aboutsummaryrefslogtreecommitdiff
path: root/src/feednim/atom.nim
blob: 5c8b4a66963a9baa171dbab09f581b58d80860e4 (plain)
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
# Nim Atom Syndication Format module

# Written by John Conway
# Released under the MIT open source license.

import httpclient
import strutils
import sequtils
import xmlparser
import xmltree
import streams
import sugar


type
    Atom* = object
        author*: AtomAuthor             # Sugar, not in Atom spec. Returns the first author.
        id*: string                     # Required Atom field
        title*: string                  # Required Atom field
        updated*: string                # Required Atom field
        authors*: seq[AtomAuthor]       # Pleuralised because the Atom spec allows more than one
        categories*: seq[AtomCategory]
        contributors*: seq[AtomAuthor]
        generator*: string
        icon*: string
        link*: AtomLink
        logo*: string
        rights*: string
        subtitle*: string
        entries*: seq[AtomEntry]

    AtomAuthor* = object
        name*: string                    # Required Atom field
        uri*: string
        email*: string

    AtomCategory* = object
        term*: string
        label*: string
        scheme*: string

    AtomLink* = object
        href*: string
        rel*: string
        linktype*: string
        hreflang*: string
        title*: string
        length*: string

    AtomEntry* = object
        id*: string                     # Required Atom field
        title*: string                  # Required Atom field
        updated*: string                # Required Atom field
        author*: AtomAuthor             # Sugar, not in Atom spec. Returns the first author.
        authors*: seq[AtomAuthor]       # Pleuralised because the Atom spec allows more than one
        categories*: seq[AtomCategory]
        content*: string
        contentSrc*: string
        contentType*: string
        contributors*: seq[AtomAuthor]
        link*: AtomLink
        published*: string
        rights*: string
        source*: AtomSource
        summary*: string

    AtomSource* = object
        author*: AtomAuthor          # Sugar, not in Atom spec. Returns the first author.
        authors*: seq[AtomAuthor]
        categories*: seq[AtomCategory]
        contributors*: seq[AtomAuthor]
        generator*: string
        icon*: string
        id*: string
        link*: AtomLink
        logo*: string
        rights*: string
        subtitle*: string
        title*: string
        updated*: string

proc parseAuthors ( node: XmlNode, mode="author") : seq[AtomAuthor] =
    var authors:seq[AtomAuthor]
    if node.child(mode) != nil:
        for athr_node in node.findAll(mode):
            var author: AtomAuthor = AtomAuthor()
            author.name = athr_node.child("name").innerText
            if athr_node.child("uri") != nil: author.uri = athr_node.child("uri").innerText
            if athr_node.child("email") != nil: author.email = athr_node.child("email").innerText
            authors.add(author)
    if authors.len == 0: return @[]
    return authors

proc parseCategories ( node: XmlNode ) : seq[AtomCategory] =
    var categories:seq[AtomCategory]
    if node.child("category") != nil:
        for cat_node in node.findAll("category"):
            var category: AtomCategory = AtomCategory()
            if cat_node.attr("term") != "": category.term = cat_node.attr("term")
            if cat_node.attr("label") != "": category.label = cat_node.attr("label")
            if cat_node.attr("scheme") != "": category.scheme = cat_node.attr("scheme")

            categories.add(category)

    if categories.len == 0: return @[]
    return categories

proc parseLink ( node: XmlNode ): AtomLink =
    var link: AtomLink = AtomLink()
    if node.attrs != nil:
        if node.attr("href") != "": link.href = node.attr("href")
        if node.attr("rel") != "": link.rel = node.attr("rel")
        if node.attr("type") != "": link.linktype = node.attr("type")
        if node.attr("hreflang") != "": link.hreflang = node.attr("hreflang")
        if node.attr("title") != "": link.title = node.attr("title")
        if node.attr("length") != "": link.length = node.attr("length")
    return link

proc parseEntry( node: XmlNode) : AtomEntry =
    var entry: AtomEntry = AtomEntry()

    # Fill the required fields
    entry.id = node.child("id").innerText
    entry.title = node.child("title").innerText
    entry.updated = node.child("updated").innerText

    # Fill the optinal fields
    entry.authors = node.parseAuthors()

    if node.child("category") != nil: entry.categories = node.parseCategories()

    if node.child("content") != nil:
        let content_node = node.child("content")
        entry.content = content_node.innerText

        if content_node.attrs != nil:
            if content_node.attr("type") == "xhtml" or content_node.attr("type") == "html":
                var content = ""
                entry.contentType = node.attr("type")
                for item in content_node.items:
                    content = content & $item
                entry.content = content
            else:
                entry.content = content_node.innerText

            entry.contentSrc = content_node.attr("src")

    if node.child("contributor") != nil:
        entry.contributors = node.parseAuthors(mode="contributor")

    if node.child("link") != nil: entry.link = node.child("link").parseLink()

    if node.child("published") != nil: entry.published = node.child("published").innerText

    if node.child("rights") != nil: entry.rights = node.child("rights").innerText

    if node.child("source") != nil:
        let source = node.child("source")
        if source.child("author") != nil: entry.source.authors = source.parseAuthors()
        if source.child("category") != nil: entry.source.categories = source.parseCategories()
        if source.child("contributor") != nil: entry.source.contributors = source.parseAuthors(mode="contributor")
        if source.child("generator") != nil: entry.source.generator = source.child("generator").innerText
        if source.child("icon") != nil: entry.source.icon = source.child("icon").innerText
        if source.child("id") != nil: entry.source.id = source.child("id").innerText
        if source.child("link") != nil: entry.source.link = source.child("link").parseLink()
        if source.child("logo") != nil: entry.source.logo = source.child("logo").innerText
        if source.child("rights") != nil: entry.source.rights = source.child("rights").innerText
        if source.child("subtitle") != nil: entry.source.subtitle = source.child("subtitle").innerText
        if source.child("title") != nil: entry.source.title = source.child("title").innerText
        if source.child("updated") != nil: entry.source.updated = source.child("updated").innerText

        entry.source.author = entry.source.authors[0]

    if node.child("summary") != nil: entry.summary = node.child("summary").innerText

    # SUGAR an easy way to access an author
    if entry.authors.len() > 0:
        entry.author = entry.authors[0]
    else:
        entry.author = AtomAuthor()

    return entry

proc parseAtom*(data: string): Atom =
    ## Parses the Atom from the given string.

    # Parse into XML.
    let node: XmlNode = parseXML(newStringStream(data))

    # Create the return object.
    var atom: Atom = Atom()

    # Fill in the required fields
    atom.id = node.child("id").innerText
    atom.title = node.child("title").innerText
    atom.updated = node.child("updated").innerText

    # Fill in the optional fields
    if node.child("author") != nil: atom.authors = node.parseAuthors()

    if node.child("category") != nil: atom.categories = node.parseCategories()

    if node.child("contributor") != nil: atom.contributors = node.parseAuthors(mode="contributor")

    if node.child("generator") != nil: atom.generator = node.child("generator").innerText

    if node.child("icon") != nil: atom.icon = node.child("icon").innerText

    if node.child("link") != nil: atom.link = node.child("link").parseLink()

    if node.child("logo") != nil: atom.logo = node.child("logo").innerText

    if node.child("rights") != nil: atom.rights = node.child("rights").innerText

    if node.child("subtitle") != nil: atom.subtitle = node.child("subtitle").innerText

    if atom.authors.len() > 0:
        atom.author = atom.authors[0]
    else:
        atom.author = AtomAuthor()

    # If there are no entries:
    if node.child("entry") == nil:
        atom.entries = @[]
        return atom

    # Otherwise, add the entries.
    if node.child("entry") != nil:
        atom.entries = map( node.findAll("entry"), parseEntry )

    # Return the Atom data.
    return atom