-
Notifications
You must be signed in to change notification settings - Fork 37
/
index.ts
118 lines (102 loc) · 3.22 KB
/
index.ts
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
/*
* Copyright 2019 Google LLC
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* https://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import * as functions from 'firebase-functions';
import * as admin from 'firebase-admin';
import {ImageAnnotatorClient} from '@google-cloud/vision';
import * as logs from './logs';
import config from './config';
import {shouldExtractText} from './util';
admin.initializeApp();
const client = new ImageAnnotatorClient();
exports.extractText = functions.storage.object().onFinalize(async object => {
if (!shouldExtractText(object)) {
return;
}
const bucket = admin.storage().bucket(object.bucket);
const imageContents = await bucket.file(object.name!).download();
const imageBase64 = Buffer.from(imageContents[0]).toString('base64');
const request = {
image: {
content: imageBase64,
},
features: [
{
type: 'TEXT_DETECTION',
},
],
};
const filePath = `gs://${object.bucket}/${object.name}`;
const [results] = await client.annotateImage(request);
const textAnnotations = results.textAnnotations;
if (!textAnnotations) {
logs.imageExtractionFailed(object.name!);
return;
}
logs.successfulImageExtraction(object.name!);
if (textAnnotations.length === 0 || !textAnnotations[0].description) {
logs.noTextFound(object.name!);
// check if document with file field filePath already exists
const snapshot = await admin
.firestore()
.collection(config.collectionPath)
.where('file', '==', filePath)
.get();
// if document with file field filePath already exists, overwrite it
if (!snapshot.empty) {
const docId = snapshot.docs[0].id;
await admin.firestore().collection(config.collectionPath).doc(docId).set(
{
file: filePath,
text: null,
},
{merge: true}
);
} else {
await admin.firestore().collection(config.collectionPath).add({
file: filePath,
text: null,
});
}
return;
}
const extractedText = textAnnotations[0].description;
const data =
config.detail === 'basic'
? {
file: `gs://${object.bucket}/${object.name}`,
text: extractedText,
}
: {
file: `gs://${object.bucket}/${object.name}`,
textAnnotations,
};
const snapshot = await admin
.firestore()
.collection(config.collectionPath)
.where('file', '==', filePath)
.get();
// if document with file field filePath already exists, overwrite it
if (!snapshot.empty) {
const docId = snapshot.docs[0].id;
await admin
.firestore()
.collection(config.collectionPath)
.doc(docId)
.set(data, {merge: true});
} else {
await admin.firestore().collection(config.collectionPath).add(data);
}
});