gistfile1.py

#!/usr/bin/env python

"""

Modified by Uldis Bojars:
 - changed to only print the list of figures referenced in LaTeX files

ToDo:
 - work around the limitation of only 2 levels of includes
 - fix the problem that it does not work if start_file is not in the current
   working directory (cwd)

Usage: find_figures.py main.tex

---
  
Original code retrieved from: 
 - http://scienceoss.com/python-script-to-package-latex-projects-for-distribution/

This script gathers the necessary images and files (from
an arbitrarily large number of unneeded figures) and
puts it all in a tarball for distribution.

Usage: latexpackager.py main.tex dissertation.tar.gz

"""

import sys
import re
import os
import tarfile
from pprint import pprint

def find_references(f):
    '''Returns a list of Latex files that f refers to,
    by parsing \include, \bibliography, \bibliographystyle,
    \input, etc.

    If nothing was found, returns an empty list.'''

    s = open(f).read()

    # Find the .tex files.
    texs = []
    for i in re.finditer(r"""[^%]\\include\{(.*)\}""", s):
        res = i.groups()[0]
        # just looking for a '.' separating filename and extension
        if res[-4:-3] == ".":
            texs.append(res)
        else:
            texs.append(res+'.tex')

    # Find the .bib files.
    bibs = []
    for i in re.finditer(r"""[^%]\\bibliography\{(.*)\}""", s):
        bibs.append(i.groups()[0]+'.bib')

    # Find the styles.
    styles = []
    for i in re.finditer(r"""[^%]\\bibliographystyle\{(.*)\}""", s):
        styles.append(i.groups()[0]+'.bst')

    # Find the document class description file
    docclass = []
    for i in re.finditer(r"""[^%]\\documentclass\{(.*)\}""", s):
        docclass.append(i.groups()[0]+'.cls')

    # Look for any inputs.
    inputs = []
    for i in re.finditer(r"""[^%]\\input\{(.*)\}""", s):
        res = i.groups()[0]
        # just looking for a '.' separating filename and extension
        if res[-4:-3] == ".":
            texs.append(res)
        else:
            texs.append(res+'.tex')

    # Here is everything that was referenced in f:
    return texs + bibs + styles + docclass + inputs

def find_figures(f):
    '''Returns a list of figures found in the file.  Only
    looks in .tex files.  If not a .tex file or no figures found,
    returns an empty list.'''

    # Short circuit if not a .tex file.
    if f[-4:] != '.tex':
        return []

    includegraphics = r"""[^%].*\\includegraphics\[.*\]\{([^\}]*)\}"""
    figures = []
    s = open(f).read()
    matches = re.finditer(includegraphics, s)

    for match in matches:
        basename = match.groups()[0]
        if basename[-4] == '.':
            # that is, it has an extension already.
            # This is for things like .png images.
            figures.append(basename)
        else:
            figures.append(basename + '.pdf')
            figures.append(basename + '.eps')

    return figures

def latex_files(start_file):
    """
    Find all LaTeX files referenced from the main start_file, up to two levels deep.
    """

    file_list = find_references(start_file)
    # Don't forget to add the start_file .tex file.
    file_list.append(start_file)

    # For each of those that main.tex referenced, look for more.
    # These are files referenced two levels deep.

    for f in file_list:
        if f[-4:] != '.tex':
            continue
        file_list.extend(find_references(f))

    return file_list

def list_figures(file_list):
    # Now look for graphics.

    figures = []
    for f in file_list:
        figures.extend(find_figures(f))

    return figures

def create_archive(fname, file_list):
    tarball = tarfile.open(fname, 'w:gz')
    for path in file_list:
        print path
        tarball.add(path)
    tarball.close()

def old_main(argv):
    main = argv[1]
    tarfn = argv[2]

    projectdir, main = os.path.split(main)
    if projectdir == '':
        projectdir = os.getcwd()

    keepers = latex_files(main)

    figures = list_figures(keepers)

    #paths = [os.path.join(projectdir, i) for i in keepers + figures]
    paths = keepers + figures

    create_archive(tarfn, paths)

def main(start_file):
    t_files = latex_files(start_file)
    figures = list_figures(t_files)

    missing_figures = filter(lambda(f): not os.path.isfile(f), figures)
    pprint(missing_figures)

if __name__ == "__main__":
    if len(sys.argv) > 1:
        main(sys.argv[1])
    else:
        print "Usage: find_figures.py main.tex"

    # oldmain(sys.argv)