CODEWITHSUNDEEP
pythonpython-2.7
user2671189
user2671189

Reputation: 13

Python: How do I parse a string into a recursive dictionary

Coming from a file I have something like the following string: 

var1 : data1
var2 : data2
dict1 {  
     var3 : data3  
     dict2 {  
         var4 : data4  
     }
     var5 : data5
}
dict3 {
     var6 : data6
     var7 : data7
}

and so on. (end of lines are \n, indents are \t each)
And I try to convert it into something like that:

Dictionary={"var1":"data1","var2":"data2", "dict1" : 
    {"var3":"data3", "dict2" : {
        "var4":"data4" }, "var5":"data5"}
    , dict3:{"var6":"data6","var7":"data7"}

(indents are only too keep it somehow human readable)
To solve it, all I can think of, is to split it into a list, then walk the list down until I find a "}" in the string, delete it (so i won't run into it later), then walk up until I find string with "{", remove the whitespaces before and the " {" after (using right now temp=re.split ('(\S+) \{',out[z]) for this example the 1st temp[1] would be 'dict2'), add everything in between, and finally move on to the next "}".

But that's not fast or elegant. I am definitely missing something.
code is currently:

def procvar(strinG):
    x=y=z=temp1=temp2=0
    back = False
    out=re.split ('\n',strinG) #left over from some other tries
    while z < len(out):
        print "z=",z," out[z]= ", out[z]
        if "{" in out[z]:
            if back == True:
                back = False
                xtemp=re.split ('(\S+) \{',out[z])
                out[z]=xtemp[1]
                ytemp=xtemp[1]
                temp2=z+1
                print "Temp: ",temp1," - ",out[temp1]
                out[z]={out[z]:[]}
                while temp2 <= temp1:
                    out[z][xtemp[1]].append(out[temp2]) # not finished here, for the time being I insert the strings as they are
                    del out[temp2]
                    temp1-=1
                print out[z]
        if "}" in out[z]:
            back = True
            del out[z]
            temp1 = z-1
        if back == True:
            z-=1
        else:
            z+=1
    return out

Upvotes: 1

Views: 1140

Answers (3)

Viktor Kerkez
Viktor Kerkez

Reputation: 46596

import re

# key : value regexp
KV_RE = re.compile(r'^\s*(?P<key>[^\s]+)\s+:\s+(?P<value>.+?)\s*$')
# dict start regexp
DS_RE = re.compile(r'^\s*(?P<key>[^\s]+)\s+{\s*$')
# dict end regexp
DE_RE = re.compile(r'^\s*}\s*$')


def parse(s):
    current = {}
    stack = []
    for line in s.strip().splitlines():
        match = KV_RE.match(line)
        if match:
            gd = match.groupdict()
            current[gd['key']] = gd['value']
            continue
        match = DS_RE.match(line)
        if match:
            stack.append(current)
            current = current.setdefault(match.groupdict()['key'], {})
            continue
        match = DE_RE.match(line)
        if match:
            current = stack.pop()
            continue
        # Error occured
        print('Error: %s' % line)
        return {}
    return current

Upvotes: 0

dawg
dawg

Reputation: 103864

If your text is in the same regular pattern as the example, you can use ast.literal_eval to parse the string.

First, let's modify the string to be legal Python dict text:

import re

st='''\
var1 : data1
var2 : data2
dict1 {  
     var3 : data3  
     dict2 {  
         var4 : data4  
     }
     var5 : data5
}
'''

# add commas after key, val pairs
st=re.sub(r'^(\s*\w+\s*:\s*\w+)\s*$',r'\1,',st,flags=re.M)

# insert colon after name and before opening brace 
st=re.sub(r'^\s*(\w+\s*){\s*$',r'\1:{',st,flags=re.M)

# add comma closing brace
st=re.sub(r'^(\s*})\s*$',r'\1,',st,flags=re.M)

# put names into quotes
st=''.join(['"{}"'.format(s.group(0)) if re.search(r'\w+',s.group(0)) else s.group(0) 
                for s in re.finditer(r'\w+|\W+',st)])

# add opening and closing braces
st='{'+st+'}'
print st

prints the modified string:

{"var1" : "data1",
"var2" : "data2",
"dict1" :{
     "var3" : "data3",
"dict2" :{
         "var4" : "data4",
     },
     "var5" : "data5",
},}

Now use ast to turn the string into a data structure:

import ast
print ast.literal_eval(st)

prints

{'dict1': {'var5': 'data5', 'var3': 'data3', 'dict2': {'var4': 'data4'}}, 'var1': 'data1', 'var2': 'data2'}

Upvotes: 0

thierrybm
thierrybm

Reputation: 129

your format is close enough to the yaml one (easy_install pyyaml): http://pyyaml.org/wiki/PyYAML

x = """var1 : data1
var2 : data2
dict1 {  
     var3 : data3  
     dict2 {  
         var4 : data4  
     }
     var5 : data5
}
dict3 {
     var6 : data6
     var7 : data7
}"""

x2 = x.replace('{', ':').replace('}','')
yaml.load(x2) 

{'dict1': {'dict2': {'var4': 'data4'}, 'var3': 'data3', 'var5': 'data5'},
 'dict3': {'var6': 'data6', 'var7': 'data7'},
 'var1': 'data1',
 'var2': 'data2'}

Upvotes: 2

Related Questions