Skip to content

Concatenate character tokens #98

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jul 18, 2017
Merged

Concatenate character tokens #98

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions tokenizer/test1.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,14 +182,14 @@

{"description":"Entity without trailing semicolon (1)",
"input":"I'm &notit",
"output":[["Character","I'm "], ["Character", "\u00ACit"]],
"output":[["Character","I'm \u00ACit"]],
"errors": [
{"code" : "missing-semicolon-after-character-reference", "line": 1, "col": 9 }
]},

{"description":"Entity without trailing semicolon (2)",
"input":"I'm &notin",
"output":[["Character","I'm "], ["Character", "\u00ACin"]],
"output":[["Character","I'm \u00ACin"]],
"errors": [
{"code" : "missing-semicolon-after-character-reference", "line": 1, "col": 9 }
]},
Expand Down
6 changes: 3 additions & 3 deletions tokenizer/test2.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@

{"description":"Hexadecimal entity pair representing a surrogate pair",
"input":"��",
"output":[["Character", "\uFFFD"], ["Character", "\uFFFD"]],
"output":[["Character", "\uFFFD\uFFFD"]],
"errors":[
{ "code": "surrogate-character-reference", "line": 1, "col": 9 },
{ "code": "surrogate-character-reference", "line": 1, "col": 17 }
Expand Down Expand Up @@ -195,7 +195,7 @@

{"description":"Unescaped <",
"input":"foo < bar",
"output":[["Character", "foo "], ["Character", "< bar"]],
"output":[["Character", "foo < bar"]],
"errors":[
{ "code": "invalid-first-character-of-tag-name", "line": 1, "col": 6 }
]},
Expand Down Expand Up @@ -242,7 +242,7 @@

{"description":"Empty end tag with following characters",
"input":"a</>bc",
"output":[["Character", "a"], ["Character", "bc"]],
"output":[["Character", "abc"]],
"errors":[
{ "code": "missing-end-tag-name", "line": 1, "col": 4 }
]},
Expand Down
4 changes: 2 additions & 2 deletions tokenizer/test3.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@

{"description":"<\\u0000",
"input":"<\u0000",
"output":[["Character", "<"], ["Character", "\u0000"]],
"output":[["Character", "<\u0000"]],
"errors":[
{ "code": "invalid-first-character-of-tag-name", "line": 1, "col": 2 },
{ "code": "unexpected-null-character", "line": 1, "col": 2 }
Expand Down Expand Up @@ -8415,7 +8415,7 @@

{"description":"<<",
"input":"<<",
"output":[["Character", "<"], ["Character", "<"]],
"output":[["Character", "<<"]],
"errors":[
{ "code": "invalid-first-character-of-tag-name", "line": 1, "col": 2 },
{ "code": "eof-before-tag-name", "line": 1, "col": 3 }
Expand Down
6 changes: 3 additions & 3 deletions tokenizer/test4.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@

{"description":"Empty hex numeric entities",
"input":"&#x &#X ",
"output":[["Character", "&#x "], ["Character", "&#X "]],
"output":[["Character", "&#x &#X "]],
"errors":[
{ "code": "absence-of-digits-in-numeric-character-reference", "line": 1, "col": 4 },
{ "code": "absence-of-digits-in-numeric-character-reference", "line": 1, "col": 8 }
Expand All @@ -205,7 +205,7 @@

{"description":"Empty decimal numeric entities",
"input":"&# &#; ",
"output":[["Character", "&# "], ["Character", "&#; "]],
"output":[["Character", "&# &#; "]],
"errors":[
{ "code": "absence-of-digits-in-numeric-character-reference", "line": 1, "col": 3 },
{ "code": "absence-of-digits-in-numeric-character-reference", "line": 1, "col": 6 }
Expand Down Expand Up @@ -274,7 +274,7 @@

{"description":"Surrogate code point edge cases",
"input":"&#xD7FF;&#xD800;&#xD801;&#xDFFE;&#xDFFF;&#xE000;",
"output":[["Character", "\uD7FF"], ["Character", "\uFFFD"], ["Character", "\uFFFD"], ["Character", "\uFFFD"], ["Character", "\uFFFD\uE000"]],
"output":[["Character", "\uD7FF\uFFFD\uFFFD\uFFFD\uFFFD\uE000"]],
"errors":[
{ "code": "surrogate-character-reference", "line": 1, "col": 17 },
{ "code": "surrogate-character-reference", "line": 1, "col": 25 },
Expand Down
4 changes: 2 additions & 2 deletions tokenizer/unicodeCharsProblematic.test
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
{"description": "Invalid Unicode character U+DFFF with valid preceding character",
"doubleEscaped":true,
"input": "a\\uDFFF",
"output":[["Character", "a"], ["Character", "\\uDFFF"]],
"output":[["Character", "a\\uDFFF"]],
"errors":[
{ "code": "surrogate-in-input-stream", "line": 1, "col": 2 }
]},
Expand All @@ -33,7 +33,7 @@

{"description":"CR followed by U+0000",
"input":"\r\u0000",
"output":[["Character", "\n"], ["Character", "\u0000"]],
"output":[["Character", "\n\u0000"]],
"errors":[
{ "code": "unexpected-null-character", "line": 2, "col": 1 }
]}
Expand Down