Develop Reference

PyParsing: parse if not a keyword

I am trying to parse a file as follows:
testp.txt
title = Test Suite A;
timeout = 10000
exp_delay = 500;
log = TRUE;
sect
{
type = typeA;
name = "HelloWorld";
output_log = "c:\test\out.log";
};
sect
{
name = "GoodbyeAll";
type = typeB;
comm1_req = 0xDEADBEEF;
comm1_resp = (int, 1234366);
};
The file first contains a section with parameters and then some sects. I can parse a file containing just parameters and I can parse a file just containing sects but I can't parse both.
from pyparsing import *
from pathlib import Path
command_req = Word(alphanums)
command_resp = "(" + delimitedList(Word(alphanums)) + ")"
kW = Word(alphas+'_', alphanums+'_') | command_req | command_resp
keyName = ~Literal("sect") + Word(alphas+'_', alphanums+'_') + FollowedBy("=")
keyValue = dblQuotedString.setParseAction( removeQuotes ) | OneOrMore(kW,stopOn=LineEnd())
param = dictOf(keyName, Suppress("=")+keyValue+Optional(Suppress(";")))
node = Group(Literal("sect") + Literal("{") + OneOrMore(param) + Literal("};"))
final = OneOrMore(node) | OneOrMore(param)
param.setDebug()
p = Path(__file__).with_name("testp.txt")
with open(p) as f:
try:
x = final.parseFile(f, parseAll=True)
print(x)
print("...")
dx = x.asDict()
print(dx)
except ParseException as pe:
print(pe)
The issue I have is that param matches against sect so it expects a =. So I tried putting in ~Literal("sect") in keyName but that just leads to another error:
Exception raised:Found unwanted token, "sect", found '\n' (at char 188), (line:4, col:56)
Expected end of text, found 's' (at char 190), (line:6, col:1)
How do I get it use one parse method for sect and another (param) if not sect?
My final goal would be to have the whole lot in a Dict with the global params and sects included.
EDIT
Think I've figured it out:
This line...
final = OneOrMore(node) | OneOrMore(param)
...should be:
final = ZeroOrMore(param) + ZeroOrMore(node)
But I wonder if there is a more structured way (as I'd ultimately like a dict)?

Tiny Language compiler using python and regex

Hello stack overflow users
I hope you having a good
so I'm doing this tiny language compiler for my homework
tried using regex
but the output is so weird
First of all, I get an Identifier called 't' which is not used in my input
And it doesn't separate Identifier 'x' from the semicolon
thanks in advance for your help
Here is my input
read x; {input an integer }
if 0 < x then { don’t compute if x <= 0 }
fact := 1;
repeat
fact := fact * x;
x := x - 1
until x = 0;
write fact { output factorial of x }
end
And that's my code using regex
# -*- coding: utf-8 -*-
"""
Created on Wed May 13 04:11:06 2020
#author: PC
"""
class OwnCompiler (object):
def __init__ (self,file):
import re
self.file=open(file,"r").readlines()
self.symbols = {
"+":"PLUS_OP",
"-":"MINUS_OP",
"*":"MUL_OP",
"/":"DIV_OP",
"=":"EQUAL_OP",
"<":"LESS_OP",
">":"GREATER_OP",
"(":"LEFT_PARENTHESIS",
")":"RIGHT_PARENTHESIS",
":=":"ASSIGN",
";":"SEMICOLON",
}
self.commentPattern = re.compile(r".*({\n*\s*.*\s*})")
self.reservePattern = re.compile(r"\s*(read|write|if|then|else|end|repeat|until)+\s*(.*)(then)*")
self.symbolPattern = re.compile(r".*(\+|\*|-|/|=|<|>|\(|\)|;)")
self.identifierSymbol = re.compile(r".*(\w+)\s+(:=)\s+(.*)")
def compileOutput(self):
self.fileWrite=open("output.txt","w")
self.fileWrite.write("Type Token\n==================\n")
for i in self.file :
print(i)
self.getComment(i)
self.getReserveWord(i)
self.getIdentify(i)
self.fileWrite.close()#end
def getComment(self,text):
try:
self.fileWrite.write("COMMENT "+self.commentPattern.match(text).group(1)+"\n")
except:
print("NO_COMMENT")
def getReserveWord(self,text):
self.Compiled = self.reservePattern.match(text)
try:
self.fileWrite.write("RESERVE_WORD "+self.Compiled.group(1)+"\n")
self.getSymbols(self.Compiled.group(2))
try:
self.fileWrite.write("RESERVE_WORD "+self.Compiled.group(3)+"\n")
except:
print("NO_RESERVE_WORD2")
except:
print("NO_RESERVE_WORD")
def getSymbols(self,text):
self.Compiled= self.symbolPattern.match(text)
self.GOT_TOKEN= self.getTokensSymbols(self.Compiled.group())
try:
self.fileWrite.write(self.GOT_TOKEN+" "+self.Compiled.group()+"\n")
except:
print("NO_SYMBOLS")
def getIdentify(self,text):
self.Compiled = self.identifierSymbol.match(text)
try:
self.fileWrite.write("IDENTIFIER "+self.Compiled.group(1)+"\n")
self.getSymbols(text)
for i in self.Compiled.group(3):
if i ==" " :
continue
if self.isNumber(i):
self.fileWrite.write("NUMBER ")
else:
self.fileWrite.write("WORD ")
self.fileWrite.write(self.Compiled.group(3)+"\n")
except:
print("NO_IDENTIFIRES")
def getTokensSymbols(self,symbol):
try:
return self.symbols[symbol]
except:
print("NOT_DEFINED_IN_SYMBOL_DICT")
return "UNKNOWN"
def isNumber(self,text):
try:
int(text)
return True
except:
return False
if __name__ == "__main__":
instance = OwnCompiler("input.txt")
instance.compileOutput()
And here is my output
Type Token
==================
COMMENT { Sample program in TINY language – computes factorial }
COMMENT {input an integer }
RESERVE_WORD read
UNKNOWN x;
COMMENT { don’t compute if x <= 0 }
RESERVE_WORD if
UNKNOWN 0 < x then { don’t compute if x <=
IDENTIFIER t
UNKNOWN fact := 1;
RESERVE_WORD repeat
IDENTIFIER t
UNKNOWN fact := fact * x;
IDENTIFIER x
UNKNOWN x := x -
RESERVE_WORD until
UNKNOWN x = 0;
COMMENT { output factorial of x }
RESERVE_WORD write
RESERVE_WORD end

If you are going to parse a language you need a 'lexer' that will return individual tokens ignoring whitespace and comments. Along these lines, just as an example:
import re, collections
class Lexer(object):
WHITESPACE = r'(?P<WHITESPACE>\s+)'
COMMENT = r'(?P<COMMENT>{[^}]*})'
READ = r'(?P<READ>\bread\b)'
WRITE = r'(?P<WRITE>\bwrite\b)'
IF = r'(?P<IF>\bif\b)'
THEN = r'(?P<THEN>\bthen\b)'
ELSE = r'(?P<ELSE>\belse\b)'
END = r'(?P<END>\bend\b)'
REPEAT = r'(?P<REPEAT>\brepeat\b)'
UNTIL = r'(?P<UNTIL>\buntil\b)'
OPERATOR = r'(?P<OPERATOR>(?:[+*/=<>-]|:=))'
LPAREN = r'(?P<LPAREN>\()'
RPAREN = r'(?P<RPAREN>\))'
IDENTIFIER = r'(?P<IDENTIFIER>[a-z]+)'
INTEGER = r'(?P<INTEGER>\d+)'
SEMICOLON = r'(?P<SEMICOLON>;)'
regex = re.compile('|'.join([
WHITESPACE,
COMMENT,
READ,
WRITE,
IF,
THEN,
ELSE,
END,
REPEAT,
UNTIL,
OPERATOR,
LPAREN,
RPAREN,
IDENTIFIER,
INTEGER,
SEMICOLON
]))
def __init__ (self, file):
def generate_tokens(text):
Token = collections.namedtuple('Token', ['type','value'])
scanner = Lexer.regex.finditer(text)
last_end = 0
for m in scanner:
start = m.start()
end = m.end()
if start != last_end:
# skipped over text to find the next token implies that there was unrecognizable text or an "error token"
text = self.text[last_end:start]
token = Token('ERROR', text)
yield token
last_end = end
token = Token(m.lastgroup, m.group())
if token.type != 'WHITESPACE' and token.type != 'COMMENT':
yield token
yield Token('EOF', '<end-of-file>')
with open(file, "r") as f:
text = f.read()
self._token_generator = generate_tokens(text)
def next_token(self):
# if you call this past the "EOF" token you will get a StopIteration exception
return self._token_generator.__next__()
lexer = Lexer('input.txt')
while True:
token = lexer.next_token()
print(token)
if token.type == 'EOF':
break
Prints:
Token(type='READ', value='read')
Token(type='IDENTIFIER', value='x')
Token(type='SEMICOLON', value=';')
Token(type='IF', value='if')
Token(type='INTEGER', value='0')
Token(type='OPERATOR', value='<')
Token(type='IDENTIFIER', value='x')
Token(type='THEN', value='then')
Token(type='IDENTIFIER', value='fact')
Token(type='OPERATOR', value=':=')
Token(type='INTEGER', value='1')
Token(type='SEMICOLON', value=';')
Token(type='REPEAT', value='repeat')
Token(type='IDENTIFIER', value='fact')
Token(type='OPERATOR', value=':=')
Token(type='IDENTIFIER', value='fact')
Token(type='OPERATOR', value='*')
Token(type='IDENTIFIER', value='x')
Token(type='SEMICOLON', value=';')
Token(type='IDENTIFIER', value='x')
Token(type='OPERATOR', value=':=')
Token(type='IDENTIFIER', value='x')
Token(type='OPERATOR', value='-')
Token(type='INTEGER', value='1')
Token(type='UNTIL', value='until')
Token(type='IDENTIFIER', value='x')
Token(type='OPERATOR', value='=')
Token(type='INTEGER', value='0')
Token(type='SEMICOLON', value=';')
Token(type='WRITE', value='write')
Token(type='IDENTIFIER', value='fact')
Token(type='END', value='end')
Token(type='EOF', value='<end-of-file>')

Can't get live output from python file to vb.net by ProcessStartInfo

Hi I know there is alot of the same question out here already but I tried every single one of them and can't seem to get why it won't work.
Here is my code
Private Sub CallbackProcessAsync(sender As Object, args As System.Diagnostics.DataReceivedEventArgs)
Console.WriteLine(args.Data)
Me.Invoke(Sub() statusRichText.AppendText(args.Data & Environment.NewLine))
End Sub
Sub SuperUpload()
Dim oProcess As New Process()
AddHandler oProcess.ErrorDataReceived, AddressOf CallbackProcessAsync
AddHandler oProcess.OutputDataReceived, AddressOf CallbackProcessAsync
Dim oStartInfo As New ProcessStartInfo("C:\Users\RKjetski\AppData\Local\Programs\Python\Python37\python.exe", "test.py " + vInfoIframe.Text + " " + vInfoID.Text)
oStartInfo.UseShellExecute = False
oStartInfo.CreateNoWindow = True
oStartInfo.RedirectStandardError = True
oStartInfo.RedirectStandardOutput = True
oProcess.EnableRaisingEvents = True
oProcess.StartInfo = oStartInfo
oProcess.Start()
oProcess.BeginErrorReadLine()
oProcess.BeginOutputReadLine()
End Sub
Private Sub Button1_Click(sender As Object, e As EventArgs) Handles btnSuperUpload.Click
Dim thread = New System.Threading.Thread(AddressOf SuperUpload)
thread.Start()
End Sub
The python file
import time
x = 0
while x < 5:
print(x)
time.sleep(2)
x = x +1
I get the following output but it's not live / in real time, the rich text box is empty until it read the program and then it prints everything instantly.
0
1
2
3
4

Multiplex address and data to show string of letters over parallel port

A month ago, i asked this about multiplexing a string of numbers with 4 7-segment displays. But now, I'm trying to update the code to multiplex a string of letters using 7 7-segment displays in python.
This is the new circuit. When i send data using the parallel port, the Latch Enable receives the most significant bit (pin 9). In the second latch, the Latch Enable receives it also but negated, that is the reason of the 7404.
That is either address is set (/LE==False) or data is set (/LE=True).
This is what I'm trying to do. The 'X' represents that the 7-segment display is off. But can't archive it.
XXXXXXX
XXXXXXS
XXXXXST
XXXXSTA
XXXSTAC
XXSTACK
XSTACKX
STACKX0
TACKX0V
ACKX0V3
CKX0V3R
KX0V3RF
X0VERFL
0VERFL0
VERFL0W
ERFL0WX
RFL0WXX
FL0WXXX
L0WXXXX
0WXXXXX
WXXXXXX
XXXXXXX
That would be the output for the string "STACK 0V3RFL0W".
Also the past code:
import sys
import parallel
class Display(object):
def __init__(self):
'''Init and blank the "display".'''
self.display = [' '] * 4
self._update()
def setData(self,data):
'''Bits 0-3 are the "value".
Bits 4-7 are positions 0-3 (first-to-last).
'''
self.display = [' '] * 4
value = data & 0xF
if data & 0x10:
self.display[0] = str(value)
if data & 0x20:
self.display[1] = str(value)
if data & 0x40:
self.display[2] = str(value)
if data & 0x80:
self.display[3] = str(value)
self._update()
def _update(self):
'''Write over the same four terminal positions each time.'''
sys.stdout.write(''.join(self.display) + '\r')
if __name__ == '__main__':
p = Display()
pp=parallel.Parallel()
nums = raw_input("Enter a string of numbers: ")
# Shift over the steam four-at-a-time.
stream = 'XXXX' + nums + 'XXXX'
data = [0] * 4
for i in range(len(stream)-3):
# Precompute data
for pos in range(4):
value = stream[i+pos]
data[pos] = 0 if value == 'X' else (1<<(pos+4)) + int(value)
# "Flicker" the display...
for delay in xrange(1000):
# Display each position briefly.
for d in data:
pp.setData(d)
# Clear the display when done
p.setData(0)

Algorithm outline:
string = "07831505"
while True:
for i in range(7):
# switch display `i` on
notlatch.set(True)
data.set(1 << i)
notlatch.set(False)
time.sleep(<very little>)
notlatch.set(True)
# display character on display `i`
data.set(char_to_7segment(string[i]))
time.sleep(0.01)

PLPGSQL using single quotes in function call (python)

I am having problems when using single quotes in a insert value for a plpgsql function
It looks like this:
"AND (u.firstname LIKE 'koen') OR
(u.firstname LIKE 'dirk')"
This is done with python
I have tried \' and '' and ''' and '''' and ''''' and even '''''''
none of them seem to be working and return the following error:
[FAIL][syntax error at or near "koen"
LINE 1: ...'u.firstname', 'ASC', 'AND (u.firstname LIKE 'koe...
Any help is appreciated!
Thanks a lot!
======================== EDIT =========================
Sorry! here is my plpgsql function:
CREATE FUNCTION get_members(IN in_company_uuid uuid, IN in_start integer, IN in_limit integer, IN in_sort character varying, IN in_order character varying, IN in_querystring CHARACTER VARYING, IN in_filterstring CHARACTER VARYING, IN OUT out_status integer, OUT out_status_description character varying, OUT out_value character varying[]) RETURNS record
LANGUAGE plpgsql
AS $$DECLARE
temp_record RECORD;
temp_out_value VARCHAR[];
--temp_member_struct MEMBER_STRUCT;
temp_iterator INTEGER := 0;
BEGIN
FOR temp_record IN EXECUTE '
SELECT DISTINCT ON
(' || in_sort || ')
u.user_uuid,
u.firstname,
u.preposition,
u.lastname,
array_to_string_ex(ARRAY(SELECT email FROM emails WHERE user_uuid = u.user_uuid)) as emails,
array_to_string_ex(ARRAY(SELECT mobilenumber FROM mobilenumbers WHERE user_uuid = u.user_uuid)) as mobilenumbers,
array_to_string_ex(ARRAY(SELECT c.name FROM targetgroupusers AS tgu LEFT JOIN membercategories as mc ON mc.targetgroup_uuid = tgu.targetgroup_uuid LEFT JOIN categories AS c ON mc.category_uuid = c.category_uuid WHERE tgu.user_uuid = u.user_uuid)) as categories,
array_to_string_ex(ARRAY(SELECT color FROM membercategories WHERE targetgroup_uuid IN(SELECT targetgroup_uuid FROM targetgroupusers WHERE user_uuid = u.user_uuid))) as colors
FROM
membercategories AS mc
LEFT JOIN
targetgroups AS tg
ON
tg.targetgroup_uuid = mc.targetgroup_uuid
LEFT JOIN
targetgroupusers AS tgu
ON
tgu.targetgroup_uuid = tg.targetgroup_uuid
LEFT JOIN
users AS u
ON
u.user_uuid = tgu.user_uuid
WHERE
mc.company_uuid = ''' || in_company_uuid || '''
' || in_querystring || '
' || in_filterstring || '
ORDER BY
' || in_sort || ' ' || in_order || '
OFFSET
' || in_start || '
LIMIT
' || in_limit
LOOP
temp_out_value[temp_iterator] = ARRAY[temp_record.user_uuid::VARCHAR(36),
temp_record.firstname,
temp_record.preposition,
temp_record.lastname,
temp_record.emails,
temp_record.mobilenumbers,
temp_record.categories,
temp_record.colors];
temp_iterator = temp_iterator+1;
END LOOP;
out_status := 0;
out_status_description := 'Members retrieved';
out_value := temp_out_value;
RETURN;
END$$;
Here is how i call the function:
def get_members(companyuuid, start, limit, sort, order, querystring = None, filterstring = None):
logRequest()
def doWork(cursor):
if not companyuuid:
raise Exception("companyuuid cannot be None!")
queryarray = [str(s) for s in querystring.split("|")]
queryfields = ['firstname', 'preposition', 'lastname', 'emails', 'mobilenumbers']
temp_querystring = ""
for j in xrange(len(queryfields)):
for i in xrange(len(queryarray)):
temp_querystring += "(u.%s LIKE ''%%%s%'') OR "%(queryfields[j], queryarray[i])
temp_querystring = "AND %s"%temp_querystring.rstrip(" OR ")
temp_filterstring = filterstring
print "querystring: %s"%temp_querystring
heizoodb.call(cursor=cursor,
scheme="public",
function="get_members",
functionArgs=(companyuuid, start, limit, sort, order, temp_querystring, temp_filterstring),
returnsValue=True)
And my latest error =D
com.gravityzoo.core.libs.sql.PostgreSQLDB.runSQLTransaction: not enough arguments for format string, result=[None]
SQLinjection to be added later ;)
Thanks!

I don't know Python well, but it probably supports data binding where you first prepare a statement (and you don't need quotes around the question marks there):
prepare("..... AND (u.firstname LIKE ?) OR (u.firstname LIKE ?)")
and then you call execute('koen', 'dirk') or whatever that function is called in Python.