{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e8b09e8e-7ffb-4fb8-86ee-16b1f2bf0f80",
   "metadata": {},
   "source": [
    "# Difference between feature 'word' and 'unicode'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a22bdfd-2f51-4383-b2a9-a78818e969ae",
   "metadata": {},
   "source": [
    "The following small script shows the differences between feature 'word' and 'unicode'."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "93a208bc-058f-45ae-81cf-2371e9158f4f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Following variables should contain the relative path and name of the two files to compare\n",
    "WordFile=\"../tf/0.4/word.tf\"\n",
    "UnicodeFile=\"../tf/0.4/unicode.tf\"\n",
    "# How many difference to show\n",
    "NumberExamples = 10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b1005f2a-dd1c-45a0-ab4c-6282b9486a5a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Comparing file  ../tf/0.4/word.tf  with  ../tf/0.4/unicode.tf \n",
      "\n",
      "Result:\n",
      "\n",
      "Line 28 differs:\n",
      "File ../tf/0.4/word.tf: Ἀβραάμ\n",
      "File ../tf/0.4/unicode.tf: Ἀβραάμ.\n",
      "\n",
      "Line 32 differs:\n",
      "File ../tf/0.4/word.tf: Ἰσαάκ\n",
      "File ../tf/0.4/unicode.tf: Ἰσαάκ,\n",
      "\n",
      "Line 37 differs:\n",
      "File ../tf/0.4/word.tf: Ἰακώβ\n",
      "File ../tf/0.4/unicode.tf: Ἰακώβ,\n",
      "\n",
      "Line 46 differs:\n",
      "File ../tf/0.4/word.tf: αὐτοῦ\n",
      "File ../tf/0.4/unicode.tf: αὐτοῦ,\n",
      "\n",
      "Line 57 differs:\n",
      "File ../tf/0.4/word.tf: Θάμαρ\n",
      "File ../tf/0.4/unicode.tf: Θάμαρ,\n",
      "\n",
      "Line 62 differs:\n",
      "File ../tf/0.4/word.tf: Ἐσρώμ\n",
      "File ../tf/0.4/unicode.tf: Ἐσρώμ,\n",
      "\n",
      "Line 67 differs:\n",
      "File ../tf/0.4/word.tf: Ἀράμ\n",
      "File ../tf/0.4/unicode.tf: Ἀράμ,\n",
      "\n",
      "Line 72 differs:\n",
      "File ../tf/0.4/word.tf: Ἀμιναδάβ\n",
      "File ../tf/0.4/unicode.tf: Ἀμιναδάβ,\n",
      "\n",
      "Line 77 differs:\n",
      "File ../tf/0.4/word.tf: Ναασσών\n",
      "File ../tf/0.4/unicode.tf: Ναασσών,\n",
      "\n",
      "Line 82 differs:\n",
      "File ../tf/0.4/word.tf: Σαλμών\n",
      "File ../tf/0.4/unicode.tf: Σαλμών,\n",
      "\n",
      "Stoped comparing after  10 differences\n",
      "Finished.\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "\n",
    "def compare_files(file1_path, file2_path):\n",
    "    FoundDifferences=0\n",
    "    with open(file1_path, 'r', encoding='utf-8') as file1, open(file2_path, 'r',encoding='utf-8') as file2:\n",
    "        lines_file1 = file1.readlines()\n",
    "        lines_file2 = file2.readlines()\n",
    "\n",
    "        # Check the number of lines in both files\n",
    "        if len(lines_file1) != len(lines_file2):\n",
    "            print(\"Files have different numbers of lines.\")\n",
    "            return\n",
    "\n",
    "        # Compare content line by line\n",
    "        for line_num, (line1, line2) in enumerate(zip(lines_file1, lines_file2)):\n",
    "            line1 = line1.strip()\n",
    "            line2 = line2.strip()\n",
    "\n",
    "            # Compare the lines and print any differences\n",
    "            if line1 != line2:\n",
    "                \n",
    "                if line1.startswith(\"@\"):\n",
    "                    continue  # Skip lines that start with \"@\"\n",
    "                if line1.startswith(\"\\n\"):\n",
    "                    continue  # Skip lines that start with \" \"\n",
    "                \n",
    "                print(f\"Line {line_num + 1} differs:\")\n",
    "                print(f\"File {file1_path}: {line1}\")\n",
    "                print(f\"File {file2_path}: {line2}\")\n",
    "                print()\n",
    "                FoundDifferences+=1\n",
    "            if FoundDifferences==NumberExamples: \n",
    "                print ('Stoped comparing after ', FoundDifferences,'differences')\n",
    "                break\n",
    "\n",
    "        # If no differences found, print a message\n",
    "        print(\"Finished.\")\n",
    "\n",
    "# main part\n",
    "#First check if the file exist, then check its content\n",
    "if os.path.exists(WordFile):\n",
    "    if os.path.exists(UnicodeFile):\n",
    "        print (\"Comparing file \",WordFile,\" with \",UnicodeFile,\"\\n\\nResult:\\n\\n\",end=\"\")  \n",
    "        compare_files(WordFile, UnicodeFile)\n",
    "    else:\n",
    "        print (f\"Could not find file {UnicodeFile}.\")\n",
    "else:\n",
    "    print(f\"Could not find file {WordFile}.\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d2322619-d269-4297-8152-187abecaf376",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}