XML/Input: Difference between revisions

Line 2,024:

| .result = .result + [.match] ;

# consume the literal string $s

def consumeliteral($s):

def q($s):

select(.remainder | startswith($s))

| .remainder |= .[$s | length :] ;

def literal($s):

~~consumeliteral~~($s)

q($s)

| .result += [$s];

Line 2,066:

Line 2,067:

(consume("'") | parse("[^']*") | consume("'")));

def CDataSec : box("@CDATA"; ~~consume~~("<!\\[CDATA\\[") | string_except("]]") | ~~consume~~("]]>") ) | ws;

def CDataSec : box("@CDATA"; q("<![CDATA[") | string_except("]]>") | q("]]>") ) | ws;

def PROLOG : box("@PROLOG"; ~~consume~~("<\\?xml") | string_except("\\?>") | ~~consume~~("\\?>"));

def PROLOG : box("@PROLOG"; q("<?xml") | string_except("\\?>") | q("?>"));

def DTD : box("@DTD"; ~~consume~~("<!") | parse("[^>]") | ~~consume~~(">"));

def DTD : box("@DTD"; q("<!") | parse("[^>]") | q(">"));

# The XML spec specifically disallows double-hyphen within comments

def COMMENT : box("@COMMENT"; ~~consume~~("") | ~~consume~~("-->"));

def COMMENT : box("@COMMENT"; q(""));

def CharData : parse("[^<]+"); # only `<` is disallowed

# This is more permissive than required:

def Name : parse("[A-Za-z:_][^/=<>\n\r\t ]*");

def Attribute : keyvalue(Name | ws | ~~consume~~("=") | ws | String | ws);

def Attribute : keyvalue(Name | ws | q("=") | ws | String | ws);

def Attributes: box( plus(Attribute) ) | .result[-1] |= {"@attributes": add} ;

Line 2,081:

Line 2,084:

def Element :

def Content : star(Element // CDataSec // CharData // COMMENT);

objectify( ~~consume~~("<")

objectify( q("<")

| Name

| .result[-1] as $name

| ws

| (Attributes // ws)

| ( (~~consume~~("/>")

| ( (q("/>")

// (~~consume~~(">") | Content | ~~consume~~("</") | ~~consumeliteral~~($name) | ~~consume~~(">")))

// (q(">") | Content | q("</") | q($name) | ws | q(">")))

| ws) ) ;