-
-
Notifications
You must be signed in to change notification settings - Fork 27
/
webworker.js
212 lines (205 loc) · 8.12 KB
/
webworker.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
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
importScripts("https://cdn.jsdelivr.net/pyodide/v0.26.2/full/pyodide.js");
function log(line) {
console.log({line})
self.postMessage({type: 'log', line: line});
}
async function startDatasette(settings) {
let toLoad = [];
let sources = [];
let needsDataDb = false;
let shouldLoadDefaults = true;
// Which version of Datasette to install?
let datasetteToInstall = 'datasette';
let pre = 'False';
if (settings.ref) {
if (settings.ref == 'pre') {
pre = 'True';
} else {
datasetteToInstall = `datasette==${settings.ref}`;
}
}
console.log({datasetteToInstall});
if (settings.sqliteUrl) {
let name = settings.sqliteUrl.split('.db')[0].split('/').slice(-1)[0];
toLoad.push([name, settings.sqliteUrl]);
shouldLoadDefaults = false;
}
['csv', 'sql', 'json', 'parquet'].forEach(sourceType => {
if (settings[`${sourceType}Urls`] && settings[`${sourceType}Urls`].length) {
sources.push([sourceType, settings[`${sourceType}Urls`]]);
needsDataDb = true;
shouldLoadDefaults = false;
}
});
if (settings.memory) {
shouldLoadDefaults = false;
}
if (needsDataDb) {
toLoad.push(["data.db", 0]);
}
if (shouldLoadDefaults) {
toLoad.push(["fixtures.db", "https://latest.datasette.io/fixtures.db"]);
toLoad.push(["content.db", "https://datasette.io/content.db"]);
}
self.pyodide = await loadPyodide({
indexURL: "https://cdn.jsdelivr.net/pyodide/v0.26.2/full/",
fullStdLib: true
});
await pyodide.loadPackage('micropip', {messageCallback: log});
await pyodide.loadPackage('ssl', {messageCallback: log});
await pyodide.loadPackage('setuptools', {messageCallback: log}); // For pkg_resources
try {
await self.pyodide.runPythonAsync(`
# https://github.com/pyodide/pyodide/issues/3880#issuecomment-1560130092
import os
os.link = os.symlink
# Grab that fixtures.db database
import sqlite3
from pyodide.http import pyfetch
names = []
for name, url in ${JSON.stringify(toLoad)}:
if url:
response = await pyfetch(url)
with open(name, "wb") as fp:
fp.write(await response.bytes())
else:
sqlite3.connect(name).execute("vacuum")
names.append(name)
import micropip
# Workaround for Requested 'h11<0.13,>=0.11', but h11==0.13.0 is already installed
await micropip.install("h11==0.12.0")
await micropip.install("httpx==0.23")
# To avoid possible 'from typing_extensions import deprecated' error:
await micropip.install('typing-extensions>=4.12.2')
await micropip.install("${datasetteToInstall}", pre=${pre})
# Install any extra ?install= dependencies
install_urls = ${JSON.stringify(settings.installUrls)}
if install_urls:
for install_url in install_urls:
await micropip.install(install_url)
# Execute any ?sql=URL SQL
sqls = ${JSON.stringify(sources.filter(source => source[0] === "sql")[0]?.[1] || [])}
if sqls:
for sql_url in sqls:
# Fetch that SQL and execute it
response = await pyfetch(sql_url)
sql = await response.string()
sqlite3.connect("data.db").executescript(sql)
metadata = {
"about": "Datasette Lite",
"about_url": "https://github.com/simonw/datasette-lite"
}
metadata_url = ${JSON.stringify(settings.metadataUrl || '')}
if metadata_url:
response = await pyfetch(metadata_url)
content = await response.string()
from datasette.utils import parse_metadata
metadata = parse_metadata(content)
# Import data from ?csv=URL CSV files/?json=URL JSON files
sources = ${JSON.stringify(sources.filter(source => ['csv', 'json', 'parquet'].includes(source[0])))}
if sources:
await micropip.install("sqlite-utils==3.28")
import sqlite_utils, json
from sqlite_utils.utils import rows_from_file, TypeTracker, Format
db = sqlite_utils.Database("data.db")
table_names = set()
for source_type, urls in sources:
for url in urls:
# Derive table name from URL
bit = url.split("/")[-1].split(".")[0].split("?")[0]
bit = bit.strip()
if not bit:
bit = "table"
prefix = 0
base_bit = bit
while bit in table_names:
prefix += 1
bit = "{}_{}".format(base_bit, prefix)
table_names.add(bit)
if source_type == "csv":
tracker = TypeTracker()
response = await pyfetch(url)
with open("csv.csv", "wb") as fp:
fp.write(await response.bytes())
db[bit].insert_all(
tracker.wrap(rows_from_file(open("csv.csv", "rb"), Format.CSV)[0]),
alter=True
)
db[bit].transform(
types=tracker.types
)
elif source_type == "json":
pk = None
response = await pyfetch(url)
with open("json.json", "wb") as fp:
json_bytes = await response.bytes()
try:
json_data = json.loads(json_bytes)
except json.decoder.JSONDecodeError:
# Maybe it's newline-delimited JSON?
# This will raise an unhandled exception if not
json_data = [json.loads(line) for line in json_bytes.splitlines()]
if isinstance(json_data, dict) and all(isinstance(v, dict) for v in json_data.values()):
fixed = []
pk = "_key"
for key, value in json_data.items():
value["_key"] = key
fixed.append(value)
json_data = fixed
elif isinstance(json_data, dict) and any(isinstance(v, list) for v in json_data.values()):
for key, value in json_data.items():
if isinstance(value, list) and value and isinstance(value[0], dict):
json_data = value
break
assert isinstance(json_data, list), "JSON data must be a list of objects"
db[bit].insert_all(json_data, pk=pk, alter=True)
elif source_type == "parquet":
await micropip.install("fastparquet")
import fastparquet
response = await pyfetch(url)
with open("parquet.parquet", "wb") as fp:
fp.write(await response.bytes())
df = fastparquet.ParquetFile("parquet.parquet").to_pandas()
df.to_sql(bit, db.conn, if_exists="replace")
from datasette.app import Datasette
ds = Datasette(names, settings={
"num_sql_threads": 0,
}, metadata=metadata, memory=${settings.memory ? 'True' : 'False'})
await ds.invoke_startup()
`);
datasetteLiteReady();
} catch (error) {
self.postMessage({error: error.message});
}
}
// Outside promise pattern
// https://github.com/simonw/datasette-lite/issues/25#issuecomment-1116948381
let datasetteLiteReady;
let readyPromise = new Promise(function(resolve) {
datasetteLiteReady = resolve;
});
self.onmessage = async (event) => {
console.log({event, data: event.data});
if (event.data.type == 'startup') {
await startDatasette(event.data);
return;
}
// make sure loading is done
await readyPromise;
console.log(event, event.data);
try {
let [status, contentType, text] = await self.pyodide.runPythonAsync(
`
import json
response = await ds.client.get(
${JSON.stringify(event.data.path)},
follow_redirects=True
)
[response.status_code, response.headers.get("content-type"), response.text]
`
);
self.postMessage({status, contentType, text});
} catch (error) {
self.postMessage({error: error.message});
}
};