Refactor JSON Feed parser to use an adapter

This commit is contained in:
Frédéric Guillot 2024-03-12 22:10:59 -07:00
parent 6bc4b35e38
commit 8429c6b0ab
4 changed files with 487 additions and 253 deletions

View File

@ -0,0 +1,173 @@
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package json // import "miniflux.app/v2/internal/reader/json"
import (
"log/slog"
"sort"
"strings"
"time"
"miniflux.app/v2/internal/crypto"
"miniflux.app/v2/internal/model"
"miniflux.app/v2/internal/reader/date"
"miniflux.app/v2/internal/reader/sanitizer"
"miniflux.app/v2/internal/urllib"
)
type JSONAdapter struct {
jsonFeed *JSONFeed
}
func NewJSONAdapter(jsonFeed *JSONFeed) *JSONAdapter {
return &JSONAdapter{jsonFeed}
}
func (j *JSONAdapter) BuildFeed(feedURL string) *model.Feed {
feed := &model.Feed{
Title: strings.TrimSpace(j.jsonFeed.Title),
FeedURL: j.jsonFeed.FeedURL,
SiteURL: j.jsonFeed.HomePageURL,
}
if feed.FeedURL == "" {
feed.FeedURL = feedURL
}
// Fallback to the feed URL if the site URL is empty.
if feed.SiteURL == "" {
feed.SiteURL = feed.FeedURL
}
if feedURL, err := urllib.AbsoluteURL(feedURL, j.jsonFeed.FeedURL); err == nil {
feed.FeedURL = feedURL
}
if siteURL, err := urllib.AbsoluteURL(feedURL, j.jsonFeed.HomePageURL); err == nil {
feed.SiteURL = siteURL
}
// Fallback to the feed URL if the title is empty.
if feed.Title == "" {
feed.Title = feed.SiteURL
}
// Populate the icon URL if present.
for _, iconURL := range []string{j.jsonFeed.FaviconURL, j.jsonFeed.IconURL} {
iconURL = strings.TrimSpace(iconURL)
if iconURL != "" {
if absoluteIconURL, err := urllib.AbsoluteURL(feed.SiteURL, iconURL); err == nil {
feed.IconURL = absoluteIconURL
break
}
}
}
for _, item := range j.jsonFeed.Items {
entry := model.NewEntry()
entry.Title = strings.TrimSpace(item.Title)
entry.URL = strings.TrimSpace(item.URL)
// Make sure the entry URL is absolute.
if entryURL, err := urllib.AbsoluteURL(feed.SiteURL, entry.URL); err == nil {
entry.URL = entryURL
}
// The entry title is optional, so we need to find a fallback.
if entry.Title == "" {
for _, value := range []string{item.Summary, item.ContentText, item.ContentHTML} {
if value != "" {
entry.Title = sanitizer.TruncateHTML(value, 100)
}
}
}
// Fallback to the entry URL if the title is empty.
if entry.Title == "" {
entry.Title = entry.URL
}
// Populate the entry content.
for _, value := range []string{item.ContentHTML, item.ContentText, item.Summary} {
value = strings.TrimSpace(value)
if value != "" {
entry.Content = value
break
}
}
// Populate the entry date.
entry.Date = time.Now()
for _, value := range []string{item.DatePublished, item.DateModified} {
value = strings.TrimSpace(value)
if value != "" {
if date, err := date.Parse(value); err != nil {
slog.Debug("Unable to parse date from JSON feed",
slog.String("date", value),
slog.String("url", entry.URL),
slog.Any("error", err),
)
} else {
entry.Date = date
break
}
}
}
// Populate the entry author.
itemAuthors := append(item.Authors, j.jsonFeed.Authors...)
itemAuthors = append(itemAuthors, item.Author, j.jsonFeed.Author)
authorNamesMap := make(map[string]bool)
for _, author := range itemAuthors {
authorName := strings.TrimSpace(author.Name)
if authorName != "" {
authorNamesMap[authorName] = true
}
}
var authors []string
for authorName := range authorNamesMap {
authors = append(authors, authorName)
}
sort.Strings(authors)
entry.Author = strings.Join(authors, ", ")
// Populate the entry enclosures.
for _, attachment := range item.Attachments {
attachmentURL := strings.TrimSpace(attachment.URL)
if attachmentURL != "" {
if absoluteAttachmentURL, err := urllib.AbsoluteURL(feed.SiteURL, attachmentURL); err == nil {
entry.Enclosures = append(entry.Enclosures, &model.Enclosure{
URL: absoluteAttachmentURL,
MimeType: attachment.MimeType,
Size: attachment.Size,
})
}
}
}
// Populate the entry tags.
for _, tag := range item.Tags {
tag = strings.TrimSpace(tag)
if tag != "" {
entry.Tags = append(entry.Tags, tag)
}
}
// Generate a hash for the entry.
for _, value := range []string{item.ID, item.URL, item.ContentText + item.ContentHTML + item.Summary} {
value = strings.TrimSpace(value)
if value != "" {
entry.Hash = crypto.Hash(value)
break
}
}
feed.Entries = append(feed.Entries, entry)
}
return feed
}

View File

@ -3,207 +3,141 @@
package json // import "miniflux.app/v2/internal/reader/json" package json // import "miniflux.app/v2/internal/reader/json"
import ( // JSON Feed specs:
"log/slog" // https://www.jsonfeed.org/version/1.1/
"strings" // https://www.jsonfeed.org/version/1/
"time" type JSONFeed struct {
// Version is the URL of the version of the format the feed uses.
// This should appear at the very top, though we recognize that not all JSON generators allow for ordering.
Version string `json:"version"`
"miniflux.app/v2/internal/crypto" // Title is the name of the feed, which will often correspond to the name of the website.
"miniflux.app/v2/internal/model" Title string `json:"title"`
"miniflux.app/v2/internal/reader/date"
"miniflux.app/v2/internal/reader/sanitizer"
"miniflux.app/v2/internal/urllib"
)
type jsonFeed struct { // HomePageURL is the URL of the resource that the feed describes.
Version string `json:"version"` // This resource may or may not actually be a “home” page, but it should be an HTML page.
Title string `json:"title"` HomePageURL string `json:"home_page_url"`
SiteURL string `json:"home_page_url"`
IconURL string `json:"icon"` // FeedURL is the URL of the feed, and serves as the unique identifier for the feed.
FaviconURL string `json:"favicon"` FeedURL string `json:"feed_url"`
FeedURL string `json:"feed_url"`
Authors []jsonAuthor `json:"authors"` // Description provides more detail, beyond the title, on what the feed is about.
Author jsonAuthor `json:"author"` Description string `json:"description"`
Items []jsonItem `json:"items"`
// IconURL is the URL of an image for the feed suitable to be used in a timeline, much the way an avatar might be used.
IconURL string `json:"icon"`
// FaviconURL is the URL of an image for the feed suitable to be used in a source list. It should be square and relatively small.
FaviconURL string `json:"favicon"`
// Authors specifies one or more feed authors. The author object has several members.
Authors []JSONAuthor `json:"authors"` // JSON Feed v1.1
// Author specifies the feed author. The author object has several members.
// JSON Feed v1 (deprecated)
Author JSONAuthor `json:"author"`
// Language is the primary language for the feed in the format specified in RFC 5646.
// The value is usually a 2-letter language tag from ISO 639-1, optionally followed by a region tag. (Examples: en or en-US.)
Language string `json:"language"`
// Expired is a boolean value that specifies whether or not the feed is finished.
Expired bool `json:"expired"`
// Items is an array, each representing an individual item in the feed.
Items []JSONItem `json:"items"`
// Hubs describes endpoints that can be used to subscribe to real-time notifications from the publisher of this feed.
Hubs []JSONHub `json:"hubs"`
} }
type jsonAuthor struct { type JSONAuthor struct {
// Author's name.
Name string `json:"name"` Name string `json:"name"`
URL string `json:"url"`
// Author's website URL (Blog or micro-blog).
WebsiteURL string `json:"url"`
// Author's avatar URL.
AvatarURL string `json:"avatar"`
} }
type jsonItem struct { type JSONHub struct {
ID string `json:"id"` // Type defines the protocol used to talk with the hub: "rssCloud" or "WebSub".
URL string `json:"url"` Type string `json:"type"`
Title string `json:"title"`
Summary string `json:"summary"` // URL is the location of the hub.
Text string `json:"content_text"` URL string `json:"url"`
HTML string `json:"content_html"`
DatePublished string `json:"date_published"`
DateModified string `json:"date_modified"`
Authors []jsonAuthor `json:"authors"`
Author jsonAuthor `json:"author"`
Attachments []jsonAttachment `json:"attachments"`
Tags []string `json:"tags"`
} }
type jsonAttachment struct { type JSONItem struct {
URL string `json:"url"` // Unique identifier for the item.
// Ideally, the id is the full URL of the resource described by the item, since URLs make great unique identifiers.
ID string `json:"id"`
// URL of the resource described by the item.
URL string `json:"url"`
// ExternalURL is the URL of a page elsewhere.
// This is especially useful for linkblogs.
// If url links to where youre talking about a thing, then external_url links to the thing youre talking about.
ExternalURL string `json:"external_url"`
// Title of the item (optional).
// Microblog items in particular may omit titles.
Title string `json:"title"`
// ContentHTML is the HTML body of the item.
ContentHTML string `json:"content_html"`
// ContentText is the text body of the item.
ContentText string `json:"content_text"`
// Summary is a plain text sentence or two describing the item.
Summary string `json:"summary"`
// ImageURL is the URL of the main image for the item.
ImageURL string `json:"image"`
// BannerImageURL is the URL of an image to use as a banner.
BannerImageURL string `json:"banner_image"`
// DatePublished is the date the item was published.
DatePublished string `json:"date_published"`
// DateModified is the date the item was modified.
DateModified string `json:"date_modified"`
// Language is the language of the item.
Language string `json:"language"`
// Authors is an array of JSONAuthor.
Authors []JSONAuthor `json:"authors"`
// Author is a JSONAuthor.
// JSON Feed v1 (deprecated)
Author JSONAuthor `json:"author"`
// Tags is an array of strings.
Tags []string `json:"tags"`
// Attachments is an array of JSONAttachment.
Attachments []JSONAttachment `json:"attachments"`
}
type JSONAttachment struct {
// URL of the attachment.
URL string `json:"url"`
// MIME type of the attachment.
MimeType string `json:"mime_type"` MimeType string `json:"mime_type"`
Title string `json:"title"`
Size int64 `json:"size_in_bytes"` // Title of the attachment.
Duration int `json:"duration_in_seconds"` Title string `json:"title"`
}
// Size of the attachment in bytes.
func (j *jsonFeed) GetAuthor() string { Size int64 `json:"size_in_bytes"`
if len(j.Authors) > 0 {
return (getAuthor(j.Authors[0])) // Duration of the attachment in seconds.
} Duration int `json:"duration_in_seconds"`
return getAuthor(j.Author)
}
func (j *jsonFeed) Transform(baseURL string) *model.Feed {
var err error
feed := new(model.Feed)
feed.FeedURL, err = urllib.AbsoluteURL(baseURL, j.FeedURL)
if err != nil {
feed.FeedURL = j.FeedURL
}
feed.SiteURL, err = urllib.AbsoluteURL(baseURL, j.SiteURL)
if err != nil {
feed.SiteURL = j.SiteURL
}
feed.IconURL = strings.TrimSpace(j.IconURL)
if feed.IconURL == "" {
feed.IconURL = strings.TrimSpace(j.FaviconURL)
}
feed.Title = strings.TrimSpace(j.Title)
if feed.Title == "" {
feed.Title = feed.SiteURL
}
for _, item := range j.Items {
entry := item.Transform()
entryURL, err := urllib.AbsoluteURL(feed.SiteURL, entry.URL)
if err == nil {
entry.URL = entryURL
}
if entry.Author == "" {
entry.Author = j.GetAuthor()
}
feed.Entries = append(feed.Entries, entry)
}
return feed
}
func (j *jsonItem) GetDate() time.Time {
for _, value := range []string{j.DatePublished, j.DateModified} {
if value != "" {
d, err := date.Parse(value)
if err != nil {
slog.Debug("Unable to parse date from JSON feed",
slog.String("date", value),
slog.String("url", j.URL),
slog.Any("error", err),
)
return time.Now()
}
return d
}
}
return time.Now()
}
func (j *jsonItem) GetAuthor() string {
if len(j.Authors) > 0 {
return getAuthor(j.Authors[0])
}
return getAuthor(j.Author)
}
func (j *jsonItem) GetHash() string {
for _, value := range []string{j.ID, j.URL, j.Text + j.HTML + j.Summary} {
if value != "" {
return crypto.Hash(value)
}
}
return ""
}
func (j *jsonItem) GetTitle() string {
if j.Title != "" {
return j.Title
}
for _, value := range []string{j.Summary, j.Text, j.HTML} {
if value != "" {
return sanitizer.TruncateHTML(value, 100)
}
}
return j.URL
}
func (j *jsonItem) GetContent() string {
for _, value := range []string{j.HTML, j.Text, j.Summary} {
if value != "" {
return value
}
}
return ""
}
func (j *jsonItem) GetEnclosures() model.EnclosureList {
enclosures := make(model.EnclosureList, 0)
for _, attachment := range j.Attachments {
if attachment.URL == "" {
continue
}
enclosures = append(enclosures, &model.Enclosure{
URL: attachment.URL,
MimeType: attachment.MimeType,
Size: attachment.Size,
})
}
return enclosures
}
func (j *jsonItem) Transform() *model.Entry {
entry := model.NewEntry()
entry.URL = j.URL
entry.Date = j.GetDate()
entry.Author = j.GetAuthor()
entry.Hash = j.GetHash()
entry.Content = j.GetContent()
entry.Title = strings.TrimSpace(j.GetTitle())
entry.Enclosures = j.GetEnclosures()
if len(j.Tags) > 0 {
entry.Tags = j.Tags
}
return entry
}
func getAuthor(author jsonAuthor) string {
if author.Name != "" {
return strings.TrimSpace(author.Name)
}
return ""
} }

View File

@ -13,10 +13,10 @@ import (
// Parse returns a normalized feed struct from a JSON feed. // Parse returns a normalized feed struct from a JSON feed.
func Parse(baseURL string, data io.Reader) (*model.Feed, error) { func Parse(baseURL string, data io.Reader) (*model.Feed, error) {
feed := new(jsonFeed) jsonFeed := new(JSONFeed)
if err := json.NewDecoder(data).Decode(&feed); err != nil { if err := json.NewDecoder(data).Decode(&jsonFeed); err != nil {
return nil, fmt.Errorf("json: unable to parse feed: %w", err) return nil, fmt.Errorf("json: unable to parse feed: %w", err)
} }
return feed.Transform(baseURL), nil return NewJSONAdapter(jsonFeed).BuildFeed(baseURL), nil
} }

View File

@ -10,7 +10,7 @@ import (
"time" "time"
) )
func TestParseJsonFeed(t *testing.T) { func TestParseJsonFeedVersion1(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
@ -49,7 +49,7 @@ func TestParseJsonFeed(t *testing.T) {
t.Errorf("Incorrect site URL, got: %s", feed.SiteURL) t.Errorf("Incorrect site URL, got: %s", feed.SiteURL)
} }
if feed.IconURL != "https://micro.blog/jsonfeed/avatar.jpg" { if feed.IconURL != "https://micro.blog/jsonfeed/favicon.png" {
t.Errorf("Incorrect icon URL, got: %s", feed.IconURL) t.Errorf("Incorrect icon URL, got: %s", feed.IconURL)
} }
@ -177,7 +177,81 @@ func TestParsePodcast(t *testing.T) {
} }
} }
func TestParseEntryWithoutAttachmentURL(t *testing.T) { func TestParseFeedWithoutTitle(t *testing.T) {
data := `{
"version": "https://jsonfeed.org/version/1",
"home_page_url": "https://example.org/",
"feed_url": "https://example.org/feed.json",
"items": [
{
"id": "2347259",
"url": "https://example.org/2347259",
"content_text": "Cats are neat. \n\nhttps://example.org/cats",
"date_published": "2016-02-09T14:22:00-07:00"
}
]
}`
feed, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data))
if err != nil {
t.Fatal(err)
}
if feed.Title != "https://example.org/" {
t.Errorf("Incorrect title, got: %s", feed.Title)
}
}
func TestParseFeedWithoutHomePage(t *testing.T) {
data := `{
"version": "https://jsonfeed.org/version/1",
"feed_url": "https://example.org/feed.json",
"title": "Some test",
"items": [
{
"id": "2347259",
"url": "https://example.org/2347259",
"content_text": "Cats are neat. \n\nhttps://example.org/cats",
"date_published": "2016-02-09T14:22:00-07:00"
}
]
}`
feed, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data))
if err != nil {
t.Fatal(err)
}
if feed.SiteURL != "https://example.org/feed.json" {
t.Errorf("Incorrect title, got: %s", feed.Title)
}
}
func TestParseFeedWithoutFeedURL(t *testing.T) {
data := `{
"version": "https://jsonfeed.org/version/1",
"title": "Some test",
"items": [
{
"id": "2347259",
"url": "https://example.org/2347259",
"content_text": "Cats are neat. \n\nhttps://example.org/cats",
"date_published": "2016-02-09T14:22:00-07:00"
}
]
}`
feed, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data))
if err != nil {
t.Fatal(err)
}
if feed.SiteURL != "https://example.org/feed.json" {
t.Errorf("Incorrect title, got: %s", feed.Title)
}
}
func TestParseItemWithoutAttachmentURL(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"user_comment": "This is a podcast feed. You can add this feed to your podcast client using the following URL: http://therecord.co/feed.json", "user_comment": "This is a podcast feed. You can add this feed to your podcast client using the following URL: http://therecord.co/feed.json",
@ -216,7 +290,7 @@ func TestParseEntryWithoutAttachmentURL(t *testing.T) {
} }
} }
func TestParseFeedWithRelativeURL(t *testing.T) { func TestParseItemWithRelativeURL(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "Example", "title": "Example",
@ -241,7 +315,7 @@ func TestParseFeedWithRelativeURL(t *testing.T) {
} }
} }
func TestParseAuthor(t *testing.T) { func TestParseItemWithLegacyAuthorField(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"user_comment": "This is a microblog feed. You can add this to your feed reader using the following URL: https://example.org/feed.json", "user_comment": "This is a microblog feed. You can add this to your feed reader using the following URL: https://example.org/feed.json",
@ -277,7 +351,7 @@ func TestParseAuthor(t *testing.T) {
} }
} }
func TestParseAuthors(t *testing.T) { func TestParseItemWithMultipleAuthorFields(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1.1", "version": "https://jsonfeed.org/version/1.1",
"user_comment": "This is a microblog feed. You can add this to your feed reader using the following URL: https://example.org/feed.json", "user_comment": "This is a microblog feed. You can add this to your feed reader using the following URL: https://example.org/feed.json",
@ -285,11 +359,11 @@ func TestParseAuthors(t *testing.T) {
"home_page_url": "https://example.org/", "home_page_url": "https://example.org/",
"feed_url": "https://example.org/feed.json", "feed_url": "https://example.org/feed.json",
"author": { "author": {
"name": "This field is deprecated, use authors", "name": "Deprecated Author Field",
"url": "http://example.org/", "url": "http://example.org/",
"avatar": "https://example.org/avatar.png" "avatar": "https://example.org/avatar.png"
}, },
"authors": [ "authors": [
{ {
"name": "Brent Simmons", "name": "Brent Simmons",
"url": "http://example.org/", "url": "http://example.org/",
@ -315,14 +389,15 @@ func TestParseAuthors(t *testing.T) {
t.Errorf("Incorrect number of entries, got: %d", len(feed.Entries)) t.Errorf("Incorrect number of entries, got: %d", len(feed.Entries))
} }
if feed.Entries[0].Author != "Brent Simmons" { if feed.Entries[0].Author != "Brent Simmons, Deprecated Author Field" {
t.Errorf("Incorrect entry author, got: %s", feed.Entries[0].Author) t.Errorf("Incorrect entry author, got: %s", feed.Entries[0].Author)
} }
} }
func TestParseFeedWithoutTitle(t *testing.T) { func TestParseItemWithMultipleDuplicateAuthors(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1.1",
"title": "Example",
"home_page_url": "https://example.org/", "home_page_url": "https://example.org/",
"feed_url": "https://example.org/feed.json", "feed_url": "https://example.org/feed.json",
"items": [ "items": [
@ -330,7 +405,24 @@ func TestParseFeedWithoutTitle(t *testing.T) {
"id": "2347259", "id": "2347259",
"url": "https://example.org/2347259", "url": "https://example.org/2347259",
"content_text": "Cats are neat. \n\nhttps://example.org/cats", "content_text": "Cats are neat. \n\nhttps://example.org/cats",
"date_published": "2016-02-09T14:22:00-07:00" "date_published": "2016-02-09T14:22:00-07:00",
"authors": [
{
"name": "Author B",
"url": "http://example.org/",
"avatar": "https://example.org/avatar.png"
},
{
"name": "Author A",
"url": "http://example.org/",
"avatar": "https://example.org/avatar.png"
},
{
"name": "Author B",
"url": "http://example.org/",
"avatar": "https://example.org/avatar.png"
}
]
} }
] ]
}` }`
@ -340,12 +432,16 @@ func TestParseFeedWithoutTitle(t *testing.T) {
t.Fatal(err) t.Fatal(err)
} }
if feed.Title != "https://example.org/" { if len(feed.Entries) != 1 {
t.Errorf("Incorrect title, got: %s", feed.Title) t.Errorf("Incorrect number of entries, got: %d", len(feed.Entries))
}
if feed.Entries[0].Author != "Author A, Author B" {
t.Errorf("Incorrect entry author, got: %s", feed.Entries[0].Author)
} }
} }
func TestParseFeedItemWithInvalidDate(t *testing.T) { func TestParseItemWithInvalidDate(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
@ -376,34 +472,7 @@ func TestParseFeedItemWithInvalidDate(t *testing.T) {
} }
} }
func TestParseFeedItemWithoutID(t *testing.T) { func TestParseItemWithoutTitleButWithURL(t *testing.T) {
data := `{
"version": "https://jsonfeed.org/version/1",
"title": "My Example Feed",
"home_page_url": "https://example.org/",
"feed_url": "https://example.org/feed.json",
"items": [
{
"content_text": "Some text."
}
]
}`
feed, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data))
if err != nil {
t.Fatal(err)
}
if len(feed.Entries) != 1 {
t.Errorf("Incorrect number of entries, got: %d", len(feed.Entries))
}
if feed.Entries[0].Hash != "13b4c5aecd1b6d749afcee968fbf9c80f1ed1bbdbe1aaf25cb34ebd01144bbe9" {
t.Errorf("Incorrect entry hash, got: %s", feed.Entries[0].Hash)
}
}
func TestParseFeedItemWithoutTitleButWithURL(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
@ -430,7 +499,7 @@ func TestParseFeedItemWithoutTitleButWithURL(t *testing.T) {
} }
} }
func TestParseFeedItemWithoutTitleButWithSummary(t *testing.T) { func TestParseItemWithoutTitleButWithSummary(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
@ -457,7 +526,7 @@ func TestParseFeedItemWithoutTitleButWithSummary(t *testing.T) {
} }
} }
func TestParseFeedItemWithoutTitleButWithHTMLContent(t *testing.T) { func TestParseItemWithoutTitleButWithHTMLContent(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
@ -484,7 +553,7 @@ func TestParseFeedItemWithoutTitleButWithHTMLContent(t *testing.T) {
} }
} }
func TestParseFeedItemWithoutTitleButWithTextContent(t *testing.T) { func TestParseItemWithoutTitleButWithTextContent(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
@ -515,7 +584,7 @@ func TestParseFeedItemWithoutTitleButWithTextContent(t *testing.T) {
} }
} }
func TestParseTruncateItemTitleUnicode(t *testing.T) { func TestParseItemWithTooLongUnicodeTitle(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
@ -573,15 +642,34 @@ func TestParseItemTitleWithXMLTags(t *testing.T) {
} }
} }
func TestParseInvalidJSON(t *testing.T) { func TestParseItemWithoutID(t *testing.T) {
data := `garbage` data := `{
_, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data)) "version": "https://jsonfeed.org/version/1",
if err == nil { "title": "My Example Feed",
t.Error("Parse should returns an error") "home_page_url": "https://example.org/",
"feed_url": "https://example.org/feed.json",
"items": [
{
"content_text": "Some text."
}
]
}`
feed, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data))
if err != nil {
t.Fatal(err)
}
if len(feed.Entries) != 1 {
t.Errorf("Incorrect number of entries, got: %d", len(feed.Entries))
}
if feed.Entries[0].Hash != "13b4c5aecd1b6d749afcee968fbf9c80f1ed1bbdbe1aaf25cb34ebd01144bbe9" {
t.Errorf("Incorrect entry hash, got: %s", feed.Entries[0].Hash)
} }
} }
func TestParseTags(t *testing.T) { func TestParseItemTags(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"user_comment": "This is a microblog feed. You can add this to your feed reader using the following URL: https://example.org/feed.json", "user_comment": "This is a microblog feed. You can add this to your feed reader using the following URL: https://example.org/feed.json",
@ -600,7 +688,8 @@ func TestParseTags(t *testing.T) {
"content_text": "Cats are neat. \n\nhttps://example.org/cats", "content_text": "Cats are neat. \n\nhttps://example.org/cats",
"date_published": "2016-02-09T14:22:00-07:00", "date_published": "2016-02-09T14:22:00-07:00",
"tags": [ "tags": [
"tag 1", " tag 1",
" ",
"tag 2" "tag 2"
] ]
} }
@ -623,11 +712,11 @@ func TestParseTags(t *testing.T) {
} }
} }
func TestParseFavicon(t *testing.T) { func TestParseFeedFavicon(t *testing.T) {
data := `{ data := `{
"version": "https://jsonfeed.org/version/1", "version": "https://jsonfeed.org/version/1",
"title": "My Example Feed", "title": "My Example Feed",
"favicon": "https://micro.blog/jsonfeed/favicon.png", "favicon": "https://example.org/jsonfeed/favicon.png",
"home_page_url": "https://example.org/", "home_page_url": "https://example.org/",
"feed_url": "https://example.org/feed.json", "feed_url": "https://example.org/feed.json",
"items": [ "items": [
@ -648,7 +737,45 @@ func TestParseFavicon(t *testing.T) {
if err != nil { if err != nil {
t.Fatal(err) t.Fatal(err)
} }
if feed.IconURL != "https://micro.blog/jsonfeed/favicon.png" { if feed.IconURL != "https://example.org/jsonfeed/favicon.png" {
t.Errorf("Incorrect icon URL, got: %s", feed.IconURL) t.Errorf("Incorrect icon URL, got: %s", feed.IconURL)
} }
} }
func TestParseFeedIcon(t *testing.T) {
data := `{
"version": "https://jsonfeed.org/version/1",
"title": "My Example Feed",
"icon": "https://example.org/jsonfeed/icon.png",
"home_page_url": "https://example.org/",
"feed_url": "https://example.org/feed.json",
"items": [
{
"id": "2",
"content_text": "This is a second item.",
"url": "https://example.org/second-item"
},
{
"id": "1",
"content_html": "<p>Hello, world!</p>",
"url": "https://example.org/initial-post"
}
]
}`
feed, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data))
if err != nil {
t.Fatal(err)
}
if feed.IconURL != "https://example.org/jsonfeed/icon.png" {
t.Errorf("Incorrect icon URL, got: %s", feed.IconURL)
}
}
func TestParseInvalidJSON(t *testing.T) {
data := `garbage`
_, err := Parse("https://example.org/feed.json", bytes.NewBufferString(data))
if err == nil {
t.Error("Parse should returns an error")
}
}