mirror of
https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git
synced 2024-12-26 04:44:18 +00:00
48 lines
1.7 KiB
Python
Executable File
48 lines
1.7 KiB
Python
Executable File
#!/usr/bin/env python3.5
|
|
# coding=utf-8
|
|
|
|
from xml.sax.saxutils import escape
|
|
from argparse import ArgumentParser
|
|
import xml.etree.ElementTree as ET
|
|
|
|
parser = ArgumentParser(description='Merges hOCR files to one P5 file.')
|
|
parser.add_argument('i', metavar='hOCR-sourcefile', nargs='+')
|
|
parser.add_argument('o', metavar='TEI-destfile',)
|
|
args = parser.parse_args()
|
|
|
|
output_file = open(args.o, 'w')
|
|
output_file.write(
|
|
'<?xml version="1.0" encoding="UTF-8"?>\n'
|
|
+ '<TEI xmlns="http://www.tei-c.org/ns/1.0" xml:id="dtabf">\n'
|
|
+ ' <teiHeader>\n'
|
|
+ ' <fileDesc>\n'
|
|
+ ' <titleStmt/>\n'
|
|
+ ' <publicationStmt/>\n'
|
|
+ ' <sourceDesc/>\n'
|
|
+ ' </fileDesc>\n'
|
|
+ ' <encodingDesc/>\n'
|
|
+ ' <profileDesc/>\n'
|
|
+ ' </teiHeader>\n'
|
|
+ ' <text>\n'
|
|
+ ' <body>\n'
|
|
)
|
|
for index, input_file in enumerate(args.i):
|
|
tree = ET.parse(input_file)
|
|
output_file.write(' <pb n="%i"/>\n' % (index + 1))
|
|
for para in tree.findall('.//*[@class="ocr_par"]'):
|
|
output_file.write(' <p>\n')
|
|
for line in para.findall('.//*[@class="ocr_line"]'):
|
|
first_word_in_line = True
|
|
for word in line.findall('.//*[@class="ocrx_word"]'):
|
|
if word.text is not None:
|
|
output_file.write((' ' if first_word_in_line else ' ') + escape(word.text.strip()))
|
|
first_word_in_line = False
|
|
if not first_word_in_line:
|
|
output_file.write('<lb/>\n')
|
|
output_file.write(' </p>\n')
|
|
output_file.write(
|
|
' </body>\n'
|
|
+ ' </text>\n'
|
|
+ '</TEI>')
|
|
output_file.close()
|