From 3b171020c3a61d9dce4d8f0422adaf14c2b142af Mon Sep 17 00:00:00 2001
From: Shlomi Fish <shlomif@shlomifish.org>
Date: Thu, 25 Jul 2024 08:52:32 +0300
Subject: [PATCH] consolidate differences in lib/html_unit_test.py

see Freecell Solver site sources and freenode programming FAQ
---
 Tests/fortunes-show-cgi.py  |  2 +-
 Tests/lib/html_unit_test.py | 36 ++++++++++++++++++++++++++++++------
 2 files changed, 31 insertions(+), 7 deletions(-)

diff --git a/Tests/fortunes-show-cgi.py b/Tests/fortunes-show-cgi.py
index f89b46a9f..2eaabd6c6 100755
--- a/Tests/fortunes-show-cgi.py
+++ b/Tests/fortunes-show-cgi.py
@@ -92,7 +92,7 @@ def test_raw_mode(self):
             'type': 'text',
             'fn': 'test_raw_mode',
             'text': resp.text.encode('utf8'),
-        })
+        }, filetype='html')
         doc.has_one(
             "//html/body/div[@class='fortune']/blockquote/" +
             "p[contains(text(), 'recorded')]"
diff --git a/Tests/lib/html_unit_test.py b/Tests/lib/html_unit_test.py
index b66209f3f..47405a5eb 100644
--- a/Tests/lib/html_unit_test.py
+++ b/Tests/lib/html_unit_test.py
@@ -14,7 +14,20 @@
 from os.path import join
 import unittest
 
+from lxml import etree
 from lxml import html
+from lxml.html import XHTML_NAMESPACE
+
+
+XML_NS = "http://www.w3.org/XML/1998/namespace"
+dbns = "http://docbook.org/ns/docbook"
+ns = {
+    "db": dbns,
+    "ncx": "http://www.daisy.org/z3986/2005/ncx/",
+    "xhtml": XHTML_NAMESPACE,
+    "xlink": "http://www.w3.org/1999/xlink",
+    "xml": XML_NS,
+}
 
 
 class HtmlTestsDocQuery:
@@ -30,18 +43,29 @@ def __len__(self):
 
 class HtmlTestsDoc:
     """A single HTML document wrapper"""
-    def __init__(self, harness, fn):
+    def __init__(self, harness, fn, filetype='html'):
+        self.filetype = filetype
         self.harness = harness
         if isinstance(fn, dict):
             assert fn['type'] == 'text'
             self.fn = fn['fn']
-            self.root = html.document_fromstring(html=fn['text'])
+            if filetype == 'html':
+                self.root = html.document_fromstring(html=fn['text'])
+            elif filetype == 'docbook5':
+                assert False
             return
         self.fn = fn
-        self.root = html.parse(fn)
+        if filetype == 'html':
+            self.root = html.parse(fn)
+        elif filetype == 'docbook5':
+            self.root = etree.parse(fn)
 
     def xpath(self, xpath_s):
-        return HtmlTestsDocQuery(self, self.root.xpath(xpath_s))
+        if self.filetype == 'html':
+            return HtmlTestsDocQuery(self, self.root.xpath(xpath_s))
+        elif self.filetype == 'docbook5':
+            return HtmlTestsDocQuery(self, self.root.xpath(
+                xpath_s, namespaces=ns))
 
     def has_count(self, xpath_s, count_, blurb=""):
         """is the length of xpath_s’s results count_"""
@@ -57,8 +81,8 @@ def has_none(self, xpath_s, blurb=""):
 
 
 class TestCase(unittest.TestCase):
-    def doc(self, path):
-        return HtmlTestsDoc(self, path)
+    def doc(self, path, filetype='html'):
+        return HtmlTestsDoc(self, path, filetype=filetype)
 
 
 def _find_htmls(root):