{ "cells": [ { "cell_type": "markdown", "id": "49e4da57", "metadata": {}, "source": [ "# String Comparison" ] }, { "cell_type": "code", "execution_count": null, "id": "81558057", "metadata": {}, "outputs": [], "source": [ "import sys\n", "from pathlib import Path\n", "\n", "# Find project root by looking for _config.yml\n", "current = Path.cwd()\n", "for parent in [current, *current.parents]:\n", " if (parent / '_config.yml').exists():\n", " project_root = parent\n", " break\n", "else:\n", " project_root = Path.cwd().parent.parent\n", "\n", "# Add project root to path\n", "sys.path.insert(0, str(project_root))\n", "\n", "# Import shared teaching helpers and cell magics\n", "from shared import thinkpython, diagram, jupyturtle, structshape\n", "from shared.download import download\n" ] }, { "cell_type": "markdown", "id": "2fa1d3e8", "metadata": {}, "source": [ "Observe the following operations." ] }, { "cell_type": "code", "execution_count": 69, "id": "fb653441", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "True\n", "True\n", "False\n", "False\n" ] } ], "source": [ "### check out the comparisons here:\n", "\n", "print(\"A\" < 'a')\n", "print(\"a\" < 'banana')\n", "print('Pineapple' > 'pineapple')\n", "print('Pineapple' > 'banana')" ] }, { "cell_type": "markdown", "id": "a7fae2a8", "metadata": {}, "source": [ "The relational operators work on strings as seen above. String comparisons are based on the ASCII code table (this one is easier to read than the one presented in an earlier chapter). As you can see in the table below, each character has a decimal number that string comparison uses to compare strings. Note that:\n", "\n", "- `0` is `48`\n", "- `A` is `65`\n", "- `a` is `97`" ] }, { "cell_type": "markdown", "id": "8547eec2", "metadata": {}, "source": [ "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
DecChrDecChrDecChrDecChrDecChr
0NUL26SUB52478N104h
1SOH27ESC53579O105i
2STX28FS54680P106j
3ETX29GS55781Q107k
4EOT30RS56882R108l
5ENQ31US57983S109m
6ACK3258:84T110n
7BEL33!59;85U111o
8BS34\"60<86V112p
9HT35#61=87W113q
10LF36$62>88X114r
11VT37%63?89Y115s
12FF38&64@90Z116t
13CR39'65A91[117u
14SO40(66B92\\118v
15SI41)67C93]119w
16DLE42*68D94^120x
17DC143+69E95_121y
18DC244,70F96`122z
19DC345-71G97a123{
20DC446.72H98b124|
21NAK47/73I99c125}
22SYN48074J100d126~
23ETB49175K101e127DEL
24CAN50276L102f
25EM51377M103g
" ] }, { "cell_type": "markdown", "id": "0a2cd659", "metadata": {}, "source": [ "So we can use the ASCII code table to compare strings." ] }, { "cell_type": "code", "execution_count": 70, "id": "b754d462", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "All right, banana.\n" ] } ], "source": [ "word = 'banana'\n", "\n", "if word == 'banana':\n", " print('All right, banana.')" ] }, { "cell_type": "markdown", "id": "e9be6097", "metadata": {}, "source": [ "Other relational operations are useful for putting words in alphabetical\n", "order:" ] }, { "cell_type": "code", "execution_count": 71, "id": "44374eb8", "metadata": {}, "outputs": [], "source": [ "def compare_word(word):\n", " if word < 'banana':\n", " print(word, 'comes before banana.')\n", " elif word > 'banana':\n", " print(word, 'comes after banana.')\n", " else:\n", " print('All right, banana.')" ] }, { "cell_type": "code", "execution_count": 72, "id": "a46f7035", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "apple comes before banana.\n" ] } ], "source": [ "compare_word('apple')" ] }, { "cell_type": "markdown", "id": "b66f449a", "metadata": {}, "source": [ "Python does not handle uppercase and lowercase letters the same way\n", "people do. All the uppercase letters come before all the lowercase\n", "letters, so:" ] }, { "cell_type": "code", "execution_count": 73, "id": "a691f9e2", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Pineapple comes before banana.\n" ] } ], "source": [ "compare_word('Pineapple')" ] }, { "cell_type": "markdown", "id": "f9b916c9", "metadata": {}, "source": [ "This can be problematic sometimes. To solve this problem, we can convert strings to a standard format, such as all lowercase or all uppercase, before performing the comparison. " ] }, { "cell_type": "code", "execution_count": 74, "id": "d4355b93", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "pineapple comes after banana.\n" ] } ], "source": [ "compare_word('Pineapple'.lower())" ] }, { "cell_type": "code", "execution_count": 75, "id": "27ca1148", "metadata": { "tags": [ "thebe-interactive" ] }, "outputs": [], "source": [ "### EXERCISE: String Comparison\n", "# Difficulty: Challenge\n", "words = ['Apple', 'apple', 'banana', 'Banana', 'cherry']\n", "# 1. Print the list sorted as-is\n", "# 2. Print the list sorted case-insensitively\n", "# 3. Build and print a list of tuples: (word, word.casefold())\n", "# 4. Print whether \"Apple\" and \"apple\" are equal under casefold\n", "### Your code starts here:\n", "\n", "\n", "### Your code ends here." ] }, { "cell_type": "code", "execution_count": 76, "id": "7af7b824", "metadata": { "tags": [ "hide-input" ] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['Apple', 'Banana', 'apple', 'banana', 'cherry']\n", "['Apple', 'apple', 'banana', 'Banana', 'cherry']\n", "[('Apple', 'apple'), ('apple', 'apple'), ('banana', 'banana'), ('Banana', 'banana'), ('cherry', 'cherry')]\n", "True\n" ] } ], "source": [ "# Solution\n", "words = ['Apple', 'apple', 'banana', 'Banana', 'cherry']\n", "print(sorted(words))\n", "print(sorted(words, key=str.casefold))\n", "pairs = [(w, w.casefold()) for w in words]\n", "print(pairs)\n", "print('Apple'.casefold() == 'apple'.casefold())" ] } ], "metadata": { "celltoolbar": "Tags", "kernelspec": { "display_name": ".venv (3.13.7)", "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": "3.13.7" } }, "nbformat": 4, "nbformat_minor": 5 }