Skip to content

pdf: Merge loops for single byte text chunk output #30567

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

Merged
QuLogic merged 1 commit into from
Sep 19, 2025
Merged

pdf: Merge loops for single byte text chunk output #30567

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
pdf: Merge loops for single byte text chunk output 
Currently, we split text into single byte chunks and multi-byte glyphs,
then iterate through single byte chunks for output and multi-byte glyphs
for output.

Instead, output the single byte chunks as we finish them, then do the
multi-byte glyphs at the end.
  • Loading branch information
@QuLogic
QuLogic committed Sep 17, 2025
commit 3e97c0d649550d805c25c71bf49f5f456fec284f
65 changes: 33 additions & 32 deletions lib/matplotlib/backends/backend_pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2376,47 +2376,48 @@ def draw_text(self, gc, x, y, s, prop, angle, ismath=False, mtext=None):
# the regular text show command (TJ) with appropriate kerning between
# chunks, whereas multibyte characters use the XObject command (Do).
else:
# List of (ft_object, start_x, [prev_kern, char, char, ...]),
# w/o zero kerns.
singlebyte_chunks = []
# List of (ft_object, start_x, glyph_index).
multibyte_glyphs = []
prev_was_multibyte = True
prev_font = font
for item in _text_helpers.layout(s, font, kern_mode=Kerning.UNFITTED):
if _font_supports_glyph(fonttype, ord(item.char)):
if prev_was_multibyte or item.ft_object != prev_font:
singlebyte_chunks.append((item.ft_object, item.x, []))
prev_font = item.ft_object
if item.prev_kern:
singlebyte_chunks[-1][2].append(item.prev_kern)
singlebyte_chunks[-1][2].append(item.char)
prev_was_multibyte = False
else:
multibyte_glyphs.append((item.ft_object, item.x, item.glyph_index))
prev_was_multibyte = True
def output_singlebyte_chunk(kerns_or_chars):
self.file.output(
# See pdf spec "Text space details" for the 1000/fontsize
# (aka. 1000/T_fs) factor.
[(-1000 * next(group) / fontsize) if tp == float # a kern
else self.encode_string("".join(group), fonttype)
for tp, group in itertools.groupby(kerns_or_chars, type)],
Op.showkern)
# Do the rotation and global translation as a single matrix
# concatenation up front
self.file.output(Op.gsave)
a = math.radians(angle)
self.file.output(math.cos(a), math.sin(a),
-math.sin(a), math.cos(a),
x, y, Op.concat_matrix)
# List of [prev_kern, char, char, ...] w/o zero kerns.
singlebyte_chunk = []
# List of (ft_object, start_x, glyph_index).
multibyte_glyphs = []
prev_font = None
prev_start_x = 0
# Emit all the 1-byte characters in a BT/ET group.
self.file.output(Op.begin_text)
prev_start_x = 0
for ft_object, start_x, kerns_or_chars in singlebyte_chunks:
ft_name = self.file.fontName(ft_object.fname)
self.file.output(ft_name, fontsize, Op.selectfont)
self._setup_textpos(start_x, 0, 0, prev_start_x, 0, 0)
self.file.output(
# See pdf spec "Text space details" for the 1000/fontsize
# (aka. 1000/T_fs) factor.
[-1000 * next(group) / fontsize if tp == float # a kern
else self.encode_string("".join(group), fonttype)
for tp, group in itertools.groupby(kerns_or_chars, type)],
Op.showkern)
prev_start_x = start_x
for item in _text_helpers.layout(s, font, kern_mode=Kerning.UNFITTED):
if _font_supports_glyph(fonttype, ord(item.char)):
if item.ft_object != prev_font:
if singlebyte_chunk:
output_singlebyte_chunk(singlebyte_chunk)
ft_name = self.file.fontName(item.ft_object.fname)
self.file.output(ft_name, fontsize, Op.selectfont)
self._setup_textpos(item.x, 0, 0, prev_start_x, 0, 0)
singlebyte_chunk = []
prev_font = item.ft_object
prev_start_x = item.x
if item.prev_kern:
singlebyte_chunk.append(item.prev_kern)
singlebyte_chunk.append(item.char)
else:
prev_font = None
multibyte_glyphs.append((item.ft_object, item.x, item.glyph_index))
if singlebyte_chunk:
output_singlebyte_chunk(singlebyte_chunk)
self.file.output(Op.end_text)
# Then emit all the multibyte characters, one at a time.
for ft_object, start_x, glyph_index in multibyte_glyphs:
Expand Down
Loading