smith-utils 0.2.1__tar.gz → 0.3.0__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-0.2.1/src/smith_utils.egg-info → smith_utils-0.3.0}/PKG-INFO +10 -1
- {smith_utils-0.2.1 → smith_utils-0.3.0}/README.md +9 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/pyproject.toml +1 -1
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/__init__.py +10 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/text/__init__.py +4 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0/src/smith_utils.egg-info}/PKG-INFO +10 -1
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils.egg-info/SOURCES.txt +1 -0
- smith_utils-0.3.0/tests/test_package_exports.py +20 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/LICENSE +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/setup.cfg +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/datetime/__init__.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/datetime/date_utils.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/numeric/__init__.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/numeric/refinement.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/text/metrics.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/text/newlines.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/text/normalization.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils/text/unicode_char_names.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils.egg-info/dependency_links.txt +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils.egg-info/requires.txt +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/src/smith_utils.egg-info/top_level.txt +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/tests/test_date_utils.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/tests/test_metrics.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/tests/test_newlines.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/tests/test_normalization.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/tests/test_refinement.py +0 -0
- {smith_utils-0.2.1 → smith_utils-0.3.0}/tests/test_unicode_char_names.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: smith-utils
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.3.0
|
|
4
4
|
Summary: A utility library for data cleaning and parsing.
|
|
5
5
|
Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
|
|
6
6
|
License: MIT License
|
|
@@ -75,7 +75,11 @@ Clean and parse messy numeric data.
|
|
|
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.
|
|
79
83
|
|
|
80
84
|
## Installation
|
|
81
85
|
|
|
@@ -90,6 +94,7 @@ pip install smith-utils
|
|
|
90
94
|
```python
|
|
91
95
|
from smith_utils import ensure_date, parse_numeric_value, normalize_text
|
|
92
96
|
from smith_utils import make_unicode_char_name_records
|
|
97
|
+
from smith_utils import normalize_file_to_lf
|
|
93
98
|
|
|
94
99
|
# Datetime
|
|
95
100
|
date = ensure_date("20231225") # datetime.date(2023, 12, 25)
|
|
@@ -103,6 +108,10 @@ clean_text = normalize_text(" Smith Utils ") # "smith uti
|
|
|
103
108
|
# Unicode metadata
|
|
104
109
|
records = make_unicode_char_name_records("Aあ")
|
|
105
110
|
# [UnicodeCharNameRecord(index=0, codepoint='U+0041', ...), ...]
|
|
111
|
+
|
|
112
|
+
# Normalize a file's newlines to LF
|
|
113
|
+
summary = normalize_file_to_lf("input.txt", "output.txt")
|
|
114
|
+
# {'newline_type': 'CRLF', 'bytes_in': ..., 'bytes_out': ...}
|
|
106
115
|
```
|
|
107
116
|
|
|
108
117
|
## Directory Structure
|
|
@@ -27,7 +27,11 @@ Clean and parse messy numeric data.
|
|
|
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.
|
|
31
35
|
|
|
32
36
|
## Installation
|
|
33
37
|
|
|
@@ -42,6 +46,7 @@ pip install smith-utils
|
|
|
42
46
|
```python
|
|
43
47
|
from smith_utils import ensure_date, parse_numeric_value, normalize_text
|
|
44
48
|
from smith_utils import make_unicode_char_name_records
|
|
49
|
+
from smith_utils import normalize_file_to_lf
|
|
45
50
|
|
|
46
51
|
# Datetime
|
|
47
52
|
date = ensure_date("20231225") # datetime.date(2023, 12, 25)
|
|
@@ -55,6 +60,10 @@ clean_text = normalize_text(" Smith Utils ") # "smith uti
|
|
|
55
60
|
# Unicode metadata
|
|
56
61
|
records = make_unicode_char_name_records("Aあ")
|
|
57
62
|
# [UnicodeCharNameRecord(index=0, codepoint='U+0041', ...), ...]
|
|
63
|
+
|
|
64
|
+
# Normalize a file's newlines to LF
|
|
65
|
+
summary = normalize_file_to_lf("input.txt", "output.txt")
|
|
66
|
+
# {'newline_type': 'CRLF', 'bytes_in': ..., 'bytes_out': ...}
|
|
58
67
|
```
|
|
59
68
|
|
|
60
69
|
## Directory Structure
|
|
@@ -1,20 +1,30 @@
|
|
|
1
1
|
from .datetime import ensure_date, format_ordinal, parse_strict_date
|
|
2
2
|
from .numeric import parse_currency_value, parse_numeric_value
|
|
3
3
|
from .text import (
|
|
4
|
+
NewlineType,
|
|
5
|
+
Relation,
|
|
6
|
+
Result,
|
|
4
7
|
StringDistance,
|
|
5
8
|
UnicodeCharNameRecord,
|
|
6
9
|
analyze_pair,
|
|
7
10
|
make_unicode_char_name_records,
|
|
11
|
+
normalize_file_to_lf,
|
|
12
|
+
normalize_newlines_stream,
|
|
8
13
|
normalize_text,
|
|
9
14
|
)
|
|
10
15
|
|
|
11
16
|
__all__ = [
|
|
17
|
+
"NewlineType",
|
|
18
|
+
"Relation",
|
|
19
|
+
"Result",
|
|
12
20
|
"StringDistance",
|
|
13
21
|
"UnicodeCharNameRecord",
|
|
14
22
|
"analyze_pair",
|
|
15
23
|
"ensure_date",
|
|
16
24
|
"format_ordinal",
|
|
17
25
|
"make_unicode_char_name_records",
|
|
26
|
+
"normalize_file_to_lf",
|
|
27
|
+
"normalize_newlines_stream",
|
|
18
28
|
"normalize_text",
|
|
19
29
|
"parse_currency_value",
|
|
20
30
|
"parse_numeric_value",
|
|
@@ -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",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: smith-utils
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.3.0
|
|
4
4
|
Summary: A utility library for data cleaning and parsing.
|
|
5
5
|
Author-email: Eiichi YAMAMOTO <info@yeiichi.com>
|
|
6
6
|
License: MIT License
|
|
@@ -75,7 +75,11 @@ Clean and parse messy numeric data.
|
|
|
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.
|
|
79
83
|
|
|
80
84
|
## Installation
|
|
81
85
|
|
|
@@ -90,6 +94,7 @@ pip install smith-utils
|
|
|
90
94
|
```python
|
|
91
95
|
from smith_utils import ensure_date, parse_numeric_value, normalize_text
|
|
92
96
|
from smith_utils import make_unicode_char_name_records
|
|
97
|
+
from smith_utils import normalize_file_to_lf
|
|
93
98
|
|
|
94
99
|
# Datetime
|
|
95
100
|
date = ensure_date("20231225") # datetime.date(2023, 12, 25)
|
|
@@ -103,6 +108,10 @@ clean_text = normalize_text(" Smith Utils ") # "smith uti
|
|
|
103
108
|
# Unicode metadata
|
|
104
109
|
records = make_unicode_char_name_records("Aあ")
|
|
105
110
|
# [UnicodeCharNameRecord(index=0, codepoint='U+0041', ...), ...]
|
|
111
|
+
|
|
112
|
+
# Normalize a file's newlines to LF
|
|
113
|
+
summary = normalize_file_to_lf("input.txt", "output.txt")
|
|
114
|
+
# {'newline_type': 'CRLF', 'bytes_in': ..., 'bytes_out': ...}
|
|
106
115
|
```
|
|
107
116
|
|
|
108
117
|
## Directory Structure
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
from src import smith_utils
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
def test_text_exports_are_available_globally():
|
|
5
|
+
expected = {
|
|
6
|
+
"NewlineType",
|
|
7
|
+
"normalize_file_to_lf",
|
|
8
|
+
"normalize_newlines_stream",
|
|
9
|
+
"StringDistance",
|
|
10
|
+
"analyze_pair",
|
|
11
|
+
"Result",
|
|
12
|
+
"Relation",
|
|
13
|
+
"normalize_text",
|
|
14
|
+
"UnicodeCharNameRecord",
|
|
15
|
+
"make_unicode_char_name_records",
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
for name in expected:
|
|
19
|
+
assert hasattr(smith_utils, name), f"missing export: {name}"
|
|
20
|
+
assert name in smith_utils.__all__
|
|
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
|