pyjour 0.0.0__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.
- pyjour-0.0.0/LICENSE +14 -0
- pyjour-0.0.0/PKG-INFO +111 -0
- pyjour-0.0.0/README.md +94 -0
- pyjour-0.0.0/pyjour/__init__.py +1 -0
- pyjour-0.0.0/pyjour/main.py +2 -0
- pyjour-0.0.0/pyjour.egg-info/PKG-INFO +111 -0
- pyjour-0.0.0/pyjour.egg-info/SOURCES.txt +10 -0
- pyjour-0.0.0/pyjour.egg-info/dependency_links.txt +1 -0
- pyjour-0.0.0/pyjour.egg-info/entry_points.txt +2 -0
- pyjour-0.0.0/pyjour.egg-info/top_level.txt +1 -0
- pyjour-0.0.0/pyproject.toml +31 -0
- pyjour-0.0.0/setup.cfg +4 -0
pyjour-0.0.0/LICENSE
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
BSD Zero Clause License
|
|
2
|
+
|
|
3
|
+
Copyright (c) Quentin Richert 2026
|
|
4
|
+
|
|
5
|
+
Permission to use, copy, modify, and/or distribute this software for any
|
|
6
|
+
purpose with or without fee is hereby granted.
|
|
7
|
+
|
|
8
|
+
THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH
|
|
9
|
+
REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
|
|
10
|
+
AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY SPECIAL, DIRECT,
|
|
11
|
+
INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM
|
|
12
|
+
LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
|
|
13
|
+
OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
|
|
14
|
+
PERFORMANCE OF THIS SOFTWARE.
|
pyjour-0.0.0/PKG-INFO
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: pyjour
|
|
3
|
+
Version: 0.0.0
|
|
4
|
+
Summary: Extract first names with confidence scores.
|
|
5
|
+
Author-email: Quentin Richert <noreply@richert.co>
|
|
6
|
+
License-Expression: 0BSD
|
|
7
|
+
Project-URL: Homepage, https://github.com/qrichert/bonjour
|
|
8
|
+
Project-URL: Repository, https://github.com/qrichert/bonjour.git
|
|
9
|
+
Keywords: first-name,name-extraction,person-name,nlp,classification
|
|
10
|
+
Classifier: Programming Language :: Python :: 3
|
|
11
|
+
Classifier: Operating System :: OS Independent
|
|
12
|
+
Classifier: Intended Audience :: Developers
|
|
13
|
+
Requires-Python: >=3.12
|
|
14
|
+
Description-Content-Type: text/markdown
|
|
15
|
+
License-File: LICENSE
|
|
16
|
+
Dynamic: license-file
|
|
17
|
+
|
|
18
|
+
# bonjour
|
|
19
|
+
|
|
20
|
+
> [!CAUTION]
|
|
21
|
+
>
|
|
22
|
+
> Work in progress, first usable version hasn't landed yet!
|
|
23
|
+
|
|
24
|
+
Experimental crate to extract first names with a confidence level.
|
|
25
|
+
|
|
26
|
+
Expected output may be something like this:
|
|
27
|
+
|
|
28
|
+
```json
|
|
29
|
+
{
|
|
30
|
+
"input": "Quentin Richert",
|
|
31
|
+
"first_name": "Quentin",
|
|
32
|
+
"confidence": 0.95,
|
|
33
|
+
"gender": "male",
|
|
34
|
+
"country": "FR"
|
|
35
|
+
}
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
The idea is that is also "detects", or at lease significantly reduces
|
|
39
|
+
confidences in company names, for instance:
|
|
40
|
+
|
|
41
|
+
```json
|
|
42
|
+
// The company marker 'SAS' significantly reduces confidence.
|
|
43
|
+
{
|
|
44
|
+
"input": "Quentin Richert SAS",
|
|
45
|
+
"first_name": "Quentin",
|
|
46
|
+
"confidence": 0.1,
|
|
47
|
+
"gender": "male",
|
|
48
|
+
"country": "FR"
|
|
49
|
+
}
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
Up to no detection at all:
|
|
53
|
+
|
|
54
|
+
```json
|
|
55
|
+
{
|
|
56
|
+
"input": "Les Motards d'Alsace",
|
|
57
|
+
"first_name": null,
|
|
58
|
+
"confidence": 0.0,
|
|
59
|
+
"gender": null,
|
|
60
|
+
"country": null
|
|
61
|
+
}
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Country and gender hints
|
|
65
|
+
|
|
66
|
+
Gender is not a property of a name alone — `Simone` is female in France,
|
|
67
|
+
male in Italy. Pass the user's country and/or gender as hints and they
|
|
68
|
+
resolve each other: a country pins the gender, a gender pins the
|
|
69
|
+
country.
|
|
70
|
+
|
|
71
|
+
```console
|
|
72
|
+
$ bonjour --country=IT Simone Veil
|
|
73
|
+
{
|
|
74
|
+
"input": "Simone Veil",
|
|
75
|
+
"first_name": "Simone",
|
|
76
|
+
"confidence": 0.65,
|
|
77
|
+
"gender": "male",
|
|
78
|
+
"country": "IT"
|
|
79
|
+
}
|
|
80
|
+
|
|
81
|
+
$ bonjour --country=FR Simone Veil
|
|
82
|
+
{
|
|
83
|
+
"input": "Simone Veil",
|
|
84
|
+
"first_name": "Simone",
|
|
85
|
+
"confidence": 0.7,
|
|
86
|
+
"gender": "female",
|
|
87
|
+
"country": "FR"
|
|
88
|
+
}
|
|
89
|
+
```
|
|
90
|
+
|
|
91
|
+
With no hint and a name whose gender differs by country, `gender` is
|
|
92
|
+
left `null` rather than guessed:
|
|
93
|
+
|
|
94
|
+
```json
|
|
95
|
+
{
|
|
96
|
+
"input": "Simone",
|
|
97
|
+
"first_name": "Simone",
|
|
98
|
+
"confidence": 0.7,
|
|
99
|
+
"gender": null,
|
|
100
|
+
"country": "FR"
|
|
101
|
+
}
|
|
102
|
+
```
|
|
103
|
+
|
|
104
|
+
## License
|
|
105
|
+
|
|
106
|
+
The source code is available under the [0BSD license](LICENSE).
|
|
107
|
+
|
|
108
|
+
Datasets distributed with or used to build this project are compiled
|
|
109
|
+
from publicly available information. They are not covered by the 0BSD
|
|
110
|
+
license; their contents remain subject to any applicable rights and
|
|
111
|
+
source terms.
|
pyjour-0.0.0/README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
1
|
+
# bonjour
|
|
2
|
+
|
|
3
|
+
> [!CAUTION]
|
|
4
|
+
>
|
|
5
|
+
> Work in progress, first usable version hasn't landed yet!
|
|
6
|
+
|
|
7
|
+
Experimental crate to extract first names with a confidence level.
|
|
8
|
+
|
|
9
|
+
Expected output may be something like this:
|
|
10
|
+
|
|
11
|
+
```json
|
|
12
|
+
{
|
|
13
|
+
"input": "Quentin Richert",
|
|
14
|
+
"first_name": "Quentin",
|
|
15
|
+
"confidence": 0.95,
|
|
16
|
+
"gender": "male",
|
|
17
|
+
"country": "FR"
|
|
18
|
+
}
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
The idea is that is also "detects", or at lease significantly reduces
|
|
22
|
+
confidences in company names, for instance:
|
|
23
|
+
|
|
24
|
+
```json
|
|
25
|
+
// The company marker 'SAS' significantly reduces confidence.
|
|
26
|
+
{
|
|
27
|
+
"input": "Quentin Richert SAS",
|
|
28
|
+
"first_name": "Quentin",
|
|
29
|
+
"confidence": 0.1,
|
|
30
|
+
"gender": "male",
|
|
31
|
+
"country": "FR"
|
|
32
|
+
}
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
Up to no detection at all:
|
|
36
|
+
|
|
37
|
+
```json
|
|
38
|
+
{
|
|
39
|
+
"input": "Les Motards d'Alsace",
|
|
40
|
+
"first_name": null,
|
|
41
|
+
"confidence": 0.0,
|
|
42
|
+
"gender": null,
|
|
43
|
+
"country": null
|
|
44
|
+
}
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
## Country and gender hints
|
|
48
|
+
|
|
49
|
+
Gender is not a property of a name alone — `Simone` is female in France,
|
|
50
|
+
male in Italy. Pass the user's country and/or gender as hints and they
|
|
51
|
+
resolve each other: a country pins the gender, a gender pins the
|
|
52
|
+
country.
|
|
53
|
+
|
|
54
|
+
```console
|
|
55
|
+
$ bonjour --country=IT Simone Veil
|
|
56
|
+
{
|
|
57
|
+
"input": "Simone Veil",
|
|
58
|
+
"first_name": "Simone",
|
|
59
|
+
"confidence": 0.65,
|
|
60
|
+
"gender": "male",
|
|
61
|
+
"country": "IT"
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
$ bonjour --country=FR Simone Veil
|
|
65
|
+
{
|
|
66
|
+
"input": "Simone Veil",
|
|
67
|
+
"first_name": "Simone",
|
|
68
|
+
"confidence": 0.7,
|
|
69
|
+
"gender": "female",
|
|
70
|
+
"country": "FR"
|
|
71
|
+
}
|
|
72
|
+
```
|
|
73
|
+
|
|
74
|
+
With no hint and a name whose gender differs by country, `gender` is
|
|
75
|
+
left `null` rather than guessed:
|
|
76
|
+
|
|
77
|
+
```json
|
|
78
|
+
{
|
|
79
|
+
"input": "Simone",
|
|
80
|
+
"first_name": "Simone",
|
|
81
|
+
"confidence": 0.7,
|
|
82
|
+
"gender": null,
|
|
83
|
+
"country": "FR"
|
|
84
|
+
}
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
## License
|
|
88
|
+
|
|
89
|
+
The source code is available under the [0BSD license](LICENSE).
|
|
90
|
+
|
|
91
|
+
Datasets distributed with or used to build this project are compiled
|
|
92
|
+
from publicly available information. They are not covered by the 0BSD
|
|
93
|
+
license; their contents remain subject to any applicable rights and
|
|
94
|
+
source terms.
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
"""Extract first names with confidence scores."""
|
|
@@ -0,0 +1,111 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: pyjour
|
|
3
|
+
Version: 0.0.0
|
|
4
|
+
Summary: Extract first names with confidence scores.
|
|
5
|
+
Author-email: Quentin Richert <noreply@richert.co>
|
|
6
|
+
License-Expression: 0BSD
|
|
7
|
+
Project-URL: Homepage, https://github.com/qrichert/bonjour
|
|
8
|
+
Project-URL: Repository, https://github.com/qrichert/bonjour.git
|
|
9
|
+
Keywords: first-name,name-extraction,person-name,nlp,classification
|
|
10
|
+
Classifier: Programming Language :: Python :: 3
|
|
11
|
+
Classifier: Operating System :: OS Independent
|
|
12
|
+
Classifier: Intended Audience :: Developers
|
|
13
|
+
Requires-Python: >=3.12
|
|
14
|
+
Description-Content-Type: text/markdown
|
|
15
|
+
License-File: LICENSE
|
|
16
|
+
Dynamic: license-file
|
|
17
|
+
|
|
18
|
+
# bonjour
|
|
19
|
+
|
|
20
|
+
> [!CAUTION]
|
|
21
|
+
>
|
|
22
|
+
> Work in progress, first usable version hasn't landed yet!
|
|
23
|
+
|
|
24
|
+
Experimental crate to extract first names with a confidence level.
|
|
25
|
+
|
|
26
|
+
Expected output may be something like this:
|
|
27
|
+
|
|
28
|
+
```json
|
|
29
|
+
{
|
|
30
|
+
"input": "Quentin Richert",
|
|
31
|
+
"first_name": "Quentin",
|
|
32
|
+
"confidence": 0.95,
|
|
33
|
+
"gender": "male",
|
|
34
|
+
"country": "FR"
|
|
35
|
+
}
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
The idea is that is also "detects", or at lease significantly reduces
|
|
39
|
+
confidences in company names, for instance:
|
|
40
|
+
|
|
41
|
+
```json
|
|
42
|
+
// The company marker 'SAS' significantly reduces confidence.
|
|
43
|
+
{
|
|
44
|
+
"input": "Quentin Richert SAS",
|
|
45
|
+
"first_name": "Quentin",
|
|
46
|
+
"confidence": 0.1,
|
|
47
|
+
"gender": "male",
|
|
48
|
+
"country": "FR"
|
|
49
|
+
}
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
Up to no detection at all:
|
|
53
|
+
|
|
54
|
+
```json
|
|
55
|
+
{
|
|
56
|
+
"input": "Les Motards d'Alsace",
|
|
57
|
+
"first_name": null,
|
|
58
|
+
"confidence": 0.0,
|
|
59
|
+
"gender": null,
|
|
60
|
+
"country": null
|
|
61
|
+
}
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Country and gender hints
|
|
65
|
+
|
|
66
|
+
Gender is not a property of a name alone — `Simone` is female in France,
|
|
67
|
+
male in Italy. Pass the user's country and/or gender as hints and they
|
|
68
|
+
resolve each other: a country pins the gender, a gender pins the
|
|
69
|
+
country.
|
|
70
|
+
|
|
71
|
+
```console
|
|
72
|
+
$ bonjour --country=IT Simone Veil
|
|
73
|
+
{
|
|
74
|
+
"input": "Simone Veil",
|
|
75
|
+
"first_name": "Simone",
|
|
76
|
+
"confidence": 0.65,
|
|
77
|
+
"gender": "male",
|
|
78
|
+
"country": "IT"
|
|
79
|
+
}
|
|
80
|
+
|
|
81
|
+
$ bonjour --country=FR Simone Veil
|
|
82
|
+
{
|
|
83
|
+
"input": "Simone Veil",
|
|
84
|
+
"first_name": "Simone",
|
|
85
|
+
"confidence": 0.7,
|
|
86
|
+
"gender": "female",
|
|
87
|
+
"country": "FR"
|
|
88
|
+
}
|
|
89
|
+
```
|
|
90
|
+
|
|
91
|
+
With no hint and a name whose gender differs by country, `gender` is
|
|
92
|
+
left `null` rather than guessed:
|
|
93
|
+
|
|
94
|
+
```json
|
|
95
|
+
{
|
|
96
|
+
"input": "Simone",
|
|
97
|
+
"first_name": "Simone",
|
|
98
|
+
"confidence": 0.7,
|
|
99
|
+
"gender": null,
|
|
100
|
+
"country": "FR"
|
|
101
|
+
}
|
|
102
|
+
```
|
|
103
|
+
|
|
104
|
+
## License
|
|
105
|
+
|
|
106
|
+
The source code is available under the [0BSD license](LICENSE).
|
|
107
|
+
|
|
108
|
+
Datasets distributed with or used to build this project are compiled
|
|
109
|
+
from publicly available information. They are not covered by the 0BSD
|
|
110
|
+
license; their contents remain subject to any applicable rights and
|
|
111
|
+
source terms.
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
pyjour
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["setuptools>=77"]
|
|
3
|
+
build-backend = "setuptools.build_meta"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "pyjour"
|
|
7
|
+
version = "0.0.0"
|
|
8
|
+
authors = [
|
|
9
|
+
{ name = "Quentin Richert", email = "noreply@richert.co" },
|
|
10
|
+
]
|
|
11
|
+
description = "Extract first names with confidence scores."
|
|
12
|
+
readme = "README.md"
|
|
13
|
+
requires-python = ">=3.12"
|
|
14
|
+
license = "0BSD"
|
|
15
|
+
license-files = ["LICENSE"]
|
|
16
|
+
keywords = ["first-name", "name-extraction", "person-name", "nlp", "classification"]
|
|
17
|
+
classifiers = [
|
|
18
|
+
"Programming Language :: Python :: 3",
|
|
19
|
+
"Operating System :: OS Independent",
|
|
20
|
+
"Intended Audience :: Developers",
|
|
21
|
+
]
|
|
22
|
+
|
|
23
|
+
[project.urls]
|
|
24
|
+
Homepage = "https://github.com/qrichert/bonjour"
|
|
25
|
+
Repository = "https://github.com/qrichert/bonjour.git"
|
|
26
|
+
|
|
27
|
+
[project.scripts]
|
|
28
|
+
pyjour = "pyjour.main:main"
|
|
29
|
+
|
|
30
|
+
[tool.setuptools]
|
|
31
|
+
packages = ["pyjour"]
|
pyjour-0.0.0/setup.cfg
ADDED