Restore "text" attr to .textboxhorizontal/etc.

Fix regression introduced in 9587cc7 / v0.6.2.
This commit is contained in:
Jeremy Singer-Vine
2022-11-22 12:24:10 -05:00
parent e63a0385bb
commit 8a0c12652c
2 changed files with 8 additions and 1 deletions
+4 -1
View File
@@ -23,6 +23,7 @@ from pdfminer.layout import (
LTLine,
LTPage,
LTRect,
LTTextContainer,
)
from pdfminer.pdfinterp import PDFPageInterpreter
from pdfminer.pdfpage import PDFPage
@@ -211,8 +212,10 @@ class Page(Container):
attr["object_type"] = kind
attr["page_number"] = self.page_number
if isinstance(obj, LTChar):
if isinstance(obj, (LTChar, LTTextContainer)):
attr["text"] = obj.get_text()
if isinstance(obj, LTChar):
gs = obj.graphicstate
attr["stroking_color"] = gs.scolor
attr["non_stroking_color"] = gs.ncolor
+4
View File
@@ -26,6 +26,8 @@ class Test(unittest.TestCase):
page = pdf.pages[0]
assert len(page.textboxhorizontals) == 27
assert len(page.textlinehorizontals) == 79
assert "text" in page.textboxhorizontals[0]
assert "text" in page.textlinehorizontals[0]
assert len(page.chars) == 4408
assert "anno" not in page.objects.keys()
@@ -38,6 +40,8 @@ class Test(unittest.TestCase):
assert len(page.textboxhorizontals) == 74
assert len(page.textlineverticals) == 11
assert len(page.textboxverticals) == 6
assert "text" in page.textboxverticals[0]
assert "text" in page.textlineverticals[0]
def test_issue_383(self):
with pdfplumber.open(self.path, laparams={}) as pdf: