def do_single_file(file_name, print_xml, write_xml_dir):
arxiv_id, arxiv_version = arxivid.filenameToArxivAndVersion(file_name)
if arxiv_id is None:
print('WARN: could not determine arXiv identifier for', file_name)
arxiv_id = '<unknown>'
arxiv_version = 0
Log.reset()
Statistics.begin_item(arxiv_id)
if file_has_suffix(file_name, '.pdf'):
Statistics.count('1) pdf')
succ = True
else:
Statistics.count('2) processed')
parser = process_article(file_name)
if parser is not None:
succ = parser['success']
bib_refs = parser['refs']
else:
succ = False
bib_refs = []
if str_contains_one_of(arxiv_id, ['gr-qc', 'hep-']):
Statistics.count('hep-processed')
if succ:
Statistics.count('hep-success')
if succ:
print('-success--------')
Statistics.count('3) success')
else:
print('-fail-----------')
Statistics.count('4) fail')
show_ref = False
if succ and show_ref:
for bib_ref in bib_refs:
print(bib_ref.key, 'with', bib_ref.cite_count,
'citations in paper')
if len(bib_ref.bib_info) == 0:
print('no reference')
else:
print(bib_ref.bib_info_as_str(keep_comments=True))
if succ and (print_xml or write_xml_dir):
xml = Element('article')
SubElement(xml, 'id').text = arxiv_id
if arxiv_version > 0:
SubElement(xml, 'version').text = str(arxiv_version)
refs = SubElement(xml, 'refs')
for bib_ref in bib_refs:
bib_text = bib_ref.bib_info_as_str(keep_comments=True)
if len(bib_text) != 0:
ncites = bib_ref.cite_count
if ncites < 1:
ncites = 1
ref = SubElement(refs,
'ref',
order=str(bib_ref.ref_order_num),
freq=str(ncites))
ref.text = bib_text
if print_xml:
print(tostring(xml))
if isinstance(write_xml_dir, str):
if arxiv_id != '<unknown>':
xml_file_name = os.path.join(
write_xml_dir,
arxiv_id.replace('/', '') + '.xml')
else:
fname = os.path.split(file_name)[1]
if fname.rfind('.') > 0:
fname = fname[:fname.rfind('.')]
xml_file_name = write_xml_dir + '/' + fname + '.xml'
file_obj = open(xml_file_name, 'wb')
file_obj.write(tostring(xml, encoding='utf-8'))
file_obj.close()
Statistics.end_item()
return succ
def do_single_file(file_name, print_xml, write_xml_dir):
arxiv_id, arxiv_version = arxivid.filenameToArxivAndVersion(file_name)
if arxiv_id is None:
print('WARN: could not determine arXiv identifier for', file_name)
arxiv_id = '<unknown>'
arxiv_version = 0
Log.reset()
Statistics.begin_item(arxiv_id)
if file_has_suffix(file_name, '.pdf'):
Statistics.count('1) pdf')
succ = True
else:
Statistics.count('2) processed')
parser = process_article(file_name)
if parser is not None :
succ = parser['success']
bib_refs = parser['refs']
else :
succ = False
bib_refs = []
if str_contains_one_of(arxiv_id, ['gr-qc', 'hep-']):
Statistics.count('hep-processed')
if succ:
Statistics.count('hep-success')
if succ:
print('-success--------')
Statistics.count('3) success')
else:
print('-fail-----------')
Statistics.count('4) fail')
show_ref = False
if succ and show_ref:
for bib_ref in bib_refs:
print(bib_ref.key, 'with', bib_ref.cite_count, 'citations in paper')
if len(bib_ref.bib_info) == 0:
print('no reference')
else:
print(bib_ref.bib_info_as_str(keep_comments=True))
if succ and (print_xml or write_xml_dir):
xml = Element('article')
SubElement(xml, 'id').text = arxiv_id
if arxiv_version > 0:
SubElement(xml, 'version').text = str(arxiv_version)
refs = SubElement(xml, 'refs')
for bib_ref in bib_refs:
bib_text = bib_ref.bib_info_as_str(keep_comments=True)
if len(bib_text) != 0:
ncites = bib_ref.cite_count
if ncites < 1:
ncites = 1
ref = SubElement(refs, 'ref', order=str(bib_ref.ref_order_num), freq=str(ncites))
ref.text = bib_text
if print_xml:
print(tostring(xml))
if isinstance(write_xml_dir, str):
if arxiv_id != '<unknown>':
xml_file_name = os.path.join(write_xml_dir, arxiv_id.replace('/', '') + '.xml')
else:
fname = os.path.split(file_name)[1]
if fname.rfind('.') > 0:
fname = fname[:fname.rfind('.')]
xml_file_name = write_xml_dir + '/' + fname + '.xml'
file_obj = open(xml_file_name, 'wb')
file_obj.write(tostring(xml, encoding='utf-8'))
file_obj.close()
Statistics.end_item()
return succ
metavar='<dir>',
help='destination directory to write XML output files')
cmd_parser.add_argument('--failed',
metavar='<file>',
help='output file to write list of failed files')
cmd_parser.add_argument('files', nargs='+', help='input files')
args = cmd_parser.parse_args()
# print date stamp
timeStart = datetime.datetime.now()
print('[ptex] started processing at', str(timeStart))
print('given', len(args.files), 'files, first file:', args.files[0])
print('================')
Statistics.clear('article')
# build list of files to process
file_list = buildFileList(args.filelist, args.files)
# ensure the destination directory exists
if args.write_xml is not None and os.path.exists(args.write_xml):
try:
os.makedirs(args.write_xml)
except:
pass
# process the files
failed_files = []
for file_name in file_list:
success = do_single_file(file_name, args.print_xml, args.write_xml)
cmd_parser = argparse.ArgumentParser(description='Parse TeX/LaTeX to find references.')
cmd_parser.add_argument('--filelist', action='store_true', help='file names on the command line each contain a list of files to process')
cmd_parser.add_argument('--print-xml', action='store_true', help='print XML output to stdout')
cmd_parser.add_argument('--write-xml', metavar='<dir>', help='destination directory to write XML output files')
cmd_parser.add_argument('--failed', metavar='<file>', help='output file to write list of failed files')
cmd_parser.add_argument('files', nargs='+', help='input files')
args = cmd_parser.parse_args()
# print date stamp
timeStart = datetime.datetime.now()
print('[ptex] started processing at', str(timeStart))
print('given', len(args.files), 'files, first file:', args.files[0])
print('================')
Statistics.clear('article')
# build list of files to process
file_list = buildFileList(args.filelist, args.files)
# ensure the destination directory exists
if args.write_xml is not None and os.path.exists(args.write_xml):
try:
os.makedirs(args.write_xml)
except:
pass
# process the files
failed_files = []
for file_name in file_list:
success = do_single_file(file_name, args.print_xml, args.write_xml)