199 lines
12 KiB
Plaintext
199 lines
12 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 380,
|
|
"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)"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 381,
|
|
"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):\r\n",
|
|
" if type(entry[\"value\"]) == str:\r\n",
|
|
" # convert values to proper types as needed\r\n",
|
|
" if entry[\"type\"][\"name\"] == \"float\":\r\n",
|
|
" converted_value = float(entry[\"value\"])\r\n",
|
|
" elif entry[\"type\"][\"name\"] == \"int\":\r\n",
|
|
" converted_value = int(entry[\"value\"])\r\n",
|
|
" elif entry[\"type\"][\"name\"] == \"vector\":\r\n",
|
|
" converted_value = entry[\"value\"].split(\",\")\r\n",
|
|
" for i, value in enumerate(converted_value):\r\n",
|
|
" converted_value[i] = float(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",
|
|
" else:\r\n",
|
|
" return entry\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\": \"\", \"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",
|
|
" # parse into proper values\r\n",
|
|
" entry = parse_entry(entry)\r\n",
|
|
" cache[stage].append(entry)\r\n",
|
|
" entry = {\"type\": \"\", \"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",
|
|
" # parse into proper values\r\n",
|
|
" entry = parse_entry(entry)\r\n",
|
|
" cache[stage].append(entry)\r\n",
|
|
" entry = {\"type\": \"\", \"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",
|
|
" # handle nested types\r\n",
|
|
" if \"=\" in entry[\"value\"]:\r\n",
|
|
" type_parent = cache[\"names\"][int(entry[\"value\"][0])]\r\n",
|
|
" type_children = entry[\"value\"][2:].split(\"/\")\r\n",
|
|
" for i, child in enumerate(type_children):\r\n",
|
|
" child_name = cache[\"names\"][int(child.split(\".\")[0])]\r\n",
|
|
" child_type = cache[\"names\"][int(child.split(\".\")[1])]\r\n",
|
|
" type_children[i] = {\"name\": child_name, \"type\": child_type}\r\n",
|
|
" this_type = {\r\n",
|
|
" \"name\": type_parent,\r\n",
|
|
" \"parameters\": type_children\r\n",
|
|
" }\r\n",
|
|
" entry[\"type\"] = this_type\r\n",
|
|
" else:\r\n",
|
|
" this_type = entry[\"value\"]\r\n",
|
|
" entry[\"type\"] = {\"name\": cache[\"names\"][int(this_type, base = 16)], \"parameters\": []}\r\n",
|
|
" entry[\"value\"] = \"\"\r\n",
|
|
" continue\r\n",
|
|
" elif char == \"&\":\r\n",
|
|
" is_reference = True\r\n",
|
|
" continue\r\n",
|
|
"\r\n",
|
|
" if consume:\r\n",
|
|
" # handle cache references\r\n",
|
|
" if is_reference:\r\n",
|
|
" cached_object = cache[\"cache\"][int(char, base = 16)]\r\n",
|
|
" entry = cached_object\r\n",
|
|
" continue\r\n",
|
|
" else:\r\n",
|
|
" entry[\"value\"] += char"
|
|
],
|
|
"outputs": [
|
|
{
|
|
"output_type": "error",
|
|
"ename": "AttributeError",
|
|
"evalue": "'dict' object has no attribute 'split'",
|
|
"traceback": [
|
|
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[1;31mAttributeError\u001b[0m Traceback (most recent call last)",
|
|
"\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_19468/2470265224.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m 57\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mstage\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[1;34m\"names\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 58\u001b[0m \u001b[1;31m# parse into proper values\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 59\u001b[1;33m \u001b[0mentry\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mparse_entry\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mentry\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 60\u001b[0m \u001b[0mcache\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mstage\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mentry\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 61\u001b[0m \u001b[0mentry\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m{\u001b[0m\u001b[1;34m\"type\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m\"\"\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"value\"\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;34m\"\"\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_19468/2470265224.py\u001b[0m in \u001b[0;36mparse_entry\u001b[1;34m(entry)\u001b[0m\n\u001b[0;32m 18\u001b[0m \u001b[0mconverted_value\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfloat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 19\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0mentry\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"type\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"name\"\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m\"object\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 20\u001b[1;33m \u001b[0mconverted_value\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mentry\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"/\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 21\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 22\u001b[0m \u001b[0mconverted_value\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mentry\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"value\"\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
|
|
"\u001b[1;31mAttributeError\u001b[0m: 'dict' object has no attribute 'split'"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"source": [
|
|
"graph = cache[\"objects\"]"
|
|
],
|
|
"outputs": [],
|
|
"metadata": {}
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"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
|
|
} |