Backport PR #40731 on branch 1.3.x (ENH: Styler.to_latex conversion from CSS)

doc/source/whatsnew/v1.3.0.rst

@@ -136,7 +136,7 @@ which has been revised and improved (:issue:`39720`, :issue:`39317`, :issue:`404
  - Many features of the :class:`.Styler` class are now either partially or fully usable on a DataFrame with a non-unique indexes or columns (:issue:`41143`)
  - One has greater control of the display through separate sparsification of the index or columns using the :ref:`new styler options <options.available>`, which are also usable via :func:`option_context` (:issue:`41142`)
  - Added the option ``styler.render.max_elements`` to avoid browser overload when styling large DataFrames (:issue:`40712`)
- - Added the method :meth:`.Styler.to_latex` (:issue:`21673`)
+ - Added the method :meth:`.Styler.to_latex` (:issue:`21673`), which also allows some limited CSS conversion (:issue:`40731`)
  - Added the method :meth:`.Styler.to_html` (:issue:`13379`)
 
 .. _whatsnew_130.enhancements.dataframe_honors_copy_with_dict:

pandas/io/formats/style.py

@@ -426,6 +426,7 @@ def to_latex(
         multicol_align: str = "r",
         siunitx: bool = False,
         encoding: str | None = None,
+        convert_css: bool = False,
     ):
         r"""
         Write Styler to a file, buffer or string in LaTeX format.
@@ -482,6 +483,10 @@ def to_latex(
             Set to ``True`` to structure LaTeX compatible with the {siunitx} package.
         encoding : str, default "utf-8"
             Character encoding setting.
+        convert_css : bool, default False
+            Convert simple cell-styles from CSS to LaTeX format. Any CSS not found in
+            conversion table is dropped. A style can be forced by adding option
+            `--latex`. See notes.
 
         Returns
         -------
@@ -661,6 +666,45 @@ def to_latex(
          & ix2 & \$3 & 4.400 & CATS \\
         L1 & ix3 & \$2 & 6.600 & COWS \\
         \end{tabular}
+
+        **CSS Conversion**
+
+        This method can convert a Styler constructured with HTML-CSS to LaTeX using
+        the following limited conversions.
+
+        ================== ==================== ============= ==========================
+        CSS Attribute      CSS value            LaTeX Command LaTeX Options
+        ================== ==================== ============= ==========================
+        font-weight        | bold               | bfseries
+                           | bolder             | bfseries
+        font-style         | italic             | itshape
+                           | oblique            | slshape
+        background-color   | red                cellcolor     | {red}--lwrap
+                           | #fe01ea                          | [HTML]{FE01EA}--lwrap
+                           | #f0e                             | [HTML]{FF00EE}--lwrap
+                           | rgb(128,255,0)                   | [rgb]{0.5,1,0}--lwrap
+                           | rgba(128,0,0,0.5)                | [rgb]{0.5,0,0}--lwrap
+                           | rgb(25%,255,50%)                 | [rgb]{0.25,1,0.5}--lwrap
+        color              | red                color         | {red}
+                           | #fe01ea                          | [HTML]{FE01EA}
+                           | #f0e                             | [HTML]{FF00EE}
+                           | rgb(128,255,0)                   | [rgb]{0.5,1,0}
+                           | rgba(128,0,0,0.5)                | [rgb]{0.5,0,0}
+                           | rgb(25%,255,50%)                 | [rgb]{0.25,1,0.5}
+        ================== ==================== ============= ==========================
+
+        It is also possible to add user-defined LaTeX only styles to a HTML-CSS Styler
+        using the ``--latex`` flag, and to add LaTeX parsing options that the
+        converter will detect within a CSS-comment.
+
+        >>> df = pd.DataFrame([[1]])
+        >>> df.style.set_properties(
+        ...     **{"font-weight": "bold /* --dwrap */", "Huge": "--latex--rwrap"}
+        ... ).to_latex(css_convert=True)
+        \begin{tabular}{lr}
+        {} & {0} \\
+        0 & {\bfseries}{\Huge{1}} \\
+        \end{tabular}
         """
         table_selectors = (
             [style["selector"] for style in self.table_styles]
@@ -740,6 +784,7 @@ def to_latex(
             sparse_columns=sparse_columns,
             multirow_align=multirow_align,
             multicol_align=multicol_align,
+            convert_css=convert_css,
         )
 
         return save_to_buffer(latex, buf=buf, encoding=encoding)

pandas/io/formats/style_render.py

@@ -2,6 +2,7 @@
 
 from collections import defaultdict
 from functools import partial
+import re
 from typing import (
     Any,
     Callable,
@@ -1253,7 +1254,9 @@ def _parse_latex_table_styles(table_styles: CSSStyles, selector: str) -> str | N
     return None
 
 
-def _parse_latex_cell_styles(latex_styles: CSSList, display_value: str) -> str:
+def _parse_latex_cell_styles(
+    latex_styles: CSSList, display_value: str, convert_css: bool = False
+) -> str:
     r"""
     Mutate the ``display_value`` string including LaTeX commands from ``latex_styles``.
 
@@ -1279,6 +1282,8 @@ def _parse_latex_cell_styles(latex_styles: CSSList, display_value: str) -> str:
     For example for styles:
     `[('c1', 'o1--wrap'), ('c2', 'o2')]` this returns: `{\c1o1 \c2o2{display_value}}
     """
+    if convert_css:
+        latex_styles = _parse_latex_css_conversion(latex_styles)
     for (command, options) in latex_styles[::-1]:  # in reverse for most recent style
         formatter = {
             "--wrap": f"{{\\{command}--to_parse {display_value}}}",
@@ -1351,6 +1356,82 @@ def _parse_latex_options_strip(value: str | int | float, arg: str) -> str:
     return str(value).replace(arg, "").replace("/*", "").replace("*/", "").strip()
 
 
+def _parse_latex_css_conversion(styles: CSSList) -> CSSList:
+    """
+    Convert CSS (attribute,value) pairs to equivalent LaTeX (command,options) pairs.
+
+    Ignore conversion if tagged with `--latex` option, skipped if no conversion found.
+    """
+
+    def font_weight(value, arg):
+        if value == "bold" or value == "bolder":
+            return "bfseries", f"{arg}"
+        return None
+
+    def font_style(value, arg):
+        if value == "italic":
+            return "itshape", f"{arg}"
+        elif value == "oblique":
+            return "slshape", f"{arg}"
+        return None
+
+    def color(value, user_arg, command, comm_arg):
+        """
+        CSS colors have 5 formats to process:
+
+         - 6 digit hex code: "#ff23ee"     --> [HTML]{FF23EE}
+         - 3 digit hex code: "#f0e"        --> [HTML]{FF00EE}
+         - rgba: rgba(128, 255, 0, 0.5)    --> [rgb]{0.502, 1.000, 0.000}
+         - rgb: rgb(128, 255, 0,)          --> [rbg]{0.502, 1.000, 0.000}
+         - string: red                     --> {red}
+
+        Additionally rgb or rgba can be expressed in % which is also parsed.
+        """
+        arg = user_arg if user_arg != "" else comm_arg
+
+        if value[0] == "#" and len(value) == 7:  # color is hex code
+            return command, f"[HTML]{{{value[1:].upper()}}}{arg}"
+        if value[0] == "#" and len(value) == 4:  # color is short hex code
+            val = f"{value[1].upper()*2}{value[2].upper()*2}{value[3].upper()*2}"
+            return command, f"[HTML]{{{val}}}{arg}"
+        elif value[:3] == "rgb":  # color is rgb or rgba
+            r = re.findall("(?<=\\()[0-9\\s%]+(?=,)", value)[0].strip()
+            r = float(r[:-1]) / 100 if "%" in r else int(r) / 255
+            g = re.findall("(?<=,)[0-9\\s%]+(?=,)", value)[0].strip()
+            g = float(g[:-1]) / 100 if "%" in g else int(g) / 255
+            if value[3] == "a":  # color is rgba
+                b = re.findall("(?<=,)[0-9\\s%]+(?=,)", value)[1].strip()
+            else:  # color is rgb
+                b = re.findall("(?<=,)[0-9\\s%]+(?=\\))", value)[0].strip()
+            b = float(b[:-1]) / 100 if "%" in b else int(b) / 255
+            return command, f"[rgb]{{{r:.3f}, {g:.3f}, {b:.3f}}}{arg}"
+        else:
+            return command, f"{{{value}}}{arg}"  # color is likely string-named
+
+    CONVERTED_ATTRIBUTES: dict[str, Callable] = {
+        "font-weight": font_weight,
+        "background-color": partial(color, command="cellcolor", comm_arg="--lwrap"),
+        "color": partial(color, command="color", comm_arg=""),
+        "font-style": font_style,
+    }
+
+    latex_styles: CSSList = []
+    for (attribute, value) in styles:
+        if isinstance(value, str) and "--latex" in value:
+            # return the style without conversion but drop '--latex'
+            latex_styles.append((attribute, value.replace("--latex", "")))
+        if attribute in CONVERTED_ATTRIBUTES.keys():
+            arg = ""
+            for x in ["--wrap", "--nowrap", "--lwrap", "--dwrap", "--rwrap"]:
+                if x in str(value):
+                    arg, value = x, _parse_latex_options_strip(value, x)
+                    break
+            latex_style = CONVERTED_ATTRIBUTES[attribute](value, arg)
+            if latex_style is not None:
+                latex_styles.extend([latex_style])
+    return latex_styles
+
+
 def _escape_latex(s):
     r"""
     Replace the characters ``&``, ``%``, ``$``, ``#``, ``_``, ``{``, ``}``,

pandas/io/formats/templates/latex.tpl

@@ -39,7 +39,7 @@
 {% endif %}
 {% for row in body %}
 {% for c in row %}{% if not loop.first %} & {% endif %}
-  {%- if c.type == 'th' %}{{parse_header(c, multirow_align, multicol_align)}}{% else %}{{parse_cell(c.cellstyle, c.display_value)}}{% endif %}
+  {%- if c.type == 'th' %}{{parse_header(c, multirow_align, multicol_align)}}{% else %}{{parse_cell(c.cellstyle, c.display_value, convert_css)}}{% endif %}
 {%- endfor %} \\
 {% endfor %}
 {% set bottomrule = parse_table(table_styles, 'bottomrule') %}

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

@@ -12,6 +12,7 @@
 from pandas.io.formats.style import Styler
 from pandas.io.formats.style_render import (
     _parse_latex_cell_styles,
+    _parse_latex_css_conversion,
     _parse_latex_header_span,
     _parse_latex_table_styles,
     _parse_latex_table_wrapping,
@@ -443,3 +444,48 @@ def test_parse_latex_table_wrapping(styler):
 def test_short_caption(styler):
     result = styler.to_latex(caption=("full cap", "short cap"))
     assert "\\caption[short cap]{full cap}" in result
+
+
+@pytest.mark.parametrize(
+    "css, expected",
+    [
+        ([("color", "red")], [("color", "{red}")]),  # test color and input format types
+        (
+            [("color", "rgb(128, 128, 128 )")],
+            [("color", "[rgb]{0.502, 0.502, 0.502}")],
+        ),
+        (
+            [("color", "rgb(128, 50%, 25% )")],
+            [("color", "[rgb]{0.502, 0.500, 0.250}")],
+        ),
+        (
+            [("color", "rgba(128,128,128,1)")],
+            [("color", "[rgb]{0.502, 0.502, 0.502}")],
+        ),
+        ([("color", "#FF00FF")], [("color", "[HTML]{FF00FF}")]),
+        ([("color", "#F0F")], [("color", "[HTML]{FF00FF}")]),
+        ([("font-weight", "bold")], [("bfseries", "")]),  # test font-weight and types
+        ([("font-weight", "bolder")], [("bfseries", "")]),
+        ([("font-weight", "normal")], []),
+        ([("background-color", "red")], [("cellcolor", "{red}--lwrap")]),
+        (
+            [("background-color", "#FF00FF")],  # test background-color command and wrap
+            [("cellcolor", "[HTML]{FF00FF}--lwrap")],
+        ),
+        ([("font-style", "italic")], [("itshape", "")]),  # test font-style and types
+        ([("font-style", "oblique")], [("slshape", "")]),
+        ([("font-style", "normal")], []),
+        ([("color", "red /*--dwrap*/")], [("color", "{red}--dwrap")]),  # css comments
+        ([("background-color", "red /* --dwrap */")], [("cellcolor", "{red}--dwrap")]),
+    ],
+)
+def test_parse_latex_css_conversion(css, expected):
+    result = _parse_latex_css_conversion(css)
+    assert result == expected
+
+
+def test_parse_latex_css_conversion_option():
+    css = [("command", "option--latex--wrap")]
+    expected = [("command", "option--wrap")]
+    result = _parse_latex_css_conversion(css)
+    assert result == expected