XPath Functions: Complete Reference with Examples

<catalog>
    <book id="b001" category="fiction">
        <title>The Hobbit</title>
        <author>J.R.R. Tolkien</author>
        <price currency="USD">12.99</price>
        <rating>4.8</rating>
        <pubdate>1937-09-21</pubdate>
    </book>
    <book id="b002" category="fiction">
        <title>The Fellowship of the Ring</title>
        <author>J.R.R. Tolkien</author>
        <price currency="USD">14.99</price>
        <rating>4.9</rating>
        <pubdate>1954-07-29</pubdate>
    </book>
    <book id="b003" category="non-fiction">
        <title>A Brief History of Time</title>
        <author>Stephen Hawking</author>
        <price currency="GBP">9.99</price>
        <rating>4.5</rating>
        <pubdate>1988-03-01</pubdate>
    </book>
</catalog>

import xml.etree.ElementTree as ET

def run_xpath_functions_demo():
    """Demonstrate XPath string functions using Python."""
    xml_str = """<catalog>
        <book id="b001"><title>The Hobbit</title><author>J.R.R. Tolkien</author></book>
        <book id="b002"><title>The Fellowship of the Ring</title><author>J.R.R. Tolkien</author></book>
    </catalog>"""
    
    root = ET.fromstring(xml_str)
    
    # Simulate XPath functions
    titles = [b.find('title').text for b in root.findall('book')]
    authors = [b.find('author').text for b in root.findall('book')]
    
    print(f"concat: {titles[0]} by {authors[0]}")
    print(f"substring(,5,5): {titles[0][4:9]}")
    print(f"contains('Hobbit'): {'Hobbit' in titles[0]}")
    print(f"string-join: {', '.join(authors)}")
    print(f"string-length: {len(titles[0])}")
    print(f"translate: {titles[0].translate(str.maketrans({'o':'O','b':'B'}))}")

run_xpath_functions_demo()

def number_functions_demo():
    """Demonstrate XPath number functions."""
    prices = [12.99, 14.99, 9.99]
    
    # Simulate XPath number functions
    print(f"sum: {sum(prices)}")
    print(f"avg: {sum(prices)/len(prices):.4f}")
    print(f"min: {min(prices)}")
    print(f"max: {max(prices)}")
    print(f"count: {len(prices)}")
    print(f"ceiling(12.99): {__import__('math').ceil(12.99)}")
    print(f"floor(12.99): {__import__('math').floor(12.99)}")
    print(f"round(12.49): {round(12.49)}")
    print(f"round(12.50): {round(12.50)}")

number_functions_demo()

from datetime import date, datetime

def date_functions_demo():
    """Demonstrate XPath date functions."""
    today = date(2026, 6, 20)
    pubdate = date(1937, 9, 21)
    
    print(f"current-date: {today}")
    print(f"year-from-date: {pubdate.year}")
    print(f"month-from-date: {pubdate.month}")
    print(f"day-from-date: {pubdate.day}")
    print(f"format-date([D] [MNn], [Y]): {pubdate.strftime('%d %B, %Y')}")
    print(f"days-difference: {(today - pubdate).days}")

date_functions_demo()

from lxml import etree

def run_xpath(xml_content, xpath_expr):
    """Evaluate an XPath expression and print the result."""
    root = etree.fromstring(xml_content)
    result = root.xpath(xpath_expr)
    
    print(f"XPath: {xpath_expr}")
    print(f"Result: {result}")
    print()

xml = """<catalog>
    <book id="b001" category="fiction">
        <title>The Hobbit</title>
        <author>J.R.R. Tolkien</author>
        <price>12.99</price>
        <rating>4.8</rating>
    </book>
    <book id="b002" category="fiction">
        <title>The Fellowship of the Ring</title>
        <author>J.R.R. Tolkien</author>
        <price>14.99</price>
        <rating>4.9</rating>
    </book>
    <book id="b003" category="non-fiction">
        <title>A Brief History of Time</title>
        <author>Stephen Hawking</author>
        <price>9.99</price>
        <rating>4.5</rating>
    </book>
</catalog>"""

# Test all function categories
run_xpath(xml, "string-join(//book/title, ' | ')")
run_xpath(xml, "sum(//book/price)")
run_xpath(xml, "round(avg(//book/rating) * 10) div 10")
run_xpath(xml, "count(//book[@category='fiction'])")
run_xpath(xml, "distinct-values(//book/author)")
run_xpath(xml, "//book[rating = max(//book/rating)]/title")
run_xpath(xml, "//book[starts-with(author, 'J.')]/title")

def xpath_query_tool():
    """Interactive XPath query tool."""
    from lxml import etree
    
    xml_content = """<catalog>
      <book cat="fiction"><title>The Hobbit</title><price>12.99</price></book>
      <book cat="fiction"><title>1984</title><price>10.99</price></book>
      <book cat="non-fiction"><title>Sapiens</title><price>15.99</price></book>
    </catalog>"""
    
    root = etree.fromstring(xml_content)
    
    queries = [
        "count(//book)",
        "string-join(//book/title, ', ')",
        "//book[price > 12]/title",
        "sum(//book/price)",
        "//book[not(title = '1984')]/title",
        "distinct-values(//book/@cat)",
    ]
    
    for q in queries:
        try:
            result = root.xpath(q)
            print(f"{'✓' if result else '∅'} {q}")
            print(f"   → {result}")
        except Exception as e:
            print(f"✗ {q}")
            print(f"   → Error: {e}")
        print()

xpath_query_tool()