strikethrough-ocr 0.3.3__py3-none-any.whl

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.
@@ -0,0 +1,42 @@
1
+ """strikethrough-ocr -- OCR for scanned pages that preserves styling.
2
+
3
+ Library use:
4
+
5
+ from strikethrough_ocr import process, render_html, html_to_markdown
6
+
7
+ model = process("page.png", lang="eng") # run the OCR pipeline
8
+ overlay = render_html(model, "page", "page.png") # styled HTML overlay
9
+ md = html_to_markdown(overlay) # Markdown in reading order
10
+ doc = html_to_document_html(overlay) # clean document HTML
11
+ """
12
+
13
+ __version__ = "0.3.3"
14
+
15
+ from .scan import (
16
+ PageModel,
17
+ draw_debug,
18
+ model_to_json,
19
+ process,
20
+ render_html,
21
+ )
22
+ from .markdown import (
23
+ html_to_document_html,
24
+ html_to_markdown,
25
+ page_to_html,
26
+ page_to_markdown,
27
+ parse_page,
28
+ )
29
+
30
+ __all__ = [
31
+ "__version__",
32
+ "PageModel",
33
+ "draw_debug",
34
+ "model_to_json",
35
+ "process",
36
+ "render_html",
37
+ "html_to_document_html",
38
+ "html_to_markdown",
39
+ "page_to_html",
40
+ "page_to_markdown",
41
+ "parse_page",
42
+ ]