def test_pull_image_files(self) -> None:
"""Copy image files to output path."""
docx2python("resources/example.docx", "delete_this/path/to/images")
assert os.listdir("delete_this/path/to/images") == [
"image1.png", "image2.jpg"
]
# clean up
shutil.rmtree("delete_this")
def test_my_checkbox(self) -> None:
"""A good selection of checked and unchecked boxes, and several dropdowns"""
extraction = docx2python(os.path.join("resources", "check_drop_my.docx"))
assert extraction.body == [
[
[
[
"[user unchecked]\u2610[user unchecked]",
"",
"[user checked]\u2612[user checked]",
"",
"[my unchecked]\u2610[my unchecked]",
"",
"[my checked]\u2612[my checked]",
"",
"User dropdown (Piihan B)",
"Piihan B",
"",
"My dropdown (no choice)",
"Choose an item.",
"",
"My dropdown (chose A)",
"my_item_A",
"",
"My dropdown (chose B)",
"my_item_B",
]
]
]
]
def test_bulleted_lists(self) -> None:
pars = docx2python("resources/created-in-pages-bulleted-lists.docx")
assert pars.text == (
"\n\nThis is a document for testing docx2python module.\n\n\n\n--\tWhy "
"did the chicken cross the road?\n\n\t--\tJust because\n\n\t--\tDon't "
"know\n\n\t--\tTo get to the other side\n\n--\tWhat's the meaning of life, "
"universe and everything?\n\n\t--\t42\n\n\t--\t0\n\n\t--\t-1\n\n")
def test_paragraphs_only(self) -> None:
"""Run without issue"""
pars = docx2python("resources/created-in-pages-paragraphs-only.docx")
assert pars.text == (
"\n\nThis is a document for testing docx2python module.\n\n\n\nThis "
"document contains paragraphs.\n\n\n\nThis document does not contain any "
"bulleted lists.\n\n")
def test_prints(self) -> None:
"""
Open a docx with ``word/document.xml`` renamed to ``word/blah_blah.xml``
and all references updated. Test that text extracts as expected."""
extraction = docx2python(
os.path.join("resources", "renamed_document_xml.docx"))
assert ('<a href="http://www.shayallenhill.com/">my website</a>'
in extraction.text)
def test_user_unchecked_dropdown1(self) -> None:
"""Get unchecked box glyph and first dd entry"""
extraction = docx2python(os.path.join("resources", "unchecked_drop0.docx"))
assert extraction.text == "\u2610 \n\n\n\n\n\nPiihan B"
def test_user_checked_dropdown0(self) -> None:
"""Get checked-out box glyph and second dd entry"""
extraction = docx2python(os.path.join("resources", "checked_drop1.docx"))
assert extraction.text == "\u2612 \n\n\n\n\n\nPIlihan A"
def test_extraction(self) -> None:
"""Image placeholder inserted into extracted text."""
extraction = docx2python(os.path.join("resources", "has_pict.docx"))
assert "image1.png" in extraction.images
assert "----media/image1.png----" in extraction.text
#!/usr/bin/env python3
# _*_ coding: utf-8 _*_
"""Test full functionality of source_old
:author: Shay Hill
:created: 7/5/2019
"""
import os
import shutil
import re
from docx2python.main import docx2python
from docx2python.iterators import iter_at_depth
OUTPUT = docx2python("resources/example.docx")
HTML_OUTPUT = docx2python("resources/example.docx", html=True)
class TestFormatting:
"""Nested list output string formatting"""
def test_header(self) -> None:
"""Header text in correct location"""
header_text = "".join(iter_at_depth(OUTPUT.header, 4))
assert re.match(r"Header text----media/image\d+\.\w+----$",
header_text)
def test_footer(self) -> None:
"""Footer text in correct location"""
footer_text = "".join(iter_at_depth(OUTPUT.footer, 4))
assert re.match(r"Footer text----media/image\d+\.\w+----$",
#!/usr/bin/env python3
# _*_ coding: utf-8 _*_
"""Test features of DocxContent that weren't tested in test_docx2python.
:author: Shay Hill
:created: 7/6/2019
"""
from docx2python.main import docx2python
INST = docx2python("resources/example.docx")
class TestDocument:
def test_combine_of_header_body_footer(self) -> None:
"""Return all content combined as instance.document """
assert (INST.document == INST.header + INST.body + INST.footer +
INST.footnotes + INST.endnotes)
def test_read_only(self) -> None:
"""Document attribute is read only."""
doc1 = INST.document
doc1 = doc1[:1]
assert doc1 != INST.document
assert (INST.document == INST.header + INST.body + INST.footer +
INST.footnotes + INST.endnotes)
class TestText:
def test_function(self) -> None:
"""Return '\n\n'-delimited paragraphs as instance.text. """
def test_dop_1013a() -> None:
"""Misidentifies ``word/document.xml`` as ``word/word/document.xml``"""
docx2python("resources/example.docx")
# noinspection SpellCheckingInspection
docx2python("resources/240-DOP-1013A Lay Down Tubulars.docx")
def test_prints(self) -> None:
"""Pull the text of the hyperlink"""
extraction = docx2python(os.path.join("resources", "hyperlink.docx"))
assert (
'<a href="http://www.shayallenhill.com/">my website</a>' in extraction.text
)
def test_get_toc_text(self) -> None:
"""Extract header text from table-of-contents header."""
assert docx2python("resources/zen_of_python.docx").text[:66] == (
'Contents\n\n\tBeautiful is better than ugly.'
'\t1</a>\n\n\n\n\n\n\n\nBeautiful i')
def test_run(self) -> None:
"""Run original code and see how it works"""
extraction = docx2python("resources/has_pict.docx")
assert "image1.png" in extraction.images
assert "----media/image1.png----" in extraction.text