Add prototype

2025-06-15 10:30:40 +00:00 · 2019-06-03 14:57:09 +02:00
parent b8fa8f47ab
commit 86557443a2
43 changed files with 24638 additions and 53 deletions
--- a/vre_ocr_node/hocrtotei
+++ b/vre_ocr_node/hocrtotei
@ -0,0 +1,44 @@
+#!/usr/bin/env python3
+# coding=utf-8
+
+import xml.etree.ElementTree as ET
+from xml.sax.saxutils import escape
+import os
+import sys
+
+input_files = filter(lambda x: x.endswith(".hocr"), sorted(os.listdir(sys.argv[1])))
+output_file = open(sys.argv[2], "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 input_file in input_files:
+    tree = ET.parse(os.path.join(sys.argv[1], input_file))
+    output_file.write('            <pb n="%s"/>\n' % (input_file.split(".")[0].split("-")[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()