fallback utf8 instead latin when charset missing

This commit is contained in:
Fabian Freund
2025-08-11 11:38:54 +02:00
parent d5400e00c5
commit 03c7081cb2
3 changed files with 46 additions and 2 deletions
+2 -1
View File
@@ -32,6 +32,7 @@ import 'package:socks5_proxy/socks_client.dart';
import 'package:universal_io/io.dart';
import 'package:weblibre/core/http_error_handler.dart';
import 'package:weblibre/data/models/web_page_info.dart';
import 'package:weblibre/extensions/http_encoding.dart';
import 'package:weblibre/features/geckoview/domain/entities/browser_icon.dart';
import 'package:weblibre/features/user/domain/repositories/cache.dart';
import 'package:weblibre/features/web_feed/utils/feed_finder.dart';
@@ -240,7 +241,7 @@ class GenericWebsiteService extends _$GenericWebsiteService {
}
}
final document = html_parser.parse(response.body);
final document = html_parser.parse(response.bodyUnicodeFallback);
final title = document.querySelector('title')?.text;
final resources = _extractIcons(baseUri, document);
+39
View File
@@ -0,0 +1,39 @@
import 'dart:convert';
import 'package:http/http.dart';
import 'package:http_parser/http_parser.dart';
/// This is modified from default latin1 fallback to use utf8
Encoding _encodingForHeaders(Map<String, String> headers) =>
_encodingForContentTypeHeader(_contentTypeForHeaders(headers), utf8);
/// Returns the [MediaType] object for the given headers' content-type.
///
/// Defaults to `application/octet-stream`.
MediaType _contentTypeForHeaders(Map<String, String> headers) {
final contentType = headers['content-type'];
if (contentType != null) return MediaType.parse(contentType);
return MediaType('application', 'octet-stream');
}
Encoding _encodingForContentTypeHeader(
MediaType contentTypeHeader, [
Encoding fallback = latin1,
]) {
final charset = contentTypeHeader.parameters['charset'];
// Default to utf8 for application/json when charset is unspecified.
if (contentTypeHeader.type == 'application' &&
contentTypeHeader.subtype == 'json' &&
charset == null) {
return utf8;
}
// Attempt to find the encoding or fall back to the default.
return charset != null ? Encoding.getByName(charset) ?? fallback : fallback;
}
extension ResponesEncoding on Response {
String get bodyUnicodeFallback =>
_encodingForHeaders(headers).decode(bodyBytes);
}
@@ -21,6 +21,7 @@ import 'package:flutter/foundation.dart';
import 'package:flutter/services.dart';
import 'package:http/http.dart' as http;
import 'package:riverpod_annotation/riverpod_annotation.dart';
import 'package:weblibre/extensions/http_encoding.dart';
import 'package:weblibre/features/web_feed/data/models/feed_parse_result.dart';
import 'package:weblibre/features/web_feed/utils/feed_parser.dart';
@@ -44,7 +45,10 @@ class FeedReader extends _$FeedReader {
.get(url)
.timeout(const Duration(seconds: 30));
final parser = FeedParser.parse(url: url, xmlString: response.body);
final parser = FeedParser.parse(
url: url,
xmlString: response.bodyUnicodeFallback,
);
final result = FeedParseResult(
feedData: parser.readGeneralData(),
articleData: parser.readArticles(),