Pandoc filters (pl and py) to collect all figures and tables at a specified place in a document

pandoc-collect-floats.pl

#!/usr/bin/env perl

=pod

Pandoc filter which emulate the LaTeX endfloat package by extracting all
elements which would be LaTeX floats (figures and tables) from a
document and putting them in div with the id "figures" or "tables"
respectively. You must mark the points in the document where you want
the floats to go with a paragraph containing *only* the text
"FiguresHere" or "TablesHere" -- exactly as written here in CamelCase --
or you will lose the floats! If there are several paragraphs with the
sentinel texts only the one first found will be replaced with a div
containing the figures/tables.

Additionally a paragraph with the text "[Figure %d about here.]" or
"[Table %d about here.]" is inserted into the document where the
figure/table used to be, with "%d" being the number of figures/tables
found so far; thus it is not and cannot be guaranteed to be the same
number as LaTeX would have assigned!

Reference: <https://groups.google.com/d/topic/pandoc-discuss/jLUuYFcRDtk/discussion>

This filter requires perl interpreter and the
JSON::MaybeXS and Data::Rmap modules to run.

Most operating systems other than Windows come with perl already installed.
If you are on Windows I recommend downloading and installing
Strawberry Perl: <http://strawberryperl.com>.

If/once you have perl installed run the following commands:

    cpan App::cpanminus

    cpanm JSON::MaybeXS Data::Rmap

Then run pandoc with the filter:

    pandoc -F ./pandoc-collect-floats.pl [OPTIONS] INPUTFILE

=cut

use utf8;        # so literals and identifiers can be in UTF-8
use strict;      # quote strings, declare variables
use warnings;    # on by default

use JSON::MaybeXS qw[ decode_json encode_json ];
use Data::Rmap qw[ rmap_hash ];

my $format = shift @ARGV;

my $json = do { local $/; <>; };
my $doc = decode_json( $json );

my %floats = (    #
    figures     => [],
    saw_figures => 0,
    tables      => [],
    saw_tables  => 0,
);

rmap_hash {
    return unless exists $_->{t} and exists $_->{c};
    my $elem = $_;
    if ( 'Para' eq $elem->{t} ) {
        return unless 1 == @{ $elem->{c} };
        if ( 'Image' eq $elem->{c}[0]{t} ) {
            return unless $elem->{c}[0]{c}[-1][1] =~ /^fig\:/;
            push @{ $floats{figures} }, $elem;
            my $count = @{ $floats{figures} };
            $_ = +{
                t => 'Para',
                c => [ +{ t => 'Str', c => "[Figure $count about here.]" } ],
            };
        }
        elsif ( 'Str' eq $elem->{c}[0]{t} ) {
            return unless $elem->{c}[0]{c} =~ /^(Figures|Tables)Here$/;
            my $id = lc "collected-$1";
            $_ = +{ t => 'Div', c => [ [ $id, [], [] ], $floats{$id} ], };
        }
    }
    elsif ( 'Table' eq $elem->{t} ) {
        push @{ $floats{tables} }, $elem;
        my $count = @{ $floats{tables} };
        $_ = +{
            t => 'Para',
            c => [ +{ t => 'Str', c => "[Table $count about here.]" } ],
        };
    }
    return;
}
$doc;

print encode_json( $doc );

pandoc-collect-floats.py

#!/usr/bin/env python

"""
Pandoc filter which emulate the LaTeX endfloat package by extracting all
elements which would be LaTeX floats (figures and tables) from a
document and putting them in div with the id "figures" or "tables"
respectively. You must mark the points in the document where you want
the floats to go with a paragraph containing *only* the text
"FiguresHere" or "TablesHere" -- exactly as written here in CamelCase --
or you will lose the floats! If there are several paragraphs with the
sentinel texts only the one first found will be replaced with a div
containing the figures/tables.

Additionally a paragraph with the text "[Figure %d about here.]" or
"[Table %d about here.]" is inserted into the document where the
figure/table used to be, with "%d" being the number of figures/tables
found so far; thus it is not and cannot be guaranteed to be the same
number as LaTeX would have assigned!

Reference: <https://groups.google.com/d/topic/pandoc-discuss/jLUuYFcRDtk/discussion>

This filter requires the pandocfilters module to be installed. You can
clone or download it from GitHub (with instructions for installing and
how to use filters): https://github.com/jgm/pandocfilters or install
from PyPI::

    pip install pandocfilters

If you have an earlier version installed you may need to do::

    pip install -U pandocfilters
"""

from pandocfilters import toJSONFilter, Div, Image, Para, Str, Table

floats = {
    'figures': [],
    'saw_figures': None,
    'tables': [],
    'saw_tables': None
}

def collect_floats(eltype, eldata, fmt, meta):
    global floats
    if eltype == 'Para':
        if len(eldata) != 1:
            return None
        elem = eldata[0];
        if elem['t'] == 'Image':
            if elem['c'][-1][1].startswith('fig:'): # title
                floats['figures'].append(Para(eldata))
                filler = "[Figure %d about here.]" % len(floats['figures'])
                return Para([Str(filler)])
        elif elem['t'] == 'Str':
            text = elem['c']
            if elem['c'] == 'FiguresHere':
                if floats['saw_figures']:
                    return None
                floats['saw_figures'] = True
                key = 'figures'
            elif elem['c'] == 'TablesHere':
                if floats['saw_tables']:
                    return None
                floats['saw_tables'] = True
                key = 'tables'
            else:
                return None
            return [Div(['collected-' + key , [], []], floats[key])]
    elif eltype == 'Table':
        floats['tables'].append(Table(*eldata))
        filler = "[Table %d about here.]" % len(floats['tables'])
        return Para([Str(filler)])
    return None

if __name__ == "__main__":
    toJSONFilter(collect_floats)

I upgraded to the newest pandoc 1.16.0.2 and this is not working anymore.

pandoc --verbose --bibliography=ASMOptim.bib --filter pandoc-citeproc
--filter pandoc-collect-floats.py ASMOptim.pandoc.tex -o
ASMOptim_0.2.0...docx #
Traceback (most recent call last):
  File "/Users/rainerkrug/bin/pandoc-collect-floats.py", line 76, in
<module>
    toJSONFilter(collect_floats)
  File "/usr/local/lib/python2.7/site-packages/pandocfilters.py", line 63,
in toJSONFilter
    altered = walk(doc, action, format, doc[0]['unMeta'])
  File "/usr/local/lib/python2.7/site-packages/pandocfilters.py", line 31,
in walk
    array.append(walk(item, action, format, meta))
  File "/usr/local/lib/python2.7/site-packages/pandocfilters.py", line 22,
in walk
    res = action(item['t'], item['c'], format, meta)
  File "/Users/rainerkrug/bin/pandoc-collect-floats.py", line 50, in
collect_floats
    if elem['c'][1][1].startswith('fig:'): # title
AttributeError: 'dict' object has no attribute 'startswith'
pandoc: Error running filter pandoc-collect-floats.py
Filter returned error status 1

I have no idea where to look - if you could take a look and possibly make
it compatible with pandoc 1.16?