def test_plain_text():
text = "paragraph 1\nparagraph 2\n\n \n \nparagraph 3\n"
doc = process(Content(data=text))
par1 = TextParagraph().append_text_segment(TextSegment("paragraph 1"))
par2 = TextParagraph().append_text_segment(TextSegment("paragraph 2"))
par3 = TextParagraph().append_text_segment(TextSegment("paragraph 3"))
expect_doc = Doc().append_blocks([par1, par2, par3])
assert doc.to_dict() == expect_doc.to_dict()
def test_move_cell():
# Table with 2 rows, 3 cols.
# C1, C3, C5
# C2, C4, C5
table = Table(2, 3) # 2 rows, 3 cols
cell1 = Cell(Rect[int](0, 0, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("C1")))
cell2 = Cell(Rect[int](0, 1, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("C2")))
cell3 = Cell(Rect[int](1, 0, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("C3")))
cell4 = Cell(Rect[int](1, 1, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("C4")))
cell5 = Cell(Rect[int](2, 0, 1, 2)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("C5")))
table.add_cell(cell1).add_cell(cell5).add_cell(cell4).add_cell(cell3)
assert table.cells()[0] == cell1
assert table.cells()[1] == cell5
assert table.cells()[2] == cell4
assert table.cells()[3] == cell3
table.add_cell(cell2)
assert table.cells()[0] == cell1
assert table.cells()[1] == cell3
assert table.cells()[2] == cell5
assert table.cells()[3] == cell2
assert table.cells()[4] == cell4
assert table.ready_to_move()
assert cell1.move(Direction.LEFT) is None
assert cell1.move(Direction.UP) is None
assert cell1.move(Direction.RIGHT) is cell3
assert cell1.move(Direction.DOWN) is cell2
assert cell2.move(Direction.LEFT) is None
assert cell2.move(Direction.UP) is cell1
assert cell2.move(Direction.RIGHT) is cell4
assert cell2.move(Direction.DOWN) is None
assert cell3.move(Direction.LEFT) is cell1
assert cell3.move(Direction.UP) is None
assert cell3.move(Direction.RIGHT) is cell5
assert cell3.move(Direction.DOWN) is cell4
assert cell4.move(Direction.LEFT) is cell2
assert cell4.move(Direction.UP) is cell3
assert cell4.move(Direction.RIGHT) is cell5
assert cell4.move(Direction.DOWN) is None
assert cell5.move(Direction.LEFT) is cell3
assert cell5.move(Direction.UP) is None
assert cell5.move(Direction.RIGHT) is None
assert cell5.move(Direction.DOWN) is None
def test_merge_segments_with_link():
# This is a link: <a href="http://www.example.com"> link </a>.
par = TextParagraph() \
.append_text_segment(TextSegment("This is a link: ")) \
.append_text_segment(TextSegment("example", "http://www.example.com")) \
.append_text_segment(TextSegment("."))
assert len(par.segments()) == 3
assert par.segments()[0].text() == "This is a link: "
assert par.segments()[1].text() == "example"
assert par.segments()[1].link() == "http://www.example.com"
assert par.segments()[2].text() == "."
def test_plain_text_from_file():
doc = process(
Content(source=ContentSource.FILE,
path="dolphin_doc_lib/testdata/plain_text.txt"))
par1 = TextParagraph().append_text_segment(TextSegment("paragraph 1"))
par2 = TextParagraph().append_text_segment(TextSegment("paragraph 2"))
par3 = TextParagraph().append_text_segment(TextSegment("paragraph 3"))
par4 = TextParagraph().append_text_segment(TextSegment("paragraph 4"))
expect_doc = Doc().append_blocks([par1, par2, par3, par4])
assert doc.to_dict() == expect_doc.to_dict()
def _process_string_node(node) -> BlocksInfo:
# strip string to mimic browser behavior, not 100% accurate
content: str = node.strip()
if not content:
return BlocksInfo()
par = TextParagraph().append_text_segment(TextSegment(content))
return BlocksInfo(blocks=[par])
def _process_text(text: str) -> Doc:
"Create Dolphin Doc from plain text"
doc = Doc()
for line in text.splitlines():
line = line.strip()
if line:
par = TextParagraph().append_text_segment(TextSegment(line))
doc.append_block(par)
return doc
def test_ignore_tags():
html = """a<style>b</style><script>c</script><noscript>d</noscript>e"""
doc = process_html(html)
expect_doc = Doc().append_blocks([
TextParagraph().append_text_segment(TextSegment("ae")),
])
assert doc.to_dict() == expect_doc.to_dict()
def test_standard_table():
html = """
<table>
<thead>
<tr>
<th>Month</th>
<th>Savings</th>
</tr>
</thead>
<tbody>
<tr>
<td>January</td>
<td>$100</td>
</tr>
<tr>
<td>February</td>
<td>$80</td>
</tr>
</tbody>
<tfoot>
<tr>
<td>Sum</td>
<td>$180</td>
</tr>
</tfoot>
</table>"""
doc = process_html(html)
expect_doc = Doc().append_block(
Table(4, 2, [
Cell(Rect[int](0, 0, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("Month"))),
Cell(Rect[int](1, 0, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("Savings"))),
Cell(Rect[int](0, 1, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("January"))),
Cell(Rect[int](1, 1, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("$100"))),
Cell(Rect[int](0, 2, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("February"))),
Cell(Rect[int](1, 2, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("$80"))),
Cell(Rect[int](0, 3, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("Sum"))),
Cell(Rect[int](1, 3, 1, 1)).append_paragraph(
TextParagraph().append_text_segment(TextSegment("$180"))),
]))
assert doc.to_dict() == expect_doc.to_dict()
def test_line_break_tags():
html = """a<p>b<br>c<h1>d<h2>e<h3>f<h4>g<h5>h<h6>i<pre>j<address>k<blockquote>l
<dl>m<div>n<fieldset>o<form>p<hr>q<ol>r<ul>s<li>t
"""
doc = process_html(html)
expect_doc = Doc().append_blocks([
TextParagraph().append_text_segment(TextSegment("a")),
TextParagraph().append_text_segment(TextSegment("b")),
TextParagraph().append_text_segment(TextSegment("c")),
TextParagraph().append_text_segment(TextSegment("d")),
TextParagraph().append_text_segment(TextSegment("e")),
TextParagraph().append_text_segment(TextSegment("f")),
TextParagraph().append_text_segment(TextSegment("g")),
TextParagraph().append_text_segment(TextSegment("h")),
TextParagraph().append_text_segment(TextSegment("i")),
TextParagraph().append_text_segment(TextSegment("j")),
TextParagraph().append_text_segment(TextSegment("k")),
TextParagraph().append_text_segment(TextSegment("l")),
TextParagraph().append_text_segment(TextSegment("m")),
TextParagraph().append_text_segment(TextSegment("n")),
TextParagraph().append_text_segment(TextSegment("o")),
TextParagraph().append_text_segment(TextSegment("p")),
TextParagraph().append_text_segment(TextSegment("q")),
TextParagraph().append_text_segment(TextSegment("r")),
TextParagraph().append_text_segment(TextSegment("s")),
TextParagraph().append_text_segment(TextSegment("t")),
])
assert doc.to_dict() == expect_doc.to_dict()
def test_merge_segments():
par = TextParagraph() \
.append_text_segment(TextSegment("Hello ")) \
.append_text_segment(TextSegment("World!"))
assert len(par.segments()) == 1
assert par.segments()[0].text() == "Hello World!"