Replace runic XSLT with a python script and tidy cbordump code

Filters records on having value < 256, or an RFC, previously hacked
into the XSLT to produce the last update, with a bit of hand-editing.
Using a python script makes it easier to control the formatting and
other details; for example, severl entries previously had descriptions
that mentioned their RFC, with specific section, to which the XSLT was
adding a redundant mention of the RFC. It is also possible to exploit
C++ string juxtaposition to get tidily-presented string literals,
without having to resort to raw strings.

Task-number: QTBUG-111228
Change-Id: Ibd1c93dc1c88689e78b2b13a6bcb59a003f4df0f
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>

3 files changed, 276 insertions, 201 deletions

diff --git a/examples/corelib/serialization/cbordump/cbortag.py b/examples/corelib/serialization/cbordump/cbortag.py
new file mode 100755
index 0000000000..8634dcdc20
--- /dev/null
+++ b/examples/corelib/serialization/cbordump/cbortag.py
@@ -0,0 +1,188 @@
+#!/bin/env python3
+# Copyright (C) 2023 The Qt Company Ltd.
+# SPDX-License-Identifier: LicenseRef-Qt-Commercial OR BSD-3-Clause
+"""Digest cbor-tags.xml file into code for insertion into main.cpp
+
+See main.cpp's comment on how to regenerate its GENERATED CODE.
+See ./cbortag.py --help for further details on how to invoke.
+You can import this is a module without invoking the script.
+"""
+
+def firstChild(parent, tag):
+    """Return parent's first child element with the given tag."""
+    return next(node for node in parent.childNodes
+                if node.nodeType == parent.ELEMENT_NODE and node.nodeName == tag)
+
+def nodeAttrIs(node, attr, seek):
+    """Checks whether the node has a given value for an attribute
+
+    Takes the node to check, the name of the attribute and the value
+    to check against.  Returns true if the node does have that value
+    for the named attribute."""
+    if node.nodeType != node.ELEMENT_NODE:
+        return False
+    if node.attributes is None or attr not in node.attributes:
+        return False
+    return node.attributes[attr].value == seek
+
+def getRfcValue(node):
+    """Extract RFC reference from an <xref type="rfc" ...> element
+
+    Some of these have a reference including section details as the
+    body of the element, otherwise the data attribute should identify
+    the RFC. If neither is found, an empty string is returned."""
+    if node.childNodes:
+        return node.childNodes[0].nodeValue # Maybe accumulate several children ?
+    if node.attributes is None or 'data' not in node.attributes:
+        return ''
+    return node.attributes['data'].value
+
+def readRegistry(filename):
+    """Handles the XML parsing and returns the relevant parts.
+
+    Single argument is the path to the cbor-tags.xml file; returns a
+    twople of the title element's text and an interator over the
+    record nodes.  Checks some things are as expected while doing so."""
+    from xml.dom.minidom import parse
+    doc = parse(filename).documentElement
+    assert nodeAttrIs(doc, 'id', 'cbor-tags')
+    title = firstChild(doc, 'title').childNodes[0].nodeValue
+    registry = firstChild(doc, 'registry')
+    assert nodeAttrIs(registry, 'id', 'tags')
+    records = (node for node in registry.childNodes if node.nodeName == 'record')
+    return title, records
+
+def digest(record):
+    """Digest a single record from cbor-tags.xml
+
+    If the record is not of interest, returns the twople (None, None).
+    For records of interest, returns (n, t) where n is the numeric tag
+    code of the record and t is a text describing it. If the record,
+    or its semantics field, has an xref child with type="rfc", the RFC
+    mentioned there is included with the text of the semantics; such a
+    record is of interest, provided it has a semantics field and no
+    dash in its value.  Records with a value field containing a dash
+    (indicating a range) are not of interest. Records with a value of
+    256 or above are only of interest if they include an RFC."""
+    data = {}
+    for kid in record.childNodes:
+        if kid.nodeName == 'xref':
+            if not nodeAttrIs(kid, 'type', 'rfc'):
+                continue
+            rfc = getRfcValue(kid)
+            if rfc:
+                # Potentially stomping one taken from semantics
+                data['rfc'] = rfc
+        elif kid.nodeName == 'semantics':
+            text = rfc = ''
+            for part in kid.childNodes:
+                if part.nodeType == kid.TEXT_NODE:
+                    text += part.nodeValue
+                elif part.nodeType == kid.ELEMENT_NODE:
+                    if part.nodeName != 'xref' or not nodeAttrIs(part, 'type', 'rfc'):
+                        continue # potentially append content to text
+                    assert not rfc, ('Duplicate RFC ?', rfc, part)
+                    rfc = getRfcValue(part)
+            if rfc:
+                if text.endswith('()'):
+                    text = text[:-2].rstrip()
+                if 'rfc' not in data:
+                    data['rfc'] = rfc
+            data['semantics'] = ' '.join(text.split())
+        elif kid.nodeName == 'value':
+            data['value'] = kid.childNodes[0].nodeValue
+    text = data.get('semantics')
+    if not text or 'value' not in data or '-' in data['value']:
+        return None, None
+    value = int(data['value'])
+    if 'rfc' in data:
+        rfc = data["rfc"].replace('rfc', 'RFC')
+        text = f'{text} [{rfc}]'
+    elif value >= 256:
+        return None, None
+    return value, text
+
+def entries(records):
+    """Digest each record of interest into a value and text.
+
+    The value and text form the raw material of the tagDescriptions
+    array in main.cpp; see digest for which records are retained."""
+    for record in records:
+        value, text = digest(record)
+        if value is not None:
+            yield value, text
+
+def marginBound(text, prior, left, right):
+    """Split up a string literal for tidy display.
+
+    The first parameter, text, is the content of the string literal;
+    quotes shall be added.  It may be split into several fragments,
+    each quoted, so as to abide by line length constraints.
+
+    The remaining parameters are integers: prior is the text already
+    present on the line before text is to be added; left is the width
+    of the left margin for all subsequent lines; and right is the
+    right margin to stay within, where possible. The returned string
+    is either a space with the whole quoted text following, to fit on
+    the line already started to length prior, or a sequence of quoted
+    strings, each preceded by a newline and indent of width left."""
+    if prior + 3 + len(text) < right: # 1 for space, 2 for quotes
+        return f' "{text}"'
+    width = right - left - 2 # 2 for the quotes
+    words = iter(text.split(' '))
+    lines, current = [''], [next(words)]
+    for word in words:
+        if len(word) + sum(len(w) + 1 for w in current) > width:
+            line = ' '.join(current)
+            lines.append(f'"{line}"')
+            current = ['', word]
+        else:
+            current.append(word)
+    line = ' '.join(current)
+    lines.append(f'"{line}"')
+    return ('\n' + ' ' * left).join(lines)
+
+def main(argv, speak):
+    """Takes care of driving the process.
+
+    Takes the command-line argument list (whose first entry is the
+    name of this script) and standard output (or compatible stream of
+    your choosing) to which to write data. If the --out option is
+    specified in the arguments, the file it names is used in place of
+    this output stream."""
+    from argparse import ArgumentParser, ArgumentDefaultsHelpFormatter
+    parser = ArgumentParser(
+        description='Digest cbor-tags.xml into code to insert in main.cpp',
+        formatter_class=ArgumentDefaultsHelpFormatter)
+    parser.add_argument('path', help='path of the cbor-tags.xml file',
+                        default='cbor-tags.xml')
+    parser.add_argument('--out', help='file to write instead of standard output')
+    args = parser.parse_args(argv[1:])
+    emit = (open(args.out) if args.out else speak).write
+
+    title, records = readRegistry(args.path)
+    emit(f"""\
+struct CborTagDescription
+{{
+    QCborTag tag;
+    const char *description;    // with space and parentheses
+}};
+
+// {title}
+static const CborTagDescription tagDescriptions[] = {{
+    // from https://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml
+""")
+
+    for value, text in sorted(entries(records)):
+        prior = f'    {{ QCborTag({value}),'
+        body = marginBound(f' ({text})', len(prior), 6, 96)
+        emit(f"{prior}{body} }},\n")
+
+    emit("""\
+    { QCborTag(-1), nullptr }
+};
+""")
+
+if __name__ == '__main__':
+    import sys
+    sys.exit(main(sys.argv, sys.stdout))
diff --git a/examples/corelib/serialization/cbordump/main.cpp b/examples/corelib/serialization/cbordump/main.cpp
index 106c408cbc..4c02abd304 100644
--- a/examples/corelib/serialization/cbordump/main.cpp
+++ b/examples/corelib/serialization/cbordump/main.cpp
@@ -17,18 +17,12 @@
 /*
  * To regenerate:
  *  curl -O https://www.iana.org/assignments/cbor-tags/cbor-tags.xml
- *  xsltproc tag-transform.xslt cbor-tags.xml
+ *  ./cbortag.py cbor-tags.xml
  *
  * The XHTML URL mentioned in the comment below is a human-readable version of
  * the same resource.
  */
 
-/* TODO (if possible): fix XSLT to replace each newline and surrounding space in
-   a semantics entry with a single space, instead of using a raw string to wrap
-   each, propagating the spacing from the XML to the output of cbordump. Also
-   auto-purge dangling spaces from the ends of generated lines.
-*/
-
 // GENERATED CODE
 struct CborTagDescription
 {
@@ -36,180 +30,101 @@ struct CborTagDescription
     const char *description;    // with space and parentheses
 };
 
-// CBOR Tags
+// Concise Binary Object Representation (CBOR) Tags
 static const CborTagDescription tagDescriptions[] = {
     // from https://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml
-    { QCborTag(0),
-      R"r( (Standard date/time string; see Section 3.4.1 [RFC8949]))r" },
-    { QCborTag(1),
-      R"r( (Epoch-based date/time; see Section 3.4.2 [RFC8949]))r" },
-    { QCborTag(2),
-      R"r( (Positive bignum; see Section 3.4.3 [RFC8949]))r" },
-    { QCborTag(3),
-      R"r( (Negative bignum; see Section 3.4.3 [RFC8949]))r" },
-    { QCborTag(4),
-      R"r( (Decimal fraction; see Section 3.4.4 [RFC8949]))r" },
-    { QCborTag(5),
-      R"r( (Bigfloat; see Section 3.4.4 [RFC8949]))r" },
-    { QCborTag(16),
-      R"r( (COSE Single Recipient Encrypted Data Object [RFC9052]))r" },
-    { QCborTag(17),
-      R"r( (COSE Mac w/o Recipients Object [RFC9052]))r" },
-    { QCborTag(18),
-      R"r( (COSE Single Signer Data Object [RFC9052]))r" },
-    { QCborTag(19),
-      R"r( (COSE standalone V2 countersignature [RFC9338]))r" },
+    { QCborTag(0), " (Standard date/time string; see Section 3.4.1 [RFC8949])" },
+    { QCborTag(1), " (Epoch-based date/time; see Section 3.4.2 [RFC8949])" },
+    { QCborTag(2), " (Positive bignum; see Section 3.4.3 [RFC8949])" },
+    { QCborTag(3), " (Negative bignum; see Section 3.4.3 [RFC8949])" },
+    { QCborTag(4), " (Decimal fraction; see Section 3.4.4 [RFC8949])" },
+    { QCborTag(5), " (Bigfloat; see Section 3.4.4 [RFC8949])" },
+    { QCborTag(16), " (COSE Single Recipient Encrypted Data Object [RFC9052])" },
+    { QCborTag(17), " (COSE Mac w/o Recipients Object [RFC9052])" },
+    { QCborTag(18), " (COSE Single Signer Data Object [RFC9052])" },
+    { QCborTag(19), " (COSE standalone V2 countersignature [RFC9338])" },
     { QCborTag(21),
-      R"r( (Expected conversion to base64url encoding; see Section 3.4.5.2  [RFC8949]))r" },
-    { QCborTag(22),
-      R"r( (Expected conversion to base64 encoding; see Section 3.4.5.2  [RFC8949]))r" },
-    { QCborTag(23),
-      R"r( (Expected conversion to base16 encoding; see Section 3.4.5.2 [RFC8949]))r" },
-    { QCborTag(24),
-      R"r( (Encoded CBOR data item; see Section 3.4.5.1 [RFC8949]))r" },
-    { QCborTag(25),
-      R"r( (reference the nth previously seen string))r" },
-    { QCborTag(26),
-      R"r( (Serialised Perl object with classname and constructor arguments))r" },
+      " (Expected conversion to base64url encoding; see Section 3.4.5.2 [RFC8949])" },
+    { QCborTag(22), " (Expected conversion to base64 encoding; see Section 3.4.5.2 [RFC8949])" },
+    { QCborTag(23), " (Expected conversion to base16 encoding; see Section 3.4.5.2 [RFC8949])" },
+    { QCborTag(24), " (Encoded CBOR data item; see Section 3.4.5.1 [RFC8949])" },
+    { QCborTag(25), " (reference the nth previously seen string)" },
+    { QCborTag(26), " (Serialised Perl object with classname and constructor arguments)" },
     { QCborTag(27),
-      R"r( (Serialised language-independent object with type name and constructor arguments))r" },
-    { QCborTag(28),
-      R"r( (mark value as (potentially) shared))r" },
-    { QCborTag(29),
-      R"r( (reference nth marked value))r" },
-    { QCborTag(30),
-      R"r( (Rational number))r" },
-    { QCborTag(31),
-      R"r( (Absent value in a CBOR Array))r" },
-    { QCborTag(32),
-      R"r( (URI; see Section 3.4.5.3 [RFC8949]))r" },
-    { QCborTag(33),
-      R"r( (base64url; see Section 3.4.5.3 [RFC8949]))r" },
-    { QCborTag(34),
-      R"r( (base64; see Section 3.4.5.3 [RFC8949]))r" },
-    { QCborTag(35),
-      R"r( (Regular expression; see Section 2.4.4.3 [RFC7049]))r" },
-    { QCborTag(36),
-      R"r( (MIME message; see Section 3.4.5.3 [RFC8949]))r" },
-    { QCborTag(37),
-      R"r( (Binary UUID (RFC4122, Section 4.1.2)))r" },
-    { QCborTag(38),
-      R"r( (Language-tagged string [RFC9290]))r" },
-    { QCborTag(39),
-      R"r( (Identifier))r" },
-    { QCborTag(40),
-      R"r( (Multi-dimensional Array, row-major order [RFC8746]))r" },
-    { QCborTag(41),
-      R"r( (Homogeneous Array [RFC8746]))r" },
-    { QCborTag(42),
-      R"r( (IPLD content identifier))r" },
-    { QCborTag(43),
-      R"r( (YANG bits datatype; see Section 6.7. [RFC9254]))r" },
-    { QCborTag(44),
-      R"r( (YANG enumeration datatype; see Section 6.6. [RFC9254]))r" },
-    { QCborTag(45),
-      R"r( (YANG identityref datatype; see Section 6.10. [RFC9254]))r" },
-    { QCborTag(46),
-      R"r( (YANG instance-identifier datatype; see Section 6.13. [RFC9254]))r" },
-    { QCborTag(47),
-      R"r( (YANG Schema Item iDentifier (sid); see Section 3.2. [RFC9254]))r" },
-    { QCborTag(52),
-      R"r( (IPv4, [prefixlen,IPv4], [IPv4,prefixpart] [RFC9164]))r" },
-    { QCborTag(54),
-      R"r( (IPv6, [prefixlen,IPv6], [IPv6,prefixpart] [RFC9164]))r" },
-    { QCborTag(61),
-      R"r( (CBOR Web Token (CWT) [RFC8392]))r" },
-    { QCborTag(63),
-      R"r( (Encoded CBOR Sequence ))r" },
-    { QCborTag(64),
-      R"r( (uint8 Typed Array [RFC8746]))r" },
-    { QCborTag(65),
-      R"r( (uint16, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(66),
-      R"r( (uint32, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(67),
-      R"r( (uint64, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(68),
-      R"r( (uint8 Typed Array, clamped arithmetic [RFC8746]))r" },
-    { QCborTag(69),
-      R"r( (uint16, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(70),
-      R"r( (uint32, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(71),
-      R"r( (uint64, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(72),
-      R"r( (sint8 Typed Array [RFC8746]))r" },
-    { QCborTag(73),
-      R"r( (sint16, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(74),
-      R"r( (sint32, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(75),
-      R"r( (sint64, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(76),
-      R"r( ((reserved) [RFC8746]))r" },
-    { QCborTag(77),
-      R"r( (sint16, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(78),
-      R"r( (sint32, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(79),
-      R"r( (sint64, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(80),
-      R"r( (IEEE 754 binary16, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(81),
-      R"r( (IEEE 754 binary32, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(82),
-      R"r( (IEEE 754 binary64, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(83),
-      R"r( (IEEE 754 binary128, big endian, Typed Array [RFC8746]))r" },
-    { QCborTag(84),
-      R"r( (IEEE 754 binary16, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(85),
-      R"r( (IEEE 754 binary32, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(86),
-      R"r( (IEEE 754 binary64, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(87),
-      R"r( (IEEE 754 binary128, little endian, Typed Array [RFC8746]))r" },
-    { QCborTag(96),
-      R"r( (COSE Encrypted Data Object [RFC9052]))r" },
-    { QCborTag(97),
-      R"r( (COSE MACed Data Object [RFC9052]))r" },
-    { QCborTag(98),
-      R"r( (COSE Signed Data Object [RFC9052]))r" },
-    { QCborTag(100),
-      R"r( (Number of days since the epoch date 1970-01-01 [RFC8943]))r" },
-    { QCborTag(101),
-      R"r( (alternatives as given by the uint + 128; see Section 9.1))r" },
-    { QCborTag(103),
-      R"r( (Geographic Coordinates))r" },
-    { QCborTag(104),
-      R"r( (Geographic Coordinate Reference System WKT or EPSG number))r" },
-    { QCborTag(110),
-      R"r( (relative object identifier (BER encoding); SDNV  sequence [RFC9090]))r" },
-    { QCborTag(111),
-      R"r( (object identifier (BER encoding) [RFC9090]))r" },
-    { QCborTag(112),
-      R"r( (object identifier (BER encoding), relative to 1.3.6.1.4.1 [RFC9090]))r" },
-    { QCborTag(120),
-      R"r( (Internet of Things Data Point))r" },
+      " (Serialised language-independent object with type name and constructor arguments)" },
+    { QCborTag(28), " (mark value as (potentially) shared)" },
+    { QCborTag(29), " (reference nth marked value)" },
+    { QCborTag(30), " (Rational number)" },
+    { QCborTag(31), " (Absent value in a CBOR Array)" },
+    { QCborTag(32), " (URI; see Section 3.4.5.3 [RFC8949])" },
+    { QCborTag(33), " (base64url; see Section 3.4.5.3 [RFC8949])" },
+    { QCborTag(34), " (base64; see Section 3.4.5.3 [RFC8949])" },
+    { QCborTag(35), " (Regular expression; see Section 2.4.4.3 [RFC7049])" },
+    { QCborTag(36), " (MIME message; see Section 3.4.5.3 [RFC8949])" },
+    { QCborTag(37), " (Binary UUID [RFC4122, Section 4.1.2])" },
+    { QCborTag(38), " (Language-tagged string [RFC9290, Appendix A])" },
+    { QCborTag(39), " (Identifier)" },
+    { QCborTag(40), " (Multi-dimensional Array, row-major order [RFC8746])" },
+    { QCborTag(41), " (Homogeneous Array [RFC8746])" },
+    { QCborTag(42), " (IPLD content identifier)" },
+    { QCborTag(43), " (YANG bits datatype; see Section 6.7. [RFC9254])" },
+    { QCborTag(44), " (YANG enumeration datatype; see Section 6.6. [RFC9254])" },
+    { QCborTag(45), " (YANG identityref datatype; see Section 6.10. [RFC9254])" },
+    { QCborTag(46), " (YANG instance-identifier datatype; see Section 6.13. [RFC9254])" },
+    { QCborTag(47), " (YANG Schema Item iDentifier (sid); see Section 3.2. [RFC9254])" },
+    { QCborTag(52), " (IPv4, [prefixlen,IPv4], [IPv4,prefixpart] [RFC9164])" },
+    { QCborTag(54), " (IPv6, [prefixlen,IPv6], [IPv6,prefixpart] [RFC9164])" },
+    { QCborTag(61), " (CBOR Web Token (CWT) [RFC8392])" },
+    { QCborTag(63), " (Encoded CBOR Sequence [RFC8742])" },
+    { QCborTag(64), " (uint8 Typed Array [RFC8746])" },
+    { QCborTag(65), " (uint16, big endian, Typed Array [RFC8746])" },
+    { QCborTag(66), " (uint32, big endian, Typed Array [RFC8746])" },
+    { QCborTag(67), " (uint64, big endian, Typed Array [RFC8746])" },
+    { QCborTag(68), " (uint8 Typed Array, clamped arithmetic [RFC8746])" },
+    { QCborTag(69), " (uint16, little endian, Typed Array [RFC8746])" },
+    { QCborTag(70), " (uint32, little endian, Typed Array [RFC8746])" },
+    { QCborTag(71), " (uint64, little endian, Typed Array [RFC8746])" },
+    { QCborTag(72), " (sint8 Typed Array [RFC8746])" },
+    { QCborTag(73), " (sint16, big endian, Typed Array [RFC8746])" },
+    { QCborTag(74), " (sint32, big endian, Typed Array [RFC8746])" },
+    { QCborTag(75), " (sint64, big endian, Typed Array [RFC8746])" },
+    { QCborTag(76), " ((reserved) [RFC8746])" },
+    { QCborTag(77), " (sint16, little endian, Typed Array [RFC8746])" },
+    { QCborTag(78), " (sint32, little endian, Typed Array [RFC8746])" },
+    { QCborTag(79), " (sint64, little endian, Typed Array [RFC8746])" },
+    { QCborTag(80), " (IEEE 754 binary16, big endian, Typed Array [RFC8746])" },
+    { QCborTag(81), " (IEEE 754 binary32, big endian, Typed Array [RFC8746])" },
+    { QCborTag(82), " (IEEE 754 binary64, big endian, Typed Array [RFC8746])" },
+    { QCborTag(83), " (IEEE 754 binary128, big endian, Typed Array [RFC8746])" },
+    { QCborTag(84), " (IEEE 754 binary16, little endian, Typed Array [RFC8746])" },
+    { QCborTag(85), " (IEEE 754 binary32, little endian, Typed Array [RFC8746])" },
+    { QCborTag(86), " (IEEE 754 binary64, little endian, Typed Array [RFC8746])" },
+    { QCborTag(87), " (IEEE 754 binary128, little endian, Typed Array [RFC8746])" },
+    { QCborTag(96), " (COSE Encrypted Data Object [RFC9052])" },
+    { QCborTag(97), " (COSE MACed Data Object [RFC9052])" },
+    { QCborTag(98), " (COSE Signed Data Object [RFC9052])" },
+    { QCborTag(100), " (Number of days since the epoch date 1970-01-01 [RFC8943])" },
+    { QCborTag(101), " (alternatives as given by the uint + 128; see Section 9.1)" },
+    { QCborTag(103), " (Geographic Coordinates)" },
+    { QCborTag(104), " (Geographic Coordinate Reference System WKT or EPSG number)" },
+    { QCborTag(110), " (relative object identifier (BER encoding); SDNV sequence [RFC9090])" },
+    { QCborTag(111), " (object identifier (BER encoding) [RFC9090])" },
+    { QCborTag(112), " (object identifier (BER encoding), relative to 1.3.6.1.4.1 [RFC9090])" },
+    { QCborTag(120), " (Internet of Things Data Point)" },
     { QCborTag(260),
-      R"r( (Network Address (IPv4 or IPv6 or MAC Address) (DEPRECATED in favor of 52 and 54
-        for IP addresses) [http://www.employees.oRg/~RaviR/CboR-netwoRk.txt]))r" },
+      " (Network Address (IPv4 or IPv6 or MAC Address) (DEPRECATED in favor of 52 and 54 for IP"
+      " addresses) [RFC9164])" },
     { QCborTag(261),
-      R"r( (Network Address Prefix (IPv4 or IPv6 Address + Mask Length) (DEPRECATED in favor of 52 and 54
-        for IP addresses) [https://github.Com/toRaviR/CBOR-Tag-SpeCs/blob/masteR/netwoRkPReFix.md]))r" },
+      " (Network Address Prefix (IPv4 or IPv6 Address + Mask Length) (DEPRECATED in favor of 52"
+      " and 54 for IP addresses) [RFC9164])" },
     { QCborTag(271),
-      R"r( (DDoS Open Threat Signaling (DOTS) signal channel object,
-        as defined in  [RFC9132]))r" },
-    { QCborTag(1004),
-      R"r( ( full-date string [RFC8943]))r" },
-    { QCborTag(1040),
-      R"r( (Multi-dimensional Array, column-major order [RFC8746]))r" },
-    { QCborTag(55799),
-      R"r( (Self-described CBOR; see Section 3.4.6 [RFC8949]))r" },
-    { QCborTag(55800),
-      R"r( (indicates that the file contains CBOR Sequences [RFC9277]))r" },
+      " (DDoS Open Threat Signaling (DOTS) signal channel object, as defined in [RFC9132])" },
+    { QCborTag(1004), " (full-date string [RFC8943])" },
+    { QCborTag(1040), " (Multi-dimensional Array, column-major order [RFC8746])" },
+    { QCborTag(55799), " (Self-described CBOR; see Section 3.4.6 [RFC8949])" },
+    { QCborTag(55800), " (indicates that the file contains CBOR Sequences [RFC9277])" },
     { QCborTag(55801),
-      R"r( (indicates that the file starts with a CBOR-Labeled Non-CBOR Data label. [RFC9277]))r" },
+      " (indicates that the file starts with a CBOR-Labeled Non-CBOR Data label. [RFC9277])" },
     { QCborTag(-1), nullptr }
 };
 // END GENERATED CODE
diff --git a/examples/corelib/serialization/cbordump/tag-transform.xslt b/examples/corelib/serialization/cbordump/tag-transform.xslt
deleted file mode 100644
index fb9f81df33..0000000000
--- a/examples/corelib/serialization/cbordump/tag-transform.xslt
+++ /dev/null
@@ -1,28 +0,0 @@
-<?xml version="1.0"?>
-<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
-                xmlns:a="http://www.iana.org/assignments" version="1.0">
-<xsl:output omit-xml-declaration="yes" indent="no" method="text"/>
-<xsl:template match="/a:registry[@id='cbor-tags']">struct CborTagDescription
-{
-    QCborTag tag;
-    const char *description;    // with space and parentheses
-};
-
-// <xsl:value-of select="a:registry/a:title"/>
-static const CborTagDescription tagDescriptions[] = {
-    // from https://www.iana.org/assignments/cbor-tags/cbor-tags.xhtml
-<xsl:for-each select="a:registry/a:record">
-    <xsl:sort select="a:value" data-type="number"/>
-        <xsl:if test="a:semantics != ''">
-            <xsl:call-template name="row"/>
-        </xsl:if>
-    </xsl:for-each>    { QCborTag(-1), nullptr }
-};
-</xsl:template>
-<xsl:template name="row">    { QCborTag(<xsl:value-of select="a:value"/>),
-      R"r( (<xsl:value-of select="a:semantics"/> <xsl:call-template name="xref"/>))r" },
-</xsl:template><!-- fn:replace(a:semantics, '\s+', ' ') -->
-<xsl:template name="xref"><xsl:if test="a:xref/@type = 'rfc'"> [<xsl:value-of
-select="translate(a:xref/@data,'rfc','RFC')"/>]</xsl:if>
-</xsl:template>
-</xsl:stylesheet>