1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
|
// Copyright 2019 Frédéric Guillot. All rights reserved.
// Use of this source code is governed by the Apache 2.0
// license that can be found in the LICENSE file.
package atom // import "miniflux.app/reader/atom"
import (
"encoding/base64"
"html"
"strings"
"time"
"miniflux.app/crypto"
"miniflux.app/logger"
"miniflux.app/model"
"miniflux.app/reader/date"
"miniflux.app/reader/sanitizer"
"miniflux.app/url"
)
// 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"`
}
func (a *atom03Feed) Transform() *model.Feed {
feed := new(model.Feed)
feed.FeedURL = a.Links.firstLinkWithRelation("self")
feed.SiteURL = a.Links.originalLink()
feed.Title = a.Title.String()
if feed.Title == "" {
feed.Title = feed.SiteURL
}
for _, entry := range a.Entries {
item := entry.Transform()
entryURL, err := url.AbsoluteURL(feed.SiteURL, item.URL)
if err == nil {
item.URL = entryURL
}
if item.Author == "" {
item.Author = a.Author.String()
}
if item.Title == "" {
item.Title = item.URL
}
feed.Entries = append(feed.Entries, item)
}
return feed
}
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"`
}
func (a *atom03Entry) Transform() *model.Entry {
entry := new(model.Entry)
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
}
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 {
logger.Error("atom: %v", 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"`
Data string `xml:",chardata"`
XML string `xml:",innerxml"`
}
func (a *atom03Text) String() string {
content := ""
switch {
case a.Mode == "xml":
content = a.XML
case a.Mode == "escaped":
content = a.Data
case a.Mode == "base64":
b, err := base64.StdEncoding.DecodeString(a.Data)
if err == nil {
content = string(b)
}
default:
content = a.Data
}
if a.Type != "text/html" {
content = html.EscapeString(content)
}
return strings.TrimSpace(content)
}
|
