feedsmith 3.0.0-rc.2 → 3.0.0-rc.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/common/config.cjs +1 -0
- package/dist/common/config.js +29 -28
- package/dist/common/utils.cjs +113 -125
- package/dist/common/utils.js +111 -124
- package/dist/feeds/atom/generate/config.cjs +6 -2
- package/dist/feeds/atom/generate/config.js +5 -1
- package/dist/feeds/atom/generate/utils.cjs +45 -8
- package/dist/feeds/atom/generate/utils.js +47 -11
- package/dist/feeds/atom/parse/config.cjs +4 -70
- package/dist/feeds/atom/parse/config.js +5 -68
- package/dist/feeds/atom/parse/index.cjs +20 -3
- package/dist/feeds/atom/parse/index.js +20 -3
- package/dist/feeds/atom/parse/utils.cjs +99 -6
- package/dist/feeds/atom/parse/utils.js +96 -8
- package/dist/feeds/json/parse/utils.cjs +29 -29
- package/dist/feeds/json/parse/utils.js +30 -30
- package/dist/feeds/rdf/parse/config.cjs +14 -24
- package/dist/feeds/rdf/parse/config.js +15 -22
- package/dist/feeds/rdf/parse/index.cjs +20 -3
- package/dist/feeds/rdf/parse/index.js +20 -3
- package/dist/feeds/rss/generate/config.cjs +6 -2
- package/dist/feeds/rss/generate/config.js +5 -1
- package/dist/feeds/rss/parse/config.cjs +0 -9
- package/dist/feeds/rss/parse/config.js +2 -9
- package/dist/feeds/rss/parse/index.cjs +19 -3
- package/dist/feeds/rss/parse/index.js +19 -3
- package/dist/namespaces/atom/common/config.cjs +68 -0
- package/dist/namespaces/atom/common/config.js +65 -1
- package/dist/namespaces/rawvoice/parse/utils.cjs +1 -1
- package/dist/namespaces/rawvoice/parse/utils.js +2 -2
- package/dist/node_modules/trousse/dist/json.cjs +16 -0
- package/dist/node_modules/trousse/dist/json.js +16 -0
- package/dist/node_modules/trousse/dist/locales.cjs +15 -0
- package/dist/node_modules/trousse/dist/locales.js +15 -0
- package/dist/node_modules/trousse/dist/urls.cjs +9 -0
- package/dist/node_modules/trousse/dist/urls.js +9 -0
- package/package.json +1 -1
|
@@ -1,18 +1,35 @@
|
|
|
1
1
|
const require_errors = require("../../../common/errors.cjs");
|
|
2
2
|
const require_config = require("../../../common/config.cjs");
|
|
3
3
|
const require_index = require("../detect/index.cjs");
|
|
4
|
+
const require_utils = require("../../../common/utils.cjs");
|
|
4
5
|
const require_config$1 = require("./config.cjs");
|
|
5
|
-
const require_utils = require("./utils.cjs");
|
|
6
|
+
const require_utils$1 = require("./utils.cjs");
|
|
7
|
+
let fast_xml_parser = require("fast-xml-parser");
|
|
6
8
|
//#region src/feeds/atom/parse/index.ts
|
|
9
|
+
const createNamespaceOptions = require_utils.createNamespaceResolver({
|
|
10
|
+
namespaceUris: require_config.namespaceUris,
|
|
11
|
+
namespacePrefixes: require_config.namespacePrefixes,
|
|
12
|
+
primaryNamespaces: ["atom"]
|
|
13
|
+
});
|
|
14
|
+
let namespaceOptions = createNamespaceOptions();
|
|
15
|
+
const parser = new fast_xml_parser.XMLParser({
|
|
16
|
+
...require_config.parserConfig,
|
|
17
|
+
stopNodes: require_config$1.stopNodes,
|
|
18
|
+
transformTagName: (name) => namespaceOptions.transformTagName(name),
|
|
19
|
+
transformAttributeName: (name) => namespaceOptions.transformAttributeName(name),
|
|
20
|
+
attributeValueProcessor: (name, value) => namespaceOptions.attributeValueProcessor(name, value),
|
|
21
|
+
updateTag: (name) => namespaceOptions.updateTag(name)
|
|
22
|
+
});
|
|
7
23
|
const parse = (value, options) => {
|
|
8
24
|
if (!require_index.detect(value)) throw new require_errors.DetectError(require_config.locales.invalidFeedFormat);
|
|
9
25
|
let normalized;
|
|
10
26
|
try {
|
|
11
|
-
|
|
27
|
+
namespaceOptions = createNamespaceOptions(value);
|
|
28
|
+
normalized = parser.parse(value);
|
|
12
29
|
} catch (error) {
|
|
13
30
|
throw new require_errors.MalformedError(require_config.locales.invalidFeedFormat, { cause: error });
|
|
14
31
|
}
|
|
15
|
-
const parsed = require_utils.retrieveFeed(normalized, options);
|
|
32
|
+
const parsed = require_utils$1.retrieveFeed(normalized, options);
|
|
16
33
|
if (!parsed) throw new require_errors.ParseError(require_config.locales.invalidFeedFormat);
|
|
17
34
|
return parsed;
|
|
18
35
|
};
|
|
@@ -1,14 +1,31 @@
|
|
|
1
1
|
import { DetectError, MalformedError, ParseError } from "../../../common/errors.js";
|
|
2
|
-
import { locales } from "../../../common/config.js";
|
|
2
|
+
import { locales, namespacePrefixes, namespaceUris, parserConfig } from "../../../common/config.js";
|
|
3
3
|
import { detect } from "../detect/index.js";
|
|
4
|
-
import {
|
|
4
|
+
import { createNamespaceResolver } from "../../../common/utils.js";
|
|
5
|
+
import { stopNodes } from "./config.js";
|
|
5
6
|
import { retrieveFeed } from "./utils.js";
|
|
7
|
+
import { XMLParser } from "fast-xml-parser";
|
|
6
8
|
//#region src/feeds/atom/parse/index.ts
|
|
9
|
+
const createNamespaceOptions = createNamespaceResolver({
|
|
10
|
+
namespaceUris,
|
|
11
|
+
namespacePrefixes,
|
|
12
|
+
primaryNamespaces: ["atom"]
|
|
13
|
+
});
|
|
14
|
+
let namespaceOptions = createNamespaceOptions();
|
|
15
|
+
const parser = new XMLParser({
|
|
16
|
+
...parserConfig,
|
|
17
|
+
stopNodes,
|
|
18
|
+
transformTagName: (name) => namespaceOptions.transformTagName(name),
|
|
19
|
+
transformAttributeName: (name) => namespaceOptions.transformAttributeName(name),
|
|
20
|
+
attributeValueProcessor: (name, value) => namespaceOptions.attributeValueProcessor(name, value),
|
|
21
|
+
updateTag: (name) => namespaceOptions.updateTag(name)
|
|
22
|
+
});
|
|
7
23
|
const parse = (value, options) => {
|
|
8
24
|
if (!detect(value)) throw new DetectError(locales.invalidFeedFormat);
|
|
9
25
|
let normalized;
|
|
10
26
|
try {
|
|
11
|
-
|
|
27
|
+
namespaceOptions = createNamespaceOptions(value);
|
|
28
|
+
normalized = parser.parse(value);
|
|
12
29
|
} catch (error) {
|
|
13
30
|
throw new MalformedError(locales.invalidFeedFormat, { cause: error });
|
|
14
31
|
}
|
|
@@ -1,4 +1,5 @@
|
|
|
1
1
|
const require_is = require("../../../node_modules/trousse/dist/is.cjs");
|
|
2
|
+
const require_urls = require("../../../node_modules/trousse/dist/urls.cjs");
|
|
2
3
|
const require_utils = require("../../../common/utils.cjs");
|
|
3
4
|
const require_utils$1 = require("../../../namespaces/admin/parse/utils.cjs");
|
|
4
5
|
const require_utils$2 = require("../../../namespaces/app/parse/utils.cjs");
|
|
@@ -22,23 +23,109 @@ const require_utils$19 = require("../../../namespaces/trackback/parse/utils.cjs"
|
|
|
22
23
|
const require_utils$20 = require("../../../namespaces/wfw/parse/utils.cjs");
|
|
23
24
|
const require_utils$21 = require("../../../namespaces/xml/parse/utils.cjs");
|
|
24
25
|
const require_utils$22 = require("../../../namespaces/yt/parse/utils.cjs");
|
|
26
|
+
let fast_xml_parser = require("fast-xml-parser");
|
|
25
27
|
//#region src/feeds/atom/parse/utils.ts
|
|
26
28
|
const createNamespaceGetter = (value, prefix) => {
|
|
27
29
|
if (!prefix) return (key) => value[key];
|
|
28
30
|
return (key) => value[prefix + key];
|
|
29
31
|
};
|
|
32
|
+
const xhtmlDivStartRegex = /^\s*<(?:([a-zA-Z][\w.-]*):)?div[\s/>]/;
|
|
33
|
+
const xhtmlDivParser = new fast_xml_parser.XMLParser({
|
|
34
|
+
preserveOrder: true,
|
|
35
|
+
stopNodes: ["x-wrap.div"],
|
|
36
|
+
processEntities: false,
|
|
37
|
+
ignoreAttributes: false,
|
|
38
|
+
attributeNamePrefix: "@",
|
|
39
|
+
removeNSPrefix: true,
|
|
40
|
+
trimValues: false,
|
|
41
|
+
commentPropName: "#comment"
|
|
42
|
+
});
|
|
43
|
+
const unwrapXhtmlDiv = (value) => {
|
|
44
|
+
if (!require_is.isNonEmptyString(value)) return value;
|
|
45
|
+
const match = value.match(xhtmlDivStartRegex);
|
|
46
|
+
if (!match) return value;
|
|
47
|
+
let children;
|
|
48
|
+
try {
|
|
49
|
+
const parsed = xhtmlDivParser.parse(`<x-wrap>${value}</x-wrap>`);
|
|
50
|
+
if (parsed.length !== 1 || !Array.isArray(parsed[0]["x-wrap"])) return value;
|
|
51
|
+
children = parsed[0]["x-wrap"];
|
|
52
|
+
} catch {
|
|
53
|
+
return value;
|
|
54
|
+
}
|
|
55
|
+
const divTexts = [];
|
|
56
|
+
for (const child of children) {
|
|
57
|
+
if (Array.isArray(child.div)) {
|
|
58
|
+
divTexts.push(child.div[0]?.["#text"] ?? "");
|
|
59
|
+
continue;
|
|
60
|
+
}
|
|
61
|
+
if (typeof child["#text"] === "string" && child["#text"].trim() === "") continue;
|
|
62
|
+
return value;
|
|
63
|
+
}
|
|
64
|
+
if (divTexts.length !== 1) return value;
|
|
65
|
+
const inner = divTexts[0];
|
|
66
|
+
if (inner === "") return;
|
|
67
|
+
const prefix = match[1];
|
|
68
|
+
if (prefix) {
|
|
69
|
+
const escapedPrefix = prefix.replace(/\./g, "\\.");
|
|
70
|
+
return inner.replace(new RegExp(`(</?)${escapedPrefix}:`, "g"), "$1");
|
|
71
|
+
}
|
|
72
|
+
return inner;
|
|
73
|
+
};
|
|
74
|
+
const isXhtmlType = (type) => {
|
|
75
|
+
return type === "xhtml" || type === "application/xhtml+xml";
|
|
76
|
+
};
|
|
77
|
+
const retrieveXhtmlDivXml = (value, type) => {
|
|
78
|
+
if (!isXhtmlType(type)) return;
|
|
79
|
+
const escaped = escapeCdataSections(require_utils.retrieveText(value));
|
|
80
|
+
if (!require_is.isNonEmptyString(escaped) || unwrapXhtmlDiv(escaped) === escaped) return;
|
|
81
|
+
const children = xhtmlDivParser.parse(`<x-wrap>${escaped}</x-wrap>`)[0]["x-wrap"];
|
|
82
|
+
for (const child of children) if (Array.isArray(child.div)) {
|
|
83
|
+
const attributes = child[":@"];
|
|
84
|
+
return require_utils.trimObject({
|
|
85
|
+
base: require_utils.parseString(attributes?.["@base"]),
|
|
86
|
+
lang: require_utils.parseString(attributes?.["@lang"])
|
|
87
|
+
});
|
|
88
|
+
}
|
|
89
|
+
};
|
|
90
|
+
const mergeXhtmlDivXml = (elementXml, divXml) => {
|
|
91
|
+
if (!divXml) return elementXml;
|
|
92
|
+
let base = divXml.base ?? elementXml?.base;
|
|
93
|
+
if (divXml.base && elementXml?.base) base = require_urls.parseUrl(divXml.base, elementXml.base)?.href ?? base;
|
|
94
|
+
return require_utils.trimObject({
|
|
95
|
+
...elementXml,
|
|
96
|
+
lang: divXml.lang ?? elementXml?.lang,
|
|
97
|
+
base
|
|
98
|
+
});
|
|
99
|
+
};
|
|
100
|
+
const cdataSectionRegex = /<!\[CDATA\[([\s\S]*?)\]\]>/g;
|
|
101
|
+
const escapeCdataSections = (value) => {
|
|
102
|
+
if (!require_is.isNonEmptyString(value)) return value;
|
|
103
|
+
return value.replace(cdataSectionRegex, (_, content) => {
|
|
104
|
+
return content.replace(/&/g, "&").replace(/</g, "<");
|
|
105
|
+
});
|
|
106
|
+
};
|
|
107
|
+
const parseTypedText = (value, type) => {
|
|
108
|
+
const text = require_utils.retrieveText(value);
|
|
109
|
+
if (!isXhtmlType(type)) return require_utils.parseString(text);
|
|
110
|
+
const escaped = escapeCdataSections(text);
|
|
111
|
+
const unwrapped = unwrapXhtmlDiv(escaped);
|
|
112
|
+
if (unwrapped !== escaped) return require_utils.parseVerbatimString(unwrapped);
|
|
113
|
+
if (require_is.isNonEmptyString(escaped) && xhtmlDivStartRegex.test(escaped)) return require_utils.parseVerbatimString(escaped);
|
|
114
|
+
return require_utils.parseString(text);
|
|
115
|
+
};
|
|
30
116
|
const parseText = (value) => {
|
|
31
117
|
if (require_is.isNonEmptyString(value)) {
|
|
32
118
|
const parsed = require_utils.parseString(value);
|
|
33
119
|
return parsed ? { value: parsed } : void 0;
|
|
34
120
|
}
|
|
35
121
|
if (!require_is.isPlainObject(value)) return;
|
|
36
|
-
const
|
|
122
|
+
const type = require_utils.parseString(value["@type"]);
|
|
123
|
+
const parsedValue = parseTypedText(value, type);
|
|
37
124
|
if (!parsedValue) return;
|
|
38
125
|
return require_utils.trimObject({
|
|
39
126
|
value: parsedValue,
|
|
40
|
-
type
|
|
41
|
-
xml: require_utils$21.retrieveItemOrFeed(value)
|
|
127
|
+
type,
|
|
128
|
+
xml: mergeXhtmlDivXml(require_utils$21.retrieveItemOrFeed(value), retrieveXhtmlDivXml(value, type))
|
|
42
129
|
});
|
|
43
130
|
};
|
|
44
131
|
const parseContent = (value) => {
|
|
@@ -47,11 +134,12 @@ const parseContent = (value) => {
|
|
|
47
134
|
return parsed ? { value: parsed } : void 0;
|
|
48
135
|
}
|
|
49
136
|
if (!require_is.isPlainObject(value)) return;
|
|
137
|
+
const type = require_utils.parseString(value["@type"]);
|
|
50
138
|
return require_utils.trimObject({
|
|
51
|
-
value:
|
|
52
|
-
type
|
|
139
|
+
value: parseTypedText(value, type),
|
|
140
|
+
type,
|
|
53
141
|
src: require_utils.parseString(value["@src"]),
|
|
54
|
-
xml: require_utils$21.retrieveItemOrFeed(value)
|
|
142
|
+
xml: mergeXhtmlDivXml(require_utils$21.retrieveItemOrFeed(value), retrieveXhtmlDivXml(value, type))
|
|
55
143
|
});
|
|
56
144
|
};
|
|
57
145
|
const parseLink = (value, options) => {
|
|
@@ -229,6 +317,8 @@ const retrieveFeed = (value, options) => {
|
|
|
229
317
|
};
|
|
230
318
|
//#endregion
|
|
231
319
|
exports.createNamespaceGetter = createNamespaceGetter;
|
|
320
|
+
exports.escapeCdataSections = escapeCdataSections;
|
|
321
|
+
exports.mergeXhtmlDivXml = mergeXhtmlDivXml;
|
|
232
322
|
exports.parseCategory = parseCategory;
|
|
233
323
|
exports.parseContent = parseContent;
|
|
234
324
|
exports.parseEntry = parseEntry;
|
|
@@ -238,9 +328,12 @@ exports.parseLink = parseLink;
|
|
|
238
328
|
exports.parsePerson = parsePerson;
|
|
239
329
|
exports.parseSource = parseSource;
|
|
240
330
|
exports.parseText = parseText;
|
|
331
|
+
exports.parseTypedText = parseTypedText;
|
|
241
332
|
exports.retrieveFeed = retrieveFeed;
|
|
242
333
|
exports.retrieveGeneratorUri = retrieveGeneratorUri;
|
|
243
334
|
exports.retrievePersonUri = retrievePersonUri;
|
|
244
335
|
exports.retrievePublished = retrievePublished;
|
|
245
336
|
exports.retrieveSubtitle = retrieveSubtitle;
|
|
246
337
|
exports.retrieveUpdated = retrieveUpdated;
|
|
338
|
+
exports.retrieveXhtmlDivXml = retrieveXhtmlDivXml;
|
|
339
|
+
exports.unwrapXhtmlDiv = unwrapXhtmlDiv;
|
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
import { isNonEmptyString, isPlainObject } from "../../../node_modules/trousse/dist/is.js";
|
|
2
|
-
import {
|
|
2
|
+
import { parseUrl } from "../../../node_modules/trousse/dist/urls.js";
|
|
3
|
+
import { detectNamespaces, parseArrayOf, parseDate, parseNumber, parseSingularOf, parseString, parseVerbatimString, retrieveText, trimObject } from "../../../common/utils.js";
|
|
3
4
|
import { retrieveFeed as retrieveFeed$1 } from "../../../namespaces/admin/parse/utils.js";
|
|
4
5
|
import { retrieveEntry } from "../../../namespaces/app/parse/utils.js";
|
|
5
6
|
import { retrieveAuthor, retrieveEntry as retrieveEntry$1 } from "../../../namespaces/arxiv/parse/utils.js";
|
|
@@ -22,23 +23,109 @@ import { retrieveItem as retrieveItem$6 } from "../../../namespaces/trackback/pa
|
|
|
22
23
|
import { retrieveItem as retrieveItem$7 } from "../../../namespaces/wfw/parse/utils.js";
|
|
23
24
|
import { retrieveItemOrFeed as retrieveItemOrFeed$7 } from "../../../namespaces/xml/parse/utils.js";
|
|
24
25
|
import { retrieveFeed as retrieveFeed$7, retrieveItem as retrieveItem$8 } from "../../../namespaces/yt/parse/utils.js";
|
|
26
|
+
import { XMLParser } from "fast-xml-parser";
|
|
25
27
|
//#region src/feeds/atom/parse/utils.ts
|
|
26
28
|
const createNamespaceGetter = (value, prefix) => {
|
|
27
29
|
if (!prefix) return (key) => value[key];
|
|
28
30
|
return (key) => value[prefix + key];
|
|
29
31
|
};
|
|
32
|
+
const xhtmlDivStartRegex = /^\s*<(?:([a-zA-Z][\w.-]*):)?div[\s/>]/;
|
|
33
|
+
const xhtmlDivParser = new XMLParser({
|
|
34
|
+
preserveOrder: true,
|
|
35
|
+
stopNodes: ["x-wrap.div"],
|
|
36
|
+
processEntities: false,
|
|
37
|
+
ignoreAttributes: false,
|
|
38
|
+
attributeNamePrefix: "@",
|
|
39
|
+
removeNSPrefix: true,
|
|
40
|
+
trimValues: false,
|
|
41
|
+
commentPropName: "#comment"
|
|
42
|
+
});
|
|
43
|
+
const unwrapXhtmlDiv = (value) => {
|
|
44
|
+
if (!isNonEmptyString(value)) return value;
|
|
45
|
+
const match = value.match(xhtmlDivStartRegex);
|
|
46
|
+
if (!match) return value;
|
|
47
|
+
let children;
|
|
48
|
+
try {
|
|
49
|
+
const parsed = xhtmlDivParser.parse(`<x-wrap>${value}</x-wrap>`);
|
|
50
|
+
if (parsed.length !== 1 || !Array.isArray(parsed[0]["x-wrap"])) return value;
|
|
51
|
+
children = parsed[0]["x-wrap"];
|
|
52
|
+
} catch {
|
|
53
|
+
return value;
|
|
54
|
+
}
|
|
55
|
+
const divTexts = [];
|
|
56
|
+
for (const child of children) {
|
|
57
|
+
if (Array.isArray(child.div)) {
|
|
58
|
+
divTexts.push(child.div[0]?.["#text"] ?? "");
|
|
59
|
+
continue;
|
|
60
|
+
}
|
|
61
|
+
if (typeof child["#text"] === "string" && child["#text"].trim() === "") continue;
|
|
62
|
+
return value;
|
|
63
|
+
}
|
|
64
|
+
if (divTexts.length !== 1) return value;
|
|
65
|
+
const inner = divTexts[0];
|
|
66
|
+
if (inner === "") return;
|
|
67
|
+
const prefix = match[1];
|
|
68
|
+
if (prefix) {
|
|
69
|
+
const escapedPrefix = prefix.replace(/\./g, "\\.");
|
|
70
|
+
return inner.replace(new RegExp(`(</?)${escapedPrefix}:`, "g"), "$1");
|
|
71
|
+
}
|
|
72
|
+
return inner;
|
|
73
|
+
};
|
|
74
|
+
const isXhtmlType = (type) => {
|
|
75
|
+
return type === "xhtml" || type === "application/xhtml+xml";
|
|
76
|
+
};
|
|
77
|
+
const retrieveXhtmlDivXml = (value, type) => {
|
|
78
|
+
if (!isXhtmlType(type)) return;
|
|
79
|
+
const escaped = escapeCdataSections(retrieveText(value));
|
|
80
|
+
if (!isNonEmptyString(escaped) || unwrapXhtmlDiv(escaped) === escaped) return;
|
|
81
|
+
const children = xhtmlDivParser.parse(`<x-wrap>${escaped}</x-wrap>`)[0]["x-wrap"];
|
|
82
|
+
for (const child of children) if (Array.isArray(child.div)) {
|
|
83
|
+
const attributes = child[":@"];
|
|
84
|
+
return trimObject({
|
|
85
|
+
base: parseString(attributes?.["@base"]),
|
|
86
|
+
lang: parseString(attributes?.["@lang"])
|
|
87
|
+
});
|
|
88
|
+
}
|
|
89
|
+
};
|
|
90
|
+
const mergeXhtmlDivXml = (elementXml, divXml) => {
|
|
91
|
+
if (!divXml) return elementXml;
|
|
92
|
+
let base = divXml.base ?? elementXml?.base;
|
|
93
|
+
if (divXml.base && elementXml?.base) base = parseUrl(divXml.base, elementXml.base)?.href ?? base;
|
|
94
|
+
return trimObject({
|
|
95
|
+
...elementXml,
|
|
96
|
+
lang: divXml.lang ?? elementXml?.lang,
|
|
97
|
+
base
|
|
98
|
+
});
|
|
99
|
+
};
|
|
100
|
+
const cdataSectionRegex = /<!\[CDATA\[([\s\S]*?)\]\]>/g;
|
|
101
|
+
const escapeCdataSections = (value) => {
|
|
102
|
+
if (!isNonEmptyString(value)) return value;
|
|
103
|
+
return value.replace(cdataSectionRegex, (_, content) => {
|
|
104
|
+
return content.replace(/&/g, "&").replace(/</g, "<");
|
|
105
|
+
});
|
|
106
|
+
};
|
|
107
|
+
const parseTypedText = (value, type) => {
|
|
108
|
+
const text = retrieveText(value);
|
|
109
|
+
if (!isXhtmlType(type)) return parseString(text);
|
|
110
|
+
const escaped = escapeCdataSections(text);
|
|
111
|
+
const unwrapped = unwrapXhtmlDiv(escaped);
|
|
112
|
+
if (unwrapped !== escaped) return parseVerbatimString(unwrapped);
|
|
113
|
+
if (isNonEmptyString(escaped) && xhtmlDivStartRegex.test(escaped)) return parseVerbatimString(escaped);
|
|
114
|
+
return parseString(text);
|
|
115
|
+
};
|
|
30
116
|
const parseText = (value) => {
|
|
31
117
|
if (isNonEmptyString(value)) {
|
|
32
118
|
const parsed = parseString(value);
|
|
33
119
|
return parsed ? { value: parsed } : void 0;
|
|
34
120
|
}
|
|
35
121
|
if (!isPlainObject(value)) return;
|
|
36
|
-
const
|
|
122
|
+
const type = parseString(value["@type"]);
|
|
123
|
+
const parsedValue = parseTypedText(value, type);
|
|
37
124
|
if (!parsedValue) return;
|
|
38
125
|
return trimObject({
|
|
39
126
|
value: parsedValue,
|
|
40
|
-
type
|
|
41
|
-
xml: retrieveItemOrFeed$7(value)
|
|
127
|
+
type,
|
|
128
|
+
xml: mergeXhtmlDivXml(retrieveItemOrFeed$7(value), retrieveXhtmlDivXml(value, type))
|
|
42
129
|
});
|
|
43
130
|
};
|
|
44
131
|
const parseContent = (value) => {
|
|
@@ -47,11 +134,12 @@ const parseContent = (value) => {
|
|
|
47
134
|
return parsed ? { value: parsed } : void 0;
|
|
48
135
|
}
|
|
49
136
|
if (!isPlainObject(value)) return;
|
|
137
|
+
const type = parseString(value["@type"]);
|
|
50
138
|
return trimObject({
|
|
51
|
-
value:
|
|
52
|
-
type
|
|
139
|
+
value: parseTypedText(value, type),
|
|
140
|
+
type,
|
|
53
141
|
src: parseString(value["@src"]),
|
|
54
|
-
xml: retrieveItemOrFeed$7(value)
|
|
142
|
+
xml: mergeXhtmlDivXml(retrieveItemOrFeed$7(value), retrieveXhtmlDivXml(value, type))
|
|
55
143
|
});
|
|
56
144
|
};
|
|
57
145
|
const parseLink = (value, options) => {
|
|
@@ -228,4 +316,4 @@ const retrieveFeed = (value, options) => {
|
|
|
228
316
|
return notNamespaced || namespaced;
|
|
229
317
|
};
|
|
230
318
|
//#endregion
|
|
231
|
-
export { createNamespaceGetter, parseCategory, parseContent, parseEntry, parseFeed, parseGenerator, parseLink, parsePerson, parseSource, parseText, retrieveFeed, retrieveGeneratorUri, retrievePersonUri, retrievePublished, retrieveSubtitle, retrieveUpdated };
|
|
319
|
+
export { createNamespaceGetter, escapeCdataSections, mergeXhtmlDivXml, parseCategory, parseContent, parseEntry, parseFeed, parseGenerator, parseLink, parsePerson, parseSource, parseText, parseTypedText, retrieveFeed, retrieveGeneratorUri, retrievePersonUri, retrievePublished, retrieveSubtitle, retrieveUpdated, retrieveXhtmlDivXml, unwrapXhtmlDiv };
|
|
@@ -12,12 +12,12 @@ const parseAuthor = (value) => {
|
|
|
12
12
|
if (require_is.isPlainObject(value)) {
|
|
13
13
|
const get = createCaseInsensitiveGetter(value);
|
|
14
14
|
return require_utils.trimObject({
|
|
15
|
-
name: require_utils.parseSingularOf(get("name"), require_utils.
|
|
16
|
-
url: require_utils.parseSingularOf(get("url"), require_utils.
|
|
17
|
-
avatar: require_utils.parseSingularOf(get("avatar"), require_utils.
|
|
15
|
+
name: require_utils.parseSingularOf(get("name"), require_utils.parseVerbatimString),
|
|
16
|
+
url: require_utils.parseSingularOf(get("url"), require_utils.parseVerbatimString),
|
|
17
|
+
avatar: require_utils.parseSingularOf(get("avatar"), require_utils.parseVerbatimString)
|
|
18
18
|
});
|
|
19
19
|
}
|
|
20
|
-
if (require_utils.isNonEmptyStringOrNumber(value)) return require_utils.trimObject({ name: require_utils.
|
|
20
|
+
if (require_utils.isNonEmptyStringOrNumber(value)) return require_utils.trimObject({ name: require_utils.parseVerbatimString(value) });
|
|
21
21
|
};
|
|
22
22
|
const retrieveAuthors = (value) => {
|
|
23
23
|
if (!require_is.isPlainObject(value)) return;
|
|
@@ -30,9 +30,9 @@ const parseAttachment = (value) => {
|
|
|
30
30
|
if (!require_is.isPlainObject(value)) return;
|
|
31
31
|
const get = createCaseInsensitiveGetter(value);
|
|
32
32
|
return require_utils.trimObject({
|
|
33
|
-
url: require_utils.parseSingularOf(get("url"), require_utils.
|
|
34
|
-
mime_type: require_utils.parseSingularOf(get("mime_type"), require_utils.
|
|
35
|
-
title: require_utils.parseSingularOf(get("title"), require_utils.
|
|
33
|
+
url: require_utils.parseSingularOf(get("url"), require_utils.parseVerbatimString),
|
|
34
|
+
mime_type: require_utils.parseSingularOf(get("mime_type"), require_utils.parseVerbatimString),
|
|
35
|
+
title: require_utils.parseSingularOf(get("title"), require_utils.parseVerbatimString),
|
|
36
36
|
size_in_bytes: require_utils.parseSingularOf(get("size_in_bytes"), require_utils.parseNumber),
|
|
37
37
|
duration_in_seconds: require_utils.parseSingularOf(get("duration_in_seconds"), require_utils.parseNumber)
|
|
38
38
|
});
|
|
@@ -41,20 +41,20 @@ const parseItem = (value, options) => {
|
|
|
41
41
|
if (!require_is.isPlainObject(value)) return;
|
|
42
42
|
const get = createCaseInsensitiveGetter(value);
|
|
43
43
|
return require_utils.trimObject({
|
|
44
|
-
id: require_utils.parseSingularOf(get("id"), require_utils.
|
|
45
|
-
url: require_utils.parseSingularOf(get("url"), require_utils.
|
|
46
|
-
external_url: require_utils.parseSingularOf(get("external_url"), require_utils.
|
|
47
|
-
title: require_utils.parseSingularOf(get("title"), require_utils.
|
|
48
|
-
content_html: require_utils.parseSingularOf(get("content_html"), require_utils.
|
|
49
|
-
content_text: require_utils.parseSingularOf(get("content_text"), require_utils.
|
|
50
|
-
summary: require_utils.parseSingularOf(get("summary"), require_utils.
|
|
51
|
-
image: require_utils.parseSingularOf(get("image"), require_utils.
|
|
52
|
-
banner_image: require_utils.parseSingularOf(get("banner_image"), require_utils.
|
|
44
|
+
id: require_utils.parseSingularOf(get("id"), require_utils.parseVerbatimString),
|
|
45
|
+
url: require_utils.parseSingularOf(get("url"), require_utils.parseVerbatimString),
|
|
46
|
+
external_url: require_utils.parseSingularOf(get("external_url"), require_utils.parseVerbatimString),
|
|
47
|
+
title: require_utils.parseSingularOf(get("title"), require_utils.parseVerbatimString),
|
|
48
|
+
content_html: require_utils.parseSingularOf(get("content_html"), require_utils.parseVerbatimString),
|
|
49
|
+
content_text: require_utils.parseSingularOf(get("content_text"), require_utils.parseVerbatimString),
|
|
50
|
+
summary: require_utils.parseSingularOf(get("summary"), require_utils.parseVerbatimString),
|
|
51
|
+
image: require_utils.parseSingularOf(get("image"), require_utils.parseVerbatimString),
|
|
52
|
+
banner_image: require_utils.parseSingularOf(get("banner_image"), require_utils.parseVerbatimString),
|
|
53
53
|
date_published: require_utils.parseSingularOf(get("date_published"), (value) => require_utils.parseDate(value, options?.parseDateFn)),
|
|
54
54
|
date_modified: require_utils.parseSingularOf(get("date_modified"), (value) => require_utils.parseDate(value, options?.parseDateFn)),
|
|
55
|
-
tags: require_utils.parseArrayOf(get("tags"), require_utils.
|
|
55
|
+
tags: require_utils.parseArrayOf(get("tags"), require_utils.parseVerbatimString),
|
|
56
56
|
authors: retrieveAuthors(value),
|
|
57
|
-
language: require_utils.parseSingularOf(get("language"), require_utils.
|
|
57
|
+
language: require_utils.parseSingularOf(get("language"), require_utils.parseVerbatimString),
|
|
58
58
|
attachments: require_utils.parseArrayOf(get("attachments"), parseAttachment)
|
|
59
59
|
});
|
|
60
60
|
};
|
|
@@ -62,23 +62,23 @@ const parseHub = (value) => {
|
|
|
62
62
|
if (!require_is.isPlainObject(value)) return;
|
|
63
63
|
const get = createCaseInsensitiveGetter(value);
|
|
64
64
|
return require_utils.trimObject({
|
|
65
|
-
type: require_utils.parseSingularOf(get("type"), require_utils.
|
|
66
|
-
url: require_utils.parseSingularOf(get("url"), require_utils.
|
|
65
|
+
type: require_utils.parseSingularOf(get("type"), require_utils.parseVerbatimString),
|
|
66
|
+
url: require_utils.parseSingularOf(get("url"), require_utils.parseVerbatimString)
|
|
67
67
|
});
|
|
68
68
|
};
|
|
69
69
|
const parseFeed = (value, options) => {
|
|
70
70
|
if (!require_is.isPlainObject(value)) return;
|
|
71
71
|
const get = createCaseInsensitiveGetter(value);
|
|
72
72
|
return require_utils.trimObject({
|
|
73
|
-
title: require_utils.parseSingularOf(get("title"), require_utils.
|
|
74
|
-
home_page_url: require_utils.parseSingularOf(get("home_page_url"), require_utils.
|
|
75
|
-
feed_url: require_utils.parseSingularOf(get("feed_url"), require_utils.
|
|
76
|
-
description: require_utils.parseSingularOf(get("description"), require_utils.
|
|
77
|
-
user_comment: require_utils.parseSingularOf(get("user_comment"), require_utils.
|
|
78
|
-
next_url: require_utils.parseSingularOf(get("next_url"), require_utils.
|
|
79
|
-
icon: require_utils.parseSingularOf(get("icon"), require_utils.
|
|
80
|
-
favicon: require_utils.parseSingularOf(get("favicon"), require_utils.
|
|
81
|
-
language: require_utils.parseSingularOf(get("language"), require_utils.
|
|
73
|
+
title: require_utils.parseSingularOf(get("title"), require_utils.parseVerbatimString),
|
|
74
|
+
home_page_url: require_utils.parseSingularOf(get("home_page_url"), require_utils.parseVerbatimString),
|
|
75
|
+
feed_url: require_utils.parseSingularOf(get("feed_url"), require_utils.parseVerbatimString),
|
|
76
|
+
description: require_utils.parseSingularOf(get("description"), require_utils.parseVerbatimString),
|
|
77
|
+
user_comment: require_utils.parseSingularOf(get("user_comment"), require_utils.parseVerbatimString),
|
|
78
|
+
next_url: require_utils.parseSingularOf(get("next_url"), require_utils.parseVerbatimString),
|
|
79
|
+
icon: require_utils.parseSingularOf(get("icon"), require_utils.parseVerbatimString),
|
|
80
|
+
favicon: require_utils.parseSingularOf(get("favicon"), require_utils.parseVerbatimString),
|
|
81
|
+
language: require_utils.parseSingularOf(get("language"), require_utils.parseVerbatimString),
|
|
82
82
|
expired: require_utils.parseSingularOf(get("expired"), require_utils.parseBoolean),
|
|
83
83
|
hubs: require_utils.parseArrayOf(get("hubs"), parseHub),
|
|
84
84
|
authors: retrieveAuthors(value),
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { isPlainObject } from "../../../node_modules/trousse/dist/is.js";
|
|
2
|
-
import { isNonEmptyStringOrNumber, parseArrayOf, parseBoolean, parseDate,
|
|
2
|
+
import { isNonEmptyStringOrNumber, parseArrayOf, parseBoolean, parseDate, parseNumber, parseSingularOf, parseVerbatimString, trimObject } from "../../../common/utils.js";
|
|
3
3
|
//#region src/feeds/json/parse/utils.ts
|
|
4
4
|
const createCaseInsensitiveGetter = (value) => {
|
|
5
5
|
return (requestedKey) => {
|
|
@@ -12,12 +12,12 @@ const parseAuthor = (value) => {
|
|
|
12
12
|
if (isPlainObject(value)) {
|
|
13
13
|
const get = createCaseInsensitiveGetter(value);
|
|
14
14
|
return trimObject({
|
|
15
|
-
name: parseSingularOf(get("name"),
|
|
16
|
-
url: parseSingularOf(get("url"),
|
|
17
|
-
avatar: parseSingularOf(get("avatar"),
|
|
15
|
+
name: parseSingularOf(get("name"), parseVerbatimString),
|
|
16
|
+
url: parseSingularOf(get("url"), parseVerbatimString),
|
|
17
|
+
avatar: parseSingularOf(get("avatar"), parseVerbatimString)
|
|
18
18
|
});
|
|
19
19
|
}
|
|
20
|
-
if (isNonEmptyStringOrNumber(value)) return trimObject({ name:
|
|
20
|
+
if (isNonEmptyStringOrNumber(value)) return trimObject({ name: parseVerbatimString(value) });
|
|
21
21
|
};
|
|
22
22
|
const retrieveAuthors = (value) => {
|
|
23
23
|
if (!isPlainObject(value)) return;
|
|
@@ -30,9 +30,9 @@ const parseAttachment = (value) => {
|
|
|
30
30
|
if (!isPlainObject(value)) return;
|
|
31
31
|
const get = createCaseInsensitiveGetter(value);
|
|
32
32
|
return trimObject({
|
|
33
|
-
url: parseSingularOf(get("url"),
|
|
34
|
-
mime_type: parseSingularOf(get("mime_type"),
|
|
35
|
-
title: parseSingularOf(get("title"),
|
|
33
|
+
url: parseSingularOf(get("url"), parseVerbatimString),
|
|
34
|
+
mime_type: parseSingularOf(get("mime_type"), parseVerbatimString),
|
|
35
|
+
title: parseSingularOf(get("title"), parseVerbatimString),
|
|
36
36
|
size_in_bytes: parseSingularOf(get("size_in_bytes"), parseNumber),
|
|
37
37
|
duration_in_seconds: parseSingularOf(get("duration_in_seconds"), parseNumber)
|
|
38
38
|
});
|
|
@@ -41,20 +41,20 @@ const parseItem = (value, options) => {
|
|
|
41
41
|
if (!isPlainObject(value)) return;
|
|
42
42
|
const get = createCaseInsensitiveGetter(value);
|
|
43
43
|
return trimObject({
|
|
44
|
-
id: parseSingularOf(get("id"),
|
|
45
|
-
url: parseSingularOf(get("url"),
|
|
46
|
-
external_url: parseSingularOf(get("external_url"),
|
|
47
|
-
title: parseSingularOf(get("title"),
|
|
48
|
-
content_html: parseSingularOf(get("content_html"),
|
|
49
|
-
content_text: parseSingularOf(get("content_text"),
|
|
50
|
-
summary: parseSingularOf(get("summary"),
|
|
51
|
-
image: parseSingularOf(get("image"),
|
|
52
|
-
banner_image: parseSingularOf(get("banner_image"),
|
|
44
|
+
id: parseSingularOf(get("id"), parseVerbatimString),
|
|
45
|
+
url: parseSingularOf(get("url"), parseVerbatimString),
|
|
46
|
+
external_url: parseSingularOf(get("external_url"), parseVerbatimString),
|
|
47
|
+
title: parseSingularOf(get("title"), parseVerbatimString),
|
|
48
|
+
content_html: parseSingularOf(get("content_html"), parseVerbatimString),
|
|
49
|
+
content_text: parseSingularOf(get("content_text"), parseVerbatimString),
|
|
50
|
+
summary: parseSingularOf(get("summary"), parseVerbatimString),
|
|
51
|
+
image: parseSingularOf(get("image"), parseVerbatimString),
|
|
52
|
+
banner_image: parseSingularOf(get("banner_image"), parseVerbatimString),
|
|
53
53
|
date_published: parseSingularOf(get("date_published"), (value) => parseDate(value, options?.parseDateFn)),
|
|
54
54
|
date_modified: parseSingularOf(get("date_modified"), (value) => parseDate(value, options?.parseDateFn)),
|
|
55
|
-
tags: parseArrayOf(get("tags"),
|
|
55
|
+
tags: parseArrayOf(get("tags"), parseVerbatimString),
|
|
56
56
|
authors: retrieveAuthors(value),
|
|
57
|
-
language: parseSingularOf(get("language"),
|
|
57
|
+
language: parseSingularOf(get("language"), parseVerbatimString),
|
|
58
58
|
attachments: parseArrayOf(get("attachments"), parseAttachment)
|
|
59
59
|
});
|
|
60
60
|
};
|
|
@@ -62,23 +62,23 @@ const parseHub = (value) => {
|
|
|
62
62
|
if (!isPlainObject(value)) return;
|
|
63
63
|
const get = createCaseInsensitiveGetter(value);
|
|
64
64
|
return trimObject({
|
|
65
|
-
type: parseSingularOf(get("type"),
|
|
66
|
-
url: parseSingularOf(get("url"),
|
|
65
|
+
type: parseSingularOf(get("type"), parseVerbatimString),
|
|
66
|
+
url: parseSingularOf(get("url"), parseVerbatimString)
|
|
67
67
|
});
|
|
68
68
|
};
|
|
69
69
|
const parseFeed = (value, options) => {
|
|
70
70
|
if (!isPlainObject(value)) return;
|
|
71
71
|
const get = createCaseInsensitiveGetter(value);
|
|
72
72
|
return trimObject({
|
|
73
|
-
title: parseSingularOf(get("title"),
|
|
74
|
-
home_page_url: parseSingularOf(get("home_page_url"),
|
|
75
|
-
feed_url: parseSingularOf(get("feed_url"),
|
|
76
|
-
description: parseSingularOf(get("description"),
|
|
77
|
-
user_comment: parseSingularOf(get("user_comment"),
|
|
78
|
-
next_url: parseSingularOf(get("next_url"),
|
|
79
|
-
icon: parseSingularOf(get("icon"),
|
|
80
|
-
favicon: parseSingularOf(get("favicon"),
|
|
81
|
-
language: parseSingularOf(get("language"),
|
|
73
|
+
title: parseSingularOf(get("title"), parseVerbatimString),
|
|
74
|
+
home_page_url: parseSingularOf(get("home_page_url"), parseVerbatimString),
|
|
75
|
+
feed_url: parseSingularOf(get("feed_url"), parseVerbatimString),
|
|
76
|
+
description: parseSingularOf(get("description"), parseVerbatimString),
|
|
77
|
+
user_comment: parseSingularOf(get("user_comment"), parseVerbatimString),
|
|
78
|
+
next_url: parseSingularOf(get("next_url"), parseVerbatimString),
|
|
79
|
+
icon: parseSingularOf(get("icon"), parseVerbatimString),
|
|
80
|
+
favicon: parseSingularOf(get("favicon"), parseVerbatimString),
|
|
81
|
+
language: parseSingularOf(get("language"), parseVerbatimString),
|
|
82
82
|
expired: parseSingularOf(get("expired"), parseBoolean),
|
|
83
83
|
hubs: parseArrayOf(get("hubs"), parseHub),
|
|
84
84
|
authors: retrieveAuthors(value),
|
|
@@ -1,29 +1,19 @@
|
|
|
1
|
-
const require_config = require("../../../common/config.cjs");
|
|
2
|
-
const require_utils = require("../../../common/utils.cjs");
|
|
3
|
-
let fast_xml_parser = require("fast-xml-parser");
|
|
4
1
|
//#region src/feeds/rdf/parse/config.ts
|
|
5
2
|
const stopNodes = [
|
|
6
|
-
...
|
|
7
|
-
"rdf
|
|
8
|
-
"rdf
|
|
9
|
-
"rdf
|
|
10
|
-
"rdf
|
|
11
|
-
"rdf
|
|
12
|
-
"rdf
|
|
13
|
-
"rdf
|
|
14
|
-
"rdf
|
|
15
|
-
"rdf
|
|
16
|
-
"rdf
|
|
17
|
-
"rdf
|
|
18
|
-
"rdf
|
|
19
|
-
"rdf
|
|
3
|
+
...require("../../../common/config.cjs").namespaceStopNodes,
|
|
4
|
+
"rdf.channel.title",
|
|
5
|
+
"rdf.channel.link",
|
|
6
|
+
"rdf.channel.description",
|
|
7
|
+
"rdf.image.title",
|
|
8
|
+
"rdf.image.link",
|
|
9
|
+
"rdf.image.url",
|
|
10
|
+
"rdf.item.title",
|
|
11
|
+
"rdf.item.link",
|
|
12
|
+
"rdf.item.description",
|
|
13
|
+
"rdf.textinput.title",
|
|
14
|
+
"rdf.textinput.description",
|
|
15
|
+
"rdf.textinput.name",
|
|
16
|
+
"rdf.textinput.link"
|
|
20
17
|
];
|
|
21
|
-
const parser = new fast_xml_parser.XMLParser({
|
|
22
|
-
...require_config.parserConfig,
|
|
23
|
-
stopNodes
|
|
24
|
-
});
|
|
25
|
-
const normalizeNamespaces = require_utils.createNamespaceNormalizator(require_config.namespaceUris, require_config.namespacePrefixes, ["rdf", "rss"]);
|
|
26
18
|
//#endregion
|
|
27
|
-
exports.normalizeNamespaces = normalizeNamespaces;
|
|
28
|
-
exports.parser = parser;
|
|
29
19
|
exports.stopNodes = stopNodes;
|