9 Commits

Author SHA1 Message Date
Olli Graf
c04c88e2af virtuelle Umgebung teil20b 2023-09-01 16:01:37 +02:00
c9aee44812 virtuelle Umgebungen teil20 und teil20a 2023-09-01 15:57:01 +02:00
69da4cda15 teil20 und teil20a 2023-09-01 15:52:37 +02:00
Olli Graf
bd29baae73 eadme.md aktualisiert. 2023-07-21 12:18:21 +02:00
Olli Graf
d6d3c54aa8 Teil 19 Flask. 2023-07-21 12:15:49 +02:00
63fee8c895 Fibonacci-Berechnung korrigiert. 2023-07-09 16:47:14 +02:00
9956835ad9 Merge branch 'master' into develop 2023-07-09 10:53:19 +02:00
124bff5e06 Kapitel 18: Generatoren und list comprehension 2023-06-08 19:38:09 +02:00
dd7d747a99 flask neu in develop 2023-06-08 19:26:49 +02:00
15258 changed files with 2930295 additions and 8 deletions

View File

@@ -22,4 +22,7 @@ CC-BY-SA Olli Graf
|15 | GPIO| |15 | GPIO|
|16 | Testing| |16 | Testing|
|17 | Datenbank| |17 | Datenbank|
|18 | Generatoren und list comprehension|
|19 | Webseiten (Flask)|
|20 | virtuelle Umgebungen|

37
dht22/weather.py Executable file
View File

@@ -0,0 +1,37 @@
#! /usr/bin/python3
from time import sleep
import logging
import Adafruit_DHT
__PIN__ = 4 # GPIO Pin, den wir nutzen
__WAIT__ = 0.5 # Warten für 0,5 Sekunden
logging.basicConfig( format='%(asctime)-15s [%(levelname)s] %(funcName)s: %(message)s', level=logging.DEBUG)
def main():
logging.debug('initialisiere Sensor')
dht22_sensor = Adafruit_DHT.DHT22
logging.debug(f'Sensor initialisiert ${dht22_sensor}')
while True:
logging.debug('lese von Sensor')
feuchte, temp_c = Adafruit_DHT.read_retry(dht22_sensor, __PIN__)
logging.debug(f'rel. Feuchte: ${feuchte:.2f}, Temperatur: ${temp_c:.2f}°C')
if __name__ =='__main__':
try:
logging.debug('Programm startet')
main()
except KeyboardInterrupt:
pass
finally:
pass

View File

@@ -5,7 +5,9 @@ import sys
def fib(n): def fib(n):
# Rekursionsbedingung # Rekursionsbedingung
if n in [0,1]: if n == 0:
return 0
elif n == 1:
return 1 return 1
else: else:
# Rekursionsaufruf # Rekursionsaufruf

View File

@@ -21,7 +21,7 @@ def fib(n):
# Rekursionsbedingung # Rekursionsbedingung
if n in [0,1]: if n in [0,1]:
return 1 return n
else: else:
# Rekursionsaufruf # Rekursionsaufruf
return fib(n-1) + fib(n-2) return fib(n-1) + fib(n-2)

Binary file not shown.

View File

@@ -6,7 +6,7 @@ def fib(n):
# Rekursionsbedingung # Rekursionsbedingung
if n in [0,1]: if n in [0,1]:
return 1 return n
else: else:
# Rekursionsaufruf # Rekursionsaufruf
return fib(n-1) + fib(n-2) return fib(n-1) + fib(n-2)

View File

@@ -10,7 +10,7 @@ result5 = fib(5)
result8 = fib(8) result8 = fib(8)
if result5 == 8 and result8 == 34: if result5 == 5 and result8 == 21:
logging.info('Tests erfolgreich') logging.info('Tests erfolgreich')
else: else:
logging.error('Tests fehlerhaft') logging.error('Tests fehlerhaft')

View File

@@ -20,17 +20,17 @@ class TestFib(unittest.TestCase):
# Die setUp() Methode wird zu Beginn jedes Testcases aufgrufen # Die setUp() Methode wird zu Beginn jedes Testcases aufgrufen
def setUp(self): def setUp(self):
logging.debug('setting up test') logging.debug('setting up test')
self.results = [1,1,2,3,5,8,13,21,34,55] self.results = [0,1,1,2,3,5,8,13,21,34,55]
#die beiden Tests aus ./testfib.py mit unittest #die beiden Tests aus ./testfib.py mit unittest
def test_fib(self): def test_fib(self):
# assertEqual(n,r) testet, ob das Resultat r der Vorgabe n entspricht. # assertEqual(n,r) testet, ob das Resultat r der Vorgabe n entspricht.
self.assertEqual(8,fib(5)) self.assertEqual(5,fib(5))
self.assertEqual(34,fib(8)) self.assertEqual(21,fib(8))
def test_mult_fib(self): def test_mult_fib(self):
results =[1,1,2,3,5,8,13,21,34,55] results =[0,1,1,2,3,5,8,13,21,34,55]
for n in range(0,9): for n in range(0,9):
self.assertEqual(results[n],fib(n)) self.assertEqual(results[n],fib(n))

1
teil18/.gitignore vendored Normal file
View File

@@ -0,0 +1 @@
./__pycache__

15
teil18/fib_gen.py Normal file
View File

@@ -0,0 +1,15 @@
import sys
def fib_generator():
a,b = 0,1
while True:
yield a
a,b = b, a+b
fibo = fib_generator()
for _ in range(int(sys.argv[1])+1):
print(next(fibo))

6
teil18/squares_for.py Normal file
View File

@@ -0,0 +1,6 @@
squares = []
for x in range(1,6):
squares.append(x**2)
print(squares)

View File

@@ -0,0 +1,3 @@
squares = [x **2 for x in range(1,6)]
print(squares)

11
teil18/vornamen_filter.py Normal file
View File

@@ -0,0 +1,11 @@
schueler = [
{'name':'Simpson','vorname': 'Bart'},
{'name':'Simpson','vorname':'Lisa'},
{'name':'van Houten','vorname':'Milhouse'},
{'name':'Wiggum','vorname':'Ralph'},
{'name':'Jones','vorname':'Jimbo'}
]
vornamen = [s['vorname'] for s in schueler if s['name'] == 'Simpson']
print(vornamen)

4
teil18/zahlen_for.py Normal file
View File

@@ -0,0 +1,4 @@
zahlen = [1,2,3,4,5,6,7,8,9,10]
for n in zahlen:
print(n)

19
teil18/zahlen_gen.py Normal file
View File

@@ -0,0 +1,19 @@
def gen_zahl():
n = 0
while n < 10:
n += 1
yield n
zahlen = gen_zahl()
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))
print(next(zahlen))

2
teil19/.gitignore vendored Normal file
View File

@@ -0,0 +1,2 @@
./__pycache__
renderhtml/__pycache__

Binary file not shown.

Binary file not shown.

45
teil19/fib/app.py Normal file
View File

@@ -0,0 +1,45 @@
from flask import Flask,render_template,request
from fib_gen import fib_generator
import logging
logging.basicConfig( format='%(asctime)-15s [%(levelname)s] %(funcName)s: %(message)s', level=logging.DEBUG)
app = Flask(__name__)
@app.route('/')
def index():
return render_template('index.html')
@app.route('/fib',methods=['GET','POST'])
def fib():
fibg = fib_generator()
result = ''
logging.debug(f'request.method={request.method}')
if request.method == 'POST':
element = request.form['element']
logging.debug(f'berechne Element:{element}')
n= int(element)
#formel= str(n-2) + '+' + str(n-1)
formel = '' # Berechnungsformel initialisieren.
if element != None:
for i in range(n+1):
fib = next(fibg)
if i == n-2: # fib(n-2) zur Berechnungsformel dazu
formel += str(fib)
if i == n-1: # fib(n-1) mit + Zeichen zur Berechnungsformel dazu
formel += '+' + str(fib)
logging.debug(f'Fibonacci-Zahl: {fib}')
logging.debug(f'formel={formel}')
result=str(fib)
elif request.method == 'GET':
logging.debug('GET-Request')
return render_template('index.html', result=result,formel=formel)
if __name__ == '__main__':
app.run(host='0.0.0.0',port=8085, debug=True)

12
teil19/fib/fib_gen.py Normal file
View File

@@ -0,0 +1,12 @@
import sys
def fib_generator():
a,b = 0,1
while True:
yield a
a,b = b, a+b

427
teil19/fib/static/css/normalize.css vendored Normal file
View File

@@ -0,0 +1,427 @@
/*! normalize.css v3.0.2 | MIT License | git.io/normalize */
/**
* 1. Set default font family to sans-serif.
* 2. Prevent iOS text size adjust after orientation change, without disabling
* user zoom.
*/
html {
font-family: sans-serif; /* 1 */
-ms-text-size-adjust: 100%; /* 2 */
-webkit-text-size-adjust: 100%; /* 2 */
}
/**
* Remove default margin.
*/
body {
margin: 0;
}
/* HTML5 display definitions
========================================================================== */
/**
* Correct `block` display not defined for any HTML5 element in IE 8/9.
* Correct `block` display not defined for `details` or `summary` in IE 10/11
* and Firefox.
* Correct `block` display not defined for `main` in IE 11.
*/
article,
aside,
details,
figcaption,
figure,
footer,
header,
hgroup,
main,
menu,
nav,
section,
summary {
display: block;
}
/**
* 1. Correct `inline-block` display not defined in IE 8/9.
* 2. Normalize vertical alignment of `progress` in Chrome, Firefox, and Opera.
*/
audio,
canvas,
progress,
video {
display: inline-block; /* 1 */
vertical-align: baseline; /* 2 */
}
/**
* Prevent modern browsers from displaying `audio` without controls.
* Remove excess height in iOS 5 devices.
*/
audio:not([controls]) {
display: none;
height: 0;
}
/**
* Address `[hidden]` styling not present in IE 8/9/10.
* Hide the `template` element in IE 8/9/11, Safari, and Firefox < 22.
*/
[hidden],
template {
display: none;
}
/* Links
========================================================================== */
/**
* Remove the gray background color from active links in IE 10.
*/
a {
background-color: transparent;
}
/**
* Improve readability when focused and also mouse hovered in all browsers.
*/
a:active,
a:hover {
outline: 0;
}
/* Text-level semantics
========================================================================== */
/**
* Address styling not present in IE 8/9/10/11, Safari, and Chrome.
*/
abbr[title] {
border-bottom: 1px dotted;
}
/**
* Address style set to `bolder` in Firefox 4+, Safari, and Chrome.
*/
b,
strong {
font-weight: bold;
}
/**
* Address styling not present in Safari and Chrome.
*/
dfn {
font-style: italic;
}
/**
* Address variable `h1` font-size and margin within `section` and `article`
* contexts in Firefox 4+, Safari, and Chrome.
*/
h1 {
font-size: 2em;
margin: 0.67em 0;
}
/**
* Address styling not present in IE 8/9.
*/
mark {
background: #ff0;
color: #000;
}
/**
* Address inconsistent and variable font size in all browsers.
*/
small {
font-size: 80%;
}
/**
* Prevent `sub` and `sup` affecting `line-height` in all browsers.
*/
sub,
sup {
font-size: 75%;
line-height: 0;
position: relative;
vertical-align: baseline;
}
sup {
top: -0.5em;
}
sub {
bottom: -0.25em;
}
/* Embedded content
========================================================================== */
/**
* Remove border when inside `a` element in IE 8/9/10.
*/
img {
border: 0;
}
/**
* Correct overflow not hidden in IE 9/10/11.
*/
svg:not(:root) {
overflow: hidden;
}
/* Grouping content
========================================================================== */
/**
* Address margin not present in IE 8/9 and Safari.
*/
figure {
margin: 1em 40px;
}
/**
* Address differences between Firefox and other browsers.
*/
hr {
-moz-box-sizing: content-box;
box-sizing: content-box;
height: 0;
}
/**
* Contain overflow in all browsers.
*/
pre {
overflow: auto;
}
/**
* Address odd `em`-unit font size rendering in all browsers.
*/
code,
kbd,
pre,
samp {
font-family: monospace, monospace;
font-size: 1em;
}
/* Forms
========================================================================== */
/**
* Known limitation: by default, Chrome and Safari on OS X allow very limited
* styling of `select`, unless a `border` property is set.
*/
/**
* 1. Correct color not being inherited.
* Known issue: affects color of disabled elements.
* 2. Correct font properties not being inherited.
* 3. Address margins set differently in Firefox 4+, Safari, and Chrome.
*/
button,
input,
optgroup,
select,
textarea {
color: inherit; /* 1 */
font: inherit; /* 2 */
margin: 0; /* 3 */
}
/**
* Address `overflow` set to `hidden` in IE 8/9/10/11.
*/
button {
overflow: visible;
}
/**
* Address inconsistent `text-transform` inheritance for `button` and `select`.
* All other form control elements do not inherit `text-transform` values.
* Correct `button` style inheritance in Firefox, IE 8/9/10/11, and Opera.
* Correct `select` style inheritance in Firefox.
*/
button,
select {
text-transform: none;
}
/**
* 1. Avoid the WebKit bug in Android 4.0.* where (2) destroys native `audio`
* and `video` controls.
* 2. Correct inability to style clickable `input` types in iOS.
* 3. Improve usability and consistency of cursor style between image-type
* `input` and others.
*/
button,
html input[type="button"], /* 1 */
input[type="reset"],
input[type="submit"] {
-webkit-appearance: button; /* 2 */
cursor: pointer; /* 3 */
}
/**
* Re-set default cursor for disabled elements.
*/
button[disabled],
html input[disabled] {
cursor: default;
}
/**
* Remove inner padding and border in Firefox 4+.
*/
button::-moz-focus-inner,
input::-moz-focus-inner {
border: 0;
padding: 0;
}
/**
* Address Firefox 4+ setting `line-height` on `input` using `!important` in
* the UA stylesheet.
*/
input {
line-height: normal;
}
/**
* It's recommended that you don't attempt to style these elements.
* Firefox's implementation doesn't respect box-sizing, padding, or width.
*
* 1. Address box sizing set to `content-box` in IE 8/9/10.
* 2. Remove excess padding in IE 8/9/10.
*/
input[type="checkbox"],
input[type="radio"] {
box-sizing: border-box; /* 1 */
padding: 0; /* 2 */
}
/**
* Fix the cursor style for Chrome's increment/decrement buttons. For certain
* `font-size` values of the `input`, it causes the cursor style of the
* decrement button to change from `default` to `text`.
*/
input[type="number"]::-webkit-inner-spin-button,
input[type="number"]::-webkit-outer-spin-button {
height: auto;
}
/**
* 1. Address `appearance` set to `searchfield` in Safari and Chrome.
* 2. Address `box-sizing` set to `border-box` in Safari and Chrome
* (include `-moz` to future-proof).
*/
input[type="search"] {
-webkit-appearance: textfield; /* 1 */
-moz-box-sizing: content-box;
-webkit-box-sizing: content-box; /* 2 */
box-sizing: content-box;
}
/**
* Remove inner padding and search cancel button in Safari and Chrome on OS X.
* Safari (but not Chrome) clips the cancel button when the search input has
* padding (and `textfield` appearance).
*/
input[type="search"]::-webkit-search-cancel-button,
input[type="search"]::-webkit-search-decoration {
-webkit-appearance: none;
}
/**
* Define consistent border, margin, and padding.
*/
fieldset {
border: 1px solid #c0c0c0;
margin: 0 2px;
padding: 0.35em 0.625em 0.75em;
}
/**
* 1. Correct `color` not being inherited in IE 8/9/10/11.
* 2. Remove padding so people aren't caught out if they zero out fieldsets.
*/
legend {
border: 0; /* 1 */
padding: 0; /* 2 */
}
/**
* Remove default vertical scrollbar in IE 8/9/10/11.
*/
textarea {
overflow: auto;
}
/**
* Don't inherit the `font-weight` (applied by a rule above).
* NOTE: the default cannot safely be changed in Chrome and Safari on OS X.
*/
optgroup {
font-weight: bold;
}
/* Tables
========================================================================== */
/**
* Remove most spacing between table cells.
*/
table {
border-collapse: collapse;
border-spacing: 0;
}
td,
th {
padding: 0;
}

418
teil19/fib/static/css/skeleton.css vendored Normal file
View File

@@ -0,0 +1,418 @@
/*
* Skeleton V2.0.4
* Copyright 2014, Dave Gamache
* www.getskeleton.com
* Free to use under the MIT license.
* http://www.opensource.org/licenses/mit-license.php
* 12/29/2014
*/
/* Table of contents
- Grid
- Base Styles
- Typography
- Links
- Buttons
- Forms
- Lists
- Code
- Tables
- Spacing
- Utilities
- Clearing
- Media Queries
*/
/* Grid
*/
.container {
position: relative;
width: 100%;
max-width: 960px;
margin: 0 auto;
padding: 0 20px;
box-sizing: border-box; }
.column,
.columns {
width: 100%;
float: left;
box-sizing: border-box; }
/* For devices larger than 400px */
@media (min-width: 400px) {
.container {
width: 85%;
padding: 0; }
}
/* For devices larger than 550px */
@media (min-width: 550px) {
.container {
width: 80%; }
.column,
.columns {
margin-left: 4%; }
.column:first-child,
.columns:first-child {
margin-left: 0; }
.one.column,
.one.columns { width: 4.66666666667%; }
.two.columns { width: 13.3333333333%; }
.three.columns { width: 22%; }
.four.columns { width: 30.6666666667%; }
.five.columns { width: 39.3333333333%; }
.six.columns { width: 48%; }
.seven.columns { width: 56.6666666667%; }
.eight.columns { width: 65.3333333333%; }
.nine.columns { width: 74.0%; }
.ten.columns { width: 82.6666666667%; }
.eleven.columns { width: 91.3333333333%; }
.twelve.columns { width: 100%; margin-left: 0; }
.one-third.column { width: 30.6666666667%; }
.two-thirds.column { width: 65.3333333333%; }
.one-half.column { width: 48%; }
/* Offsets */
.offset-by-one.column,
.offset-by-one.columns { margin-left: 8.66666666667%; }
.offset-by-two.column,
.offset-by-two.columns { margin-left: 17.3333333333%; }
.offset-by-three.column,
.offset-by-three.columns { margin-left: 26%; }
.offset-by-four.column,
.offset-by-four.columns { margin-left: 34.6666666667%; }
.offset-by-five.column,
.offset-by-five.columns { margin-left: 43.3333333333%; }
.offset-by-six.column,
.offset-by-six.columns { margin-left: 52%; }
.offset-by-seven.column,
.offset-by-seven.columns { margin-left: 60.6666666667%; }
.offset-by-eight.column,
.offset-by-eight.columns { margin-left: 69.3333333333%; }
.offset-by-nine.column,
.offset-by-nine.columns { margin-left: 78.0%; }
.offset-by-ten.column,
.offset-by-ten.columns { margin-left: 86.6666666667%; }
.offset-by-eleven.column,
.offset-by-eleven.columns { margin-left: 95.3333333333%; }
.offset-by-one-third.column,
.offset-by-one-third.columns { margin-left: 34.6666666667%; }
.offset-by-two-thirds.column,
.offset-by-two-thirds.columns { margin-left: 69.3333333333%; }
.offset-by-one-half.column,
.offset-by-one-half.columns { margin-left: 52%; }
}
/* Base Styles
*/
/* NOTE
html is set to 62.5% so that all the REM measurements throughout Skeleton
are based on 10px sizing. So basically 1.5rem = 15px :) */
html {
font-size: 62.5%; }
body {
font-size: 1.5em; /* currently ems cause chrome bug misinterpreting rems on body element */
line-height: 1.6;
font-weight: 400;
font-family: "Raleway", "HelveticaNeue", "Helvetica Neue", Helvetica, Arial, sans-serif;
color: #222; }
/* Typography
*/
h1, h2, h3, h4, h5, h6 {
margin-top: 0;
margin-bottom: 2rem;
font-weight: 300; }
h1 { font-size: 4.0rem; line-height: 1.2; letter-spacing: -.1rem;}
h2 { font-size: 3.6rem; line-height: 1.25; letter-spacing: -.1rem; }
h3 { font-size: 3.0rem; line-height: 1.3; letter-spacing: -.1rem; }
h4 { font-size: 2.4rem; line-height: 1.35; letter-spacing: -.08rem; }
h5 { font-size: 1.8rem; line-height: 1.5; letter-spacing: -.05rem; }
h6 { font-size: 1.5rem; line-height: 1.6; letter-spacing: 0; }
/* Larger than phablet */
@media (min-width: 550px) {
h1 { font-size: 5.0rem; }
h2 { font-size: 4.2rem; }
h3 { font-size: 3.6rem; }
h4 { font-size: 3.0rem; }
h5 { font-size: 2.4rem; }
h6 { font-size: 1.5rem; }
}
p {
margin-top: 0; }
/* Links
*/
a {
color: #1EAEDB; }
a:hover {
color: #0FA0CE; }
/* Buttons
*/
.button,
button,
input[type="submit"],
input[type="reset"],
input[type="button"] {
display: inline-block;
height: 38px;
padding: 0 30px;
color: #555;
text-align: center;
font-size: 11px;
font-weight: 600;
line-height: 38px;
letter-spacing: .1rem;
text-transform: uppercase;
text-decoration: none;
white-space: nowrap;
background-color: transparent;
border-radius: 4px;
border: 1px solid #bbb;
cursor: pointer;
box-sizing: border-box; }
.button:hover,
button:hover,
input[type="submit"]:hover,
input[type="reset"]:hover,
input[type="button"]:hover,
.button:focus,
button:focus,
input[type="submit"]:focus,
input[type="reset"]:focus,
input[type="button"]:focus {
color: #333;
border-color: #888;
outline: 0; }
.button.button-primary,
button.button-primary,
input[type="submit"].button-primary,
input[type="reset"].button-primary,
input[type="button"].button-primary {
color: #FFF;
background-color: #33C3F0;
border-color: #33C3F0; }
.button.button-primary:hover,
button.button-primary:hover,
input[type="submit"].button-primary:hover,
input[type="reset"].button-primary:hover,
input[type="button"].button-primary:hover,
.button.button-primary:focus,
button.button-primary:focus,
input[type="submit"].button-primary:focus,
input[type="reset"].button-primary:focus,
input[type="button"].button-primary:focus {
color: #FFF;
background-color: #1EAEDB;
border-color: #1EAEDB; }
/* Forms
*/
input[type="email"],
input[type="number"],
input[type="search"],
input[type="text"],
input[type="tel"],
input[type="url"],
input[type="password"],
textarea,
select {
height: 38px;
padding: 6px 10px; /* The 6px vertically centers text on FF, ignored by Webkit */
background-color: #fff;
border: 1px solid #D1D1D1;
border-radius: 4px;
box-shadow: none;
box-sizing: border-box; }
/* Removes awkward default styles on some inputs for iOS */
input[type="email"],
input[type="number"],
input[type="search"],
input[type="text"],
input[type="tel"],
input[type="url"],
input[type="password"],
textarea {
-webkit-appearance: none;
-moz-appearance: none;
appearance: none; }
textarea {
min-height: 65px;
padding-top: 6px;
padding-bottom: 6px; }
input[type="email"]:focus,
input[type="number"]:focus,
input[type="search"]:focus,
input[type="text"]:focus,
input[type="tel"]:focus,
input[type="url"]:focus,
input[type="password"]:focus,
textarea:focus,
select:focus {
border: 1px solid #33C3F0;
outline: 0; }
label,
legend {
display: block;
margin-bottom: .5rem;
font-weight: 600; }
fieldset {
padding: 0;
border-width: 0; }
input[type="checkbox"],
input[type="radio"] {
display: inline; }
label > .label-body {
display: inline-block;
margin-left: .5rem;
font-weight: normal; }
/* Lists
*/
ul {
list-style: circle inside; }
ol {
list-style: decimal inside; }
ol, ul {
padding-left: 0;
margin-top: 0; }
ul ul,
ul ol,
ol ol,
ol ul {
margin: 1.5rem 0 1.5rem 3rem;
font-size: 90%; }
li {
margin-bottom: 1rem; }
/* Code
*/
code {
padding: .2rem .5rem;
margin: 0 .2rem;
font-size: 90%;
white-space: nowrap;
background: #F1F1F1;
border: 1px solid #E1E1E1;
border-radius: 4px; }
pre > code {
display: block;
padding: 1rem 1.5rem;
white-space: pre; }
/* Tables
*/
th,
td {
padding: 12px 15px;
text-align: left;
border-bottom: 1px solid #E1E1E1; }
th:first-child,
td:first-child {
padding-left: 0; }
th:last-child,
td:last-child {
padding-right: 0; }
/* Spacing
*/
button,
.button {
margin-bottom: 1rem; }
input,
textarea,
select,
fieldset {
margin-bottom: 1.5rem; }
pre,
blockquote,
dl,
figure,
table,
p,
ul,
ol,
form {
margin-bottom: 2.5rem; }
/* Utilities
*/
.u-full-width {
width: 100%;
box-sizing: border-box; }
.u-max-full-width {
max-width: 100%;
box-sizing: border-box; }
.u-pull-right {
float: right; }
.u-pull-left {
float: left; }
/* Misc
*/
hr {
margin-top: 3rem;
margin-bottom: 3.5rem;
border-width: 0;
border-top: 1px solid #E1E1E1; }
/* Clearing
*/
/* Self Clearing Goodness */
.container:after,
.row:after,
.u-cf {
content: "";
display: table;
clear: both; }
/* Media Queries
*/
/*
Note: The best way to structure the use of media queries is to create the queries
near the relevant code. For example, if you wanted to change the styles for buttons
on small devices, paste the mobile query code up in the buttons section and style it
there.
*/
/* Larger than mobile */
@media (min-width: 400px) {}
/* Larger than phablet (also point when grid becomes active) */
@media (min-width: 550px) {}
/* Larger than tablet */
@media (min-width: 750px) {}
/* Larger than desktop */
@media (min-width: 1000px) {}
/* Larger than Desktop HD */
@media (min-width: 1200px) {}

View File

@@ -0,0 +1,26 @@
<!DOCTYPE html>
<html lang='en'>
<head>
<meta charset='utf-8' />
<link href='static/css/skeleton.css' rel='stylesheet' type='text/css' />
<title>Fibonacci Zahlen berechnen</title>
</head>
<body>
<h2>Fibonacci Generator </h2
<!--FORM -->
<form action='fib' method='post'>
<label> Folgen Element</label>
<input
type='text'
placeholder='Fibonacci Element'
name='element'
value='{{request.form.element}}'
</input><br />
<button type='submit'>Berechnen</button>
<p>Formel: {{formel}} </p>
<p>Fibonacci-Zahl: {{result}} </p>
</form>
</body>
</html>

View File

@@ -0,0 +1,19 @@
from flask import Flask
app = Flask(__name__)
@app.route('/')
def index():
return 'Ein erstes Hallo'
@app.route('/second')
def second():
return '<b>Ein zweites Hallo</b>'
if __name__ == '__main__':
app.run(host='0.0.0.0',port=8085, debug=True)

4
teil19/firsthello/setenv.sh Executable file
View File

@@ -0,0 +1,4 @@
#!/usr/bin/bash
export FLASK_APP=first
export FLASK_ENV=development

View File

@@ -0,0 +1,45 @@
#encoding: utf-8
import mysql.connector
import logging
logging.basicConfig( format='%(asctime)-15s [%(levelname)s] %(funcName)s: %(message)s', level=logging.DEBUG)
class DBConnection():
def __init__(self):
self.dbconnection = None
#Verbindung zur Datenbank mit den übergebenen Werten herstellen.
def connect(self, host, user, password, database):
self.connection= mysql.connector.connect(host=host, user=user,password=password,database=database)
# Verbindung trennen
def disconnect(self):
if self.connection is not None:
self.connection.close()
self.connection = None
# Schüler-Record in die Tabelle einfügen.
def insertSchueler(self,schueler):
self.execute_query('insert into schueler (name,vorname) values(%s,%s)', (schueler['name'],schueler['vorname']))
# Liefert True, wenn die Verbindung zur DB besteht, sonst False
def isConnected(self):
if self.connection is not None:
return self.connection.is_connected()
return False
# Wenn DB-Verbindung besteht, wird der Cursor geliefert, sonst None
def cursor(self):
if self.isConnected():
return self.connection.cursor()
return None
# Datenbank Kommando ausführen. Das params-Tupel wird in die Query eingesetzt.
# Liefert ein Resultset zurück.
def execute_query(self, query, params = None):
if self.isConnected():
cursor = self.cursor()
if cursor is not None:
cursor.execute(query,params) #Kommdo ausführen
return cursor.fetchall() # Ergebnis zurückliefern.

8
teil19/renderhtml/db.ini Normal file
View File

@@ -0,0 +1,8 @@
[pidb]
host=database
user=piuser
password=SW_Ep.6:ROTJ
database=pidb

View File

@@ -0,0 +1,28 @@
from flask import Flask,render_template
app = Flask(__name__)
zaehler = 0
@app.route('/')
def index():
global zaehler
zaehler=zaehler +1
return render_template('index.html', counter=zaehler)
schueler = [
{'name':'Simpson','vorname': 'Bart'},
{'name':'Simpson','vorname':'Lisa'},
{'name':'van Houten','vorname':'Milhouse'},
{'name':'Wiggum','vorname':'Ralph'},
{'name':'Jones','vorname':'Jimbo'}
]
@app.route('/students')
def students():
return render_template('students.html',schueler=schueler)
if __name__ == '__main__':
app.run(host='0.0.0.0',port=8085, debug=True)

View File

@@ -0,0 +1,427 @@
/*! normalize.css v3.0.2 | MIT License | git.io/normalize */
/**
* 1. Set default font family to sans-serif.
* 2. Prevent iOS text size adjust after orientation change, without disabling
* user zoom.
*/
html {
font-family: sans-serif; /* 1 */
-ms-text-size-adjust: 100%; /* 2 */
-webkit-text-size-adjust: 100%; /* 2 */
}
/**
* Remove default margin.
*/
body {
margin: 0;
}
/* HTML5 display definitions
========================================================================== */
/**
* Correct `block` display not defined for any HTML5 element in IE 8/9.
* Correct `block` display not defined for `details` or `summary` in IE 10/11
* and Firefox.
* Correct `block` display not defined for `main` in IE 11.
*/
article,
aside,
details,
figcaption,
figure,
footer,
header,
hgroup,
main,
menu,
nav,
section,
summary {
display: block;
}
/**
* 1. Correct `inline-block` display not defined in IE 8/9.
* 2. Normalize vertical alignment of `progress` in Chrome, Firefox, and Opera.
*/
audio,
canvas,
progress,
video {
display: inline-block; /* 1 */
vertical-align: baseline; /* 2 */
}
/**
* Prevent modern browsers from displaying `audio` without controls.
* Remove excess height in iOS 5 devices.
*/
audio:not([controls]) {
display: none;
height: 0;
}
/**
* Address `[hidden]` styling not present in IE 8/9/10.
* Hide the `template` element in IE 8/9/11, Safari, and Firefox < 22.
*/
[hidden],
template {
display: none;
}
/* Links
========================================================================== */
/**
* Remove the gray background color from active links in IE 10.
*/
a {
background-color: transparent;
}
/**
* Improve readability when focused and also mouse hovered in all browsers.
*/
a:active,
a:hover {
outline: 0;
}
/* Text-level semantics
========================================================================== */
/**
* Address styling not present in IE 8/9/10/11, Safari, and Chrome.
*/
abbr[title] {
border-bottom: 1px dotted;
}
/**
* Address style set to `bolder` in Firefox 4+, Safari, and Chrome.
*/
b,
strong {
font-weight: bold;
}
/**
* Address styling not present in Safari and Chrome.
*/
dfn {
font-style: italic;
}
/**
* Address variable `h1` font-size and margin within `section` and `article`
* contexts in Firefox 4+, Safari, and Chrome.
*/
h1 {
font-size: 2em;
margin: 0.67em 0;
}
/**
* Address styling not present in IE 8/9.
*/
mark {
background: #ff0;
color: #000;
}
/**
* Address inconsistent and variable font size in all browsers.
*/
small {
font-size: 80%;
}
/**
* Prevent `sub` and `sup` affecting `line-height` in all browsers.
*/
sub,
sup {
font-size: 75%;
line-height: 0;
position: relative;
vertical-align: baseline;
}
sup {
top: -0.5em;
}
sub {
bottom: -0.25em;
}
/* Embedded content
========================================================================== */
/**
* Remove border when inside `a` element in IE 8/9/10.
*/
img {
border: 0;
}
/**
* Correct overflow not hidden in IE 9/10/11.
*/
svg:not(:root) {
overflow: hidden;
}
/* Grouping content
========================================================================== */
/**
* Address margin not present in IE 8/9 and Safari.
*/
figure {
margin: 1em 40px;
}
/**
* Address differences between Firefox and other browsers.
*/
hr {
-moz-box-sizing: content-box;
box-sizing: content-box;
height: 0;
}
/**
* Contain overflow in all browsers.
*/
pre {
overflow: auto;
}
/**
* Address odd `em`-unit font size rendering in all browsers.
*/
code,
kbd,
pre,
samp {
font-family: monospace, monospace;
font-size: 1em;
}
/* Forms
========================================================================== */
/**
* Known limitation: by default, Chrome and Safari on OS X allow very limited
* styling of `select`, unless a `border` property is set.
*/
/**
* 1. Correct color not being inherited.
* Known issue: affects color of disabled elements.
* 2. Correct font properties not being inherited.
* 3. Address margins set differently in Firefox 4+, Safari, and Chrome.
*/
button,
input,
optgroup,
select,
textarea {
color: inherit; /* 1 */
font: inherit; /* 2 */
margin: 0; /* 3 */
}
/**
* Address `overflow` set to `hidden` in IE 8/9/10/11.
*/
button {
overflow: visible;
}
/**
* Address inconsistent `text-transform` inheritance for `button` and `select`.
* All other form control elements do not inherit `text-transform` values.
* Correct `button` style inheritance in Firefox, IE 8/9/10/11, and Opera.
* Correct `select` style inheritance in Firefox.
*/
button,
select {
text-transform: none;
}
/**
* 1. Avoid the WebKit bug in Android 4.0.* where (2) destroys native `audio`
* and `video` controls.
* 2. Correct inability to style clickable `input` types in iOS.
* 3. Improve usability and consistency of cursor style between image-type
* `input` and others.
*/
button,
html input[type="button"], /* 1 */
input[type="reset"],
input[type="submit"] {
-webkit-appearance: button; /* 2 */
cursor: pointer; /* 3 */
}
/**
* Re-set default cursor for disabled elements.
*/
button[disabled],
html input[disabled] {
cursor: default;
}
/**
* Remove inner padding and border in Firefox 4+.
*/
button::-moz-focus-inner,
input::-moz-focus-inner {
border: 0;
padding: 0;
}
/**
* Address Firefox 4+ setting `line-height` on `input` using `!important` in
* the UA stylesheet.
*/
input {
line-height: normal;
}
/**
* It's recommended that you don't attempt to style these elements.
* Firefox's implementation doesn't respect box-sizing, padding, or width.
*
* 1. Address box sizing set to `content-box` in IE 8/9/10.
* 2. Remove excess padding in IE 8/9/10.
*/
input[type="checkbox"],
input[type="radio"] {
box-sizing: border-box; /* 1 */
padding: 0; /* 2 */
}
/**
* Fix the cursor style for Chrome's increment/decrement buttons. For certain
* `font-size` values of the `input`, it causes the cursor style of the
* decrement button to change from `default` to `text`.
*/
input[type="number"]::-webkit-inner-spin-button,
input[type="number"]::-webkit-outer-spin-button {
height: auto;
}
/**
* 1. Address `appearance` set to `searchfield` in Safari and Chrome.
* 2. Address `box-sizing` set to `border-box` in Safari and Chrome
* (include `-moz` to future-proof).
*/
input[type="search"] {
-webkit-appearance: textfield; /* 1 */
-moz-box-sizing: content-box;
-webkit-box-sizing: content-box; /* 2 */
box-sizing: content-box;
}
/**
* Remove inner padding and search cancel button in Safari and Chrome on OS X.
* Safari (but not Chrome) clips the cancel button when the search input has
* padding (and `textfield` appearance).
*/
input[type="search"]::-webkit-search-cancel-button,
input[type="search"]::-webkit-search-decoration {
-webkit-appearance: none;
}
/**
* Define consistent border, margin, and padding.
*/
fieldset {
border: 1px solid #c0c0c0;
margin: 0 2px;
padding: 0.35em 0.625em 0.75em;
}
/**
* 1. Correct `color` not being inherited in IE 8/9/10/11.
* 2. Remove padding so people aren't caught out if they zero out fieldsets.
*/
legend {
border: 0; /* 1 */
padding: 0; /* 2 */
}
/**
* Remove default vertical scrollbar in IE 8/9/10/11.
*/
textarea {
overflow: auto;
}
/**
* Don't inherit the `font-weight` (applied by a rule above).
* NOTE: the default cannot safely be changed in Chrome and Safari on OS X.
*/
optgroup {
font-weight: bold;
}
/* Tables
========================================================================== */
/**
* Remove most spacing between table cells.
*/
table {
border-collapse: collapse;
border-spacing: 0;
}
td,
th {
padding: 0;
}

View File

@@ -0,0 +1,418 @@
/*
* Skeleton V2.0.4
* Copyright 2014, Dave Gamache
* www.getskeleton.com
* Free to use under the MIT license.
* http://www.opensource.org/licenses/mit-license.php
* 12/29/2014
*/
/* Table of contents
- Grid
- Base Styles
- Typography
- Links
- Buttons
- Forms
- Lists
- Code
- Tables
- Spacing
- Utilities
- Clearing
- Media Queries
*/
/* Grid
*/
.container {
position: relative;
width: 100%;
max-width: 960px;
margin: 0 auto;
padding: 0 20px;
box-sizing: border-box; }
.column,
.columns {
width: 100%;
float: left;
box-sizing: border-box; }
/* For devices larger than 400px */
@media (min-width: 400px) {
.container {
width: 85%;
padding: 0; }
}
/* For devices larger than 550px */
@media (min-width: 550px) {
.container {
width: 80%; }
.column,
.columns {
margin-left: 4%; }
.column:first-child,
.columns:first-child {
margin-left: 0; }
.one.column,
.one.columns { width: 4.66666666667%; }
.two.columns { width: 13.3333333333%; }
.three.columns { width: 22%; }
.four.columns { width: 30.6666666667%; }
.five.columns { width: 39.3333333333%; }
.six.columns { width: 48%; }
.seven.columns { width: 56.6666666667%; }
.eight.columns { width: 65.3333333333%; }
.nine.columns { width: 74.0%; }
.ten.columns { width: 82.6666666667%; }
.eleven.columns { width: 91.3333333333%; }
.twelve.columns { width: 100%; margin-left: 0; }
.one-third.column { width: 30.6666666667%; }
.two-thirds.column { width: 65.3333333333%; }
.one-half.column { width: 48%; }
/* Offsets */
.offset-by-one.column,
.offset-by-one.columns { margin-left: 8.66666666667%; }
.offset-by-two.column,
.offset-by-two.columns { margin-left: 17.3333333333%; }
.offset-by-three.column,
.offset-by-three.columns { margin-left: 26%; }
.offset-by-four.column,
.offset-by-four.columns { margin-left: 34.6666666667%; }
.offset-by-five.column,
.offset-by-five.columns { margin-left: 43.3333333333%; }
.offset-by-six.column,
.offset-by-six.columns { margin-left: 52%; }
.offset-by-seven.column,
.offset-by-seven.columns { margin-left: 60.6666666667%; }
.offset-by-eight.column,
.offset-by-eight.columns { margin-left: 69.3333333333%; }
.offset-by-nine.column,
.offset-by-nine.columns { margin-left: 78.0%; }
.offset-by-ten.column,
.offset-by-ten.columns { margin-left: 86.6666666667%; }
.offset-by-eleven.column,
.offset-by-eleven.columns { margin-left: 95.3333333333%; }
.offset-by-one-third.column,
.offset-by-one-third.columns { margin-left: 34.6666666667%; }
.offset-by-two-thirds.column,
.offset-by-two-thirds.columns { margin-left: 69.3333333333%; }
.offset-by-one-half.column,
.offset-by-one-half.columns { margin-left: 52%; }
}
/* Base Styles
*/
/* NOTE
html is set to 62.5% so that all the REM measurements throughout Skeleton
are based on 10px sizing. So basically 1.5rem = 15px :) */
html {
font-size: 62.5%; }
body {
font-size: 1.5em; /* currently ems cause chrome bug misinterpreting rems on body element */
line-height: 1.6;
font-weight: 400;
font-family: "Raleway", "HelveticaNeue", "Helvetica Neue", Helvetica, Arial, sans-serif;
color: #222; }
/* Typography
*/
h1, h2, h3, h4, h5, h6 {
margin-top: 0;
margin-bottom: 2rem;
font-weight: 300; }
h1 { font-size: 4.0rem; line-height: 1.2; letter-spacing: -.1rem;}
h2 { font-size: 3.6rem; line-height: 1.25; letter-spacing: -.1rem; }
h3 { font-size: 3.0rem; line-height: 1.3; letter-spacing: -.1rem; }
h4 { font-size: 2.4rem; line-height: 1.35; letter-spacing: -.08rem; }
h5 { font-size: 1.8rem; line-height: 1.5; letter-spacing: -.05rem; }
h6 { font-size: 1.5rem; line-height: 1.6; letter-spacing: 0; }
/* Larger than phablet */
@media (min-width: 550px) {
h1 { font-size: 5.0rem; }
h2 { font-size: 4.2rem; }
h3 { font-size: 3.6rem; }
h4 { font-size: 3.0rem; }
h5 { font-size: 2.4rem; }
h6 { font-size: 1.5rem; }
}
p {
margin-top: 0; }
/* Links
*/
a {
color: #1EAEDB; }
a:hover {
color: #0FA0CE; }
/* Buttons
*/
.button,
button,
input[type="submit"],
input[type="reset"],
input[type="button"] {
display: inline-block;
height: 38px;
padding: 0 30px;
color: #555;
text-align: center;
font-size: 11px;
font-weight: 600;
line-height: 38px;
letter-spacing: .1rem;
text-transform: uppercase;
text-decoration: none;
white-space: nowrap;
background-color: transparent;
border-radius: 4px;
border: 1px solid #bbb;
cursor: pointer;
box-sizing: border-box; }
.button:hover,
button:hover,
input[type="submit"]:hover,
input[type="reset"]:hover,
input[type="button"]:hover,
.button:focus,
button:focus,
input[type="submit"]:focus,
input[type="reset"]:focus,
input[type="button"]:focus {
color: #333;
border-color: #888;
outline: 0; }
.button.button-primary,
button.button-primary,
input[type="submit"].button-primary,
input[type="reset"].button-primary,
input[type="button"].button-primary {
color: #FFF;
background-color: #33C3F0;
border-color: #33C3F0; }
.button.button-primary:hover,
button.button-primary:hover,
input[type="submit"].button-primary:hover,
input[type="reset"].button-primary:hover,
input[type="button"].button-primary:hover,
.button.button-primary:focus,
button.button-primary:focus,
input[type="submit"].button-primary:focus,
input[type="reset"].button-primary:focus,
input[type="button"].button-primary:focus {
color: #FFF;
background-color: #1EAEDB;
border-color: #1EAEDB; }
/* Forms
*/
input[type="email"],
input[type="number"],
input[type="search"],
input[type="text"],
input[type="tel"],
input[type="url"],
input[type="password"],
textarea,
select {
height: 38px;
padding: 6px 10px; /* The 6px vertically centers text on FF, ignored by Webkit */
background-color: #fff;
border: 1px solid #D1D1D1;
border-radius: 4px;
box-shadow: none;
box-sizing: border-box; }
/* Removes awkward default styles on some inputs for iOS */
input[type="email"],
input[type="number"],
input[type="search"],
input[type="text"],
input[type="tel"],
input[type="url"],
input[type="password"],
textarea {
-webkit-appearance: none;
-moz-appearance: none;
appearance: none; }
textarea {
min-height: 65px;
padding-top: 6px;
padding-bottom: 6px; }
input[type="email"]:focus,
input[type="number"]:focus,
input[type="search"]:focus,
input[type="text"]:focus,
input[type="tel"]:focus,
input[type="url"]:focus,
input[type="password"]:focus,
textarea:focus,
select:focus {
border: 1px solid #33C3F0;
outline: 0; }
label,
legend {
display: block;
margin-bottom: .5rem;
font-weight: 600; }
fieldset {
padding: 0;
border-width: 0; }
input[type="checkbox"],
input[type="radio"] {
display: inline; }
label > .label-body {
display: inline-block;
margin-left: .5rem;
font-weight: normal; }
/* Lists
*/
ul {
list-style: circle inside; }
ol {
list-style: decimal inside; }
ol, ul {
padding-left: 0;
margin-top: 0; }
ul ul,
ul ol,
ol ol,
ol ul {
margin: 1.5rem 0 1.5rem 3rem;
font-size: 90%; }
li {
margin-bottom: 1rem; }
/* Code
*/
code {
padding: .2rem .5rem;
margin: 0 .2rem;
font-size: 90%;
white-space: nowrap;
background: #F1F1F1;
border: 1px solid #E1E1E1;
border-radius: 4px; }
pre > code {
display: block;
padding: 1rem 1.5rem;
white-space: pre; }
/* Tables
*/
th,
td {
padding: 12px 15px;
text-align: left;
border-bottom: 1px solid #E1E1E1; }
th:first-child,
td:first-child {
padding-left: 0; }
th:last-child,
td:last-child {
padding-right: 0; }
/* Spacing
*/
button,
.button {
margin-bottom: 1rem; }
input,
textarea,
select,
fieldset {
margin-bottom: 1.5rem; }
pre,
blockquote,
dl,
figure,
table,
p,
ul,
ol,
form {
margin-bottom: 2.5rem; }
/* Utilities
*/
.u-full-width {
width: 100%;
box-sizing: border-box; }
.u-max-full-width {
max-width: 100%;
box-sizing: border-box; }
.u-pull-right {
float: right; }
.u-pull-left {
float: left; }
/* Misc
*/
hr {
margin-top: 3rem;
margin-bottom: 3.5rem;
border-width: 0;
border-top: 1px solid #E1E1E1; }
/* Clearing
*/
/* Self Clearing Goodness */
.container:after,
.row:after,
.u-cf {
content: "";
display: table;
clear: both; }
/* Media Queries
*/
/*
Note: The best way to structure the use of media queries is to create the queries
near the relevant code. For example, if you wanted to change the styles for buttons
on small devices, paste the mobile query code up in the buttons section and style it
there.
*/
/* Larger than mobile */
@media (min-width: 400px) {}
/* Larger than phablet (also point when grid becomes active) */
@media (min-width: 550px) {}
/* Larger than tablet */
@media (min-width: 750px) {}
/* Larger than desktop */
@media (min-width: 1000px) {}
/* Larger than Desktop HD */
@media (min-width: 1200px) {}

View File

@@ -0,0 +1,3 @@
p {
color:green;
}

View File

@@ -0,0 +1,14 @@
<!DOCTYPE html>
<html lang='en'>
<head>
<meta charset='utf-8' />
<title>Titlevon static/index.html</title>
</head>
<body>
<p>
Ich bin der <strong>Seiteninhalt <em>23</em></strong>
</p>
</body>
</html

View File

@@ -0,0 +1,3 @@
p {
color:green;
}

View File

@@ -0,0 +1,30 @@
from flask import Flask,render_template
from DBConnection import DBConnection
import logging
import configparser
logging.basicConfig( format='%(asctime)-15s [%(levelname)s] %(funcName)s: %(message)s', level=logging.DEBUG)
config = configparser.ConfigParser()
config.read('db.ini')
db_connection = DBConnection()
db_connection.connect(config['pidb']['host'],config['pidb']['user'],config['pidb']['password'],config['pidb']['database'])
app = Flask(__name__)
schueler = [
{'name':'Simpson','vorname': 'Bart','highlight': 'True'},
{'name':'Simpson','vorname':'Lisa',highlight': 'True'},
{'name':'van Houten','vorname':'Milhouse','highlight':'False'},
{'name':'Wiggum','vorname':'Ralph','highlight':'False'},
{'name':'Jones','vorname':'Jimbo','highlight':'False'}
]
@app.route('/')
def index():
return render_template('students.html',schueler=schueler)
if __name__ == '__main__':
app.run(host='0.0.0.0',port=8085, debug=True)

View File

@@ -0,0 +1,14 @@
<!DOCTYPE html>
<html lang='en'>
<head>
<meta charset='utf-8' />
<title>Title von templates/index.html</title>
</head>
<body>
<p>
Hier steht der <strong>Text der Seite <em>{{counter}}</em></strong>
</p>
</body>
</html>

View File

@@ -0,0 +1,23 @@
<!DOCTYPE html>
<html lang='de'>
<head>
<meta charset='utf-8' />
<title>Schüler</title>
</head>
<body>
<p>
Schülerverzeichnis
</p>
<ul>
{% for s in schueler %}
{%if s['name'] == "Simpson" %}
<li><b>{{s['name']}}, {{s['vorname']}}</b></li>
{%else %}
<li>{{s['name']}}, {{s['vorname']}}</li>
{%endif %}
{%endfor %}
</ul>
</body>
</html>

83
teil20/bin/activate Normal file
View File

@@ -0,0 +1,83 @@
# This file must be used with "source bin/activate" *from bash*
# you cannot run it directly
if [ "${BASH_SOURCE-}" = "$0" ]; then
echo "You must source this script: \$ source $0" >&2
exit 33
fi
deactivate () {
unset -f pydoc >/dev/null 2>&1 || true
# reset old environment variables
# ! [ -z ${VAR+_} ] returns true if VAR is declared at all
if ! [ -z "${_OLD_VIRTUAL_PATH:+_}" ] ; then
PATH="$_OLD_VIRTUAL_PATH"
export PATH
unset _OLD_VIRTUAL_PATH
fi
if ! [ -z "${_OLD_VIRTUAL_PYTHONHOME+_}" ] ; then
PYTHONHOME="$_OLD_VIRTUAL_PYTHONHOME"
export PYTHONHOME
unset _OLD_VIRTUAL_PYTHONHOME
fi
# The hash command must be called to get it to forget past
# commands. Without forgetting past commands the $PATH changes
# we made may not be respected
hash -r 2>/dev/null
if ! [ -z "${_OLD_VIRTUAL_PS1+_}" ] ; then
PS1="$_OLD_VIRTUAL_PS1"
export PS1
unset _OLD_VIRTUAL_PS1
fi
unset VIRTUAL_ENV
if [ ! "${1-}" = "nondestructive" ] ; then
# Self destruct!
unset -f deactivate
fi
}
# unset irrelevant variables
deactivate nondestructive
VIRTUAL_ENV='/home/pi/git/pythonkurs/teil20'
if ([ "$OSTYPE" = "cygwin" ] || [ "$OSTYPE" = "msys" ]) && $(command -v cygpath &> /dev/null) ; then
VIRTUAL_ENV=$(cygpath -u "$VIRTUAL_ENV")
fi
export VIRTUAL_ENV
_OLD_VIRTUAL_PATH="$PATH"
PATH="$VIRTUAL_ENV/bin:$PATH"
export PATH
# unset PYTHONHOME if set
if ! [ -z "${PYTHONHOME+_}" ] ; then
_OLD_VIRTUAL_PYTHONHOME="$PYTHONHOME"
unset PYTHONHOME
fi
if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT-}" ] ; then
_OLD_VIRTUAL_PS1="${PS1-}"
if [ "x" != x ] ; then
PS1="() ${PS1-}"
else
PS1="(`basename \"$VIRTUAL_ENV\"`) ${PS1-}"
fi
export PS1
fi
# Make sure to unalias pydoc if it's already there
alias pydoc 2>/dev/null >/dev/null && unalias pydoc || true
pydoc () {
python -m pydoc "$@"
}
# The hash command must be called to get it to forget past
# commands. Without forgetting past commands the $PATH changes
# we made may not be respected
hash -r 2>/dev/null

55
teil20/bin/activate.csh Normal file
View File

@@ -0,0 +1,55 @@
# This file must be used with "source bin/activate.csh" *from csh*.
# You cannot run it directly.
# Created by Davide Di Blasi <davidedb@gmail.com>.
set newline='\
'
alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH:q" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT:q" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; test "\!:*" != "nondestructive" && unalias deactivate && unalias pydoc'
# Unset irrelevant variables.
deactivate nondestructive
setenv VIRTUAL_ENV '/home/pi/git/pythonkurs/teil20'
set _OLD_VIRTUAL_PATH="$PATH:q"
setenv PATH "$VIRTUAL_ENV:q/bin:$PATH:q"
if ('' != "") then
set env_name = '() '
else
set env_name = '('"$VIRTUAL_ENV:t:q"') '
endif
if ( $?VIRTUAL_ENV_DISABLE_PROMPT ) then
if ( $VIRTUAL_ENV_DISABLE_PROMPT == "" ) then
set do_prompt = "1"
else
set do_prompt = "0"
endif
else
set do_prompt = "1"
endif
if ( $do_prompt == "1" ) then
# Could be in a non-interactive environment,
# in which case, $prompt is undefined and we wouldn't
# care about the prompt anyway.
if ( $?prompt ) then
set _OLD_VIRTUAL_PROMPT="$prompt:q"
if ( "$prompt:q" =~ *"$newline:q"* ) then
:
else
set prompt = "$env_name:q$prompt:q"
endif
endif
endif
unset env_name
unset do_prompt
alias pydoc python -m pydoc
rehash

100
teil20/bin/activate.fish Normal file
View File

@@ -0,0 +1,100 @@
# This file must be used using `source bin/activate.fish` *within a running fish ( http://fishshell.com ) session*.
# Do not run it directly.
function _bashify_path -d "Converts a fish path to something bash can recognize"
set fishy_path $argv
set bashy_path $fishy_path[1]
for path_part in $fishy_path[2..-1]
set bashy_path "$bashy_path:$path_part"
end
echo $bashy_path
end
function _fishify_path -d "Converts a bash path to something fish can recognize"
echo $argv | tr ':' '\n'
end
function deactivate -d 'Exit virtualenv mode and return to the normal environment.'
# reset old environment variables
if test -n "$_OLD_VIRTUAL_PATH"
# https://github.com/fish-shell/fish-shell/issues/436 altered PATH handling
if test (echo $FISH_VERSION | head -c 1) -lt 3
set -gx PATH (_fishify_path "$_OLD_VIRTUAL_PATH")
else
set -gx PATH $_OLD_VIRTUAL_PATH
end
set -e _OLD_VIRTUAL_PATH
end
if test -n "$_OLD_VIRTUAL_PYTHONHOME"
set -gx PYTHONHOME "$_OLD_VIRTUAL_PYTHONHOME"
set -e _OLD_VIRTUAL_PYTHONHOME
end
if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
and functions -q _old_fish_prompt
# Set an empty local `$fish_function_path` to allow the removal of `fish_prompt` using `functions -e`.
set -l fish_function_path
# Erase virtualenv's `fish_prompt` and restore the original.
functions -e fish_prompt
functions -c _old_fish_prompt fish_prompt
functions -e _old_fish_prompt
set -e _OLD_FISH_PROMPT_OVERRIDE
end
set -e VIRTUAL_ENV
if test "$argv[1]" != 'nondestructive'
# Self-destruct!
functions -e pydoc
functions -e deactivate
functions -e _bashify_path
functions -e _fishify_path
end
end
# Unset irrelevant variables.
deactivate nondestructive
set -gx VIRTUAL_ENV '/home/pi/git/pythonkurs/teil20'
# https://github.com/fish-shell/fish-shell/issues/436 altered PATH handling
if test (echo $FISH_VERSION | head -c 1) -lt 3
set -gx _OLD_VIRTUAL_PATH (_bashify_path $PATH)
else
set -gx _OLD_VIRTUAL_PATH $PATH
end
set -gx PATH "$VIRTUAL_ENV"'/bin' $PATH
# Unset `$PYTHONHOME` if set.
if set -q PYTHONHOME
set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
set -e PYTHONHOME
end
function pydoc
python -m pydoc $argv
end
if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
# Copy the current `fish_prompt` function as `_old_fish_prompt`.
functions -c fish_prompt _old_fish_prompt
function fish_prompt
# Run the user's prompt first; it might depend on (pipe)status.
set -l prompt (_old_fish_prompt)
# Prompt override provided?
# If not, just prepend the environment name.
if test -n ''
printf '(%s) ' ''
else
printf '(%s) ' (basename "$VIRTUAL_ENV")
end
string join -- \n $prompt # handle multi-line prompts
end
set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
end

117
teil20/bin/activate.nu Normal file
View File

@@ -0,0 +1,117 @@
# virtualenv activation module
# Activate with `overlay use activate.nu`
# Deactivate with `deactivate`, as usual
#
# To customize the overlay name, you can call `overlay use activate.nu as foo`,
# but then simply `deactivate` won't work because it is just an alias to hide
# the "activate" overlay. You'd need to call `overlay hide foo` manually.
export-env {
def is-string [x] {
($x | describe) == 'string'
}
def has-env [name: string] {
$name in (env).name
}
# Emulates a `test -z`, but btter as it handles e.g 'false'
def is-env-true [name: string] {
if (has-env $name) {
# Try to parse 'true', '0', '1', and fail if not convertible
let parsed = do -i { $env | get $name | into bool }
if ($parsed | describe) == 'bool' {
$parsed
} else {
not ($env | get $name | is-empty)
}
} else {
false
}
}
let is_windows = ($nu.os-info.name | str downcase) == 'windows'
let virtual_env = '/home/pi/git/pythonkurs/teil20'
let bin = 'bin'
let path_sep = (char esep)
let path_name = if $is_windows {
if (has-env 'Path') {
'Path'
} else {
'PATH'
}
} else {
'PATH'
}
let old_path = (
if $is_windows {
if (has-env 'Path') {
$env.Path
} else {
$env.PATH
}
} else {
$env.PATH
} | if (is-string $in) {
# if Path/PATH is a string, make it a list
$in | split row $path_sep | path expand
} else {
$in
}
)
let venv_path = ([$virtual_env $bin] | path join)
let new_path = ($old_path | prepend $venv_path | str collect $path_sep)
let new_env = {
$path_name : $new_path
VIRTUAL_ENV : $virtual_env
}
let new_env = if (is-env-true 'VIRTUAL_ENV_DISABLE_PROMPT') {
$new_env
} else {
# Creating the new prompt for the session
let virtual_prompt = if ('' == '') {
$'(char lparen)($virtual_env | path basename)(char rparen) '
} else {
'() '
}
# Back up the old prompt builder
let old_prompt_command = if (has-env 'VIRTUAL_ENV') and (has-env '_OLD_PROMPT_COMMAND') {
$env._OLD_PROMPT_COMMAND
} else {
if (has-env 'PROMPT_COMMAND') {
$env.PROMPT_COMMAND
} else {
''
}
}
# If there is no default prompt, then only the env is printed in the prompt
let new_prompt = if (has-env 'PROMPT_COMMAND') {
if ($old_prompt_command | describe) == 'block' {
{ $'($virtual_prompt)(do $old_prompt_command)' }
} else {
{ $'($virtual_prompt)($old_prompt_command)' }
}
} else {
{ $'($virtual_prompt)' }
}
$new_env | merge {
_OLD_VIRTUAL_PATH : ($old_path | str collect $path_sep)
_OLD_PROMPT_COMMAND : $old_prompt_command
PROMPT_COMMAND : $new_prompt
VIRTUAL_PROMPT : $virtual_prompt
}
}
# Environment variables that will be loaded as the virtual env
load-env $new_env
}
export alias pydoc = python -m pydoc
export alias deactivate = overlay hide activate

60
teil20/bin/activate.ps1 Normal file
View File

@@ -0,0 +1,60 @@
$script:THIS_PATH = $myinvocation.mycommand.path
$script:BASE_DIR = Split-Path (Resolve-Path "$THIS_PATH/..") -Parent
function global:deactivate([switch] $NonDestructive) {
if (Test-Path variable:_OLD_VIRTUAL_PATH) {
$env:PATH = $variable:_OLD_VIRTUAL_PATH
Remove-Variable "_OLD_VIRTUAL_PATH" -Scope global
}
if (Test-Path function:_old_virtual_prompt) {
$function:prompt = $function:_old_virtual_prompt
Remove-Item function:\_old_virtual_prompt
}
if ($env:VIRTUAL_ENV) {
Remove-Item env:VIRTUAL_ENV -ErrorAction SilentlyContinue
}
if (!$NonDestructive) {
# Self destruct!
Remove-Item function:deactivate
Remove-Item function:pydoc
}
}
function global:pydoc {
python -m pydoc $args
}
# unset irrelevant variables
deactivate -nondestructive
$VIRTUAL_ENV = $BASE_DIR
$env:VIRTUAL_ENV = $VIRTUAL_ENV
New-Variable -Scope global -Name _OLD_VIRTUAL_PATH -Value $env:PATH
$env:PATH = "$env:VIRTUAL_ENV/bin:" + $env:PATH
if (!$env:VIRTUAL_ENV_DISABLE_PROMPT) {
function global:_old_virtual_prompt {
""
}
$function:_old_virtual_prompt = $function:prompt
if ("" -ne "") {
function global:prompt {
# Add the custom prefix to the existing prompt
$previous_prompt_value = & $function:_old_virtual_prompt
("() " + $previous_prompt_value)
}
}
else {
function global:prompt {
# Add a prefix to the current prompt, but don't discard it.
$previous_prompt_value = & $function:_old_virtual_prompt
$new_prompt_value = "($( Split-Path $env:VIRTUAL_ENV -Leaf )) "
($new_prompt_value + $previous_prompt_value)
}
}
}

View File

@@ -0,0 +1,31 @@
"""Activate virtualenv for current interpreter:
Use exec(open(this_file).read(), {'__file__': this_file}).
This can be used when you must use an existing Python interpreter, not the virtualenv bin/python.
"""
import os
import site
import sys
try:
abs_file = os.path.abspath(__file__)
except NameError:
raise AssertionError("You must use exec(open(this_file).read(), {'__file__': this_file}))")
bin_dir = os.path.dirname(abs_file)
base = bin_dir[: -len("bin") - 1] # strip away the bin part from the __file__, plus the path separator
# prepend bin to PATH (this file is inside the bin directory)
os.environ["PATH"] = os.pathsep.join([bin_dir] + os.environ.get("PATH", "").split(os.pathsep))
os.environ["VIRTUAL_ENV"] = base # virtual env is right above bin directory
# add the virtual environments libraries to the host python import mechanism
prev_length = len(sys.path)
for lib in "../lib/python3.11/site-packages".split(os.pathsep):
path = os.path.realpath(os.path.join(bin_dir, lib))
site.addsitedir(path.decode("utf-8") if "" else path)
sys.path[:] = sys.path[prev_length:] + sys.path[0:prev_length]
sys.real_prefix = sys.prefix
sys.prefix = base

8
teil20/bin/f2py Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from numpy.f2py.f2py2e import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/f2py3 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from numpy.f2py.f2py2e import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/f2py3.11 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from numpy.f2py.f2py2e import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/ninja Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from ninja import ninja
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(ninja())

8
teil20/bin/normalizer Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from charset_normalizer.cli.normalizer import cli_detect
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(cli_detect())

8
teil20/bin/pip Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/pip-3.11 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/pip3 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/pip3.11 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from pip._internal.cli.main import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

1
teil20/bin/python Symbolic link
View File

@@ -0,0 +1 @@
/usr/bin/python3

1
teil20/bin/python3 Symbolic link
View File

@@ -0,0 +1 @@
python

1
teil20/bin/python3.11 Symbolic link
View File

@@ -0,0 +1 @@
python

8
teil20/bin/wheel Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from wheel.cli import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/wheel-3.11 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from wheel.cli import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/wheel3 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from wheel.cli import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

8
teil20/bin/wheel3.11 Executable file
View File

@@ -0,0 +1,8 @@
#!/home/pi/git/pythonkurs/teil20/bin/python
# -*- coding: utf-8 -*-
import re
import sys
from wheel.cli import main
if __name__ == '__main__':
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
sys.exit(main())

View File

@@ -0,0 +1,222 @@
# don't import any costly modules
import sys
import os
is_pypy = '__pypy__' in sys.builtin_module_names
def warn_distutils_present():
if 'distutils' not in sys.modules:
return
if is_pypy and sys.version_info < (3, 7):
# PyPy for 3.6 unconditionally imports distutils, so bypass the warning
# https://foss.heptapod.net/pypy/pypy/-/blob/be829135bc0d758997b3566062999ee8b23872b4/lib-python/3/site.py#L250
return
import warnings
warnings.warn(
"Distutils was imported before Setuptools, but importing Setuptools "
"also replaces the `distutils` module in `sys.modules`. This may lead "
"to undesirable behaviors or errors. To avoid these issues, avoid "
"using distutils directly, ensure that setuptools is installed in the "
"traditional way (e.g. not an editable install), and/or make sure "
"that setuptools is always imported before distutils."
)
def clear_distutils():
if 'distutils' not in sys.modules:
return
import warnings
warnings.warn("Setuptools is replacing distutils.")
mods = [
name
for name in sys.modules
if name == "distutils" or name.startswith("distutils.")
]
for name in mods:
del sys.modules[name]
def enabled():
"""
Allow selection of distutils by environment variable.
"""
which = os.environ.get('SETUPTOOLS_USE_DISTUTILS', 'local')
return which == 'local'
def ensure_local_distutils():
import importlib
clear_distutils()
# With the DistutilsMetaFinder in place,
# perform an import to cause distutils to be
# loaded from setuptools._distutils. Ref #2906.
with shim():
importlib.import_module('distutils')
# check that submodules load as expected
core = importlib.import_module('distutils.core')
assert '_distutils' in core.__file__, core.__file__
assert 'setuptools._distutils.log' not in sys.modules
def do_override():
"""
Ensure that the local copy of distutils is preferred over stdlib.
See https://github.com/pypa/setuptools/issues/417#issuecomment-392298401
for more motivation.
"""
if enabled():
warn_distutils_present()
ensure_local_distutils()
class _TrivialRe:
def __init__(self, *patterns):
self._patterns = patterns
def match(self, string):
return all(pat in string for pat in self._patterns)
class DistutilsMetaFinder:
def find_spec(self, fullname, path, target=None):
# optimization: only consider top level modules and those
# found in the CPython test suite.
if path is not None and not fullname.startswith('test.'):
return
method_name = 'spec_for_{fullname}'.format(**locals())
method = getattr(self, method_name, lambda: None)
return method()
def spec_for_distutils(self):
if self.is_cpython():
return
import importlib
import importlib.abc
import importlib.util
try:
mod = importlib.import_module('setuptools._distutils')
except Exception:
# There are a couple of cases where setuptools._distutils
# may not be present:
# - An older Setuptools without a local distutils is
# taking precedence. Ref #2957.
# - Path manipulation during sitecustomize removes
# setuptools from the path but only after the hook
# has been loaded. Ref #2980.
# In either case, fall back to stdlib behavior.
return
class DistutilsLoader(importlib.abc.Loader):
def create_module(self, spec):
mod.__name__ = 'distutils'
return mod
def exec_module(self, module):
pass
return importlib.util.spec_from_loader(
'distutils', DistutilsLoader(), origin=mod.__file__
)
@staticmethod
def is_cpython():
"""
Suppress supplying distutils for CPython (build and tests).
Ref #2965 and #3007.
"""
return os.path.isfile('pybuilddir.txt')
def spec_for_pip(self):
"""
Ensure stdlib distutils when running under pip.
See pypa/pip#8761 for rationale.
"""
if self.pip_imported_during_build():
return
clear_distutils()
self.spec_for_distutils = lambda: None
@classmethod
def pip_imported_during_build(cls):
"""
Detect if pip is being imported in a build script. Ref #2355.
"""
import traceback
return any(
cls.frame_file_is_setup(frame) for frame, line in traceback.walk_stack(None)
)
@staticmethod
def frame_file_is_setup(frame):
"""
Return True if the indicated frame suggests a setup.py file.
"""
# some frames may not have __file__ (#2940)
return frame.f_globals.get('__file__', '').endswith('setup.py')
def spec_for_sensitive_tests(self):
"""
Ensure stdlib distutils when running select tests under CPython.
python/cpython#91169
"""
clear_distutils()
self.spec_for_distutils = lambda: None
sensitive_tests = (
[
'test.test_distutils',
'test.test_peg_generator',
'test.test_importlib',
]
if sys.version_info < (3, 10)
else [
'test.test_distutils',
]
)
for name in DistutilsMetaFinder.sensitive_tests:
setattr(
DistutilsMetaFinder,
f'spec_for_{name}',
DistutilsMetaFinder.spec_for_sensitive_tests,
)
DISTUTILS_FINDER = DistutilsMetaFinder()
def add_shim():
DISTUTILS_FINDER in sys.meta_path or insert_shim()
class shim:
def __enter__(self):
insert_shim()
def __exit__(self, exc, value, tb):
remove_shim()
def insert_shim():
sys.meta_path.insert(0, DISTUTILS_FINDER)
def remove_shim():
try:
sys.meta_path.remove(DISTUTILS_FINDER)
except ValueError:
pass

View File

@@ -0,0 +1 @@
__import__('_distutils_hack').do_override()

View File

@@ -0,0 +1 @@
import _virtualenv

View File

@@ -0,0 +1,130 @@
"""Patches that are applied at runtime to the virtual environment"""
# -*- coding: utf-8 -*-
import os
import sys
VIRTUALENV_PATCH_FILE = os.path.join(__file__)
def patch_dist(dist):
"""
Distutils allows user to configure some arguments via a configuration file:
https://docs.python.org/3/install/index.html#distutils-configuration-files
Some of this arguments though don't make sense in context of the virtual environment files, let's fix them up.
"""
# we cannot allow some install config as that would get packages installed outside of the virtual environment
old_parse_config_files = dist.Distribution.parse_config_files
def parse_config_files(self, *args, **kwargs):
result = old_parse_config_files(self, *args, **kwargs)
install = self.get_option_dict("install")
if "prefix" in install: # the prefix governs where to install the libraries
install["prefix"] = VIRTUALENV_PATCH_FILE, os.path.abspath(sys.prefix)
for base in ("purelib", "platlib", "headers", "scripts", "data"):
key = "install_{}".format(base)
if key in install: # do not allow global configs to hijack venv paths
install.pop(key, None)
return result
dist.Distribution.parse_config_files = parse_config_files
# Import hook that patches some modules to ignore configuration values that break package installation in case
# of virtual environments.
_DISTUTILS_PATCH = "distutils.dist", "setuptools.dist"
if sys.version_info > (3, 4):
# https://docs.python.org/3/library/importlib.html#setting-up-an-importer
class _Finder:
"""A meta path finder that allows patching the imported distutils modules"""
fullname = None
# lock[0] is threading.Lock(), but initialized lazily to avoid importing threading very early at startup,
# because there are gevent-based applications that need to be first to import threading by themselves.
# See https://github.com/pypa/virtualenv/issues/1895 for details.
lock = []
def find_spec(self, fullname, path, target=None): # noqa: U100
if fullname in _DISTUTILS_PATCH and self.fullname is None:
# initialize lock[0] lazily
if len(self.lock) == 0:
import threading
lock = threading.Lock()
# there is possibility that two threads T1 and T2 are simultaneously running into find_spec,
# observing .lock as empty, and further going into hereby initialization. However due to the GIL,
# list.append() operation is atomic and this way only one of the threads will "win" to put the lock
# - that every thread will use - into .lock[0].
# https://docs.python.org/3/faq/library.html#what-kinds-of-global-value-mutation-are-thread-safe
self.lock.append(lock)
from functools import partial
from importlib.util import find_spec
with self.lock[0]:
self.fullname = fullname
try:
spec = find_spec(fullname, path)
if spec is not None:
# https://www.python.org/dev/peps/pep-0451/#how-loading-will-work
is_new_api = hasattr(spec.loader, "exec_module")
func_name = "exec_module" if is_new_api else "load_module"
old = getattr(spec.loader, func_name)
func = self.exec_module if is_new_api else self.load_module
if old is not func:
try:
setattr(spec.loader, func_name, partial(func, old))
except AttributeError:
pass # C-Extension loaders are r/o such as zipimporter with <python 3.7
return spec
finally:
self.fullname = None
@staticmethod
def exec_module(old, module):
old(module)
if module.__name__ in _DISTUTILS_PATCH:
patch_dist(module)
@staticmethod
def load_module(old, name):
module = old(name)
if module.__name__ in _DISTUTILS_PATCH:
patch_dist(module)
return module
sys.meta_path.insert(0, _Finder())
else:
# https://www.python.org/dev/peps/pep-0302/
from imp import find_module
from pkgutil import ImpImporter, ImpLoader
class _VirtualenvImporter(object, ImpImporter):
def __init__(self, path=None):
object.__init__(self)
ImpImporter.__init__(self, path)
def find_module(self, fullname, path=None):
if fullname in _DISTUTILS_PATCH:
try:
return _VirtualenvLoader(fullname, *find_module(fullname.split(".")[-1], path))
except ImportError:
pass
return None
class _VirtualenvLoader(object, ImpLoader):
def __init__(self, fullname, file, filename, etc):
object.__init__(self)
ImpLoader.__init__(self, fullname, file, filename, etc)
def load_module(self, fullname):
module = super(_VirtualenvLoader, self).load_module(fullname)
patch_dist(module)
module.__loader__ = None # distlib fallback
return module
sys.meta_path.append(_VirtualenvImporter())

View File

@@ -0,0 +1,21 @@
This package contains a modified version of ca-bundle.crt:
ca-bundle.crt -- Bundle of CA Root Certificates
Certificate data from Mozilla as of: Thu Nov 3 19:04:19 2011#
This is a bundle of X.509 certificates of public Certificate Authorities
(CA). These were automatically extracted from Mozilla's root certificates
file (certdata.txt). This file can be found in the mozilla source tree:
https://hg.mozilla.org/mozilla-central/file/tip/security/nss/lib/ckfw/builtins/certdata.txt
It contains the certificates in PEM format and therefore
can be directly used with curl / libcurl / php_curl, or with
an Apache+mod_ssl webserver for SSL client authentication.
Just configure this file as the SSLCACertificateFile.#
***** BEGIN LICENSE BLOCK *****
This Source Code Form is subject to the terms of the Mozilla Public License,
v. 2.0. If a copy of the MPL was not distributed with this file, You can obtain
one at http://mozilla.org/MPL/2.0/.
***** END LICENSE BLOCK *****
@(#) $RCSfile: certdata.txt,v $ $Revision: 1.80 $ $Date: 2011/11/03 15:11:58 $

View File

@@ -0,0 +1,66 @@
Metadata-Version: 2.1
Name: certifi
Version: 2023.7.22
Summary: Python package for providing Mozilla's CA Bundle.
Home-page: https://github.com/certifi/python-certifi
Author: Kenneth Reitz
Author-email: me@kennethreitz.com
License: MPL-2.0
Project-URL: Source, https://github.com/certifi/python-certifi
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
Classifier: Natural Language :: English
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
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
Requires-Python: >=3.6
License-File: LICENSE
Certifi: Python SSL Certificates
================================
Certifi provides Mozilla's carefully curated collection of Root Certificates for
validating the trustworthiness of SSL certificates while verifying the identity
of TLS hosts. It has been extracted from the `Requests`_ project.
Installation
------------
``certifi`` is available on PyPI. Simply install it with ``pip``::
$ pip install certifi
Usage
-----
To reference the installed certificate authority (CA) bundle, you can use the
built-in function::
>>> import certifi
>>> certifi.where()
'/usr/local/lib/python3.7/site-packages/certifi/cacert.pem'
Or from the command line::
$ python -m certifi
/usr/local/lib/python3.7/site-packages/certifi/cacert.pem
Enjoy!
.. _`Requests`: https://requests.readthedocs.io/en/master/
Addition/Removal of Certificates
--------------------------------
Certifi does not support any addition/removal or other modification of the
CA trust store content. This project is intended to provide a reliable and
highly portable root of trust to python deployments. Look to upstream projects
for methods to use alternate trust.

View File

@@ -0,0 +1,14 @@
certifi-2023.7.22.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
certifi-2023.7.22.dist-info/LICENSE,sha256=oC9sY4-fuE0G93ZMOrCF2K9-2luTwWbaVDEkeQd8b7A,1052
certifi-2023.7.22.dist-info/METADATA,sha256=RgdzxZw4VOIL_B8Rnp13_JJcWJyeRNQo_N39WoaO6y0,2171
certifi-2023.7.22.dist-info/RECORD,,
certifi-2023.7.22.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
certifi-2023.7.22.dist-info/top_level.txt,sha256=KMu4vUCfsjLrkPbSNdgdekS-pVJzBAJFO__nI8NF6-U,8
certifi/__init__.py,sha256=L_j-d0kYuA_MzA2_2hraF1ovf6KT6DTquRdV3paQwOk,94
certifi/__main__.py,sha256=xBBoj905TUWBLRGANOcf7oi6e-3dMP4cEoG9OyMs11g,243
certifi/__pycache__/__init__.cpython-311.pyc,,
certifi/__pycache__/__main__.cpython-311.pyc,,
certifi/__pycache__/core.cpython-311.pyc,,
certifi/cacert.pem,sha256=eU0Dn_3yd8BH4m8sfVj4Glhl2KDrcCSg-sEWT-pNJ88,281617
certifi/core.py,sha256=lhewz0zFb2b4ULsQurElmloYwQoecjWzPqY67P8T7iM,4219
certifi/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0

View File

@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.40.0)
Root-Is-Purelib: true
Tag: py3-none-any

View File

@@ -0,0 +1,4 @@
from .core import contents, where
__all__ = ["contents", "where"]
__version__ = "2023.07.22"

View File

@@ -0,0 +1,12 @@
import argparse
from certifi import contents, where
parser = argparse.ArgumentParser()
parser.add_argument("-c", "--contents", action="store_true")
args = parser.parse_args()
if args.contents:
print(contents())
else:
print(where())

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,108 @@
"""
certifi.py
~~~~~~~~~~
This module returns the installation location of cacert.pem or its contents.
"""
import sys
if sys.version_info >= (3, 11):
from importlib.resources import as_file, files
_CACERT_CTX = None
_CACERT_PATH = None
def where() -> str:
# This is slightly terrible, but we want to delay extracting the file
# in cases where we're inside of a zipimport situation until someone
# actually calls where(), but we don't want to re-extract the file
# on every call of where(), so we'll do it once then store it in a
# global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you to
# manage the cleanup of this file, so it doesn't actually return a
# path, it returns a context manager that will give you the path
# when you enter it and will do any cleanup when you leave it. In
# the common case of not needing a temporary file, it will just
# return the file system location and the __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = as_file(files("certifi").joinpath("cacert.pem"))
_CACERT_PATH = str(_CACERT_CTX.__enter__())
return _CACERT_PATH
def contents() -> str:
return files("certifi").joinpath("cacert.pem").read_text(encoding="ascii")
elif sys.version_info >= (3, 7):
from importlib.resources import path as get_path, read_text
_CACERT_CTX = None
_CACERT_PATH = None
def where() -> str:
# This is slightly terrible, but we want to delay extracting the
# file in cases where we're inside of a zipimport situation until
# someone actually calls where(), but we don't want to re-extract
# the file on every call of where(), so we'll do it once then store
# it in a global variable.
global _CACERT_CTX
global _CACERT_PATH
if _CACERT_PATH is None:
# This is slightly janky, the importlib.resources API wants you
# to manage the cleanup of this file, so it doesn't actually
# return a path, it returns a context manager that will give
# you the path when you enter it and will do any cleanup when
# you leave it. In the common case of not needing a temporary
# file, it will just return the file system location and the
# __exit__() is a no-op.
#
# We also have to hold onto the actual context manager, because
# it will do the cleanup whenever it gets garbage collected, so
# we will also store that at the global level as well.
_CACERT_CTX = get_path("certifi", "cacert.pem")
_CACERT_PATH = str(_CACERT_CTX.__enter__())
return _CACERT_PATH
def contents() -> str:
return read_text("certifi", "cacert.pem", encoding="ascii")
else:
import os
import types
from typing import Union
Package = Union[types.ModuleType, str]
Resource = Union[str, "os.PathLike"]
# This fallback will work for Python versions prior to 3.7 that lack the
# importlib.resources module but relies on the existing `where` function
# so won't address issues with environments like PyOxidizer that don't set
# __file__ on modules.
def read_text(
package: Package,
resource: Resource,
encoding: str = 'utf-8',
errors: str = 'strict'
) -> str:
with open(where(), encoding=encoding) as data:
return data.read()
# If we don't have importlib.resources, then we will just do the old logic
# of assuming we're on the filesystem and munge the path directly.
def where() -> str:
f = os.path.dirname(__file__)
return os.path.join(f, "cacert.pem")
def contents() -> str:
return read_text("certifi", "cacert.pem", encoding="ascii")

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.

View File

@@ -0,0 +1,628 @@
Metadata-Version: 2.1
Name: charset-normalizer
Version: 3.2.0
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
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,charset,charset-detector,detector,normalization,unicode,chardet,detect
Classifier: Development Status :: 5 - Production/Stable
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 :: 3.7
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: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: Implementation :: PyPy
Classifier: Topic :: Text Processing :: Linguistic
Classifier: Topic :: Utilities
Classifier: Typing :: Typed
Requires-Python: >=3.7.0
Description-Content-Type: text/markdown
License-File: LICENSE
Provides-Extra: unicode_backport
<h1 align="center">Charset Detection, for Everyone 👋</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://pepy.tech/project/charset-normalizer/">
<img alt="Download Count Total" src="https://pepy.tech/badge/charset-normalizer/month" />
</a>
<a href="https://bestpractices.coreinfrastructure.org/projects/7297">
<img src="https://bestpractices.coreinfrastructure.org/projects/7297/badge">
</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 | ✅ | ✅ | ✅ |
| `License` | LGPL-2.1<br>_restrictive_ | MIT | MPL-1.1<br>_restrictive_ |
| `Native Python` | ✅ | ✅ | ❌ |
| `Detect spoken language` | ❌ | ✅ | N/A |
| `UnicodeDecodeError Safety` | ❌ | ✅ | ❌ |
| `Whl Size` | 193.6 kB | 40 kB | ~200 kB |
| `Supported Encoding` | 33 | 🎉 [90](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)
## ⚡ 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) | 86 % | 200 ms | 5 file/sec |
| charset-normalizer | **98 %** | **10 ms** | 100 file/sec |
| Package | 99th percentile | 95th percentile | 50th percentile |
|-----------------------------------------------|:---------------:|:---------------:|:---------------:|
| [chardet](https://github.com/chardet/chardet) | 1200 ms | 287 ms | 23 ms |
| charset-normalizer | 100 ms | 50 ms | 5 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.
> Keep in mind that the stats are generous and that Chardet accuracy vs our is measured using Chardet initial capability
> (eg. Supported Encoding) Challenge-them if you want.
## ✨ Installation
Using pip:
```sh
pip install charset-normalizer -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
```
🎉 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()))
```
*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 noise, 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 noise/mess and coherence according to **YOU ?**
*Noise :* 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 noise is probably incomplete, 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.
## ⚠️ About Python EOLs
**If you are running:**
- Python >=2.7,<3.5: Unsupported
- Python 3.5: charset-normalizer < 2.1
- Python 3.6: charset-normalizer < 3.1
Upgrade your Python interpreter as soon as possible.
## 👤 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 © [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/)
## 💼 For Enterprise
Professional support for charset-normalizer is available as part of the [Tidelift
Subscription][1]. Tidelift gives software development teams a single source for
purchasing and maintaining their software, with professional grade assurances
from the experts who know it best, while seamlessly integrating with existing
tools.
[1]: https://tidelift.com/subscription/pkg/pypi-charset-normalizer?utm_source=pypi-charset-normalizer&utm_medium=readme
# Changelog
All notable changes to charset-normalizer will be documented in this file. This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [3.2.0](https://github.com/Ousret/charset_normalizer/compare/3.1.0...3.2.0) (2023-06-07)
### Changed
- Typehint for function `from_path` no longer enforce `PathLike` as its first argument
- Minor improvement over the global detection reliability
### Added
- Introduce function `is_binary` that relies on main capabilities, and optimized to detect binaries
- Propagate `enable_fallback` argument throughout `from_bytes`, `from_path`, and `from_fp` that allow a deeper control over the detection (default True)
- Explicit support for Python 3.12
### Fixed
- Edge case detection failure where a file would contain 'very-long' camel cased word (Issue #289)
## [3.1.0](https://github.com/Ousret/charset_normalizer/compare/3.0.1...3.1.0) (2023-03-06)
### Added
- Argument `should_rename_legacy` for legacy function `detect` and disregard any new arguments without errors (PR #262)
### Removed
- Support for Python 3.6 (PR #260)
### Changed
- Optional speedup provided by mypy/c 1.0.1
## [3.0.1](https://github.com/Ousret/charset_normalizer/compare/3.0.0...3.0.1) (2022-11-18)
### Fixed
- Multi-bytes cutter/chunk generator did not always cut correctly (PR #233)
### Changed
- Speedup provided by mypy/c 0.990 on Python >= 3.7
## [3.0.0](https://github.com/Ousret/charset_normalizer/compare/2.1.1...3.0.0) (2022-10-20)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
- Sphinx warnings when generating the documentation
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [3.0.0rc1](https://github.com/Ousret/charset_normalizer/compare/3.0.0b2...3.0.0rc1) (2022-10-18)
### Added
- Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results
- Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES
- Add parameter `language_threshold` in `from_bytes`, `from_path` and `from_fp` to adjust the minimum expected coherence ratio
### Changed
- Build with static metadata using 'build' frontend
- Make the language detection stricter
### Fixed
- CLI with opt --normalize fail when using full path for files
- TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it
### Removed
- Coherence detector no longer return 'Simple English' instead return 'English'
- Coherence detector no longer return 'Classical Chinese' instead return 'Chinese'
## [3.0.0b2](https://github.com/Ousret/charset_normalizer/compare/3.0.0b1...3.0.0b2) (2022-08-21)
### Added
- `normalizer --version` now specify if current version provide extra speedup (meaning mypyc compilation whl)
### Removed
- Breaking: Method `first()` and `best()` from CharsetMatch
- UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII)
### Fixed
- Sphinx warnings when generating the documentation
## [3.0.0b1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...3.0.0b1) (2022-08-15)
### Changed
- Optional: Module `md.py` can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1
### Removed
- Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches
- Breaking: Top-level function `normalize`
- Breaking: Properties `chaos_secondary_pass`, `coherence_non_latin` and `w_counter` from CharsetMatch
- Support for the backport `unicodedata2`
## [2.1.1](https://github.com/Ousret/charset_normalizer/compare/2.1.0...2.1.1) (2022-08-19)
### Deprecated
- Function `normalize` scheduled for removal in 3.0
### Changed
- Removed useless call to decode in fn is_unprintable (#206)
### Fixed
- Third-party library (i18n xgettext) crashing not recognizing utf_8 (PEP 263) with underscore from [@aleksandernovikov](https://github.com/aleksandernovikov) (#204)
## [2.1.0](https://github.com/Ousret/charset_normalizer/compare/2.0.12...2.1.0) (2022-06-19)
### Added
- Output the Unicode table version when running the CLI with `--version` (PR #194)
### Changed
- Re-use decoded buffer for single byte character sets from [@nijel](https://github.com/nijel) (PR #175)
- Fixing some performance bottlenecks from [@deedy5](https://github.com/deedy5) (PR #183)
### Fixed
- Workaround potential bug in cpython with Zero Width No-Break Space located in Arabic Presentation Forms-B, Unicode 1.1 not acknowledged as space (PR #175)
- CLI default threshold aligned with the API threshold from [@oleksandr-kuzmenko](https://github.com/oleksandr-kuzmenko) (PR #181)
### Removed
- Support for Python 3.5 (PR #192)
### Deprecated
- Use of backport unicodedata from `unicodedata2` as Python is quickly catching up, scheduled for removal in 3.0 (PR #194)
## [2.0.12](https://github.com/Ousret/charset_normalizer/compare/2.0.11...2.0.12) (2022-02-12)
### Fixed
- ASCII miss-detection on rare cases (PR #170)
## [2.0.11](https://github.com/Ousret/charset_normalizer/compare/2.0.10...2.0.11) (2022-01-30)
### Added
- Explicit support for Python 3.11 (PR #164)
### Changed
- The logging behavior have been completely reviewed, now using only TRACE and DEBUG levels (PR #163 #165)
## [2.0.10](https://github.com/Ousret/charset_normalizer/compare/2.0.9...2.0.10) (2022-01-04)
### Fixed
- Fallback match entries might lead to UnicodeDecodeError for large bytes sequence (PR #154)
### Changed
- Skipping the language-detection (CD) on ASCII (PR #155)
## [2.0.9](https://github.com/Ousret/charset_normalizer/compare/2.0.8...2.0.9) (2021-12-03)
### Changed
- Moderating the logging impact (since 2.0.8) for specific environments (PR #147)
### Fixed
- Wrong logging level applied when setting kwarg `explain` to True (PR #146)
## [2.0.8](https://github.com/Ousret/charset_normalizer/compare/2.0.7...2.0.8) (2021-11-24)
### Changed
- Improvement over Vietnamese detection (PR #126)
- MD improvement on trailing data and long foreign (non-pure latin) data (PR #124)
- Efficiency improvements in cd/alphabet_languages from [@adbar](https://github.com/adbar) (PR #122)
- call sum() without an intermediary list following PEP 289 recommendations from [@adbar](https://github.com/adbar) (PR #129)
- Code style as refactored by Sourcery-AI (PR #131)
- Minor adjustment on the MD around european words (PR #133)
- Remove and replace SRTs from assets / tests (PR #139)
- Initialize the library logger with a `NullHandler` by default from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Setting kwarg `explain` to True will add provisionally (bounded to function lifespan) a specific stream handler (PR #135)
### Fixed
- Fix large (misleading) sequence giving UnicodeDecodeError (PR #137)
- Avoid using too insignificant chunk (PR #137)
### Added
- Add and expose function `set_logging_handler` to configure a specific StreamHandler from [@nmaynes](https://github.com/nmaynes) (PR #135)
- Add `CHANGELOG.md` entries, format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) (PR #141)
## [2.0.7](https://github.com/Ousret/charset_normalizer/compare/2.0.6...2.0.7) (2021-10-11)
### Added
- Add support for Kazakh (Cyrillic) language detection (PR #109)
### Changed
- Further, improve inferring the language from a given single-byte code page (PR #112)
- Vainly trying to leverage PEP263 when PEP3120 is not supported (PR #116)
- Refactoring for potential performance improvements in loops from [@adbar](https://github.com/adbar) (PR #113)
- Various detection improvement (MD+CD) (PR #117)
### Removed
- Remove redundant logging entry about detected language(s) (PR #115)
### Fixed
- Fix a minor inconsistency between Python 3.5 and other versions regarding language detection (PR #117 #102)
## [2.0.6](https://github.com/Ousret/charset_normalizer/compare/2.0.5...2.0.6) (2021-09-18)
### Fixed
- Unforeseen regression with the loss of the backward-compatibility with some older minor of Python 3.5.x (PR #100)
- Fix CLI crash when using --minimal output in certain cases (PR #103)
### Changed
- Minor improvement to the detection efficiency (less than 1%) (PR #106 #101)
## [2.0.5](https://github.com/Ousret/charset_normalizer/compare/2.0.4...2.0.5) (2021-09-14)
### Changed
- The project now comply with: flake8, mypy, isort and black to ensure a better overall quality (PR #81)
- The BC-support with v1.x was improved, the old staticmethods are restored (PR #82)
- The Unicode detection is slightly improved (PR #93)
- Add syntax sugar \_\_bool\_\_ for results CharsetMatches list-container (PR #91)
### Removed
- The project no longer raise warning on tiny content given for detection, will be simply logged as warning instead (PR #92)
### Fixed
- In some rare case, the chunks extractor could cut in the middle of a multi-byte character and could mislead the mess detection (PR #95)
- Some rare 'space' characters could trip up the UnprintablePlugin/Mess detection (PR #96)
- The MANIFEST.in was not exhaustive (PR #78)
## [2.0.4](https://github.com/Ousret/charset_normalizer/compare/2.0.3...2.0.4) (2021-07-30)
### Fixed
- The CLI no longer raise an unexpected exception when no encoding has been found (PR #70)
- Fix accessing the 'alphabets' property when the payload contains surrogate characters (PR #68)
- The logger could mislead (explain=True) on detected languages and the impact of one MBCS match (PR #72)
- Submatch factoring could be wrong in rare edge cases (PR #72)
- Multiple files given to the CLI were ignored when publishing results to STDOUT. (After the first path) (PR #72)
- Fix line endings from CRLF to LF for certain project files (PR #67)
### Changed
- Adjust the MD to lower the sensitivity, thus improving the global detection reliability (PR #69 #76)
- Allow fallback on specified encoding if any (PR #71)
## [2.0.3](https://github.com/Ousret/charset_normalizer/compare/2.0.2...2.0.3) (2021-07-16)
### Changed
- Part of the detection mechanism has been improved to be less sensitive, resulting in more accurate detection results. Especially ASCII. (PR #63)
- According to the community wishes, the detection will fall back on ASCII or UTF-8 in a last-resort case. (PR #64)
## [2.0.2](https://github.com/Ousret/charset_normalizer/compare/2.0.1...2.0.2) (2021-07-15)
### Fixed
- Empty/Too small JSON payload miss-detection fixed. Report from [@tseaver](https://github.com/tseaver) (PR #59)
### Changed
- Don't inject unicodedata2 into sys.modules from [@akx](https://github.com/akx) (PR #57)
## [2.0.1](https://github.com/Ousret/charset_normalizer/compare/2.0.0...2.0.1) (2021-07-13)
### Fixed
- Make it work where there isn't a filesystem available, dropping assets frequencies.json. Report from [@sethmlarson](https://github.com/sethmlarson). (PR #55)
- Using explain=False permanently disable the verbose output in the current runtime (PR #47)
- One log entry (language target preemptive) was not show in logs when using explain=True (PR #47)
- Fix undesired exception (ValueError) on getitem of instance CharsetMatches (PR #52)
### Changed
- Public function normalize default args values were not aligned with from_bytes (PR #53)
### Added
- You may now use charset aliases in cp_isolation and cp_exclusion arguments (PR #47)
## [2.0.0](https://github.com/Ousret/charset_normalizer/compare/1.4.1...2.0.0) (2021-07-02)
### Changed
- 4x to 5 times faster than the previous 1.4.0 release. At least 2x faster than Chardet.
- Accent has been made on UTF-8 detection, should perform rather instantaneous.
- The backward compatibility with Chardet has been greatly improved. The legacy detect function returns an identical charset name whenever possible.
- The detection mechanism has been slightly improved, now Turkish content is detected correctly (most of the time)
- The program has been rewritten to ease the readability and maintainability. (+Using static typing)+
- utf_7 detection has been reinstated.
### Removed
- This package no longer require anything when used with Python 3.5 (Dropped cached_property)
- Removed support for these languages: Catalan, Esperanto, Kazakh, Baque, Volapük, Azeri, Galician, Nynorsk, Macedonian, and Serbocroatian.
- The exception hook on UnicodeDecodeError has been removed.
### Deprecated
- Methods coherence_non_latin, w_counter, chaos_secondary_pass of the class CharsetMatch are now deprecated and scheduled for removal in v3.0
### Fixed
- The CLI output used the relative path of the file(s). Should be absolute.
## [1.4.1](https://github.com/Ousret/charset_normalizer/compare/1.4.0...1.4.1) (2021-05-28)
### Fixed
- Logger configuration/usage no longer conflict with others (PR #44)
## [1.4.0](https://github.com/Ousret/charset_normalizer/compare/1.3.9...1.4.0) (2021-05-21)
### Removed
- Using standard logging instead of using the package loguru.
- Dropping nose test framework in favor of the maintained pytest.
- Choose to not use dragonmapper package to help with gibberish Chinese/CJK text.
- Require cached_property only for Python 3.5 due to constraint. Dropping for every other interpreter version.
- Stop support for UTF-7 that does not contain a SIG.
- Dropping PrettyTable, replaced with pure JSON output in CLI.
### Fixed
- BOM marker in a CharsetNormalizerMatch instance could be False in rare cases even if obviously present. Due to the sub-match factoring process.
- Not searching properly for the BOM when trying utf32/16 parent codec.
### Changed
- Improving the package final size by compressing frequencies.json.
- Huge improvement over the larges payload.
### Added
- CLI now produces JSON consumable output.
- Return ASCII if given sequences fit. Given reasonable confidence.
## [1.3.9](https://github.com/Ousret/charset_normalizer/compare/1.3.8...1.3.9) (2021-05-13)
### Fixed
- In some very rare cases, you may end up getting encode/decode errors due to a bad bytes payload (PR #40)
## [1.3.8](https://github.com/Ousret/charset_normalizer/compare/1.3.7...1.3.8) (2021-05-12)
### Fixed
- Empty given payload for detection may cause an exception if trying to access the `alphabets` property. (PR #39)
## [1.3.7](https://github.com/Ousret/charset_normalizer/compare/1.3.6...1.3.7) (2021-05-12)
### Fixed
- The legacy detect function should return UTF-8-SIG if sig is present in the payload. (PR #38)
## [1.3.6](https://github.com/Ousret/charset_normalizer/compare/1.3.5...1.3.6) (2021-02-09)
### Changed
- Amend the previous release to allow prettytable 2.0 (PR #35)
## [1.3.5](https://github.com/Ousret/charset_normalizer/compare/1.3.4...1.3.5) (2021-02-08)
### Fixed
- Fix error while using the package with a python pre-release interpreter (PR #33)
### Changed
- Dependencies refactoring, constraints revised.
### Added
- Add python 3.9 and 3.10 to the supported interpreters
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.

View File

@@ -0,0 +1,33 @@
../../../bin/normalizer,sha256=sAlg_Asa5t12YXHUzxhlqemzKLkYUqg_bYTzWenW7hY,269
charset_normalizer-3.2.0.dist-info/INSTALLER,sha256=zuuue4knoyJ-UwPPXg8fezS7VCrXJQrAP7zeNuwvFQg,4
charset_normalizer-3.2.0.dist-info/LICENSE,sha256=6zGgxaT7Cbik4yBV0lweX5w1iidS_vPNcgIT0cz-4kE,1070
charset_normalizer-3.2.0.dist-info/METADATA,sha256=K2QHhX9fQ7jFxO7y4IQk7TqYZSH7iTyxgTJQxA65EH0,31284
charset_normalizer-3.2.0.dist-info/RECORD,,
charset_normalizer-3.2.0.dist-info/WHEEL,sha256=pkctZYzUS4AYVn6dJ-7367OJZivF2e8RA9b_ZBjif18,92
charset_normalizer-3.2.0.dist-info/entry_points.txt,sha256=uYo8aIGLWv8YgWfSna5HnfY_En4pkF1w4bgawNAXzP0,76
charset_normalizer-3.2.0.dist-info/top_level.txt,sha256=7ASyzePr8_xuZWJsnqJjIBtyV8vhEo0wBCv1MPRRi3Q,19
charset_normalizer/__init__.py,sha256=UzI3xC8PhmcLRMzSgPb6minTmRq0kWznnCBJ8ZCc2XI,1577
charset_normalizer/__pycache__/__init__.cpython-311.pyc,,
charset_normalizer/__pycache__/api.cpython-311.pyc,,
charset_normalizer/__pycache__/cd.cpython-311.pyc,,
charset_normalizer/__pycache__/constant.cpython-311.pyc,,
charset_normalizer/__pycache__/legacy.cpython-311.pyc,,
charset_normalizer/__pycache__/md.cpython-311.pyc,,
charset_normalizer/__pycache__/models.cpython-311.pyc,,
charset_normalizer/__pycache__/utils.cpython-311.pyc,,
charset_normalizer/__pycache__/version.cpython-311.pyc,,
charset_normalizer/api.py,sha256=WOlWjy6wT8SeMYFpaGbXZFN1TMXa-s8vZYfkL4G29iQ,21097
charset_normalizer/assets/__init__.py,sha256=wpRfujN7GJuEE5wHHo3wEDVoJ5ovzRIxsImyimCBfGU,20069
charset_normalizer/assets/__pycache__/__init__.cpython-311.pyc,,
charset_normalizer/cd.py,sha256=mZuiTSKq4XpweSDD2H4T4R3Axtaa-QS0tpEWdpMuAzQ,12554
charset_normalizer/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/cli/__pycache__/__init__.cpython-311.pyc,,
charset_normalizer/cli/__pycache__/normalizer.cpython-311.pyc,,
charset_normalizer/cli/normalizer.py,sha256=2F-xURZJzo063Ye-2RLJ2wcmURpbKeAzKwpiws65dAs,9744
charset_normalizer/constant.py,sha256=PmCeoKXqq3ZbCtCUpKHwwFBIv9DXMT_an1yd24q28mA,19101
charset_normalizer/legacy.py,sha256=T-QuVMsMeDiQEk8WSszMrzVJg_14AMeSkmHdRYhdl1k,2071
charset_normalizer/md.py,sha256=gEWM354DqBsiSoNkKzFrIW4KRFQjQLbqYnbHAdBwj74,18682
charset_normalizer/models.py,sha256=mC11wo84l00u2o03TRNX7M5ItBAbPUKKXgJSFxA35GY,11492
charset_normalizer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
charset_normalizer/utils.py,sha256=HdwmBy9vRqcRVGHKZqYWtpiS5wA35cLjnlVQCm0Bq9s,11578
charset_normalizer/version.py,sha256=LbH8odlzMnwR4xZF9wCsnGXQA19axDO7HZ-J9hegIX0,79

View File

@@ -0,0 +1,5 @@
Wheel-Version: 1.0
Generator: bdist_wheel (0.40.0)
Root-Is-Purelib: true
Tag: py3-none-any

View File

@@ -0,0 +1,2 @@
[console_scripts]
normalizer = charset_normalizer.cli.normalizer:cli_detect

View File

@@ -0,0 +1 @@
charset_normalizer

View File

@@ -0,0 +1,46 @@
# -*- coding: utf-8 -*-
"""
Charset-Normalizer
~~~~~~~~~~~~~~
The Real First Universal Charset Detector.
A library that helps you read text from an unknown charset encoding.
Motivated by chardet, This package is 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.
Basic usage:
>>> from charset_normalizer import from_bytes
>>> results = from_bytes('Bсеки човек има право на образование. Oбразованието!'.encode('utf_8'))
>>> best_guess = results.best()
>>> str(best_guess)
'Bсеки човек има право на образование. Oбразованието!'
Others methods and usages are available - see the full documentation
at <https://github.com/Ousret/charset_normalizer>.
:copyright: (c) 2021 by Ahmed TAHRI
:license: MIT, see LICENSE for more details.
"""
import logging
from .api import from_bytes, from_fp, from_path, is_binary
from .legacy import detect
from .models import CharsetMatch, CharsetMatches
from .utils import set_logging_handler
from .version import VERSION, __version__
__all__ = (
"from_fp",
"from_path",
"from_bytes",
"is_binary",
"detect",
"CharsetMatch",
"CharsetMatches",
"__version__",
"VERSION",
"set_logging_handler",
)
# Attach a NullHandler to the top level logger by default
# https://docs.python.org/3.3/howto/logging.html#configuring-logging-for-a-library
logging.getLogger("charset_normalizer").addHandler(logging.NullHandler())

View File

@@ -0,0 +1,626 @@
import logging
from os import PathLike
from typing import BinaryIO, List, Optional, Set, Union
from .cd import (
coherence_ratio,
encoding_languages,
mb_encoding_languages,
merge_coherence_ratios,
)
from .constant import IANA_SUPPORTED, TOO_BIG_SEQUENCE, TOO_SMALL_SEQUENCE, TRACE
from .md import mess_ratio
from .models import CharsetMatch, CharsetMatches
from .utils import (
any_specified_encoding,
cut_sequence_chunks,
iana_name,
identify_sig_or_bom,
is_cp_similar,
is_multi_byte_encoding,
should_strip_sig_or_bom,
)
# Will most likely be controversial
# logging.addLevelName(TRACE, "TRACE")
logger = logging.getLogger("charset_normalizer")
explain_handler = logging.StreamHandler()
explain_handler.setFormatter(
logging.Formatter("%(asctime)s | %(levelname)s | %(message)s")
)
def from_bytes(
sequences: Union[bytes, bytearray],
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.2,
cp_isolation: Optional[List[str]] = None,
cp_exclusion: Optional[List[str]] = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Given a raw bytes sequence, return the best possibles charset usable to render str objects.
If there is no results, it is a strong indicator that the source is binary/not text.
By default, the process will extract 5 blocks of 512o each to assess the mess and coherence of a given sequence.
And will give up a particular code page after 20% of measured mess. Those criteria are customizable at will.
The preemptive behavior DOES NOT replace the traditional detection workflow, it prioritize a particular code page
but never take it for granted. Can improve the performance.
You may want to focus your attention to some code page or/and not others, use cp_isolation and cp_exclusion for that
purpose.
This function will strip the SIG in the payload/sequence every time except on UTF-16, UTF-32.
By default the library does not setup any handler other than the NullHandler, if you choose to set the 'explain'
toggle to True it will alter the logger configuration to add a StreamHandler that is suitable for debugging.
Custom logging format and handler can be set manually.
"""
if not isinstance(sequences, (bytearray, bytes)):
raise TypeError(
"Expected object of type bytes or bytearray, got: {0}".format(
type(sequences)
)
)
if explain:
previous_logger_level: int = logger.level
logger.addHandler(explain_handler)
logger.setLevel(TRACE)
length: int = len(sequences)
if length == 0:
logger.debug("Encoding detection on empty bytes, assuming utf_8 intention.")
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level or logging.WARNING)
return CharsetMatches([CharsetMatch(sequences, "utf_8", 0.0, False, [], "")])
if cp_isolation is not None:
logger.log(
TRACE,
"cp_isolation is set. use this flag for debugging purpose. "
"limited list of encoding allowed : %s.",
", ".join(cp_isolation),
)
cp_isolation = [iana_name(cp, False) for cp in cp_isolation]
else:
cp_isolation = []
if cp_exclusion is not None:
logger.log(
TRACE,
"cp_exclusion is set. use this flag for debugging purpose. "
"limited list of encoding excluded : %s.",
", ".join(cp_exclusion),
)
cp_exclusion = [iana_name(cp, False) for cp in cp_exclusion]
else:
cp_exclusion = []
if length <= (chunk_size * steps):
logger.log(
TRACE,
"override steps (%i) and chunk_size (%i) as content does not fit (%i byte(s) given) parameters.",
steps,
chunk_size,
length,
)
steps = 1
chunk_size = length
if steps > 1 and length / steps < chunk_size:
chunk_size = int(length / steps)
is_too_small_sequence: bool = len(sequences) < TOO_SMALL_SEQUENCE
is_too_large_sequence: bool = len(sequences) >= TOO_BIG_SEQUENCE
if is_too_small_sequence:
logger.log(
TRACE,
"Trying to detect encoding from a tiny portion of ({}) byte(s).".format(
length
),
)
elif is_too_large_sequence:
logger.log(
TRACE,
"Using lazy str decoding because the payload is quite large, ({}) byte(s).".format(
length
),
)
prioritized_encodings: List[str] = []
specified_encoding: Optional[str] = (
any_specified_encoding(sequences) if preemptive_behaviour else None
)
if specified_encoding is not None:
prioritized_encodings.append(specified_encoding)
logger.log(
TRACE,
"Detected declarative mark in sequence. Priority +1 given for %s.",
specified_encoding,
)
tested: Set[str] = set()
tested_but_hard_failure: List[str] = []
tested_but_soft_failure: List[str] = []
fallback_ascii: Optional[CharsetMatch] = None
fallback_u8: Optional[CharsetMatch] = None
fallback_specified: Optional[CharsetMatch] = None
results: CharsetMatches = CharsetMatches()
sig_encoding, sig_payload = identify_sig_or_bom(sequences)
if sig_encoding is not None:
prioritized_encodings.append(sig_encoding)
logger.log(
TRACE,
"Detected a SIG or BOM mark on first %i byte(s). Priority +1 given for %s.",
len(sig_payload),
sig_encoding,
)
prioritized_encodings.append("ascii")
if "utf_8" not in prioritized_encodings:
prioritized_encodings.append("utf_8")
for encoding_iana in prioritized_encodings + IANA_SUPPORTED:
if cp_isolation and encoding_iana not in cp_isolation:
continue
if cp_exclusion and encoding_iana in cp_exclusion:
continue
if encoding_iana in tested:
continue
tested.add(encoding_iana)
decoded_payload: Optional[str] = None
bom_or_sig_available: bool = sig_encoding == encoding_iana
strip_sig_or_bom: bool = bom_or_sig_available and should_strip_sig_or_bom(
encoding_iana
)
if encoding_iana in {"utf_16", "utf_32"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s won't be tested as-is because it require a BOM. Will try some sub-encoder LE/BE.",
encoding_iana,
)
continue
if encoding_iana in {"utf_7"} and not bom_or_sig_available:
logger.log(
TRACE,
"Encoding %s won't be tested as-is because detection is unreliable without BOM/SIG.",
encoding_iana,
)
continue
try:
is_multi_byte_decoder: bool = is_multi_byte_encoding(encoding_iana)
except (ModuleNotFoundError, ImportError):
logger.log(
TRACE,
"Encoding %s does not provide an IncrementalDecoder",
encoding_iana,
)
continue
try:
if is_too_large_sequence and is_multi_byte_decoder is False:
str(
sequences[: int(50e4)]
if strip_sig_or_bom is False
else sequences[len(sig_payload) : int(50e4)],
encoding=encoding_iana,
)
else:
decoded_payload = str(
sequences
if strip_sig_or_bom is False
else sequences[len(sig_payload) :],
encoding=encoding_iana,
)
except (UnicodeDecodeError, LookupError) as e:
if not isinstance(e, LookupError):
logger.log(
TRACE,
"Code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
similar_soft_failure_test: bool = False
for encoding_soft_failed in tested_but_soft_failure:
if is_cp_similar(encoding_iana, encoding_soft_failed):
similar_soft_failure_test = True
break
if similar_soft_failure_test:
logger.log(
TRACE,
"%s is deemed too similar to code page %s and was consider unsuited already. Continuing!",
encoding_iana,
encoding_soft_failed,
)
continue
r_ = range(
0 if not bom_or_sig_available else len(sig_payload),
length,
int(length / steps),
)
multi_byte_bonus: bool = (
is_multi_byte_decoder
and decoded_payload is not None
and len(decoded_payload) < length
)
if multi_byte_bonus:
logger.log(
TRACE,
"Code page %s is a multi byte encoding table and it appear that at least one character "
"was encoded using n-bytes.",
encoding_iana,
)
max_chunk_gave_up: int = int(len(r_) / 4)
max_chunk_gave_up = max(max_chunk_gave_up, 2)
early_stop_count: int = 0
lazy_str_hard_failure = False
md_chunks: List[str] = []
md_ratios = []
try:
for chunk in cut_sequence_chunks(
sequences,
encoding_iana,
r_,
chunk_size,
bom_or_sig_available,
strip_sig_or_bom,
sig_payload,
is_multi_byte_decoder,
decoded_payload,
):
md_chunks.append(chunk)
md_ratios.append(
mess_ratio(
chunk,
threshold,
explain is True and 1 <= len(cp_isolation) <= 2,
)
)
if md_ratios[-1] >= threshold:
early_stop_count += 1
if (early_stop_count >= max_chunk_gave_up) or (
bom_or_sig_available and strip_sig_or_bom is False
):
break
except (
UnicodeDecodeError
) as e: # Lazy str loading may have missed something there
logger.log(
TRACE,
"LazyStr Loading: After MD chunk decode, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
early_stop_count = max_chunk_gave_up
lazy_str_hard_failure = True
# We might want to check the sequence again with the whole content
# Only if initial MD tests passes
if (
not lazy_str_hard_failure
and is_too_large_sequence
and not is_multi_byte_decoder
):
try:
sequences[int(50e3) :].decode(encoding_iana, errors="strict")
except UnicodeDecodeError as e:
logger.log(
TRACE,
"LazyStr Loading: After final lookup, code page %s does not fit given bytes sequence at ALL. %s",
encoding_iana,
str(e),
)
tested_but_hard_failure.append(encoding_iana)
continue
mean_mess_ratio: float = sum(md_ratios) / len(md_ratios) if md_ratios else 0.0
if mean_mess_ratio >= threshold or early_stop_count >= max_chunk_gave_up:
tested_but_soft_failure.append(encoding_iana)
logger.log(
TRACE,
"%s was excluded because of initial chaos probing. Gave up %i time(s). "
"Computed mean chaos is %f %%.",
encoding_iana,
early_stop_count,
round(mean_mess_ratio * 100, ndigits=3),
)
# Preparing those fallbacks in case we got nothing.
if (
enable_fallback
and encoding_iana in ["ascii", "utf_8", specified_encoding]
and not lazy_str_hard_failure
):
fallback_entry = CharsetMatch(
sequences, encoding_iana, threshold, False, [], decoded_payload
)
if encoding_iana == specified_encoding:
fallback_specified = fallback_entry
elif encoding_iana == "ascii":
fallback_ascii = fallback_entry
else:
fallback_u8 = fallback_entry
continue
logger.log(
TRACE,
"%s passed initial chaos probing. Mean measured chaos is %f %%",
encoding_iana,
round(mean_mess_ratio * 100, ndigits=3),
)
if not is_multi_byte_decoder:
target_languages: List[str] = encoding_languages(encoding_iana)
else:
target_languages = mb_encoding_languages(encoding_iana)
if target_languages:
logger.log(
TRACE,
"{} should target any language(s) of {}".format(
encoding_iana, str(target_languages)
),
)
cd_ratios = []
# We shall skip the CD when its about ASCII
# Most of the time its not relevant to run "language-detection" on it.
if encoding_iana != "ascii":
for chunk in md_chunks:
chunk_languages = coherence_ratio(
chunk,
language_threshold,
",".join(target_languages) if target_languages else None,
)
cd_ratios.append(chunk_languages)
cd_ratios_merged = merge_coherence_ratios(cd_ratios)
if cd_ratios_merged:
logger.log(
TRACE,
"We detected language {} using {}".format(
cd_ratios_merged, encoding_iana
),
)
results.append(
CharsetMatch(
sequences,
encoding_iana,
mean_mess_ratio,
bom_or_sig_available,
cd_ratios_merged,
decoded_payload,
)
)
if (
encoding_iana in [specified_encoding, "ascii", "utf_8"]
and mean_mess_ratio < 0.1
):
logger.debug(
"Encoding detection: %s is most likely the one.", encoding_iana
)
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([results[encoding_iana]])
if encoding_iana == sig_encoding:
logger.debug(
"Encoding detection: %s is most likely the one as we detected a BOM or SIG within "
"the beginning of the sequence.",
encoding_iana,
)
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return CharsetMatches([results[encoding_iana]])
if len(results) == 0:
if fallback_u8 or fallback_ascii or fallback_specified:
logger.log(
TRACE,
"Nothing got out of the detection process. Using ASCII/UTF-8/Specified fallback.",
)
if fallback_specified:
logger.debug(
"Encoding detection: %s will be used as a fallback match",
fallback_specified.encoding,
)
results.append(fallback_specified)
elif (
(fallback_u8 and fallback_ascii is None)
or (
fallback_u8
and fallback_ascii
and fallback_u8.fingerprint != fallback_ascii.fingerprint
)
or (fallback_u8 is not None)
):
logger.debug("Encoding detection: utf_8 will be used as a fallback match")
results.append(fallback_u8)
elif fallback_ascii:
logger.debug("Encoding detection: ascii will be used as a fallback match")
results.append(fallback_ascii)
if results:
logger.debug(
"Encoding detection: Found %s as plausible (best-candidate) for content. With %i alternatives.",
results.best().encoding, # type: ignore
len(results) - 1,
)
else:
logger.debug("Encoding detection: Unable to determine any suitable charset.")
if explain:
logger.removeHandler(explain_handler)
logger.setLevel(previous_logger_level)
return results
def from_fp(
fp: BinaryIO,
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: Optional[List[str]] = None,
cp_exclusion: Optional[List[str]] = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but using a file pointer that is already ready.
Will not close the file pointer.
"""
return from_bytes(
fp.read(),
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
language_threshold,
enable_fallback,
)
def from_path(
path: Union[str, bytes, PathLike], # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: Optional[List[str]] = None,
cp_exclusion: Optional[List[str]] = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = True,
) -> CharsetMatches:
"""
Same thing than the function from_bytes but with one extra step. Opening and reading given file path in binary mode.
Can raise IOError.
"""
with open(path, "rb") as fp:
return from_fp(
fp,
steps,
chunk_size,
threshold,
cp_isolation,
cp_exclusion,
preemptive_behaviour,
explain,
language_threshold,
enable_fallback,
)
def is_binary(
fp_or_path_or_payload: Union[PathLike, str, BinaryIO, bytes], # type: ignore[type-arg]
steps: int = 5,
chunk_size: int = 512,
threshold: float = 0.20,
cp_isolation: Optional[List[str]] = None,
cp_exclusion: Optional[List[str]] = None,
preemptive_behaviour: bool = True,
explain: bool = False,
language_threshold: float = 0.1,
enable_fallback: bool = False,
) -> bool:
"""
Detect if the given input (file, bytes, or path) points to a binary file. aka. not a string.
Based on the same main heuristic algorithms and default kwargs at the sole exception that fallbacks match
are disabled to be stricter around ASCII-compatible but unlikely to be a string.
"""
if isinstance(fp_or_path_or_payload, (str, PathLike)):
guesses = from_path(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
elif isinstance(
fp_or_path_or_payload,
(
bytes,
bytearray,
),
):
guesses = from_bytes(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
else:
guesses = from_fp(
fp_or_path_or_payload,
steps=steps,
chunk_size=chunk_size,
threshold=threshold,
cp_isolation=cp_isolation,
cp_exclusion=cp_exclusion,
preemptive_behaviour=preemptive_behaviour,
explain=explain,
language_threshold=language_threshold,
enable_fallback=enable_fallback,
)
return not guesses

File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More