aykhans/AzSuicideDataVisualization
1
0
Fork 0
mirror of https://github.com/aykhans/AzSuicideDataVisualization.git synced 2025-09-05 10:33:33 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

first commit

Browse Source
This commit is contained in:
Ayxan
2022-05-23 00:16:32 +04:00
commit d660f2a4ca
24786 changed files with 4428337 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.venv/Lib/site-packages/charset_normalizer-2.0.12.dist-info/INSTALLER Normal file
View File

@@ -0,0 +1 @@
pip

21
.venv/Lib/site-packages/charset_normalizer-2.0.12.dist-info/LICENSE Normal file
View File

@@ -0,0 +1,21 @@
MIT License
Copyright (c) 2019 TAHRI Ahmed R.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.

269
.venv/Lib/site-packages/charset_normalizer-2.0.12.dist-info/METADATA Normal file
View File

@@ -0,0 +1,269 @@
Metadata-Version: 2.1
Name: charset-normalizer
Version: 2.0.12
Summary: The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet.
Home-page: https://github.com/ousret/charset_normalizer
Author: Ahmed TAHRI @Ousret
Author-email: ahmed.tahri@cloudnursery.dev
License: MIT
Project-URL: Bug Reports, https://github.com/Ousret/charset_normalizer/issues
Project-URL: Documentation, https://charset-normalizer.readthedocs.io/en/latest
Keywords: encoding,i18n,txt,text,charset,charset-detector,normalization,unicode,chardet
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.5
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Utilities
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Typing :: Typed
Requires-Python: >=3.5.0
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: unicode_backport
Requires-Dist: unicodedata2 ; extra == 'unicode_backport'
<h1 align="center">Charset Detection, for Everyone 👋 <a href="https://twitter.com/intent/tweet?text=The%20Real%20First%20Universal%20Charset%20%26%20Language%20Detector&url=https://www.github.com/Ousret/charset_normalizer&hashtags=python,encoding,chardet,developers"><img src="https://img.shields.io/twitter/url/http/shields.io.svg?style=social"/></a></h1>
<p align="center">
<sup>The Real First Universal Charset Detector</sup><br>
<a href="https://pypi.org/project/charset-normalizer">
<img src="https://img.shields.io/pypi/pyversions/charset_normalizer.svg?orange=blue" />
</a>
<a href="https://codecov.io/gh/Ousret/charset_normalizer">
<img src="https://codecov.io/gh/Ousret/charset_normalizer/branch/master/graph/badge.svg" />
</a>
<a href="https://pepy.tech/project/charset-normalizer/">
<img alt="Download Count Total" src="https://pepy.tech/badge/charset-normalizer/month" />
</a>
</p>
> A library that helps you read text from an unknown charset encoding.<br /> Motivated by `chardet`,
> I'm trying to resolve the issue by taking a new approach.
> All IANA character set names for which the Python core library provides codecs are supported.
<p align="center">
>>>>> <a href="https://charsetnormalizerweb.ousret.now.sh" target="_blank">👉 Try Me Online Now, Then Adopt Me 👈 </a> <<<<<
</p>
This project offers you an alternative to **Universal Charset Encoding Detector**, also known as **Chardet**.
| Feature | [Chardet](https://github.com/chardet/chardet) | Charset Normalizer | [cChardet](https://github.com/PyYoshi/cChardet) |
| ------------- | :-------------: | :------------------: | :------------------: |
| `Fast` | ❌<br> | ✅<br> | ✅ <br> |
| `Universal**` | ❌ | ✅ | ❌ |
| `Reliable` **without** distinguishable standards | ❌ | ✅ | ✅ |
| `Reliable` **with** distinguishable standards | ✅ | ✅ | ✅ |
| `Free & Open` | ✅ | ✅ | ✅ |
| `License` | LGPL-2.1 | MIT | MPL-1.1
| `Native Python` | ✅ | ✅ | ❌ |
| `Detect spoken language` | ❌ | ✅ | N/A |
| `Supported Encoding` | 30 | :tada: [93](https://charset-normalizer.readthedocs.io/en/latest/user/support.html#supported-encodings) | 40
<p align="center">
<img src="https://i.imgflip.com/373iay.gif" alt="Reading Normalized Text" width="226"/><img src="https://media.tenor.com/images/c0180f70732a18b4965448d33adba3d0/tenor.gif" alt="Cat Reading Text" width="200"/>
*\*\* : They are clearly using specific code for a specific encoding even if covering most of used one*<br>
Did you got there because of the logs? See [https://charset-normalizer.readthedocs.io/en/latest/user/miscellaneous.html](https://charset-normalizer.readthedocs.io/en/latest/user/miscellaneous.html)
## ⭐ Your support
*Fork, test-it, star-it, submit your ideas! We do listen.*
## ⚡ Performance
This package offer better performance than its counterpart Chardet. Here are some numbers.
| Package | Accuracy | Mean per file (ms) | File per sec (est) |
| ------------- | :-------------: | :------------------: | :------------------: |
| [chardet](https://github.com/chardet/chardet) | 92 % | 220 ms | 5 file/sec |
| charset-normalizer | **98 %** | **40 ms** | 25 file/sec |
| Package | 99th percentile | 95th percentile | 50th percentile |
| ------------- | :-------------: | :------------------: | :------------------: |
| [chardet](https://github.com/chardet/chardet) | 1115 ms | 300 ms | 27 ms |
| charset-normalizer | 460 ms | 240 ms | 18 ms |
Chardet's performance on larger file (1MB+) are very poor. Expect huge difference on large payload.
> Stats are generated using 400+ files using default parameters. More details on used files, see GHA workflows.
> And yes, these results might change at any time. The dataset can be updated to include more files.
> The actual delays heavily depends on your CPU capabilities. The factors should remain the same.
[cchardet](https://github.com/PyYoshi/cChardet) is a non-native (cpp binding) and unmaintained faster alternative with
a better accuracy than chardet but lower than this package. If speed is the most important factor, you should try it.
## ✨ Installation
Using PyPi for latest stable
```sh
pip install charset-normalizer -U
```
If you want a more up-to-date `unicodedata` than the one available in your Python setup.
```sh
pip install charset-normalizer[unicode_backport] -U
```
## 🚀 Basic Usage
### CLI
This package comes with a CLI.
```
usage: normalizer [-h] [-v] [-a] [-n] [-m] [-r] [-f] [-t THRESHOLD]
file [file ...]
The Real First Universal Charset Detector. Discover originating encoding used
on text file. Normalize text to unicode.
positional arguments:
files File(s) to be analysed
optional arguments:
-h, --help show this help message and exit
-v, --verbose Display complementary information about file if any.
Stdout will contain logs about the detection process.
-a, --with-alternative
Output complementary possibilities if any. Top-level
JSON WILL be a list.
-n, --normalize Permit to normalize input file. If not set, program
does not write anything.
-m, --minimal Only output the charset detected to STDOUT. Disabling
JSON output.
-r, --replace Replace file when trying to normalize it instead of
creating a new one.
-f, --force Replace file without asking if you are sure, use this
flag with caution.
-t THRESHOLD, --threshold THRESHOLD
Define a custom maximum amount of chaos allowed in
decoded content. 0. <= chaos <= 1.
--version Show version information and exit.
```
```bash
normalizer ./data/sample.1.fr.srt
```
:tada: Since version 1.4.0 the CLI produce easily usable stdout result in JSON format.
```json
{
"path": "/home/default/projects/charset_normalizer/data/sample.1.fr.srt",
"encoding": "cp1252",
"encoding_aliases": [
"1252",
"windows_1252"
],
"alternative_encodings": [
"cp1254",
"cp1256",
"cp1258",
"iso8859_14",
"iso8859_15",
"iso8859_16",
"iso8859_3",
"iso8859_9",
"latin_1",
"mbcs"
],
"language": "French",
"alphabets": [
"Basic Latin",
"Latin-1 Supplement"
],
"has_sig_or_bom": false,
"chaos": 0.149,
"coherence": 97.152,
"unicode_path": null,
"is_preferred": true
}
```
### Python
*Just print out normalized text*
```python
from charset_normalizer import from_path
results = from_path('./my_subtitle.srt')
print(str(results.best()))
```
*Normalize any text file*
```python
from charset_normalizer import normalize
try:
normalize('./my_subtitle.srt') # should write to disk my_subtitle-***.srt
except IOError as e:
print('Sadly, we are unable to perform charset normalization.', str(e))
```
*Upgrade your code without effort*
```python
from charset_normalizer import detect
```
The above code will behave the same as **chardet**. We ensure that we offer the best (reasonable) BC result possible.
See the docs for advanced usage : [readthedocs.io](https://charset-normalizer.readthedocs.io/en/latest/)
## 😇 Why
When I started using Chardet, I noticed that it was not suited to my expectations, and I wanted to propose a
reliable alternative using a completely different method. Also! I never back down on a good challenge!
I **don't care** about the **originating charset** encoding, because **two different tables** can
produce **two identical rendered string.**
What I want is to get readable text, the best I can.
In a way, **I'm brute forcing text decoding.** How cool is that ? 😎
Don't confuse package **ftfy** with charset-normalizer or chardet. ftfy goal is to repair unicode string whereas charset-normalizer to convert raw file in unknown encoding to unicode.
## 🍰 How
- Discard all charset encoding table that could not fit the binary content.
- Measure chaos, or the mess once opened (by chunks) with a corresponding charset encoding.
- Extract matches with the lowest mess detected.
- Additionally, we measure coherence / probe for a language.
**Wait a minute**, what is chaos/mess and coherence according to **YOU ?**
*Chaos :* I opened hundred of text files, **written by humans**, with the wrong encoding table. **I observed**, then
**I established** some ground rules about **what is obvious** when **it seems like** a mess.
I know that my interpretation of what is chaotic is very subjective, feel free to contribute in order to
improve or rewrite it.
*Coherence :* For each language there is on earth, we have computed ranked letter appearance occurrences (the best we can). So I thought
that intel is worth something here. So I use those records against decoded text to check if I can detect intelligent design.
## ⚡ Known limitations
- Language detection is unreliable when text contains two or more languages sharing identical letters. (eg. HTML (english tags) + Turkish content (Sharing Latin characters))
- Every charset detector heavily depends on sufficient content. In common cases, do not bother run detection on very tiny content.
## 👤 Contributing
Contributions, issues and feature requests are very much welcome.<br />
Feel free to check [issues page](https://github.com/ousret/charset_normalizer/issues) if you want to contribute.
## 📝 License
Copyright © 2019 [Ahmed TAHRI @Ousret](https://github.com/Ousret).<br />
This project is [MIT](https://github.com/Ousret/charset_normalizer/blob/master/LICENSE) licensed.
Characters frequencies used in this project © 2012 [Denny Vrandečić](http://simia.net/letters/)

33
.venv/Lib/site-packages/charset_normalizer-2.0.12.dist-info/RECORD Normal file
View File

@@ -0,0 +1,33 @@
../../Scripts/normalizer.exe,sha256=M2lL5SxcA4Ks-HOlcAQPjPyhkKeSc8HzFQfbTWx2MVQ,106413
charset_normalizer-2.0.12.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
charset_normalizer-2.0.12.dist-info/LICENSE,sha256=6zGgxaT7Cbik4yBV0lweX5w1iidS_vPNcgIT0cz-4kE,1070
charset_normalizer-2.0.12.dist-info/METADATA,sha256=eX-U3s7nb6wcvXZFyM1mdBf1yz4I0msVBgNvLEscAbo,11713
charset_normalizer-2.0.12.dist-info/RECORD,,
charset_normalizer-2.0.12.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
charset_normalizer-2.0.12.dist-info/entry_points.txt,sha256=5AJq_EPtGGUwJPgQLnBZfbVr-FYCIwT0xP7dIEZO3NI,77
charset_normalizer-2.0.12.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
charset_normalizer/__init__.py,sha256=x2A2OW29MBcqdxsvy6t1wzkUlH3ma0guxL6ZCfS8J94,1790
charset_normalizer/__pycache__/__init__.cpython-310.pyc,,
charset_normalizer/__pycache__/api.cpython-310.pyc,,
charset_normalizer/__pycache__/cd.cpython-310.pyc,,
charset_normalizer/__pycache__/constant.cpython-310.pyc,,
charset_normalizer/__pycache__/legacy.cpython-310.pyc,,
charset_normalizer/__pycache__/md.cpython-310.pyc,,
charset_normalizer/__pycache__/models.cpython-310.pyc,,
charset_normalizer/__pycache__/utils.cpython-310.pyc,,
charset_normalizer/__pycache__/version.cpython-310.pyc,,
charset_normalizer/api.py,sha256=r__Wz85F5pYOkRwEY5imXY_pCZ2Nil1DkdaAJY7T5o0,20303
charset_normalizer/assets/__init__.py,sha256=FPnfk8limZRb8ZIUQcTvPEcbuM1eqOdWGw0vbWGycDs,25485
charset_normalizer/assets/__pycache__/__init__.cpython-310.pyc,,
charset_normalizer/cd.py,sha256=a9Kzzd9tHl_W08ExbCFMmRJqdo2k7EBQ8Z_3y9DmYsg,11076
charset_normalizer/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/cli/__pycache__/__init__.cpython-310.pyc,,
charset_normalizer/cli/__pycache__/normalizer.cpython-310.pyc,,
charset_normalizer/cli/normalizer.py,sha256=LkeFIRc1l28rOgXpEby695x0bcKQv4D8z9FmA3Z2c3A,9364
charset_normalizer/constant.py,sha256=51u_RS10I1vYVpBao__xHqf--HHNrR6me1A1se5r5Y0,19449
charset_normalizer/legacy.py,sha256=XKeZOts_HdYQU_Jb3C9ZfOjY2CiUL132k9_nXer8gig,3384
charset_normalizer/md.py,sha256=WEwnu2MyIiMeEaorRduqcTxGjIBclWIG3i-9_UL6LLs,18191
charset_normalizer/models.py,sha256=XrGpVxfonhcilIWC1WeiP3-ZORGEe_RG3sgrfPLl9qM,13303
charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/utils.py,sha256=AWSL0z1B42IwdLfjX4ZMASA9cTUsTp0PweCdW98SI-4,9308
charset_normalizer/version.py,sha256=uxO2cT0YIavQv4dQlNGmHPIOOwOa-exspxXi3IR7dck,80

5
.venv/Lib/site-packages/charset_normalizer-2.0.12.dist-info/WHEEL Normal file
View File

@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.37.1)
Root-Is-Purelib: true
Tag: py3-none-any

3
.venv/Lib/site-packages/charset_normalizer-2.0.12.dist-info/entry_points.txt Normal file
View File

@@ -0,0 +1,3 @@
[console_scripts]
normalizer = charset_normalizer.cli.normalizer:cli_detect

1
.venv/Lib/site-packages/charset_normalizer-2.0.12.dist-info/top_level.txt Normal file
View File

@@ -0,0 +1 @@
charset_normalizer