overleaf_kludge.py

import os
import re
import shutil
import subprocess


ROOT_DIR = "overleaf_kludge"
DISSERTATION_FILES_DIR = os.path.join(ROOT_DIR, "_jbn_dissertation_files")


###############################################################################
#        ____                    _____                _                       #
#       / ___|___  _ __  _   _  | ____|_ ____   _____| | ___  _ __   ___      #
#      | |   / _ \| '_ \| | | | |  _| | '_ \ \ / / _ \ |/ _ \| '_ \ / _ \     #
#      | |__| (_) | |_) | |_| | | |___| | | \ V /  __/ | (_) | |_) |  __/     #
#       \____\___/| .__/ \__, | |_____|_| |_|\_/ \___|_|\___/| .__/ \___|     #
#                 |_|    |___/                               |_|              #
###############################################################################


shutil.rmtree(ROOT_DIR, ignore_errors=True)
shutil.copytree(os.path.join("template"),  os.path.join(ROOT_DIR))
shutil.copy("bibliography.bibtex", os.path.join(ROOT_DIR, "bibliography.bibtex"))
shutil.copytree("_jbn_dissertation_files", DISSERTATION_FILES_DIR)


###############################################################################
#           ____  ____  _____     _  __         ______     ______             #
#          |  _ \|  _ \|  ___|   (_)/ _|_   _  / ___\ \   / / ___|___         #
#          | |_) | | | | |_ _____| | |_| | | | \___ \\ \ / / |  _/ __|        #
#          |  __/| |_| |  _|_____| |  _| |_| |  ___) |\ V /| |_| \__ \        #
#          |_|   |____/|_|       |_|_|  \__, | |____/  \_/  \____|___/        #
#                                       |___/                                 #
###############################################################################


for file_name in os.listdir(DISSERTATION_FILES_DIR):
    if not file_name.endswith('.svg'):
        continue
    
    src_path = os.path.join(DISSERTATION_FILES_DIR, file_name)
    dst_path = os.path.join(DISSERTATION_FILES_DIR, file_name.replace(".svg", ".pdf"))
    subprocess.check_call(["rsvg-convert", "-f", "pdf", "-o", dst_path, src_path])
    
    
with open("build/thesis.tex") as fp:
    tex = fp.read()
    tex = tex.replace("/src/template/sigs/compsocsci.tex", "sigs/compsocsci.tex")
    tex = tex.replace(".svg}", ".pdf}")

    
###############################################################################
#         ____            _   _ _   _               _____ _ _                 #
#        |  _ \ __ _ _ __| |_(_) |_(_) ___  _ __   |  ___(_) | ___  ___       #
#        | |_) / _` | '__| __| | __| |/ _ \| '_ \  | |_  | | |/ _ \/ __|      #
#        |  __/ (_| | |  | |_| | |_| | (_) | | | | |  _| | | |  __/\__ \      #
#        |_|   \__,_|_|   \__|_|\__|_|\___/|_| |_| |_|   |_|_|\___||___/      #
#                                                                             #
###############################################################################


CHAPTER_RE = re.compile(r"\\hypertarget{[^}]+}{%\n\\chapter\*?{([^}]+)}\\label{[^}]+}}", re.M|re.I)

names, boundaries = [], []
for i, m in enumerate(CHAPTER_RE.finditer(tex)):
    pythonized_name = m.group(1).replace("\n", " ").replace("Appendix: ", "").replace(" ", "_").lower()
    names.append(f'{i+1:02d}_{pythonized_name}')
    boundaries.append(m.start())    
names.append("__ignored__")
boundaries.append(len(tex))


###############################################################################
#               ____                    _ _         _____                     #
#              |  _ \ _____      ___ __(_) |_ ___  |_   _|____  __            #
#              | |_) / _ \ \ /\ / / '__| | __/ _ \   | |/ _ \ \/ /            #
#              |  _ <  __/\ V  V /| |  | | ||  __/   | |  __/>  <             #
#              |_| \_\___| \_/\_/ |_|  |_|\__\___|   |_|\___/_/\_\            #
#                                                                             #
###############################################################################


INCLUDE_GRAPHICS_RE = re.compile(r"\\includegraphics{(_jbn_dissertation_files[^}]+)}", re.M|re.I)

BLANK_LISTING = "\\begin{lstlisting}[language=Python]\n\\end{lstlisting}"


def translate_images(tex, chapter):
    assert isinstance(chapter, str)

    chapter_name = chapter + "_media"
    chapter_path = os.path.join(ROOT_DIR, chapter_name)

    os.makedirs(chapter_path, exist_ok=True)

    n = 0
    while True:
        m = INCLUDE_GRAPHICS_RE.search(tex)

        if not m:
            break

        src = m.group(1)
        dst = os.path.join(chapter_name, f"{n:03d}.pdf")

        shutil.copyfile(os.path.join(ROOT_DIR, src), 
                        os.path.join(ROOT_DIR, dst))

        tex = tex.replace(m.group(0), r"\includegraphics{" + dst + "}")

        if n > 1000:
            break
        n += 1
        
    return tex


new_tex = tex[:boundaries[0]]
chapters = range(1, len(boundaries)+1)

for chapter, name, start, end in zip(chapters, names, boundaries[:-1], boundaries[1:]):
    output_path = os.path.join(ROOT_DIR, name + ".tex")
    
    with open(output_path, "w") as fp:
        sub_tex = tex[start:end].replace(BLANK_LISTING, "")
        sub_tex = translate_images(sub_tex, name.split("_")[0])
        fp.write(sub_tex)
    
    new_tex += "\n\\input{" + name + "}\n"    
    
    
with open(os.path.join(ROOT_DIR, "jbn_dissertation.tex"), "w") as fp:
    fp.write(new_tex)
    
    
shutil.rmtree(DISSERTATION_FILES_DIR, True)