organicmaps/pugixml
13
Fork 0
Code Issues 1 Pull requests Projects Releases Wiki Activity Actions

Escape TAB character in attribute values with 	

Browse source 
This change modifies the table entries for ctx_special_attr to treat TAB
character as special, which makes the output code escape it.

Before this change, trying to use TAB in an attribute value would output
it verbatim; during subsequent parsing, pugixml - and other compliant
parsers - would apply attribute-value normalization, turning the TAB
into a space and losing the original value.

Using 	 fixes this; if an input document has 	 in an attribute
value, that gets unescaped into \t during parsing and escaped back into
	 during output, which means we can now roundtrip values like this.

Fixes #242.
This commit is contained in:
Arseny Kapoulkine 2018-11-19 22:22:03 -08:00
parent 7d2436ec2f
commit aac75cd299
2 changed files with 17 additions and 3 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 (except \t), &, <, >, "
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, _, -, .
@ -1869,7 +1869,7 @@ PUGI__NS_BEGIN
static const unsigned char chartypex_table[256] =
{
3, 3, 3, 3, 3, 3, 3, 3, 3, 0, 2, 3, 3, 2, 3, 3, // 0-15
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
24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 0, 0, 3, 0, 3, 0, // 48-63

16
tests/test_write.cpp
View file

@ -193,7 +193,21 @@ 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;\t\">&lt;&gt;'\"&amp;&#04;\r\n\t</node>"));
CHECK_NODE(doc, STR("<node attr=\"&lt;&gt;'&quot;&amp;&#04;&#13;&#10;&#09;\">&lt;&gt;'\"&amp;&#04;\r\n\t</node>"));
}
TEST_XML(write_escape_roundtrip, "<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"));
std::string contents = write_narrow(doc, format_raw, encoding_utf8);
CHECK(doc.load_buffer(contents.c_str(), contents.size()));
// 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>"));
}
TEST_XML(write_escape_unicode, "<node attr='&#x3c00;'/>")