fork(1) download
copy 
  1. textstream=[
  2.   "This ",
  3.   "is ",
  4.   "a ",
  5.   "reference ",
  6.   "[",  # Notice that anything can be broken across different messages
  7.   "r1] ",
  8.   "and ",
  9.   "here",
  10.   "'s ",
  11.   "an ",
  12.   "image ",
  13.   "of ",
  14.   "a ",
  15.   "cat <",  # A more extreme example, breaking messages completely arbitrary
  16.   "ima",
  17.   "ge",
  18.   ">a ",
  19.   "black ",
  20.   "ca",
  21.   "t</i",
  22.   "mage>.",
  23. ]
  24. charstream=(char for fragment in textstream for char in fragment)
  25.  
  26. state="text"  # state, can switch to "reference" and "tag"
  27. collector=""  # temporary storage between state changes
  28. parsed=[]     # list of parsed result
  29.  
  30. for character in charstream:
  31.   oldstate=state             # 2. (so we recognize state changes)
  32.   if character=="[":         # 1.
  33.     state="reference"
  34.   elif character=="]":
  35.     state="text"
  36.   elif character=="<":
  37.     state="tag"
  38.   elif character==">":
  39.     state="text"
  40.   else:
  41.     collector+=character
  42.   if oldstate!=state and collector:        # 2.
  43.     parsed.append({oldstate:collector})
  44.     collector=""
  45.  
  46. if collector:                # 3.-ish
  47.   parsed.append({state:collector}) # could be an error if not state is not "text"
  48.  
  49. import json
  50. print(json.dumps(parsed,indent=2))
  51.  
  52. print("-----------------------------------")
  53.  
  54. result=[]
  55. tag=""
  56. for element in parsed:
  57.   if "tag" in element:
  58.     if tag=="":           # entering a tag
  59.       tag=element["tag"]
  60.     else:
  61.       tag=""              # it's an exit, could be validated
  62.   else:
  63.     if tag=="":           # we are at top level
  64.       result.append(element)
  65.     else:                 # we use the tag, and also expect "text"
  66.       result.append({tag:element["text"]})
  67.  
  68. print(json.dumps(result,indent=2))
Success #stdin #stdout 0.03s 9724KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
[
  {
    "text": "This is a reference "
  },
  {
    "reference": "r1"
  },
  {
    "text": " and here's an image of a cat "
  },
  {
    "tag": "image"
  },
  {
    "text": "a black cat"
  },
  {
    "tag": "/image"
  },
  {
    "text": "."
  }
]
-----------------------------------
[
  {
    "text": "This is a reference "
  },
  {
    "reference": "r1"
  },
  {
    "text": " and here's an image of a cat "
  },
  {
    "image": "a black cat"
  },
  {
    "text": "."
  }
]
https://ideone.com/UR5E5i
language:
Python 3 (python  3.12)
created:
1 year ago
visibility:
secret

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!