java-defects4j-jsoup-36-datautil

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.helper;
2
3import org.jsoup.nodes.Document;
4import org.jsoup.nodes.Element;
5import org.jsoup.parser.Parser;
6
7import java.io.*;
8import java.nio.ByteBuffer;
9import java.nio.charset.Charset;
10import java.util.regex.Matcher;
11import java.util.regex.Pattern;
12import java.util.Locale;
13
14/**
15 * Internal static utilities for handling data.
16 *
17 */
18public class DataUtil {
19    private static final Pattern charsetPattern = Pattern.compile("(?i)\\bcharset=\\s*\"?([^\\s;\"]*)");
20    static final String defaultCharset = "UTF-8"; // used if not found in header or meta charset
21    private static final int bufferSize = 0x20000; // ~130K.
22
23    private DataUtil() {}
24
25    /**
…lines 26–80 unchanged (55 lines)
81            Element meta = doc.select("meta[http-equiv=content-type], meta[charset]").first();
82            if (meta != null) { // if not found, will keep utf-8 as best attempt
83
84                String foundCharset;
85                if (meta.hasAttr("http-equiv")) {
86                    foundCharset = getCharsetFromContentType(meta.attr("content"));
87                } else {
88                    foundCharset = meta.attr("charset");
89                }
90
91                if (foundCharset != null && foundCharset.length() != 0 && !foundCharset.equals(defaultCharset)) { // need to re-decode
92                    charsetName = foundCharset;
93                    byteData.rewind();
94                    docData = Charset.forName(foundCharset).decode(byteData).toString();
95                    doc = null;
96                }
97            }
98        } else { // specified by content type header (or by user on file load)
…lines 99–154 unchanged (56 lines)
155     */
156    static String getCharsetFromContentType(String contentType) {
157        if (contentType == null) return null;
158        Matcher m = charsetPattern.matcher(contentType);
159        if (m.find()) {
160            String charset = m.group(1).trim();
161                if (Charset.isSupported(charset)) return charset;
162                charset = charset.toUpperCase(Locale.ENGLISH);
163                if (Charset.isSupported(charset)) return charset;
164                // if our advanced charset matching fails.... we just take the default
165        }
166        return null;
167    }
168    
169    
170}
171

After1package org.jsoup.helper;
2
3import org.jsoup.nodes.Document;
4import org.jsoup.nodes.Element;
5import org.jsoup.parser.Parser;
6
7import java.io.*;
8import java.nio.ByteBuffer;
9import java.nio.charset.Charset;
10import java.nio.charset.IllegalCharsetNameException;
11import java.util.regex.Matcher;
12import java.util.regex.Pattern;
13import java.util.Locale;
14
15/**
16 * Internal static utilities for handling data.
17 *
18 */
19public class DataUtil {
20    private static final Pattern charsetPattern = Pattern.compile("(?i)\\bcharset=\\s*(?:\"|')?([^\\s,;\"']*)");
21    static final String defaultCharset = "UTF-8"; // used if not found in header or meta charset
22    private static final int bufferSize = 0x20000; // ~130K.
23
24    private DataUtil() {}
25
26    /**
…lines 27–81 unchanged (55 lines)
82            Element meta = doc.select("meta[http-equiv=content-type], meta[charset]").first();
83            if (meta != null) { // if not found, will keep utf-8 as best attempt
84
85                String foundCharset;
86                if (meta.hasAttr("http-equiv")) {
87                    foundCharset = getCharsetFromContentType(meta.attr("content"));
88                    if (foundCharset == null && meta.hasAttr("charset")) {
89                        try {
90                            if (Charset.isSupported(meta.attr("charset"))) {
91                                foundCharset = meta.attr("charset");
92                            }
93                        } catch (IllegalCharsetNameException e) {
94                            foundCharset = null;
95                        }
96                    }
97                } else {
98                    foundCharset = meta.attr("charset");
99                }
100
101                if (foundCharset != null && foundCharset.length() != 0 && !foundCharset.equals(defaultCharset)) { // need to re-decode
102                    foundCharset = foundCharset.trim().replaceAll("[\"']", "");
103                    charsetName = foundCharset;
104                    byteData.rewind();
105                    docData = Charset.forName(foundCharset).decode(byteData).toString();
106                    doc = null;
107                }
108            }
…lines 109–165 unchanged (57 lines)
166     */
167    static String getCharsetFromContentType(String contentType) {
168        if (contentType == null) return null;
169        Matcher m = charsetPattern.matcher(contentType);
170        if (m.find()) {
171            String charset = m.group(1).trim();
172            charset = charset.replace("charset=", "");
173            if (charset.isEmpty()) return null;
174            try {
175                if (Charset.isSupported(charset)) return charset;
176                charset = charset.toUpperCase(Locale.ENGLISH);
177                if (Charset.isSupported(charset)) return charset;
178            } catch (IllegalCharsetNameException e) {
179                // if our advanced charset matching fails.... we just take the default
180                return null;
181            }
182        }
183        return null;
184    }
185    
186    
187}
188

Before1package org.jsoup.helper;
2
3import org.jsoup.nodes.Document;
4import org.jsoup.nodes.Element;
5import org.jsoup.parser.Parser;
6
7import java.io.*;
8import java.nio.ByteBuffer;
9import java.nio.charset.Charset;
10import java.util.regex.Matcher;
11import java.util.regex.Pattern;
12import java.util.Locale;
13
14/**
15 * Internal static utilities for handling data.
16 *
17 */
18public class DataUtil {
19    private static final Pattern charsetPattern = Pattern.compile("(?i)\\bcharset=\\s*\"?([^\\s;\"]*)");
20    static final String defaultCharset = "UTF-8"; // used if not found in header or meta charset
21    private static final int bufferSize = 0x20000; // ~130K.
22
23    private DataUtil() {}
24
25    /**
…lines 26–80 unchanged (55 lines)
81            Element meta = doc.select("meta[http-equiv=content-type], meta[charset]").first();
82            if (meta != null) { // if not found, will keep utf-8 as best attempt
83
84                String foundCharset;
85                if (meta.hasAttr("http-equiv")) {
86                    foundCharset = getCharsetFromContentType(meta.attr("content"));
87                } else {
88                    foundCharset = meta.attr("charset");
89                }
90
91                if (foundCharset != null && foundCharset.length() != 0 && !foundCharset.equals(defaultCharset)) { // need to re-decode
92                    charsetName = foundCharset;
93                    byteData.rewind();
94                    docData = Charset.forName(foundCharset).decode(byteData).toString();
95                    doc = null;
96                }
97            }
98        } else { // specified by content type header (or by user on file load)
…lines 99–154 unchanged (56 lines)
155     */
156    static String getCharsetFromContentType(String contentType) {
157        if (contentType == null) return null;
158        Matcher m = charsetPattern.matcher(contentType);
159        if (m.find()) {
160            String charset = m.group(1).trim();
161                if (Charset.isSupported(charset)) return charset;
162                charset = charset.toUpperCase(Locale.ENGLISH);
163                if (Charset.isSupported(charset)) return charset;
164                // if our advanced charset matching fails.... we just take the default
165        }
166        return null;
167    }
168    
169    
170}
171

After1package org.jsoup.helper;
2
3import org.jsoup.nodes.Document;
4import org.jsoup.nodes.Element;
5import org.jsoup.parser.Parser;
6
7import java.io.*;
8import java.nio.ByteBuffer;
9import java.nio.charset.Charset;
10import java.nio.charset.IllegalCharsetNameException;
11import java.util.regex.Matcher;
12import java.util.regex.Pattern;
13import java.util.Locale;
14
15/**
16 * Internal static utilities for handling data.
17 *
18 */
19public class DataUtil {
20    private static final Pattern charsetPattern = Pattern.compile("(?i)\\bcharset=\\s*(?:\"|')?([^\\s,;\"']*)");
21    static final String defaultCharset = "UTF-8"; // used if not found in header or meta charset
22    private static final int bufferSize = 0x20000; // ~130K.
23
24    private DataUtil() {}
25
26    /**
…lines 27–81 unchanged (55 lines)
82            Element meta = doc.select("meta[http-equiv=content-type], meta[charset]").first();
83            if (meta != null) { // if not found, will keep utf-8 as best attempt
84
85                String foundCharset;
86                if (meta.hasAttr("http-equiv")) {
87                    foundCharset = getCharsetFromContentType(meta.attr("content"));
88                    if (foundCharset == null && meta.hasAttr("charset")) {
89                        try {
90                            if (Charset.isSupported(meta.attr("charset"))) {
91                                foundCharset = meta.attr("charset");
92                            }
93                        } catch (IllegalCharsetNameException e) {
94                            foundCharset = null;
95                        }
96                    }
97                } else {
98                    foundCharset = meta.attr("charset");
99                }
100
101                if (foundCharset != null && foundCharset.length() != 0 && !foundCharset.equals(defaultCharset)) { // need to re-decode
102                    foundCharset = foundCharset.trim().replaceAll("[\"']", "");
103                    charsetName = foundCharset;
104                    byteData.rewind();
105                    docData = Charset.forName(foundCharset).decode(byteData).toString();
106                    doc = null;
107                }
108            }
…lines 109–165 unchanged (57 lines)
166     */
167    static String getCharsetFromContentType(String contentType) {
168        if (contentType == null) return null;
169        Matcher m = charsetPattern.matcher(contentType);
170        if (m.find()) {
171            String charset = m.group(1).trim();
172            charset = charset.replace("charset=", "");
173            if (charset.isEmpty()) return null;
174            try {
175                if (Charset.isSupported(charset)) return charset;
176                charset = charset.toUpperCase(Locale.ENGLISH);
177                if (Charset.isSupported(charset)) return charset;
178            } catch (IllegalCharsetNameException e) {
179                // if our advanced charset matching fails.... we just take the default
180                return null;
181            }
182        }
183        return null;
184    }
185    
186    
187}
188

Before

program

package_declaration

package "package"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "helper"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

. "."

identifier "Document"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

. "."

identifier "Element"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "parser"

. "."

identifier "Parser"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "io"

. "."

asterisk

* "*"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "nio"

. "."

identifier "ByteBuffer"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "nio"

. "."

identifier "charset"

. "."

identifier "Charset"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "regex"

. "."

identifier "Matcher"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "regex"

. "."

identifier "Pattern"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "Locale"

; ";"

block_comment "/**\n * Internal static utilities for handling data.\n *\n */"

class_declaration

modifiers

public "public"

class "class"

identifier "DataUtil"

class_body

{ "{"

field_declaration

modifiers

private "private"

static "static"

final "final"

type_identifier "Pattern"

variable_declarator

identifier "charsetPattern"

= "="

method_invocation

identifier "Pattern"

. "."

identifier "compile"

argument_list

( "("

string_literal

" "\""

string_fragment "(?i)"

escape_sequence "\\\\"

string_fragment "bcharset="

escape_sequence "\\\\"

string_fragment "s*"

escape_sequence "\\\""

string_fragment "?([^"

escape_sequence "\\\\"

string_fragment "s;"

escape_sequence "\\\""

string_fragment "]*)"

" "\""

) ")"

; ";"

field_declaration

modifiers

static "static"

final "final"

type_identifier "String"

variable_declarator

identifier "defaultCharset"

= "="

string_literal

" "\""

string_fragment "UTF-8"

" "\""

; ";"

line_comment "// used if not found in header or meta charset"

field_declaration

modifiers

private "private"

static "static"

final "final"

integral_type

int "int"

variable_declarator

identifier "bufferSize"

= "="

hex_integer_literal "0x20000"

; ";"

line_comment "// ~130K."

constructor_declaration

modifiers

private "private"

identifier "DataUtil"

formal_parameters

( "("

) ")"

constructor_body

{ "{"

} "}"

block_comment "/**\n * Loads a file to a Document.\n * @param in file"...

method_declaration (+106 nodes collapsed)

block_comment "/**\n * Parses a Document from an input steam.\n * @pa"...

method_declaration (+59 nodes collapsed)

block_comment "/**\n * Parses a Document from an input steam, using the "...

method_declaration (+57 nodes collapsed)

line_comment "// reads bytes first into a buffer, then decodes with the ap"...

line_comment "// switching the chartset midstream when a meta http-equiv t"...

method_declaration

modifiers

static "static"

type_identifier "Document"

identifier "parseByteData"

formal_parameters

( "("

formal_parameter

type_identifier "ByteBuffer"

identifier "byteData"

, ","

formal_parameter

type_identifier "String"

identifier "charsetName"

, ","

formal_parameter

type_identifier "String"

identifier "baseUri"

, ","

formal_parameter

type_identifier "Parser"

identifier "parser"

) ")"

block

{ "{"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "docData"

; ";"

local_variable_declaration

type_identifier "Document"

variable_declarator

identifier "doc"

= "="

null_literal "null"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

identifier "charsetName"

== "=="

null_literal "null"

) ")"

block

{ "{"

line_comment "// determine from meta. safe parse as UTF-8"

line_comment "// look for <meta http-equiv=\"Content-Type\" content=\"text/ht"...

expression_statement (+26 nodes collapsed)

expression_statement

assignment_expression

identifier "doc"

= "="

method_invocation

identifier "parser"

. "."

identifier "parseInput"

argument_list

( "("

identifier "docData"

, ","

identifier "baseUri"

) ")"

; ";"

local_variable_declaration (+23 nodes collapsed)

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

identifier "meta"

!= "!="

null_literal "null"

) ")"

block

{ "{"

line_comment "// if not found, will keep utf-8 as best attempt"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "foundCharset"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "meta"

. "."

identifier "hasAttr"

argument_list

( "("

string_literal

" "\""

string_fragment "http-equiv"

" "\""

) ")"

block

{ "{"

expression_statement (+21 nodes collapsed)

} "}"

else "else"

block

{ "{"

expression_statement

assignment_expression

identifier "foundCharset"

= "="

method_invocation

identifier "meta"

. "."

identifier "attr"

argument_list

( "("

string_literal

" "\""

string_fragment "charset"

" "\""

) ")"

; ";"

} "}"

if_statement

if "if"

parenthesized_expression (+31 nodes collapsed)

block

{ "{"

line_comment "// need to re-decode"

expression_statement

assignment_expression

identifier "charsetName"

= "="

identifier "foundCharset"

; ";"

expression_statement

method_invocation

identifier "byteData"

. "."

identifier "rewind"

argument_list

( "("

) ")"

; ";"

expression_statement (+26 nodes collapsed)

expression_statement

assignment_expression

identifier "doc"

= "="

null_literal "null"

; ";"

} "}"

else "else"

block (+45 nodes collapsed)

if_statement (+87 nodes collapsed)

return_statement

return "return"

identifier "doc"

; ";"

} "}"

block_comment "/**\n * Read the input stream into a byte buffer.\n * "...

method_declaration (+216 nodes collapsed)

method_declaration (+28 nodes collapsed)

block_comment "/**\n * Parse out a charset from a content type header. I"...

method_declaration

modifiers

static "static"

type_identifier "String"

identifier "getCharsetFromContentType"

formal_parameters

( "("

formal_parameter

type_identifier "String"

identifier "contentType"

) ")"

block

{ "{"

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

identifier "contentType"

== "=="

null_literal "null"

) ")"

return_statement

return "return"

null_literal "null"

; ";"

local_variable_declaration

type_identifier "Matcher"

variable_declarator

identifier "m"

= "="

method_invocation

identifier "charsetPattern"

. "."

identifier "matcher"

argument_list

( "("

identifier "contentType"

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "m"

. "."

identifier "find"

argument_list

( "("

) ")"

block

{ "{"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "charset"

= "="

method_invocation

identifier "m"

. "."

identifier "group"

argument_list

( "("

decimal_integer_literal "1"

) ")"

. "."

identifier "trim"

argument_list

( "("

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "Charset"

. "."

identifier "isSupported"

argument_list

( "("

identifier "charset"

) ")"

return_statement

return "return"

identifier "charset"

; ";"

expression_statement

assignment_expression

identifier "charset"

= "="

method_invocation

identifier "charset"

. "."

identifier "toUpperCase"

argument_list

( "("

field_access

identifier "Locale"

. "."

identifier "ENGLISH"

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "Charset"

. "."

identifier "isSupported"

argument_list

( "("

identifier "charset"

) ")"

return_statement

return "return"

identifier "charset"

; ";"

line_comment "// if our advanced charset matching fails.... we just take t"...

} "}"

return_statement

return "return"

null_literal "null"

; ";"

} "}"

After

program

package_declaration

package "package"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "helper"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

. "."

identifier "Document"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "nodes"

. "."

identifier "Element"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "org"

. "."

identifier "jsoup"

. "."

identifier "parser"

. "."

identifier "Parser"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "io"

. "."

asterisk

* "*"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "nio"

. "."

identifier "ByteBuffer"

; ";"

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 "IllegalCharsetNameException"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "regex"

. "."

identifier "Matcher"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "regex"

. "."

identifier "Pattern"

; ";"

import_declaration

import "import"

scoped_identifier

identifier "java"

. "."

identifier "util"

. "."

identifier "Locale"

; ";"

block_comment "/**\n * Internal static utilities for handling data.\n *\n */"

class_declaration

modifiers

public "public"

class "class"

identifier "DataUtil"

class_body

{ "{"

field_declaration

modifiers

private "private"

static "static"

final "final"

type_identifier "Pattern"

variable_declarator

identifier "charsetPattern"

= "="

method_invocation

identifier "Pattern"

. "."

identifier "compile"

argument_list

( "("

string_literal

" "\""

string_fragment "(?i)"

escape_sequence "\\\\"

string_fragment "bcharset="

escape_sequence "\\\\"

string_fragment "s*(?:"

escape_sequence "\\\""

string_fragment "|')?([^"

escape_sequence "\\\\"

string_fragment "s,;"

escape_sequence "\\\""

string_fragment "']*)"

" "\""

) ")"

; ";"

field_declaration

modifiers

static "static"

final "final"

type_identifier "String"

variable_declarator

identifier "defaultCharset"

= "="

string_literal

" "\""

string_fragment "UTF-8"

" "\""

; ";"

line_comment "// used if not found in header or meta charset"

field_declaration

modifiers

private "private"

static "static"

final "final"

integral_type

int "int"

variable_declarator

identifier "bufferSize"

= "="

hex_integer_literal "0x20000"

; ";"

line_comment "// ~130K."

constructor_declaration

modifiers

private "private"

identifier "DataUtil"

formal_parameters

( "("

) ")"

constructor_body

{ "{"

} "}"

block_comment "/**\n * Loads a file to a Document.\n * @param in file"...

method_declaration (+106 nodes collapsed)

block_comment "/**\n * Parses a Document from an input steam.\n * @pa"...

method_declaration (+59 nodes collapsed)

block_comment "/**\n * Parses a Document from an input steam, using the "...

method_declaration (+57 nodes collapsed)

line_comment "// reads bytes first into a buffer, then decodes with the ap"...

line_comment "// switching the chartset midstream when a meta http-equiv t"...

method_declaration

modifiers

static "static"

type_identifier "Document"

identifier "parseByteData"

formal_parameters

( "("

formal_parameter

type_identifier "ByteBuffer"

identifier "byteData"

, ","

formal_parameter

type_identifier "String"

identifier "charsetName"

, ","

formal_parameter

type_identifier "String"

identifier "baseUri"

, ","

formal_parameter

type_identifier "Parser"

identifier "parser"

) ")"

block

{ "{"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "docData"

; ";"

local_variable_declaration

type_identifier "Document"

variable_declarator

identifier "doc"

= "="

null_literal "null"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

identifier "charsetName"

== "=="

null_literal "null"

) ")"

block

{ "{"

line_comment "// determine from meta. safe parse as UTF-8"

line_comment "// look for <meta http-equiv=\"Content-Type\" content=\"text/ht"...

expression_statement (+26 nodes collapsed)

expression_statement

assignment_expression

identifier "doc"

= "="

method_invocation

identifier "parser"

. "."

identifier "parseInput"

argument_list

( "("

identifier "docData"

, ","

identifier "baseUri"

) ")"

; ";"

local_variable_declaration (+23 nodes collapsed)

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

identifier "meta"

!= "!="

null_literal "null"

) ")"

block

{ "{"

line_comment "// if not found, will keep utf-8 as best attempt"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "foundCharset"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "meta"

. "."

identifier "hasAttr"

argument_list

( "("

string_literal

" "\""

string_fragment "http-equiv"

" "\""

) ")"

block

{ "{"

expression_statement (+21 nodes collapsed)

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

identifier "foundCharset"

== "=="

null_literal "null"

&& "&&"

method_invocation

identifier "meta"

. "."

identifier "hasAttr"

argument_list

( "("

string_literal

" "\""

string_fragment "charset"

" "\""

) ")"

block

{ "{"

try_statement

try "try"

block

{ "{"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "Charset"

. "."

identifier "isSupported"

argument_list

( "("

method_invocation

identifier "meta"

. "."

identifier "attr"

argument_list

( "("

string_literal

" "\""

string_fragment "charset"

" "\""

) ")"

block

{ "{"

expression_statement

assignment_expression

identifier "foundCharset"

= "="

method_invocation

identifier "meta"

. "."

identifier "attr"

argument_list

( "("

string_literal

" "\""

string_fragment "charset"

" "\""

) ")"

; ";"

} "}"

catch_clause

catch "catch"

( "("

catch_formal_parameter

catch_type

type_identifier "IllegalCharsetNameException"

identifier "e"

) ")"

block

{ "{"

expression_statement

assignment_expression

identifier "foundCharset"

= "="

null_literal "null"

; ";"

} "}"

else "else"

block

{ "{"

expression_statement

assignment_expression

identifier "foundCharset"

= "="

method_invocation

identifier "meta"

. "."

identifier "attr"

argument_list

( "("

string_literal

" "\""

string_fragment "charset"

" "\""

) ")"

; ";"

} "}"

if_statement

if "if"

parenthesized_expression (+31 nodes collapsed)

block

{ "{"

line_comment "// need to re-decode"

expression_statement

assignment_expression

identifier "foundCharset"

= "="

method_invocation

identifier "foundCharset"

. "."

identifier "trim"

argument_list

( "("

) ")"

. "."

identifier "replaceAll"

argument_list

( "("

string_literal

" "\""

string_fragment "["

escape_sequence "\\\""

string_fragment "']"

" "\""

, ","

string_literal

" "\""

) ")"

; ";"

expression_statement

assignment_expression

identifier "charsetName"

= "="

identifier "foundCharset"

; ";"

expression_statement

method_invocation

identifier "byteData"

. "."

identifier "rewind"

argument_list

( "("

) ")"

; ";"

expression_statement (+26 nodes collapsed)

expression_statement

assignment_expression

identifier "doc"

= "="

null_literal "null"

; ";"

} "}"

else "else"

block (+45 nodes collapsed)

if_statement (+87 nodes collapsed)

return_statement

return "return"

identifier "doc"

; ";"

} "}"

block_comment "/**\n * Read the input stream into a byte buffer.\n * "...

method_declaration (+216 nodes collapsed)

method_declaration (+28 nodes collapsed)

block_comment "/**\n * Parse out a charset from a content type header. I"...

method_declaration

modifiers

static "static"

type_identifier "String"

identifier "getCharsetFromContentType"

formal_parameters

( "("

formal_parameter

type_identifier "String"

identifier "contentType"

) ")"

block

{ "{"

if_statement

if "if"

parenthesized_expression

( "("

binary_expression

identifier "contentType"

== "=="

null_literal "null"

) ")"

return_statement

return "return"

null_literal "null"

; ";"

local_variable_declaration

type_identifier "Matcher"

variable_declarator

identifier "m"

= "="

method_invocation

identifier "charsetPattern"

. "."

identifier "matcher"

argument_list

( "("

identifier "contentType"

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "m"

. "."

identifier "find"

argument_list

( "("

) ")"

block

{ "{"

local_variable_declaration

type_identifier "String"

variable_declarator

identifier "charset"

= "="

method_invocation

identifier "m"

. "."

identifier "group"

argument_list

( "("

decimal_integer_literal "1"

) ")"

. "."

identifier "trim"

argument_list

( "("

) ")"

; ";"

expression_statement

assignment_expression

identifier "charset"

= "="

method_invocation

identifier "charset"

. "."

identifier "replace"

argument_list

( "("

string_literal

" "\""

string_fragment "charset="

" "\""

, ","

string_literal

" "\""

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "charset"

. "."

identifier "isEmpty"

argument_list

( "("

) ")"

return_statement

return "return"

null_literal "null"

; ";"

try_statement

try "try"

block

{ "{"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "Charset"

. "."

identifier "isSupported"

argument_list

( "("

identifier "charset"

) ")"

return_statement

return "return"

identifier "charset"

; ";"

expression_statement

assignment_expression

identifier "charset"

= "="

method_invocation

identifier "charset"

. "."

identifier "toUpperCase"

argument_list

( "("

field_access

identifier "Locale"

. "."

identifier "ENGLISH"

) ")"

; ";"

if_statement

if "if"

parenthesized_expression

( "("

method_invocation

identifier "Charset"

. "."

identifier "isSupported"

argument_list

( "("

identifier "charset"

) ")"

return_statement

return "return"

identifier "charset"

; ";"

} "}"

catch_clause

catch "catch"

( "("

catch_formal_parameter

catch_type

type_identifier "IllegalCharsetNameException"

identifier "e"

) ")"

block

{ "{"

line_comment "// if our advanced charset matching fails.... we just take t"...

return_statement

return "return"

null_literal "null"

; ";"

} "}"

return_statement

return "return"

null_literal "null"

; ";"

} "}"