
Om je vaardigheden met groeperingen en kwantoren in reguliere expressies te versterken, schrijf je nu een functie om datums uit tekst te extraheren. Het doel is om datums te herkennen in de formaten **"YYYY-MM-DD"** (zoals `2024-06-15`) en **"DD/MM/YYYY"** (zoals `15/06/2024`). Je functie moet een string scannen en alle overeenkomende datums in een lijst retourneren. Deze oefening helpt je om te oefenen met **groepen**, **kwantoren** en **alternatie** om meerdere datumformaten betrouwbaar te matchen.


import unittest
import user_code
import ast
import re   
import unittest
import importlib
import io
from contextlib import redirect_stdout

class TestTask(unittest.TestCase):
    def test_example_output(self):
        import user_code

        importlib.reload(user_code)
        text = "The events are on 2024-06-15 and 15/06/2024."
        result = user_code.extract_dates(text)
        expected = ["2024-06-15", "15/06/2024"]
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Function returns correct list for mixed formats.",
            f"Expected {expected}, got {result}",
        )

    def test_multiple_dates(self):
        import user_code
        importlib.reload(user_code)
        text = "Dates: 2022-01-01, 31/12/2023, and 2020-05-10."
        result = user_code.extract_dates(text)
        expected = ["2022-01-01", "31/12/2023", "2020-05-10"]
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Function finds multiple dates in both formats.",
            f"Expected {expected}, got {result}",
        )

    def test_no_dates(self):
        import user_code
        importlib.reload(user_code)
        text = "There are no dates here."
        result = user_code.extract_dates(text)
        expected = []
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Function returns empty list when no dates present.",
            f"Expected {expected}, got {result}",
        )

    # def test_edge_cases(self):
    #     import user_code
    #     importlib.reload(user_code)
    #     text = "Start:2021-12-31End:01/01/2022More:2022-02-02!"
    #     result = user_code.extract_dates(text)
    #     expected = ["2021-12-31", "01/01/2022", "2022-02-02"]
    #     _dynamic_test(
    #         self,
    #         isinstance(result, list) and result == expected,
    #         "Function finds dates at string edges and with punctuation.",
    #         f"Expected {expected}, got {result}",
    #    )

    def test_invalid_dates(self):
        import user_code
        importlib.reload(user_code)
        text = "These are not dates: 2024-6-15, 5/6/2024, 20240615, 15-06-2024."
        result = user_code.extract_dates(text)
        expected = []
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Function does not match invalid date formats.",
            f"Expected {expected}, got {result}",
        )

    def test_overlapping_dates(self):
        import user_code
        importlib.reload(user_code)
        text = "2023-12-24/2023-12-25 and 24/12/2023/25/12/2023"
        result = user_code.extract_dates(text)
        expected = ["2023-12-24", "2023-12-25", "24/12/2023", "25/12/2023"]
        _dynamic_test(
            self,
            isinstance(result, list) and result == expected,
            "Function finds adjacent and overlapping dates.",
            f"Expected {expected}, got {result}",
        )

def _dynamic_test(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
        test_case.assertTrue(True, success_message)
    else:
        test_case._testMethodName = failure_message
        test_case.fail(failure_message)

def normalize_text(text):
    text = text.lower()
    text = re.sub(r"\s{2,}", " ", text)
    text = re.sub(r"\s*([,:?])\s*", r"\1 ", text)
    return text.strip()

def change_var(code: str, var_name: str, value: str) -> str:
    tree = ast.parse(code)
    lines = code.splitlines()
    for i, node in enumerate(tree.body):
        if isinstance(node, ast.Assign):
            for target in node.targets:
                if isinstance(target, ast.Name) and target.id == var_name:
                    start_line = node.lineno - 1
                    line = lines[start_line]
                    indent = ' ' * (len(line) - len(line.lstrip()))
                    lines[start_line] = f"{indent}{var_name} = {value}"
                    next_line = len(lines)
                    for next_node in tree.body[i+1:]:
                        if hasattr(next_node, 'lineno'):
                            next_line = next_node.lineno - 1
                            break
                    if next_line > start_line + 1:
                        lines[start_line+1:next_line] = []
                    
                    return '\\n'.join(lines)
    return code

if __name__ == "__main__":
    unittest.main()


test_main.py

Een uitgebreide cursus over Python-regular expressions, ontworpen voor cursisten met basiskennis van Python. Deze cursus behandelt regex-syntaxis, patroonherkenning, geavanceerde functies en praktische toepassingen via theorie en praktische opdrachten.

Leer de basisprincipes van reguliere expressies in Python, inclusief de basis-syntaxis, patroonherkenning en essentiële regex-functies.

Verdiep je verder in regex met groepering, kwantoren, ankers en substitutietechnieken.

Beheers geavanceerde regex-functies zoals lookahead/lookbehind, niet-gretige overeenkomsten, en pas regex toe op tekstverwerkingsproblemen uit de praktijk.

Uitdaging: Data Extraheren in Verschillende Formaten

Uitdaging: Data Extraheren in Verschillende Formaten

Oplossing