|
+
"normalize_file_to_lf",
|
|
30
|
+
"normalize_newlines_stream",
|
|
18
31
|
"normalize_text",
|
|
19
32
|
"parse_currency_value",
|
|
20
33
|
"parse_numeric_value",
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
"""Utilities for calculating SHA-256 digests."""
|
|
2
|
+
|
|
3
|
+
import hashlib
|
|
4
|
+
import sys
|
|
5
|
+
from pathlib import Path
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
def get_text_digest(text, encoding="utf-8"):
|
|
9
|
+
"""Return the SHA-256 hexadecimal digest for ``text`` encoded as ``encoding``."""
|
|
10
|
+
|
|
11
|
+
return hashlib.sha256(text.encode(encoding)).hexdigest()
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
def get_file_digest(file_path):
|
|
15
|
+
"""Return the SHA-256 hexadecimal digest for the file at ``file_path``."""
|
|
16
|
+
|
|
17
|
+
file_path = Path(file_path)
|
|
18
|
+
if sys.version_info >= (3, 11):
|
|
19
|
+
with open(file_path, "rb") as file:
|
|
20
|
+
return hashlib.file_digest(file, "sha256").hexdigest()
|
|
21
|
+
|
|
22
|
+
hasher = hashlib.sha256()
|
|
23
|
+
with open(file_path, "rb") as file:
|
|
24
|
+
while chunk := file.read(65536):
|
|
25
|
+
hasher.update(chunk)
|
|
26
|
+
return hasher.hexdigest()
|
|
@@ -1,8 +1,12 @@
|
|
|
1
1
|
from .metrics import StringDistance, analyze_pair, Result, Relation
|
|
2
|
+
from .newlines import NewlineType, normalize_file_to_lf, normalize_newlines_stream
|
|
2
3
|
from .normalization import normalize_text
|
|
3
4
|
from .unicode_char_names import UnicodeCharNameRecord, make_unicode_char_name_records
|
|
4
5
|
|
|
5
6
|
__all__ = [
|
|
7
|
+
"NewlineType",
|
|
8
|
+
"normalize_file_to_lf",
|
|
9
|
+
"normalize_newlines_stream",
|
|
6
10
|
"StringDistance",
|
|
7
11
|
"analyze_pair",
|
|
8
12
|
"Result",
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
import hashlib
|
|
2
|
+
|
|
3
|
+
from src.smith_utils import crypto
|
|
4
|
+
from src.smith_utils.crypto import hashes
|
|
5
|
+
from src.smith_utils.crypto import get_file_digest, get_text_digest
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
def test_get_file_digest_returns_sha256_hexdigest(tmp_path):
|
|
9
|
+
sample_file = tmp_path / "sample.txt"
|
|
10
|
+
content = b"smith-utils\n"
|
|
11
|
+
sample_file.write_bytes(content)
|
|
12
|
+
|
|
13
|
+
assert get_file_digest(sample_file) == hashlib.sha256(content).hexdigest()
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
def test_get_text_digest_returns_sha256_hexdigest():
|
|
17
|
+
text = "smith-utils\n"
|
|
18
|
+
|
|
19
|
+
assert get_text_digest(text) == hashlib.sha256(text.encode("utf-8")).hexdigest()
|
|
20
|
+
|
|
21
|
+
|
|
22
|
+
def test_get_text_digest_handles_unicode_text():
|
|
23
|
+
text = "こんにちは smith-utils"
|
|
24
|
+
|
|
25
|
+
assert get_text_digest(text) == hashlib.sha256(text.encode("utf-8")).hexdigest()
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
def test_crypto_package_exports_hash_functions():
|
|
29
|
+
assert "get_file_digest" in crypto.__all__
|
|
30
|
+
assert "get_text_digest" in crypto.__all__
|
|
31
|
+
assert crypto.get_file_digest is get_file_digest
|
|
32
|
+
assert crypto.get_text_digest is get_text_digest
|
|
33
|
+
assert hashes.get_file_digest is get_file_digest
|
|
34
|
+
assert hashes.get_text_digest is get_text_digest
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
from src import smith_utils
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
def test_exports_are_available_globally():
|
|
5
|
+
expected = {
|
|
6
|
+
"get_file_digest",
|
|
7
|
+
"get_text_digest",
|
|
8
|
+
"NewlineType",
|
|
9
|
+
"normalize_file_to_lf",
|
|
10
|
+
"normalize_newlines_stream",
|
|
11
|
+
"StringDistance",
|
|
12
|
+
"analyze_pair",
|
|
13
|
+
"Result",
|
|
14
|
+
"Relation",
|
|
15
|
+
"normalize_text",
|
|
16
|
+
"UnicodeCharNameRecord",
|
|
17
|
+
"make_unicode_char_name_records",
|
|
18
|
+
}
|
|
19
|
+
|
|
20
|
+
for name in expected:
|
|
21
|
+
assert hasattr(smith_utils, name), f"missing export: {name}"
|
|
22
|
+
assert name in smith_utils.__all__
|
smith_utils-0.2.1/PKG-INFO
DELETED
|
@@ -1,114 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: smith-utils
|
|
3
|
-
Version: 0.2.1
|
|
4
|
-
Summary: A utility library for data cleaning and parsing.
|
|
5
|
-
Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
|
|
6
|
-
License: MIT License
|
|
7
|
-
|
|
8
|
-
Copyright (c) 2026 Eiichi YAMAMOTO
|
|
9
|
-
|
|
10
|
-
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
11
|
-
of this software and associated documentation files (the "Software"), to deal
|
|
12
|
-
in the Software without restriction, including without limitation the rights
|
|
13
|
-
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
14
|
-
copies of the Software, and to permit persons to whom the Software is
|
|
15
|
-
furnished to do so, subject to the following conditions:
|
|
16
|
-
|
|
17
|
-
The above copyright notice and this permission notice shall be included in
|
|
18
|
-
all copies or substantial portions of the Software.
|
|
19
|
-
|
|
20
|
-
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
21
|
-
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
22
|
-
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
23
|
-
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
24
|
-
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
|
|
25
|
-
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
|
|
26
|
-
IN THE SOFTWARE.
|
|
27
|
-
|
|
28
|
-
Project-URL: Homepage, https://github.com/yeiichi/smith-utils
|
|
29
|
-
Project-URL: Repository, https://github.com/yeiichi/smith-utils
|
|
30
|
-
Project-URL: Documentation, https://smith-utils.readthedocs.io/
|
|
31
|
-
Project-URL: Changelog, https://smith-utils.readthedocs.io/en/latest/changelog.html
|
|
32
|
-
Keywords: csv,deduplication,data-filtering,file-organization,filtering
|
|
33
|
-
Classifier: Programming Language :: Python :: 3
|
|
34
|
-
Classifier: Programming Language :: Python :: 3 :: Only
|
|
35
|
-
Classifier: License :: OSI Approved :: MIT License
|
|
36
|
-
Classifier: Intended Audience :: Developers
|
|
37
|
-
Classifier: Topic :: Software Development :: Libraries
|
|
38
|
-
Classifier: Topic :: Utilities
|
|
39
|
-
Requires-Python: >=3.10
|
|
40
|
-
Description-Content-Type: text/markdown
|
|
41
|
-
License-File: LICENSE
|
|
42
|
-
Provides-Extra: docs
|
|
43
|
-
Requires-Dist: sphinx<9,>=8; extra == "docs"
|
|
44
|
-
Requires-Dist: furo>=2024.8.6; extra == "docs"
|
|
45
|
-
Provides-Extra: release
|
|
46
|
-
Requires-Dist: python-semantic-release<10,>=9; extra == "release"
|
|
47
|
-
Dynamic: license-file
|
|
48
|
-
|
|
49
|
-
# smith-utils
|
|
50
|
-
[](https://pypi.org/project/smith-utils/)
|
|
51
|
-

|
|
52
|
-

|
|
53
|
-

|
|
54
|
-

|
|
55
|
-
[](https://smith-utils.readthedocs.io/en/latest/?badge=latest)
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
**Smith Utils** is a central hub for data cleaning and parsing scripts.
|
|
59
|
-
This package consolidates distributed utility functions to improve code reuse and maintenance efficiency across all yeiichi projects.
|
|
60
|
-
|
|
61
|
-
## Key Features
|
|
62
|
-
|
|
63
|
-
### 📅 Datetime Utilities (`smith_utils.datetime`)
|
|
64
|
-
Robust date parsing and formatting.
|
|
65
|
-
- `ensure_date`: Flexible conversion of strings, `datetime.date` objects, or `None` (returns today) into a `date` object.
|
|
66
|
-
- `parse_strict_date`: Strict parsing for `YYYYMMDD` or `YYYY-MM-DD` formats, rejecting ambiguous inputs.
|
|
67
|
-
- `format_ordinal`: Converts integers to ordinal strings (e.g., `1` → `"1st"`, `22` → `"22nd"`).
|
|
68
|
-
|
|
69
|
-
### 🔢 Numeric Refinement (`smith_utils.numeric`)
|
|
70
|
-
Clean and parse messy numeric data.
|
|
71
|
-
- `parse_numeric_value`: Handles custom separators, decimals, and negative formats like `(1,234.56)`.
|
|
72
|
-
- `parse_currency_value`: Alias for numeric parsing, specifically for currency strings.
|
|
73
|
-
|
|
74
|
-
### 📝 Text Normalization & Metrics (`smith_utils.text`)
|
|
75
|
-
Standardize text and compare string similarity.
|
|
76
|
-
- `normalize_text`: Unicode NFKC normalization, case folding, and whitespace handling.
|
|
77
|
-
- `StringDistance`: Implementation of Damerau-Levenshtein and Jaro-Winkler algorithms for fuzzy matching.
|
|
78
|
-
- `make_unicode_char_name_records`: Extract Unicode codepoint/name metadata from text.
|
|
79
|
-
|
|
80
|
-
## Installation
|
|
81
|
-
|
|
82
|
-
Install via pip:
|
|
83
|
-
|
|
84
|
-
```bash
|
|
85
|
-
pip install smith-utils
|
|
86
|
-
```
|
|
87
|
-
|
|
88
|
-
## Quick Start
|
|
89
|
-
|
|
90
|
-
```python
|
|
91
|
-
from smith_utils import ensure_date, parse_numeric_value, normalize_text
|
|
92
|
-
from smith_utils import make_unicode_char_name_records
|
|
93
|
-
|
|
94
|
-
# Datetime
|
|
95
|
-
date = ensure_date("20231225") # datetime.date(2023, 12, 25)
|
|
96
|
-
|
|
97
|
-
# Numeric
|
|
98
|
-
value = parse_numeric_value("(1,250.50)") # -1250.5
|
|
99
|
-
|
|
100
|
-
# Text
|
|
101
|
-
clean_text = normalize_text(" Smith Utils ") # "smith utils"
|
|
102
|
-
|
|
103
|
-
# Unicode metadata
|
|
104
|
-
records = make_unicode_char_name_records("Aあ")
|
|
105
|
-
# [UnicodeCharNameRecord(index=0, codepoint='U+0041', ...), ...]
|
|
106
|
-
```
|
|
107
|
-
|
|
108
|
-
## Directory Structure
|
|
109
|
-
- `src/smith_utils/`: Main package source.
|
|
110
|
-
- `legacy/`: Legacy scripts and templates (not included in distribution).
|
|
111
|
-
- `tests/`: Comprehensive test suite.
|
|
112
|
-
|
|
113
|
-
## License
|
|
114
|
-
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
|
smith_utils-0.2.1/setup.cfg
DELETED
|
@@ -1,24 +0,0 @@
|
|
|
1
|
-
LICENSE
|
|
2
|
-
README.md
|
|
3
|
-
pyproject.toml
|
|
4
|
-
src/smith_utils/__init__.py
|
|
5
|
-
src/smith_utils.egg-info/PKG-INFO
|
|
6
|
-
src/smith_utils.egg-info/SOURCES.txt
|
|
7
|
-
src/smith_utils.egg-info/dependency_links.txt
|
|
8
|
-
src/smith_utils.egg-info/requires.txt
|
|
9
|
-
src/smith_utils.egg-info/top_level.txt
|
|
10
|
-
src/smith_utils/datetime/__init__.py
|
|
11
|
-
src/smith_utils/datetime/date_utils.py
|
|
12
|
-
src/smith_utils/numeric/__init__.py
|
|
13
|
-
src/smith_utils/numeric/refinement.py
|
|
14
|
-
src/smith_utils/text/__init__.py
|
|
15
|
-
src/smith_utils/text/metrics.py
|
|
16
|
-
src/smith_utils/text/newlines.py
|
|
17
|
-
src/smith_utils/text/normalization.py
|
|
18
|
-
src/smith_utils/text/unicode_char_names.py
|
|
19
|
-
tests/test_date_utils.py
|
|
20
|
-
tests/test_metrics.py
|
|
21
|
-
tests/test_newlines.py
|
|
22
|
-
tests/test_normalization.py
|
|
23
|
-
tests/test_refinement.py
|
|
24
|
-
tests/test_unicode_char_names.py
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
smith_utils
|
|
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
|