Merge branch 'master' into feature/apriori-association-rules

Author: simoderyouch

.pre-commit-config.yaml

@@ -16,7 +16,7 @@ repos:
       - id: auto-walrus
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.13.0
+    rev: v0.13.1
     hooks:
       - id: ruff-check
       - id: ruff-format
@@ -47,7 +47,7 @@ repos:
       - id: validate-pyproject
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.18.1
+    rev: v1.18.2
     hooks:
       - id: mypy
         args:

data_structures/arrays/sudoku_solver.py

@@ -11,6 +11,19 @@
 def cross(items_a, items_b):
     """
     Cross product of elements in A and elements in B.
+
+    >>> cross('AB', '12')
+    ['A1', 'A2', 'B1', 'B2']
+    >>> cross('ABC', '123')
+    ['A1', 'A2', 'A3', 'B1', 'B2', 'B3', 'C1', 'C2', 'C3']
+    >>> cross('ABC', '1234')
+    ['A1', 'A2', 'A3', 'A4', 'B1', 'B2', 'B3', 'B4', 'C1', 'C2', 'C3', 'C4']
+    >>> cross('', '12')
+    []
+    >>> cross('A', '')
+    []
+    >>> cross('', '')
+    []
     """
     return [a + b for a in items_a for b in items_b]
 

strings/edit_distance.py

@@ -14,6 +14,20 @@ def edit_distance(source: str, target: str) -> int:
 
     >>> edit_distance("GATTIC", "GALTIC")
     1
+    >>> edit_distance("NUM3", "HUM2")
+    2
+    >>> edit_distance("cap", "CAP")
+    3
+    >>> edit_distance("Cat", "")
+    3
+    >>> edit_distance("cat", "cat")
+    0
+    >>> edit_distance("", "123456789")
+    9
+    >>> edit_distance("Be@uty", "Beautyyyy!")
+    5
+    >>> edit_distance("lstring", "lsstring")
+    1
     """
     if len(source) == 0:
         return len(target)

web_programming/covid_stats_via_xpath.py

@@ -1,7 +1,8 @@
 """
-This is to show simple COVID19 info fetching from worldometers archive site using lxml
-* The main motivation to use lxml in place of bs4 is that it is faster and therefore
-more convenient to use in Python web projects (e.g. Django or Flask-based)
+This script demonstrates fetching simple COVID-19 statistics from the
+Worldometers archive site using lxml. lxml is chosen over BeautifulSoup
+for its speed and convenience in Python web projects (such as Django or
+Flask).
 """
 
 # /// script
@@ -25,15 +26,34 @@ class CovidData(NamedTuple):
 
 
 def covid_stats(
-    url: str = "https://web.archive.org/web/20250825095350/https://www.worldometers.info/coronavirus/",
+    url: str = (
+        "https://web.archive.org/web/20250825095350/"
+        "https://www.worldometers.info/coronavirus/"
+    ),
 ) -> CovidData:
     xpath_str = '//div[@class = "maincounter-number"]/span/text()'
-    return CovidData(
-        *html.fromstring(httpx.get(url, timeout=10).content).xpath(xpath_str)
+    try:
+        response = httpx.get(url, timeout=10).raise_for_status()
+    except httpx.TimeoutException:
+        print(
+            "Request timed out. Please check your network connection "
+            "or try again later."
+        )
+        return CovidData("N/A", "N/A", "N/A")
+    except httpx.HTTPStatusError as e:
+        print(f"HTTP error occurred: {e}")
+        return CovidData("N/A", "N/A", "N/A")
+    data = html.fromstring(response.content).xpath(xpath_str)
+    if len(data) != 3:
+        print("Unexpected data format. The page structure may have changed.")
+        data = "N/A", "N/A", "N/A"
+    return CovidData(*data)
+
+
+if __name__ == "__main__":
+    fmt = (
+        "Total COVID-19 cases in the world: {}\n"
+        "Total deaths due to COVID-19 in the world: {}\n"
+        "Total COVID-19 patients recovered in the world: {}"
     )
-
-
-fmt = """Total COVID-19 cases in the world: {}
-Total deaths due to COVID-19 in the world: {}
-Total COVID-19 patients recovered in the world: {}"""
-print(fmt.format(*covid_stats()))
+    print(fmt.format(*covid_stats()))