java-defects4j-jsoup-23-tokeniser

A painting is a person's account of this edit as text, recorded independently of the node mapping - a rendering often has several equally defensible answers where the mapping has one. Deletions and insertions carry no position on the opposite side in a painting, so that panel draws no caret for them.

Before

program

package_declaration

package "package"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "parser"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "helper"

. "."

identifier "Validate"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

. "."

identifier "Entities"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "ArrayList"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "List"

; ";"

block_comment "/**\n * Readers the input stream into tokens.\n */"

class_declaration

class "class"

identifier "Tokeniser"

class_body

{ "{"

field_declaration

modifiers

static "static"

final "final"

integral_type

char "char"

variable_declarator

identifier "replacementChar"

= "="

character_literal "'\\uFFFD'"

; ";"

line_comment "// replaces null character"

field_declaration

modifiers

private "private"

type_identifier "CharacterReader"

variable_declarator

identifier "reader"

; ";"

line_comment "// html input"

field_declaration

modifiers

private "private"

type_identifier "ParseErrorList"

variable_declarator

identifier "errors"

; ";"

line_comment "// errors found while tokenising"

field_declaration

modifiers

private "private"

type_identifier "TokeniserState"

variable_declarator

identifier "state"

= "="

field_access

identifier "TokeniserState"

. "."

identifier "Data"

; ";"

line_comment "// current tokenisation state"

field_declaration

modifiers

private "private"

type_identifier "Token"

variable_declarator

identifier "emitPending"

; ";"

line_comment "// the token we are about to emit on next read"

field_declaration

modifiers

private "private"

boolean_type "boolean"

variable_declarator

identifier "isEmitPending"

= "="

false "false"

; ";"

field_declaration

modifiers

private "private"

type_identifier "StringBuilder"

variable_declarator

identifier "charBuffer"

= "="

object_creation_expression

new "new"

type_identifier "StringBuilder"

argument_list

( "("

) ")"

; ";"

line_comment "// buffers characters to output as one token"

field_declaration

type_identifier "StringBuilder"

variable_declarator

identifier "dataBuffer"

; ";"

line_comment "// buffers data looking for </script>"

field_declaration

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "Tag"

variable_declarator

identifier "tagPending"

; ";"

line_comment "// tag we are building up"

field_declaration

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "Doctype"

variable_declarator

identifier "doctypePending"

; ";"

line_comment "// doctype building up"

field_declaration

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "Comment"

variable_declarator

identifier "commentPending"

; ";"

line_comment "// comment building up"

field_declaration

modifiers

private "private"

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "StartTag"

variable_declarator

identifier "lastStartTag"

; ";"

line_comment "// the last start tag emitted, to test appropriate end tag"

field_declaration

modifiers

private "private"

boolean_type "boolean"

variable_declarator

identifier "selfClosingFlagAcknowledged"

= "="

true "true"

; ";"

constructor_declaration (+33 nodes collapsed)

method_declaration (+134 nodes collapsed)

method_declaration (+166 nodes collapsed)

method_declaration (+24 nodes collapsed)

method_declaration (+23 nodes collapsed)

method_declaration

type_identifier "TokeniserState"

identifier "getState"

formal_parameters

( "("

) ")"

block

{ "{"

return_statement

return "return"

identifier "state"

; ";"

} "}"

method_declaration (+21 nodes collapsed)

method_declaration (+30 nodes collapsed)

method_declaration

void_type "void"

identifier "acknowledgeSelfClosingFlag"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

assignment_expression

identifier "selfClosingFlagAcknowledged"

= "="

true "true"

; ";"

} "}"

method_declaration

type_identifier "Character"

identifier "consumeCharacterReference"

formal_parameters

( "("

formal_parameter

type_identifier "Character"

identifier "additionalAllowedCharacter"

, ","

formal_parameter

boolean_type "boolean"

identifier "inAttribute"

) ")"

block

{ "{"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "reader"

. "."

identifier "isEmpty"

argument_list

( "("

) ")"

return_statement

return "return"

null_literal "null"

; ";"

if_statement (+25 nodes collapsed)

if_statement (+27 nodes collapsed)

expression_statement

method_invocation

identifier "reader"

. "."

identifier "mark"

argument_list

( "("

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "reader"

. "."

identifier "matchConsume"

argument_list

( "("

string_literal

" "\""

string_fragment "#"

" "\""

) ")"

block (+238 nodes collapsed)

else "else"

block

{ "{"

line_comment "// named"

line_comment "// get as many letters as possible, and look for matching en"...

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "nameRef"

= "="

method_invocation

identifier "reader"

. "."

identifier "consumeLetterSequence"

argument_list

( "("

) ")"

; ";"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "origNameRef"

= "="

object_creation_expression

new "new"

type_identifier "String"

argument_list

( "("

identifier "nameRef"

) ")"

; ";"

line_comment "// for error reporting. nameRef gets chomped looking for mat"...

local_variable_declaration

boolean_type "boolean"

variable_declarator

identifier "looksLegit"

= "="

method_invocation

identifier "reader"

. "."

identifier "matches"

argument_list

( "("

character_literal "';'"

) ")"

; ";"

local_variable_declaration

boolean_type "boolean"

variable_declarator

identifier "found"

= "="

false "false"

; ";"

while_statement (+79 nodes collapsed)

if_statement (+51 nodes collapsed)

if_statement (+58 nodes collapsed)

if_statement (+29 nodes collapsed)

line_comment "// missing semi"

return_statement

return "return"

method_invocation

identifier "Entities"

. "."

identifier "getCharacterByName"

argument_list

( "("

identifier "nameRef"

) ")"

; ";"

} "}"

method_declaration (+46 nodes collapsed)

method_declaration (+26 nodes collapsed)

method_declaration (+23 nodes collapsed)

method_declaration

void_type "void"

identifier "emitCommentPending"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

method_invocation

identifier "emit"

argument_list

( "("

identifier "commentPending"

) ")"

; ";"

} "}"

method_declaration (+23 nodes collapsed)

method_declaration

void_type "void"

identifier "emitDoctypePending"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

method_invocation

identifier "emit"

argument_list

( "("

identifier "doctypePending"

) ")"

; ";"

} "}"

method_declaration

void_type "void"

identifier "createTempBuffer"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

assignment_expression

identifier "dataBuffer"

= "="

object_creation_expression

new "new"

type_identifier "StringBuilder"

argument_list

( "("

) ")"

; ";"

} "}"

method_declaration (+26 nodes collapsed)

method_declaration

type_identifier "String"

identifier "appropriateEndTagName"

formal_parameters

( "("

) ")"

block

{ "{"

return_statement

return "return"

field_access

identifier "lastStartTag"

. "."

identifier "tagName"

; ";"

} "}"

method_declaration (+61 nodes collapsed)

method_declaration (+53 nodes collapsed)

method_declaration (+55 nodes collapsed)

method_declaration (+50 nodes collapsed)

method_declaration

boolean_type "boolean"

identifier "currentNodeInHtmlNS"

formal_parameters

( "("

) ")"

block

{ "{"

line_comment "// todo: implememnt namespaces correctly"

return_statement

return "return"

true "true"

; ";"

line_comment "// Element currentNode = currentNode();"

line_comment "// return currentNode != null && currentNode.namespace().equ"...

} "}"

After

program

package_declaration

package "package"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "parser"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "helper"

. "."

identifier "Validate"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

. "."

identifier "Entities"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "ArrayList"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "List"

; ";"

block_comment "/**\n * Readers the input stream into tokens.\n */"

class_declaration

class "class"

identifier "Tokeniser"

class_body

{ "{"

field_declaration

modifiers

static "static"

final "final"

integral_type

char "char"

variable_declarator

identifier "replacementChar"

= "="

character_literal "'\\uFFFD'"

; ";"

line_comment "// replaces null character"

field_declaration

modifiers

private "private"

type_identifier "CharacterReader"

variable_declarator

identifier "reader"

; ";"

line_comment "// html input"

field_declaration

modifiers

private "private"

type_identifier "ParseErrorList"

variable_declarator

identifier "errors"

; ";"

line_comment "// errors found while tokenising"

field_declaration

modifiers

private "private"

type_identifier "TokeniserState"

variable_declarator

identifier "state"

= "="

field_access

identifier "TokeniserState"

. "."

identifier "Data"

; ";"

line_comment "// current tokenisation state"

field_declaration

modifiers

private "private"

type_identifier "Token"

variable_declarator

identifier "emitPending"

; ";"

line_comment "// the token we are about to emit on next read"

field_declaration

modifiers

private "private"

boolean_type "boolean"

variable_declarator

identifier "isEmitPending"

= "="

false "false"

; ";"

field_declaration

modifiers

private "private"

type_identifier "StringBuilder"

variable_declarator

identifier "charBuffer"

= "="

object_creation_expression

new "new"

type_identifier "StringBuilder"

argument_list

( "("

) ")"

; ";"

line_comment "// buffers characters to output as one token"

field_declaration

type_identifier "StringBuilder"

variable_declarator

identifier "dataBuffer"

; ";"

line_comment "// buffers data looking for </script>"

field_declaration

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "Tag"

variable_declarator

identifier "tagPending"

; ";"

line_comment "// tag we are building up"

field_declaration

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "Doctype"

variable_declarator

identifier "doctypePending"

; ";"

line_comment "// doctype building up"

field_declaration

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "Comment"

variable_declarator

identifier "commentPending"

; ";"

line_comment "// comment building up"

field_declaration

modifiers

private "private"

scoped_type_identifier

type_identifier "Token"

. "."

type_identifier "StartTag"

variable_declarator

identifier "lastStartTag"

; ";"

line_comment "// the last start tag emitted, to test appropriate end tag"

field_declaration

modifiers

private "private"

boolean_type "boolean"

variable_declarator

identifier "selfClosingFlagAcknowledged"

= "="

true "true"

; ";"

constructor_declaration (+33 nodes collapsed)

method_declaration (+134 nodes collapsed)

method_declaration (+166 nodes collapsed)

method_declaration (+24 nodes collapsed)

method_declaration (+23 nodes collapsed)

method_declaration

type_identifier "TokeniserState"

identifier "getState"

formal_parameters

( "("

) ")"

block

{ "{"

return_statement

return "return"

identifier "state"

; ";"

} "}"

method_declaration (+21 nodes collapsed)

method_declaration (+30 nodes collapsed)

method_declaration

void_type "void"

identifier "acknowledgeSelfClosingFlag"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

assignment_expression

identifier "selfClosingFlagAcknowledged"

= "="

true "true"

; ";"

} "}"

method_declaration

type_identifier "Character"

identifier "consumeCharacterReference"

formal_parameters

( "("

formal_parameter

type_identifier "Character"

identifier "additionalAllowedCharacter"

, ","

formal_parameter

boolean_type "boolean"

identifier "inAttribute"

) ")"

block

{ "{"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "reader"

. "."

identifier "isEmpty"

argument_list

( "("

) ")"

return_statement

return "return"

null_literal "null"

; ";"

if_statement (+25 nodes collapsed)

if_statement (+27 nodes collapsed)

expression_statement

method_invocation

identifier "reader"

. "."

identifier "mark"

argument_list

( "("

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "reader"

. "."

identifier "matchConsume"

argument_list

( "("

string_literal

" "\""

string_fragment "#"

" "\""

) ")"

block (+238 nodes collapsed)

else "else"

block

{ "{"

line_comment "// named"

line_comment "// get as many letters as possible, and look for matching en"...

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "nameRef"

= "="

method_invocation

identifier "reader"

. "."

identifier "consumeLetterThenDigitSequence"

argument_list

( "("

) ")"

; ";"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "origNameRef"

= "="

object_creation_expression

new "new"

type_identifier "String"

argument_list

( "("

identifier "nameRef"

) ")"

; ";"

line_comment "// for error reporting. nameRef gets chomped looking for mat"...

local_variable_declaration

boolean_type "boolean"

variable_declarator

identifier "looksLegit"

= "="

method_invocation

identifier "reader"

. "."

identifier "matches"

argument_list

( "("

character_literal "';'"

) ")"

; ";"

local_variable_declaration

boolean_type "boolean"

variable_declarator

identifier "found"

= "="

false "false"

; ";"

while_statement (+79 nodes collapsed)

if_statement (+51 nodes collapsed)

if_statement (+58 nodes collapsed)

if_statement (+29 nodes collapsed)

line_comment "// missing semi"

return_statement

return "return"

method_invocation

identifier "Entities"

. "."

identifier "getCharacterByName"

argument_list

( "("

identifier "nameRef"

) ")"

; ";"

} "}"

method_declaration (+46 nodes collapsed)

method_declaration (+26 nodes collapsed)

method_declaration (+23 nodes collapsed)

method_declaration

void_type "void"

identifier "emitCommentPending"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

method_invocation

identifier "emit"

argument_list

( "("

identifier "commentPending"

) ")"

; ";"

} "}"

method_declaration (+23 nodes collapsed)

method_declaration

void_type "void"

identifier "emitDoctypePending"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

method_invocation

identifier "emit"

argument_list

( "("

identifier "doctypePending"

) ")"

; ";"

} "}"

method_declaration

void_type "void"

identifier "createTempBuffer"

formal_parameters

( "("

) ")"

block

{ "{"

expression_statement

assignment_expression

identifier "dataBuffer"

= "="

object_creation_expression

new "new"

type_identifier "StringBuilder"

argument_list

( "("

) ")"

; ";"

} "}"

method_declaration (+26 nodes collapsed)

method_declaration

type_identifier "String"

identifier "appropriateEndTagName"

formal_parameters

( "("

) ")"

block

{ "{"

return_statement

return "return"

field_access

identifier "lastStartTag"

. "."

identifier "tagName"

; ";"

} "}"

method_declaration (+61 nodes collapsed)

method_declaration (+53 nodes collapsed)

method_declaration (+55 nodes collapsed)

method_declaration (+50 nodes collapsed)

method_declaration

boolean_type "boolean"

identifier "currentNodeInHtmlNS"

formal_parameters

( "("

) ")"

block

{ "{"

line_comment "// todo: implememnt namespaces correctly"

return_statement

return "return"

true "true"

; ";"

line_comment "// Element currentNode = currentNode();"

line_comment "// return currentNode != null && currentNode.namespace().equ"...

} "}"