@xuda.io/drive_module 1.1.938 → 1.1.940
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/index.js +3 -3
- package/package.json +1 -1
package/index.js
CHANGED
|
@@ -1727,7 +1727,7 @@ const ocr_drive_file = async function (app_id, doc) {
|
|
|
1727
1727
|
case "image": {
|
|
1728
1728
|
const tesseract = require("node-tesseract-ocr");
|
|
1729
1729
|
ocr = await tesseract.recognize(target_file, {
|
|
1730
|
-
lang: "eng",
|
|
1730
|
+
// lang: "eng",
|
|
1731
1731
|
oem: 1,
|
|
1732
1732
|
psm: 3,
|
|
1733
1733
|
});
|
|
@@ -1744,7 +1744,7 @@ const ocr_drive_file = async function (app_id, doc) {
|
|
|
1744
1744
|
const images = await convertPDF(target_file);
|
|
1745
1745
|
for await (const imageData of images) {
|
|
1746
1746
|
ocr += await tesseract.recognize(imageData.path, {
|
|
1747
|
-
lang: "eng",
|
|
1747
|
+
// lang: "eng",
|
|
1748
1748
|
oem: 1,
|
|
1749
1749
|
psm: 3,
|
|
1750
1750
|
});
|
|
@@ -1793,7 +1793,7 @@ const ocr_drive_file = async function (app_id, doc) {
|
|
|
1793
1793
|
break;
|
|
1794
1794
|
}
|
|
1795
1795
|
|
|
1796
|
-
doc.ocr = ocr.replace(/<\/?[^>]+(>|$)/g, "").replace(/[\n\t]/g, "");
|
|
1796
|
+
doc.ocr = ocr.replace(/<\/?[^>]+(>|$)/g, "").replace(/[\n\t]/g, " ");
|
|
1797
1797
|
doc.ocr_stat = 3;
|
|
1798
1798
|
} catch (err) {
|
|
1799
1799
|
// doc.ocr_stat = 4;
|