Develop Reference

PYTHON SQLITE selecting multiple where conditions that may or may not exist

Working on some code that uses pysimplegui as the UI and SQlite for the data sorting. I'm using SQLite's execute function to select data based on input from the user in the UI through variables. For example user wants to search for part name they input all or part of the name into the box, hit the search button which then runs my "parts_search" method, which will then only filter the result based on part name. OR the user enters information in multiple boxes which then filters based on the boxes that have information.
This here is runnable code provided you add a file base1.db in the same folder location as the script itself
import PySimpleGUI as sg
import os.path
import sqlite3
# sql var
c = None
conn = None
setup = None
# list var
parts = []
def sql():
global setup
conn_sql()
c.execute("""CREATE TABLE IF NOT EXISTS parts (part_name TEXT, part_number TEXT, part_series TEXT,
part_size INTEGER, job_type TEXT)""")
conn.commit()
if conn:
conn.close()
def conn_sql():
global c
global conn
# SQL connection var
if os.path.isfile('./base1.db'):
conn = sqlite3.connect('base1.db')
c = conn.cursor()
def main_gui_parts():
global parts
layout = [[sg.Text('Part Name: '), sg.Input(size=(20, 1), key='-PName-'), sg.Text('Part Series:'),
sg.Input(size=(10, 1), key='-PSeries-')],
[sg.Text('Part Number:'), sg.Input(size=(20, 1), key='-PNumber-'), sg.Text('Part Size:'),
sg.Input(size=(10, 1), key='-PSize-')],
[sg.Checkbox('Fit', key='-PFit-'), sg.Checkbox('Weld', key='-PWeld-'),
sg.Checkbox('Assemble', key='-PAssemble-'),
sg.Button('Search', key='-PSearch-')],
[sg.Listbox(parts, size=(58, 10), key='-PParts-')], [sg.Button('Back', key='-PBack-')]]
window = sg.Window('parts list', layout, grab_anywhere=True)
sql()
while True:
event, values = window.read()
if event == 'Close' or event == sg.WIN_CLOSED:
break
# PART WINDOW
part_name = values['-PName-']
part_series = values['-PSeries-']
part_number = values['-PNumber-']
part_size = values['-PSize-']
fit = values['-PFit-']
weld = values['-PWeld-']
assemble = values['-PAssemble-']
if event == '-PSearch-':
print('search parts')
part_search(part_name, part_series, part_number, part_size, fit, weld, assemble)
if event == '-PBack-':
break
window.close()
def part_search(part_name, part_series, part_number, part_size, fit, weld, assemble):
global parts
conn_sql()
filter_original = """SELECT * FROM parts WHERE """
filter = filter_original
if part_name:
print('part name: ' + part_name)
if filter == filter_original:
filter += """part_name LIKE ? """
else:
filter += """AND part_name LIKE ? """
if part_series:
print('part series: ' + part_series)
if filter == filter_original:
filter += """part_series=(?) """
else:
filter += """AND part_series=(?) """
if part_number:
print('part number: ' + part_number)
if filter == filter_original:
filter += """part_number LIKE ? """ ### DONT USE LIKE???
else:
filter += """AND part_number LIKE ? """ ### DONT USE LIKE???
if part_size:
print('part size: ' + part_size)
if filter == filter_original:
filter += """part_size=(?) """
else:
filter += """AND part_size=(?) """
if fit:
print('job type: ' + str(fit))
if filter == filter_original:
filter += """job_type = fit """
else:
filter += """AND job_type = fit """
if weld:
print('job type: ' + str(weld))
if filter == filter_original:
filter += """job_type = weld """
else:
filter += """AND job_type = weld """
if assemble:
print('job type: ' + str(assemble))
if filter == filter_original:
filter += """job_type = assemble"""
else:
filter += """AND job_type = assemble"""
print(filter)
#if filter != filter_original:
#c.execute(filter, ())
#else:
#c.execute("""SELECT * FROM parts""")
main_gui_parts()
THE PROBLEM: The commented code at the bottom is where I'm having trouble figuring out (in the "part_search" method). I don't use all of the variables all the time. Only filter with the variables provided by the user. which means the tuple should only have the variables which was input by the user.
If all the variables were used this is what it would look like. c.execute(filter, (part_name, part_series, part_number, part_size, fit, weld, assemble)) but more often than not only some of those variable will have been used and may need to look like this instead. c.execute(filter, (part_name, part_series, weld)) Somehow I need the variables here to be removeable(for lack of better word)
I've been learning a lot about SQLite but I could be seeing tunnel vision and can't think of a different way to go about this.

Probably the easiest way to deal with this is to put all the filter conditions and values into lists, and then only add a WHERE clause if the length of the filters list is non-zero. For example:
query = """SELECT * FROM parts"""
filters = []
values = []
if part_name:
filters.append("""part_name LIKE ?""")
values.append(part_name)
...
if len(filters):
query += ' WHERE ' + ' AND '.join(filters)
c.execute(query, tuple(values))
Note: should your filters ever include OR conditions, you need to parenthesise them when building the query to ensure correct operation i.e.
query += ' WHERE (' + ') AND ('.join(filters) + ')'

Is there a way to programmatically combine Korean unicode into one?

Using a Korean Input Method Editor (IME), it's possible to type 버리 + 어 and it will automatically become 버려.
Is there a way to programmatically do that in Python?
>>> x, y = '버리', '어'
>>> z = '버려'
>>> ord(z[-1])
47140
>>> ord(x[-1]), ord(y)
(47532, 50612)
Is there a way to compute that 47532 + 50612 -> 47140?
Here's some more examples:
가보 + 아 -> 가봐
끝나 + ㄹ -> 끝날

I'm a Korean. First, if you type 버리 + 어, it becomes 버리어 not 버려. 버려 is an abbreviation of 버리어 and it's not automatically generated. Also 가보아 cannot becomes 가봐 automatically during typing by the same reason.
Second, by contrast, 끝나 + ㄹ becomes 끝날 because 나 has no jongseong(종성). Note that one character of Hangul is made of choseong(초성), jungseong(중성), and jongseong. choseong and jongseong are a consonant, jungseong is a vowel. See more at Wikipedia. So only when there's no jongseong during typing (like 끝나), there's a chance that it can have jongseong(ㄹ).
If you want to make 버리 + 어 to 버려, you should implement some Korean language grammar like, especially for this case, abbreviation of jungseong. For example ㅣ + ㅓ = ㅕ, ㅗ + ㅏ = ㅘ as you provided. 한글 맞춤법 chapter 4. section 5 (I can't find English pages right now) defines abbreviation like this. It's possible, but not so easy job especially for non-Koreans.
Next, if what you want is just to make 끝나 + ㄹ to 끝날, it can be a relatively easy job since there're libraries which can handle composition and decomposition of choseong, jungseong, jongseong. In case of Python, I found hgtk. You can try like this (nonpractical code):
# hgtk methods take one character at a time
cjj1 = hgtk.letter.decompose('나') # ('ㄴ', 'ㅏ', '')
cjj2 = hgtk.letter.decompose('ㄹ') # ('ㄹ', '', '')
if cjj1[2]) == '' and cjj2[1]) == '':
cjj = (cjj1[0], cjj1[1], cjj2[0])
cjj2 = None
Still, without proper knowledge of Hangul, it will be very hard to get it done.

You could use your own Translation table.
The drawback is you have to input all pairs manual or you have a file to get it from.
For instance:
# Sample Korean chars to map
k = [[('버리', '어'), ('버려')], [('가보', '아'), ('가봐')], [('끝나', 'ㄹ'), ('끝날')]]
class Korean(object):
def __init__(self):
self.map = {}
for m in k:
key = m[0][0] + m[0][1]
self.map[hash(key)] = m[1]
def __getitem__(self, item):
return self.map[hash(item)]
def translate(self, s):
return [ self.map[hash(token)] for token in s]
if __name__ == '__main__':
k_map = Korean()
k_chars = [ m[0][0] + m[0][1] for m in k]
print('Input: %s' % k_chars)
print('Output: %s' % k_map.translate(k_chars))
one_char_3 = k[0][0][0] + k[0][0][1]
print('%s = %s' % (one_char_3, k_map[ one_char_3 ]) )
Input: ['버리어', '가보아', '끝나ㄹ']
Output: ['버려', '가봐', '끝날']
버리어 = 버려
Tested with Python:3.4.2

How to replace text in curly brackets with another text based on comparisons using Python Regex

I am quiet new to regular expressions. I have a string that looks like this:
str = "abc/def/([default], [testing])"
and a dictionary
dict = {'abc/def/[default]' : '2.7', 'abc/def/[testing]' : '2.1'}
and using Python RE, I want str in this form, after comparisons of each element in dict to str:
str = "abc/def/(2.7, 2.1)"
Any help how to do it using Python RE?
P.S. its not the part of any assignment, instead it is the part of my project at work and I have spent many hours to figure out solution but in vain.

import re
st = "abc/def/([default], [testing], [something])"
dic = {'abc/def/[default]' : '2.7',
'abc/def/[testing]' : '2.1',
'bcd/xed/[something]' : '3.1'}
prefix_regex = "^[\w*/]*"
tag_regex = "\[\w*\]"
prefix = re.findall(prefix_regex, st)[0]
tags = re.findall(tag_regex, st)
for key in dic:
key_prefix = re.findall(prefix_regex, key)[0]
key_tag = re.findall(tag_regex, key)[0]
if prefix == key_prefix:
for tag in tags:
if tag == key_tag:
st = st.replace(tag, dic[key])
print st
OUTPUT:
abc/def/(2.7, 2.1, [something])

Here is a solution using re module.
Hypotheses :
there is a dictionary whose keys are composed of a prefix and a variable part, the variable part is enclosed in brackets ([])
the values are strings by which the variable parts are to be replaced in the string
the string is composed by a prefix, a (, a list of variable parts and a )
the variable parts in the string are enclosed in []
the variable parts in the string are separated by a comma followed by optional spaces
Python code :
import re
class splitter:
pref = re.compile("[^(]+")
iden = re.compile("\[[^]]*\]")
def __init__(self, d):
self.d = d
def split(self, s):
m = self.pref.match(s)
if m is not None:
p = m.group(0)
elts = self.iden.findall(s, m.span()[1])
return p, elts
return None
def convert(self, s):
p, elts = self.split(s)
return p + "(" + ", ".join((self.d[p + elt] for elt in elts)) + ")"
Usage :
s = "abc/def/([default], [testing])"
d = {'abc/def/[default]' : '2.7', 'abc/def/[testing]' : '2.1'}
sp = splitter(d)
print(sp.convert(s))
output :
abc/def/(2.7, 2.1)

Regex is probably not required here. Hope this helps
lhs,rhs = str.split("/(")
rhs1,rhs2 = rhs.strip(")").split(", ")
lhs+="/"
print "{0}({1},{2})".format(lhs,dict[lhs+rhs1],dict[lhs+rhs2])
output
abc/def/(2.7,2.1)

pretty print assertEqual() for HTML strings

I want to compare two strings in a python unittest which contain html.
Is there a method which outputs the result in a human friendly (diff like) version?

A simple method is to strip whitespace from the HTML and split it into a list. Python 2.7's unittest (or the backported unittest2) then gives a human-readable diff between the lists.
import re
def split_html(html):
return re.split(r'\s*\n\s*', html.strip())
def test_render_html():
expected = ['<div>', '...', '</div>']
got = split_html(render_html())
self.assertEqual(expected, got)
If I'm writing a test for working code, I usually first set expected = [], insert a self.maxDiff = None before the assert and let the test fail once. The expected list can then be copy-pasted from the test output.
You might need to tweak how whitespace is stripped depending on what your HTML looks like.

I submitted a patch to do this some years back. The patch was rejected but you can still view it on the python bug list.
I doubt you would want to hack your unittest.py to apply the patch (if it even still works after all this time), but here's the function for reducing two strings a manageable size while still keeping at least part of what differs. So long as all you didn't want the complete differences this might be what you want:
def shortdiff(x,y):
'''shortdiff(x,y)
Compare strings x and y and display differences.
If the strings are too long, shorten them to fit
in one line, while still keeping at least some difference.
'''
import difflib
LINELEN = 79
def limit(s):
if len(s) > LINELEN:
return s[:LINELEN-3] + '...'
return s
def firstdiff(s, t):
span = 1000
for pos in range(0, max(len(s), len(t)), span):
if s[pos:pos+span] != t[pos:pos+span]:
for index in range(pos, pos+span):
if s[index:index+1] != t[index:index+1]:
return index
left = LINELEN/4
index = firstdiff(x, y)
if index > left + 7:
x = x[:left] + '...' + x[index-4:index+LINELEN]
y = y[:left] + '...' + y[index-4:index+LINELEN]
else:
x, y = x[:LINELEN+1], y[:LINELEN+1]
left = 0
cruncher = difflib.SequenceMatcher(None)
xtags = ytags = ""
cruncher.set_seqs(x, y)
editchars = { 'replace': ('^', '^'),
'delete': ('-', ''),
'insert': ('', '+'),
'equal': (' ',' ') }
for tag, xi1, xi2, yj1, yj2 in cruncher.get_opcodes():
lx, ly = xi2 - xi1, yj2 - yj1
edits = editchars[tag]
xtags += edits[0] * lx
ytags += edits[1] * ly
# Include ellipsis in edits line.
if left:
xtags = xtags[:left] + '...' + xtags[left+3:]
ytags = ytags[:left] + '...' + ytags[left+3:]
diffs = [ x, xtags, y, ytags ]
if max([len(s) for s in diffs]) < LINELEN:
return '\n'.join(diffs)
diffs = [ limit(s) for s in diffs ]
return '\n'.join(diffs)

Maybe this is a quite 'verbose' solution. You could add a new 'equality function' for your user defined type (e.g: HTMLString) which you have to define first:
class HTMLString(str):
pass
Now you have to define a type equality function:
def assertHTMLStringEqual(first, second):
if first != second:
message = ... # TODO here: format your message, e.g a diff
raise AssertionError(message)
All you have to do is format your message as you like. You can also use a class method in your specific TestCase as a type equality function. This gives you more functionality to format your message, since unittest.TestCase does this a lot.
Now you have to register this equality function in your unittest.TestCase:
...
def __init__(self):
self.addTypeEqualityFunc(HTMLString, assertHTMLStringEqual)
The same for a class method:
...
def __init__(self):
self.addTypeEqualityFunc(HTMLString, 'assertHTMLStringEqual')
And now you can use it in your tests:
def test_something(self):
htmlstring1 = HTMLString(...)
htmlstring2 = HTMLString(...)
self.assertEqual(htmlstring1, htmlstring2)
This should work well with python 2.7.

I (the one asking this question) use BeautfulSoup now:
def assertEqualHTML(string1, string2, file1='', file2=''):
u'''
Compare two unicode strings containing HTML.
A human friendly diff goes to logging.error() if there
are not equal, and an exception gets raised.
'''
from BeautifulSoup import BeautifulSoup as bs
import difflib
def short(mystr):
max=20
if len(mystr)>max:
return mystr[:max]
return mystr
p=[]
for mystr, file in [(string1, file1), (string2, file2)]:
if not isinstance(mystr, unicode):
raise Exception(u'string ist not unicode: %r %s' % (short(mystr), file))
soup=bs(mystr)
pretty=soup.prettify()
p.append(pretty)
if p[0]!=p[1]:
for line in difflib.unified_diff(p[0].splitlines(), p[1].splitlines(), fromfile=file1, tofile=file2):
logging.error(line)
raise Exception('Not equal %s %s' % (file1, file2))

Displaying prices

I'm getting prices in different currencies and want to display Brazilian R$
My formatting doesn't work and the display looks like this:
Price: 1.15..000.,00 R$
For good flexibility I've stored the price as a string: price=db.StringProperty(verbose_name="price")
I tried to implement my own filter and it didn't work:
{{ ad.price|separate }} R$
def separate(n, sep='.'):
ln = list(str(n))
ln.reverse()
newn = []
while len(ln) > 3:
newn.extend(ln[:3])
newn.append(sep)
ln = ln[3:]
newn.extend(ln)
newn.reverse()
return "".join(newn)
Can you help me? Should I just remove the filter? Should I enforce some regex to the input instead? A link to my site is http://www.koolbusiness.com/servead/4252196
UPDATE: I'm considering using something like one of these filters:
import locale
locale.setlocale(locale.LC_ALL, '')
def currency(value): # doesn't work
locale.setlocale(locale.LC_ALL, '')
return locale.currency(value, grouping=True)
register.filter(currency)
def currencyWithoutUsingLocale(value): # needs adjustment
value=float(value)
symbol = '$'
thousand_sep = ''
decimal_sep = ''
# try to use settings if set
try:
symbol = settings.CURRENCY_SYMBOL
except AttributeError:
pass
try:
thousand_sep = settings.THOUSAND_SEPARATOR
decimal_sep = settings.DECIMAL_SEPARATOR
except AttributeError:
thousand_sep = ','
decimal_sep = '.'
intstr = str(int(value))
f = lambda x, n, acc=[]: f(x[:-n], n, [(x[-n:])]+acc) if x else acc
intpart = thousand_sep.join(f(intstr, 3))
return "%s%s%s%s" % (symbol, intpart, decimal_sep, ("%0.2f" % value)[-2:])
register.filter(currencyWithoutUsingLocale)

Storing the price as a string is the first problem. It should be a Decimal. If you look at the Python standard library documentation for Decimal, you will see this http://docs.python.org/library/decimal.html#recipes
That moneyfmt recipe should do what you want

Currency formatting is a feature of locale.
http://docs.python.org/library/locale.html#locale.currency

You can use locale._override_localeconv dict to set your own overwrites:
>>> import locale
>>> locale.setlocale(locale.LC_MONETARY, 'pt_BR.UTF-8')
>>> locale.currency(1234.56)
'1234,56 R$'
>>> locale._override_localeconv.update({'p_cs_precedes': 1, 'n_cs_precedes': 1})
>>> locale.currency(1234.56)
'R$ 1234,56'
You can use this locale._override_localeconv.update({'p_cs_precedes': 1, 'n_cs_precedes': 1}) line right after the import locale, if you want.