mirror of
https://github.com/jsvine/pdfplumber.git
synced 2026-08-30 00:50:24 +08:00
Jeremy Singer-Vine
237742039d
This commit adds an `--laparams` flag to the pdfplumber CLI, giving it more feature parity with the core library. To do so, it makes some internal changes to `convert.py`, including changing the list of objects to convert from *a predefined default list* to *all types extracted*.
48 lines
1.6 KiB
Python
48 lines
1.6 KiB
Python
#!/usr/bin/env python
|
|
import unittest
|
|
import pdfplumber
|
|
import os
|
|
|
|
import logging
|
|
|
|
logging.disable(logging.ERROR)
|
|
|
|
HERE = os.path.abspath(os.path.dirname(__file__))
|
|
|
|
|
|
class Test(unittest.TestCase):
|
|
@classmethod
|
|
def setup_class(self):
|
|
self.path = os.path.join(HERE, "pdfs/issue-13-151201DSP-Fond-581-90D.pdf")
|
|
|
|
def test_without_laparams(self):
|
|
with pdfplumber.open(self.path, laparams=None) as pdf:
|
|
objs = pdf.pages[0].objects
|
|
assert "textboxhorizontal" not in objs.keys()
|
|
assert len(objs["char"]) == 4408
|
|
|
|
def test_with_laparams(self):
|
|
with pdfplumber.open(self.path, laparams={}) as pdf:
|
|
page = pdf.pages[0]
|
|
assert len(page.textboxhorizontals) == 21
|
|
assert len(page.textlinehorizontals) == 79
|
|
assert len(page.chars) == 4408
|
|
assert "anno" not in page.objects.keys()
|
|
|
|
def test_vertical_texts(self):
|
|
path = os.path.join(HERE, "pdfs/issue-192-example.pdf")
|
|
laparams = {"detect_vertical": True}
|
|
with pdfplumber.open(path, laparams=laparams) as pdf:
|
|
page = pdf.pages[0]
|
|
assert len(page.textlinehorizontals) == 142
|
|
assert len(page.textboxhorizontals) == 74
|
|
assert len(page.textlineverticals) == 11
|
|
assert len(page.textboxverticals) == 6
|
|
|
|
def test_issue_383(self):
|
|
with pdfplumber.open(self.path, laparams={}) as pdf:
|
|
p0 = pdf.pages[0]
|
|
assert "anno" not in p0.objects.keys()
|
|
cropped = p0.crop((0, 0, 100, 100))
|
|
assert len(cropped.objects)
|