mirrors
/
miniflux-v2
mirror of https://github.com/miniflux/v2.git
2
0
Fork 0
Code Issues Projects Releases Wiki Activity

Refactor Atom parser to use an adapter

This commit is contained in:
Frédéric Guillot 2024-03-15 16:39:32 -07:00
parent 2ba893bc79
commit dd4fb660c1
11 changed files with 795 additions and 500 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

216
internal/reader/atom/atom_03.go
View File

@ -6,158 +6,114 @@ package atom // import "miniflux.app/v2/internal/reader/atom"
import (
"encoding/base64"
"html"
"log/slog"
"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"
)
// Specs: http://web.archive.org/web/20060811235523/http://www.mnot.net/drafts/draft-nottingham-atom-format-02.html
type atom03Feed struct {
ID string `xml:"id"`
Title atom03Text `xml:"title"`
Author atomPerson `xml:"author"`
Links atomLinks `xml:"link"`
Entries []atom03Entry `xml:"entry"`
type Atom03Feed struct {
Version string `xml:"version,attr"`
// The "atom:id" element's content conveys a permanent, globally unique identifier for the feed.
// It MUST NOT change over time, even if the feed is relocated. atom:feed elements MAY contain an atom:id element,
// but MUST NOT contain more than one. The content of this element, when present, MUST be a URI.
ID string `xml:"http://purl.org/atom/ns# id"`
// The "atom:title" element is a Content construct that conveys a human-readable title for the feed.
// atom:feed elements MUST contain exactly one atom:title element.
// If the feed describes a Web resource, its content SHOULD be the same as that resource's title.
Title Atom03Content `xml:"http://purl.org/atom/ns# title"`
// The "atom:link" element is a Link construct that conveys a URI associated with the feed.
// The nature of the relationship as well as the link itself is determined by the element's content.
// atom:feed elements MUST contain at least one atom:link element with a rel attribute value of "alternate".
// atom:feed elements MUST NOT contain more than one atom:link element with a rel attribute value of "alternate" that has the same type attribute value.
// atom:feed elements MAY contain additional atom:link elements beyond those described above.
Links AtomLinks `xml:"http://purl.org/atom/ns# link"`
// The "atom:author" element is a Person construct that indicates the default author of the feed.
// atom:feed elements MUST contain exactly one atom:author element,
// UNLESS all of the atom:feed element's child atom:entry elements contain an atom:author element.
// atom:feed elements MUST NOT contain more than one atom:author element.
Author AtomPerson `xml:"http://purl.org/atom/ns# author"`
// The "atom:entry" element's represents an individual entry that is contained by the feed.
// atom:feed elements MAY contain one or more atom:entry elements.
Entries []Atom03Entry `xml:"http://purl.org/atom/ns# entry"`
}
func (a *atom03Feed) Transform(baseURL string) *model.Feed {
var err error
type Atom03Entry struct {
// The "atom:id" element's content conveys a permanent, globally unique identifier for the entry.
// It MUST NOT change over time, even if other representations of the entry (such as a web representation pointed to by the entry's atom:link element) are relocated.
// If the same entry is syndicated in two atom:feeds published by the same entity, the entry's atom:id MUST be the same in both feeds.
ID string `xml:"id"`
feed := new(model.Feed)
// The "atom:title" element is a Content construct that conveys a human-readable title for the entry.
// atom:entry elements MUST have exactly one "atom:title" element.
// If an entry describes a Web resource, its content SHOULD be the same as that resource's title.
Title Atom03Content `xml:"title"`
feedURL := a.Links.firstLinkWithRelation("self")
feed.FeedURL, err = urllib.AbsoluteURL(baseURL, feedURL)
if err != nil {
feed.FeedURL = feedURL
}
// The "atom:modified" element is a Date construct that indicates the time that the entry was last modified.
// atom:entry elements MUST contain an atom:modified element, but MUST NOT contain more than one.
// The content of an atom:modified element MUST have a time zone whose value SHOULD be "UTC".
Modified string `xml:"modified"`
siteURL := a.Links.originalLink()
feed.SiteURL, err = urllib.AbsoluteURL(baseURL, siteURL)
if err != nil {
feed.SiteURL = siteURL
}
// The "atom:issued" element is a Date construct that indicates the time that the entry was issued.
// atom:entry elements MUST contain an atom:issued element, but MUST NOT contain more than one.
// The content of an atom:issued element MAY omit a time zone.
Issued string `xml:"issued"`
feed.Title = a.Title.String()
if feed.Title == "" {
feed.Title = feed.SiteURL
}
// The "atom:created" element is a Date construct that indicates the time that the entry was created.
// atom:entry elements MAY contain an atom:created element, but MUST NOT contain more than one.
// The content of an atom:created element MUST have a time zone whose value SHOULD be "UTC".
// If atom:created is not present, its content MUST considered to be the same as that of atom:modified.
Created string `xml:"created"`
for _, entry := range a.Entries {
item := entry.Transform()
entryURL, err := urllib.AbsoluteURL(feed.SiteURL, item.URL)
if err == nil {
item.URL = entryURL
}
// The "atom:link" element is a Link construct that conveys a URI associated with the entry.
// The nature of the relationship as well as the link itself is determined by the element's content.
// atom:entry elements MUST contain at least one atom:link element with a rel attribute value of "alternate".
// atom:entry elements MUST NOT contain more than one atom:link element with a rel attribute value of "alternate" that has the same type attribute value.
// atom:entry elements MAY contain additional atom:link elements beyond those described above.
Links AtomLinks `xml:"link"`
if item.Author == "" {
item.Author = a.Author.String()
}
// The "atom:summary" element is a Content construct that conveys a short summary, abstract or excerpt of the entry.
// atom:entry elements MAY contain an atom:created element, but MUST NOT contain more than one.
Summary Atom03Content `xml:"summary"`
if item.Title == "" {
item.Title = sanitizer.TruncateHTML(item.Content, 100)
}
// The "atom:content" element is a Content construct that conveys the content of the entry.
// atom:entry elements MAY contain one or more atom:content elements.
Content Atom03Content `xml:"content"`
if item.Title == "" {
item.Title = item.URL
}
feed.Entries = append(feed.Entries, item)
}
return feed
// The "atom:author" element is a Person construct that indicates the default author of the entry.
// atom:entry elements MUST contain exactly one atom:author element,
// UNLESS the atom:feed element containing them contains an atom:author element itself.
// atom:entry elements MUST NOT contain more than one atom:author element.
Author AtomPerson `xml:"author"`
}
type atom03Entry struct {
ID string `xml:"id"`
Title atom03Text `xml:"title"`
Modified string `xml:"modified"`
Issued string `xml:"issued"`
Created string `xml:"created"`
Links atomLinks `xml:"link"`
Summary atom03Text `xml:"summary"`
Content atom03Text `xml:"content"`
Author atomPerson `xml:"author"`
}
type Atom03Content struct {
// Content constructs MAY have a "type" attribute, whose value indicates the media type of the content.
// When present, this attribute's value MUST be a registered media type [RFC2045].
// If not present, its value MUST be considered to be "text/plain".
Type string `xml:"type,attr"`
func (a *atom03Entry) Transform() *model.Entry {
entry := model.NewEntry()
entry.URL = a.Links.originalLink()
entry.Date = a.entryDate()
entry.Author = a.Author.String()
entry.Hash = a.entryHash()
entry.Content = a.entryContent()
entry.Title = a.entryTitle()
return entry
}
// Content constructs MAY have a "mode" attribute, whose value indicates the method used to encode the content.
// When present, this attribute's value MUST be listed below.
// If not present, its value MUST be considered to be "xml".
//
// "xml": A mode attribute with the value "xml" indicates that the element's content is inline xml (for example, namespace-qualified XHTML).
//
// "escaped": A mode attribute with the value "escaped" indicates that the element's content is an escaped string.
// Processors MUST unescape the element's content before considering it as content of the indicated media type.
//
// "base64": A mode attribute with the value "base64" indicates that the element's content is base64-encoded [RFC2045].
// Processors MUST decode the element's content before considering it as content of the the indicated media type.
Mode string `xml:"mode,attr"`
func (a *atom03Entry) entryTitle() string {
return sanitizer.StripTags(a.Title.String())
}
func (a *atom03Entry) entryContent() string {
content := a.Content.String()
if content != "" {
return content
}
summary := a.Summary.String()
if summary != "" {
return summary
}
return ""
}
func (a *atom03Entry) entryDate() time.Time {
dateText := ""
for _, value := range []string{a.Issued, a.Modified, a.Created} {
if value != "" {
dateText = value
break
}
}
if dateText != "" {
result, err := date.Parse(dateText)
if err != nil {
slog.Debug("Unable to parse date from Atom 0.3 feed",
slog.String("date", dateText),
slog.String("id", a.ID),
slog.Any("error", err),
)
return time.Now()
}
return result
}
return time.Now()
}
func (a *atom03Entry) entryHash() string {
for _, value := range []string{a.ID, a.Links.originalLink()} {
if value != "" {
return crypto.Hash(value)
}
}
return ""
}
type atom03Text struct {
Type string `xml:"type,attr"`
Mode string `xml:"mode,attr"`
CharData string `xml:",chardata"`
InnerXML string `xml:",innerxml"`
}
func (a *atom03Text) String() string {
func (a *Atom03Content) Content() string {
content := ""
switch {

115
internal/reader/atom/atom_03_adapter.go Normal file
View File

@ -0,0 +1,115 @@
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package atom // import "miniflux.app/v2/internal/reader/atom"
import (
"log/slog"
"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 Atom03Adapter struct {
atomFeed *Atom03Feed
}
func NewAtom03Adapter(atomFeed *Atom03Feed) *Atom03Adapter {
return &Atom03Adapter{atomFeed}
}
func (a *Atom03Adapter) BuildFeed(baseURL string) *model.Feed {
feed := new(model.Feed)
// Populate the feed URL.
feedURL := a.atomFeed.Links.firstLinkWithRelation("self")
if feedURL != "" {
if absoluteFeedURL, err := urllib.AbsoluteURL(baseURL, feedURL); err == nil {
feed.FeedURL = absoluteFeedURL
}
} else {
feed.FeedURL = baseURL
}
// Populate the site URL.
siteURL := a.atomFeed.Links.OriginalLink()
if siteURL != "" {
if absoluteSiteURL, err := urllib.AbsoluteURL(baseURL, siteURL); err == nil {
feed.SiteURL = absoluteSiteURL
}
} else {
feed.SiteURL = baseURL
}
// Populate the feed title.
feed.Title = a.atomFeed.Title.Content()
if feed.Title == "" {
feed.Title = feed.SiteURL
}
for _, atomEntry := range a.atomFeed.Entries {
entry := model.NewEntry()
// Populate the entry URL.
entry.URL = atomEntry.Links.OriginalLink()
if entry.URL != "" {
if absoluteEntryURL, err := urllib.AbsoluteURL(feed.SiteURL, entry.URL); err == nil {
entry.URL = absoluteEntryURL
}
}
// Populate the entry content.
entry.Content = atomEntry.Content.Content()
if entry.Content == "" {
entry.Content = atomEntry.Summary.Content()
}
// Populate the entry title.
entry.Title = atomEntry.Title.Content()
if entry.Title == "" {
entry.Title = sanitizer.TruncateHTML(entry.Content, 100)
}
if entry.Title == "" {
entry.Title = entry.URL
}
// Populate the entry author.
entry.Author = atomEntry.Author.PersonName()
if entry.Author == "" {
entry.Author = a.atomFeed.Author.PersonName()
}
// Populate the entry date.
for _, value := range []string{atomEntry.Issued, atomEntry.Modified, atomEntry.Created} {
if parsedDate, err := date.Parse(value); err == nil {
entry.Date = parsedDate
break
} else {
slog.Debug("Unable to parse date from Atom 0.3 feed",
slog.String("date", value),
slog.String("id", atomEntry.ID),
slog.Any("error", err),
)
}
}
if entry.Date.IsZero() {
entry.Date = time.Now()
}
// Generate the entry hash.
for _, value := range []string{atomEntry.ID, atomEntry.Links.OriginalLink()} {
if value != "" {
entry.Hash = crypto.Hash(value)
break
}
}
feed.Entries = append(feed.Entries, entry)
}
return feed
}

26
internal/reader/atom/atom_03_test.go
View File

@ -27,7 +27,7 @@ func TestParseAtom03(t *testing.T) {
</entry>
</feed>`
feed, err := Parse("http://diveintomark.org/", bytes.NewReader([]byte(data)), "0.3")
feed, err := Parse("http://diveintomark.org/atom.xml", bytes.NewReader([]byte(data)), "0.3")
if err != nil {
t.Fatal(err)
}
@ -36,7 +36,7 @@ func TestParseAtom03(t *testing.T) {
t.Errorf("Incorrect title, got: %s", feed.Title)
}
if feed.FeedURL != "http://diveintomark.org/" {
if feed.FeedURL != "http://diveintomark.org/atom.xml" {
t.Errorf("Incorrect feed URL, got: %s", feed.FeedURL)
}
@ -74,6 +74,28 @@ func TestParseAtom03(t *testing.T) {
}
}
func TestParseAtom03WithoutSiteURL(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
<modified>2003-12-13T18:30:02Z</modified>
<author><name>Mark Pilgrim</name></author>
<entry>
<title>Atom 0.3 snapshot</title>
<link rel="alternate" type="text/html" href="http://diveintomark.org/2003/12/13/atom03"/>
<id>tag:diveintomark.org,2003:3.2397</id>
</entry>
</feed>`
feed, err := Parse("http://diveintomark.org/atom.xml", bytes.NewReader([]byte(data)), "0.3")
if err != nil {
t.Fatal(err)
}
if feed.SiteURL != "http://diveintomark.org/atom.xml" {
t.Errorf("Incorrect title, got: %s", feed.Title)
}
}
func TestParseAtom03WithoutFeedTitle(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed version="0.3" xmlns="http://purl.org/atom/ns#">

407
internal/reader/atom/atom_10.go
View File

@ -6,286 +6,199 @@ package atom // import "miniflux.app/v2/internal/reader/atom"
import (
"encoding/xml"
"html"
"log/slog"
"strconv"
"strings"
"time"
"miniflux.app/v2/internal/crypto"
"miniflux.app/v2/internal/model"
"miniflux.app/v2/internal/reader/date"
"miniflux.app/v2/internal/reader/media"
"miniflux.app/v2/internal/reader/sanitizer"
"miniflux.app/v2/internal/urllib"
)
// The "atom:feed" element is the document (i.e., top-level) element of
// an Atom Feed Document, acting as a container for metadata and data
// associated with the feed. Its element children consist of metadata
// elements followed by zero or more atom:entry child elements.
//
// Specs:
// https://tools.ietf.org/html/rfc4287
// https://validator.w3.org/feed/docs/atom.html
type atom10Feed struct {
XMLName xml.Name `xml:"http://www.w3.org/2005/Atom feed"`
ID string `xml:"id"`
Title atom10Text `xml:"title"`
Authors atomAuthors `xml:"author"`
Icon string `xml:"icon"`
Links atomLinks `xml:"link"`
Entries []atom10Entry `xml:"entry"`
type Atom10Feed struct {
XMLName xml.Name `xml:"http://www.w3.org/2005/Atom feed"`
// The "atom:id" element conveys a permanent, universally unique
// identifier for an entry or feed.
//
// Its content MUST be an IRI, as defined by [RFC3987]. Note that the
// definition of "IRI" excludes relative references. Though the IRI
// might use a dereferencable scheme, Atom Processors MUST NOT assume it
// can be dereferenced.
//
// atom:feed elements MUST contain exactly one atom:id element.
ID string `xml:"http://www.w3.org/2005/Atom id"`
// The "atom:title" element is a Text construct that conveys a human-
// readable title for an entry or feed.
//
// atom:feed elements MUST contain exactly one atom:title element.
Title Atom10Text `xml:"http://www.w3.org/2005/Atom title"`
// The "atom:author" element is a Person construct that indicates the
// author of the entry or feed.
//
// atom:feed elements MUST contain one or more atom:author elements,
// unless all of the atom:feed element's child atom:entry elements
// contain at least one atom:author element.
Authors AtomPersons `xml:"http://www.w3.org/2005/Atom author"`
// The "atom:icon" element's content is an IRI reference [RFC3987] that
// identifies an image that provides iconic visual identification for a
// feed.
//
// atom:feed elements MUST NOT contain more than one atom:icon element.
Icon string `xml:"http://www.w3.org/2005/Atom icon"`
// The "atom:logo" element's content is an IRI reference [RFC3987] that
// identifies an image that provides visual identification for a feed.
//
// atom:feed elements MUST NOT contain more than one atom:logo element.
Logo string `xml:"http://www.w3.org/2005/Atom logo"`
// atom:feed elements SHOULD contain one atom:link element with a rel
// attribute value of "self". This is the preferred URI for
// retrieving Atom Feed Documents representing this Atom feed.
//
// atom:feed elements MUST NOT contain more than one atom:link
// element with a rel attribute value of "alternate" that has the
// same combination of type and hreflang attribute values.
Links AtomLinks `xml:"http://www.w3.org/2005/Atom link"`
// The "atom:category" element conveys information about a category
// associated with an entry or feed. This specification assigns no
// meaning to the content (if any) of this element.
//
// atom:feed elements MAY contain any number of atom:category
// elements.
Categories AtomCategories `xml:"http://www.w3.org/2005/Atom category"`
Entries []Atom10Entry `xml:"http://www.w3.org/2005/Atom entry"`
}
func (a *atom10Feed) Transform(baseURL string) *model.Feed {
var err error
type Atom10Entry struct {
// The "atom:id" element conveys a permanent, universally unique
// identifier for an entry or feed.
//
// Its content MUST be an IRI, as defined by [RFC3987]. Note that the
// definition of "IRI" excludes relative references. Though the IRI
// might use a dereferencable scheme, Atom Processors MUST NOT assume it
// can be dereferenced.
//
// atom:entry elements MUST contain exactly one atom:id element.
ID string `xml:"http://www.w3.org/2005/Atom id"`
feed := new(model.Feed)
// The "atom:title" element is a Text construct that conveys a human-
// readable title for an entry or feed.
//
// atom:entry elements MUST contain exactly one atom:title element.
Title Atom10Text `xml:"http://www.w3.org/2005/Atom title"`
feedURL := a.Links.firstLinkWithRelation("self")
feed.FeedURL, err = urllib.AbsoluteURL(baseURL, feedURL)
if err != nil {
feed.FeedURL = feedURL
}
// The "atom:published" element is a Date construct indicating an
// instant in time associated with an event early in the life cycle of
// the entry.
Published string `xml:"http://www.w3.org/2005/Atom published"`
siteURL := a.Links.originalLink()
feed.SiteURL, err = urllib.AbsoluteURL(baseURL, siteURL)
if err != nil {
feed.SiteURL = siteURL
}
// The "atom:updated" element is a Date construct indicating the most
// recent instant in time when an entry or feed was modified in a way
// the publisher considers significant. Therefore, not all
// modifications necessarily result in a changed atom:updated value.
//
// atom:entry elements MUST contain exactly one atom:updated element.
Updated string `xml:"http://www.w3.org/2005/Atom updated"`
feed.Title = html.UnescapeString(a.Title.String())
if feed.Title == "" {
feed.Title = feed.SiteURL
}
// atom:entry elements MUST NOT contain more than one atom:link
// element with a rel attribute value of "alternate" that has the
// same combination of type and hreflang attribute values.
Links AtomLinks `xml:"http://www.w3.org/2005/Atom link"`
feed.IconURL = strings.TrimSpace(a.Icon)
// atom:entry elements MUST contain an atom:summary element in either
// of the following cases:
// * the atom:entry contains an atom:content that has a "src"
// attribute (and is thus empty).
// * the atom:entry contains content that is encoded in Base64;
// i.e., the "type" attribute of atom:content is a MIME media type
// [MIMEREG], but is not an XML media type [RFC3023], does not
// begin with "text/", and does not end with "/xml" or "+xml".
//
// atom:entry elements MUST NOT contain more than one atom:summary
// element.
Summary Atom10Text `xml:"http://www.w3.org/2005/Atom summary"`
for _, entry := range a.Entries {
item := entry.Transform()
entryURL, err := urllib.AbsoluteURL(feed.SiteURL, item.URL)
if err == nil {
item.URL = entryURL
}
// atom:entry elements MUST NOT contain more than one atom:content
// element.
Content Atom10Text `xml:"http://www.w3.org/2005/Atom content"`
if item.Author == "" {
item.Author = a.Authors.String()
}
// The "atom:author" element is a Person construct that indicates the
// author of the entry or feed.
//
// atom:entry elements MUST contain one or more atom:author elements
Authors AtomPersons `xml:"http://www.w3.org/2005/Atom author"`
if item.Title == "" {
item.Title = sanitizer.TruncateHTML(item.Content, 100)
}
// The "atom:category" element conveys information about a category
// associated with an entry or feed. This specification assigns no
// meaning to the content (if any) of this element.
//
// atom:entry elements MAY contain any number of atom:category
// elements.
Categories AtomCategories `xml:"http://www.w3.org/2005/Atom category"`
if item.Title == "" {
item.Title = item.URL
}
feed.Entries = append(feed.Entries, item)
}
return feed
}
type atom10Entry struct {
ID string `xml:"id"`
Title atom10Text `xml:"title"`
Published string `xml:"published"`
Updated string `xml:"updated"`
Links atomLinks `xml:"link"`
Summary atom10Text `xml:"summary"`
Content atom10Text `xml:"http://www.w3.org/2005/Atom content"`
Authors atomAuthors `xml:"author"`
Categories []atom10Category `xml:"category"`
media.MediaItemElement
}
func (a *atom10Entry) Transform() *model.Entry {
entry := model.NewEntry()
entry.URL = a.Links.originalLink()
entry.Date = a.entryDate()
entry.Author = a.Authors.String()
entry.Hash = a.entryHash()
entry.Content = a.entryContent()
entry.Title = a.entryTitle()
entry.Enclosures = a.entryEnclosures()
entry.CommentsURL = a.entryCommentsURL()
entry.Tags = a.entryCategories()
return entry
}
func (a *atom10Entry) entryTitle() string {
return html.UnescapeString(a.Title.String())
}
func (a *atom10Entry) entryContent() string {
content := a.Content.String()
if content != "" {
return content
}
summary := a.Summary.String()
if summary != "" {
return summary
}
mediaDescription := a.FirstMediaDescription()
if mediaDescription != "" {
return mediaDescription
}
return ""
}
// Note: The published date represents the original creation date for YouTube feeds.
// Example:
// <published>2019-01-26T08:02:28+00:00</published>
// <updated>2019-01-29T07:27:27+00:00</updated>
func (a *atom10Entry) entryDate() time.Time {
dateText := a.Published
if dateText == "" {
dateText = a.Updated
}
if dateText != "" {
result, err := date.Parse(dateText)
if err != nil {
slog.Debug("Unable to parse date from Atom 0.3 feed",
slog.String("date", dateText),
slog.String("id", a.ID),
slog.Any("error", err),
)
return time.Now()
}
return result
}
return time.Now()
}
func (a *atom10Entry) entryHash() string {
for _, value := range []string{a.ID, a.Links.originalLink()} {
if value != "" {
return crypto.Hash(value)
}
}
return ""
}
func (a *atom10Entry) entryEnclosures() model.EnclosureList {
enclosures := make(model.EnclosureList, 0)
duplicates := make(map[string]bool)
for _, mediaThumbnail := range a.AllMediaThumbnails() {
if _, found := duplicates[mediaThumbnail.URL]; !found {
duplicates[mediaThumbnail.URL] = true
enclosures = append(enclosures, &model.Enclosure{
URL: mediaThumbnail.URL,
MimeType: mediaThumbnail.MimeType(),
Size: mediaThumbnail.Size(),
})
}
}
for _, link := range a.Links {
if strings.EqualFold(link.Rel, "enclosure") {
if link.URL == "" {
continue
}
if _, found := duplicates[link.URL]; !found {
duplicates[link.URL] = true
length, _ := strconv.ParseInt(link.Length, 10, 0)
enclosures = append(enclosures, &model.Enclosure{URL: link.URL, MimeType: link.Type, Size: length})
}
}
}
for _, mediaContent := range a.AllMediaContents() {
if _, found := duplicates[mediaContent.URL]; !found {
duplicates[mediaContent.URL] = true
enclosures = append(enclosures, &model.Enclosure{
URL: mediaContent.URL,
MimeType: mediaContent.MimeType(),
Size: mediaContent.Size(),
})
}
}
for _, mediaPeerLink := range a.AllMediaPeerLinks() {
if _, found := duplicates[mediaPeerLink.URL]; !found {
duplicates[mediaPeerLink.URL] = true
enclosures = append(enclosures, &model.Enclosure{
URL: mediaPeerLink.URL,
MimeType: mediaPeerLink.MimeType(),
Size: mediaPeerLink.Size(),
})
}
}
return enclosures
}
func (r *atom10Entry) entryCategories() []string {
categoryList := make([]string, 0)
for _, atomCategory := range r.Categories {
if strings.TrimSpace(atomCategory.Label) != "" {
categoryList = append(categoryList, strings.TrimSpace(atomCategory.Label))
} else {
categoryList = append(categoryList, strings.TrimSpace(atomCategory.Term))
}
}
return categoryList
}
// See https://tools.ietf.org/html/rfc4685#section-4
// If the type attribute of the atom:link is omitted, its value is assumed to be "application/atom+xml".
// We accept only HTML or XHTML documents for now since the intention is to have the same behavior as RSS.
func (a *atom10Entry) entryCommentsURL() string {
commentsURL := a.Links.firstLinkWithRelationAndType("replies", "text/html", "application/xhtml+xml")
if urllib.IsAbsoluteURL(commentsURL) {
return commentsURL
}
return ""
}
type atom10Text struct {
Type string `xml:"type,attr"`
CharData string `xml:",chardata"`
InnerXML string `xml:",innerxml"`
XHTMLRootElement atomXHTMLRootElement `xml:"http://www.w3.org/1999/xhtml div"`
}
type atom10Category struct {
Term string `xml:"term,attr"`
Label string `xml:"label,attr"`
}
// A Text construct contains human-readable text, usually in small
// quantities. The content of Text constructs is Language-Sensitive.
// Specs: https://datatracker.ietf.org/doc/html/rfc4287#section-3.1
// Text: https://datatracker.ietf.org/doc/html/rfc4287#section-3.1.1.1
// HTML: https://datatracker.ietf.org/doc/html/rfc4287#section-3.1.1.2
// XHTML: https://datatracker.ietf.org/doc/html/rfc4287#section-3.1.1.3
func (a *atom10Text) String() string {
type Atom10Text struct {
Type string `xml:"type,attr"`
CharData string `xml:",chardata"`
InnerXML string `xml:",innerxml"`
XHTMLRootElement AtomXHTMLRootElement `xml:"http://www.w3.org/1999/xhtml div"`
}
func (a *Atom10Text) Body() string {
var content string
switch {
case a.Type == "", a.Type == "text", a.Type == "text/plain":
if strings.HasPrefix(strings.TrimSpace(a.InnerXML), `<![CDATA[`) {
content = html.EscapeString(a.CharData)
} else {
content = a.InnerXML
}
case a.Type == "xhtml":
var root = a.XHTMLRootElement
if root.XMLName.Local == "div" {
content = root.InnerXML
} else {
content = a.InnerXML
}
default:
if strings.EqualFold(a.Type, "xhtml") {
content = a.xhtmlContent()
} else {
content = a.CharData
}
return strings.TrimSpace(content)
}
type atomXHTMLRootElement struct {
func (a *Atom10Text) Title() string {
var content string
if strings.EqualFold(a.Type, "xhtml") {
content = a.xhtmlContent()
} else if strings.Contains(a.InnerXML, "<![CDATA[") {
content = html.UnescapeString(a.CharData)
} else {
content = a.CharData
}
content = sanitizer.StripTags(content)
return strings.TrimSpace(content)
}
func (a *Atom10Text) xhtmlContent() string {
if a.XHTMLRootElement.XMLName.Local == "div" {
return a.XHTMLRootElement.InnerXML
}
return a.InnerXML
}
type AtomXHTMLRootElement struct {
XMLName xml.Name `xml:"div"`
InnerXML string `xml:",innerxml"`
}

210
internal/reader/atom/atom_10_adapter.go Normal file
View File

@ -0,0 +1,210 @@
// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package atom // import "miniflux.app/v2/internal/reader/atom"
import (
"log/slog"
"slices"
"sort"
"strconv"
"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 Atom10Adapter struct {
atomFeed *Atom10Feed
}
func NewAtom10Adapter(atomFeed *Atom10Feed) *Atom10Adapter {
return &Atom10Adapter{atomFeed}
}
func (a *Atom10Adapter) BuildFeed(baseURL string) *model.Feed {
feed := new(model.Feed)
// Populate the feed URL.
feedURL := a.atomFeed.Links.firstLinkWithRelation("self")
if feedURL != "" {
if absoluteFeedURL, err := urllib.AbsoluteURL(baseURL, feedURL); err == nil {
feed.FeedURL = absoluteFeedURL
}
} else {
feed.FeedURL = baseURL
}
// Populate the site URL.
siteURL := a.atomFeed.Links.OriginalLink()
if siteURL != "" {
if absoluteSiteURL, err := urllib.AbsoluteURL(baseURL, siteURL); err == nil {
feed.SiteURL = absoluteSiteURL
}
} else {
feed.SiteURL = baseURL
}
// Populate the feed title.
feed.Title = a.atomFeed.Title.Body()
if feed.Title == "" {
feed.Title = feed.SiteURL
}
// Populate the feed icon.
if a.atomFeed.Icon != "" {
if absoluteIconURL, err := urllib.AbsoluteURL(feed.SiteURL, a.atomFeed.Icon); err == nil {
feed.IconURL = absoluteIconURL
}
} else if a.atomFeed.Logo != "" {
if absoluteLogoURL, err := urllib.AbsoluteURL(feed.SiteURL, a.atomFeed.Logo); err == nil {
feed.IconURL = absoluteLogoURL
}
}
for _, atomEntry := range a.atomFeed.Entries {
entry := model.NewEntry()
// Populate the entry URL.
entry.URL = atomEntry.Links.OriginalLink()
if entry.URL != "" {
if absoluteEntryURL, err := urllib.AbsoluteURL(feed.SiteURL, entry.URL); err == nil {
entry.URL = absoluteEntryURL
}
}
// Populate the entry content.
entry.Content = atomEntry.Content.Body()
if entry.Content == "" {
entry.Content = atomEntry.Summary.Body()
}
if entry.Content == "" {
entry.Content = atomEntry.FirstMediaDescription()
}
// Populate the entry title.
entry.Title = atomEntry.Title.Title()
if entry.Title == "" {
entry.Title = sanitizer.TruncateHTML(entry.Content, 100)
}
if entry.Title == "" {
entry.Title = entry.URL
}
// Populate the entry author.
authors := atomEntry.Authors.PersonNames()
if len(authors) == 0 {
authors = append(authors, a.atomFeed.Authors.PersonNames()...)
}
authors = slices.Compact(authors)
sort.Strings(authors)
entry.Author = strings.Join(authors, ", ")
// Populate the entry date.
for _, value := range []string{atomEntry.Published, atomEntry.Updated} {
if parsedDate, err := date.Parse(value); err != nil {
slog.Debug("Unable to parse date from Atom 1.0 feed",
slog.String("date", value),
slog.String("url", entry.URL),
slog.Any("error", err),
)
} else {
entry.Date = parsedDate
break
}
}
if entry.Date.IsZero() {
entry.Date = time.Now()
}
// Populate categories.
categories := atomEntry.Categories.CategoryNames()
if len(categories) == 0 {
categories = append(categories, a.atomFeed.Categories.CategoryNames()...)
}
if len(categories) > 0 {
categories = slices.Compact(categories)
sort.Strings(categories)
entry.Tags = categories
}
// Populate the commentsURL if defined.
// See https://tools.ietf.org/html/rfc4685#section-4
// If the type attribute of the atom:link is omitted, its value is assumed to be "application/atom+xml".
// We accept only HTML or XHTML documents for now since the intention is to have the same behavior as RSS.
commentsURL := atomEntry.Links.firstLinkWithRelationAndType("replies", "text/html", "application/xhtml+xml")
if urllib.IsAbsoluteURL(commentsURL) {
entry.CommentsURL = commentsURL
}
// Generate the entry hash.
for _, value := range []string{atomEntry.ID, atomEntry.Links.OriginalLink()} {
if value != "" {
entry.Hash = crypto.Hash(value)
break
}
}
// Populate the entry enclosures.
uniqueEnclosuresMap := make(map[string]bool)
for _, mediaThumbnail := range atomEntry.AllMediaThumbnails() {
if _, found := uniqueEnclosuresMap[mediaThumbnail.URL]; !found {
uniqueEnclosuresMap[mediaThumbnail.URL] = true
entry.Enclosures = append(entry.Enclosures, &model.Enclosure{
URL: mediaThumbnail.URL,
MimeType: mediaThumbnail.MimeType(),
Size: mediaThumbnail.Size(),
})
}
}
for _, link := range atomEntry.Links {
if strings.EqualFold(link.Rel, "enclosure") {
if link.Href == "" {
continue
}
if _, found := uniqueEnclosuresMap[link.Href]; !found {
uniqueEnclosuresMap[link.Href] = true
length, _ := strconv.ParseInt(link.Length, 10, 0)
entry.Enclosures = append(entry.Enclosures, &model.Enclosure{
URL: link.Href,
MimeType: link.Type,
Size: length,
})
}
}
}
for _, mediaContent := range atomEntry.AllMediaContents() {
if _, found := uniqueEnclosuresMap[mediaContent.URL]; !found {
uniqueEnclosuresMap[mediaContent.URL] = true
entry.Enclosures = append(entry.Enclosures, &model.Enclosure{
URL: mediaContent.URL,
MimeType: mediaContent.MimeType(),
Size: mediaContent.Size(),
})
}
}
for _, mediaPeerLink := range atomEntry.AllMediaPeerLinks() {
if _, found := uniqueEnclosuresMap[mediaPeerLink.URL]; !found {
uniqueEnclosuresMap[mediaPeerLink.URL] = true
entry.Enclosures = append(entry.Enclosures, &model.Enclosure{
URL: mediaPeerLink.URL,
MimeType: mediaPeerLink.MimeType(),
Size: mediaPeerLink.Size(),
})
}
}
feed.Entries = append(feed.Entries, entry)
}
return feed
}

145
internal/reader/atom/atom_10_test.go
View File

@ -12,7 +12,6 @@ import (
func TestParseAtomSample(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<link href="http://example.org/"/>
<updated>2003-12-13T18:30:02Z</updated>
@ -20,7 +19,6 @@ func TestParseAtomSample(t *testing.T) {
<name>John Doe</name>
</author>
<id>urn:uuid:60a76c80-d399-11d9-b93C-0003939e0af6</id>
<entry>
<title>Atom-Powered Robots Run Amok</title>
<link href="http://example.org/2003/12/13/atom03"/>
@ -28,7 +26,6 @@ func TestParseAtomSample(t *testing.T) {
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
</entry>
</feed>`
feed, err := Parse("http://example.org/feed.xml", bytes.NewReader([]byte(data)), "10")
@ -420,7 +417,7 @@ func TestParseEntryWithPlainTextTitle(t *testing.T) {
expected := `AT&T bought by SBC!`
for i := range 2 {
if feed.Entries[i].Title != expected {
t.Errorf("Incorrect title for entry #%d, got: %q", i, feed.Entries[i].Title)
t.Errorf("Incorrect title for entry #%d, got: %q instead of %q", i, feed.Entries[i].Title, expected)
}
}
}
@ -430,33 +427,20 @@ func TestParseEntryWithHTMLTitle(t *testing.T) {
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<link href="http://example.org/"/>
<entry>
<title type="html">&lt;code&gt;Test&lt;/code&gt; Test</title>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
<title type="html">&lt;code&gt;Code&lt;/code&gt; Test</title>
<link href="http://example.org/z"/>
</entry>
<entry>
<title type="html"><![CDATA[Test &#8220;Test&#8221;]]></title>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
<title type="html"><![CDATA[Test with &#8220;unicode quote&#8221;]]></title>
<link href="http://example.org/b"/>
</entry>
<entry>
<title>
<![CDATA[Entry title with space around CDATA]]>
</title>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
<link href="http://example.org/c"/>
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
@ -464,11 +448,11 @@ func TestParseEntryWithHTMLTitle(t *testing.T) {
t.Fatal(err)
}
if feed.Entries[0].Title != "<code>Test</code> Test" {
if feed.Entries[0].Title != "Code Test" {
t.Errorf("Incorrect entry title, got: %q", feed.Entries[0].Title)
}
if feed.Entries[1].Title != "Test “Test”" {
if feed.Entries[1].Title != "Test with “unicode quote”" {
t.Errorf("Incorrect entry title, got: %q", feed.Entries[1].Title)
}
@ -502,8 +486,8 @@ func TestParseEntryWithXHTMLTitle(t *testing.T) {
t.Fatal(err)
}
if feed.Entries[0].Title != `This is <b>XHTML</b> content.` {
t.Errorf("Incorrect entry title, got: %q", feed.Entries[1].Title)
if feed.Entries[0].Title != `This is XHTML content.` {
t.Errorf("Incorrect entry title, got: %q", feed.Entries[0].Title)
}
}
@ -608,7 +592,7 @@ func TestParseEntryWithDoubleEncodedEntitiesTitle(t *testing.T) {
t.Fatal(err)
}
if feed.Entries[0].Title != `&#39;AT&amp;T&#39;` {
if feed.Entries[0].Title != `'AT&T'` {
t.Errorf("Incorrect entry title, got: %q", feed.Entries[0].Title)
}
}
@ -644,31 +628,21 @@ func TestParseEntryWithHTMLSummary(t *testing.T) {
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<link href="http://example.org/"/>
<entry>
<title type="html">Example</title>
<title type="html">Example 1</title>
<link href="http://example.org/1"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary type="html">&lt;code&gt;std::unique_ptr&amp;lt;S&amp;gt;&lt;/code&gt;</summary>
<summary type="html">&lt;code&gt;std::unique_ptr&amp;lt;S&amp;gt; myvar;&lt;/code&gt;</summary>
</entry>
<entry>
<title type="html">Example</title>
<title type="html">Example 2</title>
<link href="http://example.org/2"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary type="text/html">&lt;code&gt;std::unique_ptr&amp;lt;S&amp;gt;&lt;/code&gt;</summary>
<summary type="text/html">&lt;code&gt;std::unique_ptr&amp;lt;S&amp;gt; myvar;&lt;/code&gt;</summary>
</entry>
<entry>
<title type="html">Example</title>
<title type="html">Example 3</title>
<link href="http://example.org/3"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary type="html"><![CDATA[<code>std::unique_ptr&lt;S&gt;</code>]]></summary>
<summary type="html"><![CDATA[<code>std::unique_ptr&lt;S&gt; myvar;</code>]]></summary>
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
@ -676,7 +650,11 @@ func TestParseEntryWithHTMLSummary(t *testing.T) {
t.Fatal(err)
}
expected := `<code>std::unique_ptr&lt;S&gt;</code>`
if len(feed.Entries) != 3 {
t.Fatalf("Incorrect number of entries, got: %d", len(feed.Entries))
}
expected := `<code>std::unique_ptr&lt;S&gt; myvar;</code>`
for i := range 3 {
if feed.Entries[i].Content != expected {
t.Errorf("Incorrect content for entry #%d, got: %q", i, feed.Entries[i].Content)
@ -728,7 +706,7 @@ func TestParseEntryWithTextSummary(t *testing.T) {
t.Fatal(err)
}
expected := `AT&amp;T &lt;S&gt;`
expected := `AT&T <S>`
for i := range 4 {
if feed.Entries[i].Content != expected {
t.Errorf("Incorrect content for entry #%d, got: %q", i, feed.Entries[i].Content)
@ -747,7 +725,7 @@ func TestParseEntryWithTextContent(t *testing.T) {
<link href="http://example.org/a"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<content>AT&amp;T &lt;S&gt;</content>
<content>AT&amp;T &lt;strong&gt;Strong Element&lt;/strong&gt;</content>
</entry>
<entry>
@ -755,7 +733,7 @@ func TestParseEntryWithTextContent(t *testing.T) {
<link href="http://example.org/b"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<content type="text">AT&amp;T &lt;S&gt;</content>
<content type="text">AT&amp;T &lt;strong&gt;Strong Element&lt;/strong&gt;</content>
</entry>
<entry>
@ -763,7 +741,7 @@ func TestParseEntryWithTextContent(t *testing.T) {
<link href="http://example.org/c"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<content type="text/plain">AT&amp;T &lt;S&gt;</content>
<content type="text/plain">AT&amp;T &lt;strong&gt;Strong Element&lt;/strong&gt;</content>
</entry>
<entry>
@ -771,7 +749,7 @@ func TestParseEntryWithTextContent(t *testing.T) {
<link href="http://example.org/d"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<content><![CDATA[AT&T <S>]]></content>
<content><![CDATA[AT&T <strong>Strong Element</strong>]]></content>
</entry>
</feed>`
@ -781,10 +759,10 @@ func TestParseEntryWithTextContent(t *testing.T) {
t.Fatal(err)
}
expected := `AT&amp;T &lt;S&gt;`
expected := `AT&T <strong>Strong Element</strong>`
for i := range 4 {
if feed.Entries[i].Content != expected {
t.Errorf("Incorrect content for entry #%d, got: %q", i, feed.Entries[i].Content)
t.Errorf("Incorrect content for entry #%d, got: %q instead of %q", i, feed.Entries[i].Content, expected)
}
}
}
@ -925,7 +903,6 @@ func TestParseEntryWithMultipleAuthors(t *testing.T) {
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<link href="http://example.org/"/>
<entry>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
@ -938,7 +915,6 @@ func TestParseEntryWithMultipleAuthors(t *testing.T) {
<name>Bob</name>
</author>
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
@ -951,7 +927,7 @@ func TestParseEntryWithMultipleAuthors(t *testing.T) {
}
}
func TestParseEntryWithoutAuthor(t *testing.T) {
func TestParseFeedWithEntryWithoutAuthor(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
@ -959,14 +935,12 @@ func TestParseEntryWithoutAuthor(t *testing.T) {
<author>
<name>John Doe</name>
</author>
<entry>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
@ -990,14 +964,15 @@ func TestParseFeedWithMultipleAuthors(t *testing.T) {
<author>
<name>Bob</name>
</author>
<author>
<name>Bob</name>
</author>
<entry>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
@ -1015,14 +990,12 @@ func TestParseFeedWithoutAuthor(t *testing.T) {
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<link href="http://example.org/"/>
<entry>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
@ -1608,27 +1581,18 @@ func TestAbsoluteCommentsURL(t *testing.T) {
}
}
func TestParseFeedWithCategories(t *testing.T) {
func TestParseItemWithCategories(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<link href="http://example.org/"/>
<author>
<name>Alice</name>
</author>
<author>
<name>Bob</name>
</author>
<entry>
<link href="http://example.org/2003/12/13/atom03"/>
<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
<link href="http://www.example.org/entries/1" />
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
<category term='Tech' />
<category term='ZZZZ' />
<category term='Technology' label='Science' />
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
@ -1637,22 +1601,53 @@ func TestParseFeedWithCategories(t *testing.T) {
}
if len(feed.Entries[0].Tags) != 2 {
t.Errorf("Incorrect number of tags, got: %d", len(feed.Entries[0].Tags))
t.Fatalf("Incorrect number of tags, got: %d", len(feed.Entries[0].Tags))
}
expected := "Tech"
expected := "Science"
result := feed.Entries[0].Tags[0]
if result != expected {
t.Errorf("Incorrect entry category, got %q instead of %q", result, expected)
}
expected = "Science"
expected = "ZZZZ"
result = feed.Entries[0].Tags[1]
if result != expected {
t.Errorf("Incorrect entry category, got %q instead of %q", result, expected)
}
}
func TestParseFeedWithCategories(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
<title>Example Feed</title>
<link href="http://example.org/"/>
<category term='Test' label='Some Label' />
<category term='Test' label='Some Label' />
<category term='Test' label='Some Label' />
<entry>
<link href="http://www.example.org/entries/1" />
<updated>2003-12-13T18:30:02Z</updated>
<summary>Some text.</summary>
</entry>
</feed>`
feed, err := Parse("https://example.org/", bytes.NewReader([]byte(data)), "10")
if err != nil {
t.Fatal(err)
}
if len(feed.Entries[0].Tags) != 1 {
t.Fatalf("Incorrect number of tags, got: %d", len(feed.Entries[0].Tags))
}
expected := "Some Label"
result := feed.Entries[0].Tags[0]
if result != expected {
t.Errorf("Incorrect entry category, got %q instead of %q", result, expected)
}
}
func TestParseFeedWithIconURL(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">

111
internal/reader/atom/atom_common.go
View File

@ -3,77 +3,91 @@
package atom // import "miniflux.app/v2/internal/reader/atom"
import "strings"
import (
"strings"
)
type atomPerson struct {
Name string `xml:"name"`
// Specs: https://datatracker.ietf.org/doc/html/rfc4287#section-3.2
type AtomPerson struct {
// The "atom:name" element's content conveys a human-readable name for the author.
// It MAY be the name of a corporation or other entity no individual authors can be named.
// Person constructs MUST contain exactly one "atom:name" element, whose content MUST be a string.
Name string `xml:"name"`
// The "atom:email" element's content conveys an e-mail address associated with the Person construct.
// Person constructs MAY contain an atom:email element, but MUST NOT contain more than one.
// Its content MUST be an e-mail address [RFC2822].
// Ordering of the element children of Person constructs MUST NOT be considered significant.
Email string `xml:"email"`
}
func (a *atomPerson) String() string {
name := ""
switch {
case a.Name != "":
name = a.Name
case a.Email != "":
name = a.Email
func (a *AtomPerson) PersonName() string {
name := strings.TrimSpace(a.Name)
if name != "" {
return name
}
return strings.TrimSpace(name)
return strings.TrimSpace(a.Email)
}
type atomAuthors []*atomPerson
type AtomPersons []*AtomPerson
func (a atomAuthors) String() string {
var authors []string
func (a AtomPersons) PersonNames() []string {
var names []string
authorNamesMap := make(map[string]bool)
for _, person := range a {
authors = append(authors, person.String())
personName := person.PersonName()
if _, ok := authorNamesMap[personName]; !ok {
names = append(names, personName)
authorNamesMap[personName] = true
}
}
return strings.Join(authors, ", ")
return names
}
type atomLink struct {
URL string `xml:"href,attr"`
// Specs: https://datatracker.ietf.org/doc/html/rfc4287#section-4.2.7
type AtomLink struct {
Href string `xml:"href,attr"`
Type string `xml:"type,attr"`
Rel string `xml:"rel,attr"`
Length string `xml:"length,attr"`
Title string `xml:"title,attr"`
}
type atomLinks []*atomLink
type AtomLinks []*AtomLink
func (a atomLinks) originalLink() string {
func (a AtomLinks) OriginalLink() string {
for _, link := range a {
if strings.EqualFold(link.Rel, "alternate") {
return strings.TrimSpace(link.URL)
return strings.TrimSpace(link.Href)
}
if link.Rel == "" && (link.Type == "" || link.Type == "text/html") {
return strings.TrimSpace(link.URL)
return strings.TrimSpace(link.Href)
}
}
return ""
}
func (a atomLinks) firstLinkWithRelation(relation string) string {
func (a AtomLinks) firstLinkWithRelation(relation string) string {
for _, link := range a {
if strings.EqualFold(link.Rel, relation) {
return strings.TrimSpace(link.URL)
return strings.TrimSpace(link.Href)
}
}
return ""
}
func (a atomLinks) firstLinkWithRelationAndType(relation string, contentTypes ...string) string {
func (a AtomLinks) firstLinkWithRelationAndType(relation string, contentTypes ...string) string {
for _, link := range a {
if strings.EqualFold(link.Rel, relation) {
for _, contentType := range contentTypes {
if strings.EqualFold(link.Type, contentType) {
return strings.TrimSpace(link.URL)
return strings.TrimSpace(link.Href)
}
}
}
@ -81,3 +95,46 @@ func (a atomLinks) firstLinkWithRelationAndType(relation string, contentTypes ..
return ""
}
// The "atom:category" element conveys information about a category
// associated with an entry or feed. This specification assigns no
// meaning to the content (if any) of this element.
//
// Specs: https://datatracker.ietf.org/doc/html/rfc4287#section-4.2.2
type AtomCategory struct {
// The "term" attribute is a string that identifies the category to
// which the entry or feed belongs. Category elements MUST have a
// "term" attribute.
Term string `xml:"term,attr"`
// The "scheme" attribute is an IRI that identifies a categorization
// scheme. Category elements MAY have a "scheme" attribute.
Scheme string `xml:"scheme,attr"`
// The "label" attribute provides a human-readable label for display in
// end-user applications. The content of the "label" attribute is
// Language-Sensitive. Entities such as "&amp;" and "&lt;" represent
// their corresponding characters ("&" and "<", respectively), not
// markup. Category elements MAY have a "label" attribute.
Label string `xml:"label,attr"`
}
type AtomCategories []AtomCategory
func (ac AtomCategories) CategoryNames() []string {
var categories []string
for _, category := range ac {
label := strings.TrimSpace(category.Label)
if label != "" {
categories = append(categories, label)
} else {
term := strings.TrimSpace(category.Term)
if term != "" {
categories = append(categories, term)
}
}
}
return categories
}

28
internal/reader/atom/parser.go
View File

@ -11,22 +11,20 @@ import (
xml_decoder "miniflux.app/v2/internal/reader/xml"
)
type atomFeed interface {
Transform(baseURL string) *model.Feed
}
// Parse returns a normalized feed struct from a Atom feed.
func Parse(baseURL string, r io.ReadSeeker, version string) (*model.Feed, error) {
var rawFeed atomFeed
if version == "0.3" {
rawFeed = new(atom03Feed)
} else {
rawFeed = new(atom10Feed)
switch version {
case "0.3":
atomFeed := new(Atom03Feed)
if err := xml_decoder.NewXMLDecoder(r).Decode(atomFeed); err != nil {
return nil, fmt.Errorf("atom: unable to parse Atom 0.3 feed: %w", err)
}
return NewAtom03Adapter(atomFeed).BuildFeed(baseURL), nil
default:
atomFeed := new(Atom10Feed)
if err := xml_decoder.NewXMLDecoder(r).Decode(atomFeed); err != nil {
return nil, fmt.Errorf("atom: unable to parse Atom 1.0 feed: %w", err)
}
return NewAtom10Adapter(atomFeed).BuildFeed(baseURL), nil
}
if err := xml_decoder.NewXMLDecoder(r).Decode(rawFeed); err != nil {
return nil, fmt.Errorf("atom: unable to parse feed: %w", err)
}
return rawFeed.Transform(baseURL), nil
}

4
internal/reader/json/adapter.go
View File

@ -98,7 +98,6 @@ func (j *JSONAdapter) BuildFeed(feedURL string) *model.Feed {
}
// Populate the entry date.
entry.Date = time.Now()
for _, value := range []string{item.DatePublished, item.DateModified} {
value = strings.TrimSpace(value)
if value != "" {
@ -114,6 +113,9 @@ func (j *JSONAdapter) BuildFeed(feedURL string) *model.Feed {
}
}
}
if entry.Date.IsZero() {
entry.Date = time.Now()
}
// Populate the entry author.
itemAuthors := append(item.Authors, j.jsonFeed.Authors...)

30
internal/reader/parser/parser_test.go
View File

@ -85,7 +85,35 @@ func FuzzParse(f *testing.F) {
})
}
func TestParseAtom(t *testing.T) {
func TestParseAtom03Feed(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed version="0.3" xmlns="http://purl.org/atom/ns#">
<title>dive into mark</title>
<link rel="alternate" type="text/html" href="http://diveintomark.org/"/>
<modified>2003-12-13T18:30:02Z</modified>
<author><name>Mark Pilgrim</name></author>
<entry>
<title>Atom 0.3 snapshot</title>
<link rel="alternate" type="text/html" href="http://diveintomark.org/2003/12/13/atom03"/>
<id>tag:diveintomark.org,2003:3.2397</id>
<issued>2003-12-13T08:29:29-04:00</issued>
<modified>2003-12-13T18:30:02Z</modified>
<summary type="text/plain">It&apos;s a test</summary>
<content type="text/html" mode="escaped"><![CDATA[<p>HTML content</p>]]></content>
</entry>
</feed>`
feed, err := ParseFeed("https://example.org/", strings.NewReader(data))
if err != nil {
t.Error(err)
}
if feed.Title != "dive into mark" {
t.Errorf("Incorrect title, got: %s", feed.Title)
}
}
func TestParseAtom10Feed(t *testing.T) {
data := `<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">

3
internal/reader/rss/adapter.go
View File

@ -69,7 +69,6 @@ func (r *RSSAdapter) BuildFeed(feedURL string) *model.Feed {
for _, item := range r.rss.Channel.Items {
entry := model.NewEntry()
entry.Author = findEntryAuthor(&item)
entry.Date = findEntryDate(&item)
entry.Content = findEntryContent(&item)
entry.Enclosures = findEntryEnclosures(&item)
@ -91,11 +90,11 @@ func (r *RSSAdapter) BuildFeed(feedURL string) *model.Feed {
if entry.Title == "" {
entry.Title = sanitizer.TruncateHTML(entry.Content, 100)
}
if entry.Title == "" {
entry.Title = entry.URL
}
entry.Author = findEntryAuthor(&item)
if entry.Author == "" {
entry.Author = findFeedAuthor(&r.rss.Channel)
}