forked from mozilla/readability
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathgenerate-testcase.js
186 lines (167 loc) · 5.23 KB
/
generate-testcase.js
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
var debug = false;
var path = require("path");
var fs = require("fs");
var JSDOM = require("jsdom").JSDOM;
var prettyPrint = require("./utils").prettyPrint;
var http = require("http");
var urlparse = require("url").parse;
var htmltidy = require("htmltidy2").tidy;
var { Readability, isProbablyReaderable } = require("../index");
var JSDOMParser = require("../JSDOMParser");
var FFX_UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:80.0) Gecko/20100101 Firefox/80.0";
var testcaseRoot = path.join(__dirname, "test-pages");
var argURL = process.argv[3]; // Could be undefined, we'll warn if it is if that is an issue.
function generateTestcase(slug) {
var destRoot = path.join(testcaseRoot, slug);
fs.mkdir(destRoot, function(err) {
if (err) {
var sourceFile = path.join(destRoot, "source.html");
fs.exists(sourceFile, function(exists) {
if (exists) {
fs.readFile(sourceFile, {encoding: "utf-8"}, function(readFileErr, data) {
if (readFileErr) {
console.error("Source existed but couldn't be read?");
process.exit(1);
return;
}
onResponseReceived(null, data, destRoot);
});
} else {
fetchSource(argURL, function(fetchErr, data) {
onResponseReceived(fetchErr, data, destRoot);
});
}
});
return;
}
fetchSource(argURL, function(fetchErr, data) {
onResponseReceived(fetchErr, data, destRoot);
});
});
}
function fetchSource(url, callbackFn) {
if (!url) {
console.error("You should pass a URL if the source doesn't exist yet!");
process.exit(1);
return;
}
var client = http;
if (url.indexOf("https") == 0) {
client = require("https");
}
var options = urlparse(url);
options.headers = {"User-Agent": FFX_UA};
client.get(options, function(response) {
if (debug) {
console.log("STATUS:", response.statusCode);
console.log("HEADERS:", JSON.stringify(response.headers));
}
response.setEncoding("utf-8");
var rv = "";
response.on("data", function(chunk) {
rv += chunk;
});
response.on("end", function() {
if (debug) {
console.log("End received");
}
sanitizeSource(rv, callbackFn);
});
});
}
function sanitizeSource(html, callbackFn) {
htmltidy(new JSDOM(html).serialize(), {
"indent": true,
"indent-spaces": 4,
"numeric-entities": true,
"output-xhtml": true,
"wrap": 0
}, callbackFn);
}
function onResponseReceived(error, source, destRoot) {
if (error) {
console.error("Couldn't tidy source html!");
console.error(error);
return;
}
if (debug) {
console.log("writing");
}
var sourcePath = path.join(destRoot, "source.html");
fs.writeFile(sourcePath, source, function(err) {
if (err) {
console.error("Couldn't write data to source.html!");
console.error(err);
return;
}
if (debug) {
console.log("Running readability stuff");
}
runReadability(source, path.join(destRoot, "expected.html"), path.join(destRoot, "expected-metadata.json"));
});
}
function runReadability(source, destPath, metadataDestPath) {
var uri = "http://fakehost/test/page.html";
var doc = new JSDOMParser().parse(source, uri);
var myReader, result, readerable;
try {
// We pass `caption` as a class to check that passing in extra classes works,
// given that it appears in some of the test documents.
myReader = new Readability(doc, { classesToPreserve: ["caption"] });
result = myReader.parse();
} catch (ex) {
console.error(ex);
ex.stack.forEach(console.log.bind(console));
}
// Use jsdom for isProbablyReaderable because it supports querySelectorAll
try {
var jsdomDoc = new JSDOM(source, {
url: uri,
}).window.document;
myReader = new Readability(jsdomDoc);
readerable = isProbablyReaderable(jsdomDoc);
} catch (ex) {
console.error(ex);
ex.stack.forEach(console.log.bind(console));
}
if (!result) {
console.error("No content generated by readability, not going to write expected.html!");
return;
}
fs.writeFile(destPath, prettyPrint(result.content), function(fileWriteErr) {
if (fileWriteErr) {
console.error("Couldn't write data to expected.html!");
console.error(fileWriteErr);
}
// Delete the result data we don't care about checking.
delete result.content;
delete result.textContent;
delete result.length;
// Add isProbablyReaderable result
result.readerable = readerable;
fs.writeFile(metadataDestPath, JSON.stringify(result, null, 2) + "\n", function(metadataWriteErr) {
if (metadataWriteErr) {
console.error("Couldn't write data to expected-metadata.json!");
console.error(metadataWriteErr);
}
});
});
}
if (process.argv.length < 3) {
console.error("Need at least a destination slug and potentially a URL (if the slug doesn't have source).");
process.exit(0);
throw "Abort";
}
if (process.argv[2] === "all") {
fs.readdir(testcaseRoot, function(err, files) {
if (err) {
console.error("error reading testcaseses");
return;
}
files.forEach(function(file) {
generateTestcase(file);
});
});
} else {
generateTestcase(process.argv[2]);
}