Merge pull request #2 from sudame/feature/support_RSS1.0

RSS1.0に対応する
Flutter-Bounty-Hunters · Mar 9, 2020 · 6fe139f · 6fe139f
2 parents cf3bb97 + 2e87746
commit 6fe139f
Show file tree

Hide file tree

Showing 13 changed files with 798 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -7,11 +7,12 @@ A dart package for parsing RSS and Atom feed.
 
 ### Features
 
-- [x] RSS
+- [x] RSS 2.0
 - [x] Atom
 - [x] Namespaces
     - [x] Media RSS
     - [x] Dublin Core
+- [x] RSS 1.0
 
 ### Installing
 
@@ -29,8 +30,9 @@ import 'package:webfeed/webfeed.dart';
 
 To parse string into `RssFeed` object use:
 ```
-var rssFeed = new RssFeed.parse(xmlString); // for parsing RSS feed
+var rssFeed = new RssFeed.parse(xmlString); // for parsing RSS 2.0 feed
 var atomFeed = new AtomFeed.parse(xmlString); // for parsing Atom feed
+var rss1Feed = new RssFeed.parse(xmlString); // for parsing RSS 1.0 feed
 ```
 
 ### Preview
@@ -105,6 +107,26 @@ item.rights
 item.media
 ```
 
+**RSS 1.0**
+```
+feed.title
+feed.description
+feed.link
+feed.items
+feed.image
+feed.updatePeriod
+feed.updateFrequency
+feed.updateBase
+feed.dc
+
+RssItem item = feed.items.first;
+item.title
+item.description
+item.link
+item.dc
+item.content
+```
+
 ## License
 
 WebFeed is licensed under the MIT License - see the [LICENSE.md](LICENSE.md) file for details
diff --git a/analysis_options.yaml b/analysis_options.yaml
@@ -1,7 +1,5 @@
 analyzer:
   language:
-    enablePreviewDart2: true
-  strong-mode: true
   errors:
     unused_import: error
     unused_local_variable: error

diff --git a/lib/domain/dublin_core/dublin_core.dart b/lib/domain/dublin_core/dublin_core.dart
@@ -6,6 +6,7 @@ class DublinCore {
   final String description;
   final String creator;
   final String subject;
+  final List<String> subjects;
   final String publisher;
   final String contributor;
   final String date;
@@ -23,6 +24,7 @@ class DublinCore {
     this.description,
     this.creator,
     this.subject,
+    this.subjects,
     this.publisher,
     this.contributor,
     this.date,
@@ -45,6 +47,9 @@ class DublinCore {
       description: findElementOrNull(element, "dc:description")?.text,
       creator: findElementOrNull(element, "dc:creator")?.text,
       subject: findElementOrNull(element, "dc:subject")?.text,
+      subjects: findAllDirectElementsOrNull(element, 'dc:subject')
+          .map((subjectElement) => subjectElement.text)
+          .toList(),
       publisher: findElementOrNull(element, "dc:publisher")?.text,
       contributor: findElementOrNull(element, "dc:contributor")?.text,
       date: findElementOrNull(element, "dc:date")?.text,

diff --git a/lib/domain/rss1_feed.dart b/lib/domain/rss1_feed.dart
@@ -0,0 +1,83 @@
+import 'dart:core';
+
+import 'package:webfeed/domain/dublin_core/dublin_core.dart';
+import 'package:webfeed/domain/rss1_item.dart';
+import 'package:webfeed/util/helpers.dart';
+import 'package:xml/xml.dart';
+
+enum UpdatePeriod {
+  Hourly,
+  Daily,
+  Weekly,
+  Monthly,
+  Yearly,
+}
+
+class Rss1Feed {
+  final String title;
+  final String description;
+  final String link;
+  final String image;
+  final List<Rss1Item> items;
+  final UpdatePeriod updatePeriod;
+  final int updateFrequency;
+  final DateTime updateBase;
+  final DublinCore dc;
+
+  Rss1Feed({
+    this.title,
+    this.description,
+    this.link,
+    this.items,
+    this.image,
+    this.updatePeriod,
+    this.updateFrequency,
+    this.updateBase,
+    this.dc,
+  });
+
+  static UpdatePeriod _parseUpdatePeriod(String updatePeriodString) {
+    switch (updatePeriodString) {
+      case 'hourly':
+        return UpdatePeriod.Hourly;
+      case 'daily':
+        return UpdatePeriod.Daily;
+      case 'weekly':
+        return UpdatePeriod.Weekly;
+      case 'monthly':
+        return UpdatePeriod.Monthly;
+      case 'yearly':
+        return UpdatePeriod.Yearly;
+      default:
+        return null;
+    }
+  }
+
+  factory Rss1Feed.parse(String xmlString) {
+    var document = parse(xmlString);
+    XmlElement rdfElement;
+    try {
+      rdfElement = document.findAllElements("rdf:RDF").first;
+    } on StateError {
+      throw ArgumentError("channel not found");
+    }
+
+    return Rss1Feed(
+      title: findElementOrNull(rdfElement, "title")?.text,
+      link: findElementOrNull(rdfElement, "link")?.text,
+      description: findElementOrNull(rdfElement, "description")?.text,
+      items: rdfElement.findElements("item").map((element) {
+        return Rss1Item.parse(element);
+      }).toList(),
+      image:
+          findElementOrNull(rdfElement, 'image')?.getAttribute('rdf:resource'),
+      updatePeriod: _parseUpdatePeriod(
+          findElementOrNull(rdfElement, 'sy:updatePeriod')?.text),
+      updateFrequency:
+          parseInt(findElementOrNull(rdfElement, 'sy:updateFrequency')?.text),
+      updateBase:
+          parseDateTime(findElementOrNull(rdfElement, 'sy:updateBase')?.text),
+      dc: DublinCore.parse(rdfElement.findElements('channel').first),
+    );
+  }
+}
diff --git a/lib/domain/rss1_item.dart b/lib/domain/rss1_item.dart
@@ -0,0 +1,38 @@
+import 'package:webfeed/domain/rss_content.dart';
+import 'package:webfeed/util/helpers.dart';
+import 'package:xml/xml.dart';
+
+import 'dublin_core/dublin_core.dart';
+
+class Rss1Item {
+  final String title;
+  final String description;
+  final String link;
+  final DublinCore dc;
+  final RssContent content;
+
+  Rss1Item({
+    this.title,
+    this.description,
+    this.link,
+    this.dc,
+    this.content,
+  });
+
+  static DateTime _dateTimeBuilder(String dateTimeStringOrNull) {
+    if (dateTimeStringOrNull == null) {
+      return null;
+    }
+    return DateTime.parse(dateTimeStringOrNull);
+  }
+
+  factory Rss1Item.parse(XmlElement element) {
+    return Rss1Item(
+      title: findElementOrNull(element, "title")?.text,
+      description: findElementOrNull(element, "description")?.text,
+      link: findElementOrNull(element, "link")?.text,
+      dc: DublinCore.parse(element),
+      content: RssContent.parse(findElementOrNull(element, "content:encoded")),
+    );
+  }
+}
diff --git a/lib/domain/rss_content.dart b/lib/domain/rss_content.dart
@@ -27,4 +27,15 @@ class RssContent {
     });
     return RssContent(content, images);
   }
+
+  @override
+  bool operator ==(Object other) =>
+      identical(this, other) ||
+      other is RssContent &&
+          runtimeType == other.runtimeType &&
+          value == other.value &&
+          images == other.images;
+
+  @override
+  int get hashCode => value.hashCode ^ images.hashCode;
 }
diff --git a/lib/util/helpers.dart b/lib/util/helpers.dart
@@ -26,3 +26,12 @@ bool parseBoolLiteral(XmlElement element, String tagName) {
   return ["yes", "true"].contains(v);
 }
 
+DateTime parseDateTime(String dateTimeString) {
+  if (dateTimeString == null) return null;
+  return DateTime.parse(dateTimeString);
+}
+
+int parseInt(String intString) {
+  if (intString == null) return null;
+  return int.parse(intString);
+}
diff --git a/test/rss1_test.dart b/test/rss1_test.dart
@@ -0,0 +1,118 @@
+import 'dart:core';
+import 'dart:io';
+
+import 'package:test/test.dart';
+import 'package:webfeed/domain/rss1_feed.dart';
+
+void main() {
+  test('parse basic RSS 1.0', () {
+    final xmlString = File('test/xml/RSS1-basic.xml').readAsStringSync();
+    final feed = new Rss1Feed.parse(xmlString);
+
+    expect(feed.title, 'XML.com');
+    expect(feed.link, 'http://xml.com/pub');
+    expect(
+      feed.description,
+      'XML.com features a rich mix of information and services for the XML community.',
+    );
+    expect(feed.image, 'http://xml.com/universal/images/xml_tiny.gif');
+
+    expect(feed.items.length, 2);
+
+    final firstItem = feed.items.first;
+    expect(firstItem.title, 'Processing Inclusions with XSLT');
+    expect(firstItem.link, 'http://xml.com/pub/2000/08/09/xslt/xslt.html');
+    expect(firstItem.description,
+        'Processing document inclusions with general XML tools can be problematic. This article proposes a way of preserving inclusion information through SAX-based processing.');
+  });
+
+  test('parse RSS1 with syndication module', () {
+    final xmlString =
+        File('test/xml/RSS1-with-syndication-module.xml').readAsStringSync();
+    final feed = new Rss1Feed.parse(xmlString);
+
+    expect(feed.title, 'Meerkat');
+    expect(feed.link, 'http://meerkat.oreillynet.com');
+    expect(feed.description, 'Meerkat: An Open Wire Service');
+
+    expect(feed.updatePeriod, UpdatePeriod.Hourly);
+    expect(feed.updateFrequency, 2);
+    expect(feed.updateBase, DateTime.parse('2000-01-01T12:00+00:00'));
+  });
+
+  test('parse RSS1 with dublin core module', () {
+    final xmlString =
+        File('test/xml/RSS1-with-dublin-core-module.xml').readAsStringSync();
+    final feed = new Rss1Feed.parse(xmlString);
+
+    expect(feed.title, 'Meerkat');
+    expect(feed.link, 'http://meerkat.oreillynet.com');
+    expect(feed.description, 'Meerkat: An Open Wire Service');
+
+    expect(feed.dc.publisher, 'The O\'Reilly Network');
+    expect(feed.dc.creator, 'Rael Dornfest (mailto:[email protected])');
+    expect(feed.dc.rights, 'Copyright © 2000 O\'Reilly & Associates, Inc.');
+    expect(feed.dc.date, '2000-01-01T12:00+00:00');
+
+    final firstItem = feed.items.first;
+    expect(
+      firstItem.dc.description,
+      'XML is placing increasingly heavy loads on the existing technical infrastructure of the Internet.',
+    );
+    expect(firstItem.dc.publisher, 'The O\'Reilly Network');
+    expect(
+      firstItem.dc.creator,
+      'Simon St.Laurent (mailto:[email protected])',
+    );
+    expect(
+        firstItem.dc.rights, 'Copyright © 2000 O\'Reilly & Associates, Inc.');
+    expect(firstItem.dc.subject, 'XML');
+  });
+
+  test('parse RSS1 with content module', () {
+    final xmlString =
+        File('test/xml/RSS1-with-content-module.xml').readAsStringSync();
+    final feed = new Rss1Feed.parse(xmlString);
+
+    expect(feed.title, 'Example Feed');
+    expect(feed.link, 'http://www.example.org');
+    expect(feed.description, 'Simply for the purpose of demonstration.');
+
+    final firstItem = feed.items.first;
+    expect(
+      firstItem.content.value,
+      '<p>What a <em>beautiful</em> day!</p>',
+    );
+    expect(
+      firstItem.content.images,
+      Iterable.empty(),
+    );
+  });
+
+  // Japanese Social Bookmark Service "Hatena Bookmark" is still using RSS1.0!
+  // As I don't know english service using RSS 1.0, I use Japanese service for test case.
+  test("parse production RSS1.0", () {
+    var xmlString =
+        new File("test/xml/RSS1-production_hatena.xml").readAsStringSync();
+
+    var feed = new Rss1Feed.parse(xmlString);
+
+    expect(feed.title, 'sampleのはてなブックマーク');
+    expect(feed.link, 'https://b.hatena.ne.jp/sample/bookmark');
+    expect(feed.description, 'sampleのはてなブックマーク (17)');
+
+    expect(feed.items.length, 17);
+
+    final firstItem = feed.items.first;
+
+    expect(firstItem.description, '');
+    expect(firstItem.title, 'はてなスタッフのブックマーク拝見！ - 営業マン編「仕事の様々なシーンでフル活用」');
+    expect(firstItem.link, 'http://b.hatena.ne.jp/guide/staff_bookmark_03');
+    expect(firstItem.dc.creator, 'sample');
+    expect(firstItem.dc.date, '2009-04-10T09:44:20Z');
+    expect(firstItem.dc.subject, 'はてな');
+    expect(firstItem.dc.subjects[0], 'はてな');
+    expect(firstItem.dc.subjects[1], 'インタビュー');
+    expect(firstItem.dc.subjects[2], 'はてなブックマーク');
+  });
+}