s444341/cnlps-caiccaic
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

solution

Browse Source
This commit is contained in:
Jakub Adamski 2023-06-12 00:59:19 +02:00
parent bc5869a233
commit 9eeb8e7eec
4 changed files with 30240 additions and 9507 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18970
dev-A/out.tsv
View File

File diff suppressed because it is too large Load Diff

49
format.ipynb
View File

@ -2,41 +2,50 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 4,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Data has been formatted and saved to output.txt\n"
]
}
],
"source": [ "source": [
"import re\n", "import re\n",
"\n", "\n",
"# Open input file in read mode and output file in write mode\n", "# Open input file in read mode and output file in write mode\n",
"with open('dev-A/out.tsv', 'r', encoding=\"utf-8\") as infile, open('dev-A/parsed.tsv', 'w', encoding=\"utf-8\") as outfile:\n", "with open('test-A/out.tsv', 'r', encoding=\"utf-8\") as infile, open('test-A/parsed.tsv', 'w', encoding=\"utf-8\") as outfile:\n",
"\n",
" # Default text to use when text segment is missing\n",
" default_text = \"Airconditioner\"\n",
"\n", "\n",
" # Iterate through each line in the input file\n", " # Iterate through each line in the input file\n",
" for line in infile:\n", " for line in infile:\n",
"\n", "\n",
" # Regular expression to match \"{...}\" or \"}\"\n", " # Regular expression to match \"{...}\" or \"}\"\n",
" match = re.search(r'({.*}|\\})', line)\n", " match = re.search(r'({.*}|\\}[^{]*$)', line)\n",
"\n", "\n",
" # If \"{...}\" or \"}\" is found\n", " # If \"{...}\" or \"}\" is found\n",
" if match:\n", " if match:\n",
" # Extract \"{...}\" or \"}\" from the line\n", " # Extract \"{...}\" or \"}\" from the line\n",
" data = match.group(0)\n", " data = match.group(0).strip()\n",
"\n", "\n",
" # Extract the text before \"{...}\" or \"}\"\n", " # Extract the text before \"{...}\" or \"}\"\n",
" text = line[:match.start()].strip()\n", " text = line[:match.start()].strip()\n",
"\n", "\n",
" # Split the text into segments\n", " # If data is not enclosed within curly braces, enclose it\n",
" segments = text.split()\n", " if not data.startswith('{'):\n",
" data = '{' + data\n",
"\n", "\n",
" # If no segments, it means only data is present\n", " # If text segment is missing, use default text\n",
" if not segments:\n", " if not text:\n",
" outfile.write(data + '\\n')\n", " text = default_text\n",
" # If only one segment, duplicate it to conform to the format \"text\\ttext\\t{data}\"\n", "\n",
" elif len(segments) == 1:\n", " # Write to output file with the desired format\n",
" outfile.write(segments[0] + '\\t' + segments[0] + '\\t' + data + '\\n')\n", " outfile.write(f\"{text}\\t{text}\\t{data}\\n\")\n",
" # If more than one segment, use them as is\n",
" else:\n",
" outfile.write('\\t'.join(segments) + '\\t' + data + '\\n')\n",
" else:\n", " else:\n",
" # If the line doesn't contain \"{...}\" or \"}\", write it as is\n", " # If the line doesn't contain \"{...}\" or \"}\", write it as is\n",
" outfile.write(line)\n", " outfile.write(line)\n",
@ -53,7 +62,15 @@
"name": "python3" "name": "python3"
}, },
"language_info": { "language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python", "name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.10" "version": "3.10.10"
}, },
"orig_nbformat": 4 "orig_nbformat": 4

10358
test-A/out.tsv Normal file
View File

File diff suppressed because it is too large Load Diff

10358
test-A/raw-out.tsv Normal file
View File

File diff suppressed because it is too large Load Diff