@credal/actions 0.2.49 → 0.2.51
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/actions/providers/confluence/updatePage.js +14 -15
- package/dist/actions/providers/generic/fillTemplateAction.d.ts +7 -0
- package/dist/actions/providers/generic/fillTemplateAction.js +18 -0
- package/dist/actions/providers/generic/genericApiCall.d.ts +3 -0
- package/dist/actions/providers/generic/genericApiCall.js +38 -0
- package/dist/actions/providers/google-oauth/getDriveContentById.d.ts +3 -0
- package/dist/actions/providers/google-oauth/getDriveContentById.js +161 -0
- package/dist/actions/providers/google-oauth/getDriveFileContentById.js +75 -54
- package/dist/actions/providers/google-oauth/searchAndGetDriveContentByKeywords.d.ts +3 -0
- package/dist/actions/providers/google-oauth/searchAndGetDriveContentByKeywords.js +47 -0
- package/dist/actions/providers/google-oauth/searchDriveAndGetContentByKeywords.d.ts +3 -0
- package/dist/actions/providers/google-oauth/searchDriveAndGetContentByKeywords.js +110 -0
- package/dist/actions/providers/google-oauth/searchDriveAndGetContentByQuery.d.ts +3 -0
- package/dist/actions/providers/google-oauth/searchDriveAndGetContentByQuery.js +78 -0
- package/dist/actions/providers/google-oauth/utils/extractContentFromDriveFileId.d.ts +15 -0
- package/dist/actions/providers/google-oauth/utils/extractContentFromDriveFileId.js +129 -0
- package/dist/actions/providers/googlemaps/nearbysearch.d.ts +3 -0
- package/dist/actions/providers/googlemaps/nearbysearch.js +96 -0
- package/dist/actions/providers/snowflake/runSnowflakeQueryWriteResultsToS3.d.ts +3 -0
- package/dist/actions/providers/snowflake/runSnowflakeQueryWriteResultsToS3.js +154 -0
- package/dist/actions/providers/x/scrapeTweetDataWithNitter.d.ts +3 -0
- package/dist/actions/providers/x/scrapeTweetDataWithNitter.js +45 -0
- package/dist/utils/google.d.ts +85 -0
- package/dist/utils/google.js +170 -0
- package/package.json +1 -1
- package/dist/actions/providers/jamf/types.d.ts +0 -8
- package/dist/actions/providers/jamf/types.js +0 -7
@@ -8,30 +8,28 @@ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, ge
|
|
8
8
|
step((generator = generator.apply(thisArg, _arguments || [])).next());
|
9
9
|
});
|
10
10
|
};
|
11
|
-
var __importDefault = (this && this.__importDefault) || function (mod) {
|
12
|
-
return (mod && mod.__esModule) ? mod : { "default": mod };
|
13
|
-
};
|
14
11
|
Object.defineProperty(exports, "__esModule", { value: true });
|
15
|
-
const
|
16
|
-
function
|
17
|
-
|
12
|
+
const axiosClient_1 = require("../../util/axiosClient");
|
13
|
+
function getConfluenceRequestConfig(baseUrl, username, apiToken) {
|
14
|
+
return {
|
18
15
|
baseURL: baseUrl,
|
19
16
|
headers: {
|
20
17
|
Accept: "application/json",
|
21
|
-
// Tokens are associated with a specific user.
|
22
18
|
Authorization: `Basic ${Buffer.from(`${username}:${apiToken}`).toString("base64")}`,
|
23
19
|
},
|
24
|
-
}
|
25
|
-
return api;
|
20
|
+
};
|
26
21
|
}
|
27
22
|
const confluenceUpdatePage = (_a) => __awaiter(void 0, [_a], void 0, function* ({ params, authParams, }) {
|
28
|
-
const { pageId,
|
29
|
-
const { baseUrl, authToken } = authParams;
|
30
|
-
|
23
|
+
const { pageId, content, title } = params;
|
24
|
+
const { baseUrl, authToken, username } = authParams;
|
25
|
+
if (!baseUrl || !authToken || !username) {
|
26
|
+
throw new Error("Missing required authentication information");
|
27
|
+
}
|
28
|
+
const config = getConfluenceRequestConfig(baseUrl, username, authToken);
|
31
29
|
// Get current version number
|
32
|
-
const response = yield
|
30
|
+
const response = yield axiosClient_1.axiosClient.get(`/api/v2/pages/${pageId}`, config);
|
33
31
|
const currVersion = response.data.version.number;
|
34
|
-
|
32
|
+
const payload = {
|
35
33
|
id: pageId,
|
36
34
|
status: "current",
|
37
35
|
title,
|
@@ -42,6 +40,7 @@ const confluenceUpdatePage = (_a) => __awaiter(void 0, [_a], void 0, function* (
|
|
42
40
|
version: {
|
43
41
|
number: currVersion + 1,
|
44
42
|
},
|
45
|
-
}
|
43
|
+
};
|
44
|
+
yield axiosClient_1.axiosClient.put(`/api/v2/pages/${pageId}`, payload, config);
|
46
45
|
});
|
47
46
|
exports.default = confluenceUpdatePage;
|
@@ -0,0 +1,18 @@
|
|
1
|
+
"use strict";
|
2
|
+
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
|
3
|
+
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
|
4
|
+
return new (P || (P = Promise))(function (resolve, reject) {
|
5
|
+
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
|
6
|
+
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
|
7
|
+
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
|
8
|
+
step((generator = generator.apply(thisArg, _arguments || [])).next());
|
9
|
+
});
|
10
|
+
};
|
11
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
12
|
+
const fillTemplateAction = (_a) => __awaiter(void 0, [_a], void 0, function* ({ template }) {
|
13
|
+
// Simply return the template without any modification
|
14
|
+
return {
|
15
|
+
result: template,
|
16
|
+
};
|
17
|
+
});
|
18
|
+
exports.default = fillTemplateAction;
|
@@ -0,0 +1,38 @@
|
|
1
|
+
"use strict";
|
2
|
+
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
|
3
|
+
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
|
4
|
+
return new (P || (P = Promise))(function (resolve, reject) {
|
5
|
+
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
|
6
|
+
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
|
7
|
+
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
|
8
|
+
step((generator = generator.apply(thisArg, _arguments || [])).next());
|
9
|
+
});
|
10
|
+
};
|
11
|
+
var __importDefault = (this && this.__importDefault) || function (mod) {
|
12
|
+
return (mod && mod.__esModule) ? mod : { "default": mod };
|
13
|
+
};
|
14
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
15
|
+
const axios_1 = __importDefault(require("axios"));
|
16
|
+
const genericApiCall = (_a) => __awaiter(void 0, [_a], void 0, function* ({ params, }) {
|
17
|
+
try {
|
18
|
+
const { endpoint, method, headers, body } = params;
|
19
|
+
const response = yield (0, axios_1.default)({
|
20
|
+
url: endpoint,
|
21
|
+
method,
|
22
|
+
headers,
|
23
|
+
data: method !== "GET" ? body : undefined,
|
24
|
+
});
|
25
|
+
return {
|
26
|
+
statusCode: response.status,
|
27
|
+
headers: response.headers,
|
28
|
+
data: response.data,
|
29
|
+
};
|
30
|
+
}
|
31
|
+
catch (error) {
|
32
|
+
if (axios_1.default.isAxiosError(error)) {
|
33
|
+
throw Error("Axios Error: " + (error.message || "Failed to make API call"));
|
34
|
+
}
|
35
|
+
throw Error("Error: " + (error || "Failed to make API call"));
|
36
|
+
}
|
37
|
+
});
|
38
|
+
exports.default = genericApiCall;
|
@@ -0,0 +1,161 @@
|
|
1
|
+
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
|
2
|
+
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
|
3
|
+
return new (P || (P = Promise))(function (resolve, reject) {
|
4
|
+
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
|
5
|
+
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
|
6
|
+
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
|
7
|
+
step((generator = generator.apply(thisArg, _arguments || [])).next());
|
8
|
+
});
|
9
|
+
};
|
10
|
+
import pdf from "pdf-parse/lib/pdf-parse.js";
|
11
|
+
import { axiosClient } from "../../util/axiosClient.js";
|
12
|
+
import mammoth from "mammoth";
|
13
|
+
import { MISSING_AUTH_TOKEN } from "../../util/missingAuthConstants.js";
|
14
|
+
const getDriveFileContentByID = (_a) => __awaiter(void 0, [_a], void 0, function* ({ params, authParams, }) {
|
15
|
+
if (!authParams.authToken) {
|
16
|
+
return { success: false, error: MISSING_AUTH_TOKEN };
|
17
|
+
}
|
18
|
+
const { fileId, limit } = params;
|
19
|
+
try {
|
20
|
+
// First, get file metadata to determine the file type
|
21
|
+
const metadataUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?fields=name,mimeType,size`;
|
22
|
+
const metadataRes = yield axiosClient.get(metadataUrl, {
|
23
|
+
headers: {
|
24
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
25
|
+
},
|
26
|
+
});
|
27
|
+
const { name: fileName, mimeType, size } = metadataRes.data;
|
28
|
+
// Check if file is too large (50MB limit for safety)
|
29
|
+
if (size && parseInt(size) > 50 * 1024 * 1024) {
|
30
|
+
return {
|
31
|
+
success: false,
|
32
|
+
error: "File too large (>50MB)",
|
33
|
+
};
|
34
|
+
}
|
35
|
+
let content = "";
|
36
|
+
// Handle different file types - read content directly
|
37
|
+
if (mimeType === "application/vnd.google-apps.document") {
|
38
|
+
// Google Docs - download as plain text
|
39
|
+
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media&format=txt`;
|
40
|
+
const downloadRes = yield axiosClient.get(downloadUrl, {
|
41
|
+
headers: {
|
42
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
43
|
+
},
|
44
|
+
responseType: 'text',
|
45
|
+
});
|
46
|
+
content = downloadRes.data;
|
47
|
+
}
|
48
|
+
else if (mimeType === "application/vnd.google-apps.spreadsheet") {
|
49
|
+
// Google Sheets - download as CSV
|
50
|
+
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media&format=csv`;
|
51
|
+
const downloadRes = yield axiosClient.get(downloadUrl, {
|
52
|
+
headers: {
|
53
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
54
|
+
},
|
55
|
+
responseType: 'text',
|
56
|
+
});
|
57
|
+
content = downloadRes.data;
|
58
|
+
}
|
59
|
+
else if (mimeType === "application/vnd.google-apps.presentation") {
|
60
|
+
// Google Slides - download as plain text
|
61
|
+
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media&format=txt`;
|
62
|
+
const downloadRes = yield axiosClient.get(downloadUrl, {
|
63
|
+
headers: {
|
64
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
65
|
+
},
|
66
|
+
responseType: 'text',
|
67
|
+
});
|
68
|
+
content = downloadRes.data;
|
69
|
+
}
|
70
|
+
else if (mimeType === "application/pdf") {
|
71
|
+
// PDF files - use pdf-parse
|
72
|
+
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media`;
|
73
|
+
const downloadRes = yield axiosClient.get(downloadUrl, {
|
74
|
+
headers: {
|
75
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
76
|
+
},
|
77
|
+
responseType: 'arraybuffer',
|
78
|
+
});
|
79
|
+
try {
|
80
|
+
const pdfData = yield pdf(downloadRes.data);
|
81
|
+
content = pdfData.text;
|
82
|
+
}
|
83
|
+
catch (pdfError) {
|
84
|
+
return {
|
85
|
+
success: false,
|
86
|
+
error: `Failed to parse PDF: ${pdfError instanceof Error ? pdfError.message : 'Unknown PDF error'}`,
|
87
|
+
};
|
88
|
+
}
|
89
|
+
}
|
90
|
+
else if (mimeType === "application/vnd.openxmlformats-officedocument.wordprocessingml.document" ||
|
91
|
+
mimeType === "application/msword") {
|
92
|
+
// Word documents (.docx or .doc) - download and extract text using mammoth
|
93
|
+
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media`;
|
94
|
+
const downloadRes = yield axiosClient.get(downloadUrl, {
|
95
|
+
headers: {
|
96
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
97
|
+
},
|
98
|
+
responseType: 'arraybuffer',
|
99
|
+
});
|
100
|
+
try {
|
101
|
+
// mammoth works with .docx files. It will ignore formatting and return raw text
|
102
|
+
const result = yield mammoth.extractRawText({ buffer: Buffer.from(downloadRes.data) });
|
103
|
+
content = result.value; // raw text
|
104
|
+
}
|
105
|
+
catch (wordError) {
|
106
|
+
return {
|
107
|
+
success: false,
|
108
|
+
error: `Failed to parse Word document: ${wordError instanceof Error ? wordError.message : 'Unknown Word error'}`,
|
109
|
+
};
|
110
|
+
}
|
111
|
+
}
|
112
|
+
else if (mimeType === "text/plain" ||
|
113
|
+
mimeType === "text/html" ||
|
114
|
+
mimeType === "application/rtf" ||
|
115
|
+
(mimeType === null || mimeType === void 0 ? void 0 : mimeType.startsWith("text/"))) {
|
116
|
+
// Text-based files
|
117
|
+
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media`;
|
118
|
+
const downloadRes = yield axiosClient.get(downloadUrl, {
|
119
|
+
headers: {
|
120
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
121
|
+
},
|
122
|
+
responseType: 'text',
|
123
|
+
});
|
124
|
+
content = downloadRes.data;
|
125
|
+
}
|
126
|
+
else if (mimeType === null || mimeType === void 0 ? void 0 : mimeType.startsWith("image/")) {
|
127
|
+
// Skip images
|
128
|
+
return {
|
129
|
+
success: false,
|
130
|
+
error: "Image files are not supported for text extraction",
|
131
|
+
};
|
132
|
+
}
|
133
|
+
else {
|
134
|
+
// Unsupported file type
|
135
|
+
return {
|
136
|
+
success: false,
|
137
|
+
error: `Unsupported file type: ${mimeType}`,
|
138
|
+
};
|
139
|
+
}
|
140
|
+
content = content.trim();
|
141
|
+
const originalLength = content.length;
|
142
|
+
// Naive way to truncate content
|
143
|
+
if (limit && content.length > limit) {
|
144
|
+
content = content.substring(0, limit);
|
145
|
+
}
|
146
|
+
return {
|
147
|
+
success: true,
|
148
|
+
content,
|
149
|
+
fileName,
|
150
|
+
fileLength: originalLength,
|
151
|
+
};
|
152
|
+
}
|
153
|
+
catch (error) {
|
154
|
+
console.error("Error getting Google Drive file content", error);
|
155
|
+
return {
|
156
|
+
success: false,
|
157
|
+
error: error instanceof Error ? error.message : "Unknown error",
|
158
|
+
};
|
159
|
+
}
|
160
|
+
});
|
161
|
+
export default getDriveFileContentByID;
|
@@ -11,14 +11,16 @@ import { axiosClient } from "../../util/axiosClient.js";
|
|
11
11
|
import mammoth from "mammoth";
|
12
12
|
import { MISSING_AUTH_TOKEN } from "../../util/missingAuthConstants.js";
|
13
13
|
import { extractTextFromPdf } from "../../../utils/pdf.js";
|
14
|
+
import { parseGoogleDocFromRawContentToPlainText, parseGoogleSheetsFromRawContentToPlainText, parseGoogleSlidesFromRawContentToPlainText, } from "../../../utils/google.js";
|
14
15
|
const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function* ({ params, authParams, }) {
|
15
16
|
if (!authParams.authToken) {
|
16
17
|
return { success: false, error: MISSING_AUTH_TOKEN };
|
17
18
|
}
|
19
|
+
const BASE_URL = "https://www.googleapis.com/drive/v3/files/";
|
18
20
|
const { fileId, limit } = params;
|
19
21
|
try {
|
20
22
|
// First, get file metadata to determine the file type and if it's in a shared drive
|
21
|
-
const metadataUrl =
|
23
|
+
const metadataUrl = `${BASE_URL}${encodeURIComponent(fileId)}?fields=name,mimeType,size,driveId,parents&supportsAllDrives=true`;
|
22
24
|
const metadataRes = yield axiosClient.get(metadataUrl, {
|
23
25
|
headers: {
|
24
26
|
Authorization: `Bearer ${authParams.authToken}`,
|
@@ -34,54 +36,82 @@ const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function
|
|
34
36
|
};
|
35
37
|
}
|
36
38
|
let content = "";
|
37
|
-
// Create shared drive parameters if the file is in a shared drive
|
38
39
|
const sharedDriveParams = driveId ? "&supportsAllDrives=true" : "";
|
39
|
-
//
|
40
|
+
// Google Docs - use Google Docs API instead of Drive export
|
40
41
|
if (mimeType === "application/vnd.google-apps.document") {
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
42
|
+
try {
|
43
|
+
const docsUrl = `https://docs.googleapis.com/v1/documents/${fileId}`;
|
44
|
+
const docsRes = yield axiosClient.get(docsUrl, {
|
45
|
+
headers: {
|
46
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
47
|
+
},
|
48
|
+
});
|
49
|
+
content = parseGoogleDocFromRawContentToPlainText(docsRes.data);
|
50
|
+
}
|
51
|
+
catch (docsError) {
|
52
|
+
console.log("Error using Google Docs API", docsError);
|
53
|
+
// Fallback to Drive API export if Docs API fails
|
54
|
+
const exportUrl = `${BASE_URL}${encodeURIComponent(fileId)}/export?mimeType=text/plain${sharedDriveParams}`;
|
55
|
+
const exportRes = yield axiosClient.get(exportUrl, {
|
56
|
+
headers: {
|
57
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
58
|
+
},
|
59
|
+
responseType: "text",
|
60
|
+
});
|
61
|
+
content = exportRes.data;
|
62
|
+
}
|
50
63
|
}
|
64
|
+
// Google Sheets - use Google Sheets API instead of Drive export
|
51
65
|
else if (mimeType === "application/vnd.google-apps.spreadsheet") {
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
.
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
+
try {
|
67
|
+
const sheetsUrl = `https://sheets.googleapis.com/v4/spreadsheets/${fileId}?includeGridData=true`;
|
68
|
+
const sheetsRes = yield axiosClient.get(sheetsUrl, {
|
69
|
+
headers: {
|
70
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
71
|
+
},
|
72
|
+
});
|
73
|
+
content = parseGoogleSheetsFromRawContentToPlainText(sheetsRes.data);
|
74
|
+
}
|
75
|
+
catch (sheetsError) {
|
76
|
+
console.log("Error using Google Sheets API", sheetsError);
|
77
|
+
const exportUrl = `${BASE_URL}${encodeURIComponent(fileId)}/export?mimeType=text/csv${sharedDriveParams}`;
|
78
|
+
const exportRes = yield axiosClient.get(exportUrl, {
|
79
|
+
headers: { Authorization: `Bearer ${authParams.authToken}` },
|
80
|
+
responseType: "text",
|
81
|
+
});
|
82
|
+
content = exportRes.data
|
83
|
+
.split("\n")
|
84
|
+
.map((line) => line.replace(/,+$/, ""))
|
85
|
+
.map((line) => line.replace(/,{2,}/g, ","))
|
86
|
+
.join("\n");
|
87
|
+
}
|
66
88
|
}
|
89
|
+
// Google Slides - use Google Slides API instead of Drive export
|
67
90
|
else if (mimeType === "application/vnd.google-apps.presentation") {
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
91
|
+
try {
|
92
|
+
const slidesUrl = `https://slides.googleapis.com/v1/presentations/${fileId}`;
|
93
|
+
const slidesRes = yield axiosClient.get(slidesUrl, {
|
94
|
+
headers: {
|
95
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
96
|
+
},
|
97
|
+
});
|
98
|
+
content = parseGoogleSlidesFromRawContentToPlainText(slidesRes.data);
|
99
|
+
}
|
100
|
+
catch (slidesError) {
|
101
|
+
console.log("Error using Google Slides API", slidesError);
|
102
|
+
const exportUrl = `${BASE_URL}${encodeURIComponent(fileId)}/export?mimeType=text/plain${sharedDriveParams}`;
|
103
|
+
const exportRes = yield axiosClient.get(exportUrl, {
|
104
|
+
headers: { Authorization: `Bearer ${authParams.authToken}` },
|
105
|
+
responseType: "text",
|
106
|
+
});
|
107
|
+
content = exportRes.data;
|
108
|
+
}
|
77
109
|
}
|
110
|
+
// PDF files - download and extract text using pdfjs-dist
|
78
111
|
else if (mimeType === "application/pdf") {
|
79
|
-
|
80
|
-
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media${sharedDriveParams}`;
|
112
|
+
const downloadUrl = `${BASE_URL}${encodeURIComponent(fileId)}?alt=media${sharedDriveParams}`;
|
81
113
|
const downloadRes = yield axiosClient.get(downloadUrl, {
|
82
|
-
headers: {
|
83
|
-
Authorization: `Bearer ${authParams.authToken}`,
|
84
|
-
},
|
114
|
+
headers: { Authorization: `Bearer ${authParams.authToken}` },
|
85
115
|
responseType: "arraybuffer",
|
86
116
|
});
|
87
117
|
try {
|
@@ -93,12 +123,11 @@ const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function
|
|
93
123
|
error: `Failed to parse PDF document: ${e instanceof Error ? e.message : JSON.stringify(e)}`,
|
94
124
|
};
|
95
125
|
}
|
96
|
-
// Extract text from PDF
|
97
126
|
}
|
127
|
+
// Word documents (.docx or .doc) - download and extract text using mammoth
|
98
128
|
else if (mimeType === "application/vnd.openxmlformats-officedocument.wordprocessingml.document" ||
|
99
129
|
mimeType === "application/msword") {
|
100
|
-
|
101
|
-
const downloadUrl = `https://www.googleapis.com/drive/v3/files/${encodeURIComponent(fileId)}?alt=media${sharedDriveParams}`;
|
130
|
+
const downloadUrl = `${BASE_URL}${encodeURIComponent(fileId)}?alt=media${sharedDriveParams}`;
|
102
131
|
const downloadRes = yield axiosClient.get(downloadUrl, {
|
103
132
|
headers: {
|
104
133
|
Authorization: `Bearer ${authParams.authToken}`,
|
@@ -122,7 +151,7 @@ const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function
|
|
122
151
|
mimeType === "application/rtf" ||
|
123
152
|
(mimeType === null || mimeType === void 0 ? void 0 : mimeType.startsWith("text/"))) {
|
124
153
|
// Text-based files
|
125
|
-
const downloadUrl =
|
154
|
+
const downloadUrl = `${BASE_URL}${encodeURIComponent(fileId)}?alt=media${sharedDriveParams}`;
|
126
155
|
const downloadRes = yield axiosClient.get(downloadUrl, {
|
127
156
|
headers: {
|
128
157
|
Authorization: `Bearer ${authParams.authToken}`,
|
@@ -131,13 +160,6 @@ const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function
|
|
131
160
|
});
|
132
161
|
content = downloadRes.data;
|
133
162
|
}
|
134
|
-
else if (mimeType === null || mimeType === void 0 ? void 0 : mimeType.startsWith("image/")) {
|
135
|
-
// Skip images
|
136
|
-
return {
|
137
|
-
success: false,
|
138
|
-
error: "Image files are not supported for text extraction",
|
139
|
-
};
|
140
|
-
}
|
141
163
|
else {
|
142
164
|
// Unsupported file type
|
143
165
|
return {
|
@@ -145,14 +167,13 @@ const getDriveFileContentById = (_a) => __awaiter(void 0, [_a], void 0, function
|
|
145
167
|
error: `Unsupported file type: ${mimeType}`,
|
146
168
|
};
|
147
169
|
}
|
170
|
+
// cleaning up parameters
|
148
171
|
content = content.trim();
|
149
172
|
const originalLength = content.length;
|
150
|
-
|
173
|
+
content = content.replace(/\r?\n+/g, " ").replace(/ +/g, " ");
|
151
174
|
if (limit && content.length > limit) {
|
152
175
|
content = content.substring(0, limit);
|
153
176
|
}
|
154
|
-
// Replace all newline characters with spaces, then collapse multiple spaces
|
155
|
-
content = content.replace(/\r?\n+/g, " ").replace(/ +/g, " ");
|
156
177
|
return {
|
157
178
|
success: true,
|
158
179
|
content,
|
@@ -0,0 +1,47 @@
|
|
1
|
+
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
|
2
|
+
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
|
3
|
+
return new (P || (P = Promise))(function (resolve, reject) {
|
4
|
+
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
|
5
|
+
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
|
6
|
+
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
|
7
|
+
step((generator = generator.apply(thisArg, _arguments || [])).next());
|
8
|
+
});
|
9
|
+
};
|
10
|
+
import { axiosClient } from "../../util/axiosClient.js";
|
11
|
+
import { MISSING_AUTH_TOKEN } from "../../util/missingAuthConstants.js";
|
12
|
+
const searchDriveByKeywords = (_a) => __awaiter(void 0, [_a], void 0, function* ({ params, authParams, }) {
|
13
|
+
var _b;
|
14
|
+
if (!authParams.authToken) {
|
15
|
+
return { success: false, error: MISSING_AUTH_TOKEN, files: [] };
|
16
|
+
}
|
17
|
+
const { keywords, limit } = params;
|
18
|
+
// Build the query: fullText contains 'keyword1' or fullText contains 'keyword2' ...
|
19
|
+
const query = keywords.map(kw => `fullText contains '${kw.replace(/'/g, "\\'")}'`).join(" or ");
|
20
|
+
const url = `https://www.googleapis.com/drive/v3/files?q=${encodeURIComponent(query)}&fields=files(id,name,mimeType,webViewLink)&supportsAllDrives=true&includeItemsFromAllDrives=true`;
|
21
|
+
// 1. Get the file metadata from google drive search
|
22
|
+
let files = [];
|
23
|
+
try {
|
24
|
+
const res = yield axiosClient.get(url, {
|
25
|
+
headers: {
|
26
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
27
|
+
},
|
28
|
+
});
|
29
|
+
files =
|
30
|
+
((_b = res.data.files) === null || _b === void 0 ? void 0 : _b.map((file) => ({
|
31
|
+
id: file.id || "",
|
32
|
+
name: file.name || "",
|
33
|
+
mimeType: file.mimeType || "",
|
34
|
+
url: file.webViewLink || "",
|
35
|
+
}))) || [];
|
36
|
+
}
|
37
|
+
catch (error) {
|
38
|
+
console.error("Error searching Google Drive", error);
|
39
|
+
return {
|
40
|
+
success: false,
|
41
|
+
error: error instanceof Error ? error.message : "Unknown error",
|
42
|
+
files: [],
|
43
|
+
};
|
44
|
+
}
|
45
|
+
files = limit ? files.splice(0, limit) : files;
|
46
|
+
});
|
47
|
+
export default searchDriveByKeywords;
|
@@ -0,0 +1,110 @@
|
|
1
|
+
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
|
2
|
+
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
|
3
|
+
return new (P || (P = Promise))(function (resolve, reject) {
|
4
|
+
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
|
5
|
+
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
|
6
|
+
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
|
7
|
+
step((generator = generator.apply(thisArg, _arguments || [])).next());
|
8
|
+
});
|
9
|
+
};
|
10
|
+
import { axiosClient } from "../../util/axiosClient.js";
|
11
|
+
import { MISSING_AUTH_TOKEN } from "../../util/missingAuthConstants.js";
|
12
|
+
import extractContentFromDriveFileId from "./utils/extractContentFromDriveFileId.js";
|
13
|
+
import { normalizeText } from "../../../utils/string.js";
|
14
|
+
/** Intelligently selects a section of text around the median occurrence of keywords */
|
15
|
+
const intelligentSelectByMedianSection = (text, keywords, limit) => {
|
16
|
+
if (!text || text.length <= limit)
|
17
|
+
return text;
|
18
|
+
if (!(keywords === null || keywords === void 0 ? void 0 : keywords.length))
|
19
|
+
return text.substring(0, limit);
|
20
|
+
// Find all keyword positions (case-insensitive, limited to first 1000 matches)
|
21
|
+
const positions = [];
|
22
|
+
const normalizedText = normalizeText(text);
|
23
|
+
for (const keyword of keywords) {
|
24
|
+
if (keyword.length < 3)
|
25
|
+
continue; // Skip very short keywords
|
26
|
+
let pos = -1;
|
27
|
+
const normalizedKeyword = normalizeText(keyword);
|
28
|
+
while ((pos = normalizedText.indexOf(normalizedKeyword, pos + 1)) !== -1 && positions.length < 1000) {
|
29
|
+
positions.push(pos);
|
30
|
+
}
|
31
|
+
}
|
32
|
+
if (!positions.length)
|
33
|
+
return text.substring(0, limit);
|
34
|
+
// Find median position (using sort for simplicity, still fast for 1000 elements)
|
35
|
+
positions.sort((a, b) => a - b);
|
36
|
+
const medianPos = positions[Math.floor(positions.length / 2)];
|
37
|
+
// Return window around median
|
38
|
+
const half = Math.floor(limit / 2);
|
39
|
+
const start = Math.max(0, medianPos - half);
|
40
|
+
const end = Math.min(text.length, start + limit);
|
41
|
+
return text.substring(start, end);
|
42
|
+
};
|
43
|
+
const searchDriveAndGetContentByKeywords = (_a) => __awaiter(void 0, [_a], void 0, function* ({ params, authParams, }) {
|
44
|
+
var _b;
|
45
|
+
if (!authParams.authToken) {
|
46
|
+
return { success: false, error: MISSING_AUTH_TOKEN, files: [] };
|
47
|
+
}
|
48
|
+
const { keywords, fileLimit, fileSizeLimit } = params;
|
49
|
+
let files = [];
|
50
|
+
// 1. Search for files and get their metadata
|
51
|
+
// Build the query: fullText contains 'keyword1' or fullText contains 'keyword2' ...
|
52
|
+
const query = keywords.map(kw => `fullText contains '${kw.replace(/'/g, "\\'")}'`).join(" or ");
|
53
|
+
const url = `https://www.googleapis.com/drive/v3/files?q=${encodeURIComponent(query)}&fields=files(id,name,mimeType,webViewLink)&supportsAllDrives=true&includeItemsFromAllDrives=true`;
|
54
|
+
try {
|
55
|
+
const res = yield axiosClient.get(url, {
|
56
|
+
headers: {
|
57
|
+
Authorization: `Bearer ${authParams.authToken}`,
|
58
|
+
},
|
59
|
+
});
|
60
|
+
files =
|
61
|
+
((_b = res.data.files) === null || _b === void 0 ? void 0 : _b.map((file) => ({
|
62
|
+
id: file.id,
|
63
|
+
name: file.name,
|
64
|
+
mimeType: file.mimeType,
|
65
|
+
url: file.webViewLink,
|
66
|
+
}))) || [];
|
67
|
+
}
|
68
|
+
catch (error) {
|
69
|
+
console.error("Error searching Google Drive", error);
|
70
|
+
return {
|
71
|
+
success: false,
|
72
|
+
error: error instanceof Error ? error.message : "Unknown error",
|
73
|
+
files: [],
|
74
|
+
};
|
75
|
+
}
|
76
|
+
files = fileLimit ? files.splice(0, fileLimit) : files;
|
77
|
+
// 2. Extract content from files and do some smart range selection
|
78
|
+
const processedFiles = yield Promise.all(files
|
79
|
+
.filter((file) => file.id && file.mimeType)
|
80
|
+
.map((file) => __awaiter(void 0, void 0, void 0, function* () {
|
81
|
+
const content = yield extractContentFromDriveFileId({
|
82
|
+
params: { fileId: file.id, mimeType: file.mimeType },
|
83
|
+
authParams,
|
84
|
+
});
|
85
|
+
if (content.success) {
|
86
|
+
let selectedContent = content.content;
|
87
|
+
if (fileSizeLimit && selectedContent && selectedContent.length > fileSizeLimit) {
|
88
|
+
selectedContent = intelligentSelectByMedianSection(selectedContent, keywords, fileSizeLimit);
|
89
|
+
}
|
90
|
+
return {
|
91
|
+
id: file.id || "",
|
92
|
+
name: file.name || "",
|
93
|
+
mimeType: file.mimeType || "",
|
94
|
+
url: file.url || "",
|
95
|
+
content: selectedContent,
|
96
|
+
};
|
97
|
+
}
|
98
|
+
else {
|
99
|
+
return {
|
100
|
+
id: file.id || "",
|
101
|
+
name: file.name || "",
|
102
|
+
mimeType: file.mimeType || "",
|
103
|
+
url: file.url || "",
|
104
|
+
error: content.error,
|
105
|
+
};
|
106
|
+
}
|
107
|
+
})));
|
108
|
+
return { success: true, files: processedFiles };
|
109
|
+
});
|
110
|
+
export default searchDriveAndGetContentByKeywords;
|