Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,781 Bytes
2cb5324 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
punctuation_dict = {
"οΌ": ",",
"γ": ".",
}
translation_table = str.maketrans(punctuation_dict)
stop_str = "<|im_end|>"
def svg_to_html(svg_content, output_filename):
html_content = f"""
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>SVG Embedded in HTML</title>
</head>
<body>
<svg width="2100" height="15000" xmlns="http://www.w3.org/2000/svg">
{svg_content}
</svg>
</body>
</html>
"""
with open(output_filename, "w") as file:
file.write(html_content)
def render_ocr_text(text, result_path, format_text=False):
if text.endswith(stop_str):
text = text[: -len(stop_str)]
text = text.strip()
if "**kern" in text:
import verovio
tk = verovio.toolkit()
tk.loadData(text)
tk.setOptions(
{
"pageWidth": 2100,
"footer": "none",
"barLineWidth": 0.5,
"beamMaxSlope": 15,
"staffLineWidth": 0.2,
"spacingStaff": 6,
}
)
tk.getPageCount()
svg = tk.renderToSVG()
svg = svg.replace('overflow="inherit"', 'overflow="visible"')
svg_to_html(svg, result_path)
if format_text and "**kern" not in text:
if "\\begin{tikzpicture}" not in text:
html_path = "./render_tools/" + "/content-mmd-to-html.html"
right_num = text.count("\\right")
left_num = text.count("\left")
if right_num != left_num:
text = (
text.replace("\left(", "(")
.replace("\\right)", ")")
.replace("\left[", "[")
.replace("\\right]", "]")
.replace("\left{", "{")
.replace("\\right}", "}")
.replace("\left|", "|")
.replace("\\right|", "|")
.replace("\left.", ".")
.replace("\\right.", ".")
)
text = text.replace('"', "``").replace("$", "")
outputs_list = text.split("\n")
gt = ""
for out in outputs_list:
gt += '"' + out.replace("\\", "\\\\") + r"\n" + '"' + "+" + "\n"
gt = gt[:-2]
with open(html_path, "r") as web_f:
lines = web_f.read()
lines = lines.split("const text =")
new_web = lines[0] + "const text =" + gt + lines[1]
else:
html_path = "./render_tools/" + "/tikz.html"
text = text.translate(translation_table)
outputs_list = text.split("\n")
gt = ""
for out in outputs_list:
if out:
if (
"\\begin{tikzpicture}" not in out
and "\\end{tikzpicture}" not in out
):
while out[-1] == " ":
out = out[:-1]
if out is None:
break
if out:
if out[-1] != ";":
gt += out[:-1] + ";\n"
else:
gt += out + "\n"
else:
gt += out + "\n"
with open(html_path, "r") as web_f:
lines = web_f.read()
lines = lines.split("const text =")
new_web = lines[0] + gt + lines[1]
with open(result_path, "w") as web_f_new:
web_f_new.write(new_web)
|