{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import re"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"EXTRA_DIGITS = {\n",
" \"i\": 1,\n",
" \"l\": 1,\n",
"}\n",
"\n",
"EXTRA_DIGIT_STR = \"\".join(EXTRA_DIGITS)\n",
"\n",
"NUMBER_SANITY_RE = re.compile(\n",
" fr\"\"\"\n",
" \\b\n",
" (?:\n",
" [0-9{EXTRA_DIGIT_STR}]\n",
" [0-9{EXTRA_DIGIT_STR}.,/-]*\n",
" [0-9{EXTRA_DIGIT_STR}]\n",
" )\n",
" \\b\n",
" \"\"\",\n",
" re.S | re.X,\n",
")\n",
"\n",
"\n",
"def numberRepl(match):\n",
" number = match.group(0)\n",
" for (extraDigit, value) in EXTRA_DIGITS.items():\n",
" number = number.replace(extraDigit, str(value))\n",
" return number"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"text = \"\"\"\n",
"de poederzuijker voor l32/243 Spaans de frazel van 27 lb, reekent 35 V2 percento
\n",
"\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"de poederzuijker voor 132/243 Spaans de frazel van 27 lb, reekent 35 V2 percento
\n",
"\n"
]
}
],
"source": [
"text = NUMBER_SANITY_RE.sub(numberRepl, text)\n",
"print(text)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"MARK_NUM = r\"\"\"\n",
" (?:\n",
" [0-9]{1,2}\n",
" (?:\n",
" \\s+\n",
" [0-9]{1,2}\n",
" )*\n",
" )\n",
"\"\"\"\n",
"\n",
"MARK_PLAIN_RE = re.compile(\n",
" fr\"\"\"\n",
" (\n",
" (?:\n",
" \n",
" {MARK_NUM}\n",
" \n",
" )\n",
" |\n",
" (?:\n",
" ⌊\n",
" [0-9]{{1,2}}\n",
" ⌋\n",
" )\n",
" |\n",
" (?:\n",
" (?<=[a-zé])\n",
" [0-9]{{1,2}}\n",
" \\b\n",
" )\n",
" |\n",
" (?:\n",
" (?<=[a-zé][;.])\n",
" [0-9]{{1,2}}\n",
" \\b\n",
" )\n",
" )\n",
" \"\"\",\n",
" re.S | re.X,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"text = \"\"\"van het eyland Zakynthos28,
\"\"\""
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"match = MARK_PLAIN_RE.search(text)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"match"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'28'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"match.group(0)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}