finished 6-7

lab/lab_06-07.ipynb

@@ -55,7 +55,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 91,
    "id": "documented-hacker",
    "metadata": {},
    "outputs": [
@@ -70,7 +70,7 @@
        " {'</root>': (36, 43)}]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 91,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -100,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 92,
    "id": "unauthorized-study",
    "metadata": {},
    "outputs": [
@@ -164,7 +164,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 93,
    "id": "beautiful-mathematics",
    "metadata": {},
    "outputs": [
@@ -218,7 +218,7 @@
        "  'year': 24}]"
       ]
      },
-     "execution_count": 77,
+     "execution_count": 93,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -289,7 +289,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 94,
    "id": "4ee148d5",
    "metadata": {},
    "outputs": [
@@ -429,13 +429,63 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 153,
    "id": "romance-judge",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'<greeting>Witaj </greeting><name>Ania! </name></name></name></name></name>John </name>'"
+      ]
+     },
+     "execution_count": 153,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
+    "import re\n",
+    "\n",
+    "def split_text(text):\n",
+    "    parts = re.split(r'(<\\w+>|<\\/\\w+>| )', text)\n",
+    "    \n",
+    "    split_list = []\n",
+    "    \n",
+    "    for part in parts:\n",
+    "        if part.strip():  \n",
+    "            split_list.append((part, part.startswith(\"<\") and part.endswith(\">\")))\n",
+    "    \n",
+    "    return split_list\n",
+    "\n",
     "def transfer_tags(source_segment, target_segment):\n",
-    "    return ''"
+    "    source_interation_index = 0\n",
+    "\n",
+    "    split_source_segment = split_text(source_segment)\n",
+    "\n",
+    "    target_text_with_tags = ''\n",
+    "\n",
+    "    for text in target_segment.split():\n",
+    "        source_element  = split_source_segment[source_interation_index]\n",
+    "        \n",
+    "        while(source_element[1]):\n",
+    "            target_text_with_tags += source_element[0]\n",
+    "            source_interation_index = source_interation_index + 1\n",
+    "            source_element  = split_source_segment[source_interation_index]\n",
+    "\n",
+    "        target_text_with_tags +=  text + ' '\n",
+    "        source_interation_index = source_interation_index + 1\n",
+    "\n",
+    "    for index in range(source_interation_index, len(split_source_segment)):\n",
+    "        target_text_with_tags += split_source_segment[index][0]\n",
+    "\n",
+    "    return target_text_with_tags\n",
+    "\n",
+    "\n",
+    "source_segment = \"<greeting>Hello</greeting> <name>Ania!</name></name></name></name></name>John</name>\"\n",
+    "target_segment = \"Witaj Ania! John\"\n",
+    "\n",
+    "transfer_tags(source_segment,target_segment)\n"
    ]
   }
  ],