Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixing issue #1236 #1257

Closed
wants to merge 3 commits into from
Closed

Fixing issue #1236 #1257

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9f56f08
Fixing issue #1236
smilerightnow Sep 4, 2024
50058c6
formatting with black
smilerightnow Sep 5, 2024
4094287
update
smilerightnow Sep 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/TextStyling.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -194,7 +194,7 @@ pdf = FPDF()
pdf.add_page()
pdf.set_font("Times", size=50)
pdf.cell(text="**Lorem** __Ipsum__ --dolor--", markdown=True, new_x='LEFT', new_y='NEXT')
pdf.cell(text="\\**Lorem\\** \\\\__Ipsum\\\\__ --dolor--", markdown=True)
pdf.cell(text="\\**Lorem\\** __\\Ipsum\\ __ --dolor--", markdown=True)
pdf.output("markdown-styled.pdf")
```

Expand Down
44 changes: 22 additions & 22 deletions fpdf/fpdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3456,9 +3456,20 @@ def frag():
font_glyphs = self.current_font.cmap
else:
font_glyphs = []
num_escape_chars = 0

while text:
tlt = text[:3] ## get triples to check for escape character
if self.MARKDOWN_ESCAPE_CHARACTER == tlt[0] and tlt[1:] in [
"**",
"__",
"--",
]:
text = text[1:] ## remove the escape character
for _ in range(2):
txt_frag.append(text[0])
text = text[1:]
yield frag()
continue
is_marker = text[:2] in (
self.MARKDOWN_BOLD_MARKER,
self.MARKDOWN_ITALICS_MARKER,
Expand All @@ -3482,27 +3493,16 @@ def frag():
and (not txt_frag or txt_frag[-1] != half_marker)
and (len(text) < 3 or text[2] != half_marker)
):
txt_frag = (
txt_frag[: -((num_escape_chars + 1) // 2)]
if num_escape_chars > 0
else txt_frag
)
if num_escape_chars % 2 == 0:
if txt_frag:
yield frag()
if text[:2] == self.MARKDOWN_BOLD_MARKER:
in_bold = not in_bold
if text[:2] == self.MARKDOWN_ITALICS_MARKER:
in_italics = not in_italics
if text[:2] == self.MARKDOWN_UNDERLINE_MARKER:
in_underline = not in_underline
text = text[2:]
continue
num_escape_chars = (
num_escape_chars + 1
if text[0] == self.MARKDOWN_ESCAPE_CHARACTER
else 0
)
if txt_frag:
yield frag()
if text[:2] == self.MARKDOWN_BOLD_MARKER:
in_bold = not in_bold
if text[:2] == self.MARKDOWN_ITALICS_MARKER:
in_italics = not in_italics
if text[:2] == self.MARKDOWN_UNDERLINE_MARKER:
in_underline = not in_underline
text = text[2:]
continue
is_link = self.MARKDOWN_LINK_REGEX.match(text)
if is_link:
link_text, link_dest, text = is_link.groups()
Expand Down
Binary file modified test/text/cell_markdown_bold_italic_escaped.pdf
View file
Open in desktop
Binary file not shown.
Binary file modified test/text/cell_markdown_escaped.pdf
View file
Open in desktop
Binary file not shown.
Binary file modified test/text/cell_markdown_with_ttf_fonts_escaped.pdf
View file
Open in desktop
Binary file not shown.
Binary file modified test/text/multi_cell_markdown_escaped.pdf
View file
Open in desktop
Binary file not shown.
Binary file modified test/text/multi_cell_markdown_with_ttf_fonts_escaped.pdf
View file
Open in desktop
Binary file not shown.
2 changes: 2 additions & 0 deletions test/text/test_cell.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,6 +178,8 @@ def test_cell_markdown_escaped(tmp_path):
pdf.add_page()
pdf.set_font("Times", size=40)
pdf.cell(text="**Lo\\rem** \\__Ipsum\\__ \\\\--dolor\\\\--", markdown=True)
pdf.write(text="\n")
pdf.cell(text="\\****BOLD**\\**", markdown=True)
assert_pdf_equal(pdf, HERE / "cell_markdown_escaped.pdf", tmp_path)


Expand Down
108 changes: 83 additions & 25 deletions test/text/test_markdown_parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,46 @@
GSTATE_BI["font_style"] = "BI"


def merge_fragments(fragments):
"""
Helper function for testing the escaping chracters

Will merge fragments that have different characters but same fragment.graphics_state
and same fragment.k and same fragment.link.

Example Input:

(
Fragment(characters=['a'], graphics_state={000}, k=1, link=None),
Fragment(characters=['b'], graphics_state={000}, k=1, link=None)
)

Example Output:
(Fragment(characters=['a', 'b'], graphics_state={000}, k=1, link=None))

"""
if not fragments:
return []

merged_fragments = []
current_fragment = fragments[0]

for fragment in fragments[1:]:
if (
fragment.graphics_state == current_fragment.graphics_state
and fragment.k == current_fragment.k
and fragment.link == current_fragment.link
):
current_fragment.characters.extend(fragment.characters)
else:
merged_fragments.append(current_fragment)
current_fragment = fragment

merged_fragments.append(current_fragment)

return tuple(merged_fragments)


def test_markdown_parse_simple_ok():
frags = tuple(FPDF()._parse_chars("**bold**, __italics__ and --underlined--", True))
expected = (
Expand All @@ -27,18 +67,22 @@ def test_markdown_parse_simple_ok():


def test_markdown_parse_simple_ok_escaped():
frags = tuple(
FPDF()._parse_chars(
"\\**bold\\**, \\__italics\\__ and \\--underlined\\-- escaped", True
frags = merge_fragments(
tuple(
FPDF()._parse_chars(
"\\**bold\\**, \\__italics\\__ and \\--underlined\\-- escaped", True
)
)
)
expected = (
Fragment("**bold**, __italics__ and --underlined-- escaped", GSTATE, k=PDF.k),
)
assert frags == expected
frags = tuple(
FPDF()._parse_chars(
r"raw \**bold\**, \__italics\__ and \--underlined\-- escaped", True
frags = merge_fragments(
tuple(
FPDF()._parse_chars(
r"raw \**bold\**, \__italics\__ and \--underlined\-- escaped", True
)
)
)
expected = (
Expand All @@ -47,10 +91,14 @@ def test_markdown_parse_simple_ok_escaped():
),
)
assert frags == expected
frags = tuple(FPDF()._parse_chars("escape *\\*between marker*\\*", True))
frags = merge_fragments(
tuple(FPDF()._parse_chars("escape *\\*between marker*\\*", True))
)
expected = (Fragment("escape *\\*between marker*\\*", GSTATE, k=PDF.k),)
assert frags == expected
frags = tuple(FPDF()._parse_chars("escape **\\after marker**\\", True))
frags = merge_fragments(
tuple(FPDF()._parse_chars("escape **\\after marker**\\", True))
)
expected = (
Fragment("escape ", GSTATE, k=PDF.k),
Fragment("\\after marker", GSTATE_B, k=PDF.k),
Expand All @@ -59,26 +107,28 @@ def test_markdown_parse_simple_ok_escaped():


def test_markdown_unrelated_escape():
frags = tuple(FPDF()._parse_chars("unrelated \\ escape \\**bold\\**", True))
frags = merge_fragments(
tuple(FPDF()._parse_chars("unrelated \\ escape \\**bold\\**", True))
)
expected = (Fragment("unrelated \\ escape **bold**", GSTATE, k=PDF.k),)
assert frags == expected
frags = tuple(
FPDF()._parse_chars("unrelated \\\\ double escape \\**bold\\**", True)
frags = merge_fragments(
tuple(FPDF()._parse_chars("unrelated \\\\ double escape \\**bold\\**", True))
)
expected = (Fragment("unrelated \\\\ double escape **bold**", GSTATE, k=PDF.k),)
assert frags == expected


def test_markdown_parse_multiple_escape():
frags = tuple(FPDF()._parse_chars("\\\\**bold\\\\** double escaped", True))
expected = (
Fragment("\\", GSTATE, k=PDF.k),
Fragment("bold\\", GSTATE_B, k=PDF.k),
Fragment(" double escaped", GSTATE, k=PDF.k),
frags = merge_fragments(
tuple(FPDF()._parse_chars("\\\\**bold\\\\** double escaped", True))
)
expected = (Fragment("\\**bold\\** double escaped", GSTATE, k=PDF.k),)
assert frags == expected
frags = tuple(FPDF()._parse_chars("\\\\\\**triple bold\\\\\\** escaped", True))
expected = (Fragment("\\**triple bold\\** escaped", GSTATE, k=PDF.k),)
frags = merge_fragments(
tuple(FPDF()._parse_chars("\\\\\\**triple bold\\\\\\** escaped", True))
)
expected = (Fragment("\\\\**triple bold\\\\** escaped", GSTATE, k=PDF.k),)
assert frags == expected


Expand All @@ -92,7 +142,9 @@ def test_markdown_parse_overlapping():


def test_markdown_parse_overlapping_escaped():
frags = tuple(FPDF()._parse_chars("**bold \\__italics\\__**", True))
frags = merge_fragments(
tuple(FPDF()._parse_chars("**bold \\__italics\\__**", True))
)
expected = (Fragment("bold __italics__", GSTATE_B, k=PDF.k),)
assert frags == expected

Expand All @@ -108,7 +160,9 @@ def test_markdown_parse_crossing_markers():


def test_markdown_parse_crossing_markers_escaped():
frags = tuple(FPDF()._parse_chars("**bold __and\\** italics__", True))
frags = merge_fragments(
tuple(FPDF()._parse_chars("**bold __and\\** italics__", True))
)
expected = (
Fragment("bold ", GSTATE_B, k=PDF.k),
Fragment("and** italics", GSTATE_BI, k=PDF.k),
Expand All @@ -126,7 +180,7 @@ def test_markdown_parse_unterminated():


def test_markdown_parse_unterminated_escaped():
frags = tuple(FPDF()._parse_chars("**bold\\** __italics__", True))
frags = merge_fragments(tuple(FPDF()._parse_chars("**bold\\** __italics__", True)))
expected = (
Fragment("bold** ", GSTATE_B, k=PDF.k),
Fragment("italics", GSTATE_BI, k=PDF.k),
Expand All @@ -153,11 +207,15 @@ def test_markdown_parse_line_of_markers():


def test_markdown_parse_line_of_markers_escaped():
frags = tuple(FPDF()._parse_chars("\\****BOLD**", True))
expected = (Fragment("\\****BOLD", GSTATE, k=PDF.k),)
frags = merge_fragments(tuple(FPDF()._parse_chars("\\****BOLD**\\**", True)))
expected = (
Fragment("**", GSTATE, k=PDF.k),
Fragment("BOLD", GSTATE_B, k=PDF.k),
Fragment("**", GSTATE, k=PDF.k),
)
assert frags == expected
frags = tuple(FPDF()._parse_chars("*\\***BOLD**", True))
expected = (Fragment("*\\***BOLD", GSTATE, k=PDF.k),)
frags = merge_fragments(tuple(FPDF()._parse_chars("*\\***BOLD**", True)))
expected = (Fragment("****BOLD", GSTATE, k=PDF.k),)
assert frags == expected


Expand Down
Loading