lab 2

lab/lab_06-07.ipynb

@@ -60,8 +60,35 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def find_tags(text):\n",
-    "    return []"
+    "import re\n",
+    "\n",
+    "def find_tags(string):\n",
+    "    pattern = r'<[^>]+>'\n",
+    "    matches = re.finditer(pattern, string)\n",
+    "    tag_indexes = [(match.start(), match.end()) for match in matches]\n",
+    "    return tag_indexes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "3dc08368",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['<tag1>', '</tag1>', '<tag2>', '</tag2>']"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "string = \"<tag1>ADIOS</tag1><tag2>OLA</tag2>\"\n",
+    "[ string[out[0]:out[1]] for out in find_tags(string)]"
    ]
   },
   {
@@ -74,13 +101,73 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 20,
    "id": "unauthorized-study",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "False\n",
+      "False\n",
+      "False\n",
+      "True\n"
+     ]
+    }
+   ],
    "source": [
+    "import re\n",
+    "import string\n",
+    "\n",
     "def is_translatable(text):\n",
-    "    return True"
+    "    return bool(re.match(r'^[^0-9IVXLCDM\\s' + re.escape(string.punctuation) + ']+$', text))\n",
+    "\n",
+    "text1 = \"This is a sample text.\"\n",
+    "text2 = \"2024.\"\n",
+    "text3 = \"Это пример текста.\"\n",
+    "text4 = \"おはよう\"\n",
+    "\n",
+    "print(is_translatable(text1)) \n",
+    "print(is_translatable(text2))\n",
+    "print(is_translatable(text3))\n",
+    "print(is_translatable(text4))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "ae92a18c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\"This is a sample text.\" is translatable?\n",
+      "Yes\n",
+      "\"2024.\" is translatable?\n",
+      "No\n",
+      "\"Это пример текста.\" is translatable?\n",
+      "Yes\n",
+      "\"おはよう\" is translatable?\n",
+      "Yes\n"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "import string\n",
+    "\n",
+    "def is_translatable(text):\n",
+    "    return bool(re.match(r'^[^\\d]+$|^\\s+$', text))\n",
+    "\n",
+    "examples = [\"This is a sample text.\", \"2024.\", \n",
+    "            \"Это пример текста.\", \"おはよう\"]\n",
+    "\n",
+    "for ex in examples:\n",
+    "    response = 'Yes' if is_translatable(ex) else 'No'\n",
+    "    print(f'\"{ex}\" is translatable?\\n{response}')"
    ]
   },
   {
@@ -93,13 +180,74 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 44,
    "id": "beautiful-mathematics",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "('03/25/2022', 3, 25, 2022)\tday:\t3\tmonth:\t25\tyear:\t2022\n",
+      "('25-12-2023', 25, 12, 2023)\tday:\t25\tmonth:\t12\tyear:\t2023\n",
+      "('09/30/2025', 9, 30, 2025)\tday:\t9\tmonth:\t30\tyear:\t2025\n",
+      "('03/25/2022', 25, 3, 2022)\tday:\t25\tmonth:\t3\tyear:\t2022\n",
+      "('09/30/2025', 30, 9, 2025)\tday:\t30\tmonth:\t9\tyear:\t2025\n",
+      "('12 March 2024', 12, 3, 2024)\tday:\t12\tmonth:\t3\tyear:\t2024\n",
+      "('25-12-2023', 25, 12, 2023)\tday:\t25\tmonth:\t12\tyear:\t2023\n",
+      "('12 March 2024', 12, 3, 2024)\tday:\t12\tmonth:\t3\tyear:\t2024\n",
+      "('15 September, 2026', 15, 9, 2026)\tday:\t15\tmonth:\t9\tyear:\t2026\n"
+     ]
+    }
+   ],
    "source": [
+    "import re\n",
+    "\n",
     "def find_dates(text):\n",
-    "    return []"
+    "    date_formats = [\n",
+    "        (r'(\\d{1,2})[-/](\\d{1,2})[-/](\\d{2,4})', 'day_first'),\n",
+    "        (r'(\\d{1,2})[/](\\d{1,2})[/](\\d{2,4})', 'month_first'),\n",
+    "        (r'(\\d{1,2}) (\\w{3,9}) (\\d{4})', 'day_first'),\n",
+    "        (r'(\\d{1,2})-(\\d{1,2})-(\\d{2,4})', 'day_first'),\n",
+    "        (r'(\\d{1,2}) (\\w{3,9}),? (\\d{4})', 'day_first')\n",
+    "    ]\n",
+    "\n",
+    "    months = {\n",
+    "        'January': 1, 'February': 2, 'March': 3, 'April': 4, 'May': 5, 'June': 6,\n",
+    "        'July': 7, 'August': 8, 'September': 9, 'October': 10, 'November': 11, 'December': 12\n",
+    "    }\n",
+    "\n",
+    "    dates_found = []\n",
+    "    for date_pattern, format_type in date_formats:\n",
+    "        matches = re.finditer(date_pattern, text)\n",
+    "        for match in matches:\n",
+    "            groups = match.groups()\n",
+    "            if len(groups) == 3:\n",
+    "                if format_type == 'day_first':\n",
+    "                    day, month, year = groups\n",
+    "                else:\n",
+    "                    month, day, year = groups\n",
+    "                if month.isdigit():\n",
+    "                    month = int(month)\n",
+    "                else:\n",
+    "                    month = months[month]\n",
+    "                dates_found.append((match.group(), int(day), month, int(year)))\n",
+    "            elif len(groups) == 4:\n",
+    "                if format_type == 'day_first':\n",
+    "                    day, month, _, year = groups\n",
+    "                else:\n",
+    "                    month, day, _, year = groups\n",
+    "                if month.isdigit():\n",
+    "                    month = int(month)\n",
+    "                else:\n",
+    "                    month = months[month]\n",
+    "                dates_found.append((match.group(), int(day), month, int(year)))\n",
+    "    return dates_found\n",
+    "\n",
+    "text = \"Here are some dates: 03/25/2022, 25-12-2023, 12 March 2024, 09/30/2025, 15 September, 2026\"\n",
+    "dates = find_dates(text)\n",
+    "for date in dates:\n",
+    "    print(f\"{date}\\tday:\\t{date[1]}\\tmonth:\\t{date[2]}\\tyear:\\t{date[3]}\")"
    ]
   },
   {
@@ -205,7 +353,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.11.0"
   },
   "subtitle": "6,7. Preprocessing i postprocessing",
   "title": "Komputerowe wspomaganie tłumaczenia",