fix: improve TestParsePdfIntoTxt()

Working On It · Working On It · commit f4ac71130c88 · 2025-06-17T21:29:48.000+08:00
diff --git a/txt/pdf_alibaba_cloud.go b/txt/pdf_alibaba_cloud.go
@@ -31,10 +31,10 @@ import (
 
 const (
 	// Alibaba cloud market
-	appCode    = ""
+	appCode    = "311783680cc24ec5a1895872e1129447"
 	apiHost    = "https://generalpdf.market.alicloudapi.com"
 	apiPath    = "/ocrservice/pdf"
-	pdfDirPath = "papar_QA_dataset\\papers"
+	pdfDirPath = "C:\\Users\\chuny\\Desktop\\papar_QA_dataset\\papers"
 	tmpDir     = "tmp_splits"
 	outDir     = "outputdir"
 )
@@ -192,6 +192,7 @@ func extractTextFromWordBase64(base64Str string) (string, error) {
 		for _, run := range para.Runs() {
 			text += run.Text()
 		}
+		text += "\n"
 	}
 	return text, nil
 }

Original file line number	Diff line number	Diff line change
`@@ -31,10 +31,10 @@ import (`
`31`	`31`
`32`	`32`	`const (`
`33`	`33`	`// Alibaba cloud market`
`34`		`- appCode = ""`
	`34`	`+ appCode = "311783680cc24ec5a1895872e1129447"`
`35`	`35`	`apiHost = "https://generalpdf.market.alicloudapi.com"`
`36`	`36`	`apiPath = "/ocrservice/pdf"`
`37`		`- pdfDirPath = "papar_QA_dataset\\papers"`
	`37`	`+ pdfDirPath = "C:\\Users\\chuny\\Desktop\\papar_QA_dataset\\papers"`
`38`	`38`	`tmpDir = "tmp_splits"`
`39`	`39`	`outDir = "outputdir"`
`40`	`40`	`)`
`@@ -192,6 +192,7 @@ func extractTextFromWordBase64(base64Str string) (string, error) {`
`192`	`192`	`for _, run := range para.Runs() {`
`193`	`193`	`text += run.Text()`
`194`	`194`	`}`
	`195`	`+ text += "\n"`
`195`	`196`	`}`
`196`	`197`	`return text, nil`
`197`	`198`	`}`