Skip to content

Commit

Permalink
Add support for using single quotes to enclose attribute values
Browse files Browse the repository at this point in the history 
This change adds format_attribute_single_quote flag that uses single quotes (`'`) instead of double quotes (`"`) for formatting attribute values.

Internal quotation marks are escaped using `"` and `'`.
  • Loading branch information
@m-naumann @zeux
m-naumann authored and zeux committed Jun 19, 2019
1 parent fcb7c8d commit 5a867cb
Show file tree
Hide file tree
Showing 5 changed files with 21 additions and 8 deletions.
2 changes: 2 additions & 0 deletions docs/manual.adoc
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1706,6 +1706,8 @@ These flags control the resulting tree contents:

* [[format_skip_control_chars]]`format_skip_control_chars` enables skipping characters belonging to range [0; 32) instead of "&#xNN;" encoding. This flag is *off* by default.

* [[format_attribute_single_quote]]`format_attribute_single_quote` enables using single quotes `'` instead of double quotes `"` for enclosing attribute values. This flag is *off* by default.

These flags control the additional output information:

* [[format_no_declaration]]`format_no_declaration` disables default node declaration output. By default, if the document is saved via `save` or `save_file` function, and it does not have any document declaration, a default declaration is output before the document contents. Enabling this flag disables this declaration. This flag has no effect in `xml_node::print` functions: they never output the default declaration. This flag is *off* by default.
Expand Down
5 changes: 4 additions & 1 deletion docs/manual.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3327,6 +3327,9 @@ <h3 id="saving.options"><a class="anchor" href="#saving.options"></a><a class="l
<li>
<p><a id="format_skip_control_chars"></a><code>format_skip_control_chars</code> enables skipping characters belonging to range [0; 32) instead of "&amp;#xNN;" encoding. This flag is <strong>off</strong> by default.</p>
</li>
<li>
<p><a id="format_attribute_single_quote"></a><code>format_attribute_single_quote</code> enables using single quotes <code>'</code> instead of double quotes <code>"</code> for enclosing attribute values. This flag is <strong>off</strong> by default.</p>
</li>
</ul>
</div>
<div class="paragraph">
Expand Down Expand Up @@ -5775,4 +5778,4 @@ <h3 id="apiref.functions"><a class="anchor" href="#apiref.functions"></a><a clas
</div>
</div>
</body>
</html>
</html>
13 changes: 9 additions & 4 deletions src/pugixml.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1861,7 +1861,7 @@ PUGI__NS_BEGIN
enum chartypex_t
{
ctx_special_pcdata = 1, // Any symbol >= 0 and < 32 (except \t, \r, \n), &, <, >
ctx_special_attr = 2, // Any symbol >= 0 and < 32, &, <, >, "
ctx_special_attr = 2, // Any symbol >= 0 and < 32, &, <, >, ", '
ctx_start_symbol = 4, // Any symbol > 127, a-z, A-Z, _
ctx_digit = 8, // 0-9
ctx_symbol = 16 // Any symbol > 127, a-z, A-Z, 0-9, _, -, .
Expand All @@ -1871,7 +1871,7 @@ PUGI__NS_BEGIN
{
3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 3, 3, 2, 3, 3, // 0-15
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, // 16-31
0, 0, 2, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 16, 16, 0, // 32-47
0, 0, 2, 0, 0, 0, 3, 2, 0, 0, 0, 0, 0, 16, 16, 0, // 32-47
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 0, 0, 3, 0, 3, 0, // 48-63

0, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, // 64-79
Expand Down Expand Up @@ -3933,6 +3933,10 @@ PUGI__NS_BEGIN
writer.write('&', 'q', 'u', 'o', 't', ';');
++s;
break;
case '\'':
writer.write('&', 'a', 'p', 'o', 's', ';');
++s;
break;
default: // s is not a usual symbol
{
unsigned int ch = static_cast<unsigned int>(*s++);
Expand Down Expand Up @@ -4064,6 +4068,7 @@ PUGI__NS_BEGIN
PUGI__FN void node_output_attributes(xml_buffered_writer& writer, xml_node_struct* node, const char_t* indent, size_t indent_length, unsigned int flags, unsigned int depth)
{
const char_t* default_name = PUGIXML_TEXT(":anonymous");
const char_t enquotation_char = (flags & format_attribute_single_quote) ? '\'' : '"';

for (xml_attribute_struct* a = node->first_attribute; a; a = a->next_attribute)
{
Expand All @@ -4079,12 +4084,12 @@ PUGI__NS_BEGIN
}

writer.write_string(a->name ? a->name + 0 : default_name);
writer.write('=', '"');
writer.write('=', enquotation_char);

if (a->value)
text_output(writer, a->value, ctx_special_attr, flags);

writer.write('"');
writer.write(enquotation_char);
}
}

Expand Down
3 changes: 3 additions & 0 deletions src/pugixml.hpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -255,6 +255,9 @@ namespace pugi
// Skip characters belonging to range [0; 32) instead of "&#xNN;" encoding. This flag is off by default.
const unsigned int format_skip_control_chars = 0x100;

// Use single quotes ' instead of double quotes " for enclosing attribute values. This flag is off by default.
const unsigned int format_attribute_single_quote = 0x200;

// The default set of formatting flags.
// Nodes are indented depending on their depth in DOM tree, a default declaration is output if document has none.
const unsigned int format_default = format_indent;
Expand Down
6 changes: 3 additions & 3 deletions tests/test_write.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -193,7 +193,7 @@ TEST_XML(write_escape, "<node attr=''>text</node>")
doc.child(STR("node")).attribute(STR("attr")) = STR("<>'\"&\x04\r\n\t");
doc.child(STR("node")).first_child().set_value(STR("<>'\"&\x04\r\n\t"));

CHECK_NODE(doc, STR("<node attr=\"&lt;&gt;'&quot;&amp;&#04;&#13;&#10;&#09;\">&lt;&gt;'\"&amp;&#04;\r\n\t</node>"));
CHECK_NODE(doc, STR("<node attr=\"&lt;&gt;&apos;&quot;&amp;&#04;&#13;&#10;&#09;\">&lt;&gt;'\"&amp;&#04;\r\n\t</node>"));
}

TEST_XML(write_escape_roundtrip, "<node attr=''>text</node>")
Expand All @@ -207,7 +207,7 @@ TEST_XML(write_escape_roundtrip, "<node attr=''>text</node>")

// Note: this string is almost identical to the string from write_escape with the exception of \r
// \r in PCDATA doesn't roundtrip because it has to go through newline conversion (which could be disabled, but is active by default)
CHECK_NODE(doc, STR("<node attr=\"&lt;&gt;'&quot;&amp;&#04;&#13;&#10;&#09;\">&lt;&gt;'\"&amp;&#04;\n\t</node>"));
CHECK_NODE(doc, STR("<node attr=\"&lt;&gt;&apos;&quot;&amp;&#04;&#13;&#10;&#09;\">&lt;&gt;'\"&amp;&#04;\n\t</node>"));
}

TEST_XML(write_escape_unicode, "<node attr='&#x3c00;'/>")
Expand Down Expand Up @@ -632,7 +632,7 @@ TEST_XML(write_no_empty_element_tags, "<node><child1/><child2>text</child2><chil

TEST_XML_FLAGS(write_roundtrip, "<node><child1 attr1='value1' attr2='value2'/><child2 attr='value'>pre<![CDATA[data]]>mid&lt;text&amp;escape<!--comment--><test/>post<?pi value?>fin</child2><child3/></node>", parse_full)
{
const unsigned int flagset[] = { format_indent, format_raw, format_no_declaration, format_indent_attributes, format_no_empty_element_tags };
const unsigned int flagset[] = { format_indent, format_raw, format_no_declaration, format_indent_attributes, format_no_empty_element_tags, format_attribute_single_quote };
size_t flagcount = sizeof(flagset) / sizeof(flagset[0]);

for (size_t i = 0; i < (size_t(1) << flagcount); ++i)
Expand Down

0 comments on commit 5a867cb

Please sign in to comment.