forked from bfijalkowski/KWT-2024
add documents
This commit is contained in:
parent
7d98005446
commit
b002f5c96a
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
|
@ -15,6 +15,38 @@
|
|||
"![Logo 2](https://git.wmi.amu.edu.pl/AITech/Szablon/raw/branch/master/Logotyp_AITech2.jpg)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"id": "51e04a27-7c37-4a2b-a6d8-31abc09ae0ca",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"form1\n",
|
||||
"form2\n",
|
||||
"form3\n",
|
||||
"form2\n",
|
||||
"form2\n",
|
||||
"form1\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import re\n",
|
||||
"# nawiasy w rexexp = tworzy z tego grupę. w tym przypadku ma 4 grupy \n",
|
||||
"# grupa o indexie 0 to grupa całość\n",
|
||||
"# grupa o indeksie 1 to to co sformatowało się dopasowało wymachowało z pierwszą grupą\n",
|
||||
"\n",
|
||||
"string = \"aaaform1aaaahform2uadaiudform3oihdhdform2oahdoihwfform2oiadoafform11\"\n",
|
||||
"pattern = re.compile(r'(form1)|(form2)|(form3)')\n",
|
||||
"x = pattern.finditer(string)\n",
|
||||
"for xx in x:\n",
|
||||
" print(xx.group())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "colored-nothing",
|
||||
|
@ -55,13 +87,42 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 40,
|
||||
"id": "documented-hacker",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import re\n",
|
||||
"def find_tags(text):\n",
|
||||
" return []"
|
||||
" pos = []\n",
|
||||
" regexp = r'(<([a-zA-Z])>)|(</([a-zA-Z])>)'\n",
|
||||
" pattern = re.compile(regexp)\n",
|
||||
" tags = pattern.finditer(text)\n",
|
||||
" for tag in tags:\n",
|
||||
" pos.append(tag.span())\n",
|
||||
" return pos"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 41,
|
||||
"id": "52a23469-3283-48df-ba49-4d23ba0d6088",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[(5, 8), (29, 33)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 41,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"string = \"aaafo<r>m1aaaahform2uadaiudfo</r>m3oihdhdform2oahdoihwfform2oiadoafform11\"\n",
|
||||
"find_tags(string)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
@ -80,6 +141,8 @@
|
|||
"outputs": [],
|
||||
"source": [
|
||||
"def is_translatable(text):\n",
|
||||
" # 4.2.1\n",
|
||||
" # \n",
|
||||
" return True"
|
||||
]
|
||||
},
|
||||
|
@ -99,6 +162,11 @@
|
|||
"outputs": [],
|
||||
"source": [
|
||||
"def find_dates(text):\n",
|
||||
" #YYYY-MM-DD\n",
|
||||
" #DD-MM-YYYY\n",
|
||||
" #\n",
|
||||
" #\n",
|
||||
" #\n",
|
||||
" return []"
|
||||
]
|
||||
},
|
||||
|
@ -190,7 +258,7 @@
|
|||
"author": "Rafał Jaworski",
|
||||
"email": "rjawor@amu.edu.pl",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
|
@ -205,7 +273,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.10"
|
||||
"version": "3.9.2"
|
||||
},
|
||||
"subtitle": "6,7. Preprocessing i postprocessing",
|
||||
"title": "Komputerowe wspomaganie tłumaczenia",
|
||||
|
|
|
@ -190,15 +190,12 @@
|
|||
"metadata": {
|
||||
"author": "Rafał Jaworski",
|
||||
"email": "rjawor@amu.edu.pl",
|
||||
"lang": "pl",
|
||||
"subtitle": "8. Wykorzystanie tłumaczenia automatycznego we wspomaganiu tłumaczenia",
|
||||
"title": "Komputerowe wspomaganie tłumaczenia",
|
||||
"year": "2021",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"lang": "pl",
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
|
@ -209,8 +206,11 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.10"
|
||||
}
|
||||
"version": "3.9.2"
|
||||
},
|
||||
"subtitle": "8. Wykorzystanie tłumaczenia automatycznego we wspomaganiu tłumaczenia",
|
||||
"title": "Komputerowe wspomaganie tłumaczenia",
|
||||
"year": "2021"
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
|
|
|
@ -237,15 +237,12 @@
|
|||
"metadata": {
|
||||
"author": "Rafał Jaworski",
|
||||
"email": "rjawor@amu.edu.pl",
|
||||
"lang": "pl",
|
||||
"subtitle": "9,10. Web scraping",
|
||||
"title": "Komputerowe wspomaganie tłumaczenia",
|
||||
"year": "2021",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"lang": "pl",
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
|
@ -256,8 +253,11 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.10"
|
||||
}
|
||||
"version": "3.9.2"
|
||||
},
|
||||
"subtitle": "9,10. Web scraping",
|
||||
"title": "Komputerowe wspomaganie tłumaczenia",
|
||||
"year": "2021"
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
|
|
|
@ -155,7 +155,7 @@
|
|||
"author": "Rafał Jaworski",
|
||||
"email": "rjawor@amu.edu.pl",
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
|
@ -170,7 +170,7 @@
|
|||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.10"
|
||||
"version": "3.9.2"
|
||||
},
|
||||
"subtitle": "15. Korekta gramatyczna",
|
||||
"title": "Komputerowe wspomaganie tłumaczenia",
|
||||
|
|
Loading…
Reference in New Issue