ENH: add environment, e.g. "longtable", to Styler.to_latex (pandas-dev#41866)

Author: attack68

doc/source/whatsnew/v1.4.0.rst

@@ -35,6 +35,7 @@ Other enhancements
 -  Additional options added to :meth:`.Styler.bar` to control alignment and display, with keyword only arguments (:issue:`26070`, :issue:`36419`)
 - :meth:`Styler.bar` now validates the input argument ``width`` and ``height`` (:issue:`42511`)
 - :meth:`Series.ewm`, :meth:`DataFrame.ewm`, now support a ``method`` argument with a ``'table'`` option that performs the windowing operation over an entire :class:`DataFrame`. See :ref:`Window Overview <window.overview>` for performance and functional benefits (:issue:`42273`)
+- Added keyword argument ``environment`` to :meth:`.Styler.to_latex` also allowing a specific "longtable" entry with a separate jinja2 template (:issue:`41866`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/io/formats/style.py

@@ -427,6 +427,7 @@ def to_latex(
         multirow_align: str = "c",
         multicol_align: str = "r",
         siunitx: bool = False,
+        environment: str | None = None,
         encoding: str | None = None,
         convert_css: bool = False,
     ):
@@ -457,6 +458,8 @@ def to_latex(
             \\begin{table}[<position>]
 
             \\<position_float>
+
+            Cannot be used if ``environment`` is "longtable".
         hrules : bool, default False
             Set to `True` to add \\toprule, \\midrule and \\bottomrule from the
             {booktabs} LaTeX package.
@@ -483,6 +486,12 @@ def to_latex(
             the left, centrally, or at the right.
         siunitx : bool, default False
             Set to ``True`` to structure LaTeX compatible with the {siunitx} package.
+        environment : str, optional
+            If given, the environment that will replace 'table' in ``\\begin{table}``.
+            If 'longtable' is specified then a more suitable template is
+            rendered.
+
+            .. versionadded:: 1.4.0
         encoding : str, default "utf-8"
             Character encoding setting.
         convert_css : bool, default False
@@ -519,6 +528,8 @@ def to_latex(
         italic (with siunitx) | \\usepackage{etoolbox}
                               | \\robustify\\itshape
                               | \\sisetup{detect-all = true}  *(within {document})*
+        environment           \\usepackage{longtable} if arg is "longtable"
+                              | or any other relevant environment package
         ===================== ==========================================================
 
         **Cell Styles**
@@ -748,6 +759,10 @@ def to_latex(
             )
 
         if position_float:
+            if environment == "longtable":
+                raise ValueError(
+                    "`position_float` cannot be used in 'longtable' `environment`"
+                )
             if position_float not in ["raggedright", "raggedleft", "centering"]:
                 raise ValueError(
                     f"`position_float` should be one of "
@@ -788,6 +803,7 @@ def to_latex(
             sparse_columns=sparse_columns,
             multirow_align=multirow_align,
             multicol_align=multicol_align,
+            environment=environment,
             convert_css=convert_css,
         )
 

pandas/io/formats/templates/latex.tpl

@@ -1,52 +1,5 @@
-{% if parse_wrap(table_styles, caption) %}
-\begin{table}
-{%- set position = parse_table(table_styles, 'position') %}
-{%- if position is not none %}
-[{{position}}]
-{%- endif %}
-
-{% set position_float = parse_table(table_styles, 'position_float') %}
-{% if position_float is not none%}
-\{{position_float}}
-{% endif %}
-{% if caption and caption is string %}
-\caption{% raw %}{{% endraw %}{{caption}}{% raw %}}{% endraw %}
-
-{% elif caption and caption is sequence %}
-\caption[{{caption[1]}}]{% raw %}{{% endraw %}{{caption[0]}}{% raw %}}{% endraw %}
-
-{% endif %}
-{% for style in table_styles %}
-{% if style['selector'] not in ['position', 'position_float', 'caption', 'toprule', 'midrule', 'bottomrule', 'column_format'] %}
-\{{style['selector']}}{{parse_table(table_styles, style['selector'])}}
-{% endif %}
-{% endfor %}
-{% endif %}
-\begin{tabular}
-{%- set column_format = parse_table(table_styles, 'column_format') %}
-{% raw %}{{% endraw %}{{column_format}}{% raw %}}{% endraw %}
-
-{% set toprule = parse_table(table_styles, 'toprule') %}
-{% if toprule is not none %}
-\{{toprule}}
-{% endif %}
-{% for row in head %}
-{% for c in row %}{%- if not loop.first %} & {% endif %}{{parse_header(c, multirow_align, multicol_align, True)}}{% endfor %} \\
-{% endfor %}
-{% set midrule = parse_table(table_styles, 'midrule') %}
-{% if midrule is not none %}
-\{{midrule}}
-{% 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, convert_css)}}{% endif %}
-{%- endfor %} \\
-{% endfor %}
-{% set bottomrule = parse_table(table_styles, 'bottomrule') %}
-{% if bottomrule is not none %}
-\{{bottomrule}}
-{% endif %}
-\end{tabular}
-{% if parse_wrap(table_styles, caption) %}
-\end{table}
+{% if environment == "longtable" %}
+{% include "latex_longtable.tpl" %}
+{% else %}
+{% include "latex_table.tpl" %}
 {% endif %}

pandas/io/formats/templates/latex_longtable.tpl

@@ -0,0 +1,73 @@
+\begin{longtable}
+{%- set position = parse_table(table_styles, 'position') %}
+{%- if position is not none %}
+[{{position}}]
+{%- endif %}
+{%- set column_format = parse_table(table_styles, 'column_format') %}
+{% raw %}{{% endraw %}{{column_format}}{% raw %}}{% endraw %}
+
+{% for style in table_styles %}
+{% if style['selector'] not in ['position', 'position_float', 'caption', 'toprule', 'midrule', 'bottomrule', 'column_format', 'label'] %}
+\{{style['selector']}}{{parse_table(table_styles, style['selector'])}}
+{% endif %}
+{% endfor %}
+{% if caption and caption is string %}
+\caption{% raw %}{{% endraw %}{{caption}}{% raw %}}{% endraw %}
+{%- set label = parse_table(table_styles, 'label') %}
+{%- if label is not none %}
+ \label{{label}}
+{%- endif %} \\
+{% elif caption and caption is sequence %}
+\caption[{{caption[1]}}]{% raw %}{{% endraw %}{{caption[0]}}{% raw %}}{% endraw %}
+{%- set label = parse_table(table_styles, 'label') %}
+{%- if label is not none %}
+ \label{{label}}
+{%- endif %} \\
+{% endif %}
+{% set toprule = parse_table(table_styles, 'toprule') %}
+{% if toprule is not none %}
+\{{toprule}}
+{% endif %}
+{% for row in head %}
+{% for c in row %}{%- if not loop.first %} & {% endif %}{{parse_header(c, multirow_align, multicol_align, True)}}{% endfor %} \\
+{% endfor %}
+{% set midrule = parse_table(table_styles, 'midrule') %}
+{% if midrule is not none %}
+\{{midrule}}
+{% endif %}
+\endfirsthead
+{% if caption and caption is string %}
+\caption[]{% raw %}{{% endraw %}{{caption}}{% raw %}}{% endraw %} \\
+{% elif caption and caption is sequence %}
+\caption[]{% raw %}{{% endraw %}{{caption[0]}}{% raw %}}{% endraw %} \\
+{% endif %}
+{% if toprule is not none %}
+\{{toprule}}
+{% endif %}
+{% for row in head %}
+{% for c in row %}{%- if not loop.first %} & {% endif %}{{parse_header(c, multirow_align, multicol_align, True)}}{% endfor %} \\
+{% endfor %}
+{% if midrule is not none %}
+\{{midrule}}
+{% endif %}
+\endhead
+{% if midrule is not none %}
+\{{midrule}}
+{% endif %}
+\multicolumn{% raw %}{{% endraw %}{{column_format|length}}{% raw %}}{% endraw %}{r}{Continued on next page} \\
+{% if midrule is not none %}
+\{{midrule}}
+{% endif %}
+\endfoot
+{% set bottomrule = parse_table(table_styles, 'bottomrule') %}
+{% if bottomrule is not none %}
+\{{bottomrule}}
+{% endif %}
+\endlastfoot
+{% 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, convert_css)}}{% endif %}
+{%- endfor %} \\
+{% endfor %}
+\end{longtable}
+{% raw %}{% endraw %}

pandas/io/formats/templates/latex_table.tpl

@@ -0,0 +1,53 @@
+{% if environment or parse_wrap(table_styles, caption) %}
+\begin{% raw %}{{% endraw %}{{environment if environment else "table"}}{% raw %}}{% endraw %}
+{%- set position = parse_table(table_styles, 'position') %}
+{%- if position is not none %}
+[{{position}}]
+{%- endif %}
+
+{% set position_float = parse_table(table_styles, 'position_float') %}
+{% if position_float is not none%}
+\{{position_float}}
+{% endif %}
+{% if caption and caption is string %}
+\caption{% raw %}{{% endraw %}{{caption}}{% raw %}}{% endraw %}
+
+{% elif caption and caption is sequence %}
+\caption[{{caption[1]}}]{% raw %}{{% endraw %}{{caption[0]}}{% raw %}}{% endraw %}
+
+{% endif %}
+{% for style in table_styles %}
+{% if style['selector'] not in ['position', 'position_float', 'caption', 'toprule', 'midrule', 'bottomrule', 'column_format'] %}
+\{{style['selector']}}{{parse_table(table_styles, style['selector'])}}
+{% endif %}
+{% endfor %}
+{% endif %}
+\begin{tabular}
+{%- set column_format = parse_table(table_styles, 'column_format') %}
+{% raw %}{{% endraw %}{{column_format}}{% raw %}}{% endraw %}
+
+{% set toprule = parse_table(table_styles, 'toprule') %}
+{% if toprule is not none %}
+\{{toprule}}
+{% endif %}
+{% for row in head %}
+{% for c in row %}{%- if not loop.first %} & {% endif %}{{parse_header(c, multirow_align, multicol_align, True)}}{% endfor %} \\
+{% endfor %}
+{% set midrule = parse_table(table_styles, 'midrule') %}
+{% if midrule is not none %}
+\{{midrule}}
+{% 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, convert_css)}}{% endif %}
+{%- endfor %} \\
+{% endfor %}
+{% set bottomrule = parse_table(table_styles, 'bottomrule') %}
+{% if bottomrule is not none %}
+\{{bottomrule}}
+{% endif %}
+\end{tabular}
+{% if environment or parse_wrap(table_styles, caption) %}
+\end{% raw %}{{% endraw %}{{environment if environment else "table"}}{% raw %}}{% endraw %}
+
+{% endif %}