Skip to content
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.

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

Fix parser #554

Merged
merged 4 commits into from
Nov 30, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion decode_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -810,7 +810,7 @@ func TestDecoder(t *testing.T) {
},
{
"a: \"\\0\"\n",
map[string]string{"a": "\\0"},
map[string]string{"a": "\x00"},
},
{
"b: 2\na: 1\nd: 4\nc: 3\nsub:\n e: 5\n",
Expand Down
2 changes: 1 addition & 1 deletion lexer/lexer_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -1347,7 +1347,7 @@ t4: 2098-01-09T10:40:47Z
Type: token.DoubleQuoteType,
CharacterType: token.CharacterTypeIndicator,
Indicator: token.QuotedScalarIndicator,
Value: "\\0",
Value: "\x00",
Origin: " \"\\0\"",
},
},
Expand Down
9 changes: 9 additions & 0 deletions parser/parser.go
Original file line number Diff line number Diff line change
Expand Up @@ -670,6 +670,15 @@ func (p *parser) parseMapValue(ctx *context, key ast.MapKeyNode, colonTk *Token)
return anchor, nil
}

if tk.Column() <= keyCol && tk.GroupType() == TokenGroupAnchorName {
// key: <value does not defined>
// &anchor
//
// key: <value does not defined>
// &anchor
return nil, errors.ErrSyntax("anchor is not allowed in this context", tk.RawToken())
}

if tk.Column() < keyCol {
// in this case,
// ----
Expand Down
10 changes: 10 additions & 0 deletions parser/token.go
Original file line number Diff line number Diff line change
Expand Up @@ -573,6 +573,16 @@ func createDocumentTokens(tokens []*Token) ([]*Token, error) {
},
}), nil
}
if tokens[i].Line() == tokens[i+1].Line() {
switch tokens[i+1].GroupType() {
case TokenGroupMapKey, TokenGroupMapKeyValue:
return nil, errors.ErrSyntax("value cannot be placed after document separator", tokens[i+1].RawToken())
}
switch tokens[i+1].Type() {
case token.SequenceEntryType:
return nil, errors.ErrSyntax("value cannot be placed after document separator", tokens[i+1].RawToken())
}
}
tks, err := createDocumentTokens(tokens[i+1:])
if err != nil {
return nil, err
Expand Down
48 changes: 44 additions & 4 deletions scanner/scanner.go
Original file line number Diff line number Diff line change
Expand Up @@ -255,15 +255,19 @@ func (s *Scanner) scanSingleQuote(ctx *Context) (*token.Token, error) {
isFirstLineChar = true
isNewLine = true
s.progressLine(ctx)
if idx+1 < size {
if err := s.validateDocumentSeparatorMarker(ctx, src[idx+1:]); err != nil {
return nil, err
}
}
continue
} else if isFirstLineChar && (c == ' ' || c == '\t') {
continue
} else if c != '\'' {
value = append(value, c)
isFirstLineChar = false
continue
}
if idx+1 < len(ctx.src) && ctx.src[idx+1] == '\'' {
} else if idx+1 < len(ctx.src) && ctx.src[idx+1] == '\'' {
// '' handle as ' character
value = append(value, c)
ctx.addOriginBuf(c)
Expand Down Expand Up @@ -339,6 +343,11 @@ func (s *Scanner) scanDoubleQuote(ctx *Context) (*token.Token, error) {
isFirstLineChar = true
isNewLine = true
s.progressLine(ctx)
if idx+1 < size {
if err := s.validateDocumentSeparatorMarker(ctx, src[idx+1:]); err != nil {
return nil, err
}
}
continue
} else if isFirstLineChar && (c == ' ' || c == '\t') {
continue
Expand Down Expand Up @@ -445,10 +454,20 @@ func (s *Scanner) scanDoubleQuote(ctx *Context) (*token.Token, error) {
progress = 1
ctx.addOriginBuf(nextChar)
value = append(value, nextChar)
case '0':
progress = 1
ctx.addOriginBuf(nextChar)
value = append(value, '\x00')
case ' ':
// skip escape character.
default:
value = append(value, c)
s.progressColumn(ctx, 1)
return nil, ErrInvalidToken(
token.Invalid(
fmt.Sprintf("found unknown escape character %q", nextChar),
string(ctx.obuf), s.pos(),
),
)
}
idx += progress
s.progressColumn(ctx, progress)
Expand Down Expand Up @@ -495,6 +514,26 @@ func (s *Scanner) scanDoubleQuote(ctx *Context) (*token.Token, error) {
)
}

func (s *Scanner) validateDocumentSeparatorMarker(ctx *Context, src []rune) error {
if len(src) < 3 {
return nil
}
var marker string
if len(src) == 3 {
marker = string(src)
} else {
marker = strings.TrimRightFunc(string(src[:4]), func(r rune) bool {
return r == ' ' || r == '\t' || r == '\n' || r == '\r'
})
}
Comment on lines +521 to +528
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Perhaps we can simplify:

Suggested change
var marker string
if len(src) == 3 {
marker = string(src)
} else {
marker = strings.TrimRightFunc(string(src[:4]), func(r rune) bool {
return r == ' ' || r == '\t' || r == '\n' || r == '\r'
})
}
marker := string(src)
if len(src) != 3 {
marker = strings.TrimRightFunc(string(src[:4]), unicode.IsSpace)
}

Copy link
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

IsSpace contains \v and others, so it does not compatible this function.
https://pkg.go.dev/unicode#IsSpace

if marker == "---" || marker == "..." {
return ErrInvalidToken(
token.Invalid("found unexpected document separator", string(ctx.obuf), s.pos()),
)
}
return nil
}

func (s *Scanner) scanQuote(ctx *Context, ch rune) (bool, error) {
if ctx.existsBuffer() {
return false, nil
Expand Down Expand Up @@ -719,7 +758,7 @@ func (s *Scanner) scanNewLine(ctx *Context, c rune) {

if ctx.isEOS() {
s.addBufferedTokenIfExists(ctx)
} else if s.isAnchor || s.isAlias {
} else if s.isAnchor || s.isAlias || s.isDirective {
s.addBufferedTokenIfExists(ctx)
}
if ctx.existsBuffer() && s.isFirstCharAtLine {
Expand Down Expand Up @@ -883,6 +922,7 @@ func (s *Scanner) scanDocumentEnd(ctx *Context) bool {
return false
}

s.addBufferedTokenIfExists(ctx)
ctx.addToken(token.DocumentEnd(string(ctx.obuf)+"...", s.pos()))
s.progressColumn(ctx, 3)
ctx.clear()
Expand Down
62 changes: 27 additions & 35 deletions yaml_test_suite_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -14,12 +14,12 @@ import (
)

var failureTestNames = []string{
"anchors-on-empty-scalars",
"aliases-in-flow-objects",
"aliases-in-explicit-block-mapping",
"anchors-on-empty-scalars", // no json.
"aliases-in-flow-objects", // no json.
"aliases-in-explicit-block-mapping", // no json.
"aliases-in-implicit-block-mapping",
"bare-document-after-document-end-marker",
"block-mapping-with-missing-keys",
"block-mapping-with-missing-keys", // no json.
"block-mapping-with-missing-values",
"block-mapping-with-multiline-scalars",
"block-scalar-with-more-spaces-than-first-content-line",
Expand All @@ -36,26 +36,21 @@ var failureTestNames = []string{
"escaped-slash-in-double-quotes",
"explicit-key-and-value-seperated-by-comment", //nolint: misspell
"extra-words-on-yaml-directive",
"empty-implicit-key-in-single-pair-flow-sequences",
"empty-keys-in-block-and-flow-mapping",
"empty-lines-at-end-of-document",
"flow-mapping-separate-values",
"empty-implicit-key-in-single-pair-flow-sequences", // no json.
"empty-keys-in-block-and-flow-mapping", // no json.
"empty-lines-at-end-of-document", // no json.
"flow-mapping-separate-values", // no json.
"flow-sequence-in-flow-mapping",
"flow-collections-over-many-lines/01",
"flow-mapping-colon-on-line-after-key/02",
"flow-mapping-edge-cases",
"flow-sequence-with-invalid-comma-at-the-beginning",
"folded-block-scalar",
"folded-block-scalar-1-3",
"implicit-flow-mapping-key-on-one-line",
"invalid-anchor-in-zero-indented-sequence",
"implicit-flow-mapping-key-on-one-line", // no json.
"invalid-comment-after-comma",
"invalid-comment-after-end-of-flow-sequence",
"invalid-document-end-marker-in-single-quoted-string",
"invalid-document-start-marker-in-doublequoted-tring",
"invalid-escape-in-double-quoted-string",
"invalid-tag",
"key-with-anchor-after-missing-explicit-mapping-value",
"leading-tabs-in-double-quoted/02",
"leading-tabs-in-double-quoted/05",
"legal-tab-after-indentation",
Expand All @@ -65,34 +60,31 @@ var failureTestNames = []string{
"literal-modifers/02",
"literal-modifers/03",
"literal-scalars",
"mapping-key-and-flow-sequence-item-anchors",
"mapping-starting-at-line",
"mapping-with-anchor-on-document-start-line",
"mapping-key-and-flow-sequence-item-anchors", // no json.
"multiline-double-quoted-implicit-keys",
"multiline-plain-flow-mapping-key",
"multiline-plain-value-with-tabs-on-empty-lines",
"multiline-scalar-at-top-level",
"multiline-scalar-at-top-level-1-3",
"multiline-single-quoted-implicit-keys",
"multiline-unidented-double-quoted-block-key",
"nested-implicit-complex-keys",
"nested-implicit-complex-keys", // no json.
"node-anchor-not-indented",
"plain-dashes-in-flow-sequence",
"plain-url-in-flow-mapping",
"question-mark-edge-cases/00",
"question-mark-edge-cases/01",
"question-mark-edge-cases/00", // no json.
"question-mark-edge-cases/01", // no json.
"scalar-doc-with-in-content/01",
"scalar-value-with-two-anchors",
"single-character-streams/01",
"single-pair-implicit-entries",
"spec-example-2-11-mapping-between-sequences",
"spec-example-6-12-separation-spaces",
"spec-example-7-16-flow-mapping-entries",
"spec-example-7-3-completely-empty-flow-nodes",
"spec-example-8-18-implicit-block-mapping-entries",
"spec-example-8-19-compact-block-mappings",
"single-character-streams/01", // no json.
"single-pair-implicit-entries", // no json.
"spec-example-2-11-mapping-between-sequences", // no json.
"spec-example-6-12-separation-spaces", // no json.
"spec-example-7-16-flow-mapping-entries", // no json.
"spec-example-7-3-completely-empty-flow-nodes", // no json.
"spec-example-8-18-implicit-block-mapping-entries", // no json.
"spec-example-8-19-compact-block-mappings", // no json.
"spec-example-6-19-secondary-tag-handle",
"spec-example-6-21-local-tag-prefix",
"spec-example-6-24-verbatim-tags",
"spec-example-6-28-non-specific-tags",
"spec-example-6-4-line-prefixes",
Expand All @@ -112,7 +104,7 @@ var failureTestNames = []string{
"spec-example-9-5-directives-documents",
"spec-example-9-6-stream",
"spec-example-9-6-stream-1-3",
"syntax-character-edge-cases/00",
"syntax-character-edge-cases/00", // no json.
"tab-at-beginning-of-line-followed-by-a-flow-mapping",
"tab-indented-top-flow",
"tabs-in-various-contexts/003",
Expand All @@ -126,14 +118,14 @@ var failureTestNames = []string{
"tabs-that-look-like-indentation/08",
"tag-shorthand-used-in-documents-but-only-defined-in-the-first",
"tags-for-block-objects",
"tags-on-empty-scalars",
"tags-on-empty-scalars", // no json.
"trailing-line-of-spaces/01", // last '\n' character is needed ?
"various-combinations-of-explicit-block-mappings", // no json
"various-trailing-comments", // no json
"various-trailing-comments-1-3", // no json
"various-combinations-of-explicit-block-mappings", // no json.
"various-trailing-comments", // no json.
"various-trailing-comments-1-3", // no json.
"wrong-indented-flow-sequence", // error ?
"wrong-indented-multiline-quoted-scalar", // error ?
"zero-indented-sequences-in-explicit-mapping-keys", // no json
"zero-indented-sequences-in-explicit-mapping-keys", // no json.
}

var failureTestNameMap map[string]struct{}
Expand Down