X-Git-Url: https://git.mdrn.pl/librarian.git/blobdiff_plain/b92b58ba86f08f04b4f0436479d3d73ce0c03f00..e7418c1630ea9b12415edc4ac1fa9e8c08679ded:/scripts/book2partner diff --git a/scripts/book2partner b/scripts/book2partner index 136fffc..f1892bb 100755 --- a/scripts/book2partner +++ b/scripts/book2partner @@ -4,162 +4,20 @@ # This file is part of Librarian, licensed under GNU Affero GPLv3 or later. # Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information. # -import os.path +import inspect import optparse -from copy import deepcopy -from lxml import etree +import os +import sys -from librarian import epub, pdf, DirDocProvider, ParseError, cover -from librarian.dcparser import BookInfo - - -def utf_trunc(text, limit): - """ truncates text to at most `limit' bytes in utf-8 """ - if text is None: - return text - orig_text = text - if len(text.encode('utf-8')) > limit: - newlimit = limit - 3 - while len(text.encode('utf-8')) > newlimit: - text = text[:(newlimit - len(text.encode('utf-8'))) / 4] - text += '...' - return text - - -def virtualo(filenames, output_dir, verbose): - xml = etree.fromstring(""" - """) - product = etree.fromstring(""" - - - - - - - Jan - Kowalski - - - 0.0 - PL - """) - - try: - for main_input in input_filenames: - if options.verbose: - print main_input - path, fname = os.path.realpath(main_input).rsplit('/', 1) - provider = DirDocProvider(path) - slug, ext = os.path.splitext(fname) - - outfile_dir = os.path.join(output_dir, slug) - os.makedirs(os.path.join(output_dir, slug)) - - info = BookInfo.from_file(main_input) - - product_elem = deepcopy(product) - product_elem[0].text = utf_trunc(slug, 100) - product_elem[1].text = utf_trunc(info.title, 255) - product_elem[2].text = utf_trunc(info.description, 255) - product_elem[3].text = utf_trunc(info.source_name, 3000) - product_elem[4][0][0].text = utf_trunc(u' '.join(info.author.first_names), 100) - product_elem[4][0][1].text = utf_trunc(info.author.last_name, 100) - xml.append(product_elem) - - cover.VirtualoCover( - u' '.join(info.author.first_names + (info.author.last_name,)), - info.title - ).save(os.path.join(outfile_dir, slug+'.jpg')) - outfile = os.path.join(outfile_dir, '1.epub') - outfile_sample = os.path.join(outfile_dir, '1.sample.epub') - epub.transform(provider, file_path=main_input, output_file=outfile) - epub.transform(provider, file_path=main_input, output_file=outfile_sample, sample=25) - except ParseError, e: - print '%(file)s:%(name)s:%(message)s' % { - 'file': main_input, - 'name': e.__class__.__name__, - 'message': e.message - } - - xml_file = open(os.path.join(output_dir, 'import_products.xml'), 'w') - xml_file.write(etree.tostring(xml, pretty_print=True, encoding=unicode).encode('utf-8')) - xml_file.close() - - -def prestigio(filenames, output_dir, verbose): - try: - for main_input in input_filenames: - if options.verbose: - print main_input - path, fname = os.path.realpath(main_input).rsplit('/', 1) - provider = DirDocProvider(path) - slug, ext = os.path.splitext(fname) - - if output_dir != '': - try: - os.makedirs(output_dir) - except: - pass - outfile = os.path.join(output_dir, slug + '.epub') - epub.transform(provider, file_path=main_input, output_file=outfile, - cover=cover.PrestigioCover, flags=('less-advertising',)) - except ParseError, e: - print '%(file)s:%(name)s:%(message)s' % { - 'file': main_input, - 'name': e.__class__.__name__, - 'message': e.message - } - - -def prestigio_pdf(filenames, output_dir, verbose): - try: - for main_input in input_filenames: - if options.verbose: - print main_input - path, fname = os.path.realpath(main_input).rsplit('/', 1) - provider = DirDocProvider(path) - slug, ext = os.path.splitext(fname) - - if output_dir != '': - try: - os.makedirs(output_dir) - except: - pass - outfile = os.path.join(output_dir, slug + '.pdf') - pdf.transform(provider, file_path=main_input, output_file=outfile, - cover=cover.PrestigioCover, verbose=options.verbose, flags=('less-advertising',)) - except ParseError, e: - print '%(file)s:%(name)s:%(message)s' % { - 'file': main_input, - 'name': e.__class__.__name__, - 'message': e.message - } - - -def bookoteka(filenames, output_dir, verbose): +from librarian import packagers +try: + from collections import OrderedDict +except ImportError: try: - for main_input in input_filenames: - if options.verbose: - print main_input - path, fname = os.path.realpath(main_input).rsplit('/', 1) - provider = DirDocProvider(path) - slug, ext = os.path.splitext(fname) - - if output_dir != '': - try: - os.makedirs(output_dir) - except: - pass - outfile = os.path.join(output_dir, slug + '.epub') - epub.transform(provider, file_path=main_input, output_file=outfile, - cover=cover.BookotekaCover) - except ParseError, e: - print '%(file)s:%(name)s:%(message)s' % { - 'file': main_input, - 'name': e.__class__.__name__, - 'message': e.message - } - + from django.utils.datastructures import SortedDict + OrderedDict = SortedDict + except ImportError: + OrderedDict = dict if __name__ == '__main__': @@ -173,26 +31,54 @@ if __name__ == '__main__': help='print status messages to stdout') parser.add_option('-O', '--output-dir', dest='output_dir', metavar='DIR', default='', help='specifies the directory for output') - parser.add_option('--bookoteka', action='store_true', dest='bookoteka', default=False, - help='prepare files for Bookoteka') - parser.add_option('--virtualo', action='store_true', dest='virtualo', default=False, - help='prepare files for Virtualo API') - parser.add_option('--prestigio', action='store_true', dest='prestigio', default=False, - help='prepare files for Prestigio') - parser.add_option('--prestigio-pdf', action='store_true', dest='prestigio_pdf', default=False, - help='prepare PDF files for Prestigio') + parser.add_option('-f', '--force-overwrite', + action='store_true', + dest='overwrite', + default=False, + help='rebuild the file even if it already exists') + parser.add_option('-p', '--packages', + dest='packages', + metavar='package,...', + default='', + help='lists packages to build') + parser.add_option('-m', '--packages-modules', + dest='packages_modules', metavar='path.to.module,...', + default='librarian.partners', + help='modules with packages definitions to load') + parser.add_option('-l', '--list-packages', + action='store_true', + dest='list_packages', + default=False, + help='lists available packages') options, input_filenames = parser.parse_args() - - if len(input_filenames) < 1: + packages = OrderedDict() + + sys.path.insert(0, os.getcwd()) + for module_name in options.packages_modules.split(','): + if not module_name: + continue + module = __import__(module_name, globals(), locals(), ['*']) + for package_name in dir(module): + package = getattr(module, package_name) + if inspect.isclass(package) and issubclass(package, packagers.Packager): + packages[package_name] = package + if not packages: + print 'No packages found!' + + if options.list_packages: + print 'Available packages:' + for package_name, package in packages.items(): + print ' ', package_name + exit(0) + + if len(input_filenames) < 1 or not options.packages: parser.print_help() exit(1) - if options.bookoteka: - bookoteka(input_filenames, options.output_dir, options.verbose) - if options.virtualo: - virtualo(input_filenames, options.output_dir, options.verbose) - if options.prestigio: - prestigio(input_filenames, options.output_dir, options.verbose) - if options.prestigio_pdf: - prestigio_pdf(input_filenames, options.output_dir, options.verbose) + used_packages = [packages[p] for p in options.packages.split(',')] + for package in used_packages: + if options.verbose: + print 'Package:', package.__name__ + package.prepare(input_filenames, + options.output_dir, options.verbose, options.overwrite)