ENH: add render_links for Styler.to_html formatting (#45058)

Author: attack68

doc/source/whatsnew/v1.4.0.rst

@@ -111,6 +111,7 @@ Additionally there are specific enhancements to the HTML specific rendering:
   - :meth:`.Styler.to_html` introduces keyword arguments ``sparse_index``, ``sparse_columns``, ``bold_headers``, ``caption``, ``max_rows`` and ``max_columns`` (:issue:`41946`, :issue:`43149`, :issue:`42972`).
   - :meth:`.Styler.to_html` omits CSSStyle rules for hidden table elements as a performance enhancement (:issue:`43619`)
   - Custom CSS classes can now be directly specified without string replacement (:issue:`43686`)
+  - Ability to render hyperlinks automatically via a new ``hyperlinks`` formatting keyword argument (:issue:`45058`)
 
 There are also some LaTeX specific enhancements:
 

pandas/io/formats/style.py

@@ -623,6 +623,7 @@ def to_latex(
                               | \\sisetup{detect-all = true}  *(within {document})*
         environment           \\usepackage{longtable} if arg is "longtable"
                               | or any other relevant environment package
+        hyperlinks            \\usepackage{hyperref}
         ===================== ==========================================================
 
         **Cell Styles**

pandas/io/formats/style_render.py

@@ -798,6 +798,7 @@ def format(
         decimal: str = ".",
         thousands: str | None = None,
         escape: str | None = None,
+        hyperlinks: str | None = None,
     ) -> StylerRenderer:
         r"""
         Format the text display value of cells.
@@ -842,6 +843,13 @@ def format(
 
             .. versionadded:: 1.3.0
 
+        hyperlinks : {"html", "latex"}, optional
+            Convert string patterns containing https://, http://, ftp:// or www. to
+            HTML <a> tags as clickable URL hyperlinks if "html", or LaTeX \href
+            commands if "latex".
+
+            .. versionadded:: 1.4.0
+
         Returns
         -------
         self : Styler
@@ -958,6 +966,7 @@ def format(
                 thousands is None,
                 na_rep is None,
                 escape is None,
+                hyperlinks is None,
             )
         ):
             self._display_funcs.clear()
@@ -980,6 +989,7 @@ def format(
                 decimal=decimal,
                 thousands=thousands,
                 escape=escape,
+                hyperlinks=hyperlinks,
             )
             for ri in ris:
                 self._display_funcs[(ri, ci)] = format_func
@@ -996,6 +1006,7 @@ def format_index(
         decimal: str = ".",
         thousands: str | None = None,
         escape: str | None = None,
+        hyperlinks: str | None = None,
     ) -> StylerRenderer:
         r"""
         Format the text display value of index labels or column headers.
@@ -1027,6 +1038,10 @@ def format_index(
             ``{``, ``}``, ``~``, ``^``, and ``\`` in the cell display string with
             LaTeX-safe sequences.
             Escaping is done before ``formatter``.
+        hyperlinks : {"html", "latex"}, optional
+            Convert string patterns containing https://, http://, ftp:// or www. to
+            HTML <a> tags as clickable URL hyperlinks if "html", or LaTeX \href
+            commands if "latex".
 
         Returns
         -------
@@ -1128,6 +1143,7 @@ def format_index(
                 thousands is None,
                 na_rep is None,
                 escape is None,
+                hyperlinks is None,
             )
         ):
             display_funcs_.clear()
@@ -1149,6 +1165,7 @@ def format_index(
                 decimal=decimal,
                 thousands=thousands,
                 escape=escape,
+                hyperlinks=hyperlinks,
             )
 
             for idx in [(i, lvl) if axis == 0 else (lvl, i) for i in range(len(obj))]:
@@ -1391,13 +1408,28 @@ def _str_escape(x, escape):
     return x
 
 
+def _render_href(x, format):
+    """uses regex to detect a common URL pattern and converts to href tag in format."""
+    if isinstance(x, str):
+        if format == "html":
+            href = '<a href="{0}" target="_blank">{0}</a>'
+        elif format == "latex":
+            href = r"\href{{{0}}}{{{0}}}"
+        else:
+            raise ValueError("``hyperlinks`` format can only be 'html' or 'latex'")
+        pat = r"(https?:\/\/|ftp:\/\/|www.)[\w/\-?=%.]+\.[\w/\-&?=%.]+"
+        return re.sub(pat, lambda m: href.format(m.group(0)), x)
+    return x
+
+
 def _maybe_wrap_formatter(
     formatter: BaseFormatter | None = None,
     na_rep: str | None = None,
     precision: int | None = None,
     decimal: str = ".",
     thousands: str | None = None,
     escape: str | None = None,
+    hyperlinks: str | None = None,
 ) -> Callable:
     """
     Allows formatters to be expressed as str, callable or None, where None returns
@@ -1431,11 +1463,17 @@ def _maybe_wrap_formatter(
     else:
         func_2 = func_1
 
+    # Render links
+    if hyperlinks is not None:
+        func_3 = lambda x: func_2(_render_href(x, format=hyperlinks))
+    else:
+        func_3 = func_2
+
     # Replace missing values if na_rep
     if na_rep is None:
-        return func_2
+        return func_3
     else:
-        return lambda x: na_rep if isna(x) else func_2(x)
+        return lambda x: na_rep if isna(x) else func_3(x)
 
 
 def non_reducing_slice(slice_: Subset):

pandas/tests/io/formats/style/test_html.py

@@ -764,3 +764,43 @@ def test_hiding_index_columns_multiindex_trimming():
     )
 
     assert result == expected
+
+
+@pytest.mark.parametrize("type", ["data", "index"])
+@pytest.mark.parametrize(
+    "text, exp, found",
+    [
+        ("no link, just text", False, ""),
+        ("subdomain not www: sub.web.com", False, ""),
+        ("www subdomain: www.web.com other", True, "www.web.com"),
+        ("scheme full structure: http://www.web.com", True, "http://www.web.com"),
+        ("scheme no top-level: http://www.web", True, "http://www.web"),
+        ("no scheme, no top-level: www.web", False, "www.web"),
+        ("https scheme: https://www.web.com", True, "https://www.web.com"),
+        ("ftp scheme: ftp://www.web", True, "ftp://www.web"),
+        ("subdirectories: www.web.com/directory", True, "www.web.com/directory"),
+        ("Multiple domains: www.1.2.3.4", True, "www.1.2.3.4"),
+    ],
+)
+def test_rendered_links(type, text, exp, found):
+    if type == "data":
+        df = DataFrame([text])
+        styler = df.style.format(hyperlinks="html")
+    else:
+        df = DataFrame([0], index=[text])
+        styler = df.style.format_index(hyperlinks="html")
+
+    rendered = '<a href="{0}" target="_blank">{0}</a>'.format(found)
+    result = styler.to_html()
+    assert (rendered in result) is exp
+    assert (text in result) is not exp  # test conversion done when expected and not
+
+
+def test_multiple_rendered_links():
+    links = ("www.a.b", "http://a.c", "https://a.d", "ftp://a.e")
+    df = DataFrame(["text {} {} text {} {}".format(*links)])
+    result = df.style.format(hyperlinks="html").to_html()
+    href = '<a href="{0}" target="_blank">{0}</a>'
+    for link in links:
+        assert href.format(link) in result
+    assert href.format("text") not in result

pandas/tests/io/formats/style/test_to_latex.py

@@ -845,3 +845,11 @@ def test_latex_hiding_index_columns_multiindex_alignment():
         """
     )
     assert result == expected
+
+
+def test_rendered_links():
+    # note the majority of testing is done in test_html.py: test_rendered_links
+    # these test only the alternative latex format is functional
+    df = DataFrame(["text www.domain.com text"])
+    result = df.style.format(hyperlinks="latex").to_latex()
+    assert r"text \href{www.domain.com}{www.domain.com} text" in result