Creating a JSON object from a tabbed text file
I have this sample text file: (I don't know what you call it, Tree?)
key1
subkey1
subkey2
choice1
key2
subkey1
subkey2
I want it to look like this:
[
{
"text":"key1",
"children":[
{
"text":"subkey1",
children:[]
},
{
"text":"subkey2",
children:[
{
"text":"choice1",
"children":[]
}
]
},
]
},
{
"text":"key2",
"children":[
{
"text":"subkey1",
children:[]
},
{
"text":"subkey2",
children:[]
},
]
}
]
This is what I am doing, I do not understand how you get the children in the parent and it should be infinitely deep possible.
import itertools
def r(f, depth, parent, l, children):
for line in f:
line = line.rstrip()
newDepth = sum(1 for i in itertools.takewhile(lambda c: c=='\t', line))
node = line.strip()
if parent is not None:
print parent, children
children = [{"txt":node, "children":[]}]
# l.append({"txt":parent, "children":children})
r(f, newDepth, node, l, children)
json_list = []
r(open("test.txt"), 0, None, json_list, [])
print json_list
+3
source to share
1 answer
First rule, avoid recursion if you can ... Here you only need to know the ancestors and they can be easily stored in a list. Note that depth
0 is reserved for the root node, and the first is "custom" depth 1
, so +1
when counting tabs.
f = open("/tmp/test.txt", "r")
depth = 0
root = { "txt": "root", "children": [] }
parents = []
node = root
for line in f:
line = line.rstrip()
newDepth = len(line) - len(line.lstrip("\t")) + 1
print newDepth, line
# if the new depth is shallower than previous, we need to remove items from the list
if newDepth < depth:
parents = parents[:newDepth]
# if the new depth is deeper, we need to add our previous node
elif newDepth == depth + 1:
parents.append(node)
# levels skipped, not possible
elif newDepth > depth + 1:
raise Exception("Invalid file")
depth = newDepth
# create the new node
node = {"txt": line.strip(), "children":[]}
# add the new node into its parent children
parents[-1]["children"].append(node)
json_list = root["children"]
print json_list
+5
source to share