在borb中高效使用西里尔字母：自定义TrueType字体与低层PDF操作

from pathlib import Path
from decimal import Decimal
from borb.pdf.canvas.layout.text.paragraph import Paragraph
from borb.pdf.canvas.layout.shape.rectangle import Rectangle
from borb.pdf.canvas.font.true_type_font import TrueTypeFont
from borb.pdf.canvas.font.font import Font
from borb.pdf.page.page import Page

# 假设 symb_arr 是一个包含 Symbol 对象的数组
# class Symbol:
#     def __init__(self, s, x, y, w, h, f):
#         self.sym = s  # character
#         self.x_coord = x
#         self.y_coord = y
#         self.width = w
#         self.height = h
#         self.font_size = f

# 1. 加载自定义TrueType字体
font_path: Path = Path(__file__).parent / "TimesNewRomanRegular.ttf"
custom_font: Font = TrueTypeFont.true_type_font_from_file(font_path)

# 假设 page 是一个 borb.pdf.page.page.Page 对象
# 假设 symb_arr 是 Symbol 对象的列表
# 假设 font_size 已经定义

for i, s in enumerate(symb_arr):
    r: Rectangle = Rectangle(
        Decimal(s.x_coord),
        Decimal(s.y_coord),
        Decimal(s.width + 2),
        Decimal(s.height + 2),
    )
    Paragraph(s.sym, font_size=Decimal(s.font_size), font=custom_font).paint(page, r)

import zlib
from decimal import Decimal
from borb.pdf.canvas.layout.text.paragraph import Paragraph
from borb.pdf.canvas.layout.shape.rectangle import Rectangle
from borb.pdf.canvas.font.true_type_font import TrueTypeFont
from borb.pdf.canvas.font.font import Font
from borb.pdf.page.page import Page
from borb.pdf.document.document import Document
from borb.pdf.canvas.geometry.rectangle import Rectangle as BorbRectangle
from borb.pdf.primitive.name import Name
from borb.pdf.primitive.stream import Stream
from borb.pdf.primitive.dictionary import Dictionary
from borb.pdf.primitive.string import String

# 假设 page 是一个 borb.pdf.page.page.Page 对象
# 假设 symb_arr 是 Symbol 对象的列表
# 假设 doc 是 borb.pdf.document.document.Document 对象

# 1. 创建内容流
content_stream = Stream()
content = b""""""
for s in symb_arr:
    # 注意：这里的 (%b) Tj 格式化字符串和编码是问题的关键
    # 后面会详细讨论如何正确处理西里尔字母编码
    content += b"""
        q
        BT
        /F1 %b Tf
        %b %b Td
        (%b) Tj
        ET
        Q
    """ % (bytes(format(s.font_size, '.4f'), 'utf-8'),
           bytes(format(s.x_coord, '.4f'), 'utf-8'),
           bytes(format(s.y_coord, '.4f'), 'utf-8'),
           bytes(str(s.sym), 'utf-8')) # 原始问题中的编码方式

content_stream[Name("DecodedBytes")] = content
content_stream[Name("Bytes")] = zlib.compress(content_stream["DecodedBytes"], 9)
content_stream[Name("Filter")] = Name("FlateDecode")
content_stream[Name("Length")] = Decimal(len(content_stream["Bytes"]))

# 2. 设置页面内容
page[Name("Contents")] = content_stream

# 3. 设置字体资源 (原始问题中的尝试)
page[Name("Resources")] = Dictionary()
# 原始问题尝试从现有页面复制字体资源，但这不适用于自定义字体
# page[Name("Resources")] = doc.get_page