klammertext/sks/image/pdf_image.py

import re, subprocess, os, shutil

# The two poppler tools a PDF image needs, found on PATH -- never by an
# absolute path: /usr/bin/pdfinfo exists on a Debian-family Linux and
# nowhere else (Homebrew puts poppler under /opt/homebrew/bin, MSYS2 under
# C:/msys64/ucrt64/bin), and a user on those systems saw "No such file"
# with no hint of what to install.  Mirrors latex_util.cpp's report of a
# missing xelatex.
def _tool(name):
    path = shutil.which(name)
    if path is None:
        raise Exception(
            f'The "{name}" command required to use a PDF file as an image is not '
            'installed. It is part of poppler: on Ubuntu "sudo apt-get install '
            'poppler-utils", with Homebrew "brew install poppler", on Windows '
            'MSYS2\'s "pacman -S mingw-w64-ucrt-x86_64-poppler" and '
            'C:\\msys64\\ucrt64\\bin on the Path')
    return path

def dimensions_from_prolog(filename):
    mediabox_pat = re.compile(r"/MediaBox\s+\[(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\]", re.S)
    width_pat = re.compile(r"/Width\s+(\d+)", re.S)
    height_pat = re.compile(r"/Height\s+(\d+)", re.S)
    width = None
    height = None
    with open(filename, mode="rb") as fp:
        line = fp.readline().decode("ascii")
        while line:
            match = mediabox_pat.match(line)
            if match:
                x1, y1, x2, y2 = [int(e) for e in match.groups()]
                width = x2 - x1
                height = y2 - y1
            else:
                match = width_pat.match(line)
                if match:
                    width = int(match.group(1))
                else:
                    match = height_pat.match(line)
                    if match:
                        height = int(match.group(1))
            if width and height:
                break
            line = fp.readline().decode("ascii")
    return width, height


def dimensions_from_pdfinfo(filename):
    sp = subprocess.Popen(
        [_tool("pdfinfo"), filename], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    out, err = sp.communicate()
    out = out.decode("ascii", errors="replace")
    width, height = None, None
    if out:
        pat = re.compile(r"Page size:\s+([\d.]+) x ([\d.]+) pts", re.S)
        match = pat.search(out)
        if match:
            width, height = [int(round(float(e))) for e in match.groups()]
    return width, height

# Doesn't agree with pdfinfo; why?
# from pdf2image import convert_from_path
# def dimensions_from_pdf2image(filename):
#     width, height = None, None
#     if pdf2image_imported:
#         img = convert_from_path(filename)[0]
#         width, height = img.size
#     return width, height


def dimensions(filename):
    # The prolog scan answers for a PDF whose MediaBox is in its first
    # lines; a compressed or binary prolog either raises (a non-ASCII byte)
    # or answers None, and EITHER is pdfinfo's turn -- the None case once
    # fell straight through to the error below without asking it.
    width, height = None, None
    try:
        width, height = dimensions_from_prolog(filename)
    except Exception:
        pass
    if width is None or height is None:
        width, height = dimensions_from_pdfinfo(filename)
    if width is None or height is None:
        raise Exception(f'Could not determine the width and height of "{filename}"')
    return width, height


def convert(pdf_filename, image_filename):
    if image_filename.endswith(".jpg"):
        arg1 = "-jpeg"
    elif image_filename.endswith(".png"):
        arg1 = "-png"
    else:
        raise Exception(f'PDF file "{pdf_filename}" can only be converted to PNG or JPEG')
    arg2 = "-singlefile"
    command = _tool("pdftoppm")
    basename = os.path.splitext(image_filename)[0]
    sp = subprocess.Popen(
        [command, arg1, arg2, pdf_filename, basename],
        stdout=subprocess.PIPE, stderr=subprocess.PIPE)
    out, err = sp.communicate()
    if sp.returncode != 0 or not os.path.exists(image_filename):
        raise Exception(f'Error creating image file from "{pdf_filename}": '
                        f'{err.decode("utf-8", errors="replace").strip()}')