Neutrino/python/NeutrinoParser.ipynb

170 lines
6.9 KiB
Plaintext

{
"cells": [
{
"cell_type": "code",
"execution_count": 109,
"source": [
"# load up the test file\r\n",
"data = open(\"Test.neu\").read()\r\n",
"\r\n",
"# deal with newlines\r\n",
"data = data.split(\"\\n\")\r\n",
"for i, line in enumerate(data):\r\n",
" data[i] = line.strip()\r\n",
"data = \"\".join(data)\r\n",
"\r\n",
"data"
],
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'@{string,float,int}#{2:\"100\"}*{&0,0:\"Hello, world! :@#*\",1:\"512.0\",&0}'"
]
},
"metadata": {},
"execution_count": 109
}
],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 110,
"source": [
"cache = {\r\n",
" \"names\": [],\r\n",
" \"cache\": [],\r\n",
" \"objects\": []\r\n",
"}\r\n",
"\r\n",
"# parse a string entry according to its type and return a dict\r\n",
"def parse_entry(entry_type, entry_value):\r\n",
" # convert values to proper types as needed\r\n",
" if entry_type == \"float\":\r\n",
" converted_value = float(entry_value)\r\n",
" elif entry_type == \"int\":\r\n",
" converted_value = int(entry_value)\r\n",
" else:\r\n",
" converted_value = entry_value\r\n",
"\r\n",
" # return a dictionary of the parsed entry\r\n",
" return {\"type\": entry_type, \"value\": converted_value}\r\n",
"\r\n",
"# iterate through each character in the raw data and create a cache of parsed strings\r\n",
"stage = \"\"\r\n",
"entry_type = \"\"\r\n",
"entry_value = \"\"\r\n",
"consume = False\r\n",
"is_literal = False\r\n",
"is_reference = False\r\n",
"for char in data:\r\n",
" if char == '\"':\r\n",
" # enter/exit literal consumption (handle special characters in values)\r\n",
" is_literal = not is_literal\r\n",
" continue\r\n",
" # ignore special characters if they're within a literal value\r\n",
" if not is_literal:\r\n",
" if char == \"@\":\r\n",
" stage = \"names\"\r\n",
" continue\r\n",
" elif char == \"*\":\r\n",
" stage = \"objects\"\r\n",
" continue\r\n",
" elif char == \"#\":\r\n",
" stage = \"cache\"\r\n",
" continue\r\n",
" elif char == \"{\":\r\n",
" # start consuming at the start of each stage\r\n",
" consume = True\r\n",
" continue\r\n",
" elif char == \"}\":\r\n",
" # commit entry\r\n",
" if stage != \"names\":\r\n",
" cache[stage].append(parse_entry(entry_type, entry_value))\r\n",
" else:\r\n",
" cache[stage].append(entry_value)\r\n",
" entry_value = \"\"\r\n",
"\r\n",
" is_reference = False\r\n",
"\r\n",
" # stop consuming at the end of each stage\r\n",
" consume = False\r\n",
" elif char == \",\":\r\n",
" # commit entry\r\n",
" if stage != \"names\":\r\n",
" cache[stage].append(parse_entry(entry_type, entry_value))\r\n",
" else:\r\n",
" cache[stage].append(entry_value)\r\n",
" entry_value = \"\"\r\n",
" \r\n",
" is_reference = False\r\n",
"\r\n",
" continue\r\n",
" elif char == \":\":\r\n",
" # handle names/types\r\n",
" entry_type = cache[\"names\"][int(entry_value, base = 16)]\r\n",
" entry_value = \"\"\r\n",
" continue\r\n",
"\r\n",
" if consume:\r\n",
" # handle cache references\r\n",
" if entry_value == \"&\":\r\n",
" cached_object = cache[\"cache\"][int(char, base = 16)]\r\n",
" entry_type = cached_object[\"type\"]\r\n",
" entry_value = cached_object[\"value\"]\r\n",
" continue\r\n",
" else:\r\n",
" entry_value += char"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 111,
"source": [
"graph = cache[\"objects\"]"
],
"outputs": [],
"metadata": {}
},
{
"cell_type": "code",
"execution_count": 112,
"source": [
"# DEBUG\r\n",
"import json\r\n",
"with open(\"NeutrinoTest_Cache.json\", \"w\") as outfile:\r\n",
" json.dump(graph, outfile, indent = 4)"
],
"outputs": [],
"metadata": {}
}
],
"metadata": {
"orig_nbformat": 4,
"language_info": {
"name": "python",
"version": "3.7.8",
"mimetype": "text/x-python",
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"pygments_lexer": "ipython3",
"nbconvert_exporter": "python",
"file_extension": ".py"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3.7.8 64-bit"
},
"interpreter": {
"hash": "57baa5815c940fdaff4d14510622de9616cae602444507ba5d0b6727c008cbd6"
}
},
"nbformat": 4,
"nbformat_minor": 2
}