3party/pugixml
0
0
Fork 0
mirror of https://github.com/zeux/pugixml.git synced 2024-12-26 12:41:06 +08:00
Code Issues Projects Releases Wiki Activity

Never escape > in attribute values

Browse Source 
According to XML spec, > sometimes needs to be escaped in PCDATA (when
it occurs as a ]]> pattern), but it doesn't need to be escaped in
attribute values.

Contributes to #272.
This commit is contained in:
Arseny Kapoulkine 2019-09-11 21:35:03 -07:00
parent 946de603b1
commit c6607740a0
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/pugixml.cpp
View File

@ -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, _, -, .
@ -1872,7 +1872,7 @@ 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, 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
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 0, 0, 3, 0, 1, 0, // 48-63
0, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, // 64-79
20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 0, 0, 0, 0, 20, // 80-95

8
tests/test_write.cpp
View File

@ -193,8 +193,8 @@ 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_EX(doc, STR("<node attr='&lt;&gt;&apos;\"&amp;&#04;&#13;&#10;&#09;'>&lt;&gt;'\"&amp;&#04;\r\n\t</node>"), STR(""), format_raw | format_attribute_single_quote);
CHECK_NODE(doc, STR("<node attr=\"&lt;>'&quot;&amp;&#04;&#13;&#10;&#09;\">&lt;&gt;'\"&amp;&#04;\r\n\t</node>"));
CHECK_NODE_EX(doc, STR("<node attr='&lt;>&apos;\"&amp;&#04;&#13;&#10;&#09;'>&lt;&gt;'\"&amp;&#04;\r\n\t</node>"), STR(""), format_raw | format_attribute_single_quote);
}
TEST_XML(write_escape_roundtrip, "<node attr=''>text</node>")
@ -208,8 +208,8 @@ 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_EX(doc, STR("<node attr='&lt;&gt;&apos;\"&amp;&#04;&#13;&#10;&#09;'>&lt;&gt;'\"&amp;&#04;\n\t</node>"), STR(""), format_raw | format_attribute_single_quote);
CHECK_NODE(doc, STR("<node attr=\"&lt;>'&quot;&amp;&#04;&#13;&#10;&#09;\">&lt;&gt;'\"&amp;&#04;\n\t</node>"));
CHECK_NODE_EX(doc, STR("<node attr='&lt;>&apos;\"&amp;&#04;&#13;&#10;&#09;'>&lt;&gt;'\"&amp;&#04;\n\t</node>"), STR(""), format_raw | format_attribute_single_quote);
}
TEST_XML(write_escape_unicode, "<node attr='&#x3c00;'/>")