status-im
/
NimYAML
mirror of https://github.com/status-im/NimYAML.git
2
0
Fork 0
Code Issues Projects Releases Wiki Activity

Support % escape sequences in tag URIs

This commit is contained in:
Felix Krause 2016-03-17 18:44:35 +01:00
parent d1c8c171a1
commit eda85be0b9
2 changed files with 31 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
private/fastparse.nim
View File

@ -569,7 +569,7 @@ proc unicodeSequence(lexer: var BaseLexer, length: int):
digitPosition = length - i - 1 digitPosition = length - i - 1
c = lexer.buf[lexer.bufpos] c = lexer.buf[lexer.bufpos]
case c case c
of EndOFFile: of EndOFFile, '\l', '\r':
lexerError(lexer, "Unfinished unicode escape sequence") lexerError(lexer, "Unfinished unicode escape sequence")
of '0' .. '9': of '0' .. '9':
unicodeChar = unicodechar or unicodeChar = unicodechar or
@ -580,10 +580,29 @@ proc unicodeSequence(lexer: var BaseLexer, length: int):
of 'a' .. 'f': of 'a' .. 'f':
unicodeChar = unicodechar or unicodeChar = unicodechar or
(cast[int](c) - 0x57) shl (digitPosition * 4) (cast[int](c) - 0x57) shl (digitPosition * 4)
else: else: lexerError(lexer, "Invalid character in unicode escape sequence")
lexerError(lexer, "Invalid character in unicode escape sequence")
return toUTF8(cast[Rune](unicodeChar)) return toUTF8(cast[Rune](unicodeChar))
proc byteSequence(lexer: var BaseLexer): char {.raises: [YamlParserError].} =
debug("lex: byteSequence")
var charCode = 0.int8
for i in 0 .. 1:
lexer.bufpos.inc()
let
digitPosition = int8(1 - i)
c = lexer.buf[lexer.bufpos]
case c
of EndOfFile, '\l', 'r':
lexerError(lexer, "Unfinished octet escape sequence")
of '0' .. '9':
charCode = charCode or (int8(c) - 0x30.int8) shl (digitPosition * 4)
of 'A' .. 'F':
charCode = charCode or (int8(c) - 0x37.int8) shl (digitPosition * 4)
of 'a' .. 'f':
charCode = charCode or (int8(c) - 0x57.int8) shl (digitPosition * 4)
else: lexerError(lexer, "Invalid character in octet escape sequence")
return char(charCode)
template processDoubleQuotedWhitespace(newlines: var int) {.dirty.} = template processDoubleQuotedWhitespace(newlines: var int) {.dirty.} =
var var
after = "" after = ""
@ -802,6 +821,7 @@ template tagHandle(lexer: var BaseLexer, content: var string,
of '!': of '!':
if shorthandEnd == -1 and i == 2: if shorthandEnd == -1 and i == 2:
content.add(c) content.add(c)
continue
elif shorthandEnd != 0: elif shorthandEnd != 0:
lexerError(lexer, "Illegal character in tag suffix") lexerError(lexer, "Illegal character in tag suffix")
shorthandEnd = i shorthandEnd = i
@ -813,18 +833,19 @@ template tagHandle(lexer: var BaseLexer, content: var string,
if i == 1: if i == 1:
shorthandEnd = -1 shorthandEnd = -1
content = "" content = ""
else: else: lexerError(lexer, "Illegal character in tag handle")
lexerError(lexer, "Illegal character in tag handle")
of '>': of '>':
if shorthandEnd == -1: if shorthandEnd == -1:
lexer.bufpos.inc() lexer.bufpos.inc()
if lexer.buf[lexer.bufpos] notin spaceOrLineEnd: if lexer.buf[lexer.bufpos] notin spaceOrLineEnd:
lexerError(lexer, "Missing space after verbatim tag handle") lexerError(lexer, "Missing space after verbatim tag handle")
break break
else: else: lexerError(lexer, "Illegal character in tag handle")
lexerError(lexer, "Illegal character in tag handle") of '%':
else: if shorthandEnd != 0:
lexerError(lexer, "Illegal character in tag handle") content.add(lexer.byteSequence())
else: lexerError(lexer, "Illegal character in tag handle")
else: lexerError(lexer, "Illegal character in tag handle")
template anchorName(lexer: BaseLexer, content: var string) = template anchorName(lexer: BaseLexer, content: var string) =
debug("lex: anchorName") debug("lex: anchorName")