From b4ee8f47bb93523c8375e64742b1c769a8d90ac6 Mon Sep 17 00:00:00 2001
From: kthoden <kthoden@mpiwg-berlin.mpg.de>
Date: Thu, 17 Dec 2020 10:58:24 +0100
Subject: [PATCH] Add XML test suite

---
 testxml.py | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100644 testxml.py

diff --git a/testxml.py b/testxml.py
new file mode 100644
index 0000000..9a3de81
--- /dev/null
+++ b/testxml.py
@@ -0,0 +1,63 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8; mode: python -*-
+
+"""A test suite for all sorts of XML modifications."""
+
+from lxml import etree
+
+NSMAP = { "tei" : "http://www.tei-c.org/ns/1.0",
+          "eoa" : "http://www.edition-open-access.de/ns"}
+
+def remove_namespace(doc, namespace):
+    """Remove namespace in the passed document in place.
+
+    Thank you, https://homework.nwsnet.de/releases/45be/
+    """
+
+    ns = u'{%s}' % namespace
+    nsl = len(ns)
+    for elem in doc.getiterator():
+        if elem.tag.startswith(ns):
+            elem.tag = elem.tag[nsl:]
+# def remove_namespace ends here
+
+# example (import ElementTree as ET)
+# elem = ET.fromstring(some_xml_string)
+# remove_namespace(elem, u'http://earth.google.com/kml/2.0')
+
+ab_string = """<a>A Text <b>B Text</b>B Tail.</a>"""
+cde_string = """<c><d/>D Tail <e>E Text</e>E Tail.</c>"""
+fragment_string = """<p xmlns="http://www.tei-c.org/ns/1.0" xmlns:tei="http://www.tei-c.org/ns/1.0">Klein <hi rend="italic">anfangen</hi> weiter.</p>"""
+fragment_string2 = """<p xmlns="http://www.tei-c.org/ns/1.0">Klein <hi rend="italic">anfangen</hi> weiter.</p>"""
+
+ab = etree.fromstring(ab_string)
+cde = etree.fromstring(cde_string)
+fragment = etree.fromstring(fragment_string)
+fragment2 = etree.fromstring(fragment_string2)
+
+xmlbit = fragment2
+
+remove_namespace(xmlbit, NSMAP['tei'])
+
+first_text = xmlbit.text
+output = f"{first_text}"
+fchildren = xmlbit.getchildren()
+
+for child in fchildren:
+    remove_namespace(child, NSMAP['tei'])
+    ct = etree.tostring(child).decode('utf-8')
+    forget = f"{ct[:]}"
+    print(forget, "forget")
+    geton = etree.fromstring(forget)
+    if geton.tag == "hi":
+        print("yes")
+        if geton.get("rend") == "italic":
+            geton.tag = "{}em"
+        del geton.attrib["rend"]
+        print(geton.tag)
+    else:
+        print("no", geton.tag)
+
+    output += f"{etree.tostring(geton).decode('utf-8')}"
+
+print(output, "end")