bib2html.py

#!/usr/bin/env python3
# -*- coding: utf-8; mode: python -*-

"""
Docstring goes here
"""

__version__ = "1.0"
__date__ = "20190313"
__author__ = "kthoden@mpiwg-berlin.mpg.de"

import argparse
import os
import subprocess
import shlex
import logging
import string
from lxml import etree
from pathlib import Path

BASE_DIR = Path( __file__ ).resolve().parent.parent
SCRIPT_PATH = Path( __file__ )
SCRIPT_NAME = SCRIPT_PATH.name

# logging.basicConfig(level=logging.DEBUG, format=' %(asctime)s - %(levelname)s - %(message)s')

NS_MAP = {"x" : 'http://www.w3.org/1999/xhtml'}

def transform_reference(reference_element, dialect='html'):
    """Formatting transformation for reference element"""

    string_from_xml = etree.tostring(reference_element).decode('utf-8')
    removed_linebreak = string_from_xml.replace("\n", "")
    removed_namespace = removed_linebreak.replace('<p xmlns="http://www.w3.org/1999/xhtml" class="noindent">', '<p>')
    cleaned_element = etree.fromstring(removed_namespace)

    links = cleaned_element.xpath("a", namespaces=NS_MAP)
    for link in links:
        link.tag = "tagtobestripped"

    ecti_span = cleaned_element.xpath("span[@class='ecti-1095']", namespaces=NS_MAP)
    for ecti in ecti_span:
        if dialect == 'tei':
            ecti.tag = "hi"
            ecti.set("rend", "italic")
        else:
            ecti.tag = "em"
        ecti.attrib.pop('class')

    ectt_span = cleaned_element.xpath("x:span[@class='ectt-1095']", namespaces=NS_MAP)
    for ectt in ectt_span:
        if dialect == 'tei':
            ectt.tag = "hi"
            ectt.set("rend", "monospace")
        else:
            ecti.tag = "code"
        ectt.attrib.pop('class')

    etree.strip_tags(cleaned_element, "tagtobestripped")

    return cleaned_element
# def transform_reference ends here

def write_dummy_latex(
        citekeys,
        bibfile,
        language,
        template_path,
        tmp_filename
):
    """Prepare a latex file"""

    allcitekeys = ""

    for key in citekeys:
        allcitekeys += """
\subsection*{%s}
\subsubsection*{authoryear}
\cite{%s}
\subsubsection*{year}
\cite*{%s}\n""" % (key, key, key)

    with open(template_path, "r") as tmp_template:
        template = tmp_template.read()

    fill_in_template = string.Template(template)

    bibfile_path = \
        bibfile if bibfile.is_absolute() else Path.cwd() / bibfile
    substitions = fill_in_template.substitute(
            language = language,
            # language = translations[language],
            bibfile = bibfile_path,
            # bibfile = '../' + bibfile,
            citations = allcitekeys
    )

    with open(tmp_filename, "w") as texfile:
        texfile.write(substitions)

    logging.info(f"Wrote {tmp_filename}")
# def write_dummy_latex ends here


def run_htlatex(tmp_filename):
    """Create HTML file from temporary LaTeX file"""

    command = f"htlatex {tmp_filename}.tex 'xhtml,charset=utf-8' ' -cunihtf -utf8'"
    arguments = shlex.split(command)
    logging.info("Using external command htlatex with command %s" % command)
    subprocess.call(arguments)

    command = f"biber {tmp_filename}"
    arguments = shlex.split(command)
    logging.info("Using external command biber with command %s" % command)
    subprocess.call(arguments)

    command = f"htlatex {tmp_filename}.tex 'xhtml,charset=utf-8' ' -cunihtf -utf8'"
    arguments = shlex.split(command)
    logging.info("Using external command htlatex with command %s" % command)
    subprocess.call(arguments)
# def run_htlatex ends here


def main(
        bib_file,
        citekeys,
        tex_template,
        language,
        temp_dir,
        tmp_filename = "temp"
):
    temp_dir = Path( temp_dir )
    tmp_filename = Path( tmp_filename )

    if not temp_dir.exists():
        os.makedirs( temp_dir )

    write_dummy_latex(
            citekeys,
            bib_file,
            language,
            template_path = tex_template,
            tmp_filename = temp_dir / tmp_filename . with_suffix( ".tex" )
    )

    wd = Path.cwd()
    os.chdir( temp_dir )
    run_htlatex(tmp_filename)
    os.chdir( wd )

    tmp_path_html = (temp_dir / tmp_filename).with_suffix( ".html" )

    xml_tree = etree.parse( str(tmp_path_html) )

    reference_list = xml_tree.xpath(f"//x:dl[@class='thebibliography']", namespaces=NS_MAP)[0]
    entries = reference_list.xpath(f"x:dt", namespaces=NS_MAP)

    reference_div = etree.fromstring("""<div id="refs" class="references"></div>""")

    for entry in entries:
        entry_citekey = entry.get("id").replace("X0-", "")
        reference_string = entry.xpath(f"following-sibling::x:dd[1]/x:p", namespaces=NS_MAP)[0]
        formatted_reference = transform_reference(reference_string)
        wrapper_div = etree.fromstring(f"""<div id="ref-{entry_citekey}"></div>""")
        wrapper_div.append(formatted_reference)
        reference_div.append(wrapper_div)
    return reference_div

    """
    <h1 id="references" class="unnumbered">References</h1>
    <div id="refs" class="references">
    <div id="ref-Appadurai_1986">
    <p>Appadurai, Arjun, ed. (1986). <em>The Social Life of Things: Commodities in Cultural Perspective</em>. Cambridge, UK: Cambridge University Press.</p>
    </div>
    """

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument(
            "bibfile",
            help="File that contains the bibliography")
    parser.add_argument(
            "--tex-template",
            default = BASE_DIR / "bibformat" / "4ht" / "bibliography4ht.tex",
            help="the latex template to use for the bibliography"
    )
    parser.add_argument(
            "--temp-dir",
            default = "tmp_files",
            help="where to store temporary files"
    )
    args = parser.parse_args()
    citekeys = ["Edwards_2017", "Riggs:2016aa", "Bruckler:2001aa", "Zdenek:1939aa", "Caraffa_2011", "Uhlikova:2010aa", "Noll:1992aa", "Schwarz:1931aa", "Schwartz_1995", "Faber:2015ab", "Rohacek:2010aa", "Lachnit:2005aa", "Groll:1865aa", "Schlosser:1934aa", "Eitelberger:1863ab", "Wirth:1939aa", "Faber:2015aa", "Trnkova:2015aa", "Trnkova:2010aa", "Frodl:1988aa"]
    language = "de"

    translations = {"de" : "german", "en" : "english", "it" : "italian", "fr" : "french"}

    temp_dir = Path( args.temp_dir )
    references_in_html = main(
            bib_file = args.bibfile,
            citekeys = citekeys,
            tex_template = args.tex_template,
            language = translations[language],
            temp_dir = args.temp_dir
    )
    print( etree.tostring( references_in_html ) )
# finis