]> _ Git - cubist_pdf.git/commitdiff
#7678
authorVincent Vanwaelscappel <vincent@cubedesigners.com>
Mon, 4 Aug 2025 13:38:03 +0000 (15:38 +0200)
committerVincent Vanwaelscappel <vincent@cubedesigners.com>
Mon, 4 Aug 2025 13:38:03 +0000 (15:38 +0200)
resources/tools/docling/convert_page.py

index 8079c54f83a73e3661c12c1641086a7a4433e7f2..7adbb749dc6feaf6cbafea33dc0a8301fa9bef5e 100644 (file)
@@ -24,12 +24,10 @@ result = converter.convert(sys.argv[1])
 allpages=result.document.export_to_markdown(page_break_placeholder="<!-- page break -->", image_mode=ImageRefMode.EMBEDDED);
 Path(sys.argv[2]+"document.md").write_text(allpages)
 i=0
-j=0
 for md in allpages.split("<!-- page break -->"):
     i+=1
-    j+=1
-    while os.stats(Path(sys.argv[2] + "/../texts/fh{j}.html")).st_size < 21:
-        Path(sys.argv[2]+"p"+str(j)+".md").write_text("")
-        j+=1
-    Path(sys.argv[2]+"p"+str(j)+".md").write_text(md)
+    while os.stat(Path(sys.argv[2] + "/../texts/fh{i}.html")).st_size < 21:
+        Path(sys.argv[2]+"p{i}.md").write_text("")
+        i+=1
+    Path(sys.argv[2]+"p{i}.md").write_text(md)