Switch charbox

VikParuchuri · Apr 26, 2024 · ae61f3d · ae61f3d
1 parent 250c513
commit ae61f3d
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 2 deletions.
diff --git a/models/dt.joblib b/models/dt.joblib
diff --git a/pdftext/pdf/chars.py b/pdftext/pdf/chars.py
@@ -74,7 +74,7 @@ def get_pdfium_chars(pdf_path, fontname_sample_freq=settings.FONTNAME_SAMPLE_FRE
 
             rotation = pdfium_c.FPDFText_GetCharAngle(text_page, i)
             rotation = rotation * 180 / math.pi # convert from radians to degrees
-            coords = text_page.get_charbox(i, loose=False)
+            coords = text_page.get_charbox(i, loose=True)
             device_coords = page_bbox_to_device_bbox(page, coords, page_width, page_height, bl_origin, page_rotation, normalize=True)
 
             char_info = {

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pdftext"
-version = "0.2.0"
+version = "0.2.1"
 description = "Extract structured text from pdfs quickly"
 authors = ["Vik Paruchuri <vik.paruchuri@gmail.com>"]
 license = "Apache-2.0"