java-defects4j-jsoup-7-document

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.

Before1package org.jsoup.nodes;
2
3import org.jsoup.helper.Validate;
4import org.jsoup.parser.Tag;
5
6import java.nio.charset.Charset;
7import java.nio.charset.CharsetEncoder;
8import java.util.ArrayList;
9import java.util.List;
10
11/**
…lines 12–105 unchanged (94 lines)
106
107        // pull text nodes out of root, html, and head els, and push into body. non-text nodes are already taken care
108        // of. do in inverse order to maintain text order.
109        normaliseTextNodes(head());
110        normaliseTextNodes(htmlEl);
111        normaliseTextNodes(this);
112
113        
114        return this;
115    }
116
117    // does not recurse.
118    private void normaliseTextNodes(Element element) {
…lines 119–130 unchanged (12 lines)
131            body().prependChild(new TextNode(" ", ""));
132            body().prependChild(node);
133        }
134    }
135
136    // merge multiple <head> or <body> contents into one, delete the remainder, and ensure they are owned by <html>
137        // ensure parented by <html>
138
139    // fast method to get first by tag name, used for html, head, body finders
140    private Element findFirstElementByTagName(String tag, Node node) {
141        if (node.nodeName().equals(tag))
142            return (Element) node;
143        else {
144            for (Node child: node.childNodes) {
…lines 145–294 unchanged (150 lines)

After1package org.jsoup.nodes;
2
3import org.jsoup.helper.Validate;
4import org.jsoup.parser.Tag;
5import org.jsoup.select.Elements;
6
7import java.nio.charset.Charset;
8import java.nio.charset.CharsetEncoder;
9import java.util.ArrayList;
10import java.util.List;
11
…lines 12–107 unchanged (96 lines)
108        // pull text nodes out of root, html, and head els, and push into body. non-text nodes are already taken care
109        // of. do in inverse order to maintain text order.
110        normaliseTextNodes(head());
111        normaliseTextNodes(htmlEl);
112        normaliseTextNodes(this);
113
114        normaliseStructure("head", htmlEl);
115        normaliseStructure("body", htmlEl);
116        
117        return this;
118    }
119
120    // does not recurse.
121    private void normaliseTextNodes(Element element) {
…lines 122–133 unchanged (12 lines)
134            body().prependChild(new TextNode(" ", ""));
135            body().prependChild(node);
136        }
137    }
138
139    // merge multiple <head> or <body> contents into one, delete the remainder, and ensure they are owned by <html>
140    private void normaliseStructure(String tag, Element htmlEl) {
141        Elements elements = this.getElementsByTag(tag);
142        Element master = elements.first(); // will always be available as created above if not existent
143        if (elements.size() > 1) { // dupes, move contents to master
144            List<Node> toMove = new ArrayList<Node>();
145            for (int i = 1; i < elements.size(); i++) {
146                Node dupe = elements.get(i);
147                for (Node node : dupe.childNodes)
148                    toMove.add(node);
149                dupe.remove();
150            }
151
152            for (Node dupe : toMove)
153                master.appendChild(dupe);
154        }
155        // ensure parented by <html>
156        if (!master.parent().equals(htmlEl)) {
157            htmlEl.appendChild(master); // includes remove()            
158        }
159    }
160
161    // fast method to get first by tag name, used for html, head, body finders
162    private Element findFirstElementByTagName(String tag, Node node) {
163        if (node.nodeName().equals(tag))
164            return (Element) node;
165        else {
…lines 166–316 unchanged (151 lines)

Before1package org.jsoup.nodes;
2
3import org.jsoup.helper.Validate;
4import org.jsoup.parser.Tag;
5
6import java.nio.charset.Charset;
7import java.nio.charset.CharsetEncoder;
8import java.util.ArrayList;
9import java.util.List;
10
11/**
…lines 12–105 unchanged (94 lines)
106
107        // pull text nodes out of root, html, and head els, and push into body. non-text nodes are already taken care
108        // of. do in inverse order to maintain text order.
109        normaliseTextNodes(head());
110        normaliseTextNodes(htmlEl);
111        normaliseTextNodes(this);
112
113        
114        return this;
115    }
116
117    // does not recurse.
118    private void normaliseTextNodes(Element element) {
…lines 119–130 unchanged (12 lines)
131            body().prependChild(new TextNode(" ", ""));
132            body().prependChild(node);
133        }
134    }
135
136    // merge multiple <head> or <body> contents into one, delete the remainder, and ensure they are owned by <html>
137        // ensure parented by <html>
138
139    // fast method to get first by tag name, used for html, head, body finders
140    private Element findFirstElementByTagName(String tag, Node node) {
141        if (node.nodeName().equals(tag))
142            return (Element) node;
143        else {
144            for (Node child: node.childNodes) {
…lines 145–294 unchanged (150 lines)

After1package org.jsoup.nodes;
2
3import org.jsoup.helper.Validate;
4import org.jsoup.parser.Tag;
5import org.jsoup.select.Elements;
6
7import java.nio.charset.Charset;
8import java.nio.charset.CharsetEncoder;
9import java.util.ArrayList;
10import java.util.List;
11
…lines 12–107 unchanged (96 lines)
108        // pull text nodes out of root, html, and head els, and push into body. non-text nodes are already taken care
109        // of. do in inverse order to maintain text order.
110        normaliseTextNodes(head());
111        normaliseTextNodes(htmlEl);
112        normaliseTextNodes(this);
113
114        normaliseStructure("head", htmlEl);
115        normaliseStructure("body", htmlEl);
116        
117        return this;
118    }
119
120    // does not recurse.
121    private void normaliseTextNodes(Element element) {
…lines 122–133 unchanged (12 lines)
134            body().prependChild(new TextNode(" ", ""));
135            body().prependChild(node);
136        }
137    }
138
139    // merge multiple <head> or <body> contents into one, delete the remainder, and ensure they are owned by <html>
140    private void normaliseStructure(String tag, Element htmlEl) {
141        Elements elements = this.getElementsByTag(tag);
142        Element master = elements.first(); // will always be available as created above if not existent
143        if (elements.size() > 1) { // dupes, move contents to master
144            List<Node> toMove = new ArrayList<Node>();
145            for (int i = 1; i < elements.size(); i++) {
146                Node dupe = elements.get(i);
147                for (Node node : dupe.childNodes)
148                    toMove.add(node);
149                dupe.remove();
150            }
151
152            for (Node dupe : toMove)
153                master.appendChild(dupe);
154        }
155        // ensure parented by <html>
156        if (!master.parent().equals(htmlEl)) {
157            htmlEl.appendChild(master); // includes remove()            
158        }
159    }
160
161    // fast method to get first by tag name, used for html, head, body finders
162    private Element findFirstElementByTagName(String tag, Node node) {
163        if (node.nodeName().equals(tag))
164            return (Element) node;
165        else {
…lines 166–316 unchanged (151 lines)

Before1package org.jsoup.nodes;
2
3import org.jsoup.helper.Validate;
4import org.jsoup.parser.Tag;
5
6import java.nio.charset.Charset;
7import java.nio.charset.CharsetEncoder;
8import java.util.ArrayList;
9import java.util.List;
10
11/**
…lines 12–105 unchanged (94 lines)
106
107        // pull text nodes out of root, html, and head els, and push into body. non-text nodes are already taken care
108        // of. do in inverse order to maintain text order.
109        normaliseTextNodes(head());
110        normaliseTextNodes(htmlEl);
111        normaliseTextNodes(this);
112
113        
114        return this;
115    }
116
117    // does not recurse.
118    private void normaliseTextNodes(Element element) {
…lines 119–130 unchanged (12 lines)
131            body().prependChild(new TextNode(" ", ""));
132            body().prependChild(node);
133        }
134    }
135
136    // merge multiple <head> or <body> contents into one, delete the remainder, and ensure they are owned by <html>
137        // ensure parented by <html>
138
139    // fast method to get first by tag name, used for html, head, body finders
140    private Element findFirstElementByTagName(String tag, Node node) {
141        if (node.nodeName().equals(tag))
142            return (Element) node;
143        else {
144            for (Node child: node.childNodes) {
…lines 145–294 unchanged (150 lines)

After1package org.jsoup.nodes;
2
3import org.jsoup.helper.Validate;
4import org.jsoup.parser.Tag;
5import org.jsoup.select.Elements;
6
7import java.nio.charset.Charset;
8import java.nio.charset.CharsetEncoder;
9import java.util.ArrayList;
10import java.util.List;
11
…lines 12–107 unchanged (96 lines)
108        // pull text nodes out of root, html, and head els, and push into body. non-text nodes are already taken care
109        // of. do in inverse order to maintain text order.
110        normaliseTextNodes(head());
111        normaliseTextNodes(htmlEl);
112        normaliseTextNodes(this);
113
114        normaliseStructure("head", htmlEl);
115        normaliseStructure("body", htmlEl);
116        
117        return this;
118    }
119
120    // does not recurse.
121    private void normaliseTextNodes(Element element) {
…lines 122–133 unchanged (12 lines)
134            body().prependChild(new TextNode(" ", ""));
135            body().prependChild(node);
136        }
137    }
138
139    // merge multiple <head> or <body> contents into one, delete the remainder, and ensure they are owned by <html>
140    private void normaliseStructure(String tag, Element htmlEl) {
141        Elements elements = this.getElementsByTag(tag);
142        Element master = elements.first(); // will always be available as created above if not existent
143        if (elements.size() > 1) { // dupes, move contents to master
144            List<Node> toMove = new ArrayList<Node>();
145            for (int i = 1; i < elements.size(); i++) {
146                Node dupe = elements.get(i);
147                for (Node node : dupe.childNodes)
148                    toMove.add(node);
149                dupe.remove();
150            }
151
152            for (Node dupe : toMove)
153                master.appendChild(dupe);
154        }
155        // ensure parented by <html>
156        if (!master.parent().equals(htmlEl)) {
157            htmlEl.appendChild(master); // includes remove()            
158        }
159    }
160
161    // fast method to get first by tag name, used for html, head, body finders
162    private Element findFirstElementByTagName(String tag, Node node) {
163        if (node.nodeName().equals(tag))
164            return (Element) node;
165        else {
…lines 166–316 unchanged (151 lines)

Before

program

package_declaration

package "package"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

; ";"

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 "parser"

. "."

identifier "Tag"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "nio"

. "."

identifier "charset"

. "."

identifier "Charset"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "nio"

. "."

identifier "charset"

. "."

identifier "CharsetEncoder"

; ";"

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 A HTML Document.\n\n @author Jonathan Hedley, jonathan@he"...

class_declaration

modifiers

public "public"

class "class"

identifier "Document"

superclass

extends "extends"

type_identifier "Element"

class_body

{ "{"

field_declaration

modifiers

private "private"

type_identifier "OutputSettings"

variable_declarator

identifier "outputSettings"

= "="

object_creation_expression

new "new"

type_identifier "OutputSettings"

argument_list

( "("

) ")"

; ";"

block_comment "/**\n Create a new, empty Document.\n @param baseUri b"...

constructor_declaration (+32 nodes collapsed)

block_comment "/**\n Create a valid, empty shell of a document, suitable"...

method_declaration (+85 nodes collapsed)

block_comment "/**\n Accessor to the document's {@code head} element.\n "...

method_declaration (+25 nodes collapsed)

block_comment "/**\n Accessor to the document's {@code body} element.\n "...

method_declaration (+25 nodes collapsed)

block_comment "/**\n Get the string contents of the document's {@code ti"...

method_declaration (+58 nodes collapsed)

block_comment "/**\n Set the document's {@code title} element. Updates t"...

method_declaration (+96 nodes collapsed)

block_comment "/**\n Create a new Element, with this document's base uri"...

method_declaration (+39 nodes collapsed)

block_comment "/**\n Normalise the document. This happens after the pars"...

method_declaration

modifiers

public "public"

type_identifier "Document"

identifier "normalise"

formal_parameters

( "("

) ")"

block

{ "{"

local_variable_declaration

type_identifier "Element"

variable_declarator

identifier "htmlEl"

= "="

method_invocation

identifier "findFirstElementByTagName"

argument_list

( "("

string_literal

" "\""

string_fragment "html"

" "\""

, ","

this "this"

) ")"

; ";"

if_statement (+23 nodes collapsed)

if_statement (+26 nodes collapsed)

line_comment "// pull text nodes out of root, html, and head els, and push"...

line_comment "// of. do in inverse order to maintain text order."

expression_statement

method_invocation

identifier "normaliseTextNodes"

argument_list

( "("

method_invocation

identifier "head"

argument_list

( "("

) ")"

; ";"

expression_statement

method_invocation

identifier "normaliseTextNodes"

argument_list

( "("

identifier "htmlEl"

) ")"

; ";"

expression_statement

method_invocation

identifier "normaliseTextNodes"

argument_list

( "("

this "this"

) ")"

; ";"

return_statement

return "return"

this "this"

; ";"

} "}"

line_comment "// does not recurse."

method_declaration (+194 nodes collapsed)

line_comment "// merge multiple <head> or <body> contents into one, delete"...

line_comment "// ensure parented by <html>"

line_comment "// fast method to get first by tag name, used for html, head"...

method_declaration (+94 nodes collapsed)

method_declaration (+25 nodes collapsed)

block_comment "/**\n Set the text of the {@code body} of this document. "...

method_declaration (+36 nodes collapsed)

method_declaration (+21 nodes collapsed)

block_comment "/**\n * A Document's output settings control the form of "...

class_declaration (+343 nodes collapsed)

block_comment "/**\n * Get the document's current output settings.\n "...

method_declaration

modifiers

public "public"

type_identifier "OutputSettings"

identifier "outputSettings"

formal_parameters

( "("

) ")"

block

{ "{"

return_statement

return "return"

identifier "outputSettings"

; ";"

} "}"

After

program

package_declaration

package "package"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

; ";"

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 "parser"

. "."

identifier "Tag"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "select"

. "."

identifier "Elements"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "nio"

. "."

identifier "charset"

. "."

identifier "Charset"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "nio"

. "."

identifier "charset"

. "."

identifier "CharsetEncoder"

; ";"

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 A HTML Document.\n\n @author Jonathan Hedley, jonathan@he"...

class_declaration

modifiers

public "public"

class "class"

identifier "Document"

superclass

extends "extends"

type_identifier "Element"

class_body

{ "{"

field_declaration

modifiers

private "private"

type_identifier "OutputSettings"

variable_declarator

identifier "outputSettings"

= "="

object_creation_expression

new "new"

type_identifier "OutputSettings"

argument_list

( "("

) ")"

; ";"

block_comment "/**\n Create a new, empty Document.\n @param baseUri b"...

constructor_declaration (+32 nodes collapsed)

block_comment "/**\n Create a valid, empty shell of a document, suitable"...

method_declaration (+85 nodes collapsed)

block_comment "/**\n Accessor to the document's {@code head} element.\n "...

method_declaration (+25 nodes collapsed)

block_comment "/**\n Accessor to the document's {@code body} element.\n "...

method_declaration (+25 nodes collapsed)

block_comment "/**\n Get the string contents of the document's {@code ti"...

method_declaration (+58 nodes collapsed)

block_comment "/**\n Set the document's {@code title} element. Updates t"...

method_declaration (+96 nodes collapsed)

block_comment "/**\n Create a new Element, with this document's base uri"...

method_declaration (+39 nodes collapsed)

block_comment "/**\n Normalise the document. This happens after the pars"...

method_declaration

modifiers

public "public"

type_identifier "Document"

identifier "normalise"

formal_parameters

( "("

) ")"

block

{ "{"

local_variable_declaration

type_identifier "Element"

variable_declarator

identifier "htmlEl"

= "="

method_invocation

identifier "findFirstElementByTagName"

argument_list

( "("

string_literal

" "\""

string_fragment "html"

" "\""

, ","

this "this"

) ")"

; ";"

if_statement (+23 nodes collapsed)

if_statement (+26 nodes collapsed)

line_comment "// pull text nodes out of root, html, and head els, and push"...

line_comment "// of. do in inverse order to maintain text order."

expression_statement

method_invocation

identifier "normaliseTextNodes"

argument_list

( "("

method_invocation

identifier "head"

argument_list

( "("

) ")"

; ";"

expression_statement

method_invocation

identifier "normaliseTextNodes"

argument_list

( "("

identifier "htmlEl"

) ")"

; ";"

expression_statement

method_invocation

identifier "normaliseTextNodes"

argument_list

( "("

this "this"

) ")"

; ";"

expression_statement

method_invocation

identifier "normaliseStructure"

argument_list

( "("

string_literal

" "\""

string_fragment "head"

" "\""

, ","

identifier "htmlEl"

) ")"

; ";"

expression_statement

method_invocation

identifier "normaliseStructure"

argument_list

( "("

string_literal

" "\""

string_fragment "body"

" "\""

, ","

identifier "htmlEl"

) ")"

; ";"

return_statement

return "return"

this "this"

; ";"

} "}"

line_comment "// does not recurse."

method_declaration (+194 nodes collapsed)

line_comment "// merge multiple <head> or <body> contents into one, delete"...

method_declaration

modifiers

private "private"

void_type "void"

identifier "normaliseStructure"

formal_parameters

( "("

formal_parameter

type_identifier "String"

identifier "tag"

, ","

formal_parameter

type_identifier "Element"

identifier "htmlEl"

) ")"

block

{ "{"

local_variable_declaration

type_identifier "Elements"

variable_declarator

identifier "elements"

= "="

method_invocation

this "this"

. "."

identifier "getElementsByTag"

argument_list

( "("

identifier "tag"

) ")"

; ";"

local_variable_declaration

type_identifier "Element"

variable_declarator

identifier "master"

= "="

method_invocation

identifier "elements"

. "."

identifier "first"

argument_list

( "("

) ")"

; ";"

line_comment "// will always be available as created above if not existent"

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

method_invocation

identifier "elements"

. "."

identifier "size"

argument_list

( "("

) ")"

> ">"

decimal_integer_literal "1"

) ")"

block

{ "{"

line_comment "// dupes, move contents to master"

local_variable_declaration

generic_type

type_identifier "List"

type_arguments

< "<"

type_identifier "Node"

> ">"

variable_declarator

identifier "toMove"

= "="

object_creation_expression

new "new"

generic_type

type_identifier "ArrayList"

type_arguments

< "<"

type_identifier "Node"

> ">"

argument_list

( "("

) ")"

; ";"

for_statement

for "for"

( "("

local_variable_declaration

integral_type

int "int"

variable_declarator

identifier "i"

= "="

decimal_integer_literal "1"

; ";"

binary_expression

identifier "i"

< "<"

method_invocation

identifier "elements"

. "."

identifier "size"

argument_list

( "("

) ")"

; ";"

update_expression

identifier "i"

++ "++"

) ")"

block

{ "{"

local_variable_declaration

type_identifier "Node"

variable_declarator

identifier "dupe"

= "="

method_invocation

identifier "elements"

. "."

identifier "get"

argument_list

( "("

identifier "i"

) ")"

; ";"

enhanced_for_statement

for "for"

( "("

type_identifier "Node"

identifier "node"

: ":"

field_access

identifier "dupe"

. "."

identifier "childNodes"

) ")"

expression_statement

method_invocation

identifier "toMove"

. "."

identifier "add"

argument_list

( "("

identifier "node"

) ")"

; ";"

expression_statement

method_invocation

identifier "dupe"

. "."

identifier "remove"

argument_list

( "("

) ")"

; ";"

} "}"

enhanced_for_statement

for "for"

( "("

type_identifier "Node"

identifier "dupe"

: ":"

identifier "toMove"

) ")"

expression_statement

method_invocation

identifier "master"

. "."

identifier "appendChild"

argument_list

( "("

identifier "dupe"

) ")"

; ";"

} "}"

line_comment "// ensure parented by <html>"

if_statement

if "if"

parenthesized_expression

( "("

unary_expression

! "!"

method_invocation

identifier "master"

. "."

identifier "parent"

argument_list

( "("

) ")"

. "."

identifier "equals"

argument_list

( "("

identifier "htmlEl"

) ")"

block

{ "{"

expression_statement

method_invocation

identifier "htmlEl"

. "."

identifier "appendChild"

argument_list

( "("

identifier "master"

) ")"

; ";"

line_comment "// includes remove() "

} "}"

line_comment "// fast method to get first by tag name, used for html, head"...

method_declaration (+94 nodes collapsed)

method_declaration (+25 nodes collapsed)

block_comment "/**\n Set the text of the {@code body} of this document. "...

method_declaration (+36 nodes collapsed)

method_declaration (+21 nodes collapsed)

block_comment "/**\n * A Document's output settings control the form of "...

class_declaration (+343 nodes collapsed)

block_comment "/**\n * Get the document's current output settings.\n "...

method_declaration

modifiers

public "public"

type_identifier "OutputSettings"

identifier "outputSettings"

formal_parameters

( "("

) ")"

block

{ "{"

return_statement

return "return"

identifier "outputSettings"

; ";"

} "}"