Spaces:
Running
Running
Update backend/utils.py
Browse files- backend/utils.py +91 -91
backend/utils.py
CHANGED
@@ -1,92 +1,92 @@
|
|
1 |
-
import aiofiles
|
2 |
-
import urllib
|
3 |
-
import mistune
|
4 |
-
|
5 |
-
async def write_to_file(filename: str, text: str) -> None:
|
6 |
-
"""Asynchronously write text to a file in UTF-8 encoding.
|
7 |
-
|
8 |
-
Args:
|
9 |
-
filename (str): The filename to write to.
|
10 |
-
text (str): The text to write.
|
11 |
-
"""
|
12 |
-
# Ensure text is a string
|
13 |
-
if not isinstance(text, str):
|
14 |
-
text = str(text)
|
15 |
-
|
16 |
-
# Convert text to UTF-8, replacing any problematic characters
|
17 |
-
text_utf8 = text.encode('utf-8', errors='replace').decode('utf-8')
|
18 |
-
|
19 |
-
async with aiofiles.open(filename, "w", encoding='utf-8') as file:
|
20 |
-
await file.write(text_utf8)
|
21 |
-
|
22 |
-
async def write_text_to_md(text: str, filename: str = "") -> str:
|
23 |
-
"""Writes text to a Markdown file and returns the file path.
|
24 |
-
|
25 |
-
Args:
|
26 |
-
text (str): Text to write to the Markdown file.
|
27 |
-
|
28 |
-
Returns:
|
29 |
-
str: The file path of the generated Markdown file.
|
30 |
-
"""
|
31 |
-
file_path = f"outputs/{filename[:60]}.md"
|
32 |
-
await write_to_file(file_path, text)
|
33 |
-
return urllib.parse.quote(file_path)
|
34 |
-
|
35 |
-
async def write_md_to_pdf(text: str, filename: str = "") -> str:
|
36 |
-
"""Converts Markdown text to a PDF file and returns the file path.
|
37 |
-
|
38 |
-
Args:
|
39 |
-
text (str): Markdown text to convert.
|
40 |
-
|
41 |
-
Returns:
|
42 |
-
str: The encoded file path of the generated PDF.
|
43 |
-
"""
|
44 |
-
file_path = f"outputs/{filename[:60]}.pdf"
|
45 |
-
|
46 |
-
try:
|
47 |
-
from md2pdf.core import md2pdf
|
48 |
-
md2pdf(file_path,
|
49 |
-
md_content=text,
|
50 |
-
# md_file_path=f"{file_path}.md",
|
51 |
-
css_file_path="./frontend/pdf_styles.css",
|
52 |
-
base_url=None)
|
53 |
-
print(f"Report written to {file_path}")
|
54 |
-
except Exception as e:
|
55 |
-
print(f"Error in converting Markdown to PDF: {e}")
|
56 |
-
return ""
|
57 |
-
|
58 |
-
encoded_file_path = urllib.parse.quote(file_path)
|
59 |
-
return encoded_file_path
|
60 |
-
|
61 |
-
async def write_md_to_word(text: str, filename: str = "") -> str:
|
62 |
-
"""Converts Markdown text to a DOCX file and returns the file path.
|
63 |
-
|
64 |
-
Args:
|
65 |
-
text (str): Markdown text to convert.
|
66 |
-
|
67 |
-
Returns:
|
68 |
-
str: The encoded file path of the generated DOCX.
|
69 |
-
"""
|
70 |
-
file_path = f"outputs/{filename[:60]}.docx"
|
71 |
-
|
72 |
-
try:
|
73 |
-
from docx import Document
|
74 |
-
from htmldocx import HtmlToDocx
|
75 |
-
# Convert report markdown to HTML
|
76 |
-
html = mistune.html(text)
|
77 |
-
# Create a document object
|
78 |
-
doc = Document()
|
79 |
-
# Convert the html generated from the report to document format
|
80 |
-
HtmlToDocx().add_html_to_document(html, doc)
|
81 |
-
|
82 |
-
# Saving the docx document to file_path
|
83 |
-
doc.save(file_path)
|
84 |
-
|
85 |
-
print(f"Report written to {file_path}")
|
86 |
-
|
87 |
-
encoded_file_path = urllib.parse.quote(file_path)
|
88 |
-
return encoded_file_path
|
89 |
-
|
90 |
-
except Exception as e:
|
91 |
-
print(f"Error in converting Markdown to DOCX: {e}")
|
92 |
return ""
|
|
|
1 |
+
import aiofiles
|
2 |
+
import urllib
|
3 |
+
import mistune
|
4 |
+
|
5 |
+
async def write_to_file(filename: str, text: str) -> None:
|
6 |
+
"""Asynchronously write text to a file in UTF-8 encoding.
|
7 |
+
|
8 |
+
Args:
|
9 |
+
filename (str): The filename to write to.
|
10 |
+
text (str): The text to write.
|
11 |
+
"""
|
12 |
+
# Ensure text is a string
|
13 |
+
if not isinstance(text, str):
|
14 |
+
text = str(text)
|
15 |
+
|
16 |
+
# Convert text to UTF-8, replacing any problematic characters
|
17 |
+
text_utf8 = text.encode('utf-8', errors='replace').decode('utf-8')
|
18 |
+
|
19 |
+
async with aiofiles.open(filename, "w", encoding='utf-8') as file:
|
20 |
+
await file.write(text_utf8)
|
21 |
+
|
22 |
+
async def write_text_to_md(text: str, filename: str = "") -> str:
|
23 |
+
"""Writes text to a Markdown file and returns the file path.
|
24 |
+
|
25 |
+
Args:
|
26 |
+
text (str): Text to write to the Markdown file.
|
27 |
+
|
28 |
+
Returns:
|
29 |
+
str: The file path of the generated Markdown file.
|
30 |
+
"""
|
31 |
+
file_path = f"/tmp/outputs/{filename[:60]}.md"
|
32 |
+
await write_to_file(file_path, text)
|
33 |
+
return urllib.parse.quote(file_path)
|
34 |
+
|
35 |
+
async def write_md_to_pdf(text: str, filename: str = "") -> str:
|
36 |
+
"""Converts Markdown text to a PDF file and returns the file path.
|
37 |
+
|
38 |
+
Args:
|
39 |
+
text (str): Markdown text to convert.
|
40 |
+
|
41 |
+
Returns:
|
42 |
+
str: The encoded file path of the generated PDF.
|
43 |
+
"""
|
44 |
+
file_path = f"outputs/{filename[:60]}.pdf"
|
45 |
+
|
46 |
+
try:
|
47 |
+
from md2pdf.core import md2pdf
|
48 |
+
md2pdf(file_path,
|
49 |
+
md_content=text,
|
50 |
+
# md_file_path=f"{file_path}.md",
|
51 |
+
css_file_path="./frontend/pdf_styles.css",
|
52 |
+
base_url=None)
|
53 |
+
print(f"Report written to {file_path}")
|
54 |
+
except Exception as e:
|
55 |
+
print(f"Error in converting Markdown to PDF: {e}")
|
56 |
+
return ""
|
57 |
+
|
58 |
+
encoded_file_path = urllib.parse.quote(file_path)
|
59 |
+
return encoded_file_path
|
60 |
+
|
61 |
+
async def write_md_to_word(text: str, filename: str = "") -> str:
|
62 |
+
"""Converts Markdown text to a DOCX file and returns the file path.
|
63 |
+
|
64 |
+
Args:
|
65 |
+
text (str): Markdown text to convert.
|
66 |
+
|
67 |
+
Returns:
|
68 |
+
str: The encoded file path of the generated DOCX.
|
69 |
+
"""
|
70 |
+
file_path = f"outputs/{filename[:60]}.docx"
|
71 |
+
|
72 |
+
try:
|
73 |
+
from docx import Document
|
74 |
+
from htmldocx import HtmlToDocx
|
75 |
+
# Convert report markdown to HTML
|
76 |
+
html = mistune.html(text)
|
77 |
+
# Create a document object
|
78 |
+
doc = Document()
|
79 |
+
# Convert the html generated from the report to document format
|
80 |
+
HtmlToDocx().add_html_to_document(html, doc)
|
81 |
+
|
82 |
+
# Saving the docx document to file_path
|
83 |
+
doc.save(file_path)
|
84 |
+
|
85 |
+
print(f"Report written to {file_path}")
|
86 |
+
|
87 |
+
encoded_file_path = urllib.parse.quote(file_path)
|
88 |
+
return encoded_file_path
|
89 |
+
|
90 |
+
except Exception as e:
|
91 |
+
print(f"Error in converting Markdown to DOCX: {e}")
|
92 |
return ""
|