def main(argv=None): args = docopt(__doc__, argv=argv, version='OpenAccess_EPUB v.' + __version__, options_first=True) if args['--images'] is not None and '*' not in args['--images']: sys.exit('Argument for --images option must contain "*"') #Basic logging configuration oae_logging.config_logging(args['--no-log-file'], args['--log-to'], args['--log-level'], args['--silent'], args['--verbosity']) #Get a logger, the 'openaccess_epub' logger was set up above command_log = logging.getLogger('openaccess_epub.commands.batch') #Load the config module, we do this after logging configuration config = openaccess_epub.utils.load_config_module() for directory in args['DIR']: for xml_file in files_with_ext('.xml', directory, recursive=args['--recursive']): #We have to temporarily re-base our log while utils work if not args['--no-log-file']: oae_logging.replace_filehandler( logname='openaccess_epub', new_file='temp.log', level=args['--log-level'], frmt=oae_logging.STANDARD_FORMAT) command_log.info('Processing input: {0}'.format(xml_file)) root_name = openaccess_epub.utils.file_root_name(xml_file) abs_input_path = openaccess_epub.utils.get_absolute_path(xml_file) if not args['--no-log-file']: log_name = root_name + '.log' log_path = os.path.join(os.path.dirname(abs_input_path), log_name) #Re-base the log file to the new file location oae_logging.replace_filehandler( logname='openaccess_epub', new_file=log_path, level=args['--log-level'], frmt=oae_logging.STANDARD_FORMAT) #Now we move over to the new log file shutil.move('temp.log', log_path) #Parse the article now that logging is ready parsed_article = Article(abs_input_path, validation=not args['--no-validate']) #Get the output directory if args['--output'] is not None: output_directory = openaccess_epub.utils.get_absolute_path( args['--output']) else: if os.path.isabs(config.default_output): # Absolute remains so output_directory = config.default_output else: # Else rendered relative to input abs_dirname = os.path.dirname(abs_input_path) output_directory = os.path.normpath( os.path.join(abs_dirname, config.default_output)) #The root name must be added on for output output_directory = os.path.join(output_directory, root_name) #Make the call to make_EPUB success = make_EPUB(parsed_article, output_directory, abs_input_path, args['--images'], config_module=config, batch=True) #Cleanup is mandatory command_log.info('Removing {0}'.format(output_directory)) shutil.rmtree(output_directory) if not args['--no-epubcheck'] and success: epub_name = '{0}.epub'.format(output_directory) openaccess_epub.utils.epubcheck(epub_name, config)
def main(argv=None): args = docopt(__doc__, argv=argv, version='OpenAccess_EPUB v.' + __version__, options_first=True) c_file = args['COLLECTION_FILE'] c_file_root = utils.file_root_name(c_file) abs_input_path = utils.get_absolute_path(c_file) if not args['--log-to']: log_to = os.path.join(os.path.dirname(abs_input_path), c_file_root + '.log') else: log_to = args['--log-to'] #Basic logging configuration oae_logging.config_logging(args['--no-log-file'], log_to, args['--log-level'], args['--silent'], args['--verbosity']) command_log = logging.getLogger('openaccess_epub.commands.collection') #Load the config module, we do this after logging configuration config = openaccess_epub.utils.load_config_module() #Quit if the collection file is not there if not os.path.isfile(c_file): command_log.critical('File does not exist {0}'.format(c_file)) sys.exit('Unable to continue') command_log.info('Parsing collection file: {0}'.format(c_file)) with open(c_file, 'r') as f: inputs = [line.strip() for line in f.readlines()] #Get the output directory if args['--output'] is not None: output_directory = utils.get_absolute_path(args['--output']) else: if os.path.isabs(config.default_output): # Absolute remains so output_directory = config.default_output else: # Else rendered relative to input abs_dirname = os.path.dirname(abs_input_path) output_directory = os.path.normpath( os.path.join(abs_dirname, config.default_output)) output_directory = os.path.join(output_directory, c_file_root) command_log.info( 'Processing collection output in {0}'.format(output_directory)) if os.path.isdir(output_directory): utils.dir_exists(output_directory) try: os.makedirs(output_directory) except OSError as err: if err.errno != 17: command_log.exception( 'Unable to recursively create output directories') #Instantiate collection NCX and OPF navigation = Navigation(collection=True) package = Package(collection=True, title=c_file_root) #Copy over the basic epub directory make_epub_base(output_directory) epub_version = None #Iterate over the inputs for xml_file in inputs: xml_path = utils.evaluate_relative_path( os.path.dirname(abs_input_path), xml_file) parsed_article = Article(xml_path, validation=not args['--no-validate']) if epub_version is None: # Only set this once, no mixing! if args['--epub2']: epub_version = 2 elif args['--epub3']: epub_version = 3 else: epub_version = parsed_article.publisher.epub_default navigation.process(parsed_article) package.process(parsed_article) #Get the Digital Object Identifier doi = parsed_article.get_DOI() journal_doi, article_doi = doi.split('/') #Get the images openaccess_epub.utils.images.get_images(output_directory, args['--images'], xml_path, config, parsed_article) parsed_article.publisher.render_content(output_directory, epub_version) if epub_version == 2: navigation.render_EPUB2(output_directory) package.render_EPUB2(output_directory) elif epub_version == 3: navigation.render_EPUB3(output_directory) package.render_EPUB3(output_directory) epub_zip(output_directory) #Cleanup removes the produced output directory, keeps the EPUB if not args['--no-cleanup']: command_log.info('Removing {0}'.format(output_directory)) shutil.rmtree(output_directory) #Running epubcheck on the output verifies the validity of the ePub, #requires a local installation of java and epubcheck. if not args['--no-epubcheck']: epub_name = '{0}.epub'.format(output_directory) openaccess_epub.utils.epubcheck(epub_name, config)
def main(argv=None): args = docopt(__doc__, argv=argv, version='OpenAccess_EPUB v.' + __version__, options_first=True) c_file = args['COLLECTION_FILE'] c_file_root = utils.file_root_name(c_file) abs_input_path = utils.get_absolute_path(c_file) if not args['--log-to']: log_to = os.path.join(os.path.dirname(abs_input_path), c_file_root + '.log') else: log_to = args['--log-to'] #Basic logging configuration oae_logging.config_logging(args['--no-log-file'], log_to, args['--log-level'], args['--silent'], args['--verbosity']) command_log = logging.getLogger('openaccess_epub.commands.collection') #Load the config module, we do this after logging configuration config = openaccess_epub.utils.load_config_module() #Quit if the collection file is not there if not os.path.isfile(c_file): command_log.critical('File does not exist {0}'.format(c_file)) sys.exit('Unable to continue') command_log.info('Parsing collection file: {0}'.format(c_file)) with open(c_file, 'r') as f: inputs = [line.strip() for line in f.readlines()] #Get the output directory if args['--output'] is not None: output_directory = utils.get_absolute_path(args['--output']) else: if os.path.isabs(config.default_output): # Absolute remains so output_directory = config.default_output else: # Else rendered relative to input abs_dirname = os.path.dirname(abs_input_path) output_directory = os.path.normpath(os.path.join(abs_dirname, config.default_output)) output_directory = os.path.join(output_directory, c_file_root) command_log.info('Processing collection output in {0}'.format(output_directory)) if os.path.isdir(output_directory): utils.dir_exists(output_directory) try: os.makedirs(output_directory) except OSError as err: if err.errno != 17: command_log.exception('Unable to recursively create output directories') #Instantiate collection NCX and OPF navigation = Navigation(collection=True) package = Package(collection=True, title=c_file_root) #Copy over the basic epub directory make_epub_base(output_directory) epub_version = None #Iterate over the inputs for xml_file in inputs: xml_path = utils.evaluate_relative_path(os.path.dirname(abs_input_path), xml_file) parsed_article = Article(xml_path, validation=not args['--no-validate']) if epub_version is None: # Only set this once, no mixing! if args['--epub2']: epub_version = 2 elif args['--epub3']: epub_version = 3 else: epub_version = parsed_article.publisher.epub_default navigation.process(parsed_article) package.process(parsed_article) #Get the Digital Object Identifier doi = parsed_article.get_DOI() journal_doi, article_doi = doi.split('/') #Get the images openaccess_epub.utils.images.get_images(output_directory, args['--images'], xml_path, config, parsed_article) parsed_article.publisher.render_content(output_directory, epub_version) if epub_version == 2: navigation.render_EPUB2(output_directory) package.render_EPUB2(output_directory) elif epub_version == 3: navigation.render_EPUB3(output_directory) package.render_EPUB3(output_directory) epub_zip(output_directory) #Cleanup removes the produced output directory, keeps the EPUB if not args['--no-cleanup']: command_log.info('Removing {0}'.format(output_directory)) shutil.rmtree(output_directory) #Running epubcheck on the output verifies the validity of the ePub, #requires a local installation of java and epubcheck. if not args['--no-epubcheck']: epub_name = '{0}.epub'.format(output_directory) openaccess_epub.utils.epubcheck(epub_name, config)
def collection_input(args, config=None): """ Collection Input Mode works to compile multiple articles into a single composite ePub. This is akin to such formats as Collections, Issues, and Omnibus; it may also be useful for those interested in the simple distribution of a reading list, personal publications, or topic reference. Collection Input Mode produces output that is necessarily unlike the output generated by Single or Batch (which is just sequential Single) input modes. The primary difference in output lies with the ePub metadata; as applying metadata from any single article to the whole would be inappropriate. Unlike other input modes, Collection Mode is strictly dependent on the local directory of execution. If there is a file named "order.txt" in the local directory, this file should contain the name of one input XML file on each line; the files will be added to the ePub output by line-order. If there is "order.txt" file, Collection Mode will assume that all XML files are input and the article in order in the collection will be random. Collection Input Mode has default epubcheck behavior, it will place a system call to epubcheck unless specified otherwise (--no-epubcheck or -N flags). """ if config is None: config = get_config_module() try: order = open('order.txt', 'r') except IOError: # No order.txt xml_files = list_xml_files(dir=os.getcwd()) else: #Add all nonempty lines, in order, to the xml_files list xml_files = [i.strip() for i in order.readlines() if i.strip()] order.close() #The output name will be the same as the parent directory name #This will also serve as the dc:title output_name = os.path.split(os.getcwd())[1] #The standard make_epub() method will not work for Collection Mode #So the work done here is an adaptation of it print('Processing output to {0}.epub'.format(output_name)) #Copy files from base_epub to the new output if os.path.isdir(output_name): dir_exists(output_name) epub_base = os.path.join(CACHE_LOCATION, 'base_epub') shutil.copytree(epub_base, output_name) if args.collection is True: try: title_txt = open('title.txt', 'r') except IOError: # No title.txt title = output_name else: title = title_txt.readline().strip() title_txt.close() if not title: title = output_name print('title.txt was empty or title was not on first line!') print('Defaulting to name of parent directory. {0}'.format(title)) else: title = args.collection toc = ncx.NCX(oae_version=__version__, location=output_name, collection_mode=True) myopf = opf.OPF(location=output_name, collection_mode=True, title=title) #Now it is time to operate on each of the xml files for xml_file in xml_files: raw_name = u_input.local_input(xml_file) # is this used? parsed_article = Article(xml_file, validation=args.no_dtd_validation) toc.take_article(parsed_article) myopf.take_article(parsed_article) #Get the Digital Object Identifier doi = parsed_article.get_DOI() journal_doi, article_doi = doi.split('/') #Check for images img_dir = os.path.join(output_name, 'OPS', 'images-{0}'.format(article_doi)) expected_local = 'images-{0}'.format(raw_name) if os.path.isdir(expected_local): utils.images.local_images(expected_local, img_dir) else: article_cache = os.path.join(config.image_cache, journal_doi, article_doi) if os.path.isdir(article_cache): utils.images.image_cache(article_cache, img_dir) else: print('Images for {0} (DOI: {1}) could not be found!'.format(xml_file, doi)) r = input('Try to download them? [Y/n]') if r in ['y', 'Y', '']: os.mkdir(img_dir) utils.images.fetch_plos_images(article_doi, img_dir, parsed_article) if config.use_image_cache: utils.images.move_images_to_cache(img_dir, article_cache) else: sys.exit(1) #TODO: Content stuff if journal_doi == '10.1371': # PLoS's publisher DOI ops_doc = ops.OPSPLoS(parsed_article, output_name) #TODO: Workflow change, parse table of contents from OPS processed document toc.write() myopf.write() utils.epub_zip(output_name) #Running epubcheck on the output verifies the validity of the ePub, #requires a local installation of java and epubcheck. if args.no_epubcheck: epubcheck('{0}.epub'.format(output_name), config)
def main(argv=None): args = docopt(__doc__, argv=argv, version='OpenAccess_EPUB v.' + __version__, options_first=True) if args['--epub3']: epub_version = 3 elif args['--epub2']: epub_version = 2 else: epub_version = None #Basic logging configuration oae_logging.config_logging(args['--no-log-file'], args['--log-to'], args['--log-level'], args['--silent'], args['--verbosity']) #Get a logger, the 'openaccess_epub' logger was set up above command_log = logging.getLogger('openaccess_epub.commands.convert') #Load the config module, we do this after logging configuration config = openaccess_epub.utils.load_config_module() current_dir = os.getcwd() #Our basic flow is to iterate over the args['INPUT'] list for inpt in args['INPUT']: #We have to temporarily re-base our log while input utils do some work if not args['--no-log-file'] and not args['--log-to']: oae_logging.replace_filehandler(logname='openaccess_epub', new_file='temp.log', level=args['--log-level'], frmt=oae_logging.STANDARD_FORMAT) command_log.info('Processing input: {0}'.format(inpt)) #First we need to know the name of the file and where it is if inpt.lower().endswith('.xml'): # This is direct XML file root_name = openaccess_epub.utils.file_root_name(inpt) abs_input_path = openaccess_epub.utils.get_absolute_path(inpt) elif inpt.lower().startswith('doi:'): # This is a DOI root_name = input_utils.doi_input(inpt) abs_input_path = os.path.join(current_dir, root_name + '.xml') elif any(inpt.lower().startswith(i) for i in ['http:', 'https:']): root_name = input_utils.url_input(inpt) abs_input_path = os.path.join(current_dir, root_name + '.xml') else: sys.exit('{0} not recognized as XML, DOI, or URL'.format(inpt)) if not args['--no-log-file'] and not args['--log-to']: log_name = root_name + '.log' log_path = os.path.join(os.path.dirname(abs_input_path), log_name) #Re-base the log file to the new file location oae_logging.replace_filehandler(logname='openaccess_epub', new_file=log_path, level=args['--log-level'], frmt=oae_logging.STANDARD_FORMAT) #Now we move over to the new log file shutil.copy2('temp.log', log_path) os.remove('temp.log') #Now that we should be done configuring logging, let's parse the article parsed_article = Article(abs_input_path, validation=not args['--no-validate']) if parsed_article.publisher is None: command_log.critical( 'Publisher support was not established, aborting') sys.exit(1) #Get the output directory if args['--output'] is not None: output_directory = openaccess_epub.utils.get_absolute_path( args['--output']) else: if os.path.isabs(config.default_output): # Absolute remains so output_directory = config.default_output else: # Else rendered relative to input abs_dirname = os.path.dirname(abs_input_path) output_directory = os.path.normpath( os.path.join(abs_dirname, config.default_output)) #The root name must be added on for output output_directory = os.path.join(output_directory, root_name) #Make the call to make_EPUB success = make_EPUB(parsed_article, output_directory, abs_input_path, args['--images'], config_module=config, epub_version=epub_version) #Cleanup removes the produced output directory, keeps the EPUB if not args['--no-cleanup']: command_log.info('Removing {0}'.format(output_directory)) shutil.rmtree(output_directory) #Running epubcheck on the output verifies the validity of the EPUB, #requires a local installation of java and epubcheck. if not args['--no-epubcheck'] and success: epub_name = '{0}.epub'.format(output_directory) openaccess_epub.utils.epubcheck(epub_name, config)