答辩模板

在华师大官网上有相关的答辩模板可使用：https://www.ecnu.edu.cn/wzcd/xxgk/xxbs.htm。

如果使用作者改进后的模板文件，在这里下载修改后华东师范大学模板。

文件打印

打印如果需要区分彩色和黑白页以节约成本，可尝试使用本文中的脚本完成。

用法：

完整参数：

this_script_name.py [OPTIONS] colorfy_document.pdf

Options:

  • -m Write out the file in multiple parts rather than a PDF for each different section;
  • -s option chooses simplex rather than duplex output;
  • -v verbose.

Python文件：

#!/usr/bin/env python
# Install gs and pdftk
# Run: python this_script_name.py colorfy_document.pdf              
# BWs ends with `_bwsplit.pdf`, while colors ends with `_colorsplit.pdf`

import fetch_num
import os, os.path, sys, string, re, tempfile, shutil, getopt
threshold=20                                           # Recommended number, to define the distance between R and G / R and B for each pixel.
def a2b(x):
    """Turn ascii into bytes for Python 3, in way that works with Python 2"""
    try:
        return bytes(x)
    except:
        return bytes(x, 'ascii')


def iscolorppm(filename):
    """Does the PPM file contain any non-grayscale colors?"""
    file = open(filename, 'rb')
    # Ugly: I read the whole file into RAM, and copy it needlessly a lot
    data = file.read()
    file.close()

    # PPM is a *very* liberal file format. It allows comments anywhere in the
    # header, even in the middle of tokens.
    comments_re = re.compile(a2b('^([^ \t\n]*)#[^\n]*\n'))
    split_re = re.compile(a2b('^([ \t\n]|#[^\n]*\n)+([^ \t\n#])'))
    tok_re = re.compile(a2b('^([^ \t\n]*)([ \t\n].*)'), re.DOTALL)
    toks = []
    while len(toks) < 4:
        while split_re.match(data):
            data = split_re.sub(r'\2', data)
        while comments_re.match(data):
            data = comments_re.sub(r'\1', data)
        (tok, data) = tok_re.match(data).groups()
        toks.append(tok)
    magic = toks[0]
    (width, height, max_color) = map(int, toks[1:])
    data = data[1:]

    if magic == b'P3':
        binary = False
    elif magic == b'P6':
        binary = True
    else:
        print("%s is not a valid PPM file" % filename)
        sys.exit(1)

    # Massage data so adjacent triples should have the same value in b/w images
    data_len = width*height*3
    if binary:
        if int(max_color) > 255:
            # Untested. Each intensity is in two bytes.
            data_len *= 2
            data = data[1:data_len:2] + data[:data_len:2]
    else:
        data = [int(x) for x in data.split()]

    if len(data) < data_len:
        print('PPM file is truncated?')
        sys.exit(1)

    triples = zip(data[0:data_len:3], data[1:data_len:3], data[2:data_len:3])
    
    black_and_white = all((abs(a-b)<threshold and abs(a-c)<threshold for (a,b,c) in triples))
    return not black_and_white


def pdfcolorsplit(file, doublesided, merge, verbose):
    # Convert to PPMs
    if verbose:
        print('Analyzing %s...' % file)
    tmpdir = tempfile.mkdtemp(prefix = 'pdfcs_')
    gs_opts = '-sDEVICE=ppmraw -dBATCH -dNOPAUSE -dSAFE -r20'
    if not verbose:
        gs_opts += ' -q'
    os.system('GSWIN64C ' + gs_opts + ' -sOutputFile="%s" "%s"' \
            % (os.path.join(tmpdir, 'tmp%06d.ppm'), file))
    PPMs = os.listdir(tmpdir)
    PPMs.sort()
    PPMpath = [os.path.join(tmpdir, x) for x in PPMs]

    # Judge colors
    total_pages = len(PPMs)
    logical_numbers=fetch_num.getPdfLogicalNumbers(file,total_pages)
    iscolor = [iscolorppm(x) for x in PPMpath]
    if doublesided:
        # Treat as color those b/w pages that share a sheet with a color page
        iscolorpair = [x or y for (x,y) in zip(iscolor[::2], iscolor[1::2])]
        iscolor[:2*len(iscolorpair):2] = iscolorpair
        iscolor[1::2] = iscolorpair

    shutil.rmtree(tmpdir)
    # Construct page range strings
    flips = [x for x in range(2,total_pages+1) if iscolor[x-1] != iscolor[x-2]]
    if not flips:
        if verbose:
            print('No splitting needs to be done, skipping %s' % file)
        return
    edges = [1] + flips + [total_pages+1]
    ranges = ['%d-%d' % (x,y-1) for (x,y) in zip(edges[:-1], edges[1:])]

    # Finally output split files
    if verbose:
        print('Outputing splits as new pdf files...')
    base_name = file
    if base_name.lower().endswith('.pdf'):
        base_name = base_name[:-4]
    suffixes = ['_bwsplit.pdf', '_colorsplit.pdf']
    # jobs is a seq of (range, filename) pairs, e.g. ('1-3', 'colorbits.pdf')
    if merge:
        jobs = ((' '.join(ranges[0::2]), base_name + suffixes[iscolor[0]]),\
                (' '.join(ranges[1::2]), base_name + suffixes[not iscolor[0]]))
    else:
        jobs = [(r, '%s_%03d%s' % (base_name,n+1,suffixes[(n+iscolor[0])%2])) \
                for (n,r) in enumerate(ranges)]
    for (pages, name) in jobs:
        if verbose:
            print('pdftk "%s" cat %s output "%s"' % (file, pages, name))
        os.system('pdftk "%s" cat %s output "%s"' % (file, pages, name))

def usage():
    progname = os.path.basename(sys.argv[0])
    print('Usage: %s [OPTIONS] <PDF-file(s)>' % progname)
    print('')
    print('Splits PDF files into color and black and white sections.')
    print('')
    print('Options:')
    print('   -m Write out the file in multiple parts rather than a PDF for')
    print('      each different section')
    print('   -s option chooses simplex rather than duplex output')
    print('   -v verbose.')

def main():
    try:
        opt_pairs, filenames = getopt.gnu_getopt(sys.argv[1:], "hvpms", ["help"])
    except getopt.GetoptError as err:
        print(str(err))
        usage()
        sys.exit(1)
    if opt_pairs:
        opts = list(zip(*opt_pairs))[0]
    else:
        opts = []
    if ('-h' in opts) or ('--help' in opts) or (not filenames):
        usage()
        sys.exit()
    verbose = '-v' in opts
    use_pdftoppm = '-p' in opts
    merge = '-m' not in opts
    doublesided = '-s' not in opts
    for file in filenames:
        pdfcolorsplit(file, doublesided, merge, verbose)

if __name__ == "__main__":
    main()