Chromium Code Reviews
chromiumcodereview-hr@appspot.gserviceaccount.com (chromiumcodereview-hr) | Please choose your nickname with Settings | Help | Chromium Project | Gerrit Changes | Sign out
(1043)

Unified Diff: pkg/third_party/html5lib/lib/src/tokenizer.dart

Issue 157983005: pkg/third_party/html5lib: lots of cleanup (Closed) Base URL: https://dart.googlecode.com/svn/branches/bleeding_edge/dart
Patch Set: bump version Created 6 years, 10 months ago
Use n/p to move between diff chunks; N/P to move between comments. Draft comments are only viewable by you.
Jump to:
View side-by-side diff with in-line comments
Download patch
Index: pkg/third_party/html5lib/lib/src/tokenizer.dart
diff --git a/pkg/third_party/html5lib/lib/src/tokenizer.dart b/pkg/third_party/html5lib/lib/src/tokenizer.dart
index 2c2ada79d5ab5fbabdc3bc0aa56f6a91717e51c0..057021b5ff1dcbedb776c4322c8780c345df979e 100644
--- a/pkg/third_party/html5lib/lib/src/tokenizer.dart
+++ b/pkg/third_party/html5lib/lib/src/tokenizer.dart
@@ -1,7 +1,6 @@
library tokenizer;
import 'dart:collection';
-import 'dart:math';
import 'package:html5lib/parser.dart' show HtmlParser;
import 'package:source_maps/span.dart' show Span, FileSpan;
import 'constants.dart';
@@ -15,7 +14,7 @@ import 'utils.dart';
// we had it implemented in Dart.
Map<String, List<String>> entitiesByFirstChar = (() {
var result = {};
- for (var k in entities.keys) {
+ for (var k in ENTITIES.keys) {
result.putIfAbsent(k[0], () => []).add(k);
}
return result;
@@ -203,7 +202,7 @@ class HtmlTokenizer implements Iterator<Token> {
var charAsInt = parseIntRadix(charStack.join(), radix);
// Certain characters get replaced with others
- var char = replacementCharacters[charAsInt];
+ var char = REPLACEMENT_CHARACTERS[charAsInt];
if (char != null) {
_addToken(new ParseErrorToken(
"illegal-codepoint-for-numeric-entity",
@@ -305,7 +304,7 @@ class HtmlTokenizer implements Iterator<Token> {
int entityLen;
for (entityLen = charStack.length - 1; entityLen > 1; entityLen--) {
var possibleEntityName = charStack.sublist(0, entityLen).join();
- if (entities.containsKey(possibleEntityName)) {
+ if (ENTITIES.containsKey(possibleEntityName)) {
entityName = possibleEntityName;
break;
}
@@ -323,7 +322,7 @@ class HtmlTokenizer implements Iterator<Token> {
stream.unget(charStack.removeLast());
output = "&${charStack.join()}";
} else {
- output = entities[entityName];
+ output = ENTITIES[entityName];
stream.unget(charStack.removeLast());
output = '${output}${slice(charStack, entityLen).join()}';
}
@@ -407,7 +406,7 @@ class HtmlTokenizer implements Iterator<Token> {
// state". At that point spaceCharacters are important so they are
// emitted separately.
_addToken(new SpaceCharactersToken(
- '${data}${stream.charsUntil(spaceCharacters, true)}'));
+ '${data}${stream.charsUntil(SPACE_CHARACTERS, true)}'));
// No need to update lastFourChars here, since the first space will
// have already been appended to lastFourChars and will have broken
// any <!-- or --> sequences
@@ -441,7 +440,7 @@ class HtmlTokenizer implements Iterator<Token> {
// state". At that point spaceCharacters are important so they are
// emitted separately.
_addToken(new SpaceCharactersToken(
- '${data}${stream.charsUntil(spaceCharacters, true)}'));
+ '${data}${stream.charsUntil(SPACE_CHARACTERS, true)}'));
} else {
var chars = stream.charsUntil("&<");
_addToken(new CharactersToken('${data}${chars}'));
@@ -998,7 +997,7 @@ class HtmlTokenizer implements Iterator<Token> {
bool beforeAttributeNameState() {
var data = stream.char();
if (isWhitespace(data)) {
- stream.charsUntil(spaceCharacters, true);
+ stream.charsUntil(SPACE_CHARACTERS, true);
} else if (isLetter(data)) {
_addAttribute(data);
state = attributeNameState;
@@ -1032,7 +1031,7 @@ class HtmlTokenizer implements Iterator<Token> {
state = beforeAttributeValueState;
} else if (isLetter(data)) {
_attributeName = '$_attributeName$data'
- '${stream.charsUntil(asciiLetters, true)}';
+ '${stream.charsUntil(ASCII_LETTERS, true)}';
leavingThisState = false;
} else if (data == ">") {
// XXX If we emit here the attributes are converted to a dict
@@ -1085,7 +1084,7 @@ class HtmlTokenizer implements Iterator<Token> {
bool afterAttributeNameState() {
var data = stream.char();
if (isWhitespace(data)) {
- stream.charsUntil(spaceCharacters, true);
+ stream.charsUntil(SPACE_CHARACTERS, true);
} else if (data == "=") {
state = beforeAttributeValueState;
} else if (data == ">") {
@@ -1116,7 +1115,7 @@ class HtmlTokenizer implements Iterator<Token> {
bool beforeAttributeValueState() {
var data = stream.char();
if (isWhitespace(data)) {
- stream.charsUntil(spaceCharacters, true);
+ stream.charsUntil(SPACE_CHARACTERS, true);
} else if (data == "\"") {
_markAttributeValueStart(0);
state = attributeValueDoubleQuotedState;
@@ -1217,7 +1216,7 @@ class HtmlTokenizer implements Iterator<Token> {
_attributeValue = '${_attributeValue}\uFFFD';
} else {
_attributeValue = '$_attributeValue$data'
- '${stream.charsUntil("&>\"\'=<`$spaceCharacters")}';
+ '${stream.charsUntil("&>\"\'=<`$SPACE_CHARACTERS")}';
}
return true;
}

Powered by Google App Engine
This is Rietveld 408576698